Tokenizer: bert-base-cased Model: bert-base-cased
	Train size: 80 Test size: 20


		-------------RUN 1-----------
Test files: ['/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/279.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/82.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/83.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/95.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/94.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/29.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/220.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/66.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/10.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/11.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/8.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/12.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/5.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/74.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/78.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/76.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/77.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/73.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/75.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/21.xml']
			------------EPOCH 1---------------
Loss:  tensor(2579.9807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2888.8286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1775.9865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2694.9189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3371.1777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3202.6111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3666.5815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1436.1865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1077.3621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(851.4411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1917.8494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2116.6201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2652.4033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2838.4146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1946.4954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1952.1759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1342.1357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1715.0310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1940.2188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1587.0288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3440.6665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1864.7000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1298.3142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1652.3347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1854.5210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1809.9176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1955.1978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2040.9634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2421.6594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1889.3308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2269.9365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1400.3019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2939.4888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2595.2285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2699.3481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4282.1328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2578.7437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1654.4600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2692.4438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2414.1709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2526.8601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1235.4817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(998.7057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(786.1892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1562.0701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1370.9302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1129.4113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(908.6618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2078.1638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.8791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2264.1631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1749.3113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2015.4031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1781.6044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1205.7964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1897.9746, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 324}, 'P': {'precision': 0.012376237623762377, 'recall': 0.015151515151515152, 'f1': 0.013623978201634877, 'number': 330}, 'overall_precision': 0.007473841554559043, 'overall_recall': 0.00764525993883792, 'overall_f1': 0.007558578987150415, 'overall_accuracy': 0.4200224971878515}
			------------EPOCH 2---------------
Loss:  tensor(1999.8708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2128.9233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1157.2350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1757.0587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2664.5298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2392.3665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2279.1235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1107.6757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(878.5907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(662.5984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1563.5050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1785.0800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2323.1765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2465.5347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1548.7368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1565.1636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1003.6570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1255.3628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1486.0680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1274.0579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2743.5532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1457.4739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1097.0803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1312.9747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1528.7363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1608.0931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1680.2996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1743.6483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2011.9099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1587.9456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2104.9648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1054.7805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2346.3813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2252.2664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2199.1553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3728.6667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2297.9419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1301.0360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2383.3198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1995.0154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2117.0481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1104.7439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(869.5753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.2408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1274.9402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.0768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(943.1918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.4498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1646.1382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(813.0663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1996.7798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1420.8271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1754.9827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1526.3511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.7715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1619.1709, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.08914728682170543, 'recall': 0.1419753086419753, 'f1': 0.10952380952380952, 'number': 324}, 'P': {'precision': 0.07807807807807808, 'recall': 0.07878787878787878, 'f1': 0.0784313725490196, 'number': 330}, 'overall_precision': 0.08480565371024736, 'overall_recall': 0.11009174311926606, 'overall_f1': 0.09580838323353295, 'overall_accuracy': 0.5333520809898763}
			------------EPOCH 3---------------
Loss:  tensor(1464.3594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1741.1448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1015.7736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1468.4874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2297.7302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2074.9409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1731.0632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(957.8363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(745.1193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.2239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1435.7307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1504.7849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2012.1387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2076.2324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1219.6592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1262.9779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.4333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1019.4211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1335.0156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1168.5652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2375.8218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1128.8977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(957.4104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1089.8364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1343.8882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1463.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1432.7727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1482.6013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1642.4177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1323.5529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1793.1761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(834.4686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1944.6254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1940.7920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1847.5625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3219.0645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1951.1455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1048.8654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1966.5532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1602.7893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1826.0314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(933.2258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(741.0637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.7292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1047.9602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(890.0588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(676.3904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.0046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1202.1531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.3849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1544.5490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1096.2513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1478.7761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1032.0342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.4846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.4927, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15876288659793814, 'recall': 0.23765432098765432, 'f1': 0.1903584672435105, 'number': 324}, 'P': {'precision': 0.10920770877944326, 'recall': 0.15454545454545454, 'f1': 0.12797992471769135, 'number': 330}, 'overall_precision': 0.13445378151260504, 'overall_recall': 0.19571865443425077, 'overall_f1': 0.15940224159402241, 'overall_accuracy': 0.521822272215973}
			------------EPOCH 4---------------
Loss:  tensor(1213.9529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1426.7408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.4781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1100.1467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1895.3812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1756.6111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1269.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(807.7028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.4499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.5247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1193.8965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1258.7570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1695.4763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1685.8949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(912.7826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(962.4557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.8772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.3945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.6935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(899.8379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1804.4631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(668.9617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.1089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(847.9393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1045.9070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1263.0249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1166.2393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1190.0676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1226.5854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1039.2817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1362.4702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.8644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1452.0959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1505.0524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1498.4067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2493.5117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1473.9060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(787.6345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1621.5305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1278.8438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1527.7285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.5465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(603.9134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.4938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(791.3657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.1912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.7436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(830.4873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.1419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1134.4730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(832.0737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1122.1184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(565.2297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(560.0711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.4323, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1946564885496183, 'recall': 0.3148148148148148, 'f1': 0.24056603773584906, 'number': 324}, 'P': {'precision': 0.22739018087855298, 'recall': 0.26666666666666666, 'f1': 0.24546722454672246, 'number': 330}, 'overall_precision': 0.20856201975850713, 'overall_recall': 0.290519877675841, 'overall_f1': 0.24281150159744408, 'overall_accuracy': 0.5771091113610799}
			------------EPOCH 5---------------
Loss:  tensor(1070.3164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1191.4116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.9744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(894.8544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1519.4988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1503.9688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(932.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.8208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.4691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.4032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(876.4595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(958.8945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1381.6826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1473.5042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.4422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(793.2263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.0526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.7227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.3800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.9012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1511.0322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.9289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.0305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.9315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(838.1348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(956.0361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.8276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(909.8289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(966.4655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(900.3050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1037.3724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.7214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1095.8878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1190.1377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1295.9979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2463.8120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1109.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.3792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1245.8892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(871.4341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1338.8901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.5049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.9862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.4680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.9143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.6324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.6895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.3475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(800.5853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.5772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1062.3639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(720.8801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(917.7313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.7967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.2276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.6430, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18867924528301888, 'recall': 0.15432098765432098, 'f1': 0.16977928692699493, 'number': 324}, 'P': {'precision': 0.1701534170153417, 'recall': 0.3696969696969697, 'f1': 0.2330468003820439, 'number': 330}, 'overall_precision': 0.17515274949083504, 'overall_recall': 0.26299694189602446, 'overall_f1': 0.21026894865525672, 'overall_accuracy': 0.5642857142857143}
			------------EPOCH 6---------------
Loss:  tensor(900.8802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(993.7062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.1935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(708.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1433.8353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1454.7119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.7435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(683.6226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.3738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.3691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.7152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(932.8859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1257.8035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1417.1876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(668.5513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.6602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.9585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.2729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(666.4557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(573.1307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1398.7810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.7131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.0346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.0175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.4185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.5388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.7305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.0632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(976.1357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(804.7036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(821.0945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.8368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(918.5188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(933.4401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.6978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1587.9066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(783.0797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.6473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(988.8210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(648.0676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1112.8015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(503.5795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.2824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.6455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(504.1085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.0630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.4007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.4310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.3749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.1165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.7436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.3371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(822.0345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.2137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.2818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.4479, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15217391304347827, 'recall': 0.2808641975308642, 'f1': 0.19739696312364427, 'number': 324}, 'P': {'precision': 0.06896551724137931, 'recall': 0.07878787878787878, 'f1': 0.07355021216407356, 'number': 330}, 'overall_precision': 0.12, 'overall_recall': 0.17889908256880735, 'overall_f1': 0.14364640883977897, 'overall_accuracy': 0.5299775028121485}
			------------EPOCH 7---------------
Loss:  tensor(778.8528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.2134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.0291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1032.2375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1276.3871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1186.3110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.5620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(404.4313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.8138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.7674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.0372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.3419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(931.6619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(983.6473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.0471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.5223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.7368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.3030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.3535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.7553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2030.9269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.1135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.1516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.9907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.2306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(786.6262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(735.8336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.6691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(787.9361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.6061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.7756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.5503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(781.9379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(758.9796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1023.8840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1509.1797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(641.5803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.9835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.7495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.5454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(984.9947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.2568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.0219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(497.9009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.6885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.4929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.6946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.4027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.2606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(845.9391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.1274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.5817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.7203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.4438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.0556, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20866141732283464, 'recall': 0.3271604938271605, 'f1': 0.25480769230769235, 'number': 324}, 'P': {'precision': 0.1023391812865497, 'recall': 0.10606060606060606, 'f1': 0.10416666666666667, 'number': 330}, 'overall_precision': 0.16588235294117648, 'overall_recall': 0.21559633027522937, 'overall_f1': 0.1875, 'overall_accuracy': 0.5726096737907762}
			------------EPOCH 8---------------
Loss:  tensor(501.6470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(681.5687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.3542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(576.8423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1024.4075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(901.2122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.7657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.4056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.9003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.6825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.0771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.8959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.6112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.3610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.1085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.3625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.3676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.9533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.7774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.7513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.6917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.0755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.8015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.3195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(639.4233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(618.9235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(572.3816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.1146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.5800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(838.4515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.7883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(699.8882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.5126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(956.8309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1823.6387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.0955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.2910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.6601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.5972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.0447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.7607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.5944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.5138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.9351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.4911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.6730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.1794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.8412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(577.2800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.5525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.9872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.1108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.7482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.8574, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.09971509971509972, 'recall': 0.10802469135802469, 'f1': 0.1037037037037037, 'number': 324}, 'P': {'precision': 0.04924242424242424, 'recall': 0.03939393939393939, 'f1': 0.04377104377104377, 'number': 330}, 'overall_precision': 0.07804878048780488, 'overall_recall': 0.07339449541284404, 'overall_f1': 0.07565011820330969, 'overall_accuracy': 0.4487626546681665}
			------------EPOCH 9---------------
Loss:  tensor(547.7777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(940.6824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(576.1555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.1251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1451.1655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.0341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1067.1182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.9808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.4291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.3209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.8374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.3318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.7827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.3329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.0287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.3327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.8975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.4073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.4967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.3777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1063.6697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.8228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.7070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.8116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.0381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(580.6768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(646.3876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.1459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(719.9250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.0878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.2526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.9029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(726.7080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.6954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(906.2295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1689.8315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(737.0474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.3397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1235.2086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(624.1935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1125.4045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(534.1273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.5604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.5482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.0665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.7679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.8046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.4260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.7723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.5996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.1506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.2290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.2390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.2013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.6802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.0990, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11945392491467577, 'recall': 0.21604938271604937, 'f1': 0.15384615384615385, 'number': 324}, 'P': {'precision': 0.028455284552845527, 'recall': 0.04242424242424243, 'f1': 0.0340632603406326, 'number': 330}, 'overall_precision': 0.07792207792207792, 'overall_recall': 0.12844036697247707, 'overall_f1': 0.09699769053117782, 'overall_accuracy': 0.5320022497187852}
			------------EPOCH 10---------------
Loss:  tensor(485.9274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.9147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.2353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.8751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(807.9017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.7177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(710.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.6749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.6736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.9487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.9878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(702.1367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.3209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.7955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.4090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.3617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.3466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.8006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.1846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1071.8534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.7787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.4841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.2690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.0851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.9034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.1718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.5810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.6855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.6213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.0662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.5297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.2489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.6224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.7751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1119.3000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.7357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.4025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.7450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.5002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(753.7201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.9544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.6106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.1252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.1772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.3081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.1624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.1100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.8187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.1348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.6047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.0422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(998.8717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.1760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.4544, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24878048780487805, 'recall': 0.1574074074074074, 'f1': 0.1928166351606805, 'number': 324}, 'P': {'precision': 0.1791907514450867, 'recall': 0.37575757575757573, 'f1': 0.2426614481409002, 'number': 330}, 'overall_precision': 0.19509476031215162, 'overall_recall': 0.26758409785932724, 'overall_f1': 0.2256608639587363, 'overall_accuracy': 0.577615298087739}
			------------EPOCH 11---------------
Loss:  tensor(598.8054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(788.6688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.2042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.6550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.2038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(981.2888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.4911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.1376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.6068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.2819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.3936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.9494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.0352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.0991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.4843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.2774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.2647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.9830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.9019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.6522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.6888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.7166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.4013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.6592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.8595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.9360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.0558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.7896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.9833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.4882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.4099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.2849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.4995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(896.4396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1121.9353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.0645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.2233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.1147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.6226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(662.0377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.3726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.0196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.5422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.7758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.3275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.0826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.1670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.9951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.2336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.4905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.8612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.5741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.7942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.5058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.7895, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21428571428571427, 'recall': 0.12037037037037036, 'f1': 0.1541501976284585, 'number': 324}, 'P': {'precision': 0.1648, 'recall': 0.31212121212121213, 'f1': 0.2157068062827225, 'number': 330}, 'overall_precision': 0.17596034696406443, 'overall_recall': 0.21712538226299694, 'overall_f1': 0.19438740588637918, 'overall_accuracy': 0.584251968503937}
			------------EPOCH 12---------------
Loss:  tensor(299.5383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.0522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.1944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.5585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.6298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.2516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.9341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.4754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.3232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.0089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.7396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.2803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.7091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.5250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.2719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.0812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.8824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.6176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.7482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.3590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.2902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.0173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.8651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.3954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.2393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.9866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.9328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.0744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.1667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.7282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.7312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.3746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.5789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(498.1280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(846.0717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.4647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.3092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.6031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.7625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.6684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.4194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.7764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.1312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.0239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.2132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.0525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.8558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.2164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.5549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.7896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.5745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.3032, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16149068322981366, 'recall': 0.24074074074074073, 'f1': 0.19330855018587362, 'number': 324}, 'P': {'precision': 0.0922242314647378, 'recall': 0.15454545454545454, 'f1': 0.11551528878822197, 'number': 330}, 'overall_precision': 0.12451737451737452, 'overall_recall': 0.19724770642201836, 'overall_f1': 0.15266272189349114, 'overall_accuracy': 0.5899325084364454}
			------------EPOCH 13---------------
Loss:  tensor(296.3533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.1475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.5633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.6190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.2780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.1358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.7615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.0999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.7848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.5841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.6270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.3680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.8141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.1492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.3946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.6210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.9541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.2895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.1207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.9657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.5316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.0575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.3909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.6046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.7089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.3045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.0376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.7752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.6832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.1646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.8510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(484.2173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(880.9175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.7347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.4423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.8164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.5577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.5105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.4812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.6660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.1127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.9524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.6643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.8552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.4700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.2664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.6584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.1658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.3811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0782, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20242214532871972, 'recall': 0.3611111111111111, 'f1': 0.2594235033259424, 'number': 324}, 'P': {'precision': 0.25, 'recall': 0.23030303030303031, 'f1': 0.2397476340694006, 'number': 330}, 'overall_precision': 0.21882086167800455, 'overall_recall': 0.29510703363914376, 'overall_f1': 0.2513020833333333, 'overall_accuracy': 0.5516310461192351}
			------------EPOCH 14---------------
Loss:  tensor(348.0968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.9880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.5748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.5186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(646.1277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.9805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.7168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.8590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.5056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.6989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.9217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.7285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.8645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.7530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.9759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.5924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.2245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.5687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.8990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.3440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.9399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.0170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.3150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.8995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.8717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.9333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.4767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.6393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.3697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.3973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.9131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.4816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.2907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.4318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.3238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(860.0428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.2193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.3479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.6461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.6088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.7126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.8292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.3904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.9009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.5604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.5882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.0274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.1678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.7361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.5573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.0269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.4038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.6371, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26790450928381965, 'recall': 0.3117283950617284, 'f1': 0.28815977175463625, 'number': 324}, 'P': {'precision': 0.2222222222222222, 'recall': 0.3333333333333333, 'f1': 0.26666666666666666, 'number': 330}, 'overall_precision': 0.24197247706422018, 'overall_recall': 0.32262996941896027, 'overall_f1': 0.2765399737876802, 'overall_accuracy': 0.6248031496062992}
			------------EPOCH 15---------------
Loss:  tensor(224.6269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.3396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.5200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.6858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.1163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.0408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.1819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.5297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.7012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.6612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.3132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.5722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.6897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.3804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.8282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.8033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.5612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.1630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.6354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.1664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.2407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.4431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.3491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.8929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.2653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.5999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.0518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.3759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.9931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.7100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.4192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.5734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.3360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.2282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.1597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.1385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.9470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.0206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.0761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.3738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.5135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.9467, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23049645390070922, 'recall': 0.2006172839506173, 'f1': 0.2145214521452145, 'number': 324}, 'P': {'precision': 0.13122171945701358, 'recall': 0.2636363636363636, 'f1': 0.17522658610271902, 'number': 330}, 'overall_precision': 0.16084656084656085, 'overall_recall': 0.2324159021406728, 'overall_f1': 0.19011882426516571, 'overall_accuracy': 0.6199100112485939}
			------------EPOCH 16---------------
Loss:  tensor(199.9206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.8367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.1460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.5244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.7000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.5411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.0726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.3083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.0588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.0326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.9951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.6182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.2642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.6117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.8467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.1793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.8855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.2953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.9036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.3976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.7462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.5259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.1663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.0671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.7832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.8037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.3234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.0541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.5097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.5408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.3478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.9183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.0808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.6768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.2477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.4317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.1278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6624, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24175824175824176, 'recall': 0.3395061728395062, 'f1': 0.282413350449294, 'number': 324}, 'P': {'precision': 0.18046709129511676, 'recall': 0.25757575757575757, 'f1': 0.2122347066167291, 'number': 330}, 'overall_precision': 0.21058315334773217, 'overall_recall': 0.2981651376146789, 'overall_f1': 0.24683544303797472, 'overall_accuracy': 0.6061304836895388}
			------------EPOCH 17---------------
Loss:  tensor(161.4810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.6787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.8245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.8462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.4194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.8598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.2052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.8129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.3258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.6947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.7488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.9040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.1876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.6162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.8751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.8197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.1637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.0958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.7755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.9553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.8408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.0661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.9773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.6119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.3396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.3234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.8422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.7781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.1036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.7113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.9864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.5684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.9793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.4594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3970, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23615160349854228, 'recall': 0.25, 'f1': 0.2428785607196402, 'number': 324}, 'P': {'precision': 0.1783783783783784, 'recall': 0.3, 'f1': 0.22372881355932203, 'number': 330}, 'overall_precision': 0.20044543429844097, 'overall_recall': 0.27522935779816515, 'overall_f1': 0.23195876288659795, 'overall_accuracy': 0.6161979752530934}
			------------EPOCH 18---------------
Loss:  tensor(144.9535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.6446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.5990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.5468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.0434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.1286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.5042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.0413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.9096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.3083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.6963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.7717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.7461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.0265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.1524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.7734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.5599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.5062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.2056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.1229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.8168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.4539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.4264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.0939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.2231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.7247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.6435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8280, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2154566744730679, 'recall': 0.2839506172839506, 'f1': 0.24500665778961384, 'number': 324}, 'P': {'precision': 0.16417910447761194, 'recall': 0.26666666666666666, 'f1': 0.20323325635103928, 'number': 330}, 'overall_precision': 0.18691588785046728, 'overall_recall': 0.27522935779816515, 'overall_f1': 0.22263450834879403, 'overall_accuracy': 0.6168166479190101}
			------------EPOCH 19---------------
Loss:  tensor(131.4798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.7828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.8766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.1367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.7700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.4263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.0929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.2061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.6523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.6948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.9977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.4817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.5849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.5515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.5651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.7531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.4769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.4468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.0196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.8248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.6148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.1068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.4204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.2025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0708, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25, 'recall': 0.2777777777777778, 'f1': 0.2631578947368421, 'number': 324}, 'P': {'precision': 0.1798165137614679, 'recall': 0.296969696969697, 'f1': 0.224, 'number': 330}, 'overall_precision': 0.20773480662983426, 'overall_recall': 0.2874617737003058, 'overall_f1': 0.24118024374599104, 'overall_accuracy': 0.6176602924634421}
			------------EPOCH 20---------------
Loss:  tensor(99.7384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.6006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.3711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.4395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.9385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.7632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.1421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.4597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.5978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.0646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.7590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.7928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.7209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.8551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.4492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.1913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.1940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.2336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.8123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.3618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.0254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.9963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.9845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.8010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.9201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.8052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0167, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21601941747572814, 'recall': 0.27469135802469136, 'f1': 0.2418478260869565, 'number': 324}, 'P': {'precision': 0.16883116883116883, 'recall': 0.27575757575757576, 'f1': 0.2094361334867664, 'number': 330}, 'overall_precision': 0.1892744479495268, 'overall_recall': 0.27522935779816515, 'overall_f1': 0.22429906542056072, 'overall_accuracy': 0.615466816647919}
			------------EPOCH 21---------------
Loss:  tensor(81.1381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.9588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.0969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.7084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.8802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.9033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.5743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.4736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.4867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.7151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.8671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.1433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.6378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.7357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.4139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.6514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.0520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.9370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.3803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.7413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.1807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.3399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.7494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0538, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24860335195530725, 'recall': 0.27469135802469136, 'f1': 0.26099706744868034, 'number': 324}, 'P': {'precision': 0.18609022556390978, 'recall': 0.3, 'f1': 0.2296983758700696, 'number': 330}, 'overall_precision': 0.21123595505617979, 'overall_recall': 0.2874617737003058, 'overall_f1': 0.2435233160621762, 'overall_accuracy': 0.6152418447694038}
			------------EPOCH 22---------------
Loss:  tensor(75.2994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.1952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.4865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.0145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.0906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.0241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.0812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.3530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.7187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.7506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.6872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.9377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.7248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.7566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.2125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.8230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.0491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.9146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.0609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.5159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.2831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.1572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.2019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.7458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8964, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22807017543859648, 'recall': 0.2808641975308642, 'f1': 0.25172890733056713, 'number': 324}, 'P': {'precision': 0.17723880597014927, 'recall': 0.2878787878787879, 'f1': 0.2193995381062356, 'number': 330}, 'overall_precision': 0.19893048128342247, 'overall_recall': 0.28440366972477066, 'overall_f1': 0.23410950283196982, 'overall_accuracy': 0.621541057367829}
			------------EPOCH 23---------------
Loss:  tensor(111.1164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.6917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.7387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.1433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.0841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.7011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.1769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.7887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.5764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.4399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.7341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.6593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.0713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.1667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.1845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.7355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.9512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.7018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.8245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.1028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.1829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.3307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.2906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.4863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3166, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.236318407960199, 'recall': 0.2932098765432099, 'f1': 0.26170798898071623, 'number': 324}, 'P': {'precision': 0.16955684007707128, 'recall': 0.26666666666666666, 'f1': 0.20730270906949352, 'number': 330}, 'overall_precision': 0.1986970684039088, 'overall_recall': 0.2798165137614679, 'overall_f1': 0.23238095238095238, 'overall_accuracy': 0.6131046119235095}
			------------EPOCH 24---------------
Loss:  tensor(144.7326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.2269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.7794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.8641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.8522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.0675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.2867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.3450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.4131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.4478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.2270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.9189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.3153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.0061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.8822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.2113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.1140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.2029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.6587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.6675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.8550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.0194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5472, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24390243902439024, 'recall': 0.2777777777777778, 'f1': 0.25974025974025977, 'number': 324}, 'P': {'precision': 0.19065420560747665, 'recall': 0.3090909090909091, 'f1': 0.23583815028901733, 'number': 330}, 'overall_precision': 0.21238938053097345, 'overall_recall': 0.29357798165137616, 'overall_f1': 0.24646983311938384, 'overall_accuracy': 0.6104611923509561}
			------------EPOCH 25---------------
Loss:  tensor(84.3620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.1368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.6545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.0213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.5519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.6609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.6034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.2211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.9455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.6682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.5423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.3978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.7769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.5372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.0155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.6715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.9330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.1668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.9470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.3426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.8367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.3075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.5912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9267, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21218961625282168, 'recall': 0.29012345679012347, 'f1': 0.24511082138200782, 'number': 324}, 'P': {'precision': 0.17054263565891473, 'recall': 0.26666666666666666, 'f1': 0.20803782505910162, 'number': 330}, 'overall_precision': 0.1897810218978102, 'overall_recall': 0.2782874617737003, 'overall_f1': 0.22566646001239923, 'overall_accuracy': 0.596962879640045}
			------------EPOCH 26---------------
Loss:  tensor(51.0246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.1836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.1224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.0891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.1247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.5428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.1320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.8867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.1968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.7431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.5739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.1858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.3616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.2258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.3178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.2798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.5563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.4388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.4226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.4685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.8139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2589, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2301980198019802, 'recall': 0.28703703703703703, 'f1': 0.2554945054945055, 'number': 324}, 'P': {'precision': 0.17058823529411765, 'recall': 0.2636363636363636, 'f1': 0.20714285714285713, 'number': 330}, 'overall_precision': 0.19693654266958424, 'overall_recall': 0.27522935779816515, 'overall_f1': 0.22959183673469385, 'overall_accuracy': 0.5960067491563554}
			------------EPOCH 27---------------
Loss:  tensor(44.1916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.8779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.1737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.2246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.6858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.3311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.3990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.1410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.2022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.0203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.2528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.1616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.0381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.8608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.1473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.5496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.3606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.4239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.2352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.0841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.3713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.6655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.7944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6926, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26176470588235295, 'recall': 0.27469135802469136, 'f1': 0.2680722891566265, 'number': 324}, 'P': {'precision': 0.17217391304347826, 'recall': 0.3, 'f1': 0.21878453038674034, 'number': 330}, 'overall_precision': 0.20546448087431693, 'overall_recall': 0.2874617737003058, 'overall_f1': 0.23964308476736773, 'overall_accuracy': 0.622103487064117}
			------------EPOCH 28---------------
Loss:  tensor(124.9908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.9248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.3322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.9461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.7607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.9171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.1019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.6508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.5813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.7703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.0913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.3603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.2856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.1875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.8069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.8030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.4300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.4566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.7181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.8955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.3313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.5443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.8795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.0520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7487, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2267818574514039, 'recall': 0.32407407407407407, 'f1': 0.2668360864040661, 'number': 324}, 'P': {'precision': 0.18584070796460178, 'recall': 0.2545454545454545, 'f1': 0.21483375959079284, 'number': 330}, 'overall_precision': 0.20655737704918034, 'overall_recall': 0.2889908256880734, 'overall_f1': 0.24091778202676864, 'overall_accuracy': 0.6055118110236221}
			------------EPOCH 29---------------
Loss:  tensor(46.0567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.1796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.9286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.0813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.8017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.7109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.1847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.3721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.6728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.6455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.1171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.5129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.3918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.4093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.1771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.5398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.0392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.1683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.8023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.4932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.1331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.5860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9872, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2606060606060606, 'recall': 0.2654320987654321, 'f1': 0.2629969418960245, 'number': 324}, 'P': {'precision': 0.20488721804511278, 'recall': 0.3303030303030303, 'f1': 0.2529002320185615, 'number': 330}, 'overall_precision': 0.22621809744779584, 'overall_recall': 0.2981651376146789, 'overall_f1': 0.25725593667546176, 'overall_accuracy': 0.6210348706411698}
			------------EPOCH 30---------------
Loss:  tensor(35.1428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.8974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.6590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.3489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.2254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.3952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.0990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.1222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.1625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.6580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.7061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.5318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.5725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.3999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.0398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.5343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.6862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.8937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.0334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.5305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9162, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23318385650224216, 'recall': 0.32098765432098764, 'f1': 0.27012987012987016, 'number': 324}, 'P': {'precision': 0.1673469387755102, 'recall': 0.24848484848484848, 'f1': 0.2, 'number': 330}, 'overall_precision': 0.1987179487179487, 'overall_recall': 0.28440366972477066, 'overall_f1': 0.23396226415094337, 'overall_accuracy': 0.6061304836895388}


		-------------RUN 2-----------
Test files: ['/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/230.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/69.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/68.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/10.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/11.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/8.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/12.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/5.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/82.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/85.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/84.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/86.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/83.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/25.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/291.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/86.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/258.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/75.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/309.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/92.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/91.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/93.xml']
			------------EPOCH 1---------------
Loss:  tensor(3479.5498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1951.1512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3533.9265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1554.6382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2843.3403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2133.9524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2028.4329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1629.0812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1675.5845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2017.3971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2653.9658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1105.4268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2318.3833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1985.9644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1900.6300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1261.8057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1317.8618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1622.9979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1271.6824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2046.8850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2571.2773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2448.6802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2669.3516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1919.6510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1627.7303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1748.3425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1772.7264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2145.9263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1899.6636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2355.5024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1461.2578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2237.8132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2259.8098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1740.3915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(843.5955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(804.2629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1573.6456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1135.0957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2254.8762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1501.2014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4021.1689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1991.9171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2264.4395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2116.8193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2872.1921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2497.9207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1450.2549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.5043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(835.0948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1427.5676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1674.1705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1320.6421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2562.2097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2561.1084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2696.5208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2308.6909, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 237}, 'P': {'precision': 0.02617801047120419, 'recall': 0.03745318352059925, 'f1': 0.030816640986132512, 'number': 267}, 'overall_precision': 0.02518891687657431, 'overall_recall': 0.01984126984126984, 'overall_f1': 0.022197558268590458, 'overall_accuracy': 0.496922024623803}
			------------EPOCH 2---------------
Loss:  tensor(2396.0925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1196.5435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2282.6675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.9796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1994.2350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1452.2126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1409.1173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.7141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1256.5101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1390.5483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1937.1960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(802.6991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1714.2659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1511.9839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1460.8188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(909.2223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(988.3311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1586.2610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(950.0367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1761.2443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2301.8962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2043.9935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2187.1958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1454.6541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1450.3208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1338.6226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1424.6239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1786.8928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1343.5571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1952.1133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1145.3094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1869.9291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1806.8999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1464.8350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.6204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.5200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1118.1165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(885.5627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1779.0652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1392.9084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3679.6582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1749.4517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2165.5466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1956.3312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2412.5105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2136.5686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1323.7997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(790.9529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.7410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1183.1879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1321.9567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1025.3665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2180.0859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2206.1108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2275.3542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1828.0811, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.42, 'recall': 0.08860759493670886, 'f1': 0.14634146341463417, 'number': 237}, 'P': {'precision': 0.057534246575342465, 'recall': 0.07865168539325842, 'f1': 0.06645569620253164, 'number': 267}, 'overall_precision': 0.10120481927710843, 'overall_recall': 0.08333333333333333, 'overall_f1': 0.09140369967355821, 'overall_accuracy': 0.5289329685362517}
