Tokenizer: roberta-base Model: roberta-base
	Train size: 80 Test size: 20


		-------------RUN 1-----------
			------------EPOCH 1---------------
Loss:  tensor(1782.2302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3178.0474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2629.4072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1549.7776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1769.3989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1621., device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1776.8479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2576.5322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1080.6951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3141.6602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3458.6792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3601.8926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2189.8638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5165.3076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3136.4614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2554.2056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2000.6985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2346.9731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1777.8313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1942.3616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1599.8032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2114.6333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2492.9075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1705.3752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2802.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1884.7502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1859.7228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1860.5559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2325.3801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2131.7725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1931.7048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2084.1470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3347.3066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1004.0614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2264.6865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3298.1506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3024.0637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1326.5842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(918.9084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1777.1600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2866.4365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1252.0278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1873.4075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2447.4897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2530.3403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1242.3291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1778.7639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1976.7876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1972.8269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2391.9604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2811.3813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2941.5161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3141.3613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2285.5625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1723.0811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1278.0797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1374.7144, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.031212484993997598, 'recall': 0.125, 'f1': 0.04995196926032661, 'number': 208}, 'P': {'precision': 0.08333333333333333, 'recall': 0.0030959752321981426, 'f1': 0.005970149253731343, 'number': 323}, 'overall_precision': 0.03195266272189349, 'overall_recall': 0.05084745762711865, 'overall_f1': 0.03924418604651163, 'overall_accuracy': 0.3544399216041007}
			------------EPOCH 2---------------
Loss:  tensor(1279.2955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2400.3184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1989.7561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1151.0842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1391.6548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1291.8357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1371.4189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1935.5902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(843.4116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2475.8340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2762.7588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2762.9087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1684.4478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4193.5811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2488.7224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2149.8188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1749.1088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1937.6969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1331.3145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1588.9365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1373.0990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1722.9600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1940.7891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1341.6641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2336.9236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1449.4036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1563.5825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1428.0908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1857.5911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1622.3430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1770.5278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1672.4852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2678.9761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(826.0570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2113.5889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2839.2563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2607.0957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1116.8489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(760.2006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1383.1229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2715.9009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(964.5457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1476.8262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2112.2866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2349.9402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1179.4674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1676.9402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1859.5924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1580.4292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2189.2170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2298.7322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2349.0752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2361.8552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1799.2117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1330.3239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1085.0835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1109.9369, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.08032128514056225, 'recall': 0.28846153846153844, 'f1': 0.1256544502617801, 'number': 208}, 'P': {'precision': 0.23529411764705882, 'recall': 0.09907120743034056, 'f1': 0.1394335511982571, 'number': 323}, 'overall_precision': 0.10419026047565119, 'overall_recall': 0.17325800376647835, 'overall_f1': 0.13012729844413015, 'overall_accuracy': 0.4994723352932308}
			------------EPOCH 3---------------
Loss:  tensor(1127.1853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2180.6040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1610.6606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1018.3613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1235.0671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1148.8369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1125.0939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1633.3015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.2091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2161.0957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2366.2449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2215.1238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1316.3378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3547.8232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1938.8171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1709.1082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1570.4623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1607.6672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(966.4266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1366.5076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1173.0142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1288.2393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1509.7195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(995.6863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1981.5203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.1936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1287.6226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1236.3074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1526.5928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1148.0420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1501.4290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1210.4974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2199.5146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(645.4180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1814.7776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2398.2827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2118.9739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(964.7991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.3152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1060.0380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2323.2773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(793.6324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1148.5686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1900.9547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1912.5061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.9310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1284.6178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1577.3367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1276.5002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1949.6011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1782.8462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1906.1213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1807.5327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1292.6135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1007.1903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(987.6195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(823.2266, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.163575042158516, 'recall': 0.46634615384615385, 'f1': 0.24219725343320847, 'number': 208}, 'P': {'precision': 0.37244897959183676, 'recall': 0.2260061919504644, 'f1': 0.28131021194605005, 'number': 323}, 'overall_precision': 0.21546261089987326, 'overall_recall': 0.32015065913371, 'overall_f1': 0.25757575757575757, 'overall_accuracy': 0.5780943766018393}
			------------EPOCH 4---------------
Loss:  tensor(917.5189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1838.9646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1381.0154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(834.2433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1103.6429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(992.9376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(889.6160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1321.0601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.8286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1826.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2054.3428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1617.4495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1049.5640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3193.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1581.9147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1345.6785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1297.8104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1286.4781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(700.3796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1135.1604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1038.0936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(980.1287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1167.1931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(693.8254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1691.8333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.8706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1093.6049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(964.1116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1173.4646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.2371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1250.0376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(932.9816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1750.1963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.0876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1479.0503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1974.0176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1730.5718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(799.2590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.2509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.9686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1839.3291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(650.6228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(961.9341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1534.4261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1146.5327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(645.9560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.7325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1061.3196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1108.2644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1673.8984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1576.0066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1545.5251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1474.1072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1279.8468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(832.5269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.4497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.3641, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20801526717557253, 'recall': 0.5240384615384616, 'f1': 0.2978142076502733, 'number': 208}, 'P': {'precision': 0.4147465437788018, 'recall': 0.2786377708978328, 'f1': 0.3333333333333333, 'number': 323}, 'overall_precision': 0.26855600539811064, 'overall_recall': 0.3747645951035782, 'overall_f1': 0.3128930817610063, 'overall_accuracy': 0.62294587667722}
			------------EPOCH 5---------------
Loss:  tensor(754.6812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1600.2419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1140.7172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(707.9429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(958.3476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(826.0791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.0416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.7690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(484.8748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1737.9346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2172.1367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1517.6519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(740.6123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2664.5630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1170.5724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1109.3550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1002.1512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.9362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.4923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(910.8409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(790.0353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.1847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1290.7864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.3267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1270.5200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(799.4584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(825.4350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.7852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(925.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.3433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(742.6187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.7294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1337.7041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.2959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(910.5377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1403.4702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1316.3739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(635.9135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.7863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.4304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1496.3395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(468.7152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.0452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1345.8379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.9822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.8960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.1623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(666.5588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(851.8572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1207.2645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1118.3123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1297.4020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1119.4409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1002.4318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.4814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.9479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.6995, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3010204081632653, 'recall': 0.5673076923076923, 'f1': 0.3933333333333333, 'number': 208}, 'P': {'precision': 0.3584905660377358, 'recall': 0.35294117647058826, 'f1': 0.35569422776911075, 'number': 323}, 'overall_precision': 0.3267605633802817, 'overall_recall': 0.4369114877589454, 'overall_f1': 0.37389202256244963, 'overall_accuracy': 0.6665912859942711}
			------------EPOCH 6---------------
Loss:  tensor(715.2081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1667.9805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1047.5627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.8702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.4167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.4101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.7414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(952.0941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.8726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1067.0143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1476.6124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.8441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.9344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2114.2451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(795.6339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.6312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.6179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(889.5155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.6656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.1177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(823.9890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.3071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(915.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(389.0074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1015.4656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.5308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.8994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.4276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(635.1854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.8895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.2361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1272.3055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.8234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(652.4980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1413.5120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.3206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(483.2974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.9378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.8531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(917.4399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.9761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.8727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(914.9264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.3639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.4957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.7050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.0124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(654.3581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(944.6824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(830.9724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1134.3330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1067.5096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(694.7689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.4875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.2977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(483.7483, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3112128146453089, 'recall': 0.6538461538461539, 'f1': 0.42170542635658914, 'number': 208}, 'P': {'precision': 0.6, 'recall': 0.35294117647058826, 'f1': 0.4444444444444445, 'number': 323}, 'overall_precision': 0.39872408293460926, 'overall_recall': 0.4708097928436911, 'overall_f1': 0.43177892918825556, 'overall_accuracy': 0.6705864616312377}