			------------EPOCH 3---------------
Loss:  tensor(1955.6830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1068.3516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2041.5406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(874.7981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1718.2974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1254.7720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1046.0540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.4805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1096.5870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1165.8086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1724.9924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(708.3331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1405.0986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1249.3589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1224.3235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.4127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.0135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1437.6288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(779.8492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1520.8840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1919.3833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1603.7214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1730.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1079.4158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1250.9258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1055.9484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1160.6934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1523.4442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1097.2812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1667.7085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(939.9545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1631.3522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1489.6794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1281.9265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(577.6918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.0728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(831.3098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(729.7840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1502.4875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1196.4429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3059.7961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1482.3771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1990.9896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1612.8075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1926.6416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1706.8569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1185.7048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.5740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.9510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(962.1759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1075.0474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(825.4134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1792.6593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1889.8523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1902.2244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1357.7451, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.27058823529411763, 'recall': 0.0970464135021097, 'f1': 0.14285714285714285, 'number': 237}, 'P': {'precision': 0.08771929824561403, 'recall': 0.11235955056179775, 'f1': 0.09852216748768472, 'number': 267}, 'overall_precision': 0.12412177985948478, 'overall_recall': 0.10515873015873016, 'overall_f1': 0.1138560687432868, 'overall_accuracy': 0.5489740082079343}
			------------EPOCH 4---------------
Loss:  tensor(1576.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(887.2114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1686.9609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(673.4656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1389.6089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1071.2944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(722.4100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.1738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(956.9462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(944.3585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1590.9019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.1018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1156.9113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1082.5060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(985.3473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.0485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.7400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1118.8018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.2748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1260.4900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1526.9456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1318.4224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1364.8977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(789.4714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(975.0831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.2379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(937.5594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1217.9011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(817.9032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1412.7444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.1470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1354.0479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1194.5620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.5464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.0911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.9615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(569.9866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.6636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1229.6111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(973.6227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2669.5640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.5520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1958.7419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1397.7454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1515.9639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1326.5963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.2935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.5834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.7420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(794.7023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(828.7024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(634.4445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1449.8030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1395.4365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1545.6526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.6373, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24731182795698925, 'recall': 0.0970464135021097, 'f1': 0.1393939393939394, 'number': 237}, 'P': {'precision': 0.10057471264367816, 'recall': 0.13108614232209737, 'f1': 0.1138211382113821, 'number': 267}, 'overall_precision': 0.13151927437641722, 'overall_recall': 0.11507936507936507, 'overall_f1': 0.12275132275132274, 'overall_accuracy': 0.5495212038303694}
			------------EPOCH 5---------------
Loss:  tensor(1379.6575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(681.0251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1478.8931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.7817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1253.6914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(904.9440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(650.1476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(707.0164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.8186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.0373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1393.5000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.1413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(918.7312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(887.7241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.1182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.0688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.1500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(804.9312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.2202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.6960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1272.0386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1087.0309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1145.5148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.4305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.4764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.2302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.6014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(936.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.6510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1148.2742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.3553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.4817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1006.2094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.0942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.1213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.5808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.1518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.1705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1012.2238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(848.3712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2731.0847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1062.0352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2002.4197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1328.2428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.0289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1073.3108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(912.6897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.3110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.1322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.2661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.6400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(536.6223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1504.0896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1405.0760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1568.0179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1022.8588, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1348314606741573, 'recall': 0.1518987341772152, 'f1': 0.14285714285714285, 'number': 237}, 'P': {'precision': 0.13850415512465375, 'recall': 0.18726591760299627, 'f1': 0.15923566878980894, 'number': 267}, 'overall_precision': 0.13694267515923567, 'overall_recall': 0.17063492063492064, 'overall_f1': 0.1519434628975265, 'overall_accuracy': 0.5623119015047879}
			------------EPOCH 6---------------
Loss:  tensor(1488.7950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.0727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1375.6547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(461.6759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.7004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(659.6445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.0514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.0450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.9839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.6438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1152.5337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.0602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1066.3907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(951.8563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1086.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.3171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.7625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(986.8995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(829.2445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1590.6326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1781.6859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1496.0507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1744.3059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(735.2807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.1758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(602.7236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(694.9866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(895.8347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(560.3520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(999.2572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(536.9379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.7361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(914.8273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(876.6904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.3824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.1668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.6451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.1443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1010.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(988.4462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2578.3867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1087.3425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1633.0431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1299.5814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1216.5071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1170.9978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.4935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.6705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.6622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1035.5557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(927.4615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(757.2427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1592.4664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1797.5239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1875.5881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1294.6462, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19607843137254902, 'recall': 0.2109704641350211, 'f1': 0.2032520325203252, 'number': 237}, 'P': {'precision': 0.2198952879581152, 'recall': 0.3146067415730337, 'f1': 0.2588597842835131, 'number': 267}, 'overall_precision': 0.21036106750392464, 'overall_recall': 0.26587301587301587, 'overall_f1': 0.23488168273444346, 'overall_accuracy': 0.5565663474692203}
			------------EPOCH 7---------------
Loss:  tensor(2687.0476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.3800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1344.9723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(497.3863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1280.8940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.6825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(966.2005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.9587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.9116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(715.7861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1151.5674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.3035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1083.8101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(865.4591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.3796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.4580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.7242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(896.1170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.2020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(939.2776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1247.2146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(986.7571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1107.6814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(601.7623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.7476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(716.6389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(694.6174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(936.6217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.7771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1178.0771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.3182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(989.6578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1078.1960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(807.0999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.3649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.8459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.6574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.7808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(916.4558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.5059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2144.2930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(922.2659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.2769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(831.1250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1035.7170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(993.7625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(778.2655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.3086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.7607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.8550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(573.1935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.2556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(883.9534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.2491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1066.5708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(655.4976, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14901960784313725, 'recall': 0.16033755274261605, 'f1': 0.15447154471544716, 'number': 237}, 'P': {'precision': 0.18313953488372092, 'recall': 0.23595505617977527, 'f1': 0.2062193126022913, 'number': 267}, 'overall_precision': 0.1686143572621035, 'overall_recall': 0.2003968253968254, 'overall_f1': 0.1831368993653672, 'overall_accuracy': 0.5751709986320109}
			------------EPOCH 8---------------
Loss:  tensor(1336.1604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.0749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.0133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.7098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.9168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(636.5406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.0129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.7810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.5780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(517.3621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(961.0168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.4841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.4706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(716.3375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(700.4312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.9837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.2582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(837.2282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.2635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(719.1512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1023.2596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(682.1682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(923.6387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.5948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(474.9755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.8063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.9023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.5664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.4791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(682.3948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.6896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.5106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(716.1033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.3870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.1296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.8912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.9060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.2368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.3746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.3893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1671.7855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.7133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(911.1017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.2512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.5510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.1464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.7794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.5243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.5641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.5729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.9242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.0438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(825.1089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(931.4598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.8486, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.116, 'recall': 0.12236286919831224, 'f1': 0.11909650924024642, 'number': 237}, 'P': {'precision': 0.15311004784688995, 'recall': 0.2397003745318352, 'f1': 0.18686131386861313, 'number': 267}, 'overall_precision': 0.13922155688622753, 'overall_recall': 0.18452380952380953, 'overall_f1': 0.15870307167235495, 'overall_accuracy': 0.5870041039671683}
			------------EPOCH 9---------------
Loss:  tensor(916.2409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.5623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(920.9344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.3922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.0352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.9416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.3661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.9802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.6558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.5849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(678.5699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.8984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.8373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.2547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.9004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.1807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.3065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.7906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.4986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.7114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.0227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.1917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(655.8606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.0113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.3498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.2159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.4747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.8057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.5027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(549.5684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.5312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.3002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.4631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.6784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.6829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.8951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.1754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.2096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.8992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.0486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1492.5093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.9088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.4015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(503.9029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(619.0820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(498.6274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.1222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.8251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.3641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.3197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.6300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.6218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.9822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.3470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(773.5358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.1060, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15019762845849802, 'recall': 0.16033755274261605, 'f1': 0.15510204081632653, 'number': 237}, 'P': {'precision': 0.16709511568123395, 'recall': 0.24344569288389514, 'f1': 0.19817073170731708, 'number': 267}, 'overall_precision': 0.16043613707165108, 'overall_recall': 0.20436507936507936, 'overall_f1': 0.17975567190226874, 'overall_accuracy': 0.6014363885088919}
			------------EPOCH 10---------------
Loss:  tensor(774.6892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(765.7245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.2515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.4678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.5831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.0474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.0210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.3717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.1884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.2560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.3194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.8394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.8418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.0829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.9544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.1072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.8813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.9072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.7015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.9705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.2151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.1548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.9793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.6190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.6821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.4635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.1461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.1665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.5498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.5799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.7136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.0269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.6722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.1934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.2562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.9750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.6002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.6823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.9508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1063.3998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.6882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.9328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.4394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.2659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.2470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.5934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.5745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.5925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.2929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.5074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.7251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(613.7740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.8755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(829.4564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.8727, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.31645569620253167, 'recall': 0.10548523206751055, 'f1': 0.15822784810126583, 'number': 237}, 'P': {'precision': 0.21153846153846154, 'recall': 0.3707865168539326, 'f1': 0.2693877551020408, 'number': 267}, 'overall_precision': 0.226691042047532, 'overall_recall': 0.24603174603174602, 'overall_f1': 0.2359657469077069, 'overall_accuracy': 0.5593023255813954}
			------------EPOCH 11---------------
Loss:  tensor(957.5173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.2984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.0800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.6077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.1994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.0325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.8173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.5284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.0973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.4987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.6302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.4388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.1536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.5957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.1336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.0526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.8797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.9772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.1943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.2039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(641.3588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.4444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.9688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.4422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.4944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.7195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.6026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.2185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.8853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.9640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(484.6103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.9344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.0561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.8589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.9623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.5825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.1539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.0504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.2021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.7902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.6045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.4991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.9991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.5725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.4085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.2987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.0705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.2289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.4958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.4994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.5075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(587.8049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.8893, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5, 'recall': 0.10126582278481013, 'f1': 0.16842105263157894, 'number': 237}, 'P': {'precision': 0.2092130518234165, 'recall': 0.40823970037453183, 'f1': 0.2766497461928934, 'number': 267}, 'overall_precision': 0.23374340949033393, 'overall_recall': 0.2638888888888889, 'overall_f1': 0.2479030754892824, 'overall_accuracy': 0.5478796169630643}
			------------EPOCH 12---------------
Loss:  tensor(725.7778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.2828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.8404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.5790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(776.6271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.3424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.6624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.3706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(963.0587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1111.3488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1425.6869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.9013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.1478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(856.7985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(716.7383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.6559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.5031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.1073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.4845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.7918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.2418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.5641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(441.2597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.4504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.0427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.9547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.9342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.9559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.6612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.9612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.2446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.8741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.8287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.2875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.7141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.1984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.2704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.7149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1202.0839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.6375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2084.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(712.3343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(912.8791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(782.4424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2117.2822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1252.8722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.2599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.7070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.8849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.8875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.5786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.5825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(586.2621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.8694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(753.4627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(603.8959, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18518518518518517, 'recall': 0.06329113924050633, 'f1': 0.09433962264150944, 'number': 237}, 'P': {'precision': 0.15471698113207547, 'recall': 0.30711610486891383, 'f1': 0.205771643663739, 'number': 267}, 'overall_precision': 0.15875613747954173, 'overall_recall': 0.19246031746031747, 'overall_f1': 0.17399103139013453, 'overall_accuracy': 0.5532147742818058}
			------------EPOCH 13---------------
Loss:  tensor(701.4989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.7583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(752.0281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.6253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.7582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.0652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.4887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.8773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.9442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.2085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(944.6691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.4518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(683.0883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.6866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.0833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.1454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.6299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(806.0148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.1042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1012.9279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1436.8090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(999.7263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1241.3792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.3468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.9802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(767.9999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.3563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(781.8352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.6151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.0596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.1995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.0696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.0309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.8759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.4020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.7860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.1118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.9053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.4187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.8702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1002.2982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.4927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.4073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.5258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.7426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.0403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.7062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.6520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.5610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.2891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.3463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.0676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.3517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.8555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1032.6564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(659.6924, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1710914454277286, 'recall': 0.24472573839662448, 'f1': 0.2013888888888889, 'number': 237}, 'P': {'precision': 0.17921146953405018, 'recall': 0.18726591760299627, 'f1': 0.18315018315018317, 'number': 267}, 'overall_precision': 0.17475728155339806, 'overall_recall': 0.21428571428571427, 'overall_f1': 0.1925133689839572, 'overall_accuracy': 0.641860465116279}
			------------EPOCH 14---------------
Loss:  tensor(793.1616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1217.1027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(404.6789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(688.4431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.6190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.2510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.7930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.8051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.2472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.3276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.2147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.0289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.4279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.9339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.9764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.3449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.8126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.5797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.4998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.6094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.8834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.1038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.4292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.8208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.0954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.0884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.0411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.2110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.9008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.5034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.8629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.2089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.2804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.9915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.9961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.3511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.7221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.5871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(904.7426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.0505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.9731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.4135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.1736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.7440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.7468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.2294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.2502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.1690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.6260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.2764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.4108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.5318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.2606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.9211, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2375, 'recall': 0.24050632911392406, 'f1': 0.2389937106918239, 'number': 237}, 'P': {'precision': 0.19658119658119658, 'recall': 0.3445692883895131, 'f1': 0.25034013605442174, 'number': 267}, 'overall_precision': 0.21045197740112995, 'overall_recall': 0.29563492063492064, 'overall_f1': 0.2458745874587459, 'overall_accuracy': 0.6057455540355677}
			------------EPOCH 15---------------
Loss:  tensor(559.8886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.4557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(603.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.6792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.5618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.7989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.3856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.9237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.5027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.1583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.1024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.6775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.7528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.0797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.8588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.8157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.1129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.6788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.3003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.4920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.3487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.9835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.8526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.0462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.9055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.7733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.5624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.0719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.7222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.8132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.4414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.5726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.9033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.0995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.1972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.1793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.5465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.2724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.6166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.4197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(694.9661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.6659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.6663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.5262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.5280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.9376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.9381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.7227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.2943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.3541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.9993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.5060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.3003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.2933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(450.9041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.3978, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19158878504672897, 'recall': 0.1729957805907173, 'f1': 0.18181818181818182, 'number': 237}, 'P': {'precision': 0.1951219512195122, 'recall': 0.299625468164794, 'f1': 0.23633677991137372, 'number': 267}, 'overall_precision': 0.19391025641025642, 'overall_recall': 0.2400793650793651, 'overall_f1': 0.21453900709219859, 'overall_accuracy': 0.6144322845417237}
			------------EPOCH 16---------------
Loss:  tensor(468.9555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.0402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.0635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.7372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.9843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.1979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.0409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.9339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.4513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.1095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.3272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.5060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.9417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.0501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.4851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.8538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.6305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.2016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.2487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.8863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.6581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.1809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.0228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.4109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.0261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.8055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.4095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.4984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.1960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.6397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.9605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.2465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.4403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.3019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.5029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.5704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.8973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.6729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.8323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.2085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.6953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.0799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.4599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.5150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.9415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.4895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.2892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.0533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.7643, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17551020408163265, 'recall': 0.18143459915611815, 'f1': 0.1784232365145228, 'number': 237}, 'P': {'precision': 0.18421052631578946, 'recall': 0.2883895131086142, 'f1': 0.2248175182481752, 'number': 267}, 'overall_precision': 0.18099547511312217, 'overall_recall': 0.23809523809523808, 'overall_f1': 0.20565552699228795, 'overall_accuracy': 0.6285909712722298}
			------------EPOCH 17---------------
Loss:  tensor(391.9022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.4432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.7665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.8752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.0388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.4796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.5880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.9795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.7479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.1071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.8603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.9981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.2308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.8423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.5446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.1117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.6773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.6034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.6479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.7495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.5422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.3788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.3397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.6733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.3374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.5109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.0440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.0987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.1892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.4986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.6891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.8300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.7780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.2188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.2007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.0755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.1603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.3203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.6983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.1045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.0981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.5202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.8021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.5522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.0559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.7558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.4463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.5075, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22009569377990432, 'recall': 0.1940928270042194, 'f1': 0.20627802690582958, 'number': 237}, 'P': {'precision': 0.18765432098765433, 'recall': 0.2846441947565543, 'f1': 0.2261904761904762, 'number': 267}, 'overall_precision': 0.1986970684039088, 'overall_recall': 0.24206349206349206, 'overall_f1': 0.21824686940966012, 'overall_accuracy': 0.6277701778385772}
			------------EPOCH 18---------------
Loss:  tensor(359.1970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.0876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.2689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.3628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.5694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.7082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.9552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.7787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.5081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.0867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.8696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.8160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.8823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.6403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.8027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.6396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.7442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.3366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.6321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.0194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.1656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.8011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.9334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.3047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.9829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.4939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(573.4478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.4066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.2121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.9392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.8150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.7802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.7924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.0427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.8018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.0434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.1081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.7001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.4912, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19367588932806323, 'recall': 0.20675105485232068, 'f1': 0.19999999999999998, 'number': 237}, 'P': {'precision': 0.17955112219451372, 'recall': 0.2696629213483146, 'f1': 0.2155688622754491, 'number': 267}, 'overall_precision': 0.18501529051987767, 'overall_recall': 0.2400793650793651, 'overall_f1': 0.20898100172711573, 'overall_accuracy': 0.6341997264021888}
			------------EPOCH 19---------------
Loss:  tensor(337.7057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.8264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.7041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.8313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.4562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.7648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.9564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.7995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.0197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.7013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.4585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.9165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.9123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.5370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.4631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.3429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.6809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.2869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.2976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.3104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.2697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.4160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.9712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.5992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.1246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.9956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.5726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.0133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.4551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.6552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.1271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.1900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.9214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.5847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.8654, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1724137931034483, 'recall': 0.16877637130801687, 'f1': 0.17057569296375266, 'number': 237}, 'P': {'precision': 0.17307692307692307, 'recall': 0.2696629213483146, 'f1': 0.2108345534407028, 'number': 267}, 'overall_precision': 0.1728395061728395, 'overall_recall': 0.2222222222222222, 'overall_f1': 0.19444444444444445, 'overall_accuracy': 0.6465800273597812}
			------------EPOCH 20---------------
Loss:  tensor(324.4497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.1334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.5449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.6826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.2544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.0561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.7524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.3007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.1261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.2352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.6914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.3951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.7435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.0330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.2613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.7127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.2627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.3040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.7540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(483.9338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.3390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.6030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.1746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.1271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.9613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.6208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.6512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.2675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.5036, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18518518518518517, 'recall': 0.189873417721519, 'f1': 0.1875, 'number': 237}, 'P': {'precision': 0.16152019002375298, 'recall': 0.2546816479400749, 'f1': 0.19767441860465115, 'number': 267}, 'overall_precision': 0.17018072289156627, 'overall_recall': 0.22420634920634921, 'overall_f1': 0.1934931506849315, 'overall_accuracy': 0.6357045143638851}
			------------EPOCH 21---------------
Loss:  tensor(296.3731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.7716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.4400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.4950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.9984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.6493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.6693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.7835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.7178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.3618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.8385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.8806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.7074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.4136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.4635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.0506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.5636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.2359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.7647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.4337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.5855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.6021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.5603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.2985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.7786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.0652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.5492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.5746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.3289, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18110236220472442, 'recall': 0.1940928270042194, 'f1': 0.1873727087576375, 'number': 237}, 'P': {'precision': 0.1782178217821782, 'recall': 0.2696629213483146, 'f1': 0.21460506706408347, 'number': 267}, 'overall_precision': 0.17933130699088146, 'overall_recall': 0.23412698412698413, 'overall_f1': 0.20309810671256454, 'overall_accuracy': 0.6341313269493845}
			------------EPOCH 22---------------
Loss:  tensor(280.7958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.0627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.1015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.2141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.5332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.5050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.0587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.5781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.7918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.3699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.2593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.4642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.2429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.5104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.5100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.0335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.0193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.8467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.1202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.1620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.8398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.3259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.5052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.2500, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19823788546255505, 'recall': 0.189873417721519, 'f1': 0.1939655172413793, 'number': 237}, 'P': {'precision': 0.16985645933014354, 'recall': 0.26591760299625467, 'f1': 0.20729927007299268, 'number': 267}, 'overall_precision': 0.17984496124031008, 'overall_recall': 0.23015873015873015, 'overall_f1': 0.20191470844212356, 'overall_accuracy': 0.6380984952120383}
			------------EPOCH 23---------------
Loss:  tensor(315.6670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.9341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.3168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.4133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.3372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.1695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.5187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.1796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.3244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.0700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.7504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.9472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.4376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.2176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.7479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.5382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.5076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.1265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.7359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.5018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.9524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.4296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.7204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.6281, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17624521072796934, 'recall': 0.1940928270042194, 'f1': 0.18473895582329314, 'number': 237}, 'P': {'precision': 0.18004866180048662, 'recall': 0.27715355805243447, 'f1': 0.2182890855457227, 'number': 267}, 'overall_precision': 0.17857142857142858, 'overall_recall': 0.23809523809523808, 'overall_f1': 0.20408163265306123, 'overall_accuracy': 0.6369357045143639}
			------------EPOCH 24---------------
Loss:  tensor(295.3871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.6334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.5394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.3369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.1986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.7901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.9925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.4681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.0093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.0811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.5659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.7435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.1366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.4587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.1392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.6169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.4588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.7239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.1087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.2348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.3064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.7840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.5295, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.176, 'recall': 0.18565400843881857, 'f1': 0.18069815195071867, 'number': 237}, 'P': {'precision': 0.1650485436893204, 'recall': 0.2546816479400749, 'f1': 0.20029455081001477, 'number': 267}, 'overall_precision': 0.1691842900302115, 'overall_recall': 0.2222222222222222, 'overall_f1': 0.19210977701543738, 'overall_accuracy': 0.6467852257181943}
			------------EPOCH 25---------------
Loss:  tensor(263.4564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.4962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.8243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.1476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.3123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.7456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.8177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.1566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.0263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.5516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.1500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.8188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.5323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.7021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.4272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.7233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.1441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.8034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.1180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.0763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.8322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.5904, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19047619047619047, 'recall': 0.18565400843881857, 'f1': 0.18803418803418803, 'number': 237}, 'P': {'precision': 0.1596244131455399, 'recall': 0.2546816479400749, 'f1': 0.19624819624819623, 'number': 267}, 'overall_precision': 0.1704718417047184, 'overall_recall': 0.2222222222222222, 'overall_f1': 0.1929371231696813, 'overall_accuracy': 0.6275649794801642}
			------------EPOCH 26---------------
Loss:  tensor(254.1308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.3729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.1260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.3107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.1793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.1252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.7884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.5249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.6038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.7934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.6676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.4876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.5872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.9050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.2264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.1346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.4413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.3610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.5652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.5964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.9413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.3469, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1744186046511628, 'recall': 0.189873417721519, 'f1': 0.18181818181818182, 'number': 237}, 'P': {'precision': 0.1531322505800464, 'recall': 0.24719101123595505, 'f1': 0.18911174785100288, 'number': 267}, 'overall_precision': 0.16110304789550073, 'overall_recall': 0.22023809523809523, 'overall_f1': 0.18608549874266553, 'overall_accuracy': 0.6306429548563611}
			------------EPOCH 27---------------
Loss:  tensor(242.0904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.9928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.7363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.9339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.1189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.9825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.5064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.8087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.6735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.4627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.1311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.6091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.5026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.2761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.1015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.2346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.4707, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19827586206896552, 'recall': 0.1940928270042194, 'f1': 0.1961620469083156, 'number': 237}, 'P': {'precision': 0.167816091954023, 'recall': 0.27340823970037453, 'f1': 0.20797720797720798, 'number': 267}, 'overall_precision': 0.17841079460269865, 'overall_recall': 0.2361111111111111, 'overall_f1': 0.20324508966695132, 'overall_accuracy': 0.6437756497948016}
			------------EPOCH 28---------------
Loss:  tensor(225.4437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.3673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.6341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.2619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.9698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.8578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.1179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.2386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.3222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.6097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.4791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.3551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.1901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.1678, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18, 'recall': 0.189873417721519, 'f1': 0.18480492813141686, 'number': 237}, 'P': {'precision': 0.16822429906542055, 'recall': 0.2696629213483146, 'f1': 0.2071942446043165, 'number': 267}, 'overall_precision': 0.17256637168141592, 'overall_recall': 0.23214285714285715, 'overall_f1': 0.19796954314720813, 'overall_accuracy': 0.638030095759234}
			------------EPOCH 29---------------
Loss:  tensor(214.7643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.3913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.2244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.2083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.6603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.7750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.2226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.9649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.9206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.1032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.8884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.9828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.9785, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1776061776061776, 'recall': 0.1940928270042194, 'f1': 0.18548387096774194, 'number': 237}, 'P': {'precision': 0.1574074074074074, 'recall': 0.2546816479400749, 'f1': 0.1945636623748212, 'number': 267}, 'overall_precision': 0.1649782923299566, 'overall_recall': 0.2261904761904762, 'overall_f1': 0.19079497907949788, 'overall_accuracy': 0.6317373461012312}
			------------EPOCH 30---------------
Loss:  tensor(223.0230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.9617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.9557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.6940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.4710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.0154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.8770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.4067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.5732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.6848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.2128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.5816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.7018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.9302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.6602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.8383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.0281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.6083, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20087336244541484, 'recall': 0.1940928270042194, 'f1': 0.19742489270386265, 'number': 237}, 'P': {'precision': 0.15198237885462554, 'recall': 0.25842696629213485, 'f1': 0.1914008321775312, 'number': 267}, 'overall_precision': 0.1683748169838946, 'overall_recall': 0.22817460317460317, 'overall_f1': 0.1937657961246841, 'overall_accuracy': 0.6405608755129959}


		-------------RUN 3-----------
Test files: ['/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/74.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/78.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/76.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/77.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/73.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/75.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/21.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/318.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/95.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/94.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/224.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/67.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/301.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/88.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/334.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/97.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/99.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/97.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/98.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/31.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/308.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/90.xml']
			------------EPOCH 1---------------
Loss:  tensor(1974.5280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2119.4744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1891.1707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2218.4958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2902.4497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2986.2617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1368.5122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2126.6353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2137.6641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1931.7958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2321.9771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2924.5874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2241.2405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2185.9270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1217.6091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1660.0997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1198.2185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1388.4010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1729.6559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2685.1001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1007.9111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1990.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1929.4595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1804.7126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1138.5963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2494.3044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1510.2770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1687.3739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1003.4905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1287.1594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1400.4537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1023.9789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1935.1796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(898.6367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.5868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1219.9277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1046.1506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.5500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1285.5015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3112.4412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2273.1172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1254.8766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(692.3109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2419.9690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2189.6436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2002.5020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1386.5959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.7271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.5308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2201.0181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2333.3228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1214.2891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1547.0813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1900.2091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(987.0891, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360}, 'P': {'precision': 0.0038314176245210726, 'recall': 0.002320185614849188, 'f1': 0.0028901734104046246, 'number': 431}, 'overall_precision': 0.002793296089385475, 'overall_recall': 0.0012642225031605564, 'overall_f1': 0.0017406440382941692, 'overall_accuracy': 0.538049576660206}
			------------EPOCH 2---------------
Loss:  tensor(1393.6482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1482.6058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1247.4581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1511.2615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2189.3369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2257.3071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(973.6187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1462.8151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1723.5098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1484.4382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1953.9336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2200.5635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1771.0590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1894.1315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(983.9766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1330.7644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1014.6713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1189.0227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1514.8340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2222.4893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.9683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1560.9874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1542.3750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1534.7177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(927.6829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2065.1213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1257.3447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1401.7905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(859.9379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1089.5366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1112.8833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(858.3514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1600.4368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(830.7379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.5553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(994.6075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(846.9305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(585.2851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1165.2046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2884.3789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2118.7771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1208.8401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.9933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1984.0389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1883.3152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1548.4866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.8690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.1417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(560.3119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1742.9978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1883.5095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(913.0580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1093.9014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1363.8583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(845.0260, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.05454545454545454, 'recall': 0.05, 'f1': 0.05217391304347826, 'number': 360}, 'P': {'precision': 0.014492753623188406, 'recall': 0.009280742459396751, 'f1': 0.011315417256011314, 'number': 431}, 'overall_precision': 0.036303630363036306, 'overall_recall': 0.02781289506953224, 'overall_f1': 0.031496062992125984, 'overall_accuracy': 0.5625828827909823}
			------------EPOCH 3---------------
Loss:  tensor(1178.5654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1307.8726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1066.2556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1322.7666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1893.2975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1939.4777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.1925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1182.1667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1422.8978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.2095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1771.7893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1884.4270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1558.6482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1717.2898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(884.2629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1179.3511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(837.8565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1057.1530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1299.6115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1911.2455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.1489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1280.2224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1270.8236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1360.6379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(745.8754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1835.6875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1073.0603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1221.5173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(744.5907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(934.8984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.1952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.2084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1306.2461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.1775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.1410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(799.9310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(662.4351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.1451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(963.1116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2614.6807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1764.1713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.8485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.4996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1691.8954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1598.9653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1186.8271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(922.5601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(682.4702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.0701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1439.8461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1486.2600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.8259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.0125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(902.3002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(697.6083, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13609467455621302, 'recall': 0.12777777777777777, 'f1': 0.1318051575931232, 'number': 360}, 'P': {'precision': 0.12460063897763578, 'recall': 0.09048723897911833, 'f1': 0.10483870967741936, 'number': 431}, 'overall_precision': 0.130568356374808, 'overall_recall': 0.10745891276864729, 'overall_f1': 0.11789181692094314, 'overall_accuracy': 0.5970111190451902}
			------------EPOCH 4---------------