			------------EPOCH 7---------------
Loss:  tensor(396.9474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.1176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.1064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.2537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.9427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(541.3513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.2663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.1611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.8641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(735.0532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1148.5845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.7417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.9569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1981.6989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.2153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.0075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(560.5913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.4301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.1731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(521.1656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(483.1251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.6942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(923.4102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.0224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.0250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.7998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.6758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.9661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(541.1115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.4060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.6437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.8802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.3589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.5239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.3670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(902.7975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(759.2789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.3649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.0200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.6919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.3608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.9702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.2075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.9156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.4598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.5344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.7799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.2742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(729.7092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.2684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(749.9912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.8145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.6829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.4344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.7897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.1597, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.37971698113207547, 'recall': 0.7740384615384616, 'f1': 0.509493670886076, 'number': 208}, 'P': {'precision': 0.615819209039548, 'recall': 0.33746130030959753, 'f1': 0.436, 'number': 323}, 'overall_precision': 0.4492512479201331, 'overall_recall': 0.5084745762711864, 'overall_f1': 0.4770318021201413, 'overall_accuracy': 0.668852706166139}
			------------EPOCH 8---------------
Loss:  tensor(225.3979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.6586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(496.2954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.6342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.2378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.7576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.4447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.6000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.9826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(558.1333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(880.9579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(729.7201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.5093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1017.0638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.0244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.5266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.7769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.4131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.2657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.5335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.8243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.4303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(821.3552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.0190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.1620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.0952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.1841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(634.1655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(517.5371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.6562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.5913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.3265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.9810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.8147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.0594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(795.0515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.0796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.5505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.0342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.5026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(484.5309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.2848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.4963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.2632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.6431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.6727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.0478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.1044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.0377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.6963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.0190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.2539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.2972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.0552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.5154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.7159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.3034, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.421455938697318, 'recall': 0.5288461538461539, 'f1': 0.4690831556503198, 'number': 208}, 'P': {'precision': 0.5194444444444445, 'recall': 0.5789473684210527, 'f1': 0.547584187408492, 'number': 323}, 'overall_precision': 0.4782608695652174, 'overall_recall': 0.559322033898305, 'overall_f1': 0.515625, 'overall_accuracy': 0.7312679029096939}
			------------EPOCH 9---------------
Loss:  tensor(203.2650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(650.3054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.1222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.9194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.9568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.0948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.3214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.4633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.5328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.9145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(539.0591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.0195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.9856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(733.2262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.1329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.4039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.0572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.8708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.8740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.4106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.9397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.4571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(998.0969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.1839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.3103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.2604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.0734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.3862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.0115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.9593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.5175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.7244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.3721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.6030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.9150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.4703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(806.5786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.1077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.8784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.4395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.5220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.4448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(720.3104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1013.3235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.2077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.2346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.5575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.6411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.7025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.1782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.1716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.5214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.6674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.2794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.6274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.2144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.6400, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3640776699029126, 'recall': 0.7211538461538461, 'f1': 0.48387096774193555, 'number': 208}, 'P': {'precision': 0.6513761467889908, 'recall': 0.43962848297213625, 'f1': 0.5249537892791127, 'number': 323}, 'overall_precision': 0.4634920634920635, 'overall_recall': 0.5499058380414312, 'overall_f1': 0.5030146425495262, 'overall_accuracy': 0.689280868385346}
			------------EPOCH 10---------------
Loss:  tensor(129.7116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.8376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.9152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.1212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.5690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.9833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.7411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.6413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.9515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.7390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(722.3528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.4775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.3153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1113.0502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.0634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(443.7730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.5021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.1266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.5052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.8562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.3061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.6690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.6351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.2973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.6952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.4080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.1865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.6535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.5638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.0801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.0091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.2446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.5834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.0038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.7081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.0381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.8521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.8519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.6429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.6430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.4861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.5966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.7282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(597.3843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.0669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.5308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.5183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.1587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.5941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(517.1995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(715.6100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.8358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.6279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.6316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(485.6551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.7583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.6681, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3173076923076923, 'recall': 0.47596153846153844, 'f1': 0.3807692307692307, 'number': 208}, 'P': {'precision': 0.5524861878453039, 'recall': 0.6191950464396285, 'f1': 0.5839416058394161, 'number': 323}, 'overall_precision': 0.443620178041543, 'overall_recall': 0.5630885122410546, 'overall_f1': 0.49626556016597506, 'overall_accuracy': 0.7127996381727725}
			------------EPOCH 11---------------
Loss:  tensor(133.7718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(404.2500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.6522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.5133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.8611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.1645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.0822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.6678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.1404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.1278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.5247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.6266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.5096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.6637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.9266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.1659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.1526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.1494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.2418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.7849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.9209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.9265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.5316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.1418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.8825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.8255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.0836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.2248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.6030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.0627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.2898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.9638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(585.0436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.6913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.4241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.4818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.6245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.5525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.0438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.1974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.1825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(498.7509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.0172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(722.1634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.2628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.0501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.2339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.9497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.5791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.7678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.1600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(560.9583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.6993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.7846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.1912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.9511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(777.4482, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3509933774834437, 'recall': 0.2548076923076923, 'f1': 0.29526462395543174, 'number': 208}, 'P': {'precision': 0.4706994328922495, 'recall': 0.7708978328173375, 'f1': 0.584507042253521, 'number': 323}, 'overall_precision': 0.4441176470588235, 'overall_recall': 0.568738229755179, 'overall_f1': 0.49876135425268375, 'overall_accuracy': 0.6972712196592794}
			------------EPOCH 12---------------
Loss:  tensor(264.1994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1386.4872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.4382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(796.1137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1095.1505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1213.4973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1054.6476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1308.7627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.7176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.8694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(951.5209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.3856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.8499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1212.3469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.8410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(485.5846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.0085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.9077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.2246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.5236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.4995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.1205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.2120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.9540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(708.7935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(713.3979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.3841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.3925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1000.2392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.8997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.4805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1317.2513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1959.0874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.3140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.3498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2101.8032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.2277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.8019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.7192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.3370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.7730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.5552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.6193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.9485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.8200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.5885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.9887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.3277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.1983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.5226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.0505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.7598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(525.8718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(576.5665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.0699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.5802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.7736, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.425, 'recall': 0.24519230769230768, 'f1': 0.31097560975609756, 'number': 208}, 'P': {'precision': 0.5059760956175299, 'recall': 0.7863777089783281, 'f1': 0.6157575757575757, 'number': 323}, 'overall_precision': 0.4903536977491961, 'overall_recall': 0.5743879472693032, 'overall_f1': 0.5290546400693843, 'overall_accuracy': 0.7390321121664405}
			------------EPOCH 13---------------