Loss:  tensor(991.1362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1062.7563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.2025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1091.4806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1546.5568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1573.0977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.9462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(900.5334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.3104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(932.4320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1441.1996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1426.8370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1183.0295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1389.6858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(776.9703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.2462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(688.0964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(861.5999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1048.4307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1533.4539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.7678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1006.2430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(960.8547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1146.4840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.0909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1472.5149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(899.4121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1020.1403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.4022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(806.9990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(585.6331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.2188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.2191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.7786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.6818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(624.5117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.3466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.9114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.6296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2223.6934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1309.9463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.4177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.3983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1447.9337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1362.7229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(916.4045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.7043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.9503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.7166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1187.2545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1180.8184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.4693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.0637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.1707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.6508, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1619047619047619, 'recall': 0.14166666666666666, 'f1': 0.15111111111111108, 'number': 360}, 'P': {'precision': 0.18604651162790697, 'recall': 0.14849187935034802, 'f1': 0.16516129032258065, 'number': 431}, 'overall_precision': 0.17450682852807284, 'overall_recall': 0.14538558786346398, 'overall_f1': 0.15862068965517243, 'overall_accuracy': 0.5981332245231051}
			------------EPOCH 5---------------
Loss:  tensor(786.1411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.3364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.6958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(906.7414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1316.8378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1287.5752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(506.6197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.2224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.2695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(737.3459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1178.9767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(939.3009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(869.5867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1113.5801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.9707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.1813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(533.8700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(721.4857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.5076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1211.0662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.6488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(698.0583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(788.1012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.3073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.7393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1233.9341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(707.8528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(856.0592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.5436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(613.1649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.0549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.9117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(765.7887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(521.1368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.7930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.1172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.0451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.3701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.9755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1849.8593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(926.4432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(692.1437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.9021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1148.1190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1057.1036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(733.1058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.3904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.0862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.8362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(945.0693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(982.8695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.0580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.4624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.0498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.8197, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17681728880157171, 'recall': 0.25, 'f1': 0.20713463751438435, 'number': 360}, 'P': {'precision': 0.3590733590733591, 'recall': 0.21577726218097448, 'f1': 0.26956521739130435, 'number': 431}, 'overall_precision': 0.23828125, 'overall_recall': 0.23135271807838179, 'overall_f1': 0.23476587556125722, 'overall_accuracy': 0.568346424563909}
			------------EPOCH 6---------------
Loss:  tensor(809.7516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(825.9965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.5512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(883.8732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.1836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1160.3081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.4949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.5115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.9248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.5547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.3087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(659.4944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.7305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(913.3872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.1758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.0554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.7138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.3683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(735.2324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1189.0483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.6096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(597.8430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(726.8212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.5831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.0208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1229.0762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(714.1647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(741.3337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.0536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.3403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.5230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.5095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(569.9196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.0907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.1935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.0938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.4745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.8323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.0515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2063.8237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1080.4646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(634.9502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.4354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1169.5441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.4141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.1110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.7812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.0118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.7183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1142.1420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1134.2242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.5511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.8672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.8812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.9124, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15873015873015872, 'recall': 0.3055555555555556, 'f1': 0.20892687559354228, 'number': 360}, 'P': {'precision': 0.15789473684210525, 'recall': 0.02088167053364269, 'f1': 0.03688524590163934, 'number': 431}, 'overall_precision': 0.15866666666666668, 'overall_recall': 0.1504424778761062, 'overall_f1': 0.15444516547696302, 'overall_accuracy': 0.4295623788636132}
			------------EPOCH 7---------------
Loss:  tensor(696.8331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(817.6125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.5901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(934.3324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1435.5576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1617.8584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.9056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(865.8598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(793.8041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(825.3908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1053.0471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1059.9929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.4033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.5021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.6341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(613.5610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.4395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(534.3585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.1147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1014.1658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.0769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.7771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(726.6836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(835.0385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.4621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1145.6719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(813.6591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.8864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.8157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.1875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.4396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.8903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.8218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.2894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.8929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.7236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.7554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.4953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(483.7527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2288.6094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.5326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(578.8857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.4351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1159.6866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1040.6165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.8755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.9907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.6017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.7802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1002.6924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1024.5441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.8572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.3013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(450.4303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.7511, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1987704918032787, 'recall': 0.26944444444444443, 'f1': 0.22877358490566035, 'number': 360}, 'P': {'precision': 0.3416666666666667, 'recall': 0.2853828306264501, 'f1': 0.3109987357774968, 'number': 431}, 'overall_precision': 0.25943396226415094, 'overall_recall': 0.2781289506953224, 'overall_f1': 0.2684563758389262, 'overall_accuracy': 0.5754360909925533}
			------------EPOCH 8---------------
Loss:  tensor(852.3823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.2297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(590.5175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.2433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1111.5754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1275.4413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.6521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.0848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.0240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(831.5997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1312.1210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1757.6650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.8306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1239.4871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(697.6866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1022.8452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(504.7891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.3099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(936.4733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1237.1072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.6183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.2269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.7280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(624.5086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.3194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(877.2137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.5745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.9095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.1368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.5506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.9019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.4933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(583.4537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.2940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.0216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.6420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.8246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.0866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.6268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1508.7410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(943.1316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.9836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.2515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1113.6865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1222.7415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(661.6649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.8071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(697.8655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.4811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(939.3426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(988.7772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.4945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.4473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(568.9022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.7324, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4166666666666667, 'recall': 0.08333333333333333, 'f1': 0.1388888888888889, 'number': 360}, 'P': {'precision': 0.2532467532467532, 'recall': 0.3619489559164733, 'f1': 0.2979942693409742, 'number': 431}, 'overall_precision': 0.2703488372093023, 'overall_recall': 0.23514538558786346, 'overall_f1': 0.2515212981744422, 'overall_accuracy': 0.601805569723554}
			------------EPOCH 9---------------
Loss:  tensor(987.0679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.0118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1216.6832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(943.8887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1689.6948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1592.1970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.7613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.1069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.2427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.0264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.8243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(855.9146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.7866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(719.1123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.0916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.4414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(412.5466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.9726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(654.4531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(964.8403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.6739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.4382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.8164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(894.1409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.8379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1426.5354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.1920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.1278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(700.2712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(694.5600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.5370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.8871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1095.4778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.5840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.0651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.4824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.8387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.3409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(536.1328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1838.5217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(807.2537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.8654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.9641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1098.1970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(865.0854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.4355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.9721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.4776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.7822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(673.6223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.3203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.7042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.4935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.0943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.5869, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3836477987421384, 'recall': 0.16944444444444445, 'f1': 0.23506743737957614, 'number': 360}, 'P': {'precision': 0.2748735244519393, 'recall': 0.37819025522041766, 'f1': 0.318359375, 'number': 431}, 'overall_precision': 0.2978723404255319, 'overall_recall': 0.2831858407079646, 'overall_f1': 0.2903434867141931, 'overall_accuracy': 0.6207283484647557}
			------------EPOCH 10---------------
Loss:  tensor(473.5729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.3342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.1592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.5364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1154.1755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1004.6852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.8043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.9291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(468.5997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.6594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.1661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(759.1056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(870.0732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1141.9000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.6486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(641.4904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.7220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.0942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1264.1139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.0582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.8536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.3208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(560.6560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.0426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(751.7245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.3495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.9721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.8392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.9844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.7106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.0625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.2727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.9645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.9325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.5005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.5439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.6004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.4632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1357.5637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.0626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.9687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.5171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(874.4037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.2128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(761.2107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.6615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.7067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.9890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.4681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(659.6632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.5439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.9878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.8931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.3691, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21252796420581654, 'recall': 0.2638888888888889, 'f1': 0.23543990086741015, 'number': 360}, 'P': {'precision': 0.28463476070528965, 'recall': 0.26218097447795824, 'f1': 0.27294685990338163, 'number': 431}, 'overall_precision': 0.24644549763033174, 'overall_recall': 0.2629582806573957, 'overall_f1': 0.25443425076452597, 'overall_accuracy': 0.6289401203713149}
			------------EPOCH 11---------------
Loss:  tensor(291.2667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.5014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.5560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.8624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(712.7202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.8756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.4351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.9730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.5873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.9229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.6161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.0876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.4016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.6160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.3961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.3485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.6200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.6997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.4556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(733.5421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.8858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.6493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(576.3825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(491.1166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.6734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.2386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(419.3730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.0693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.5858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.8640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.2853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.9421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.5322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.8172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.2776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.3824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.4352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.8441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.9608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1081.2002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.0464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.8461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.2131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.3397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.3273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.5333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.2283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.6247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.2713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.0814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.9298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.0646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.2825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.8001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.4454, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2768595041322314, 'recall': 0.18611111111111112, 'f1': 0.22259136212624586, 'number': 360}, 'P': {'precision': 0.1515650741350906, 'recall': 0.21345707656612528, 'f1': 0.1772639691714836, 'number': 431}, 'overall_precision': 0.1872791519434629, 'overall_recall': 0.20101137800252844, 'overall_f1': 0.19390243902439022, 'overall_accuracy': 0.6491380189737835}
			------------EPOCH 12---------------
Loss:  tensor(268.9985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.5533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.7180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.2041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(645.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.8284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.3895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.4969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.1448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.9176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.4734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.0886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.3272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(404.2826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.3610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.2467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.6360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.4944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.4546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.5621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.0121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.8937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.9742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.6178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.3363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(506.8461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.2310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.5890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.5977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.3855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.8739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.5558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.6131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.5090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.4473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.8442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.5200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.7991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.1794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(793.3085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.2797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.5685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.4649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.0486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.5069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.0977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.9828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.7561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.0804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.8761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.5010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.3171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.3552, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29245283018867924, 'recall': 0.25833333333333336, 'f1': 0.27433628318584075, 'number': 360}, 'P': {'precision': 0.2972972972972973, 'recall': 0.33178654292343385, 'f1': 0.31359649122807015, 'number': 431}, 'overall_precision': 0.295369211514393, 'overall_recall': 0.29835651074589126, 'overall_f1': 0.2968553459119497, 'overall_accuracy': 0.6333775374885239}
			------------EPOCH 13---------------
Loss:  tensor(199.6964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.9441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.1349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.7760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.3681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(521.9813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.5062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.8382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.3220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.8356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.3297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.6352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.0149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.0723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.9022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.4758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.5435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.6817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.2829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.3728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.9153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.9798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.2780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.8912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.2730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.9230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.0402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.5364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.4100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.9977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.6644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.2216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.9960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.5693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.1900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.7254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.7977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.9978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.9468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.7262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.5863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.7691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.0403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.7645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.1339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.5897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.9565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.6612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.9761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.2243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.5598, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2537313432835821, 'recall': 0.2361111111111111, 'f1': 0.24460431654676257, 'number': 360}, 'P': {'precision': 0.23232323232323232, 'recall': 0.2668213457076566, 'f1': 0.24838012958963282, 'number': 431}, 'overall_precision': 0.24096385542168675, 'overall_recall': 0.2528445006321112, 'overall_f1': 0.24676125848241823, 'overall_accuracy': 0.6516882586963174}
			------------EPOCH 14---------------
Loss:  tensor(124.4149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.6808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.1278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.6072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.7584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.2875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.3304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.6943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.6693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.1884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.6324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.4728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.1557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.5347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.5893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.3230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.9643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.3882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.5575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.8937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.7715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.6132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.1930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.5148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.8032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.5299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.7895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.6636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.8033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.7135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.4762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.8236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.1383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.5567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.8296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.6595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.3568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.7370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.0188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.2435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.3908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.7160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.2518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.8236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.5298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.7634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.2433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.5995, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2727272727272727, 'recall': 0.25, 'f1': 0.2608695652173913, 'number': 360}, 'P': {'precision': 0.22445255474452555, 'recall': 0.2853828306264501, 'f1': 0.2512768130745659, 'number': 431}, 'overall_precision': 0.24259681093394078, 'overall_recall': 0.2692793931731985, 'overall_f1': 0.2552426602756141, 'overall_accuracy': 0.6475058655513618}
			------------EPOCH 15---------------
Loss:  tensor(91.8915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.2656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.1618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.1772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.0257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.1751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.3805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.8747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.6204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.6546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.8564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.4314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.2356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.4665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.5392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.1947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.3435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.7809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.7156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.4336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.7505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.3788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.9686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.9538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.7453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.1739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.2713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.7927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.7868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.4890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.3638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.3298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.1087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.9336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.7270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.5727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.7281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.6097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.3248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.0527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.4843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.2795, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26176470588235295, 'recall': 0.24722222222222223, 'f1': 0.25428571428571434, 'number': 360}, 'P': {'precision': 0.28063241106719367, 'recall': 0.3294663573085847, 'f1': 0.3030949839914621, 'number': 431}, 'overall_precision': 0.2730496453900709, 'overall_recall': 0.2920353982300885, 'overall_f1': 0.2822235797189982, 'overall_accuracy': 0.6506681628073039}
			------------EPOCH 16---------------
Loss:  tensor(72.7897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.1087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.0185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.2673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.5681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.1782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.5226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.1468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.7422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.8867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.7365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.0887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.0480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.0612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.3552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.9841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.7826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.2311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.6525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.9341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.5876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.8281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.2144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.0446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.9949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.0496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.4780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.7350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.5484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.3270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.5528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.8799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.4835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.9975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.6470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.6303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.0545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2654, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2216624685138539, 'recall': 0.24444444444444444, 'f1': 0.23249669749009247, 'number': 360}, 'P': {'precision': 0.20816326530612245, 'recall': 0.23665893271461716, 'f1': 0.22149837133550487, 'number': 431}, 'overall_precision': 0.21420518602029312, 'overall_recall': 0.2402022756005057, 'overall_f1': 0.22646007151370678, 'overall_accuracy': 0.652402325818627}
			------------EPOCH 17---------------
Loss:  tensor(53.9906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.1259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.0345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.6144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.1899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.0859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.8794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.0757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.8597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.5130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.4463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.2909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.1399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.7948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.1325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.6458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.9548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.5333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.9316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.1068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.2480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.9895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.2304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.5611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.9643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.4283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.1435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.1856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.5960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.9305, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25705329153605017, 'recall': 0.22777777777777777, 'f1': 0.24153166421207659, 'number': 360}, 'P': {'precision': 0.2565905096660808, 'recall': 0.33874709976798145, 'f1': 0.292, 'number': 431}, 'overall_precision': 0.25675675675675674, 'overall_recall': 0.28824273072060685, 'overall_f1': 0.2715902322811197, 'overall_accuracy': 0.6510762011629093}
			------------EPOCH 18---------------
Loss:  tensor(48.5890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.7924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.1513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.5951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.0399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.9526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.6174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.1403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.6156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.9975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.3964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.3657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.9462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.4047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.1984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.0495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.4178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.1824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.7769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.5174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.8583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5617, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2409972299168975, 'recall': 0.24166666666666667, 'f1': 0.24133148404993066, 'number': 360}, 'P': {'precision': 0.2613861386138614, 'recall': 0.3062645011600928, 'f1': 0.282051282051282, 'number': 431}, 'overall_precision': 0.2528868360277136, 'overall_recall': 0.27686472819216185, 'overall_f1': 0.26433313216656606, 'overall_accuracy': 0.6520962970519228}
			------------EPOCH 19---------------
Loss:  tensor(35.2065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.0697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.2103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.3987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.7159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.3700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.3204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.9065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.0280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.2848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.3200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.5214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.3907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.0238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.2581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.9597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.9743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.0713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.8234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.1794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.8463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.0118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.1952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.3234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1306, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22113022113022113, 'recall': 0.25, 'f1': 0.23468057366362452, 'number': 360}, 'P': {'precision': 0.23694779116465864, 'recall': 0.2737819025522042, 'f1': 0.25403659849300325, 'number': 431}, 'overall_precision': 0.22983425414364642, 'overall_recall': 0.2629582806573957, 'overall_f1': 0.2452830188679245, 'overall_accuracy': 0.652555340201979}
			------------EPOCH 20---------------
Loss:  tensor(23.3805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.5721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.6594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.1123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.2318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.1420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.3754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.6763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.3760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.8503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.7128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.2963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.1513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.3197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.9554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.4415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.6450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.6580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.2571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.5195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.0503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.1862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.1109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.8094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8339, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2389937106918239, 'recall': 0.2111111111111111, 'f1': 0.22418879056047197, 'number': 360}, 'P': {'precision': 0.19732441471571907, 'recall': 0.2737819025522042, 'f1': 0.2293488824101069, 'number': 431}, 'overall_precision': 0.21179039301310043, 'overall_recall': 0.24525916561314792, 'overall_f1': 0.22729935559461042, 'overall_accuracy': 0.6425073956951953}
			------------EPOCH 21---------------
Loss:  tensor(22.6583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.1950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.1560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.2933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.2194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.0449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.8362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.6569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.8875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.9952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.4293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.1686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.4669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.3366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.4849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.1543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.2056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.4802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.6783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.1949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.6160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.8272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.4105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.0166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0729, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2340966921119593, 'recall': 0.25555555555555554, 'f1': 0.24435590969455515, 'number': 360}, 'P': {'precision': 0.28778467908902694, 'recall': 0.3225058004640371, 'f1': 0.3041575492341357, 'number': 431}, 'overall_precision': 0.2636986301369863, 'overall_recall': 0.2920353982300885, 'overall_f1': 0.27714457108578283, 'overall_accuracy': 0.651280220340712}
			------------EPOCH 22---------------
Loss:  tensor(19.6661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.9327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.9661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.3923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.9034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.2663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.9197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.2784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.9497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.0743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.5359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.3721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.3128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.4504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.6371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.8549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.0698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.8096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.4106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.3482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.2919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9059, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21103117505995203, 'recall': 0.24444444444444444, 'f1': 0.22651222651222652, 'number': 360}, 'P': {'precision': 0.1867704280155642, 'recall': 0.22273781902552203, 'f1': 0.20317460317460317, 'number': 431}, 'overall_precision': 0.19763694951664876, 'overall_recall': 0.23261694058154236, 'overall_f1': 0.21370499419279904, 'overall_accuracy': 0.6458737121289401}
			------------EPOCH 23---------------
Loss:  tensor(14.7901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.9729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.5892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.6407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.5662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.3207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.6833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.3441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.2142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.3817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.2975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.2546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.1075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.6847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.0435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.1189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.0281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.0976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.7472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.9908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.1865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.3903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8978, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25227963525835867, 'recall': 0.23055555555555557, 'f1': 0.2409288824383164, 'number': 360}, 'P': {'precision': 0.2802303262955854, 'recall': 0.33874709976798145, 'f1': 0.3067226890756303, 'number': 431}, 'overall_precision': 0.26941176470588235, 'overall_recall': 0.2895069532237674, 'overall_f1': 0.2790981109079829, 'overall_accuracy': 0.6532694073242885}
			------------EPOCH 24---------------
Loss:  tensor(12.5236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.8346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.4366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.2051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.1370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.8594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.1906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.4749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.6814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.5534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.8661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.8392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.6448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.6549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.7322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.7346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.9705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.7314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.0703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.2925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.2225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5349, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20745920745920746, 'recall': 0.24722222222222223, 'f1': 0.2256020278833967, 'number': 360}, 'P': {'precision': 0.2140077821011673, 'recall': 0.2552204176334107, 'f1': 0.23280423280423282, 'number': 431}, 'overall_precision': 0.2110286320254507, 'overall_recall': 0.2515802781289507, 'overall_f1': 0.22952710495963088, 'overall_accuracy': 0.645720697745588}
			------------EPOCH 25---------------
Loss:  tensor(9.0414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.0965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.9297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.6299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.2185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.4932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.5492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.7229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.4679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.6775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.8850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.7643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.2413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.8428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.4051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2849, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23848238482384823, 'recall': 0.24444444444444444, 'f1': 0.24142661179698216, 'number': 360}, 'P': {'precision': 0.26862745098039215, 'recall': 0.31786542923433875, 'f1': 0.2911795961742827, 'number': 431}, 'overall_precision': 0.25597269624573377, 'overall_recall': 0.28445006321112515, 'overall_f1': 0.26946107784431134, 'overall_accuracy': 0.6547995511578089}
			------------EPOCH 26---------------
Loss:  tensor(7.7022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.3485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.4321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.6807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.5184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.3349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.6024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.3908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.3998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.7165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.1958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.0314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.6705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.3243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.0708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.6869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.8769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.0154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.6528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3163, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2459016393442623, 'recall': 0.25, 'f1': 0.24793388429752067, 'number': 360}, 'P': {'precision': 0.2379182156133829, 'recall': 0.29698375870069604, 'f1': 0.26418988648090813, 'number': 431}, 'overall_precision': 0.2411504424778761, 'overall_recall': 0.27560050568900124, 'overall_f1': 0.25722713864306784, 'overall_accuracy': 0.6549525655411609}
			------------EPOCH 27---------------
Loss:  tensor(6.6931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.0202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.7513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.1402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.8148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.1068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.3110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.4788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.6717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.9780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.2365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.9208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.6513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.3149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.4845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.4314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.8315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9086, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2158273381294964, 'recall': 0.25, 'f1': 0.23166023166023164, 'number': 360}, 'P': {'precision': 0.2375249500998004, 'recall': 0.27610208816705334, 'f1': 0.2553648068669528, 'number': 431}, 'overall_precision': 0.22766884531590414, 'overall_recall': 0.26422250316055623, 'overall_f1': 0.24458747805734346, 'overall_accuracy': 0.6452106498010813}
			------------EPOCH 28---------------
Loss:  tensor(5.3673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.2434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.4006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.8096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.8779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.3195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.0853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.6562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.1544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.5615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.9432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.1832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.2499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.3440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.2276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.7904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.6555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.5586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7729, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26239067055393583, 'recall': 0.25, 'f1': 0.25604551920341395, 'number': 360}, 'P': {'precision': 0.29981378026070765, 'recall': 0.37354988399071926, 'f1': 0.33264462809917356, 'number': 431}, 'overall_precision': 0.2852272727272727, 'overall_recall': 0.3173198482932996, 'overall_f1': 0.3004189108318372, 'overall_accuracy': 0.6572987860858921}
			------------EPOCH 29---------------
Loss:  tensor(5.9218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.1410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.6115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.3537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.3330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.1081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.1860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.1693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.0273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.9621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.9961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.4706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.1145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.0001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.6769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.5912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.8332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.1554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.6657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.4825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1473, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21014492753623187, 'recall': 0.24166666666666667, 'f1': 0.22480620155038758, 'number': 360}, 'P': {'precision': 0.1833976833976834, 'recall': 0.22041763341067286, 'f1': 0.20021074815595363, 'number': 431}, 'overall_precision': 0.19527896995708155, 'overall_recall': 0.23008849557522124, 'overall_f1': 0.21125943122460825, 'overall_accuracy': 0.6428644292563501}
			------------EPOCH 30---------------
Loss:  tensor(5.1039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.5587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.7192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.0129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.9691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.9219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.4128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.7798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.5092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.3746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.9805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.5681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.0506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.2509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.6693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8390, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24675324675324675, 'recall': 0.2638888888888889, 'f1': 0.25503355704697983, 'number': 360}, 'P': {'precision': 0.25142857142857145, 'recall': 0.3062645011600928, 'f1': 0.2761506276150628, 'number': 431}, 'overall_precision': 0.24945054945054945, 'overall_recall': 0.28697850821744625, 'overall_f1': 0.266901822457378, 'overall_accuracy': 0.6485769662348261}


		-------------RUN 4-----------
Test files: ['/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/95.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/94.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/29.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/261.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/76.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/77.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/291.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/86.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/220.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/66.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/247.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/70.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/32.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/11.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/12.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/309.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/92.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/91.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/93.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/251.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/73.xml']
			------------EPOCH 1---------------
Loss:  tensor(2157.2378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1954.1464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1983.3035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2308.6289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3467.3965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1957.7061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1405.3744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2879.1528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1356.4501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2026.6714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(758.9438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1234.7517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1598.0780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2006.5454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2756.0840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3341.0269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2926.5256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2418.0974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1685.5098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1641.7910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3049.1306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2091.2773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.5076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(925.7340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2406.0303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2788.2744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2790.9458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2768.7097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2651.9126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3123.1443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2221.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1651.8862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2633.4487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2802.1882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3561.9287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2651.6670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2850.5566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2245.8389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1983.1440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2321.6099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.8354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2487.1729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1426.0566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1974.0757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2260.2925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1868.3866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1329.9917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1075.4128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.8325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(874.0645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1378.5181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1763.9944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1870.0988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1111.7731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1933.1360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1804.5078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1388.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1144.2137, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.04, 'recall': 0.07755102040816327, 'f1': 0.05277777777777778, 'number': 245}, 'P': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 372}, 'overall_precision': 0.04, 'overall_recall': 0.03079416531604538, 'overall_f1': 0.0347985347985348, 'overall_accuracy': 0.36363636363636365}
			------------EPOCH 2---------------
Loss:  tensor(1724.3181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1476.4344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1367.2853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1680.3756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2669.7791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1202.4846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(964.9914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2040.5146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1121.5896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1809.3999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(655.2921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(950.5221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1309.4399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1688.5317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2250.5017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2757.4707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2331.9668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2275.8184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1270.4440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1317.1816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2672.2549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1693.9248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.6809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(777.4069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1999.2664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2325.3599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2411.2722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2563.1318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2108.8823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2371.9482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1866.0812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1411.4331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2322.2388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2496.9937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3238.4595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2436.6045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2693.0298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1930.8604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1630.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1986.5969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.9979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2089.4106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1122.0596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1618.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1973.1533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1608.0823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1112.8142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(901.4664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(841.4969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.2377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1203.4014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1529.9072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1610.5710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(931.4182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1647.1321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1501.5837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1075.8848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(908.2770, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.06395348837209303, 'recall': 0.1346938775510204, 'f1': 0.08672798948751644, 'number': 245}, 'P': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 372}, 'overall_precision': 0.06395348837209303, 'overall_recall': 0.05348460291734198, 'overall_f1': 0.05825242718446602, 'overall_accuracy': 0.36464199517296864}
			------------EPOCH 3---------------
Loss:  tensor(1519.8629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1287.4086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1168.9995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1466.8962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2257.1248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(999.6240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(814.0974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1851.4509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1009.4590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1619.3552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.1803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.5312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1147.9675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1430.3851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1978.4637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2299.9536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1694.9656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1957.6038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1043.8723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1111.2747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2334.8188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1127.9919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(761.3904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(627.2305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1672.2815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1875.7317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2134.8721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2130.2498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1810.2288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2086.8423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1556.9136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1197.6027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1903.2185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2076.2686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2809.2974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2055.4302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2357.6123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1606.6389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1284.9436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1524.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(682.0801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1745.3306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(788.0809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1255.3906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1744.4305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1310.3440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(855.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.3840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.6705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.1058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1029.1191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1237.3173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1393.0317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.0607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1307.1624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(963.9894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.6969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.9694, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.08086785009861933, 'recall': 0.1673469387755102, 'f1': 0.10904255319148937, 'number': 245}, 'P': {'precision': 0.1875, 'recall': 0.04032258064516129, 'f1': 0.06637168141592921, 'number': 372}, 'overall_precision': 0.09540034071550256, 'overall_recall': 0.09076175040518639, 'overall_f1': 0.0930232558139535, 'overall_accuracy': 0.45092518101367657}
			------------EPOCH 4---------------
Loss:  tensor(1026.5985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(911.1388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(891.2482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1147.9750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1833.6615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(753.7097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(578.2398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1448.5619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(805.6980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1308.7440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.6695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(698.2699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(948.6123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1147.2179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1563.6893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1946.0913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1287.7976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1473.6021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(799.8216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(860.5079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1824.9987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(733.9764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.5699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.2177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1195.7706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1340.4718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1644.5068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1747.1637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1389.0112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1544.0417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1263.4232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(969.8684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1632.3745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1897.4967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2504.9456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1869.2517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2002.9465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.4711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(948.3802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1001.0917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.9663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1498.7742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.5656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.8940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1422.4114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1176.1024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.3599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(474.1865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.9076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.7445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(977.1179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.9707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1306.1465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(549.4789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1158.1931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(707.2081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.2184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.7894, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14538310412573674, 'recall': 0.3020408163265306, 'f1': 0.1962864721485411, 'number': 245}, 'P': {'precision': 0.20930232558139536, 'recall': 0.07258064516129033, 'f1': 0.10778443113772455, 'number': 372}, 'overall_precision': 0.15830721003134796, 'overall_recall': 0.16369529983792544, 'overall_f1': 0.16095617529880477, 'overall_accuracy': 0.4627245910431751}
			------------EPOCH 5---------------
Loss:  tensor(1003.2261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(897.6090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.0161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(971.3223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1615.0605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.2739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.2748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1317.7155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.1995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1244.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.4891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.0050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(791.9514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(899.7678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1350.9060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1664.8435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(992.4145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1235.4849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.8595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.6287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1517.3381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.1219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.3010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.3668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(866.4894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1017.6974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1365.2634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1578.0233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1239.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1459.7529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1331.7943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.4114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1376.6509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1479.7107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2175.9604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1499.6887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1365.1189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(996.5027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(835.7201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(758.8355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.0428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1440.2722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(491.2072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(748.2271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1264.7778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.8620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.6107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.2751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(389.2123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.8200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.8883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.4725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1103.6465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.5818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(742.3389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.6388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.4367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.2539, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14031620553359683, 'recall': 0.2897959183673469, 'f1': 0.18908122503328892, 'number': 245}, 'P': {'precision': 0.3233082706766917, 'recall': 0.11559139784946236, 'f1': 0.17029702970297028, 'number': 372}, 'overall_precision': 0.1784037558685446, 'overall_recall': 0.1847649918962723, 'overall_f1': 0.18152866242038218, 'overall_accuracy': 0.4906811477607938}
			------------EPOCH 6---------------
Loss:  tensor(888.1781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.9399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.0428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(802.6395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1809.1313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.8702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.1624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(971.3088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(750.5625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.3507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.9869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.9371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.0566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(913.7432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1159.9827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1862.6523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1034.9692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.4299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.2250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.9860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1140.4077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(481.0334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.2100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.8025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.9020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(820.7722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.8395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1431.5833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1189.7838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1434.3601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1266.2972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(848.9518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1265.4253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1259.8523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2021.8075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1336.4329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1686.3340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(995.9030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.2450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.7964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.0240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1313.4170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.5995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.7229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(922.1080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(807.9417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.7402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.8857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.6074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.7209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.4174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.5020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(915.1283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.8840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(616.0347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.8253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.7738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.7627, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14925373134328357, 'recall': 0.3673469387755102, 'f1': 0.21226415094339623, 'number': 245}, 'P': {'precision': 0.05, 'recall': 0.013440860215053764, 'f1': 0.0211864406779661, 'number': 372}, 'overall_precision': 0.13513513513513514, 'overall_recall': 0.1539708265802269, 'overall_f1': 0.14393939393939392, 'overall_accuracy': 0.43295789755966746}
			------------EPOCH 7---------------
Loss:  tensor(688.5959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.2374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.7805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.5715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1356.2812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.1903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.5999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.8364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(569.4434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1108.2812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.7648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.0657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.5821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(842.6451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1121.6390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1641.8425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(900.4774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1195.8784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.5006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.6895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1093.2528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.2484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.7338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.3031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.2935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(752.9064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.6631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1219.7291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(911.1086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1242.9365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(926.0890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.2958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.3312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(851.9712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1332.6455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(946.5250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.6973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.9349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.0244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.7877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.0637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1079.6016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.3190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.0518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1004.5183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.3531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.5424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.4796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.2312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.5401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1045.6724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1246.8672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1339.9519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.7229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(899.7740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.4743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.6591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.5137, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15441176470588236, 'recall': 0.17142857142857143, 'f1': 0.16247582205029013, 'number': 245}, 'P': {'precision': 0.0735632183908046, 'recall': 0.08602150537634409, 'f1': 0.07930607187112763, 'number': 372}, 'overall_precision': 0.10466760961810467, 'overall_recall': 0.11993517017828201, 'overall_f1': 0.11178247734138973, 'overall_accuracy': 0.5699249128452668}
			------------EPOCH 8---------------
Loss:  tensor(594.8055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(534.8074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(681.2219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(847.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1034.3787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.3881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.6250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(801.3121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.4201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.2474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.5384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.2411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.6013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(804.6977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1116.3379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.0269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(927.9342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.2694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.1665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.8043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.9638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.6140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.6196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(805.9268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.6715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(890.7659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1189.5242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1444.8732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(981.5950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.1095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1024.8566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(999.9071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1379.4001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1004.9387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(893.3055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(712.5721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.6769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.3590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.3130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.5193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.9612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.8645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.8047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(597.7374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.2059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.4180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.1705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.1452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(767.3019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.5358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(909.7292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.9989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.7709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.2532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.1292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.5446, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16560509554140126, 'recall': 0.10612244897959183, 'f1': 0.12935323383084577, 'number': 245}, 'P': {'precision': 0.06928406466512702, 'recall': 0.08064516129032258, 'f1': 0.07453416149068322, 'number': 372}, 'overall_precision': 0.09491525423728814, 'overall_recall': 0.09076175040518639, 'overall_f1': 0.09279204639602319, 'overall_accuracy': 0.5002681684097613}
			------------EPOCH 9---------------
Loss:  tensor(480.8868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.7145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(742.3918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(742.9016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1196.7892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.6979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.6213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.1199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.8726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(988.7234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.3852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.4896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.1173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.5918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1269.6355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1292.9692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.8019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(880.9382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.5280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.2043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.0537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.8719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.0061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.0511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.6013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.2269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.9489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(985.5449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.6188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(828.6213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.1008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.5663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.5917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.2516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.6964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.7012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.6240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.2919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.5037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.7205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.6734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.6147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.3105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.5295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(758.6049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.2373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.4673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.6382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.0874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.7139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.3906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.7748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.5187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.4023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.3745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.7758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.3400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.5233, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1889168765743073, 'recall': 0.30612244897959184, 'f1': 0.2336448598130841, 'number': 245}, 'P': {'precision': 0.17857142857142858, 'recall': 0.21505376344086022, 'f1': 0.1951219512195122, 'number': 372}, 'overall_precision': 0.1834319526627219, 'overall_recall': 0.25121555915721233, 'overall_f1': 0.21203830369357046, 'overall_accuracy': 0.6297264682220435}
			------------EPOCH 10---------------
Loss:  tensor(393.1423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.5142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.3383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.3418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1303.0806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.3258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.6018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.9135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.5519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.5689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.0612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.8391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.4741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.9179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.4202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(900.3773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(700.0937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.8026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.5965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.2669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1465.4839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(533.1314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.4530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.6984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.6469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.6772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(759.8862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1441.4797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.4980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(782.6716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(742.7059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.6370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.2046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.1383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(918.9514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.4142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.3386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.2158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.8365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.6432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.1747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(585.3144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.2932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.7473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.7400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(586.3441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.9139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.2759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.3234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(876.9717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(796.7939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1213.7229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.4536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.9339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(793.6179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.9728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.9378, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2430939226519337, 'recall': 0.17959183673469387, 'f1': 0.20657276995305163, 'number': 245}, 'P': {'precision': 0.1487603305785124, 'recall': 0.24193548387096775, 'f1': 0.1842374616171955, 'number': 372}, 'overall_precision': 0.17048346055979643, 'overall_recall': 0.2171799027552674, 'overall_f1': 0.1910192444761226, 'overall_accuracy': 0.6430008045052292}
			------------EPOCH 11---------------
Loss:  tensor(419.0672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.7845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(602.0789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(965.6008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1154.2344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.0465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.6375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.1615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.8989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.7758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.2135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.9610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.7292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.8888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.4926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.8757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.7902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.6998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.0351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.4635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(739.3901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.5957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.1225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.2679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(733.5122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1380.3669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1084.0482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1202.6826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1183.9160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.7405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(603.6102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.7208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.7626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1149.8422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.5566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.5707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(534.3524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(525.5749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.2546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.2799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.8263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.6018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.6673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.6726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.0359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.1602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.2728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.5878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.1865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.0587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.1830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.2852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.9811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.9144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.7775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.0656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.7269, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26143790849673204, 'recall': 0.16326530612244897, 'f1': 0.20100502512562812, 'number': 245}, 'P': {'precision': 0.14206128133704735, 'recall': 0.27419354838709675, 'f1': 0.1871559633027523, 'number': 372}, 'overall_precision': 0.16303099885189437, 'overall_recall': 0.23014586709886548, 'overall_f1': 0.19086021505376347, 'overall_accuracy': 0.6430678466076696}
			------------EPOCH 12---------------
Loss:  tensor(252.4697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.8239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.7245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.9879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1817.0817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.2812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.6632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.3242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(946.1611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(900.2894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.3185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(939.1187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(830.5045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1150.6967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2325.2617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2184.3169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.9427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1229.2986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(536.3005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.9728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(773.8845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.6248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.9601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.0551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.1669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.9025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.3575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(873.1559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(572.3660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.8589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(534.8290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.1674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.3693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.6805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1027.5732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.5400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.7523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.5863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.8594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.1148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.8190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1522.5264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.7500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(576.2294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1044.2454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(858.3531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.2265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.4729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.3934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.9305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.3489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.5575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(734.7178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.9853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(650.0559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.5930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.2596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.5772, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21227621483375958, 'recall': 0.33877551020408164, 'f1': 0.2610062893081761, 'number': 245}, 'P': {'precision': 0.0975, 'recall': 0.10483870967741936, 'f1': 0.10103626943005183, 'number': 372}, 'overall_precision': 0.15423514538558786, 'overall_recall': 0.19773095623987033, 'overall_f1': 0.17329545454545456, 'overall_accuracy': 0.6002949852507374}
			------------EPOCH 13---------------
Loss:  tensor(317.0629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.0938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.8184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.1112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(859.0822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.7791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.6145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.0744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.3362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.4200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.1940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.3907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.9686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.9220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.0305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(718.3318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.3587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.5878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.4201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.8748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.2341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.8651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.4639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.3557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.5059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.5784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(441.4360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(824.9213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.4003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(655.2430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(644.9388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.8883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(568.5688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.6277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1037.7881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.5223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.7377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.7295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.4843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.1157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.8055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.8353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.9005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.7334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.2786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.0444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.3097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.4319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.2352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.5638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.2059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.2072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.3067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.4097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.4063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.8151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.9490, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17674418604651163, 'recall': 0.31020408163265306, 'f1': 0.2251851851851852, 'number': 245}, 'P': {'precision': 0.1, 'recall': 0.11290322580645161, 'f1': 0.10606060606060608, 'number': 372}, 'overall_precision': 0.1388235294117647, 'overall_recall': 0.1912479740680713, 'overall_f1': 0.16087252897068846, 'overall_accuracy': 0.6005631536604988}
			------------EPOCH 14---------------
Loss:  tensor(201.8716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.0114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.9262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.9363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.0212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.9729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.3119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.1403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.0888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.5648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.6799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.1804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.8562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.4432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.6845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.2765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(441.7211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.6313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.7114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.0375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.2853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.8691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.4493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.3049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.7600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.7081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.7186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.1266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.9583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.1101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.9236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.5178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(712.1780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.6843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.2042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.7211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.9207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.5031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.7172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.6799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.6259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.9335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.6070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.5396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.9770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.5504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.3683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.5020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.3111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.0969, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2517482517482518, 'recall': 0.2938775510204082, 'f1': 0.2711864406779661, 'number': 245}, 'P': {'precision': 0.15051546391752577, 'recall': 0.19623655913978494, 'f1': 0.17036172695449242, 'number': 372}, 'overall_precision': 0.1880674448767834, 'overall_recall': 0.23500810372771475, 'overall_f1': 0.20893371757925072, 'overall_accuracy': 0.6783990345937249}
			------------EPOCH 15---------------
Loss:  tensor(119.5502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.2446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.8026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.4296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.7739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.6392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.3998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.2081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.1935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.6445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.9151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.4355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.7312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.4542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.7225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.2434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.9423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.9856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.5708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.9248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.5726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.7424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.2514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.4685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.1464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.4240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.4853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.1723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.0724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(644.9935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.4140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.0530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.4566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.6794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.7488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.7676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.6215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.3877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.5629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.0907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.5718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.9416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.6871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.6391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.1637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.8975, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1989389920424403, 'recall': 0.30612244897959184, 'f1': 0.24115755627009644, 'number': 245}, 'P': {'precision': 0.13580246913580246, 'recall': 0.1478494623655914, 'f1': 0.14157014157014156, 'number': 372}, 'overall_precision': 0.16624040920716113, 'overall_recall': 0.2106969205834684, 'overall_f1': 0.18584703359542531, 'overall_accuracy': 0.6281174577634755}
			------------EPOCH 16---------------
Loss:  tensor(105.9173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.6305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.7794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(560.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.4855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.6224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.6056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.2254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.8547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.4957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.0923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.4490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.4582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.6962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.5784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.0604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.3881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.6783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.8695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.1888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.6125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.5911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.9916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.5602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.8057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.1036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.8523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.9222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.2155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.6611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.2131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.4323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.3175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.3276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.3325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.8982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.0415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.3826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.4495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.1127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.8395, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2347266881028939, 'recall': 0.2979591836734694, 'f1': 0.262589928057554, 'number': 245}, 'P': {'precision': 0.13865546218487396, 'recall': 0.1774193548387097, 'f1': 0.15566037735849056, 'number': 372}, 'overall_precision': 0.17662007623888182, 'overall_recall': 0.2252836304700162, 'overall_f1': 0.19800569800569798, 'overall_accuracy': 0.67135961383749}
			------------EPOCH 17---------------
Loss:  tensor(102.4825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.0351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.2365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.5022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.4030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.9741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.7798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.3549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.1078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.9302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.1786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.4202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(441.6287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.9473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.2284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.3494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.9499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.0881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.1713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.4762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(577.6661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.5158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.3295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.5167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.1947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.8333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.1376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.5342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.9066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.5059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.3251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.5386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.7472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.4567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.9442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.8682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.3013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.8703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.8898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.6992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.9791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.3746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9954, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.207492795389049, 'recall': 0.2938775510204082, 'f1': 0.24324324324324326, 'number': 245}, 'P': {'precision': 0.1546134663341646, 'recall': 0.16666666666666666, 'f1': 0.16041397153945666, 'number': 372}, 'overall_precision': 0.17914438502673796, 'overall_recall': 0.2171799027552674, 'overall_f1': 0.19633699633699636, 'overall_accuracy': 0.6338160364709037}
			------------EPOCH 18---------------
Loss:  tensor(88.2559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.8735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.5787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.8718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.5471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.2830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.3587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.0085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.3357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.9041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.2911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.6129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.7951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.6685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.2698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.6344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.1060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.9843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.1829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.5216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.0782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.4281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.2884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.9517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.6201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.8786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.8336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.4359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.3639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.3370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.3326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.1748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.5894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.3780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.9140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.7464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5404, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23333333333333334, 'recall': 0.2857142857142857, 'f1': 0.25688073394495414, 'number': 245}, 'P': {'precision': 0.13552361396303902, 'recall': 0.1774193548387097, 'f1': 0.15366705471478465, 'number': 372}, 'overall_precision': 0.17280813214739518, 'overall_recall': 0.22042139384116693, 'overall_f1': 0.19373219373219375, 'overall_accuracy': 0.670555108608206}
			------------EPOCH 19---------------
Loss:  tensor(88.7602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.9826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.9144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(461.1567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.5164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.4326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.5849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.8350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.0969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.2405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.5535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.9345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.4961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.5204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.9407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.7610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.2076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.5970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.6325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.3726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.4117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.9530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.8627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(481.4433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.4155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.3206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.2515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.0620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.6800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.7562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.5315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.7295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.6842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6314, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19602272727272727, 'recall': 0.2816326530612245, 'f1': 0.23115577889447236, 'number': 245}, 'P': {'precision': 0.14652956298200515, 'recall': 0.1532258064516129, 'f1': 0.14980289093298294, 'number': 372}, 'overall_precision': 0.1700404858299595, 'overall_recall': 0.20421393841166938, 'overall_f1': 0.18556701030927833, 'overall_accuracy': 0.6243631000268168}
			------------EPOCH 20---------------
Loss:  tensor(78.4698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.2499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.5375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.6727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.8629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.4504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.1735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.9533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.5942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.0524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.0331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.4043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.5952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.2156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.8240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.2676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.6245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.1797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.2930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.6323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.1015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.7858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.2654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.2138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.3535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.6414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7046, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2222222222222222, 'recall': 0.2693877551020408, 'f1': 0.24354243542435425, 'number': 245}, 'P': {'precision': 0.13441955193482688, 'recall': 0.1774193548387097, 'f1': 0.152954808806489, 'number': 372}, 'overall_precision': 0.16751269035532995, 'overall_recall': 0.21393841166936792, 'overall_f1': 0.1879003558718861, 'overall_accuracy': 0.6722982032716546}
			------------EPOCH 21---------------
Loss:  tensor(81.2527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.7702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.3673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.5406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.4841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.0556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.2935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.0889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.4154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.9994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.8586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.3258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.6680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.5681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.4196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.7372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.4860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.7661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.4635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.9913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.1589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.6244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.0968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.3527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.8055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.2685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.4539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.7261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4055, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18206521739130435, 'recall': 0.27346938775510204, 'f1': 0.21859706362153344, 'number': 245}, 'P': {'precision': 0.15803108808290156, 'recall': 0.1639784946236559, 'f1': 0.16094986807387865, 'number': 372}, 'overall_precision': 0.16976127320954906, 'overall_recall': 0.20745542949756887, 'overall_f1': 0.18672501823486506, 'overall_accuracy': 0.6223518369536069}
			------------EPOCH 22---------------
Loss:  tensor(73.9525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.5993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.1100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.9254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.5968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.1078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.4141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.0551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.6219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.3154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.6475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.5162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.6649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.5022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.9539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.5343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.2566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.2868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.5909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.0958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.9502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.3385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.5323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.7884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.8508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8499, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22372881355932203, 'recall': 0.2693877551020408, 'f1': 0.24444444444444444, 'number': 245}, 'P': {'precision': 0.1419491525423729, 'recall': 0.18010752688172044, 'f1': 0.15876777251184834, 'number': 372}, 'overall_precision': 0.17340286831812254, 'overall_recall': 0.21555915721231766, 'overall_f1': 0.19219653179190752, 'overall_accuracy': 0.6604987932421561}
			------------EPOCH 23---------------
Loss:  tensor(79.6765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.5995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.0570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.0532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.5589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.3799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.7617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.7431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.6578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.5233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.3612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.7816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.9979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.2334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.3387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.1722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.6166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.1266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.8743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.4486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.2810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.1831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.9907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.0364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0318, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1842818428184282, 'recall': 0.27755102040816326, 'f1': 0.2214983713355049, 'number': 245}, 'P': {'precision': 0.1525, 'recall': 0.1639784946236559, 'f1': 0.15803108808290156, 'number': 372}, 'overall_precision': 0.16775032509752927, 'overall_recall': 0.20907617504051865, 'overall_f1': 0.18614718614718614, 'overall_accuracy': 0.6261061946902655}
			------------EPOCH 24---------------
Loss:  tensor(69.6779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.4723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.9338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.6269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.8145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.0306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.0454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.5110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.1747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.4968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.4747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.7478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.2185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.6360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.0667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.1702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.7069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.7061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.2295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.2267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.3117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.3728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.6218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2278, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2135593220338983, 'recall': 0.2571428571428571, 'f1': 0.23333333333333334, 'number': 245}, 'P': {'precision': 0.16294642857142858, 'recall': 0.19623655913978494, 'f1': 0.17804878048780487, 'number': 372}, 'overall_precision': 0.18304172274562583, 'overall_recall': 0.22042139384116693, 'overall_f1': 0.19999999999999998, 'overall_accuracy': 0.6747117189595065}
			------------EPOCH 25---------------
Loss:  tensor(78.3366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.9615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.6237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.8743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.6845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.4306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.3929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.2884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.8593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.0663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.9794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.6631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.4487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.9802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.9926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.2917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.8867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.1998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.1570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.2455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.5107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.3742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3149, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1918158567774936, 'recall': 0.30612244897959184, 'f1': 0.2358490566037736, 'number': 245}, 'P': {'precision': 0.14987714987714987, 'recall': 0.1639784946236559, 'f1': 0.15661103979460844, 'number': 372}, 'overall_precision': 0.17042606516290726, 'overall_recall': 0.22042139384116693, 'overall_f1': 0.192226148409894, 'overall_accuracy': 0.6274470367390721}
			------------EPOCH 26---------------
Loss:  tensor(104.7431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.5874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(521.9106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.3866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.3796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.8197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.7294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.2336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.7590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.8095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.2585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.4447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.8798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.1378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.3689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.7031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.7707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.3978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.3915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.0331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.0564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.6864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9529, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23529411764705882, 'recall': 0.2612244897959184, 'f1': 0.24758220502901354, 'number': 245}, 'P': {'precision': 0.1689497716894977, 'recall': 0.1989247311827957, 'f1': 0.18271604938271602, 'number': 372}, 'overall_precision': 0.19436619718309858, 'overall_recall': 0.22366288492706646, 'overall_f1': 0.2079879427279578, 'overall_accuracy': 0.6657951193349424}
			------------EPOCH 27---------------
Loss:  tensor(83.4656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.3653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.6772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.0428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.2874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.4254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.9044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.1405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.2325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.7662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.4894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.4561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.8434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.7302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.8355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.7863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.5030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.4348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.3537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.3185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.1150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.0304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.4475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.4841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.8191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5719, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2066115702479339, 'recall': 0.30612244897959184, 'f1': 0.2467105263157895, 'number': 245}, 'P': {'precision': 0.13975903614457832, 'recall': 0.15591397849462366, 'f1': 0.14739517153748413, 'number': 372}, 'overall_precision': 0.17095115681233933, 'overall_recall': 0.21555915721231766, 'overall_f1': 0.1906810035842294, 'overall_accuracy': 0.6269777420219899}
			------------EPOCH 28---------------
Loss:  tensor(67.8349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.5010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.6632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.5441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.1641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.7578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.6764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.5272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.2814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.3475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.7193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.7810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.8130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.6603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.8074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.8777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.8199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.8098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.6847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.1021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.2254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.3784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.9027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1724, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23, 'recall': 0.2816326530612245, 'f1': 0.25321100917431194, 'number': 245}, 'P': {'precision': 0.1707865168539326, 'recall': 0.20430107526881722, 'f1': 0.186046511627907, 'number': 372}, 'overall_precision': 0.19463087248322147, 'overall_recall': 0.23500810372771475, 'overall_f1': 0.21292217327459617, 'overall_accuracy': 0.6639849825690534}
			------------EPOCH 29---------------
Loss:  tensor(60.7720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.7982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.4311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.7838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.0616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.3725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.7441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.1144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.0590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.7702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.6627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.3647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.6585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.6714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.6867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.2393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.1172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.5968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.4006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.4086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.9677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.0961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5103, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1896551724137931, 'recall': 0.2693877551020408, 'f1': 0.22259696458684652, 'number': 245}, 'P': {'precision': 0.14352941176470588, 'recall': 0.1639784946236559, 'f1': 0.15307402760351316, 'number': 372}, 'overall_precision': 0.16429495472186287, 'overall_recall': 0.20583468395461912, 'overall_f1': 0.18273381294964028, 'overall_accuracy': 0.639916867792974}
			------------EPOCH 30---------------
Loss:  tensor(56.9524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(389.7827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.3725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.4609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.0831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.0644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.6145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.9279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.9310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.8613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.1040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.1337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.7995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.3722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.3338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.3952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.6099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.9336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.2923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.9126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2849, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23809523809523808, 'recall': 0.2857142857142857, 'f1': 0.25974025974025977, 'number': 245}, 'P': {'precision': 0.16192560175054704, 'recall': 0.1989247311827957, 'f1': 0.17852834740651385, 'number': 372}, 'overall_precision': 0.19174434087882822, 'overall_recall': 0.233387358184765, 'overall_f1': 0.2105263157894737, 'overall_accuracy': 0.6653928667203004}


		-------------RUN 5-----------
Test files: ['/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/92.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/93.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/28.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/279.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/82.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/83.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/338.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/99.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/98.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/230.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/69.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/68.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/256.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/74.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/224.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/67.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/261.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/76.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/77.xml']
			------------EPOCH 1---------------
Loss:  tensor(1602.7166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3292.8586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1412.5669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2822.2883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2358.6143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1418.8097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1590.0381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1337.6758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1309.3473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1795.1794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1264.4000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1864.7499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1709.9861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(902.7188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3001.5244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2748.3091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1089.0699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1492.7371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1294.5841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1955.5770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3004.7915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3480.2539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2735.2871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1656.9240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2683.8101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1970.8801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2564.5532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1467.6095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1688.9640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1743.0386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1745.2173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1940.2754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(928.0521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1844.7716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1641.2571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1427.3057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1096.5347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2136.1792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1547.1501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2570.3784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1809.0114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.5684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2000.6682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1608.5195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2285.5078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1645.9918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2131.2366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1594.7384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1348.0342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1304.3256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1342.1450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1948.4821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.5607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1657.8013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1025.2122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(782.8821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2394.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.6860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1557.2068, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 208}, 'P': {'precision': 0.05185185185185185, 'recall': 0.08076923076923077, 'f1': 0.06315789473684211, 'number': 260}, 'overall_precision': 0.04276985743380855, 'overall_recall': 0.04487179487179487, 'overall_f1': 0.043795620437956206, 'overall_accuracy': 0.43579055141143774}
			------------EPOCH 2---------------
Loss:  tensor(1063.2100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2108.9890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.7137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1734.9250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1815.1604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1061.3921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1062.3660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(914.9131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1020.9644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1595.8467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.1694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1365.6290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1356.1289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.9771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2552.8716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2332.2896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(859.7125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1255.2710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(980.4736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1644.6064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2480.6260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3007.4175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2325.4717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1308.3721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1874.7300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1383.9097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2163.7441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1311.4546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1573.6598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1542.4952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1553.3571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1784.4946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(755.7444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1642.5690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1364.4902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.3157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(863.9244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1638.5664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1408.6138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2215.6987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1372.1013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.3329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1695.9664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1322.5979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2002.2195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1356.3735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1737.8252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1322.4480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1136.9613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1126.2682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1116.8806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1685.5933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(624.9786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1375.1240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(869.8484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(644.4350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1976.9326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(907.7251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1243.5435, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.08602150537634409, 'recall': 0.07692307692307693, 'f1': 0.08121827411167513, 'number': 208}, 'P': {'precision': 0.1336405529953917, 'recall': 0.2230769230769231, 'f1': 0.1671469740634006, 'number': 260}, 'overall_precision': 0.11935483870967742, 'overall_recall': 0.1581196581196581, 'overall_f1': 0.13602941176470587, 'overall_accuracy': 0.48193652186631564}
			------------EPOCH 3---------------
Loss:  tensor(870.1587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1736.6982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(646.3017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1369.1094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1493.3020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(902.9819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(840.9286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(740.0326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(823.3005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1370.3242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(794.5760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1103.3704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1071.9830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.7360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2149.1052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1985.3105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.3372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.1442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(817.3557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1329.9417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2039.2437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2590.4805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1977.6001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1108.1687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1388.7792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.9487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1836.1074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1146.1895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1398.5690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1303.1230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1234.8988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1467.7476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.9152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1400.4000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(946.0641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(814.4244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.1416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1334.3739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1196.7654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1807.0768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.5093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.4958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1388.9135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1136.4670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1806.3706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1070.0847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1384.2161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1043.5166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(908.1597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(956.8797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(908.0673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1560.0380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(500.8950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1051.9988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.2874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(517.8864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1295.6837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.2762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.2068, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13125, 'recall': 0.20192307692307693, 'f1': 0.1590909090909091, 'number': 208}, 'P': {'precision': 0.19451371571072318, 'recall': 0.3, 'f1': 0.2360060514372163, 'number': 260}, 'overall_precision': 0.1664355062413315, 'overall_recall': 0.2564102564102564, 'overall_f1': 0.2018502943650126, 'overall_accuracy': 0.49692847740236945}
			------------EPOCH 4---------------
Loss:  tensor(683.2423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1378.0695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.3419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(999.9922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1233.8792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.6180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.8684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(534.6049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(613.9143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.4415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(644.4043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(838.4946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.2316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.0632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1653.6011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1629.8154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.6102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(928.7075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.6256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1019.8101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1511.5645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2117.8726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1432.7263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(884.7719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1055.2988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.5429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1548.3755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.2390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(994.1663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.5303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(965.3679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1160.5310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.6783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1032.7552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.6443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(566.1978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.9297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.0890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1096.2676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1486.9756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(750.7889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.3809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1105.2424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(945.0755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1516.1062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(880.0239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1089.1968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(841.7511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.2671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(757.6132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.0892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1220.3896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.6339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(759.5679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(560.1046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.1123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(923.0644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.9657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.2010, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12745098039215685, 'recall': 0.1875, 'f1': 0.1517509727626459, 'number': 208}, 'P': {'precision': 0.12780269058295965, 'recall': 0.21923076923076923, 'f1': 0.16147308781869688, 'number': 260}, 'overall_precision': 0.1276595744680851, 'overall_recall': 0.20512820512820512, 'overall_f1': 0.15737704918032785, 'overall_accuracy': 0.5244259178002048}
			------------EPOCH 5---------------
Loss:  tensor(478.1218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1294.0774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.8727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(769.1315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(875.3252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.8616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.1492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.3305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.8674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(793.0688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.1060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.1747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(587.6353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.3740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1369.9001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1415.3806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.9902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(758.3743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(506.5520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(793.1985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1096.8584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1793.7900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1020.5353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.9622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.4863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.8348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1149.7936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(726.3365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.0312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(733.6276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(779.5383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(976.5791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.9183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1156.3019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.9688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.5262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.7425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(848.3665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(897.6329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1505.3530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(534.3204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.8672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(761.0720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.8503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1441.5920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(842.3383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1016.8953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(828.3942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(572.9753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.7563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.0941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1201.3196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.1428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.3396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.1290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.5262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(832.5972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.5464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.5135, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13247863247863248, 'recall': 0.2980769230769231, 'f1': 0.1834319526627219, 'number': 208}, 'P': {'precision': 0.22167487684729065, 'recall': 0.17307692307692307, 'f1': 0.19438444924406045, 'number': 260}, 'overall_precision': 0.15946348733233978, 'overall_recall': 0.22863247863247863, 'overall_f1': 0.18788410886742754, 'overall_accuracy': 0.462337282433816}
			------------EPOCH 6---------------
Loss:  tensor(507.5750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1091.9023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.2145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.7777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(869.3402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.7490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.5968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.6423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.8600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.0739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.8526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.3017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.3889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.6848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1221.8657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1247.4055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.0936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.5651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.5541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.5511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1086.7012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1704.8004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1203.8628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.8257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(682.9506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.0185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(912.7562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(541.5532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.5136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.0176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(742.3253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.5151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.4953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(676.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.2379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.6577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.8146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.9131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.9291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1072.7034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.7741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.8963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.9336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.3081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1860.9116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1070.3569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1671.2284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1066.8093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.6691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(764.9272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(750.1212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1233.7683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.7408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(684.2396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.6610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.0957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.8412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.4211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.8714, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2242152466367713, 'recall': 0.2403846153846154, 'f1': 0.2320185614849188, 'number': 208}, 'P': {'precision': 0.26066350710900477, 'recall': 0.4230769230769231, 'f1': 0.32258064516129037, 'number': 260}, 'overall_precision': 0.24806201550387597, 'overall_recall': 0.3418803418803419, 'overall_f1': 0.2875112309074573, 'overall_accuracy': 0.5147725610647945}
			------------EPOCH 7---------------
Loss:  tensor(299.0602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.2915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.7363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.5988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.1541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.7574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.6148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.4941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.3508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.3979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.8685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.1843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.9297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.7806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1269.9951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1208.7893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.8756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(735.1617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.2395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(851.4872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(952.6023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1552.7598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(943.8135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.4286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.7752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.3677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.8221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.3730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.4441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(650.4305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.2017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.7734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.2210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.6883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.3701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.1970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.4815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.8798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.5357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1446.3760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.4940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.9693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.6137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(461.6131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.2199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.7046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.8846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.6138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(468.9799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.0663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(847.6018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.3395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.5108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.1434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.2950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.1375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.5578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.3289, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12912087912087913, 'recall': 0.22596153846153846, 'f1': 0.16433566433566435, 'number': 208}, 'P': {'precision': 0.18077803203661327, 'recall': 0.3038461538461538, 'f1': 0.22668579626972737, 'number': 260}, 'overall_precision': 0.15730337078651685, 'overall_recall': 0.2692307692307692, 'overall_f1': 0.19858156028368792, 'overall_accuracy': 0.50972648822583}
			------------EPOCH 8---------------