Loss:  tensor(192.3333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(650.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.0232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(412.5326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(517.1553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.8627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(959.1709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1127.8916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.9926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(969.6398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.3247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(840.4472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.0967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2146.0479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.7489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(926.9055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.7952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.9289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.1421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(636.9653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.7923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.5958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.7335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.0522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.5981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(441.4674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(517.4526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.0237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.3342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.8648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.4988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(807.6680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1668.4209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.3126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(946.3271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1673.6453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1123.5562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(558.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.3480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(619.8033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(694.6791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.7235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.9940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(899.7539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.4849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.6494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.1105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.1461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.2266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.4709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.7890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(603.7106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(884.6500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1365.1122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(636.6498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.0382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.1873, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3672566371681416, 'recall': 0.39903846153846156, 'f1': 0.3824884792626728, 'number': 208}, 'P': {'precision': 0.4143222506393862, 'recall': 0.5015479876160991, 'f1': 0.45378151260504207, 'number': 323}, 'overall_precision': 0.39708265802269044, 'overall_recall': 0.4613935969868173, 'overall_f1': 0.4268292682926829, 'overall_accuracy': 0.723579074325343}
			------------EPOCH 14---------------
Loss:  tensor(181.2747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.9324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.4970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.0230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.4293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.4005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.1036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.4841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.6098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.8948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.9705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.2343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.3362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1049.8925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.6375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.4175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.6808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.6114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.7716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.3758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.2527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.6727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.8643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.2784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.8493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.8466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.1608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.0854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.9380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.4291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.6089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.7440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.8971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.0096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.6387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.1319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.7899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.8185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.1448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.0661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.0445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.1055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.8505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.6602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.6887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.1013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.3583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.4158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.7961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(504.7929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(498.1590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.4896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.8145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.8452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.1358, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.44694533762057875, 'recall': 0.6682692307692307, 'f1': 0.535645472061657, 'number': 208}, 'P': {'precision': 0.658273381294964, 'recall': 0.56656346749226, 'f1': 0.6089850249584027, 'number': 323}, 'overall_precision': 0.5466893039049237, 'overall_recall': 0.6064030131826742, 'overall_f1': 0.575, 'overall_accuracy': 0.7627016432986582}
			------------EPOCH 15---------------
Loss:  tensor(89.3129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.3836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.3147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.8272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.1314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.0305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.4612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.1680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.9044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.6334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.3340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.2484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.5330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.3391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.5095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.6057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.5510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.4326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.8671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.3768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.0686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.8338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.2178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.2818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.5162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.7245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.1600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.8054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.6908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.5713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.0002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.3239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.9315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.6394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.5498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.3092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.2569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.3320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.7756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.4200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.8988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.0491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.3657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.6381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.8317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.9550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.8684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.7622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.1093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.4464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.1336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.7394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.5467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.3683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.8781, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.42570281124497994, 'recall': 0.5096153846153846, 'f1': 0.4638949671772429, 'number': 208}, 'P': {'precision': 0.5823529411764706, 'recall': 0.6130030959752322, 'f1': 0.5972850678733032, 'number': 323}, 'overall_precision': 0.5161290322580645, 'overall_recall': 0.5725047080979284, 'overall_f1': 0.5428571428571428, 'overall_accuracy': 0.7497361676466154}
			------------EPOCH 16---------------
Loss:  tensor(49.1671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.2209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.8384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.4892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.2713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.4917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.5232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.5950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.1648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.3387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.2932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.6932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.4927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.6818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.8678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.9897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.6429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.7662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.0635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.9048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.1339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.8797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.2474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.3211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.9994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.5607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.5373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.0722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.5706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.8598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.3337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.6231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.2308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.8161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.6576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.0571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.4069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.2194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.1175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.4035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.5999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.4112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.2574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.7226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.3834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.1328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.8403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.3243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.5641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.4497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.5592, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4580152671755725, 'recall': 0.5769230769230769, 'f1': 0.5106382978723403, 'number': 208}, 'P': {'precision': 0.6463022508038585, 'recall': 0.6222910216718266, 'f1': 0.6340694006309148, 'number': 323}, 'overall_precision': 0.5602094240837696, 'overall_recall': 0.6045197740112994, 'overall_f1': 0.5815217391304347, 'overall_accuracy': 0.7607417458163727}
			------------EPOCH 17---------------
Loss:  tensor(41.0338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.0726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.5364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.1715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.7888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.4143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.7139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.8393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.2443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.5448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.4185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.1252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.6448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.6590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.7034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.6203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.6053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.8772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.1100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.3034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.9847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.7151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.8526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.5509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.8218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.0370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.2755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.9626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.4332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.1081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.9087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.4925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.5089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.2255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.1712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.9816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.0839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.8979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.4511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.7277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.0447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.5578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.0130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.9372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.0298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.9938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.1801, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4566929133858268, 'recall': 0.5576923076923077, 'f1': 0.5021645021645021, 'number': 208}, 'P': {'precision': 0.6075949367088608, 'recall': 0.5944272445820433, 'f1': 0.6009389671361502, 'number': 323}, 'overall_precision': 0.5403508771929825, 'overall_recall': 0.5800376647834274, 'overall_f1': 0.5594913714804722, 'overall_accuracy': 0.7657168701944821}
			------------EPOCH 18---------------
Loss:  tensor(34.5700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.2638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.5712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.0160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.8482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.9753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.6060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.8427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.4759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.6028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.1465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.2688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.5844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.0124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.2995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.8745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.8879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.6681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.7340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.8448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.6142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.5638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.2044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.3142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.6021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.8316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.7880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.3397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.2312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.2059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.0225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.7073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.1910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.2221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.5988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.1127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.1026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.8343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.1974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.2615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.3568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.7367, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.46184738955823296, 'recall': 0.5528846153846154, 'f1': 0.5032822757111598, 'number': 208}, 'P': {'precision': 0.6012461059190031, 'recall': 0.5975232198142415, 'f1': 0.5993788819875776, 'number': 323}, 'overall_precision': 0.5403508771929825, 'overall_recall': 0.5800376647834274, 'overall_f1': 0.5594913714804722, 'overall_accuracy': 0.7707673752449872}
			------------EPOCH 19---------------
Loss:  tensor(29.7144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.3261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.3469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.1138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.8874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.3855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.6873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.8252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.7022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.6836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.0773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.9894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.3713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.5514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.9761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.9059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.6466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.6951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.5313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.3185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.2552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.8894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.4130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.4865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.2405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.2918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.2378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.3568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.9882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.9676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.8708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.2662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.7004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.6231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.9554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.9031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.6434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.6409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.8301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.5402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.8297, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.46, 'recall': 0.5528846153846154, 'f1': 0.5021834061135372, 'number': 208}, 'P': {'precision': 0.6088328075709779, 'recall': 0.5975232198142415, 'f1': 0.603125, 'number': 323}, 'overall_precision': 0.5432098765432098, 'overall_recall': 0.5800376647834274, 'overall_f1': 0.5610200364298724, 'overall_accuracy': 0.7674506256595809}
			------------EPOCH 20---------------
Loss:  tensor(25.8185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.7863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.9141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.1068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.8866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.7014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.1828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.1377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.2674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.6653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.9684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.2214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.5356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.5263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.9473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.5121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.3371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.1360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.9440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.5050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.8404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.6128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.1168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.1386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.9704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.2122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.8160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.5244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.9582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.9047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.0577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.8800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.5846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1220, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.47540983606557374, 'recall': 0.5576923076923077, 'f1': 0.5132743362831858, 'number': 208}, 'P': {'precision': 0.6024844720496895, 'recall': 0.6006191950464397, 'f1': 0.6015503875968993, 'number': 323}, 'overall_precision': 0.5477031802120141, 'overall_recall': 0.583804143126177, 'overall_f1': 0.5651777575205105, 'overall_accuracy': 0.7699381878486357}
			------------EPOCH 21---------------
Loss:  tensor(22.4828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.2167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.1222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.7495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.2485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.9745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.8388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.4852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.5947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.0914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.5421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.4408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.9377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.8425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.7412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.6971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.1443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.0046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.3895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.1027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.7445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.7292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.7239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.5423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.1016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.4975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.8400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.6732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.6406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.8258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.6646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2361, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4773662551440329, 'recall': 0.5576923076923077, 'f1': 0.5144124168514412, 'number': 208}, 'P': {'precision': 0.6037151702786377, 'recall': 0.6037151702786377, 'f1': 0.6037151702786377, 'number': 323}, 'overall_precision': 0.549469964664311, 'overall_recall': 0.5856873822975518, 'overall_f1': 0.5670009115770283, 'overall_accuracy': 0.7708427559173828}
			------------EPOCH 22---------------
Loss:  tensor(19.7478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.6463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.4461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.4934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.7670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.5590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.6018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.3999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.7087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.6675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.8664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.6482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.1783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.4707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.8949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.3026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.0270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.6167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.7486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.9143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.3438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.1874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.6087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.2333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.0202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.6702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.5237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6122, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4560669456066946, 'recall': 0.5240384615384616, 'f1': 0.48769574944071586, 'number': 208}, 'P': {'precision': 0.6086956521739131, 'recall': 0.6068111455108359, 'f1': 0.6077519379844962, 'number': 323}, 'overall_precision': 0.5436720142602496, 'overall_recall': 0.5743879472693032, 'overall_f1': 0.5586080586080586, 'overall_accuracy': 0.77174732398613}
			------------EPOCH 23---------------
Loss:  tensor(17.3689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.2830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.4520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.3663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.5399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.1503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.5352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.3401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.4461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.5999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.3054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.7776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.5472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.2779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.5758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.7832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.2551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.8042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.0868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.9179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.9432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.1913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.6243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.5405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.6196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.7889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.6893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.6264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.5458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.0152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.9766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.1654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.1781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9822, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.43621399176954734, 'recall': 0.5096153846153846, 'f1': 0.4700665188470066, 'number': 208}, 'P': {'precision': 0.6086956521739131, 'recall': 0.6068111455108359, 'f1': 0.6077519379844962, 'number': 323}, 'overall_precision': 0.5345132743362832, 'overall_recall': 0.568738229755179, 'overall_f1': 0.5510948905109488, 'overall_accuracy': 0.76986280717624}
			------------EPOCH 24---------------
Loss:  tensor(15.2958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.9823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.0353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.8473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.3964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.8405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.8867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.8834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.5235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.2198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.3082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.9819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.5987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.9543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.5737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.8294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.2290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.3852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.1341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.2162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.9528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.6196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.0291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.9287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.4072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.8031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.5094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.1644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.5916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.6462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.7821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.7410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.4005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.8540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.7422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.7222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0224, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4369747899159664, 'recall': 0.5, 'f1': 0.4663677130044843, 'number': 208}, 'P': {'precision': 0.6068111455108359, 'recall': 0.6068111455108359, 'f1': 0.6068111455108359, 'number': 323}, 'overall_precision': 0.5347593582887701, 'overall_recall': 0.5649717514124294, 'overall_f1': 0.5494505494505495, 'overall_accuracy': 0.7700889491934269}
			------------EPOCH 25---------------
Loss:  tensor(13.4212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.4848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.7225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.8631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.3492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.1492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.3291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.6995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.3209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.8641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.5487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.9180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.3672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.5326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.3627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.9432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.2269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.1465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.0970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.9475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.8205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.0892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.0545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.6286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.1674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.1844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2300, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4297872340425532, 'recall': 0.4855769230769231, 'f1': 0.4559819413092551, 'number': 208}, 'P': {'precision': 0.6068111455108359, 'recall': 0.6068111455108359, 'f1': 0.6068111455108359, 'number': 323}, 'overall_precision': 0.532258064516129, 'overall_recall': 0.559322033898305, 'overall_f1': 0.5454545454545455, 'overall_accuracy': 0.7692597617970752}


		-------------RUN 2-----------
			------------EPOCH 1---------------
Loss:  tensor(2484.6704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3952.0403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2659.0244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2980.0356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1607.0896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2720.0757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1410.7692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1746.1398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2394.4587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4087.3518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3132.1816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2824.6108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2702.7690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2185.4968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2722.9312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2464.1055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1226.9457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1262.3267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2359.2610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1363.9211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2203.5884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1585.4409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1583.9004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.5363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1986.4995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1923.1049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1728.3698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2022.5385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1192.8755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2040.5193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2016.8192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1076.8218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1857.5688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(795.6182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.8212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1002.0499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(879.8129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2337.4487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1410.8420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1598.8826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2434.6143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.8577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1912.4993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1250.7046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(861.5745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2209.0449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1373.2007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2197.8479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(984.4071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(978.2628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2700.0825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1929.4258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2709.9348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2620.6992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2551.5771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1135.0190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1698.8629, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1016949152542373, 'recall': 0.02631578947368421, 'f1': 0.041811846689895474, 'number': 228}, 'P': {'precision': 0.05102040816326531, 'recall': 0.03496503496503497, 'f1': 0.04149377593360996, 'number': 286}, 'overall_precision': 0.06274509803921569, 'overall_recall': 0.0311284046692607, 'overall_f1': 0.04161248374512354, 'overall_accuracy': 0.41404358353510895}
			------------EPOCH 2---------------
Loss:  tensor(1562.5927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2594.3164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1788.7002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1866.3298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1065.0835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2172.3716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.4080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1152.8545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1800.7683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3238.8176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2339.3357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2111.8774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1999.5017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1397.7410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1869.0862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2021.7168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(962.9733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(921.5580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1756.2123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1013.4561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1740.8296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1435.0106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1462.1990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(948.3953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1827.8140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1376.4822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1437.3970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1548.5847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(968.6434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1602.1099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1526.4353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.4232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1534.8524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.3361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(643.2365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.0764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(676.8003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1837.6180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1128.0659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1293.1880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2018.4091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.4434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1513.3252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.4971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(703.0764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1812.5481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1138.0227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1860.9823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.4075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(824.1578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2168.6118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1652.1553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2297.7959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2200.1008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2173.9756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(970.2946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1454.7173, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21311475409836064, 'recall': 0.05701754385964912, 'f1': 0.08996539792387544, 'number': 228}, 'P': {'precision': 0.1880952380952381, 'recall': 0.2762237762237762, 'f1': 0.22379603399433426, 'number': 286}, 'overall_precision': 0.19126819126819128, 'overall_recall': 0.17898832684824903, 'overall_f1': 0.18492462311557786, 'overall_accuracy': 0.592751698820589}
			------------EPOCH 3---------------
Loss:  tensor(1162.2067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2051.0991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1460.1796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1390.2180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(855.2017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2061.8975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.8925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(953.5779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1498.9060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2994.3362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2017.4734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1794.7621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1706.9365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1132.2554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1579.8636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1732.2732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.9551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(729.5262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1454.1956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.3220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1417.8325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1072.5854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1033.5787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(703.7915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1357.3374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1115.7816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1324.4719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1388.3829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(850.5764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1358.1206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1275.9855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(735.2770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1339.2812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.9758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.3655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(726.9554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.4987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1442.3070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(914.9951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.2130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1662.9644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(536.1701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1242.0508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(956.8383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.3954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1287.1364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.0646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1495.2668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(716.0478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.6106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1673.2737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1398.9890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1893.9938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1798.7045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1752.6544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(822.3253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1232.8342, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12650602409638553, 'recall': 0.09210526315789473, 'f1': 0.1065989847715736, 'number': 228}, 'P': {'precision': 0.25280898876404495, 'recall': 0.3146853146853147, 'f1': 0.28037383177570097, 'number': 286}, 'overall_precision': 0.21264367816091953, 'overall_recall': 0.21595330739299612, 'overall_f1': 0.21428571428571427, 'overall_accuracy': 0.6029055690072639}