Loss:  tensor(195.4826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(713.7432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.8919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.7639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.5291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.8298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.6277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.4042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.3096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(419.8975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.8041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.6868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.9017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.0651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(864.4548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(914.4262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.3134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.8601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.6838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.0248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.9516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1176.7362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(597.3607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(646.6346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.2668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.7280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.3887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.7189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.7639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.8611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.7524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.1504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.1712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.3809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.7975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.6724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.8138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.4794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.1025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.6769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.0355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.0140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.9902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.1136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(922.3940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.4957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.0733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.2564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.3615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.3868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.3638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(745.8566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.6993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.2865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.7775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.3359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.8475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.7479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.9293, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1943127962085308, 'recall': 0.1971153846153846, 'f1': 0.1957040572792363, 'number': 208}, 'P': {'precision': 0.1926782273603083, 'recall': 0.38461538461538464, 'f1': 0.25673940949935814, 'number': 260}, 'overall_precision': 0.19315068493150686, 'overall_recall': 0.30128205128205127, 'overall_f1': 0.2353923205342237, 'overall_accuracy': 0.5150650870264736}
			------------EPOCH 9---------------
Loss:  tensor(166.2119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(688.2370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.0671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.2879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.1615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.8539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.9827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.6001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.3775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.2563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.0806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.9535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.3064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(602.8424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(665.9428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.2384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.9463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.9333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.3129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.0563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1079.7136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.7140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.4474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.9846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.5714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.3073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.8586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.8977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.2215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.2011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.1792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.2627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.5645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.5858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.8318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.2834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.6223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.1666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.4949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.5054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.4122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(779.3796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.5853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.2482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.3943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.7806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.3899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.5239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.7731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.2653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.5598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.9653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.2734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.8863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.5353, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2631578947368421, 'recall': 0.14423076923076922, 'f1': 0.18633540372670807, 'number': 208}, 'P': {'precision': 0.19320214669051877, 'recall': 0.4153846153846154, 'f1': 0.26373626373626374, 'number': 260}, 'overall_precision': 0.2050520059435364, 'overall_recall': 0.2948717948717949, 'overall_f1': 0.24189307624890447, 'overall_accuracy': 0.5158695334210911}
			------------EPOCH 10---------------
Loss:  tensor(155.9052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(744.4214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.1517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.5483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.5379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.6174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.2059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.7461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.4750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.0248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.2056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.1763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.3311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.8992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.8426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.8406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.6300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.8431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.6252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.8231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.1458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(910.1298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.0696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.1575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.9058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.7722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.4520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.6172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.6106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.6296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.2374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.4313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.9010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.8289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.1614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.2881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.8063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.4015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(603.7260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.5923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.7187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.1107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.1141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(740.4980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.9370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(485.1940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.4368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.6616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.5487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.9539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(484.3722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.5142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.0584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.1855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.1348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.9030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.5678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7254, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.36538461538461536, 'recall': 0.09134615384615384, 'f1': 0.14615384615384613, 'number': 208}, 'P': {'precision': 0.17656500802568217, 'recall': 0.4230769230769231, 'f1': 0.24915062287655718, 'number': 260}, 'overall_precision': 0.19111111111111112, 'overall_recall': 0.27564102564102566, 'overall_f1': 0.2257217847769029, 'overall_accuracy': 0.5135293257276583}
			------------EPOCH 11---------------
Loss:  tensor(227.3883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(939.0549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.9352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.8582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.7280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.8364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.1680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.0446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.8481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.6762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.5040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.9111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.7593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.1075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.7970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(811.3027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.2619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.8041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.5622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.9951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.3477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1121.8163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.8752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.5678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.5996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.1995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.6290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.0880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.0320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.2296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.9288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.4901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.7960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.0237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.2803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.3039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.5014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.1560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.9793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(673.3711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.4617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.9903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(886.2288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(666.6562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1120.9386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.7859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(643.6118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.8723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.3759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.0317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.2959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.6799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.2544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.6555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.5149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.3048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.5955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.9789, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16279069767441862, 'recall': 0.0673076923076923, 'f1': 0.09523809523809525, 'number': 208}, 'P': {'precision': 0.15289256198347106, 'recall': 0.4269230769230769, 'f1': 0.22515212981744417, 'number': 260}, 'overall_precision': 0.1539408866995074, 'overall_recall': 0.2670940170940171, 'overall_f1': 0.1953125, 'overall_accuracy': 0.5008775778850373}
			------------EPOCH 12---------------
Loss:  tensor(90.5999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(534.1973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.8594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.7364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.1516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.6192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.2132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.7379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.7461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(843.8790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.6724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.6265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.5766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.5050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1155.1047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1293.7366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.3771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(752.7350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.0585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.2712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1281.8575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2215.8213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1160.0129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(744.2529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(497.5336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.4940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(871.5741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(534.7676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.1558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.9120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.5301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.8838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.3805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.6617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.8757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.7290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.7222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.8676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.9843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(389.1885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.0214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(474.7931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.1493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(943.8387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.6398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(644.0519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.4418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.4139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.9801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.2024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(781.3359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.7730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(517.1147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.8554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.1044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.7794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.4226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.3663, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15778688524590165, 'recall': 0.3701923076923077, 'f1': 0.22126436781609196, 'number': 208}, 'P': {'precision': 0.2767857142857143, 'recall': 0.23846153846153847, 'f1': 0.256198347107438, 'number': 260}, 'overall_precision': 0.1952247191011236, 'overall_recall': 0.297008547008547, 'overall_f1': 0.23559322033898306, 'overall_accuracy': 0.4468334064648238}
			------------EPOCH 13---------------
Loss:  tensor(251.0734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.3924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.6471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.5923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(713.6219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.6673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.1525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.6727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.5358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.8416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.4678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.5734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.7282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.5761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.6403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.6006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.5675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.3160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.8777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.8009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(545.4602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1312.4036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.8380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.2246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.0250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.1851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.0544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.3902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.4536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.5265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.9242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.7770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.9274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.7236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.8871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.3399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.1328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.8244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.5153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.7264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.7234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.3110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.7478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.8608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.5257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.6647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(558.8024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.1412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.3240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.9723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.7444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.3017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.0157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.8273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.6594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.6113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.8607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0157, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1856060606060606, 'recall': 0.23557692307692307, 'f1': 0.2076271186440678, 'number': 208}, 'P': {'precision': 0.20634920634920634, 'recall': 0.35, 'f1': 0.2596291012838801, 'number': 260}, 'overall_precision': 0.19858156028368795, 'overall_recall': 0.29914529914529914, 'overall_f1': 0.23870417732310314, 'overall_accuracy': 0.524352786309785}
			------------EPOCH 14---------------
Loss:  tensor(86.4982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.4044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.1666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.3452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.4897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.7404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.1843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.0223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.7291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.5288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.6437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.6321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.0794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.1671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.2018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.4583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.0302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.1343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.4161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.2933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(866.7777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.5417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.5263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.3638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.7749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.5283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.1791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.8815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.1738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.5526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.0418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.4354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.4960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.1012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.2716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.9580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.3706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.6642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.3224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.5012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.9031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.0822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.7108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.7632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.5002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.9799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.0192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.4087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.3738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.1815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.3414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.7961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.7045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.9706, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12184873949579832, 'recall': 0.27884615384615385, 'f1': 0.1695906432748538, 'number': 208}, 'P': {'precision': 0.09293680297397769, 'recall': 0.09615384615384616, 'f1': 0.09451795841209829, 'number': 260}, 'overall_precision': 0.11140939597315436, 'overall_recall': 0.17735042735042736, 'overall_f1': 0.1368507831821929, 'overall_accuracy': 0.5245721807810443}
			------------EPOCH 15---------------
Loss:  tensor(167.1222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.0751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.4909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.4190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.2810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.0690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.6996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.7135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.3857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.9869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.9881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.7390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.3857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.1982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.6902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.9275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.7320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.7981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.5950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.0171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.3635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.9564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.7890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.7513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.4190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.3465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.7339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.5049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.3123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.3264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.9156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.9028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.8727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.4210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.0094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.5221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.2312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.4069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.1483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.9602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.5592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.0930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.9716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.8550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.5367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.5869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.3307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.8397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.4296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.6871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.3685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.7492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.2272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.6836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9574, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13333333333333333, 'recall': 0.3173076923076923, 'f1': 0.18776671408250356, 'number': 208}, 'P': {'precision': 0.08132530120481928, 'recall': 0.10384615384615385, 'f1': 0.09121621621621623, 'number': 260}, 'overall_precision': 0.1124546553808948, 'overall_recall': 0.1987179487179487, 'overall_f1': 0.14362934362934363, 'overall_accuracy': 0.49941494807664183}
			------------EPOCH 16---------------
Loss:  tensor(61.6959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.6746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.6810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.3053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.8260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.1649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.8488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.4637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.7775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.3421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.2968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.3138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.7492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.5197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.1834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.1911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.1048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.6450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.9219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(786.3290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.0963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.9167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.0426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.2798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.4132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.2797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.3987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.1876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.6633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.5852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.5444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.6611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.5782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.5109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.9743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.4557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.2782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.1779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.0161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.8160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.7770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.6024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.5486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.3506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.1344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.3832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.9792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.8134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1843, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.225, 'recall': 0.21634615384615385, 'f1': 0.22058823529411767, 'number': 208}, 'P': {'precision': 0.21775898520084566, 'recall': 0.39615384615384613, 'f1': 0.2810368349249659, 'number': 260}, 'overall_precision': 0.2199108469539376, 'overall_recall': 0.3162393162393162, 'overall_f1': 0.25942156003505695, 'overall_accuracy': 0.5273511774169958}
			------------EPOCH 17---------------
Loss:  tensor(56.3620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.1331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.4050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.3668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.7194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.6352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.8761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.0467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.9919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.2961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.6683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.7539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.6631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.9891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.7319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.9185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.2457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.1329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.4185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.1336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.9248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.7020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.9347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.2810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.1656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.8428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.8744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.3940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.8113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.4418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.3808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.5590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.9680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.2338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.4876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.6541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.2755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.7605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.7912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.4906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2752, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12408759124087591, 'recall': 0.24519230769230768, 'f1': 0.16478190630048467, 'number': 208}, 'P': {'precision': 0.17571059431524547, 'recall': 0.26153846153846155, 'f1': 0.21020092735703247, 'number': 260}, 'overall_precision': 0.14912280701754385, 'overall_recall': 0.25427350427350426, 'overall_f1': 0.1879936808846761, 'overall_accuracy': 0.5364194822290478}
			------------EPOCH 18---------------
Loss:  tensor(32.0106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.1446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.4334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.1095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.3183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.2555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.0114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.4595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.9619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.2298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.7217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.9237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.9404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.5718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.5374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.5081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.1819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.0568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.2253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.9580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.7316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.6106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.4391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.2843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.2598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.9888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.2372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.8597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.1429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9410, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16611295681063123, 'recall': 0.2403846153846154, 'f1': 0.19646365422396858, 'number': 208}, 'P': {'precision': 0.19540229885057472, 'recall': 0.3269230769230769, 'f1': 0.2446043165467626, 'number': 260}, 'overall_precision': 0.18342391304347827, 'overall_recall': 0.28846153846153844, 'overall_f1': 0.22425249169435219, 'overall_accuracy': 0.5366388767003072}
			------------EPOCH 19---------------
Loss:  tensor(16.4774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.0534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.6745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.9533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.5298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.4547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.6505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.5263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.3757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.6744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.8110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.2749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.6029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.9802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.1600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.1981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.3445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.2521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.9093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.5857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.9635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.7894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.8287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.3712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.3342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.2002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.6540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4615, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13559322033898305, 'recall': 0.23076923076923078, 'f1': 0.1708185053380783, 'number': 208}, 'P': {'precision': 0.2, 'recall': 0.31153846153846154, 'f1': 0.24360902255639102, 'number': 260}, 'overall_precision': 0.16996047430830039, 'overall_recall': 0.27564102564102566, 'overall_f1': 0.21026894865525672, 'overall_accuracy': 0.5402223197308761}
			------------EPOCH 20---------------
Loss:  tensor(10.4666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.1817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.4026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.9907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.6050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.8867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.2057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.2762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.7063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.7906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.5647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.3340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.3331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.2176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.7484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.7233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.9210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.1193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.9594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.5440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.0025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.7979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.7896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7500, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15483870967741936, 'recall': 0.23076923076923078, 'f1': 0.18532818532818535, 'number': 208}, 'P': {'precision': 0.18444444444444444, 'recall': 0.3192307692307692, 'f1': 0.23380281690140844, 'number': 260}, 'overall_precision': 0.1723684210526316, 'overall_recall': 0.2799145299145299, 'overall_f1': 0.21335504885993486, 'overall_accuracy': 0.5427819218955683}
			------------EPOCH 21---------------
Loss:  tensor(7.9518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.3741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.8808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.6097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.3994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.9202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.5671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.2669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.9077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.8407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.2632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.7754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.8842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.3306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.2725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.7194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.8211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.2450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.8984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.5385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4931, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14244186046511628, 'recall': 0.23557692307692307, 'f1': 0.17753623188405798, 'number': 208}, 'P': {'precision': 0.19902912621359223, 'recall': 0.3153846153846154, 'f1': 0.24404761904761904, 'number': 260}, 'overall_precision': 0.17328042328042328, 'overall_recall': 0.2799145299145299, 'overall_f1': 0.21405228758169936, 'overall_accuracy': 0.5323972502559602}
			------------EPOCH 22---------------
Loss:  tensor(6.4195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.7385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.6749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.5576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.9857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.4151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.5497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.6693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.8063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.9089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.6421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.6133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.3732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.1805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.7065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.8984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.7964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.1287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.3696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.7248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8760, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13387978142076504, 'recall': 0.23557692307692307, 'f1': 0.1707317073170732, 'number': 208}, 'P': {'precision': 0.18627450980392157, 'recall': 0.2923076923076923, 'f1': 0.2275449101796407, 'number': 260}, 'overall_precision': 0.16149870801033592, 'overall_recall': 0.2670940170940171, 'overall_f1': 0.20128824476650567, 'overall_accuracy': 0.5415386865584321}
			------------EPOCH 23---------------
Loss:  tensor(5.3859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.2648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.0240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.9329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.1738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.5536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.4359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.7944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.7384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.6303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.6942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.9615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.5344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.5882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.9076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.3065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.4786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.4386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.5252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.0708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.5705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.3412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.9459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3177, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1523809523809524, 'recall': 0.23076923076923078, 'f1': 0.18355640535372852, 'number': 208}, 'P': {'precision': 0.16666666666666666, 'recall': 0.2846153846153846, 'f1': 0.21022727272727273, 'number': 260}, 'overall_precision': 0.16073781291172595, 'overall_recall': 0.2606837606837607, 'overall_f1': 0.19885900570497148, 'overall_accuracy': 0.5343718004972942}
			------------EPOCH 24---------------
Loss:  tensor(4.4939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.6221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.8312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.1551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.3930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.1026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.6497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.8123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.8903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.4350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.4130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.7212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.3542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.7959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.7474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.4581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.0344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.5076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.6388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.0962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.3574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0062, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13774104683195593, 'recall': 0.2403846153846154, 'f1': 0.17513134851138354, 'number': 208}, 'P': {'precision': 0.20759493670886076, 'recall': 0.3153846153846154, 'f1': 0.25038167938931294, 'number': 260}, 'overall_precision': 0.1741424802110818, 'overall_recall': 0.28205128205128205, 'overall_f1': 0.21533442088091354, 'overall_accuracy': 0.5394910048266783}
			------------EPOCH 25---------------
Loss:  tensor(4.0274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.1575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.7867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.8835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.2382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.6782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.1025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.0092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.8748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.5320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.1000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.5079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.2438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.9054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.2585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.9313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.2594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.9275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.3847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.6107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.1986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8192, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13720316622691292, 'recall': 0.25, 'f1': 0.17717206132879046, 'number': 208}, 'P': {'precision': 0.1918158567774936, 'recall': 0.28846153846153844, 'f1': 0.2304147465437788, 'number': 260}, 'overall_precision': 0.16493506493506493, 'overall_recall': 0.27136752136752135, 'overall_f1': 0.20516962843295639, 'overall_accuracy': 0.5479011262249525}
			------------EPOCH 26---------------
Loss:  tensor(3.3458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.9271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.4553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.1529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.8863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.8373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.7667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.2504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.1071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.7432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.9549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.3521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.8363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.8826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.4141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.5233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.8259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.9478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.7987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5468, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16549295774647887, 'recall': 0.22596153846153846, 'f1': 0.1910569105691057, 'number': 208}, 'P': {'precision': 0.18201284796573874, 'recall': 0.3269230769230769, 'f1': 0.233837689133425, 'number': 260}, 'overall_precision': 0.17576564580559254, 'overall_recall': 0.28205128205128205, 'overall_f1': 0.2165709598031173, 'overall_accuracy': 0.5329823021793184}
			------------EPOCH 27---------------
Loss:  tensor(2.8248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.1420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.3021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.2574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.8114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.4692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.0342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.5730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.0932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.3567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.8279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.0285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.5912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.6211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.8433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.2134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.1929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.5627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.7444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3965, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14786967418546365, 'recall': 0.28365384615384615, 'f1': 0.1943986820428336, 'number': 208}, 'P': {'precision': 0.21282798833819241, 'recall': 0.28076923076923077, 'f1': 0.24212271973466004, 'number': 260}, 'overall_precision': 0.1778975741239892, 'overall_recall': 0.28205128205128205, 'overall_f1': 0.21818181818181817, 'overall_accuracy': 0.5218663156355127}
			------------EPOCH 28---------------
Loss:  tensor(2.9393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.7481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.2542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.3358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.3564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.4078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.0727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.1700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.0630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.3682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.7497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.2618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.4861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.3893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.2140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.2263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.0795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.1192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.3390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.8501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3741, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15315315315315314, 'recall': 0.24519230769230768, 'f1': 0.18853974121996303, 'number': 208}, 'P': {'precision': 0.1613588110403397, 'recall': 0.2923076923076923, 'f1': 0.2079343365253078, 'number': 260}, 'overall_precision': 0.15796019900497513, 'overall_recall': 0.27136752136752135, 'overall_f1': 0.19968553459119498, 'overall_accuracy': 0.5391984788649993}
			------------EPOCH 29---------------
Loss:  tensor(2.5351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.1631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.6951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.7015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.5089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.0644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.7272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.8997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.4983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.8683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.6448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.0909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.5666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.2806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.3771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.0883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.5823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.9785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.4582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.9358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4590, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16129032258064516, 'recall': 0.2644230769230769, 'f1': 0.20036429872495445, 'number': 208}, 'P': {'precision': 0.2144638403990025, 'recall': 0.33076923076923076, 'f1': 0.26021180030257185, 'number': 260}, 'overall_precision': 0.19002695417789758, 'overall_recall': 0.30128205128205127, 'overall_f1': 0.23305785123966943, 'overall_accuracy': 0.5236214714055872}
			------------EPOCH 30---------------
Loss:  tensor(2.5576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.1128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.4477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.4277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.4014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.4564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.7487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.4307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.8122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.9626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.6333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.1445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.4451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.7716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.4988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.6870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.5963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.8218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.5328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1796, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14207650273224043, 'recall': 0.25, 'f1': 0.18118466898954702, 'number': 208}, 'P': {'precision': 0.19487179487179487, 'recall': 0.2923076923076923, 'f1': 0.23384615384615384, 'number': 260}, 'overall_precision': 0.1693121693121693, 'overall_recall': 0.27350427350427353, 'overall_f1': 0.2091503267973856, 'overall_accuracy': 0.5264735995319585}
	Train size: 50 Test size: 50


		-------------RUN 1-----------
Test files: ['/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/82.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/85.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/84.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/86.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/83.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/25.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/248.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/72.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/71.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/95.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/94.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/29.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/277.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/81.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/261.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/76.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/77.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/224.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/67.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/72.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/69.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/71.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/70.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/19.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/263.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/78.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/79.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/66.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/67.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/68.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/18.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/251.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/73.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/0.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/1.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/0.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/1.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/301.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/88.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/291.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/86.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/256.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/74.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/99.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/97.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/98.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/31.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/10.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/11.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/8.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/12.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/5.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/329.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/96.xml']
			------------EPOCH 1---------------
Loss:  tensor(1703.6289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1793.5305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2187.0293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2863.4617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1157.5531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3083.3538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1754.9562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3385.6860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1565.6394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2532.7754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2147.8359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.0696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1627.1185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2513.3748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2188.7307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2982.7183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4792.0723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2456.0059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2215.8850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1518.5298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2712.4639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2402.7349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2792.7388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2546.0610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2784.4102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3265.4541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1916.3613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2168.8735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3516.0898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1711.2595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1391.2808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2191.1289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1208.4805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1277.5774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1586.9943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2274.3706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1264.3451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1588.0908, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.011494252873563218, 'recall': 0.0015873015873015873, 'f1': 0.002789400278940028, 'number': 630}, 'P': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 860}, 'overall_precision': 0.01098901098901099, 'overall_recall': 0.0006711409395973154, 'overall_f1': 0.001265022137887413, 'overall_accuracy': 0.3066591754287396}
			------------EPOCH 2---------------
Loss:  tensor(1317.0803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1417.4961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1658.8579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2326.9263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(970.7396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2522.8054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1482.0593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2876.7656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1251.9127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1945.9293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1753.9308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.9150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1452.4269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2165.1370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1831.1809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2548.5425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4479.3047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2197.9009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2016.5454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1349.1379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2468.9971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2232.9919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2570.1416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2287.3799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2514.2544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2902.3560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1709.3123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1808.6003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3162.4565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1406.3051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.3704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1861.8911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1136.5226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1159.5530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1463.3726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2178.3809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1106.2034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1456.6523, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0060790273556231, 'recall': 0.0031746031746031746, 'f1': 0.004171011470281543, 'number': 630}, 'P': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 860}, 'overall_precision': 0.005063291139240506, 'overall_recall': 0.0013422818791946308, 'overall_f1': 0.002122015915119363, 'overall_accuracy': 0.37274259571394175}
			------------EPOCH 3---------------
Loss:  tensor(1162.7726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1236.6887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1407.6694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2092.4668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(876.7482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2155.1982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1263.8926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2580.3232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1128.2653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1719.7119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1592.2645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.5446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1250.7358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1868.6155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1651.6005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2309.3994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4170.4800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2015.6011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1809.8080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1187.4941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2205.4124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1995.6812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2179.7314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1994.8292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2253.9712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2503.3740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1538.5229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1429.3615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2638.6475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1185.9849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1042.0111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1622.1614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1098.3591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1004.5355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1406.6305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2037.1733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(938.5042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1305.7159, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.06125166444740346, 'recall': 0.07301587301587302, 'f1': 0.06661839246922521, 'number': 630}, 'P': {'precision': 0.08320493066255778, 'recall': 0.06279069767441861, 'f1': 0.07157057654075548, 'number': 860}, 'overall_precision': 0.07142857142857142, 'overall_recall': 0.06711409395973154, 'overall_f1': 0.06920415224913495, 'overall_accuracy': 0.531128769029082}
			------------EPOCH 4---------------
Loss:  tensor(990.0289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1065.8113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.7852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1851.2823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.6515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1706.1609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1034.5613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2193.5537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(927.3876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1370.4062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1298.5215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.0146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1110.6588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1628.6935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1360.2417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1962.8549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3424.7253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1732.0177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1596.8931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1058.0425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1903.8225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1675.5312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1678.5657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1720.8341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1977.0203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2039.3789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1237.3354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1060.2791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2118.9419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(921.2850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(845.4812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1280.7312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(975.5864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(848.7030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1282.2998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1741.0532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.7256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1129.6963, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11784511784511785, 'recall': 0.16666666666666666, 'f1': 0.13806706114398423, 'number': 630}, 'P': {'precision': 0.10846560846560846, 'recall': 0.09534883720930233, 'f1': 0.10148514851485148, 'number': 860}, 'overall_precision': 0.1135397692774742, 'overall_recall': 0.12550335570469798, 'overall_f1': 0.11922218680267771, 'overall_accuracy': 0.5705380314096905}
			------------EPOCH 5---------------
Loss:  tensor(869.8473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(978.8531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(981.5431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1643.7036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.7888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1398.5789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(857.2734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1884.4280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(737.3268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1047.2803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(973.2562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.4823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(893.1194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1383.9330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1125.5660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1616.2319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2981.3428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1443.0254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1334.2144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(867.1252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1600.1064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1303.5439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1204.5186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1375.4250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1666.2703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1706.7430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1001.8962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(876.9043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1758.8893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(603.0182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.5737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(964.7410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(790.4146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(693.3890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1007.6921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1259.6278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(644.8722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.0765, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13867924528301886, 'recall': 0.23333333333333334, 'f1': 0.1739644970414201, 'number': 630}, 'P': {'precision': 0.13607188703465983, 'recall': 0.12325581395348838, 'f1': 0.12934716290420986, 'number': 860}, 'overall_precision': 0.1375747688961392, 'overall_recall': 0.1697986577181208, 'overall_f1': 0.1519975968759387, 'overall_accuracy': 0.5733204912111727}
			------------EPOCH 6---------------
Loss:  tensor(686.7543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(815.0973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(742.5333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1430.9451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.6477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1132.1001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.6276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1603.6801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.2810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(855.7159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(801.2674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.1077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.8508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1477.1792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.6245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1582.7620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2592.4529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1156.0437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1022.4611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.6401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1193.5983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1017.9331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(961.8743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1007.6456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1322.1631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1360.5049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(759.7299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.8968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1634.5376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.3804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(569.2738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(889.9186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.1677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.2341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(946.2552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1115.8629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.8212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(815.2885, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14499252615844543, 'recall': 0.15396825396825398, 'f1': 0.1493456505003849, 'number': 630}, 'P': {'precision': 0.0970873786407767, 'recall': 0.10465116279069768, 'f1': 0.10072747621712366, 'number': 860}, 'overall_precision': 0.11716791979949874, 'overall_recall': 0.12550335570469798, 'overall_f1': 0.12119248217757615, 'overall_accuracy': 0.6175187949808706}
			------------EPOCH 7---------------
Loss:  tensor(517.7509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(636.8027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.8893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1182.7837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.7182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.7936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.2648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1073.0485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.4941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.2346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.4060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.9459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(597.2640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.8398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.2651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1218.9438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2035.1339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.8340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(858.5849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(451.1976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(957.9420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(849.6107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(950.1459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(806.6075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1200.4185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.9119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(693.0800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(558.0700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(951.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.3847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.4804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(578.6824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.9706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.4818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(673.0688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.7943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.3197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(757.4488, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13716814159292035, 'recall': 0.09841269841269841, 'f1': 0.11460258780036969, 'number': 630}, 'P': {'precision': 0.08943089430894309, 'recall': 0.07674418604651163, 'f1': 0.08260325406758448, 'number': 860}, 'overall_precision': 0.10756302521008404, 'overall_recall': 0.08590604026845637, 'overall_f1': 0.09552238805970148, 'overall_accuracy': 0.5558230997672365}
			------------EPOCH 8---------------
Loss:  tensor(455.7436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.8414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(484.1694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.0610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.6491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.8500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.3638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1111.1992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.7834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.4457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.1654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.1147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.0075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.4180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(716.4203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1032.6057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1617.8588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.9161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(577.2650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.9639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(702.7274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(587.4343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(443.6486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.0246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(927.5773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(976.1379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.5027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.7411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(759.4465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.8391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.5581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.0590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.0382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.0245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.9387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(806.4604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(389.3224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(891.6926, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15983026874115983, 'recall': 0.17936507936507937, 'f1': 0.16903515332834704, 'number': 630}, 'P': {'precision': 0.16794478527607362, 'recall': 0.25465116279069766, 'f1': 0.20240295748613682, 'number': 860}, 'overall_precision': 0.1650919940328195, 'overall_recall': 0.22281879194630871, 'overall_f1': 0.18966009711510995, 'overall_accuracy': 0.6156459854991038}
			------------EPOCH 9---------------
Loss:  tensor(354.5946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.4899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.9065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1078.7463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.3597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.0988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.1619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(718.4069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.6778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.6423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.2787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.5110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.8904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.2474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.1729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.7218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1443.1543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(569.6938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(619.3837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.8275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(663.6212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.7537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.1488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.1754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(972.6432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.0195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.0502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.8670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(705.1716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.5813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.4978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.1939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.0561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.3221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.3416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.7251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.0551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(521.9040, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20178041543026706, 'recall': 0.10793650793650794, 'f1': 0.140641158221303, 'number': 630}, 'P': {'precision': 0.14662960389159138, 'recall': 0.2453488372093023, 'f1': 0.18355806872553285, 'number': 860}, 'overall_precision': 0.1570945945945946, 'overall_recall': 0.187248322147651, 'overall_f1': 0.17085119412124924, 'overall_accuracy': 0.6204885357305294}
			------------EPOCH 10---------------
Loss:  tensor(280.1361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.8970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.3550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(829.8883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.8342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.8021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.9053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.6719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.2908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.1364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.1947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.9138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.1781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.9524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.9329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(873.8519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1518.3802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(576.7378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.0183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.2177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.2900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(577.0684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(587.1194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.7785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.9368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.5084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.1204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.9108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.1156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.9198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.3720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.8761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.4349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.8993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.1714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.9081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.3900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.4001, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.31521739130434784, 'recall': 0.09206349206349207, 'f1': 0.14250614250614252, 'number': 630}, 'P': {'precision': 0.1814488828706838, 'recall': 0.3116279069767442, 'f1': 0.2293538724860933, 'number': 860}, 'overall_precision': 0.1962673088500903, 'overall_recall': 0.21879194630872484, 'overall_f1': 0.20691843859092351, 'overall_accuracy': 0.582416994408326}
			------------EPOCH 11---------------
Loss:  tensor(373.4067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(648.3842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(688.0161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(966.3704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.6500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.4854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.9566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(832.1427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.0740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.7132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.9841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.7076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.9108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.3808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.7959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.6838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1102.7260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.3317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.2872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.9396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.4444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.4225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.4914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1173.5718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(981.6779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.8239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.7780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1478.8055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.6689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.0795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(712.0500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.8120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.2650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(694.0389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(739.8805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.0914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.6802, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18808193668528864, 'recall': 0.16031746031746033, 'f1': 0.17309340188517566, 'number': 630}, 'P': {'precision': 0.15246636771300448, 'recall': 0.2372093023255814, 'f1': 0.18562329390354868, 'number': 860}, 'overall_precision': 0.16266666666666665, 'overall_recall': 0.20469798657718122, 'overall_f1': 0.18127786032689452, 'overall_accuracy': 0.628274072290446}
			------------EPOCH 12---------------
Loss:  tensor(210.7176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.7370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.5869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.1638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.8302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.8502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.8182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.1976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(491.0792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.4486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.2157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.6387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1820.3186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1504.3566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1978.4919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4026.2930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1849.2637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1142.2579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(741.4065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1324.8303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1054.3341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1025.9502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.2986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.4769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.2744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.3517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.6708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.3519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.3675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.8587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.3385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.1906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.9149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.2703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.7766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1421.3237, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.09897828863346105, 'recall': 0.24603174603174602, 'f1': 0.14116575591985425, 'number': 630}, 'P': {'precision': 0.11290322580645161, 'recall': 0.00813953488372093, 'f1': 0.015184381778741865, 'number': 860}, 'overall_precision': 0.09950859950859951, 'overall_recall': 0.1087248322147651, 'overall_f1': 0.10391276459268761, 'overall_accuracy': 0.4319233753377746}