			------------EPOCH 4---------------
Loss:  tensor(948.4057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1707.4524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1170.0835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1137.3640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.9056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1527.9991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.4143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.9074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1104.2883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2355.5767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1501.4854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1275.2559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1401.5085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(822.0195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1300.5295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1365.2273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(652.4478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(539.6148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(960.9396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.6818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1008.7209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.9279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.0990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.6835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(889.0814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(832.6011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1048.6844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1014.1158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.4729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1054.6361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.1340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.5801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1001.4244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.0796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.6441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(533.2209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.8080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1018.3958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.0627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(670.5890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1289.0452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.7057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(887.7623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.1924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.1247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.8348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.9348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1074.1113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.8051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.0687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1298.6685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(953.0135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1139.6464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1254.3379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1200.6251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(681.4514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(831.4313, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21428571428571427, 'recall': 0.23684210526315788, 'f1': 0.225, 'number': 228}, 'P': {'precision': 0.37383177570093457, 'recall': 0.4195804195804196, 'f1': 0.3953871499176277, 'number': 286}, 'overall_precision': 0.3036649214659686, 'overall_recall': 0.33852140077821014, 'overall_f1': 0.3201471941122355, 'overall_accuracy': 0.6910880262438491}
			------------EPOCH 5---------------
Loss:  tensor(626.0320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1140.7819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.3542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(875.2650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(441.6333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1038.5693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.7835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.6113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(777.1541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1894.2937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(877.3755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(891.2366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1166.2759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.1145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1169.3241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1043.4666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.7241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.8926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.7868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.0290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(782.9869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.1302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.3881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.4424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.5227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.4056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(724.4276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.0691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.2177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.9887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(876.1858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.1477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(823.8073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.2030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.4299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.9782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.6722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(897.8047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(566.7422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.8105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(835.7613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.4187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.0924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.6035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.0507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.9120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.9491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.4254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.4830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1115.3075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.0947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.4863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(874.9605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(884.5739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.7288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.2449, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23545706371191136, 'recall': 0.37280701754385964, 'f1': 0.28862478777589134, 'number': 228}, 'P': {'precision': 0.4090909090909091, 'recall': 0.4090909090909091, 'f1': 0.4090909090909091, 'number': 286}, 'overall_precision': 0.312210200927357, 'overall_recall': 0.39299610894941633, 'overall_f1': 0.3479758828596038, 'overall_accuracy': 0.7256892915722878}
			------------EPOCH 6---------------
Loss:  tensor(439.7573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(777.7831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.7139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(646.6367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.6537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.3713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.1554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.6573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.8160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1611.9009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.7568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(838.1643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.6432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.2856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(798.6006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.1077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.9222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.3958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.8652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.9036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(718.9724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.0834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.2903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.7623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(857.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.1050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1215.0697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(896.8431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(753.8281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1333.3870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(925.6757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.0584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(855.8215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.5449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.8464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(590.6216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.9998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.7988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.3028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.6267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.1766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.2789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.9449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.6501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.8314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(545.1658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.3420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.2415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(619.1080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.9968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.8602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(684.2311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(788.6410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1183.2776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(992.6042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.6044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.7764, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17687074829931973, 'recall': 0.11403508771929824, 'f1': 0.13866666666666666, 'number': 228}, 'P': {'precision': 0.32407407407407407, 'recall': 0.48951048951048953, 'f1': 0.38997214484679665, 'number': 286}, 'overall_precision': 0.2867012089810017, 'overall_recall': 0.3229571984435798, 'overall_f1': 0.30375114364135414, 'overall_accuracy': 0.6848394907443568}
			------------EPOCH 7---------------
Loss:  tensor(415.5886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(927.7576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.0918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.1229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.2241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(716.4191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.0875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.3141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.0251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1152.9326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.4863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.8337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.4420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.9021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.4209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.5890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.1090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.6779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.8556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.0515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.9861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.5911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.0936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.0094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.0751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.0572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.1765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.7022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(750.4277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(688.9114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.1088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.7556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.6936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.7160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.7514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.3158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.6311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.8327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.8392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.7302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.7947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(441.5676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.0778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.1599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(491.8925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.7589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.1318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.3421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.7304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(721.3468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.2374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.1282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.3466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.5705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.9141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.6673, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3013698630136986, 'recall': 0.09649122807017543, 'f1': 0.1461794019933555, 'number': 228}, 'P': {'precision': 0.4769874476987448, 'recall': 0.7972027972027972, 'f1': 0.5968586387434555, 'number': 286}, 'overall_precision': 0.4537205081669691, 'overall_recall': 0.48638132295719844, 'overall_f1': 0.4694835680751173, 'overall_accuracy': 0.699679762555651}
			------------EPOCH 8---------------
Loss:  tensor(480.0254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.5130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.4552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(646.7151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.7378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(619.3013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.4141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.7635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1025.2014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.5458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.4055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.4846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.8452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.6682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.7012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.1206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.7770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.6046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.4823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(481.7232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.8240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.3884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.9734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.8735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.4523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.4362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.4505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.9278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.2995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.3404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.2180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.7212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.9531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.1783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.5433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.2703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.6242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.5110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.3435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.3732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.3116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.5287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.4214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.4235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.1251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.7598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.0397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.5483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.7678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(666.9822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.2240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.1660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.8382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.1642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.7530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.5828, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3142857142857143, 'recall': 0.2894736842105263, 'f1': 0.3013698630136986, 'number': 228}, 'P': {'precision': 0.5256410256410257, 'recall': 0.5734265734265734, 'f1': 0.5484949832775919, 'number': 286}, 'overall_precision': 0.44061302681992337, 'overall_recall': 0.4474708171206226, 'overall_f1': 0.444015444015444, 'overall_accuracy': 0.7292821994844958}
			------------EPOCH 9---------------
Loss:  tensor(246.0797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.9223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.5241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.5100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.0218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.9741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.2428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.0398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.6885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(807.1324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.5143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.2365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.1577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.9822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.9820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.9819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.9346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.4757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.4294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.7264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.1573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.4335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.5047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.1166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.1945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.9676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.9772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.1744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.8966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.4764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.9827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.9178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.9949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.6800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.5829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.9269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.8546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.6689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.5989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.6924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(549.8417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.6088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.5070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.0266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.2693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.8438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.5919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.1702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.3470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.8280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.3976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.4489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.3123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.0445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.7455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.0661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.5282, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4221105527638191, 'recall': 0.3684210526315789, 'f1': 0.39344262295081966, 'number': 228}, 'P': {'precision': 0.47721822541966424, 'recall': 0.6958041958041958, 'f1': 0.566145092460882, 'number': 286}, 'overall_precision': 0.4594155844155844, 'overall_recall': 0.5505836575875487, 'overall_f1': 0.5008849557522123, 'overall_accuracy': 0.7045223775677576}
			------------EPOCH 10---------------
Loss:  tensor(267.0351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.5136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.0203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.2768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.5554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.3887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.4304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.9113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.0389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1165.8304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.4269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.2741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.5228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.0653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.1313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.7502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.4543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.2584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.7698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.9233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(577.4117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.4601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.9547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.1216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.6194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.7390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.4264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.3269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.9234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.6746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.0664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.1747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.4799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.1969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.2776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.9437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.0732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.6475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.8680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.5762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.8422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.4745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.2108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.1508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.4539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.1891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.6277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.7423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.3754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.2181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.8190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(468.1317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.6920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(583.3715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.1470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.5096, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3722627737226277, 'recall': 0.6710526315789473, 'f1': 0.47887323943661964, 'number': 228}, 'P': {'precision': 0.6491228070175439, 'recall': 0.5174825174825175, 'f1': 0.575875486381323, 'number': 286}, 'overall_precision': 0.47104851330203446, 'overall_recall': 0.585603112840467, 'overall_f1': 0.5221162185602776, 'overall_accuracy': 0.6938998672186206}
			------------EPOCH 11---------------
Loss:  tensor(488.5448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(742.1075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.3431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.5270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.1599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.2354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.2424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.4014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.0887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.2782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.7441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.2383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.2923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.8316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.0660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.0461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.4962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.9843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.5240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(506.6851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.9323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.0743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.7038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(497.7858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.5382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.1546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.3748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.9469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(670.2598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.6552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.6116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.9914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.3887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.8782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.8221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.8222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.5587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.8550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.9366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.7770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.7731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.6968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.2236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.7513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.7648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.7485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.1578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.6403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.2810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.3283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.6179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.2896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.9695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.8502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.7089, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.37389380530973454, 'recall': 0.7412280701754386, 'f1': 0.4970588235294118, 'number': 228}, 'P': {'precision': 0.6688311688311688, 'recall': 0.36013986013986016, 'f1': 0.46818181818181814, 'number': 286}, 'overall_precision': 0.44884488448844884, 'overall_recall': 0.5291828793774319, 'overall_f1': 0.48571428571428577, 'overall_accuracy': 0.6645317503710068}
			------------EPOCH 12---------------
Loss:  tensor(423.2733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1094.1882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.0483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.5930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(419.5159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.0464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.5511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.5212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.3215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.8505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.2154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.8933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.4328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.5883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.1595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.3392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.2380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.4551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.6510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.5159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.9566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.3195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.3205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.8225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1025.6783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.4414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(873.4718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.6240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1095.1489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(772.4353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.6119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.8751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.9722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.3375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.9744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.6978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.5108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.1060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.5580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.2913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.4305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.9108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.6869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.9673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.7255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.6066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.4919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.9755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.6286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.9648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.9973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.1548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.9330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.0616, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.332579185520362, 'recall': 0.6447368421052632, 'f1': 0.4388059701492537, 'number': 228}, 'P': {'precision': 0.4489795918367347, 'recall': 0.07692307692307693, 'f1': 0.13134328358208958, 'number': 286}, 'overall_precision': 0.34419551934826886, 'overall_recall': 0.32879377431906615, 'overall_f1': 0.3363184079601991, 'overall_accuracy': 0.5712723580410841}
			------------EPOCH 13---------------
Loss:  tensor(905.9073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1989.7349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.1281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1477.0725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.8057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1226.9701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.4775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(666.3855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.0247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1066.0055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(825.5947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.7147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.2182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.8687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(419.7303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.1550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.1259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.4674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.5239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.8608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.4217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.8630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.8321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.9236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.4104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.9131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(985.7222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(750.0828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.6166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(716.0273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.5265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.5065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(580.6909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(764.0350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1060.3250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(661.5372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.0287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1501.0935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1082.1976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1785.6001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1083.5371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.9145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.8848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.2222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(521.4648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.0706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.2716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(843.4669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.3688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.1255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.6941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(451.8777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.0334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.5065, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.40350877192982454, 'recall': 0.706140350877193, 'f1': 0.5135566188197767, 'number': 228}, 'P': {'precision': 0.5879396984924623, 'recall': 0.4090909090909091, 'f1': 0.48247422680412366, 'number': 286}, 'overall_precision': 0.46488294314381273, 'overall_recall': 0.5408560311284046, 'overall_f1': 0.5, 'overall_accuracy': 0.6831211434819964}
			------------EPOCH 14---------------
Loss:  tensor(405.5779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.8219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(419.1331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.8956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.8812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(541.8741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.1641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(389.9044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.4161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(790.5573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.2103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(646.1625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.7532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.6619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.1339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.3471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.0798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.2863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.9790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.7678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.7842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.8323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.9517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.9430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.6927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.4414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.6077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.7639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.6919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.2764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.8785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.2115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.3835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.2896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.7168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.1980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.8326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.2088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.6649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.7022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.6732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.1412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.2961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.9993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.5996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.8960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.9238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.1701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.1008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.3769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.0854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.2233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.2405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.4064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.5252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.2399, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4177215189873418, 'recall': 0.4342105263157895, 'f1': 0.42580645161290326, 'number': 228}, 'P': {'precision': 0.5744047619047619, 'recall': 0.6748251748251748, 'f1': 0.6205787781350481, 'number': 286}, 'overall_precision': 0.5095986038394416, 'overall_recall': 0.5680933852140078, 'overall_f1': 0.5372585096596136, 'overall_accuracy': 0.742560337420917}
			------------EPOCH 15---------------
Loss:  tensor(185.3379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.5201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.7492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.7891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.3234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.2343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.4816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.7885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.4546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.6840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.0194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.4719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.6113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.3558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.8406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.3110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.9740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.1840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.9798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.6490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.1071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.3837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.8942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.8722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.4930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.3614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.9852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.4027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.2562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.7251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.5216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.9714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.2155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.7920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.1898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.1817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.4245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.0744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.7721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.8437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.6071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.1956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.6196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.0823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.1979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.1725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.9651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.1240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.7935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.4722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.0987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2246, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.45819397993311034, 'recall': 0.6008771929824561, 'f1': 0.5199240986717267, 'number': 228}, 'P': {'precision': 0.5746753246753247, 'recall': 0.6188811188811189, 'f1': 0.5959595959595959, 'number': 286}, 'overall_precision': 0.5172981878088962, 'overall_recall': 0.6108949416342413, 'overall_f1': 0.5602140945584301, 'overall_accuracy': 0.7541982347887214}
			------------EPOCH 16---------------