			------------EPOCH 13---------------
Loss:  tensor(747.1501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(806.0680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(892.4575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1744.9574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1844.6389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.8260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2650.7124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(684.3080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1135.8463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.9782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.3522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(967.5545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(678.0156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1414.8037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1914.2712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.2983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(825.6842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.6045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(635.8024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(745.9059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(503.9203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(927.1735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1092.2104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.4460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.2114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(616.0157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.5006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.0618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.0565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.4035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.9457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.8150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.3517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.9247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(419.4068, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1617873651771957, 'recall': 0.16666666666666666, 'f1': 0.1641907740422205, 'number': 630}, 'P': {'precision': 0.14933135215453194, 'recall': 0.23372093023255813, 'f1': 0.1822302810516772, 'number': 860}, 'overall_precision': 0.15338345864661654, 'overall_recall': 0.20536912751677852, 'overall_f1': 0.175609756097561, 'overall_accuracy': 0.6300131096663724}
			------------EPOCH 14---------------
Loss:  tensor(281.6578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.6144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.5583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.5536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.7647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.6735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.2743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.7369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.9583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.3655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.7340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.5802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.6371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.9683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.1945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.9859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1680.3625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(627.8236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.0913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.2998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(587.7434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.6783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.6648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.8874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.1699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.2521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.0439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.3736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.2284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.2849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.4768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.7482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.7309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.7873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.3232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.9559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.7921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.4950, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15692307692307692, 'recall': 0.24285714285714285, 'f1': 0.19065420560747662, 'number': 630}, 'P': {'precision': 0.12427745664739884, 'recall': 0.15, 'f1': 0.13593256059009481, 'number': 860}, 'overall_precision': 0.14008941877794337, 'overall_recall': 0.18926174496644296, 'overall_f1': 0.1610048529831573, 'overall_accuracy': 0.606710008828959}
			------------EPOCH 15---------------
Loss:  tensor(175.5063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.1174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.5176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(500.2995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.3697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.0109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.8575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.9992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.7927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.5551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.3861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.4878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.6131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.3406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.3844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.8358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.1725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.8860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.2032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.5567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.9504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.3966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.8210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.7253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(525.9919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(565.6899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.5598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.4680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.1543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.8686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.8425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.9269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.5465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.8388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.2741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.1764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.4690, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14568345323741008, 'recall': 0.2571428571428571, 'f1': 0.18599311136624572, 'number': 630}, 'P': {'precision': 0.14285714285714285, 'recall': 0.14418604651162792, 'f1': 0.14351851851851852, 'number': 860}, 'overall_precision': 0.14444444444444443, 'overall_recall': 0.1919463087248322, 'overall_f1': 0.1648414985590778, 'overall_accuracy': 0.6035529871311234}
			------------EPOCH 16---------------
Loss:  tensor(131.9373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.3245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.0865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.3068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.3751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.9620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.6792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.3184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.2010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.3824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.7619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.6033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.1515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.4709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.1306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.7753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.3480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.7409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.8730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.2865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.4702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.1711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.1483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.6433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.0098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.5382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.4215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.6210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.9832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.8632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.6109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.8127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.9366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.1954, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1641086186540732, 'recall': 0.22063492063492063, 'f1': 0.1882193635748138, 'number': 630}, 'P': {'precision': 0.15875754961173424, 'recall': 0.21395348837209302, 'f1': 0.1822684497275879, 'number': 860}, 'overall_precision': 0.16101694915254236, 'overall_recall': 0.21677852348993287, 'overall_f1': 0.18478260869565216, 'overall_accuracy': 0.6400460176044092}
			------------EPOCH 17---------------
Loss:  tensor(95.6677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.4869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.7889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.9974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.0416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.1678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.8087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.4736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.4461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.9089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.8074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.9861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(798.2034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.0333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.2530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.9578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.1410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.6505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.7471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.7215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.9053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.1508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.4112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.9253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.3205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.7299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.4576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.6374, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18297331639135958, 'recall': 0.22857142857142856, 'f1': 0.20324629498941424, 'number': 630}, 'P': {'precision': 0.15488215488215487, 'recall': 0.21395348837209302, 'f1': 0.17968749999999997, 'number': 860}, 'overall_precision': 0.1660759493670886, 'overall_recall': 0.22013422818791947, 'overall_f1': 0.18932178932178934, 'overall_accuracy': 0.6411429488723012}
			------------EPOCH 18---------------
Loss:  tensor(79.7681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.6619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.5033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.0891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.0250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.9888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.2198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.6059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.8633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.6188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.1650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.9292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.0872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.7462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.5960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.6348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.9153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.9461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.0238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.1888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.3501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.9482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.4307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.8997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.4549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.7313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.1697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.6568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.3190, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18876404494382024, 'recall': 0.26666666666666666, 'f1': 0.2210526315789474, 'number': 630}, 'P': {'precision': 0.16461267605633803, 'recall': 0.21744186046511627, 'f1': 0.187374749498998, 'number': 860}, 'overall_precision': 0.17522211253701875, 'overall_recall': 0.23825503355704697, 'overall_f1': 0.20193401592718999, 'overall_accuracy': 0.6386012788613319}
			------------EPOCH 19---------------
Loss:  tensor(64.6128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.1794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.3823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.7117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.2119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.9363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.5190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.6691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.2806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.0438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.9069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.7204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.6271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.3982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.4239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.6336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.0461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.5630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.6572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.5870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.7360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.1663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.2885, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17990654205607476, 'recall': 0.24444444444444444, 'f1': 0.2072678331090175, 'number': 630}, 'P': {'precision': 0.15138772077375945, 'recall': 0.20930232558139536, 'f1': 0.17569546120058566, 'number': 860}, 'overall_precision': 0.16332518337408314, 'overall_recall': 0.22416107382550335, 'overall_f1': 0.18896746817538895, 'overall_accuracy': 0.642721459721219}
			------------EPOCH 20---------------
Loss:  tensor(53.1100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.9304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.2548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.5294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.9142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.9795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.4016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.0375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.5425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(670.5430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.4273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.0559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.1811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.5688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.1199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.4551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.1848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.0080, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18160919540229886, 'recall': 0.2507936507936508, 'f1': 0.21066666666666667, 'number': 630}, 'P': {'precision': 0.16103896103896104, 'recall': 0.21627906976744185, 'f1': 0.1846153846153846, 'number': 860}, 'overall_precision': 0.16987654320987655, 'overall_recall': 0.23087248322147652, 'overall_f1': 0.19573257467994312, 'overall_accuracy': 0.6376113652781122}
			------------EPOCH 21---------------
Loss:  tensor(44.4465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.8448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.9767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.9412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.8227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.8170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.7664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(646.6450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.6207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.9025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.3879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.2120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.9939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.2222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.9235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.7148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.1697, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18497109826589594, 'recall': 0.25396825396825395, 'f1': 0.21404682274247488, 'number': 630}, 'P': {'precision': 0.16595012897678418, 'recall': 0.22441860465116278, 'f1': 0.19080573405832918, 'number': 860}, 'overall_precision': 0.17406311637080868, 'overall_recall': 0.23691275167785236, 'overall_f1': 0.2006822057987493, 'overall_accuracy': 0.6406613692912754}
			------------EPOCH 22---------------
Loss:  tensor(36.3249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.8273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.2617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.3191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.8720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.4272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.0596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.6118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.5355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.1782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.4795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.2754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.2015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.8596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.6938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.2026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.5005, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18433179723502305, 'recall': 0.25396825396825395, 'f1': 0.2136181575433912, 'number': 630}, 'P': {'precision': 0.161400512382579, 'recall': 0.21976744186046512, 'f1': 0.18611521418020682, 'number': 860}, 'overall_precision': 0.17116233447768514, 'overall_recall': 0.2342281879194631, 'overall_f1': 0.1977897421365826, 'overall_accuracy': 0.6376916285416165}
			------------EPOCH 23---------------
Loss:  tensor(29.6973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.8964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.0447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.2001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.5837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.9901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.5379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.4907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.3105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.2002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.5257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.0038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.5343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.8376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.6931, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18714121699196326, 'recall': 0.25873015873015875, 'f1': 0.2171885409726849, 'number': 630}, 'P': {'precision': 0.1753472222222222, 'recall': 0.23488372093023255, 'f1': 0.2007952286282306, 'number': 860}, 'overall_precision': 0.18042511122095897, 'overall_recall': 0.24496644295302014, 'overall_f1': 0.20779960148021634, 'overall_accuracy': 0.6390561040211895}
			------------EPOCH 24---------------
Loss:  tensor(23.6369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.9026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.5931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.9204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.1315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.7445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.1738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.7830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(601.5235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.4789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.4543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.7141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.1718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.5324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.9936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.4961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.3936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.8285, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1745049504950495, 'recall': 0.22380952380952382, 'f1': 0.19610570236439498, 'number': 630}, 'P': {'precision': 0.15564516129032258, 'recall': 0.22441860465116278, 'f1': 0.18380952380952378, 'number': 860}, 'overall_precision': 0.1630859375, 'overall_recall': 0.22416107382550335, 'overall_f1': 0.18880723572639913, 'overall_accuracy': 0.6370762768547502}
			------------EPOCH 25---------------
Loss:  tensor(19.9771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.5353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.8417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.1274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.3039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.4921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.5143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.1462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.2455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.2802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.2471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.2889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.5834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.5502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.2068, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19658119658119658, 'recall': 0.2920634920634921, 'f1': 0.23499361430395913, 'number': 630}, 'P': {'precision': 0.1719171917191719, 'recall': 0.22209302325581395, 'f1': 0.19381024860476914, 'number': 860}, 'overall_precision': 0.18319491939423546, 'overall_recall': 0.2516778523489933, 'overall_f1': 0.21204410517387617, 'overall_accuracy': 0.6198999384648313}
			------------EPOCH 26---------------
Loss:  tensor(18.1334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.0511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.8907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.7720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.0636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.3537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.6377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.0628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.0670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.9744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.7076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.2000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.0277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.6770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.5488, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16099476439790575, 'recall': 0.19523809523809524, 'f1': 0.1764705882352941, 'number': 630}, 'P': {'precision': 0.15146831530139104, 'recall': 0.22790697674418606, 'f1': 0.18198700092850514, 'number': 860}, 'overall_precision': 0.15500485908649175, 'overall_recall': 0.21409395973154363, 'overall_f1': 0.1798196166854566, 'overall_accuracy': 0.6390025951788533}
			------------EPOCH 27---------------
Loss:  tensor(16.4516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.1271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.6986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.4838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.9937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.8282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.6975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.8664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.0664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.8447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.7822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.0569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.2077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.2188, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19320843091334894, 'recall': 0.2619047619047619, 'f1': 0.2223719676549865, 'number': 630}, 'P': {'precision': 0.17974683544303796, 'recall': 0.24767441860465117, 'f1': 0.20831295843520778, 'number': 860}, 'overall_precision': 0.18538499264345268, 'overall_recall': 0.2536912751677852, 'overall_f1': 0.2142249929158402, 'overall_accuracy': 0.6377986462262889}
			------------EPOCH 28---------------
Loss:  tensor(13.2569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.1046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.8776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.5623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.9821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.1582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.8513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.3798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.0158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.8287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.5176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.7277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.4875, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19682151589242053, 'recall': 0.25555555555555554, 'f1': 0.22237569060773477, 'number': 630}, 'P': {'precision': 0.17656903765690377, 'recall': 0.2453488372093023, 'f1': 0.205352798053528, 'number': 860}, 'overall_precision': 0.18479880774962743, 'overall_recall': 0.24966442953020135, 'overall_f1': 0.21238938053097345, 'overall_accuracy': 0.6470289215292827}
			------------EPOCH 29---------------
Loss:  tensor(9.6534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.6034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.8752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.3968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.6578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(568.3324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.8290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.7234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.4703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.7590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.3227, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19464720194647203, 'recall': 0.25396825396825395, 'f1': 0.2203856749311295, 'number': 630}, 'P': {'precision': 0.16876574307304787, 'recall': 0.23372093023255813, 'f1': 0.1960019502681619, 'number': 860}, 'overall_precision': 0.17933432687531048, 'overall_recall': 0.24228187919463087, 'overall_f1': 0.20610904938624036, 'overall_accuracy': 0.6451293576263477}
			------------EPOCH 30---------------
Loss:  tensor(7.7943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.1819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.2321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.8762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.5840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.5184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.2980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.9221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.3461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.6400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.6161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.6942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.1016, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20121951219512196, 'recall': 0.2619047619047619, 'f1': 0.22758620689655173, 'number': 630}, 'P': {'precision': 0.18786857624262848, 'recall': 0.2593023255813954, 'f1': 0.21787982413287738, 'number': 860}, 'overall_precision': 0.1933233682112606, 'overall_recall': 0.26040268456375837, 'overall_f1': 0.2219044895624821, 'overall_accuracy': 0.6456644460497097}


		-------------RUN 2-----------
Test files: ['/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/247.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/70.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/29.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/10.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/279.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/82.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/83.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/293.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/87.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/334.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/97.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/251.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/73.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/256.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/74.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/329.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/96.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/338.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/99.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/98.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/261.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/76.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/77.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/266.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/80.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/230.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/69.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/68.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/258.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/75.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/277.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/81.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/309.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/92.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/91.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/93.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/301.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/88.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/263.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/78.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/79.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/91.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/88.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/90.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/87.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/27.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/66.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/67.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/68.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/18.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/32.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/11.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/12.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/302.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/89.xml']
			------------EPOCH 1---------------
Loss:  tensor(1848.0579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1388.2339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1246.4050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2420.9067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3320.2319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(871.7667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(841.9860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1617.7256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1407.1501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1529.2372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2200.7668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(966.4547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2294.2300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1788.7738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2360.2119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1443.6654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1537.1134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.3718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1631.7966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1402.2480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1137.0840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(868.1902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2018.7303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1377.3629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1747.7950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1935.4326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1283.2335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.7876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3015.5110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2837.0952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3739.5713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2767.7576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2599.8687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1486.2063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1931.4224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2071.7383, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.005504587155963303, 'recall': 0.003963011889035667, 'f1': 0.004608294930875576, 'number': 757}, 'P': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 998}, 'overall_precision': 0.005494505494505495, 'overall_recall': 0.0017094017094017094, 'overall_f1': 0.002607561929595828, 'overall_accuracy': 0.35864149563468484}
			------------EPOCH 2---------------
Loss:  tensor(1232.4473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(889.1299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(859.8864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1689.6194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2828.3035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(772.2748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(678.5793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1236.9474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1187.9984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1291.1613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1959.2552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.8588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2055.0664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1563.3455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2085.9082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1259.9376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1582.1694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(645.1987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1364.6542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1249.2175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1012.6930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(805.1746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1914.2795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1180.7358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1551.8020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1753.2900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1235.0557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.5601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2301.0391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2315.1152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3150.9346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2337.6221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2250.3992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1275.0887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1773.0890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1891.3322, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.03036876355748373, 'recall': 0.018494055482166448, 'f1': 0.022988505747126436, 'number': 757}, 'P': {'precision': 0.01809954751131222, 'recall': 0.008016032064128256, 'f1': 0.011111111111111113, 'number': 998}, 'overall_precision': 0.024363233665559248, 'overall_recall': 0.012535612535612535, 'overall_f1': 0.016553799849510907, 'overall_accuracy': 0.5274717740092334}
			------------EPOCH 3---------------
Loss:  tensor(1221.9373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(856.1858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(788.6274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1641.1919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1941.9797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.2556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.5442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1160.1953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1139.5469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1163.2246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1712.4015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(639.2162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1759.7031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1512.1422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1483.1484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(918.1824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1362.5690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(587.3451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1209.3774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1055.6293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.0598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.3628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1493.1996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(921.6635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1252.2444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1584.8728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1013.0377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(886.7308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2187.7207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2112.1167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2842.9512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2059.5869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2025.9468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1003.5172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1649.9937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1696.6111, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.031806615776081425, 'recall': 0.03302509907529723, 'f1': 0.03240440699935192, 'number': 757}, 'P': {'precision': 0.02877697841726619, 'recall': 0.01603206412825651, 'f1': 0.020592020592020588, 'number': 998}, 'overall_precision': 0.030551415797317436, 'overall_recall': 0.023361823361823363, 'overall_f1': 0.02647723603487246, 'overall_accuracy': 0.5091420213009097}
			------------EPOCH 4---------------
Loss:  tensor(907.0168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.9293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.4937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1281.7679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1741.5916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(580.5776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.8672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(980.2915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(967.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(999.2697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1565.5405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(565.4805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1528.6498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1214.9888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1198.4609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.4737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1228.8997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.6519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1002.8000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.2128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.8650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.8749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1269.8638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(681.1053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(994.1691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1373.1079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.6324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.6891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1809.7394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1819.1936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2528.8091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1785.7158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1717.0637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(778.3278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1458.4673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1470.6890, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.07700534759358289, 'recall': 0.095112285336856, 'f1': 0.0851063829787234, 'number': 757}, 'P': {'precision': 0.08491761723700887, 'recall': 0.06713426853707415, 'f1': 0.07498601007274762, 'number': 998}, 'overall_precision': 0.08062645011600927, 'overall_recall': 0.07920227920227921, 'overall_f1': 0.0799080195458465, 'overall_accuracy': 0.5477213511907483}
			------------EPOCH 5---------------
Loss:  tensor(653.8105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(389.9506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1065.6072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1316.3983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.1473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.2375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(801.3113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.7001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.3403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1377.8796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.6963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1224.5487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(977.3348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.9960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.4274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1013.6219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.9235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.3773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.6628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.2045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.0956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1108.2252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.4995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(740.4376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1168.9558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(666.9440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.9396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1409.9952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1422.8479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2098.1025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1413.5237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1370.4739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(578.3246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1181.6138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1125.1741, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18001978239366964, 'recall': 0.2404227212681638, 'f1': 0.2058823529411765, 'number': 757}, 'P': {'precision': 0.24539170506912442, 'recall': 0.21342685370741482, 'f1': 0.2282958199356913, 'number': 998}, 'overall_precision': 0.21021820117083556, 'overall_recall': 0.22507122507122507, 'overall_f1': 0.2173913043478261, 'overall_accuracy': 0.5697307674726882}
			------------EPOCH 6---------------
Loss:  tensor(438.5224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.8363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.3426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(866.0361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(993.2305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.0949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.9536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.3196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(752.5691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(641.4644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1219.2478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.8816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1034.4937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.7783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.5869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.3183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.9320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.3206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.4518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(443.4862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.1657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.2293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(916.4189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.1486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.0399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1008.4795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.6713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.7966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1164.5648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1153.6608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1815.9409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1163.4347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1138.5310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.8158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1051.2878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(919.7856, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1584875301689461, 'recall': 0.26023778071334214, 'f1': 0.19699999999999998, 'number': 757}, 'P': {'precision': 0.24466750313676286, 'recall': 0.19539078156312625, 'f1': 0.21727019498607242, 'number': 998}, 'overall_precision': 0.19215686274509805, 'overall_recall': 0.22336182336182336, 'overall_f1': 0.20658761528326744, 'overall_accuracy': 0.5588974722311103}
			------------EPOCH 7---------------
Loss:  tensor(281.1498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.5919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.9804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.0693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(765.3425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.6626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.8250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.2912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(662.4363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(545.5905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1061.2610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.8609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.8663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.5231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.6756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.5218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(703.6321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.5132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(603.2836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.4235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.1926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.3264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(781.8314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.6714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.1251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(891.5321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.5832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.8354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1112.7097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(987.2496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1613.2626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(907.7092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(870.3444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.3513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(741.9803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(670.9224, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13501483679525222, 'recall': 0.1202113606340819, 'f1': 0.12718378756114607, 'number': 757}, 'P': {'precision': 0.0653061224489796, 'recall': 0.01603206412825651, 'f1': 0.02574416733708769, 'number': 998}, 'overall_precision': 0.11643090315560392, 'overall_recall': 0.06096866096866097, 'overall_f1': 0.08002991772625281, 'overall_accuracy': 0.43445170727247795}
			------------EPOCH 8---------------
Loss:  tensor(330.4802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.5852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.8194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(654.7775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1315.8336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.3654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.7807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.4724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.6564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.1183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1211.5959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.1712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(938.9669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(802.6414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(817.9142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.1854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.5759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.9939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.4374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.2418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.1153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.4018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.7861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.9156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.1113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.0681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.8484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.1562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1482.2019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1238.9769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1698.4474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(936.6658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1233.7440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.2060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1247.7117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1052.9727, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20689655172413793, 'recall': 0.10303830911492734, 'f1': 0.13756613756613756, 'number': 757}, 'P': {'precision': 0.222007722007722, 'recall': 0.3456913827655311, 'f1': 0.27037617554858934, 'number': 998}, 'overall_precision': 0.21905748316934232, 'overall_recall': 0.24102564102564103, 'overall_f1': 0.22951709169831797, 'overall_accuracy': 0.5700050281117155}
			------------EPOCH 9---------------
Loss:  tensor(409.2422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.1380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.3641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(926.4225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(985.7979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.5221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.9500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.9304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.8918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.4590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1016.7578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.9484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.1420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.6254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.8358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.9703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.3691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.8550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.7119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.0890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.3521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.3463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.9127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.8322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(481.5282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1097.0958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(776.9886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.0842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1300.7744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1157.8280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1739.9910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1195.4905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1105.7332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.7881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.7604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.7928, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22641509433962265, 'recall': 0.095112285336856, 'f1': 0.133953488372093, 'number': 757}, 'P': {'precision': 0.10734463276836158, 'recall': 0.13326653306613226, 'f1': 0.11890925346446134, 'number': 998}, 'overall_precision': 0.13166345536287732, 'overall_recall': 0.1168091168091168, 'overall_f1': 0.12379227053140096, 'overall_accuracy': 0.5757873565845408}
			------------EPOCH 10---------------
Loss:  tensor(246.0635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.4883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.5593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(491.0586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(804.4923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.1752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.8496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(568.6259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(949.5914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(942.3289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1344.6284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.1902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1313.3098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.4630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.6492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.8287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(829.2046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.1461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.5790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(702.0637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.7230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.2741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(885.2070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.7814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.5078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(716.5199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.7518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.2792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(894.9014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(835.5154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1157.5518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.3388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(705.8804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.6516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(583.6111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.4290, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15313081215127092, 'recall': 0.32628797886393657, 'f1': 0.20843881856540084, 'number': 757}, 'P': {'precision': 0.2415966386554622, 'recall': 0.11523046092184369, 'f1': 0.1560379918588874, 'number': 998}, 'overall_precision': 0.1732886548587841, 'overall_recall': 0.20626780626780628, 'overall_f1': 0.1883454734651405, 'overall_accuracy': 0.5099419481647393}
			------------EPOCH 11---------------
Loss:  tensor(226.7006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.6086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.4392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(549.5397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(734.2644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.7267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.7298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.3457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.4169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.4912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(934.9207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.6423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.5258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.8704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(481.1153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.3785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.7906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.3193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.6401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.5513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.1599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.6161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.1864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.4761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.9276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.6416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.4967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.8382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(719.5652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(643.2302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(949.2004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.4930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(558.7610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.5114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.8618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.7661, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18195488721804512, 'recall': 0.15984147952443858, 'f1': 0.17018284106891704, 'number': 757}, 'P': {'precision': 0.1653372008701958, 'recall': 0.22845691382765532, 'f1': 0.1918384518300379, 'number': 998}, 'overall_precision': 0.17074363992172212, 'overall_recall': 0.19886039886039886, 'overall_f1': 0.18373256120031586, 'overall_accuracy': 0.6137724550898204}
			------------EPOCH 12---------------
Loss:  tensor(182.2020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.3406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.6810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.9657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(451.5998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.1674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.3450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.8007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.9492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.2792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.0989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.7113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.1631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.0760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.9364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.7847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.2665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.3841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.6166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.1902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.7882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.9092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.0076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.9052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.5920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.3813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.1753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.1070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(572.8706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.6265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(795.2390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.7293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.1868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.5044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.4992, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17342879872712808, 'recall': 0.28797886393659183, 'f1': 0.21648460774577954, 'number': 757}, 'P': {'precision': 0.20990312163616792, 'recall': 0.19539078156312625, 'f1': 0.2023871302542813, 'number': 998}, 'overall_precision': 0.1889295516925892, 'overall_recall': 0.23532763532763531, 'overall_f1': 0.20959147424511546, 'overall_accuracy': 0.5905060108790053}
			------------EPOCH 13---------------
Loss:  tensor(113.4576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.1384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.7859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.2892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.1122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.4261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.9487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.3315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.7969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.6069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.7942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.6113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.2137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.9922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.2725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.2946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.5629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.6744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.0228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.2294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.8780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.5640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.1060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.2419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.8514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.5397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.8411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.9075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.9700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.2951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.8017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.8972, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19956850053937433, 'recall': 0.24438573315719947, 'f1': 0.21971496437054633, 'number': 757}, 'P': {'precision': 0.18497109826589594, 'recall': 0.22444889779559118, 'f1': 0.20280669986419192, 'number': 998}, 'overall_precision': 0.19130028063610852, 'overall_recall': 0.23304843304843303, 'overall_f1': 0.21012072951451324, 'overall_accuracy': 0.6191891027106093}
			------------EPOCH 14---------------
Loss:  tensor(93.6279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.6591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.9998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.1866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.6665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.9286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.5881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.8173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.5413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.6658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.6252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.1402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.9840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.2379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.8370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.7914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.8383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.3025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.3412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.1921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.2823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.9933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.7582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.5255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.7503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.6826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.4961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.2735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.1853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.2853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.7798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.1654, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1832412523020258, 'recall': 0.2628797886393659, 'f1': 0.21595225176342916, 'number': 757}, 'P': {'precision': 0.21225983531564502, 'recall': 0.23246492985971945, 'f1': 0.2219033955045433, 'number': 998}, 'overall_precision': 0.19779715465810005, 'overall_recall': 0.2455840455840456, 'overall_f1': 0.21911540416878494, 'overall_accuracy': 0.6129496731727385}
			------------EPOCH 15---------------
Loss:  tensor(74.6829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.2072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.1410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.6629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.1836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.7559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.9206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.3358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.4247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.5081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.0885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.6431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.9072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.3842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.2107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.9204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.3906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.3679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.3609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.4066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.9138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.2054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.2081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.4504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.5491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.6915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.4765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.1576, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21253071253071254, 'recall': 0.2285336856010568, 'f1': 0.22024188415022278, 'number': 757}, 'P': {'precision': 0.19510385756676557, 'recall': 0.2635270541082164, 'f1': 0.22421142369991476, 'number': 998}, 'overall_precision': 0.20166512488436633, 'overall_recall': 0.24843304843304842, 'overall_f1': 0.2226193515445494, 'overall_accuracy': 0.6214060428760799}
			------------EPOCH 16---------------
Loss:  tensor(58.6248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.8021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.6026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.7336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.8697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.8265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.8437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.4274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.2971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.7792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.5043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.8626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.4127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.2015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.9747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.8148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.1386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.8973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.9214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(688.6481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.7271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.4046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.5871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.4164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.4967, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17432784041630528, 'recall': 0.2655217965653897, 'f1': 0.21047120418848167, 'number': 757}, 'P': {'precision': 0.19326923076923078, 'recall': 0.20140280561122245, 'f1': 0.197252208047105, 'number': 998}, 'overall_precision': 0.18331053351573187, 'overall_recall': 0.22905982905982905, 'overall_f1': 0.20364741641337386, 'overall_accuracy': 0.5953284271152351}
			------------EPOCH 17---------------
Loss:  tensor(48.2646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.0858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.9316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.2192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.0315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.3858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.2644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.5171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.1323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.5714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.5934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.9842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.4711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.1015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.1436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.5779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.6454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.1926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.0521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.6083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.5757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.3913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.2910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.7363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.4948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.8702, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18165627782724844, 'recall': 0.26948480845442535, 'f1': 0.21702127659574466, 'number': 757}, 'P': {'precision': 0.2345309381237525, 'recall': 0.23547094188376755, 'f1': 0.235, 'number': 998}, 'overall_precision': 0.20658823529411766, 'overall_recall': 0.2501424501424501, 'overall_f1': 0.22628865979381443, 'overall_accuracy': 0.5869634776249029}
			------------EPOCH 18---------------
Loss:  tensor(41.0137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.7935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.5729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.0625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.5549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.1050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.5914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.6597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.6719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.9824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.4953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.8267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.3932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.5355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.9579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.9604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.4292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.7662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.0783, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20907079646017698, 'recall': 0.24966974900924702, 'f1': 0.2275737507525587, 'number': 757}, 'P': {'precision': 0.1875968992248062, 'recall': 0.24248496993987975, 'f1': 0.21153846153846156, 'number': 998}, 'overall_precision': 0.19644484958979033, 'overall_recall': 0.2455840455840456, 'overall_f1': 0.21828310964801215, 'overall_accuracy': 0.6162179457878136}
			------------EPOCH 19---------------
Loss:  tensor(30.0589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.7871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.8176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.0895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.3421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.5372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.2768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.3731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.0334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.0369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.3424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.7649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.7843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(412.8618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.9039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.2067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.5332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.3561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6566, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2023928215353938, 'recall': 0.26816380449141347, 'f1': 0.2306818181818182, 'number': 757}, 'P': {'precision': 0.20843881856540084, 'recall': 0.24749498997995992, 'f1': 0.22629409070087034, 'number': 998}, 'overall_precision': 0.2056672760511883, 'overall_recall': 0.2564102564102564, 'overall_f1': 0.22825259954349483, 'overall_accuracy': 0.6112583992320703}
			------------EPOCH 20---------------
Loss:  tensor(22.6378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.7095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.0285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.5373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.2061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.6143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.5443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.7934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.8956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.2328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.6924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.2740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.0717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.2145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.4406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.9208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7447, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21008403361344538, 'recall': 0.26420079260237783, 'f1': 0.23405500292568754, 'number': 757}, 'P': {'precision': 0.205233033524121, 'recall': 0.251503006012024, 'f1': 0.22602431337235476, 'number': 998}, 'overall_precision': 0.20735632183908045, 'overall_recall': 0.256980056980057, 'overall_f1': 0.22951653944020356, 'overall_accuracy': 0.6157836997760204}
			------------EPOCH 21---------------
Loss:  tensor(17.4697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.4101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.3929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.6797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.3367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.6543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.8909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.3763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.0861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.4929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.6274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.8788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5212, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20040485829959515, 'recall': 0.261558784676354, 'f1': 0.22693409742120343, 'number': 757}, 'P': {'precision': 0.18145483613109512, 'recall': 0.22745490981963928, 'f1': 0.20186749666518453, 'number': 998}, 'overall_precision': 0.1898168825368468, 'overall_recall': 0.24216524216524216, 'overall_f1': 0.2128192288432649, 'overall_accuracy': 0.6125611372674499}
			------------EPOCH 22---------------
Loss:  tensor(14.3221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.3693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.8796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.1161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.3388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.4373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.5420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.6856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.9619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.6992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.2789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.5883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.6248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.4412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3157, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21141649048625794, 'recall': 0.26420079260237783, 'f1': 0.2348796241926013, 'number': 757}, 'P': {'precision': 0.22447325769854132, 'recall': 0.2775551102204409, 'f1': 0.2482078853046595, 'number': 998}, 'overall_precision': 0.21880733944954128, 'overall_recall': 0.2717948717948718, 'overall_f1': 0.24243964421855146, 'overall_accuracy': 0.6143438314211273}
			------------EPOCH 23---------------
Loss:  tensor(11.8564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.8563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.2369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.0327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.8539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.7486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.8028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.7971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.2686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.3124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.2302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.8095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2216, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20102564102564102, 'recall': 0.25891677675033026, 'f1': 0.22632794457274827, 'number': 757}, 'P': {'precision': 0.1721698113207547, 'recall': 0.21943887775551102, 'f1': 0.19295154185022023, 'number': 998}, 'overall_precision': 0.1846906987093903, 'overall_recall': 0.23646723646723647, 'overall_f1': 0.20739630184907548, 'overall_accuracy': 0.6126297024272066}
			------------EPOCH 24---------------
Loss:  tensor(9.9697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.8424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.4806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.6952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.5251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.9772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.6738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.3204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.2077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.9829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.4458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4464, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20523560209424083, 'recall': 0.25891677675033026, 'f1': 0.22897196261682246, 'number': 757}, 'P': {'precision': 0.22598425196850394, 'recall': 0.2875751503006012, 'f1': 0.25308641975308643, 'number': 998}, 'overall_precision': 0.21707865168539325, 'overall_recall': 0.27521367521367524, 'overall_f1': 0.24271356783919598, 'overall_accuracy': 0.6126982675869634}
			------------EPOCH 25---------------
Loss:  tensor(8.4817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.9420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.3186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.3849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.5593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.5892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.5470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.1545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.5128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7939, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20540540540540542, 'recall': 0.2509907529722589, 'f1': 0.2259215219976219, 'number': 757}, 'P': {'precision': 0.18064024390243902, 'recall': 0.2374749498997996, 'f1': 0.2051948051948052, 'number': 998}, 'overall_precision': 0.19088064371926688, 'overall_recall': 0.2433048433048433, 'overall_f1': 0.21392785571142287, 'overall_accuracy': 0.615829409882525}
			------------EPOCH 26---------------
Loss:  tensor(7.1944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.4215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.8647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.1020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.7119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.6732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.9736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.8908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.6815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.1170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.9584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8526, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21321961620469082, 'recall': 0.26420079260237783, 'f1': 0.2359882005899705, 'number': 757}, 'P': {'precision': 0.2087912087912088, 'recall': 0.2665330661322645, 'f1': 0.2341549295774648, 'number': 998}, 'overall_precision': 0.21066907775768534, 'overall_recall': 0.2655270655270655, 'overall_f1': 0.23493824048399292, 'overall_accuracy': 0.6167664670658682}
			------------EPOCH 27---------------
Loss:  tensor(5.9589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.6131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.5381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.1899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.5652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.8100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.7360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.6637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.9656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.4785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.4330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.3491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.8836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8609, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1881720430107527, 'recall': 0.2774108322324967, 'f1': 0.22423918846769889, 'number': 757}, 'P': {'precision': 0.18671152228763668, 'recall': 0.22244488977955912, 'f1': 0.20301783264746232, 'number': 998}, 'overall_precision': 0.18741865509761388, 'overall_recall': 0.24615384615384617, 'overall_f1': 0.21280788177339902, 'overall_accuracy': 0.6088357635873292}
			------------EPOCH 28---------------
Loss:  tensor(5.3484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.4289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.7250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.8994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.7605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.1810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.8174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.2252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.6588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.3708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.0658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.2311, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22297297297297297, 'recall': 0.261558784676354, 'f1': 0.24072948328267477, 'number': 757}, 'P': {'precision': 0.1781874039938556, 'recall': 0.23246492985971945, 'f1': 0.20173913043478262, 'number': 998}, 'overall_precision': 0.1963470319634703, 'overall_recall': 0.245014245014245, 'overall_f1': 0.21799746514575413, 'overall_accuracy': 0.6150980481784523}
			------------EPOCH 29---------------
Loss:  tensor(5.5223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.0415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.2733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.3956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.7110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.3638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.9841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.6317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.8208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.2706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.8161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.9612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.2589, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.229404309252218, 'recall': 0.23910171730515192, 'f1': 0.23415265200517463, 'number': 757}, 'P': {'precision': 0.1818815331010453, 'recall': 0.26152304609218435, 'f1': 0.21454993834771888, 'number': 998}, 'overall_precision': 0.19874100719424462, 'overall_recall': 0.2518518518518518, 'overall_f1': 0.22216637346066848, 'overall_accuracy': 0.6191433926041048}
			------------EPOCH 30---------------
Loss:  tensor(5.4010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.4656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.7877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.0843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.7800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.4080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.6178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.8087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.5556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.9991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.8094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.4841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.1948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8875, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18909410729991205, 'recall': 0.28401585204755614, 'f1': 0.22703273495248152, 'number': 757}, 'P': {'precision': 0.17290108063175394, 'recall': 0.20841683366733466, 'f1': 0.1890049977283053, 'number': 998}, 'overall_precision': 0.18076923076923077, 'overall_recall': 0.24102564102564103, 'overall_f1': 0.2065934065934066, 'overall_accuracy': 0.6050646798007039}


		-------------RUN 3-----------
Test files: ['/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/248.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/72.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/71.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/74.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/78.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/76.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/77.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/73.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/75.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/21.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/251.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/73.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/92.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/93.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/28.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/308.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/90.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/82.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/85.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/84.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/86.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/83.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/25.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/289.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/85.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/84.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/277.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/81.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/329.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/96.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/261.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/76.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/77.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/80.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/79.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/81.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/23.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/10.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/11.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/8.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/12.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/5.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/0.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/1.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/0.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/1.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/258.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/75.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/29.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/10.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/72.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/69.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/71.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/70.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/19.xml']
			------------EPOCH 1---------------
Loss:  tensor(2740.2271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2893.2837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2930.6907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3649.6860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3480.9204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1986.9932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2323.5964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2728.1934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1822.3032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2742.6709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1887.8663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1910.3011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1945.7225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1939.4066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2527.6985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2139.6445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2729.0706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2216.5513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1632.2583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2453.6528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1710.5884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1529.7251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1419.2274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1942.9255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1558.6161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1900.7146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1669.3367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1645.6589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1416.8474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1884.0720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1186.6796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2027.9059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2981.4900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1366.6377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2464.8950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2929.3425, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 753}, 'P': {'precision': 0.0030120481927710845, 'recall': 0.0013192612137203166, 'f1': 0.0018348623853211008, 'number': 758}, 'overall_precision': 0.0024937655860349127, 'overall_recall': 0.0006618133686300463, 'overall_f1': 0.0010460251046025104, 'overall_accuracy': 0.4094386462660857}
			------------EPOCH 2---------------
Loss:  tensor(1781.8303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2048.2554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2259.0591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2559.2524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2634.1233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1452.4194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1952.4327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2067.5991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1435.7847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2254.6938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1310.5364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1373.0854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1618.9910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1651.8499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2111.4912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1709.0703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2514.4102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1887.3414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1426.7759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2211.6790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1572.2639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1335.9799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1158.6321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1710.7191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1370.5342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1752.7955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1550.1650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1441.9773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.5404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1665.7860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1002.5350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1741.5746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2612.5063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1199.1543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2206.0952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2635.7432, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.005917159763313609, 'recall': 0.0013280212483399733, 'f1': 0.0021691973969631237, 'number': 753}, 'P': {'precision': 0.043548387096774194, 'recall': 0.03562005277044855, 'f1': 0.039187227866473155, 'number': 758}, 'overall_precision': 0.035487959442332066, 'overall_recall': 0.018530774321641297, 'overall_f1': 0.02434782608695652, 'overall_accuracy': 0.47395886108014995}
			------------EPOCH 3---------------
Loss:  tensor(1525.2183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1843.9529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2133.2622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2309.2839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2429.3994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1285.6046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1923.0818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1923.0723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1300.6501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1924.3873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1111.8652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1171.0840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1455.5806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1615.8557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1875.4716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1349.2664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2184.2224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1658.8630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1265.1401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1986.7175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1452.3008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1203.4963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.5828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1513.9412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1195.7981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1505.0912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1376.7448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1273.0454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1147.4216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1570.4893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.8560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1574.3005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2086.0925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1047.1708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2004.6633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2404.4917, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.045454545454545456, 'recall': 0.03187250996015936, 'f1': 0.03747072599531616, 'number': 753}, 'P': {'precision': 0.11518858307849134, 'recall': 0.14907651715039577, 'f1': 0.12995974698102358, 'number': 758}, 'overall_precision': 0.09078860172299535, 'overall_recall': 0.09066843150231635, 'overall_f1': 0.09072847682119205, 'overall_accuracy': 0.5583899077920762}
			------------EPOCH 4---------------
Loss:  tensor(1298.8584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1612.1924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1789.3539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2004.8125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2121.4741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.8230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1763.3489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1639.0526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1161.4762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1757.8186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(911.0829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(989.4763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1310.7777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1604.9313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1684.3292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1126.0057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1929.3038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1521.7861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1147.3840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1790.3625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1232.6464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1017.3856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(913.3461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1300.9849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.5739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1213.0038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1128.6996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(942.7806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(980.2554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1342.4014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.6676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1320.4683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1871.0957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(885.4413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1773.6106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2130.8345, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.07821901323706378, 'recall': 0.08632138114209828, 'f1': 0.08207070707070706, 'number': 753}, 'P': {'precision': 0.15333333333333332, 'recall': 0.1820580474934037, 'f1': 0.16646562123039807, 'number': 758}, 'overall_precision': 0.1172732524552282, 'overall_recall': 0.1343481138318994, 'overall_f1': 0.12523133867982725, 'overall_accuracy': 0.5733610294862701}
			------------EPOCH 5---------------
Loss:  tensor(1139.9688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1423.5715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1431.3439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1703.7399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1777.3046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.5405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1555.1829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1351.8428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1025.5693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1554.0146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(720.0491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(797.5491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.4694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1429.8430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1438.3687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.2767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1659.0129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1272.1038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(963.2930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1505.6060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1017.6096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(824.8289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.7501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1097.6995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(708.6882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.1265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(945.6624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(662.8881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.3780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.6863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.0408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1058.5798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1699.9280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(650.4487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1512.3508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1775.6389, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11824324324324324, 'recall': 0.18592297476759628, 'f1': 0.14455343314403718, 'number': 753}, 'P': {'precision': 0.1276595744680851, 'recall': 0.10290237467018469, 'f1': 0.1139517896274653, 'number': 758}, 'overall_precision': 0.12144846796657381, 'overall_recall': 0.1442753143613501, 'overall_f1': 0.13188142770719904, 'overall_accuracy': 0.5731583747086838}
			------------EPOCH 6---------------
Loss:  tensor(977.9648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1286.2377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1154.9124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1424.8087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1471.2643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(627.5093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1285.3151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1090.8953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(879.2391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1330.6691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.1080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.2609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.5706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1265.3141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1215.9022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(755.5465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1443.0583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1106.7744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(791.6647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1321.2032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(858.0515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.4689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.0839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(962.4243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.1140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.9577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(718.1580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(496.1635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.2837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.9930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.0869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(813.2588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1376.1753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.2865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1190.8762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1477.9032, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10107197549770292, 'recall': 0.1752988047808765, 'f1': 0.12821758135017, 'number': 753}, 'P': {'precision': 0.09768637532133675, 'recall': 0.05013192612137203, 'f1': 0.06625980819529205, 'number': 758}, 'overall_precision': 0.10029498525073746, 'overall_recall': 0.11250827266710788, 'overall_f1': 0.10605115408608859, 'overall_accuracy': 0.5196068497314824}
			------------EPOCH 7---------------
Loss:  tensor(795.6202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1115.6862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.0341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1308.7982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1305.9539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.6281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1170.3870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1015.0771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(760.6666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1259.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.9414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.7449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(793.5700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.6886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(967.7678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.3735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1174.3173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(918.9261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.4236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1086.7218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(750.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.2803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.2269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(948.8434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.3860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.6626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(777.8920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.6429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(719.3308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(968.4733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.4205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1003.4319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1508.9758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.9793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1551.0493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1561.6572, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1292270531400966, 'recall': 0.14209827357237717, 'f1': 0.1353573687539532, 'number': 753}, 'P': {'precision': 0.09814323607427056, 'recall': 0.09762532981530343, 'f1': 0.09788359788359789, 'number': 758}, 'overall_precision': 0.11441213653603034, 'overall_recall': 0.11978821972203839, 'overall_f1': 0.11703847397348852, 'overall_accuracy': 0.541696220488398}
			------------EPOCH 8---------------
Loss:  tensor(676.8997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(945.8129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.4780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1020.5442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1144.8822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.8849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.7056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(795.0587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(831.4291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1596.4465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.9802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.1569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(980.6694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(886.1038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1322.9808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1015.2172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1819.2930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1010.0500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(838.9078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1380.8557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.3953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.4683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(566.8928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.9800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.3416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.5968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.2302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.6304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(481.0782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.7771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.6725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(721.4208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1456.7979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.8622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1491.6157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1570.0488, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23776223776223776, 'recall': 0.0451527224435591, 'f1': 0.07589285714285715, 'number': 753}, 'P': {'precision': 0.17472118959107807, 'recall': 0.3100263852242744, 'f1': 0.2234902520209225, 'number': 758}, 'overall_precision': 0.18077956989247312, 'overall_recall': 0.17802779616148245, 'overall_f1': 0.17939313104368124, 'overall_accuracy': 0.525103860573513}
			------------EPOCH 9---------------
Loss:  tensor(1136.5906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1354.2949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1680.6151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1799.6069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1833.9084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1054.9901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1494.7654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1372.7797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(884.8000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.0188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.1423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(549.9816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(699.5591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(822.9780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(893.8282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.0740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1020.3694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.9346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.8541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1093.3789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(750.2222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.6726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.3621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(663.8726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.6415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(699.4668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.7290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.6576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(921.1904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1121.6118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.1121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(866.2651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1123.3301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.2265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1218.0867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1620.0118, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14583333333333334, 'recall': 0.20451527224435592, 'f1': 0.17025981205085683, 'number': 753}, 'P': {'precision': 0.16511318242343542, 'recall': 0.16358839050131926, 'f1': 0.16434724983432739, 'number': 758}, 'overall_precision': 0.15384615384615385, 'overall_recall': 0.1839841164791529, 'overall_f1': 0.16757082579867388, 'overall_accuracy': 0.5699665619616983}
			------------EPOCH 10---------------
Loss:  tensor(579.1079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(822.6307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.0635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(846.7127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(895.7414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.4817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(778.0421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.8997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.6877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1219.8729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.3705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(718.2734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(795.0103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.2880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(565.4073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1012.6936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.6550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.9389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.2304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(536.2849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.7827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.2256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.1273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.9672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.1229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.5762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.8460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.9589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.7084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.4261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.6907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1343.0276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.9039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1029.6587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1344.9070, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2306368330464716, 'recall': 0.17795484727755645, 'f1': 0.20089955022488756, 'number': 753}, 'P': {'precision': 0.2680320569902048, 'recall': 0.3970976253298153, 'f1': 0.32004253056884635, 'number': 758}, 'overall_precision': 0.25528169014084506, 'overall_recall': 0.2878888153540701, 'overall_f1': 0.27060653188180406, 'overall_accuracy': 0.5893200932211977}
			------------EPOCH 11---------------
Loss:  tensor(750.5671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1116.2450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1072.8643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(977.4260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(878.8087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.8531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1076.2925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(764.4747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.3729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(911.1250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.1386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.5571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.2078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.5283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.7286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.4118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.8472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.6468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(817.5321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(802.2133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.2987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(483.9557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.6389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.1462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(797.0466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(772.4733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(404.6904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.4263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.2576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.7635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.7517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1102.2950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.5898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(716.8916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(896.0251, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20309050772626933, 'recall': 0.24435590969455512, 'f1': 0.2218203737191079, 'number': 753}, 'P': {'precision': 0.25, 'recall': 0.31398416886543534, 'f1': 0.2783625730994152, 'number': 758}, 'overall_precision': 0.2271259418729817, 'overall_recall': 0.27928524156187956, 'overall_f1': 0.25051944197091125, 'overall_accuracy': 0.5981355760462053}
			------------EPOCH 12---------------
Loss:  tensor(552.2651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.5110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(624.9099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.5990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.9221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.4013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(902.3090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.0282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(663.8624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1063.3057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.8286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.7743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.5957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1105.8267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1104.7407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.8535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.4135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(879.0534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.8262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1164.1467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(618.8942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.7829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.4320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.1653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.8328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.0931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.4726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.9644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.1725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.3188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.6408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.3863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.8345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.6090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(665.4940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(806.2028, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1373913043478261, 'recall': 0.1049136786188579, 'f1': 0.11897590361445784, 'number': 753}, 'P': {'precision': 0.10531220876048462, 'recall': 0.14907651715039577, 'f1': 0.12342981977061714, 'number': 758}, 'overall_precision': 0.11650485436893204, 'overall_recall': 0.1270681667769689, 'overall_f1': 0.12155745489078823, 'overall_accuracy': 0.5756408957341169}
			------------EPOCH 13---------------
Loss:  tensor(515.6742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(639.6687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(498.7173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.9948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.9738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.8725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.7480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.4781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.7334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(779.9305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.6249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.0368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.5288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.1812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.7532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.1492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.9263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.4306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.0441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.6863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.9899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.9333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.1319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.5649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.0502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.0448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.1982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.6405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.9731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.2172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.7189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.4272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.6858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.5418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.2435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.1588, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18202764976958524, 'recall': 0.2098273572377158, 'f1': 0.19494139420111042, 'number': 753}, 'P': {'precision': 0.19575699132111862, 'recall': 0.2678100263852243, 'f1': 0.22618384401114205, 'number': 758}, 'overall_precision': 0.18950131233595802, 'overall_recall': 0.23891462607544672, 'overall_f1': 0.21135831381733022, 'overall_accuracy': 0.6054564798865133}
			------------EPOCH 14---------------
Loss:  tensor(330.5357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.7819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.4061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.9006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.5711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.4991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.9911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.0331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.6787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(627.2192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.3634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.2946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.4084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.2278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.8653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.4639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.2609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.1184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.2702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.3518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.8320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.4284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.7338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.4629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.2782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.9490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.7033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.8898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.6474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.2350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.1537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.0531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.0732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.9048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.1808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.2626, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1671388101983003, 'recall': 0.15670650730411687, 'f1': 0.16175462645647704, 'number': 753}, 'P': {'precision': 0.17888307155322863, 'recall': 0.2704485488126649, 'f1': 0.21533613445378152, 'number': 758}, 'overall_precision': 0.1744060475161987, 'overall_recall': 0.21376571806750497, 'overall_f1': 0.19209039548022597, 'overall_accuracy': 0.6061404397608674}
			------------EPOCH 15---------------
Loss:  tensor(296.7917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.2162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.1356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.7870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.8719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.5418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.9587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.7744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.7326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.6335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.8480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.5360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.4410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.6017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.0547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.5324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.3918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.6819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.8236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.5459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.3154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.7634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.9284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.3109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.2926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.0189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.1258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.9044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.3995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.5630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.9330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.4440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.2743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.8429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.6228, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19682959048877147, 'recall': 0.19787516600265603, 'f1': 0.19735099337748344, 'number': 753}, 'P': {'precision': 0.18313689936536717, 'recall': 0.26649076517150394, 'f1': 0.21708758731864589, 'number': 758}, 'overall_precision': 0.18870967741935485, 'overall_recall': 0.23229649238914626, 'overall_f1': 0.2082468110353011, 'overall_accuracy': 0.6087749518694904}
			------------EPOCH 16---------------
Loss:  tensor(241.7835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.3996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.0829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.6960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.3946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.7349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.7102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.2946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.2888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.8011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.8220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.0933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.8902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.6049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.8864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.6361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.1594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.4196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.0387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.2875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.3230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.2718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.8952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.4086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.1245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.4138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.8495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.7609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.9763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.8586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.0963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.2006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.9615, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16945373467112598, 'recall': 0.20185922974767595, 'f1': 0.18424242424242426, 'number': 753}, 'P': {'precision': 0.1604032997250229, 'recall': 0.23087071240105542, 'f1': 0.18929150892374255, 'number': 758}, 'overall_precision': 0.16448692152917505, 'overall_recall': 0.21641297154202516, 'overall_f1': 0.18691054587024866, 'overall_accuracy': 0.6046711926233661}
			------------EPOCH 17---------------
Loss:  tensor(206.3975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.0762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.0223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.5049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.3195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.9842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.5552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.4247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.4761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.5586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.2915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.1561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.7885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.7471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.8070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.7949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.4248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.6502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.8163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.4353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.3683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.9521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.7558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.0814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.7051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.8753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.9200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.8243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.1653, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20323741007194246, 'recall': 0.150066401062417, 'f1': 0.17265087853323147, 'number': 753}, 'P': {'precision': 0.16925465838509315, 'recall': 0.287598944591029, 'f1': 0.2130987292277615, 'number': 758}, 'overall_precision': 0.17950108459869848, 'overall_recall': 0.21906022501654535, 'overall_f1': 0.19731743666169896, 'overall_accuracy': 0.5928918836761576}
			------------EPOCH 18---------------
Loss:  tensor(192.6452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.2040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.4822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.5728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.9470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.8865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.6250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.1368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.5919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.5066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.1621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.8392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.6863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.8512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.4223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.1299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.6871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.8025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.4138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.4688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.5551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.6187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.0737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.4388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.4412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.4135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.7543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.6193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.0708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.2051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.2100, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16276703967446593, 'recall': 0.21248339973439576, 'f1': 0.18433179723502302, 'number': 753}, 'P': {'precision': 0.164, 'recall': 0.21635883905013192, 'f1': 0.18657565415244598, 'number': 758}, 'overall_precision': 0.16338880484114976, 'overall_recall': 0.21442753143613502, 'overall_f1': 0.1854607899255867, 'overall_accuracy': 0.6019100212787516}
			------------EPOCH 19---------------
Loss:  tensor(194.1246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.3990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.8607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.6864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.0033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.1062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.4381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.0436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.2892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.7718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.5655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.3338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.4157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.7271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.4492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.4748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.3142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.8715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.0282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.2201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.8488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.2718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.9520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.8332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.5752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.5165, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19500780031201248, 'recall': 0.16600265604249667, 'f1': 0.1793400286944046, 'number': 753}, 'P': {'precision': 0.1645367412140575, 'recall': 0.2717678100263852, 'f1': 0.20497512437810944, 'number': 758}, 'overall_precision': 0.17485472794506074, 'overall_recall': 0.21906022501654535, 'overall_f1': 0.19447708578143363, 'overall_accuracy': 0.6072043773431959}
			------------EPOCH 20---------------
Loss:  tensor(188.3839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.5894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.6989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.0939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.2775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.7218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.3413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.1900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.2417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.5623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.8575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.3078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.6407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.9999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.2248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.4395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.7292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.0541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.3781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.8372, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1842410196987254, 'recall': 0.21115537848605578, 'f1': 0.1967821782178218, 'number': 753}, 'P': {'precision': 0.1696014828544949, 'recall': 0.24142480211081793, 'f1': 0.19923788786064234, 'number': 758}, 'overall_precision': 0.17610710607621008, 'overall_recall': 0.22634017207147583, 'overall_f1': 0.19808861859252822, 'overall_accuracy': 0.6017580301955618}
			------------EPOCH 21---------------
Loss:  tensor(138.8755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.6790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.4136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.8028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.0130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.6843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.0120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.0931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.8738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.2372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.5513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.5477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.2138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.5945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.4906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.9058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.7303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.2145, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18708827404479578, 'recall': 0.18857901726427623, 'f1': 0.18783068783068782, 'number': 753}, 'P': {'precision': 0.16652858326429162, 'recall': 0.26517150395778366, 'f1': 0.2045801526717557, 'number': 758}, 'overall_precision': 0.17446592065106817, 'overall_recall': 0.22700198544010589, 'overall_f1': 0.19729651998849584, 'overall_accuracy': 0.6079896646063431}
			------------EPOCH 22---------------
Loss:  tensor(104.9057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.7241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.8626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.2785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.3791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.9659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.8276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.4198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.3661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.8265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.0179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.4046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.7809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.5519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.3406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.9908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.0469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.3158, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19848293299620734, 'recall': 0.20849933598937584, 'f1': 0.20336787564766837, 'number': 753}, 'P': {'precision': 0.15775862068965518, 'recall': 0.24142480211081793, 'f1': 0.1908237747653806, 'number': 758}, 'overall_precision': 0.17426960533059968, 'overall_recall': 0.22501654533421575, 'overall_f1': 0.19641825534373195, 'overall_accuracy': 0.6052791569561252}
			------------EPOCH 23---------------
Loss:  tensor(81.0741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.7751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.5173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.2396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.0878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.2350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.3223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.5323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.5111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.3732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.5361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.2677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.7106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.6187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.6310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.1781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.1336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.5000, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18102372034956304, 'recall': 0.19256308100929614, 'f1': 0.18661518661518658, 'number': 753}, 'P': {'precision': 0.16284779050736498, 'recall': 0.262532981530343, 'f1': 0.201010101010101, 'number': 758}, 'overall_precision': 0.17004448838358874, 'overall_recall': 0.22766379880873594, 'overall_f1': 0.19468024900962083, 'overall_accuracy': 0.6062417671496606}
			------------EPOCH 24---------------
Loss:  tensor(69.1310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.7597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.7726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.9493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.8509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.0519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.9527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.6645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.6516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.8274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.2224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.6091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.2420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.4615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.2315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.2657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.4615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.4852, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19310344827586207, 'recall': 0.18592297476759628, 'f1': 0.18944519621109607, 'number': 753}, 'P': {'precision': 0.1718213058419244, 'recall': 0.2638522427440633, 'f1': 0.20811654526534862, 'number': 758}, 'overall_precision': 0.17998941238750663, 'overall_recall': 0.22501654533421575, 'overall_f1': 0.19999999999999998, 'overall_accuracy': 0.6035312594994428}
			------------EPOCH 25---------------
Loss:  tensor(125.5194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.8819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.5726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.1613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.0336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.4353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.3345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.2401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.4921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.0319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.2683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.5004, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18681318681318682, 'recall': 0.20318725099601595, 'f1': 0.1946564885496183, 'number': 753}, 'P': {'precision': 0.164043082021541, 'recall': 0.2612137203166227, 'f1': 0.2015267175572519, 'number': 758}, 'overall_precision': 0.1732477788746298, 'overall_recall': 0.23229649238914626, 'overall_f1': 0.1984732824427481, 'overall_accuracy': 0.6060391123720742}
			------------EPOCH 26---------------
Loss:  tensor(299.1656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.0219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.4123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.3796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.7108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.0223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.9433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.0520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.7604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.1315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.2623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.1603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.3356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.3802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.3531, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19382022471910113, 'recall': 0.18326693227091634, 'f1': 0.18839590443686005, 'number': 753}, 'P': {'precision': 0.18294701986754966, 'recall': 0.29155672823219, 'f1': 0.22482197355035607, 'number': 758}, 'overall_precision': 0.18697916666666667, 'overall_recall': 0.23759099933818664, 'overall_f1': 0.20926843485864177, 'overall_accuracy': 0.6109788225757422}
			------------EPOCH 27---------------
Loss:  tensor(85.4309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.5772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.6313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.6631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.7486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.2219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.9971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.3484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.4218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.3885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.7389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.3241, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17122473246135553, 'recall': 0.19123505976095617, 'f1': 0.1806775407779172, 'number': 753}, 'P': {'precision': 0.14156378600823044, 'recall': 0.22691292875989447, 'f1': 0.17435377597567156, 'number': 758}, 'overall_precision': 0.15369649805447472, 'overall_recall': 0.20913302448709464, 'overall_f1': 0.17717970283151108, 'overall_accuracy': 0.6059124531360827}
			------------EPOCH 28---------------
Loss:  tensor(82.1308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.6875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.5757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.5599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.3001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.7737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.9368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.5354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.7589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.6167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.1890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.6540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.2475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.5503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.7776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.9788, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18867924528301888, 'recall': 0.18592297476759628, 'f1': 0.18729096989966554, 'number': 753}, 'P': {'precision': 0.18355481727574752, 'recall': 0.29155672823219, 'f1': 0.2252803261977574, 'number': 758}, 'overall_precision': 0.1855087358684481, 'overall_recall': 0.23891462607544672, 'overall_f1': 0.20885160543824124, 'overall_accuracy': 0.6103201945485864}
			------------EPOCH 29---------------
Loss:  tensor(55.4002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.4674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.9042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.1284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.8764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.3869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.2791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.7701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.0422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.5098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.3333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.8078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.2912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.6285, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.184863523573201, 'recall': 0.19787516600265603, 'f1': 0.19114817190506736, 'number': 753}, 'P': {'precision': 0.14585079631181894, 'recall': 0.22955145118733508, 'f1': 0.17837006663249616, 'number': 758}, 'overall_precision': 0.1615807903951976, 'overall_recall': 0.21376571806750497, 'overall_f1': 0.18404558404558405, 'overall_accuracy': 0.6079136690647482}
			------------EPOCH 30---------------
Loss:  tensor(49.4058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.0228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.5836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.6300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.7758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.1451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.6718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.8709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.2282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.9375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.7973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.1765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.7033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.7711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.4764, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18733850129198967, 'recall': 0.19256308100929614, 'f1': 0.1899148657498363, 'number': 753}, 'P': {'precision': 0.1697019867549669, 'recall': 0.2704485488126649, 'f1': 0.20854526958290945, 'number': 758}, 'overall_precision': 0.17658930373360243, 'overall_recall': 0.2316346790205162, 'overall_f1': 0.2004008016032064, 'overall_accuracy': 0.6085469652447056}


		-------------RUN 4-----------
Test files: ['/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/95.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/94.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/29.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/32.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/11.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/12.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/301.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/88.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/261.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/76.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/77.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/266.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/80.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/91.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/88.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/90.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/87.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/27.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/224.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/67.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/329.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/96.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/0.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/1.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/0.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/1.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/248.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/72.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/71.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/80.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/79.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/81.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/23.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/277.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/81.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/308.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/90.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/302.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/89.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/10.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/11.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/8.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/12.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/5.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/309.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/92.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/91.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/93.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/318.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/95.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/94.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/279.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/82.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/83.xml']
			------------EPOCH 1---------------
Loss:  tensor(3511.5879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1946.8544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2803.6531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2597.1533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2581.5776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2051.3994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3228.6470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3526.9746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1702.2225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2511.8567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1645.1783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2526.4700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1506.6935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1160.7985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1313.7253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(976.3113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2563.4995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2011.5743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1528.9587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1283.8193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1923.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1735.8826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1607.8403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1198.0746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1364.0808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1336.9888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1869.3396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.5453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2069.5771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1085.6216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2327.6682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1384.7817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2730.4302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2467.9270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(718.8586, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.011025358324145534, 'recall': 0.03694581280788178, 'f1': 0.01698273422020945, 'number': 812}, 'P': {'precision': 0.020761245674740483, 'recall': 0.006103763987792472, 'f1': 0.009433962264150943, 'number': 983}, 'overall_precision': 0.011960132890365448, 'overall_recall': 0.020055710306406686, 'overall_f1': 0.014984391259105098, 'overall_accuracy': 0.41149444490852893}
			------------EPOCH 2---------------
Loss:  tensor(2876.4746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1585.5498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2348.0945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2056.8796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2349.9048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1906.8672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2666.1582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3085.9138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1430.9441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2322.0317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1550.6516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2249.5190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1258.3596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(982.8481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1129.4927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.2123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2318.3027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1695.3230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1254.3459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1108.1790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1709.9269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1639.0490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1519.2955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1105.8218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1257.6665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1268.4237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1804.8540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1173.5336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2028.2688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1015.9561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2099.4543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1350.3975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2497.5557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2146.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.5585, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 812}, 'P': {'precision': 0.04523107177974434, 'recall': 0.04679552390640895, 'f1': 0.046, 'number': 983}, 'overall_precision': 0.03394833948339483, 'overall_recall': 0.02562674094707521, 'overall_f1': 0.029206349206349208, 'overall_accuracy': 0.4803065742210342}
			------------EPOCH 3---------------
Loss:  tensor(2313.7312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1376.3063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1871.9493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1611.8745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1920.8386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1469.8735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2374.9485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2687.5432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1270.5479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2004.3464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1321.8206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2043.6140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1135.6113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(860.8327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(959.7313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.6360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2149.9321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1506.5906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1096.4396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.4958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1482.9490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1443.6823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1322.5325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(971.7367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1073.7172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.2596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1541.2148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(916.7443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1723.6697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.5125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1919.1024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1034.9485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2019.0173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2000.5917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.0255, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.029697315819531698, 'recall': 0.06403940886699508, 'f1': 0.04057744830277019, 'number': 812}, 'P': {'precision': 0.08989805375347544, 'recall': 0.09867751780264497, 'f1': 0.09408341416100872, 'number': 983}, 'overall_precision': 0.05265017667844523, 'overall_recall': 0.083008356545961, 'overall_f1': 0.06443243243243242, 'overall_accuracy': 0.5485548408654248}
			------------EPOCH 4---------------
Loss:  tensor(2172.3809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1217.5994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1795.6179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1393.4004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1697.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1302.5654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1995.7582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2448.7639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1084.8008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1721.1946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1158.7844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1842.3682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(982.3687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.1957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(765.9470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.9800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1899.9019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1197.6910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(772.8011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.5729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1206.8267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1352.9860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1185.0046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(863.6486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(914.4537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(981.6305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1443.4980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(879.4753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1721.3149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.4535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1631.1484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(968.3729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1734.5980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1696.7455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.3909, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.047396138092451724, 'recall': 0.09975369458128079, 'f1': 0.064260214200714, 'number': 812}, 'P': {'precision': 0.1283987915407855, 'recall': 0.17293997965412003, 'f1': 0.14737754659731253, 'number': 983}, 'overall_precision': 0.08275634685130234, 'overall_recall': 0.13983286908077994, 'overall_f1': 0.103976801988401, 'overall_accuracy': 0.5646353688079525}
			------------EPOCH 5---------------
Loss:  tensor(1924.2346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(984.2711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1436.9845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1081.0549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1360.8091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1025.8246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1724.4194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2056.0093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(933.7369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1445.0051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.9136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1487.6138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.0308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.6511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.2501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(578.4656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1577.7366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.9360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.6122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(576.9727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(843.6495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1124.3442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.2717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(749.9357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(714.5493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(813.4579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1192.8835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(668.6610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1420.1809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.2132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1351.4304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(741.8209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1389.3396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1426.8752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.9422, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0639367816091954, 'recall': 0.10960591133004927, 'f1': 0.0807622504537205, 'number': 812}, 'P': {'precision': 0.18232044198895028, 'recall': 0.2685656154628688, 'f1': 0.21719457013574658, 'number': 983}, 'overall_precision': 0.12429577464788732, 'overall_recall': 0.1966573816155989, 'overall_f1': 0.152319309600863, 'overall_accuracy': 0.5704828335143263}
			------------EPOCH 6---------------
Loss:  tensor(1648.9675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.0808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1108.4426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.6694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1094.4971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.4447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1480.5431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1715.2251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(720.6317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1202.1663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.2365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1185.7925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.2489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.7641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.7095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.1675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1257.8749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.3799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.4634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.6092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.5065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(950.0721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.3668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(648.3301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.2131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.4485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(966.9184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.7566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1257.4097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.0960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1078.6251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.3022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1317.6971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1417.1772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.5478, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12015888778550149, 'recall': 0.14901477832512317, 'f1': 0.13304013194062672, 'number': 812}, 'P': {'precision': 0.2300635144671842, 'recall': 0.3316378433367243, 'f1': 0.27166666666666667, 'number': 983}, 'overall_precision': 0.1844059405940594, 'overall_recall': 0.249025069637883, 'overall_f1': 0.2118985541597535, 'overall_accuracy': 0.5829086960153704}
			------------EPOCH 7---------------
Loss:  tensor(1476.3666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.6414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(834.3356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.9516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(873.0811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.2144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1262.6042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1374.4045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.0459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(962.5367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(682.7346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(925.2145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(539.2538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.0640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.5047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.9443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1216.3809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.7603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.1001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.3771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(521.8392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.2147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(654.8680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.0876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.9391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.3751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.3513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.5032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1164.4795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.8541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.8038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.3888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1080.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1287.5537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.8156, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11409395973154363, 'recall': 0.2512315270935961, 'f1': 0.15692307692307694, 'number': 812}, 'P': {'precision': 0.2591397849462366, 'recall': 0.2451678535096643, 'f1': 0.2519602718243597, 'number': 983}, 'overall_precision': 0.1637233259749816, 'overall_recall': 0.2479108635097493, 'overall_f1': 0.19720806558830048, 'overall_accuracy': 0.5381547072090886}
			------------EPOCH 8---------------
Loss:  tensor(1711.3623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.4114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.5671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.9904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(898.0759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(783.7904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1187.5974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1542.0889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(693.7694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1190.4407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(799.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1267.1703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(560.3438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.0306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.5723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.8326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1198.4387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(497.9299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.5835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.4935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(498.7395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(826.2583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.1549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.9938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.9840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.4089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.6196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(521.4858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1262.9421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.3279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.3365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(616.5914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1223.4219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1200.2195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.2141, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.07237746220797069, 'recall': 0.19458128078817735, 'f1': 0.10550918196994992, 'number': 812}, 'P': {'precision': 0.07721639656816015, 'recall': 0.08240081383519837, 'f1': 0.0797244094488189, 'number': 983}, 'overall_precision': 0.0739480198019802, 'overall_recall': 0.1331476323119777, 'overall_f1': 0.0950865327232942, 'overall_accuracy': 0.5654707209088631}
			------------EPOCH 9---------------
Loss:  tensor(1379.4417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.4152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1097.4738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(894.7189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(821.2181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.1229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1054.9945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1300.1060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.4633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(968.2872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(694.6962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1037.2051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.5783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.0905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.7549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.4886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.5232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(412.3542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.4736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.0456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(724.2302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1058.8624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.2094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.5365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.8539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(733.4667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1185.2483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(577.1233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1313.7335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.3663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(928.9291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(498.5923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1076.6226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1139.8218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.8540, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16374871266735325, 'recall': 0.1958128078817734, 'f1': 0.1783510936623668, 'number': 812}, 'P': {'precision': 0.23843416370106763, 'recall': 0.340793489318413, 'f1': 0.280569514237856, 'number': 983}, 'overall_precision': 0.2079124579124579, 'overall_recall': 0.27520891364902506, 'overall_f1': 0.23687365140254138, 'overall_accuracy': 0.5822195305321193}
			------------EPOCH 10---------------
Loss:  tensor(1187.7263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.1320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(585.8568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.2068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.5851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.0528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(814.1073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(995.3082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.4026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.1072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.5370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.8009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.1224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.3623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.0688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.5114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.3297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.2874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.1705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.9664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.3499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.7417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.8558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.9861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.2335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.7565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.7555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.8793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(901.6357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.2685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.3869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.5725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(720.4601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(721.9306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.3986, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0935720097640358, 'recall': 0.1416256157635468, 'f1': 0.11268985791278785, 'number': 812}, 'P': {'precision': 0.14861995753715498, 'recall': 0.2136317395727365, 'f1': 0.17529215358931555, 'number': 983}, 'overall_precision': 0.12301286903860711, 'overall_recall': 0.181058495821727, 'overall_f1': 0.14649537976109983, 'overall_accuracy': 0.5934132486843204}
			------------EPOCH 11---------------