Loss:  tensor(147.8121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.1446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.2892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.2870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.1120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.2912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.5089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.2779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.6715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.2057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.3493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.1263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.4787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.2157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.2577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.0855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.2931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.9285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.2049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.6395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.9568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.3154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.3779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.4847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.0680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.3108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.7830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.6623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.6438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.2028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.2613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.3009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.8034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.7369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.7056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.6114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.6102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.8995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.2664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.3398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.2679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.1108, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.45864661654135336, 'recall': 0.5350877192982456, 'f1': 0.4939271255060729, 'number': 228}, 'P': {'precision': 0.5517241379310345, 'recall': 0.6153846153846154, 'f1': 0.5818181818181819, 'number': 286}, 'overall_precision': 0.5094017094017094, 'overall_recall': 0.5797665369649806, 'overall_f1': 0.5423111919927206, 'overall_accuracy': 0.7534171678512849}
			------------EPOCH 17---------------
Loss:  tensor(97.9987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.5355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.4869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.2503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.7799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.2925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.3448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.3399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.5023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.7944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.8993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.2652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.4142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.4406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.6500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.1712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.5724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.2100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.4009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.9777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.6108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.8207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.5688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.1656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.8519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.3924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5269, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4732824427480916, 'recall': 0.543859649122807, 'f1': 0.5061224489795919, 'number': 228}, 'P': {'precision': 0.5799373040752351, 'recall': 0.6468531468531469, 'f1': 0.6115702479338844, 'number': 286}, 'overall_precision': 0.53184165232358, 'overall_recall': 0.6011673151750972, 'overall_f1': 0.5643835616438356, 'overall_accuracy': 0.7552136218073889}
			------------EPOCH 18---------------
Loss:  tensor(84.4222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.1186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.4676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.8039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.7384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.3127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.7547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.4033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.8008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.6349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.3885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.8254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.6794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.6034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.5242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.2772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.9213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.2147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.7567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.2509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.2747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0731, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4868913857677903, 'recall': 0.5701754385964912, 'f1': 0.5252525252525253, 'number': 228}, 'P': {'precision': 0.5921052631578947, 'recall': 0.6293706293706294, 'f1': 0.6101694915254237, 'number': 286}, 'overall_precision': 0.542907180385289, 'overall_recall': 0.603112840466926, 'overall_f1': 0.5714285714285713, 'overall_accuracy': 0.7481840193704601}
			------------EPOCH 19---------------
Loss:  tensor(73.9727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.6660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.8974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.3969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.4621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.2426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.3770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.8992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.1530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.9064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.6606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.6159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.1797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.1533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.1318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.6788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.4689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.4604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.2137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9944, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4924812030075188, 'recall': 0.5745614035087719, 'f1': 0.5303643724696356, 'number': 228}, 'P': {'precision': 0.5863192182410424, 'recall': 0.6293706293706294, 'f1': 0.6070826306913997, 'number': 286}, 'overall_precision': 0.5427574171029669, 'overall_recall': 0.6050583657587548, 'overall_f1': 0.5722171113155474, 'overall_accuracy': 0.7449816449269703}
			------------EPOCH 20---------------
Loss:  tensor(68.4601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.6502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.3746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.4576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.3027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.1815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.1820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.6695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.7161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.7770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.2657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3523, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4867924528301887, 'recall': 0.5657894736842105, 'f1': 0.5233265720081136, 'number': 228}, 'P': {'precision': 0.5844155844155844, 'recall': 0.6293706293706294, 'f1': 0.606060606060606, 'number': 286}, 'overall_precision': 0.5392670157068062, 'overall_recall': 0.6011673151750972, 'overall_f1': 0.5685372585096595, 'overall_accuracy': 0.7418573771772241}
			------------EPOCH 21---------------
Loss:  tensor(71.2594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.2568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.3706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.4471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.4977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.2556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.7753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.4299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.8555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.3744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.2437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.7197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.2517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.2423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4972, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.48363636363636364, 'recall': 0.5833333333333334, 'f1': 0.5288270377733599, 'number': 228}, 'P': {'precision': 0.584717607973422, 'recall': 0.6153846153846154, 'f1': 0.5996592844974448, 'number': 286}, 'overall_precision': 0.5364583333333334, 'overall_recall': 0.6011673151750972, 'overall_f1': 0.5669724770642202, 'overall_accuracy': 0.744591111458252}
			------------EPOCH 22---------------
Loss:  tensor(44.7439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.4281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.2939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.2922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.9049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4882, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4697508896797153, 'recall': 0.5789473684210527, 'f1': 0.518664047151277, 'number': 228}, 'P': {'precision': 0.6112956810631229, 'recall': 0.6433566433566433, 'f1': 0.6269165247018739, 'number': 286}, 'overall_precision': 0.5429553264604811, 'overall_recall': 0.6147859922178989, 'overall_f1': 0.5766423357664234, 'overall_accuracy': 0.7545106615636961}
			------------EPOCH 23---------------
Loss:  tensor(39.2119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.8068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.8380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4355, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4697508896797153, 'recall': 0.5789473684210527, 'f1': 0.518664047151277, 'number': 228}, 'P': {'precision': 0.6151315789473685, 'recall': 0.6538461538461539, 'f1': 0.6338983050847458, 'number': 286}, 'overall_precision': 0.5452991452991452, 'overall_recall': 0.6206225680933852, 'overall_f1': 0.5805277525022748, 'overall_accuracy': 0.7520893540576428}
			------------EPOCH 24---------------
Loss:  tensor(34.1713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.4768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.1833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.2038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6511, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.48375451263537905, 'recall': 0.5877192982456141, 'f1': 0.5306930693069307, 'number': 228}, 'P': {'precision': 0.6258278145695364, 'recall': 0.6608391608391608, 'f1': 0.6428571428571428, 'number': 286}, 'overall_precision': 0.5578583765112263, 'overall_recall': 0.6284046692607004, 'overall_f1': 0.5910338517840806, 'overall_accuracy': 0.7526361009138484}
			------------EPOCH 25---------------
Loss:  tensor(31.5835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.4474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.3042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7473, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4874551971326165, 'recall': 0.5964912280701754, 'f1': 0.5364891518737672, 'number': 228}, 'P': {'precision': 0.6212624584717608, 'recall': 0.6538461538461539, 'f1': 0.637137989778535, 'number': 286}, 'overall_precision': 0.5568965517241379, 'overall_recall': 0.6284046692607004, 'overall_f1': 0.5904936014625227, 'overall_accuracy': 0.7503710067952823}


		-------------RUN 3-----------
			------------EPOCH 1---------------
Loss:  tensor(2043.1255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2844.1416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1235.1738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1453.8657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2633.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1888.4148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1632.2498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1960.8258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2293.8318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1480.4891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2399.9519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1865.5273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1468.6350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2141.6262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(998.0077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.2309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1051.5293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1640.5825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2530.5923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3100.2173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3124.0496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1612.0128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1967.8038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2485.6643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2054.0581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1069.2969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2013.9988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2699.7471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1340.9447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1646.9883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2337.2988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2931.5588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2012.4203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2436.4229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2745.0483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1756.3102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1658.7697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(840.8704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1461.4858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1755.4182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1373.2096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1111.7379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2137.2754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1144.5378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1106.0212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2228.5430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2011.1250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(916.1241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1103.0337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1528.5920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1624.3367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1956.6775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1916.0933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1089.4370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1720.4924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1481.3004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1553.2700, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.03529411764705882, 'recall': 0.03543307086614173, 'f1': 0.03536345776031434, 'number': 254}, 'P': {'precision': 0.16907216494845362, 'recall': 0.2019704433497537, 'f1': 0.18406285072951736, 'number': 406}, 'overall_precision': 0.12297297297297298, 'overall_recall': 0.13787878787878788, 'overall_f1': 0.12999999999999998, 'overall_accuracy': 0.593255215775936}
			------------EPOCH 2---------------
Loss:  tensor(1360.4574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1760.9156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(773.4249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(893.4534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1705.7876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1102.0302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1029.1063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.4971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1268.8518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(912.5956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1453.7880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1161.7279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(834.3967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1214.6206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.0638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(566.2606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.8152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1257.2136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2061.5056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2227.4199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2248.2710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(961.3046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1576.1228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1748.7484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1542.2009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.0309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1663.6968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2013.2435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1034.0330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1172.2163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1741.6394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2106.8618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1654.0925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1978.3834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1827.9556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1120.6001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1264.7678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.9356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1065.4390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1611.8887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1169.8057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(904.1786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1858.4995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.9334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(783.9883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1688.7021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1516.2629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(721.7895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(873.2892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1177.2448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1224.8167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1526.1511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1409.1313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(781.0193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1327.2515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1174.5477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1282.3468, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.056133056133056136, 'recall': 0.1062992125984252, 'f1': 0.07346938775510205, 'number': 254}, 'P': {'precision': 0.36211031175059955, 'recall': 0.37192118226600984, 'f1': 0.3669501822600243, 'number': 406}, 'overall_precision': 0.19821826280623608, 'overall_recall': 0.2696969696969697, 'overall_f1': 0.22849807445442877, 'overall_accuracy': 0.6444126893398113}
			------------EPOCH 3---------------
Loss:  tensor(1166.9080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1468.1238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.4245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(751.4791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1402.2908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.2754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.2000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(986.3809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(951.6385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.2563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1156.7961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(944.6671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.1549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(963.1459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.3878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.8799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.4304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(970.8650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1474.9603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1742.1172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1790.6116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(797.6362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1292.7048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1477.1566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1282.1351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.7199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1292.8906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1596.5146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(761.0389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(945.1823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1415.7402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1687.0073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1219.5883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1557.2318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1400.1499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(794.9366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(969.8042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.9637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(753.0635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(959.8496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.6859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.0342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1342.3713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(684.1221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.0974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1248.0688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1280.9008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.9589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.5632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.4794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(869.8176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1192.2996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1058.0947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.9962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1007.7676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(830.6440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1166.4445, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24313725490196078, 'recall': 0.2440944881889764, 'f1': 0.243614931237721, 'number': 254}, 'P': {'precision': 0.426890756302521, 'recall': 0.625615763546798, 'f1': 0.5074925074925074, 'number': 406}, 'overall_precision': 0.37176470588235294, 'overall_recall': 0.47878787878787876, 'overall_f1': 0.4185430463576158, 'overall_accuracy': 0.6615032866533295}