Loss:  tensor(969.3522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.0146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.2342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.4821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.9939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.5256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.7238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(855.5341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.1170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.0479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(404.4822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.4374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.3794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.5421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.4983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.1327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.6169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.8070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.8585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.0114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.8051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(568.3026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.4707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.2523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.7480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.1106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.8451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.3287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(786.0298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.0579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.4238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.7341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.1342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.3508, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13705179282868526, 'recall': 0.21182266009852216, 'f1': 0.1664247701983551, 'number': 812}, 'P': {'precision': 0.21288515406162464, 'recall': 0.30925737538148523, 'f1': 0.2521775197013687, 'number': 983}, 'overall_precision': 0.1774133432724562, 'overall_recall': 0.26518105849582174, 'overall_f1': 0.21259490844126844, 'overall_accuracy': 0.5947498120457773}
			------------EPOCH 12---------------
Loss:  tensor(844.4835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.9208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.3911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.3304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.9163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.5899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.9422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(619.2607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.2382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.1166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.9937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.3260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.3103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.7966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.5408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.6546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.3983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.8187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.8486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.2522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.5502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.1799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.7296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.1647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.5388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.9955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.9227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.3465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.9909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.2193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.8657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.1398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.5176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(441.1755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.4192, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13430127041742287, 'recall': 0.18226600985221675, 'f1': 0.15464994775339602, 'number': 812}, 'P': {'precision': 0.1585195530726257, 'recall': 0.23092573753814852, 'f1': 0.18799171842650103, 'number': 983}, 'overall_precision': 0.1479873717442778, 'overall_recall': 0.20891364902506965, 'overall_f1': 0.17325017325017322, 'overall_accuracy': 0.6055885055550915}
			------------EPOCH 13---------------
Loss:  tensor(700.9146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.0681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.5660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.6574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.3195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.6791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.1410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.7934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.7430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.9830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.5815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.6399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.4163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.1473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.7575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.0347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.3704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.8411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.3285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.2173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.0247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.4096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.9890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.9128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.8477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.0500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.6238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.5781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.9146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.9561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(419.9036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.1460, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1437037037037037, 'recall': 0.23891625615763548, 'f1': 0.17946345975948194, 'number': 812}, 'P': {'precision': 0.17827868852459017, 'recall': 0.26551373346897256, 'f1': 0.213322435635472, 'number': 983}, 'overall_precision': 0.16169154228855723, 'overall_recall': 0.25348189415041783, 'overall_f1': 0.19743979171186807, 'overall_accuracy': 0.5939353437473895}
			------------EPOCH 14---------------
Loss:  tensor(603.3794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.2269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.8615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.2682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.6851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.1427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.7916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.1122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.2255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.3642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.3203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.8019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.3898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.9695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.5996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.4777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.8424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.9611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.7942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.9329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.6698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.2866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.5010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.9901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.5848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.0148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.4774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.9560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.3520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.4125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.8044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1123, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15060240963855423, 'recall': 0.21551724137931033, 'f1': 0.17730496453900707, 'number': 812}, 'P': {'precision': 0.18970380818053598, 'recall': 0.2736520854526958, 'f1': 0.22407330279050397, 'number': 983}, 'overall_precision': 0.17209302325581396, 'overall_recall': 0.24735376044568244, 'overall_f1': 0.20297142857142858, 'overall_accuracy': 0.606423857656002}
			------------EPOCH 15---------------
Loss:  tensor(553.8372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.0608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.0713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.0166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.7311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.8456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.2928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.1218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.1790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.3833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.9818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.1260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.4243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.9441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.9918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.8738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.0995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.8527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.0984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.6611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.5561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.9317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.4621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.2721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.1478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.3427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.8052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.0936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3203, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1481164383561644, 'recall': 0.21305418719211822, 'f1': 0.17474747474747473, 'number': 812}, 'P': {'precision': 0.14592545799115603, 'recall': 0.23499491353001017, 'f1': 0.18004676539360873, 'number': 983}, 'overall_precision': 0.14685568884042166, 'overall_recall': 0.22506963788300835, 'overall_f1': 0.17773867135943686, 'overall_accuracy': 0.5983000584746471}
			------------EPOCH 16---------------
Loss:  tensor(499.2281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.1007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.5979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.5668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.5227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.6492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.0894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.3469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.3622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.7146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.8684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.8196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.1244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.7246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.3764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.2788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.2530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.6280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.7931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.8057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.8783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.7517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.1000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.5174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.5980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.8875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.5309, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15411558669001751, 'recall': 0.21674876847290642, 'f1': 0.18014329580348007, 'number': 812}, 'P': {'precision': 0.180669614655717, 'recall': 0.29094608341810785, 'f1': 0.22291504286827746, 'number': 983}, 'overall_precision': 0.16954128440366972, 'overall_recall': 0.2573816155988858, 'overall_f1': 0.20442477876106194, 'overall_accuracy': 0.5995739704285357}
			------------EPOCH 17---------------
Loss:  tensor(422.1796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.7828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.7242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.6875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.4981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.3045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.2663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.6729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.7597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.9957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.2367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.9908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.2501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.4247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.2807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.3589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.8803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3879, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15110759493670886, 'recall': 0.23522167487684728, 'f1': 0.18400770712909442, 'number': 812}, 'P': {'precision': 0.1665542818610924, 'recall': 0.25127161749745675, 'f1': 0.20032441200324413, 'number': 983}, 'overall_precision': 0.15944666909355662, 'overall_recall': 0.24401114206128133, 'overall_f1': 0.19286657859973583, 'overall_accuracy': 0.5956269317517333}
			------------EPOCH 18---------------
Loss:  tensor(378.0815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.0534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.2189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.1853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.3259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.3503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.6700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.5024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.2517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.2701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.3661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.8246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.9295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.6726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.7804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.9503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.6483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.2241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5730, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15664690939881457, 'recall': 0.22783251231527094, 'f1': 0.18564977420973408, 'number': 812}, 'P': {'precision': 0.17583892617449665, 'recall': 0.26653102746693796, 'f1': 0.21188839466235343, 'number': 983}, 'overall_precision': 0.16735305129165107, 'overall_recall': 0.249025069637883, 'overall_f1': 0.20017913121361397, 'overall_accuracy': 0.5941859493776627}
			------------EPOCH 19---------------
Loss:  tensor(367.6637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.0973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.2153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.1242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.8383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.5629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.9611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.2363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.9102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.2015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.1372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.6210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.7590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.6629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.8643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.2708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.2205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0379, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16144349477682812, 'recall': 0.20935960591133004, 'f1': 0.1823056300268097, 'number': 812}, 'P': {'precision': 0.1496559633027523, 'recall': 0.26551373346897256, 'f1': 0.1914191419141914, 'number': 983}, 'overall_precision': 0.15409367179120487, 'overall_recall': 0.24011142061281338, 'overall_f1': 0.1877177700348432, 'overall_accuracy': 0.5989892239578982}
			------------EPOCH 20---------------
Loss:  tensor(416.1047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.4637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.0181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.6993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.6746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.5615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.9374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.2001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.4156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.1063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.7977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.8531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.2312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.0352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8441, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14592545799115603, 'recall': 0.28448275862068967, 'f1': 0.19290187891440502, 'number': 812}, 'P': {'precision': 0.1941564561734213, 'recall': 0.20956256358087488, 'f1': 0.2015655577299413, 'number': 983}, 'overall_precision': 0.16527987897125568, 'overall_recall': 0.2434540389972145, 'overall_f1': 0.1968911917098446, 'overall_accuracy': 0.5761005763929496}
			------------EPOCH 21---------------
Loss:  tensor(537.2607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.4687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.6846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.6275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.2266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.1503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.0159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.0574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.4215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.2814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.0561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.2571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.6953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.5280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.8002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0826, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18766404199475065, 'recall': 0.17610837438423646, 'f1': 0.18170266836086404, 'number': 812}, 'P': {'precision': 0.16640665626625065, 'recall': 0.32553407934893186, 'f1': 0.22023399862353754, 'number': 983}, 'overall_precision': 0.17243947858473, 'overall_recall': 0.25793871866295265, 'overall_f1': 0.2066964285714286, 'overall_accuracy': 0.5932670620666611}
			------------EPOCH 22---------------
Loss:  tensor(392.8383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.4313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.7579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.0611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.8832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.6191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.6635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.2413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.8152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.8620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.0167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.7341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.7838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.9711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.8279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2169, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1575, 'recall': 0.3103448275862069, 'f1': 0.208955223880597, 'number': 812}, 'P': {'precision': 0.1484375, 'recall': 0.19328585961342828, 'f1': 0.16791869200176757, 'number': 983}, 'overall_precision': 0.15347222222222223, 'overall_recall': 0.24623955431754874, 'overall_f1': 0.18909090909090912, 'overall_accuracy': 0.5947289282432545}
			------------EPOCH 23---------------
Loss:  tensor(320.4512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.6750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.9964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.9458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.6877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.3529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.8937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.2908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.2204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.4574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.6326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.6047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5815, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2048780487804878, 'recall': 0.20689655172413793, 'f1': 0.20588235294117646, 'number': 812}, 'P': {'precision': 0.19201409277745154, 'recall': 0.3326551373346897, 'f1': 0.24348473566641846, 'number': 983}, 'overall_precision': 0.1961950059453032, 'overall_recall': 0.2757660167130919, 'overall_f1': 0.22927281148679945, 'overall_accuracy': 0.5956686993567789}
			------------EPOCH 24---------------
Loss:  tensor(296.0760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.1663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.2332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.3840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.6887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.5409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.3790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.5395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.5122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.6064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.6288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0963, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1487603305785124, 'recall': 0.2438423645320197, 'f1': 0.18478768082127858, 'number': 812}, 'P': {'precision': 0.14012345679012345, 'recall': 0.23092573753814852, 'f1': 0.174414137533615, 'number': 983}, 'overall_precision': 0.14401897661809557, 'overall_recall': 0.23676880222841226, 'overall_f1': 0.17909818794774549, 'overall_accuracy': 0.5958148859744382}
			------------EPOCH 25---------------
Loss:  tensor(289.9781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.1600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.6237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.2110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.2507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.9771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.7062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.8907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.0506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.9934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.7152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6533, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1984732824427481, 'recall': 0.2561576354679803, 'f1': 0.22365591397849463, 'number': 812}, 'P': {'precision': 0.1974900924702774, 'recall': 0.3041709053916582, 'f1': 0.23948738486183418, 'number': 983}, 'overall_precision': 0.19789227166276346, 'overall_recall': 0.28245125348189415, 'overall_f1': 0.23272894193252236, 'overall_accuracy': 0.6054005513323866}
			------------EPOCH 26---------------
Loss:  tensor(305.5420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.2771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.9332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.0084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.6961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.2389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.1302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.9313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.9970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.8832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6426, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1370757180156658, 'recall': 0.25862068965517243, 'f1': 0.17918088737201363, 'number': 812}, 'P': {'precision': 0.1346153846153846, 'recall': 0.19226856561546288, 'f1': 0.15835777126099707, 'number': 983}, 'overall_precision': 0.1358991825613079, 'overall_recall': 0.2222841225626741, 'overall_f1': 0.1686746987951807, 'overall_accuracy': 0.5865842452593768}
			------------EPOCH 27---------------
Loss:  tensor(331.6784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.6120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.9023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.3656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.2240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.6223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.7192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.5057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.6386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.9348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.1033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3301, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21521997621878716, 'recall': 0.2229064039408867, 'f1': 0.21899576527525713, 'number': 812}, 'P': {'precision': 0.20123076923076924, 'recall': 0.3326551373346897, 'f1': 0.25076687116564417, 'number': 983}, 'overall_precision': 0.2060016220600162, 'overall_recall': 0.283008356545961, 'overall_f1': 0.23844168035672378, 'overall_accuracy': 0.5910533789992481}
			------------EPOCH 28---------------
Loss:  tensor(343.8268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.7072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.3121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.2858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.2183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.3172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.8703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.9678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.1429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.3060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.3632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.1439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1219, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1402390438247012, 'recall': 0.21674876847290642, 'f1': 0.17029511369134012, 'number': 812}, 'P': {'precision': 0.1393939393939394, 'recall': 0.23397761953204477, 'f1': 0.17470565894417014, 'number': 983}, 'overall_precision': 0.13975903614457832, 'overall_recall': 0.22618384401114205, 'overall_f1': 0.1727659574468085, 'overall_accuracy': 0.5974647063737365}
			------------EPOCH 29---------------
Loss:  tensor(287.8552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.4384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.2404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.9364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.8542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.5028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.3674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.9022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.9649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.5838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.9956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.1942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0223, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17298187808896212, 'recall': 0.25862068965517243, 'f1': 0.20730503455083912, 'number': 812}, 'P': {'precision': 0.17955112219451372, 'recall': 0.29298067141403866, 'f1': 0.22265172013915735, 'number': 983}, 'overall_precision': 0.1767210787792761, 'overall_recall': 0.27743732590529246, 'overall_f1': 0.21591155430305656, 'overall_accuracy': 0.5968590761005764}
			------------EPOCH 30---------------
Loss:  tensor(238.3886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.7772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.3139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.5773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.5696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.2260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.6322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.6230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7170, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1804733727810651, 'recall': 0.22536945812807882, 'f1': 0.2004381161007667, 'number': 812}, 'P': {'precision': 0.17383618149675897, 'recall': 0.30010172939979657, 'f1': 0.22014925373134325, 'number': 983}, 'overall_precision': 0.17631870158613058, 'overall_recall': 0.2662952646239554, 'overall_f1': 0.21216156236129605, 'overall_accuracy': 0.6007016957647648}


		-------------RUN 5-----------
Test files: ['/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/230.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/69.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/68.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/293.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/87.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/92.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/93.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/28.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/309.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/92.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/91.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/93.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/334.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/97.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/318.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/95.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/94.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/95.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/94.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/29.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/261.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/76.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/77.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/266.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/80.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/247.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/70.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/10.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/11.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/8.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/12.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/5.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/291.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/86.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/248.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/72.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/71.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/256.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/74.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/99.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/97.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/98.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/31.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/0.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/1.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/0.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/1.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/258.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/75.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/80.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/79.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/81.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/23.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/negative/220.xml', '/home/XXXXXXd/arg_m2/change-my-view-modes/v2.0/positive/66.xml']
			------------EPOCH 1---------------
Loss:  tensor(2380.8796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1780.0464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1542.8129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2977.3145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3273.4570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3155.6680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3174.3306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3344.0339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1988.3907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1962.0775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1507.2402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2225.1914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1623.2009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1332.3689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.3488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2061.4810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2544.2849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1628.5876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2245.4382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2848.3503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1360.4940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1284.2960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2994.6636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2506.7332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2009.8431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1575.9514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1488.2432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1529.7346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2236.6416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1045.8447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1838.3699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2467.7236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1406.9171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2152.9556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2153.4543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1070.4084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2057.8882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1358.0488, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.08614232209737828, 'recall': 0.031724137931034485, 'f1': 0.046370967741935484, 'number': 725}, 'P': {'precision': 0.04496124031007752, 'recall': 0.030949839914621132, 'f1': 0.036662452591656125, 'number': 937}, 'overall_precision': 0.05701754385964912, 'overall_recall': 0.031287605294825514, 'overall_f1': 0.04040404040404041, 'overall_accuracy': 0.5025268855835788}
			------------EPOCH 2---------------
Loss:  tensor(1575.4714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.1125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1029.6111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2056.9341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2688.1826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2542.2312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2610.1162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2512.9937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1610.6188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1792.8126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1275.6682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1875.1633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1305.5242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1082.7443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.1646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1626.9299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2155.7114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1402.3883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1990.4904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2358.2739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1204.1479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1134.1222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2803.3301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2279.7346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1894.4939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1440.3060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1371.8538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1395.5112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2055.4692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(971.9139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1645.6199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2168.4102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1181.1083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1885.3987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1866.5884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(936.6683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1812.2300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1218.5479, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.046153846153846156, 'recall': 0.008275862068965517, 'f1': 0.014035087719298248, 'number': 725}, 'P': {'precision': 0.12871287128712872, 'recall': 0.18036286019210246, 'f1': 0.15022222222222223, 'number': 937}, 'overall_precision': 0.12127512127512127, 'overall_recall': 0.10529482551143202, 'overall_f1': 0.11272141706924316, 'overall_accuracy': 0.5203468180402865}
			------------EPOCH 3---------------
Loss:  tensor(1480.3141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1078.5859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(932.8376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1821.7729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2142.2871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2420.4409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2293.7666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2318.6921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1506.8453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1589.2893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.1456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1588.5592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1151.1517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(927.5400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.3776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1402.0272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1905.2601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1297.2594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1947.3972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2217.2554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1110.0981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(950.5277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2416.4021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2021.5360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1530.8853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1283.1554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.9562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1137.1598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1775.0608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.8142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1483.9304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1943.6787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1012.1752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1664.8301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1647.7136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(772.4777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1564.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.6307, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10648148148148148, 'recall': 0.031724137931034485, 'f1': 0.048884165781083955, 'number': 725}, 'P': {'precision': 0.12527154236060825, 'recall': 0.18463180362860193, 'f1': 0.14926660914581535, 'number': 937}, 'overall_precision': 0.12273011897307451, 'overall_recall': 0.11793020457280386, 'overall_f1': 0.12028229518257134, 'overall_accuracy': 0.5581902229886709}
			------------EPOCH 4---------------
Loss:  tensor(1158.2372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.5806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(755.5477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1478.3232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1838.1755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2032.9019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1815.0204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2001.9218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1356.5201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1344.3790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(920.9613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1320.5231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(920.9733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.5909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(646.9753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1251.4423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1512.7506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1012.7451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1874.7354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2013.8645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(972.8845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(850.6462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2162.3750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1836.4443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1264.9375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1169.1622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.7122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.4672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1489.6069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(761.8575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1261.9845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1726.7072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.8569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1456.9457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1414.3586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.4598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1309.2822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1001.5327, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12780269058295965, 'recall': 0.07862068965517241, 'f1': 0.09735269000853972, 'number': 725}, 'P': {'precision': 0.1153169014084507, 'recall': 0.13980789754535752, 'f1': 0.12638687891944042, 'number': 937}, 'overall_precision': 0.11883691529709228, 'overall_recall': 0.11311672683513839, 'overall_f1': 0.1159062885326757, 'overall_accuracy': 0.5589327201743671}
			------------EPOCH 5---------------
Loss:  tensor(899.4886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(525.0621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.4589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1229.9120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1724.5352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1706.0781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1511.4066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1740.7065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1172.1777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1192.5082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(798.5099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1121.0862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(707.5768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(533.9015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.5482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1071.3634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1152.6655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(794.1930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1689.1072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1810.2056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(869.2386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(753.1748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1937.3840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1670.4459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1077.3442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1071.4589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(977.0913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(859.1548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1321.3043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(627.9996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1057.8610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1585.5786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(782.3234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1307.8354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.9990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.4491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.5063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(879.5071, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13642756680731363, 'recall': 0.13379310344827586, 'f1': 0.1350974930362117, 'number': 725}, 'P': {'precision': 0.11831726555652936, 'recall': 0.144076840981857, 'f1': 0.12993262752646775, 'number': 937}, 'overall_precision': 0.12526997840172785, 'overall_recall': 0.13959085439229843, 'overall_f1': 0.13204325554923163, 'overall_accuracy': 0.5868362434432708}
			------------EPOCH 6---------------
Loss:  tensor(660.2050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.0615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.6838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(907.7521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1531.7693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1378.7510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1285.8840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1463.2391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1033.6406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1123.8112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.8123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(994.9758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(565.5363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.2651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.5919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(899.7764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.1243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.2444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1328.9834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1432.4377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.1549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1692.5146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1419.5068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.7772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(878.9031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.9360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.5997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1213.1980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.3031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(807.6917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1325.7617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.1390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1104.1527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(986.4569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.1295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(909.2732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.2491, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.173512154233026, 'recall': 0.28551724137931034, 'f1': 0.21584984358706985, 'number': 725}, 'P': {'precision': 0.1866151866151866, 'recall': 0.15474919957310565, 'f1': 0.1691948658109685, 'number': 937}, 'overall_precision': 0.17868020304568527, 'overall_recall': 0.21179302045728038, 'overall_f1': 0.1938325991189427, 'overall_accuracy': 0.5620464180498671}
			------------EPOCH 7---------------
Loss:  tensor(546.1179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.9468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.7867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(857.9047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1512.9661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1535.9346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1422.0435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1559.6674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(917.2001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.2383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(655.0475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.0861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.3127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.4872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.9023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(703.4962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(779.5644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.7840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1204.5020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1445.7300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.4518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(693.3547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1666.9724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1334.0496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1107.0266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.4192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(922.6845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(813.9155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1421.8286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(534.1840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(873.7410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1290.3485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.9779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(933.3011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.1843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.6808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(821.7313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.0664, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17708333333333334, 'recall': 0.11724137931034483, 'f1': 0.14107883817427386, 'number': 725}, 'P': {'precision': 0.18625277161862527, 'recall': 0.2689434364994664, 'f1': 0.2200873362445415, 'number': 937}, 'overall_precision': 0.18385160938352427, 'overall_recall': 0.20276774969915765, 'overall_f1': 0.1928469241773963, 'overall_accuracy': 0.5856626188594285}
			------------EPOCH 8---------------
Loss:  tensor(482.2414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.7385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.8287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.0457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1056.4194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1045.5139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(892.6649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1115.5774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(759.9982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(779.5970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.2250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(708.3525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.6508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.6853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.6126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(777.2589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1008.8545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.4766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1176.4313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1587.7184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.7599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.6957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1640.4824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1455.2676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(755.7484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(710.5898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.6801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.2159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(936.8639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.0694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.6460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(973.9295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.6956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.5385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.7223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.8857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(443.6062, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18340611353711792, 'recall': 0.057931034482758624, 'f1': 0.08805031446540881, 'number': 725}, 'P': {'precision': 0.19268635724331926, 'recall': 0.29242262540021347, 'f1': 0.23230182280627384, 'number': 937}, 'overall_precision': 0.1913991520290733, 'overall_recall': 0.1901323706377858, 'overall_f1': 0.19076365831572592, 'overall_accuracy': 0.5739024214988863}
			------------EPOCH 9---------------
Loss:  tensor(514.5723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.1836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.8075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.2809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1255.0110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1194.2617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1105.7483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1571.8306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.4181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(761.6397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.3220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(987.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.2764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.5061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.5447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.9979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.0134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.7928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(779.2518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1312.5037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.5163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.9232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1078.6117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(940.9162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.0265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.4808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.9894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.9124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(921.1028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.4023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.7946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.4049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.2443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(700.5935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(684.9775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.4767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.5615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.7985, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1407079646017699, 'recall': 0.2193103448275862, 'f1': 0.17142857142857143, 'number': 725}, 'P': {'precision': 0.1517509727626459, 'recall': 0.1664887940234792, 'f1': 0.15877862595419845, 'number': 937}, 'overall_precision': 0.1459684893419833, 'overall_recall': 0.18953068592057762, 'overall_f1': 0.1649214659685864, 'overall_accuracy': 0.5764412828435247}
			------------EPOCH 10---------------
Loss:  tensor(270.1529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.1435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.1610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.7191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(880.7557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.8320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.5010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(750.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.1778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.3724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.2637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.3962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.3166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.0573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.1489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.3167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.9863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.9352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(708.1542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(960.5244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.1413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.8682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.6330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(849.8618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(517.6533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.7256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.6783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.3977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(825.5057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.6366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.1431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.3185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.4678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.7895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.9969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.1892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.6261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.6645, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15405405405405406, 'recall': 0.07862068965517241, 'f1': 0.10410958904109588, 'number': 725}, 'P': {'precision': 0.1446587537091988, 'recall': 0.20811099252934898, 'f1': 0.17067833698030635, 'number': 937}, 'overall_precision': 0.14668218859138532, 'overall_recall': 0.15162454873646208, 'overall_f1': 0.14911242603550295, 'overall_accuracy': 0.5961054825034131}
			------------EPOCH 11---------------
Loss:  tensor(302.6624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.5042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.5139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.0306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.1457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.4387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(566.7433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(636.3816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.4453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.7972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.2261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.5971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.4949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.4335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.6797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.5898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.1722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.3932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.7490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(786.9296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.1431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.5624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(789.1573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(634.2030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.4836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.4941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.8259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.7109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.4514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.2090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.9093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.6852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.9239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.8803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.8114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.7936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.9224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.7512, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17018469656992086, 'recall': 0.17793103448275863, 'f1': 0.17397167902899532, 'number': 725}, 'P': {'precision': 0.20286396181384247, 'recall': 0.272145144076841, 'f1': 0.2324521422060164, 'number': 937}, 'overall_precision': 0.19057071960297767, 'overall_recall': 0.23104693140794225, 'overall_f1': 0.2088659233070438, 'overall_accuracy': 0.6093027711911092}
			------------EPOCH 12---------------
Loss:  tensor(202.3290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.1928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.2526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.7895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.9121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.4023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.7447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.9664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.0389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.6126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.7416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.3112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.2731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.8175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.8871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.2179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.1461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.2935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.1850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.4954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.3480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.3731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.0369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.0338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.8238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.9756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.9383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.1799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.8542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.1823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.4472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.4011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.6972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.4380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.4306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.0593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.4314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.7241, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17692307692307693, 'recall': 0.15862068965517243, 'f1': 0.1672727272727273, 'number': 725}, 'P': {'precision': 0.18853046594982079, 'recall': 0.28068303094983993, 'f1': 0.225557461406518, 'number': 937}, 'overall_precision': 0.18484107579462103, 'overall_recall': 0.22743682310469315, 'overall_f1': 0.20393849473968167, 'overall_accuracy': 0.6159373428181361}
			------------EPOCH 13---------------
Loss:  tensor(167.7299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.0245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.8120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.4103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.7066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.7971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.8803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.6006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.3839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.2557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.4293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.2946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.1466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.8095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.8534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.6918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.4725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.8649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(558.2009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.3816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.5231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.4496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.1590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.2008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.2158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.7166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.5751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.7625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.5616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.7547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.1414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.5492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.5801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.0861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.4897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.2172, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16312997347480107, 'recall': 0.1696551724137931, 'f1': 0.1663286004056795, 'number': 725}, 'P': {'precision': 0.15250379362670713, 'recall': 0.21451440768409819, 'f1': 0.17827050997782704, 'number': 937}, 'overall_precision': 0.15637065637065636, 'overall_recall': 0.19494584837545126, 'overall_f1': 0.1735404392072844, 'overall_accuracy': 0.6177576584991976}
			------------EPOCH 14---------------
Loss:  tensor(117.0978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.3279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.4172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.6979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.8333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.2050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.1600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.5388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.2469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.6643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.0713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.2231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.9657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.4688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.2028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.7728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.1064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.5944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(504.4489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.0503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.3604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(419.5011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.0306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.4825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.4464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.8994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.4277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.2489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.0334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.6460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.8984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.4398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.8005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.8890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.1798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6271, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17063492063492064, 'recall': 0.23724137931034484, 'f1': 0.1984997114829775, 'number': 725}, 'P': {'precision': 0.16833333333333333, 'recall': 0.21558164354322304, 'f1': 0.1890500701918577, 'number': 937}, 'overall_precision': 0.1693840579710145, 'overall_recall': 0.2250300842358604, 'overall_f1': 0.19328165374677006, 'overall_accuracy': 0.6167756460923092}
			------------EPOCH 15---------------
Loss:  tensor(108.5339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.3377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.8436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.3512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.3666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.4670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.2172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.2851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.1003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.4015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.5849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.8171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.4268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.0809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.7607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.5119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.7941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.2360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.9022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.6036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.9218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.0286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.6086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.5448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.3001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.2024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.9349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.3381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.8152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.5616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.6106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.8246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.0436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.7499, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22153209109730848, 'recall': 0.14758620689655172, 'f1': 0.1771523178807947, 'number': 725}, 'P': {'precision': 0.19099590723055934, 'recall': 0.29882604055496265, 'f1': 0.23304203079483976, 'number': 937}, 'overall_precision': 0.19856336582863007, 'overall_recall': 0.2328519855595668, 'overall_f1': 0.21434505677097757, 'overall_accuracy': 0.6102129290316399}
			------------EPOCH 16---------------
Loss:  tensor(103.0172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.2918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.8672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.1552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.7046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.2210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.7143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.0266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.6255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.1964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.5298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.9735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.1984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.5615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.8778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.3131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.9130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.6225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.8091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.4546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.6231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.2012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.6142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.7329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.7706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.3207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.8827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.4070, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19031531531531531, 'recall': 0.23310344827586207, 'f1': 0.20954742715437075, 'number': 725}, 'P': {'precision': 0.16932422171602127, 'recall': 0.23799359658484526, 'f1': 0.19787045252883761, 'number': 937}, 'overall_precision': 0.17777777777777778, 'overall_recall': 0.2358604091456077, 'overall_f1': 0.2027411430049134, 'overall_accuracy': 0.6154343608536322}
			------------EPOCH 17---------------
Loss:  tensor(72.1720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.0518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.5942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.7281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.8012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.1482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.5507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.6487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.7194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(404.8740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.8507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.6185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.0615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.7175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.9431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.4591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.1208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.7478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.7833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.2343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.5743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.3436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2290, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17423133235724744, 'recall': 0.16413793103448276, 'f1': 0.1690340909090909, 'number': 725}, 'P': {'precision': 0.14479945615227735, 'recall': 0.22732123799359658, 'f1': 0.17691029900332225, 'number': 937}, 'overall_precision': 0.1541318477251625, 'overall_recall': 0.19975932611311673, 'overall_f1': 0.1740041928721174, 'overall_accuracy': 0.6187396709060861}
			------------EPOCH 18---------------
Loss:  tensor(62.3628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.9035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.2463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.4620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.2314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.1730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.9930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.4500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.4368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.0886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.3098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.4137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.6087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.6673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.8333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.5611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.3588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.6940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.9169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.3067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.8204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.8252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5544, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21179624664879357, 'recall': 0.21793103448275863, 'f1': 0.21481985044187626, 'number': 725}, 'P': {'precision': 0.19401896425966447, 'recall': 0.2838847385272145, 'f1': 0.23050259965337955, 'number': 937}, 'overall_precision': 0.2002834199338687, 'overall_recall': 0.25511432009626955, 'overall_f1': 0.2243979888859487, 'overall_accuracy': 0.6122009053675361}
			------------EPOCH 19---------------
Loss:  tensor(45.8929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.7643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.8921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.5773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.3966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.7615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.5228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.1971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.7678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.9252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.1475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.9952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.7361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.7518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.1824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.0006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.1044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.1431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.7230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.7875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.7268, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1836461126005362, 'recall': 0.1889655172413793, 'f1': 0.18626784500339905, 'number': 725}, 'P': {'precision': 0.17259905977165882, 'recall': 0.2742796157950907, 'f1': 0.21187139323990103, 'number': 937}, 'overall_precision': 0.17628635346756152, 'overall_recall': 0.23706377858002406, 'overall_f1': 0.20220682576340773, 'overall_accuracy': 0.622260544657613}
			------------EPOCH 20---------------
Loss:  tensor(33.2544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.8317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.7531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.5146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.2146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.5254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.1509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.5282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.9982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.2309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.9065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.5557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.0203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.7102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.6881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2357, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2170439414114514, 'recall': 0.22482758620689655, 'f1': 0.22086720867208676, 'number': 725}, 'P': {'precision': 0.17580872011251758, 'recall': 0.26680896478121663, 'f1': 0.21195421788893598, 'number': 937}, 'overall_precision': 0.19005982512655314, 'overall_recall': 0.24849578820697954, 'overall_f1': 0.2153846153846154, 'overall_accuracy': 0.6155301669421092}
			------------EPOCH 21---------------
Loss:  tensor(26.8381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.7725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.5355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.9989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.5263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.5779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.4388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.6435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.4637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.3004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.4017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.6784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2290, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2037037037037037, 'recall': 0.19724137931034483, 'f1': 0.20042046250875964, 'number': 725}, 'P': {'precision': 0.1675531914893617, 'recall': 0.2689434364994664, 'f1': 0.2064727570667759, 'number': 937}, 'overall_precision': 0.17905711695376247, 'overall_recall': 0.23766546329723226, 'overall_f1': 0.20423991726990692, 'overall_accuracy': 0.6171349189240977}
			------------EPOCH 22---------------
Loss:  tensor(22.9219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.1452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.9693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.8628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.2513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.2664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.6047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.8730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.1236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.5064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.1140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.9939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7506, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1977886977886978, 'recall': 0.22206896551724137, 'f1': 0.20922677063027942, 'number': 725}, 'P': {'precision': 0.17231434751261715, 'recall': 0.2550693703308431, 'f1': 0.2056798623063683, 'number': 937}, 'overall_precision': 0.18173557473875512, 'overall_recall': 0.24067388688327315, 'overall_f1': 0.20709293295366293, 'overall_accuracy': 0.619458216569663}
			------------EPOCH 23---------------
Loss:  tensor(19.4524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.2635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.6149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.8316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.7280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.1628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.2032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.5166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.8719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.5089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9099, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20145985401459854, 'recall': 0.19034482758620688, 'f1': 0.19574468085106383, 'number': 725}, 'P': {'precision': 0.16753926701570682, 'recall': 0.27321237993596587, 'f1': 0.20770791075050712, 'number': 937}, 'overall_precision': 0.1780388612742883, 'overall_recall': 0.23706377858002406, 'overall_f1': 0.2033548387096774, 'overall_accuracy': 0.6156978275969438}
			------------EPOCH 24---------------
Loss:  tensor(16.8880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.8044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.6515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.4754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.2453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.8429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.2633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.1290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.0676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.2635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.3315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.5156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.1605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2268, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20119760479041915, 'recall': 0.2317241379310345, 'f1': 0.21538461538461537, 'number': 725}, 'P': {'precision': 0.1673881673881674, 'recall': 0.24759871931696906, 'f1': 0.19974171330176496, 'number': 937}, 'overall_precision': 0.180099054479964, 'overall_recall': 0.24067388688327315, 'overall_f1': 0.20602626834921453, 'overall_accuracy': 0.6193863620033053}
			------------EPOCH 25---------------
Loss:  tensor(14.4330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.7274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.1493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.4561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.3029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.9573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.6804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.4772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.0632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.3453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.8288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7793, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18156424581005587, 'recall': 0.1793103448275862, 'f1': 0.18043025676613464, 'number': 725}, 'P': {'precision': 0.16352624495289367, 'recall': 0.25933831376734257, 'f1': 0.20057779612051177, 'number': 937}, 'overall_precision': 0.16939146230699365, 'overall_recall': 0.22442839951865223, 'overall_f1': 0.19306418219461696, 'overall_accuracy': 0.61394936648224}
			------------EPOCH 26---------------
Loss:  tensor(12.6908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.8990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.3238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.1620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.1738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.1242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.7309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.3151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.9254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.2691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7587, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.205, 'recall': 0.22620689655172413, 'f1': 0.21508196721311476, 'number': 725}, 'P': {'precision': 0.1695865451997197, 'recall': 0.25827107790821774, 'f1': 0.2047377326565144, 'number': 937}, 'overall_precision': 0.18230803771890436, 'overall_recall': 0.24428399518652227, 'overall_f1': 0.2087940344561584, 'overall_accuracy': 0.6165121793489976}
			------------EPOCH 27---------------
Loss:  tensor(11.3601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.7883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.8918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.8815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.3695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.2434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.0092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.4645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.8918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.6454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8633, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1940700808625337, 'recall': 0.1986206896551724, 'f1': 0.19631901840490795, 'number': 725}, 'P': {'precision': 0.16073871409028728, 'recall': 0.2508004268943437, 'f1': 0.19591496456857024, 'number': 937}, 'overall_precision': 0.17196007259528132, 'overall_recall': 0.22803850782190133, 'overall_f1': 0.19606828763579928, 'overall_accuracy': 0.6173744341452899}
			------------EPOCH 28---------------
Loss:  tensor(10.5058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.5803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.8228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.0955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.5094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.0999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.5006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.3266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.6288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.1387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5315, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20162224797219003, 'recall': 0.24, 'f1': 0.21914357682619648, 'number': 725}, 'P': {'precision': 0.16884057971014493, 'recall': 0.2486659551760939, 'f1': 0.20112214069917997, 'number': 937}, 'overall_precision': 0.18145341061078912, 'overall_recall': 0.24488567990373045, 'overall_f1': 0.2084507042253521, 'overall_accuracy': 0.6163684702162823}
			------------EPOCH 29---------------
Loss:  tensor(10.6317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.5909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.4414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.5190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.5554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.4624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.7186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.9838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.8128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.4101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1030, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19463087248322147, 'recall': 0.2, 'f1': 0.19727891156462585, 'number': 725}, 'P': {'precision': 0.15691489361702127, 'recall': 0.2518676627534685, 'f1': 0.19336337566571077, 'number': 937}, 'overall_precision': 0.1694086260560249, 'overall_recall': 0.2292418772563177, 'overall_f1': 0.19483508054206083, 'overall_accuracy': 0.6171828219683361}
			------------EPOCH 30---------------
Loss:  tensor(9.3118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.4910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.1964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.5850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.5756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.5244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.6135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.6631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.0840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.2062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4063, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2262210796915167, 'recall': 0.24275862068965517, 'f1': 0.23419827012641384, 'number': 725}, 'P': {'precision': 0.16981132075471697, 'recall': 0.25933831376734257, 'f1': 0.20523648648648646, 'number': 937}, 'overall_precision': 0.18967858759619738, 'overall_recall': 0.25210589651022863, 'overall_f1': 0.216481529320589, 'overall_accuracy': 0.6145960575794591}