			------------EPOCH 4---------------
Loss:  tensor(1202.3646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1418.6250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.3918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(715.5229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1388.7196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(670.9800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.5854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.5579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.4014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.1832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(883.7884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(733.0363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.7527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.8025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.0506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.9519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.0758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.8806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1083.1600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1312.1909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1414.1555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.8710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(988.8829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1200.8807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1016.6161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.5375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(981.9380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1216.9253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(572.4200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.7825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1058.5085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1297.6046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.7534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1198.8496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1069.0914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.6020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.0195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.4976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.9843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.3181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.7560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.0856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(972.4308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.0541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.7777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1062.3645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.7108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.9214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.6468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.4760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.8442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(937.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1223.4355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(700.4656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(951.9740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(775.8130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(906.3129, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.304, 'recall': 0.44881889763779526, 'f1': 0.3624801271860096, 'number': 254}, 'P': {'precision': 0.43013100436681223, 'recall': 0.4852216748768473, 'f1': 0.45601851851851855, 'number': 406}, 'overall_precision': 0.37334933973589435, 'overall_recall': 0.4712121212121212, 'overall_f1': 0.41661085063630277, 'overall_accuracy': 0.6860817376393256}
			------------EPOCH 5---------------
Loss:  tensor(794.9586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(908.8069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.3932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.9550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1244.1469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.4794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(602.2930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(813.0673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.5919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.8648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(873.8099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.1675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.3022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.4496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.2197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.9290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.7379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.4335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1116.0931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1413.7581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1090.6177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.6749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(866.8931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(928.0421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.4573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.0238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(837.4980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1023.2833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.2852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.5468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1122.3055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1431.0363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(791.9401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1041.4768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1035.4902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.1529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.5430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.8766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.9260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.0786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.2579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.0600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(880.1724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.1426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.0359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1252.1650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1232.3428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.7255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.5205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.7964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.7526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1013.7177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.3266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.7313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.0812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.3422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(713.3867, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28450106157112526, 'recall': 0.5275590551181102, 'f1': 0.36965517241379314, 'number': 254}, 'P': {'precision': 0.5917721518987342, 'recall': 0.4605911330049261, 'f1': 0.5180055401662049, 'number': 406}, 'overall_precision': 0.4078780177890724, 'overall_recall': 0.4863636363636364, 'overall_f1': 0.4436765722183829, 'overall_accuracy': 0.6432123463846814}
			------------EPOCH 6---------------
Loss:  tensor(600.8335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.1514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.6280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.2409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(926.4451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.9042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.4375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(718.3120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.4357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.3080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(715.9794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(624.6602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.6663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.2149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.4404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.3177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.3936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.8673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.6630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(859.2914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(863.2313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.8670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.9114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.2456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.5897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.2404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(624.6252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(869.7047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.4366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.4650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.0490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(953.7391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.2983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(753.4326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.8761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.1296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.9954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.9512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.1391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.7320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.5745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.6046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.4722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.9872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.8322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.1580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(643.6110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.6499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.3709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.8956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.9341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.9634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.5616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.2087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(503.7494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.6462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.8251, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.35777126099706746, 'recall': 0.48031496062992124, 'f1': 0.41008403361344536, 'number': 254}, 'P': {'precision': 0.6381909547738693, 'recall': 0.625615763546798, 'f1': 0.6318407960199005, 'number': 406}, 'overall_precision': 0.5087956698240866, 'overall_recall': 0.5696969696969697, 'overall_f1': 0.5375268048606148, 'overall_accuracy': 0.719519862817948}
			------------EPOCH 7---------------
Loss:  tensor(472.7956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.9789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.4336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.3653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.8934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.6822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.9492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.4557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.3204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.2197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.9874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.9951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.2735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.8199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.2888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.6505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.6477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.5049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(778.4465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.7294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.3808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(619.7054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(665.5170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.7192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.5538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.6273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.5835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.8363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.9044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.6699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(718.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.8191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.9288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.7839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.8550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.5284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.9942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.0679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.9787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.7270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.6626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.7992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(450.2252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.5257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.2619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(710.1738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.1063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.9286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.1930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.5395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.5896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.1504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.7109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.2247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.0197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.9777, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.34498834498834496, 'recall': 0.5826771653543307, 'f1': 0.43338213762811123, 'number': 254}, 'P': {'precision': 0.6712328767123288, 'recall': 0.603448275862069, 'f1': 0.6355382619974059, 'number': 406}, 'overall_precision': 0.49496221662468515, 'overall_recall': 0.5954545454545455, 'overall_f1': 0.5405777166437414, 'overall_accuracy': 0.6929408402400686}
			------------EPOCH 8---------------
Loss:  tensor(346.5358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.5674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.4041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.8279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.4893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.6325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.8091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.0242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.9955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.8662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.1065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.2321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.4664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.8413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.1633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.3261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.2411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.8889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.4591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.8790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.1633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.7257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.8192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.0496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.2605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.9244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.5298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.1664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.7404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.6263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.3702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.1887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.9240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.2900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.4279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.1531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.1471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.0766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.9863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.9014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.4610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.7549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.8770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.8054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.5917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.9533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.5147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.2564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.4344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.1921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.1845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.8022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.9743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.0485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.4084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.6252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.1389, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3381294964028777, 'recall': 0.5551181102362205, 'f1': 0.4202682563338301, 'number': 254}, 'P': {'precision': 0.6263736263736264, 'recall': 0.4211822660098522, 'f1': 0.503681885125184, 'number': 406}, 'overall_precision': 0.45217391304347826, 'overall_recall': 0.4727272727272727, 'overall_f1': 0.4622222222222222, 'overall_accuracy': 0.6862532152043441}
			------------EPOCH 9---------------
Loss:  tensor(240.9576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.1697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.9390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.5267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.2754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.4967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.0837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.7834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.0098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.8462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.6957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.6580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.2850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.3389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.8007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.1015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.6740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.7613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.3010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.1826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.8898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.6324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.9086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.3419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.0414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.0810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.0677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(558.2246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.4374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.4963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.4785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.1256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.8532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.6694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.2265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.1603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.9966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.5443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.9446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.0889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.6940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.3570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.4603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.5250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.4576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.7960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.3530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.8762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.3006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.4157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.4743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.6969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.5984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.0539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.3151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.4496, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22727272727272727, 'recall': 0.11811023622047244, 'f1': 0.15544041450777202, 'number': 254}, 'P': {'precision': 0.515625, 'recall': 0.4064039408866995, 'f1': 0.45454545454545453, 'number': 406}, 'overall_precision': 0.4314159292035398, 'overall_recall': 0.29545454545454547, 'overall_f1': 0.3507194244604317, 'overall_accuracy': 0.5846813375250072}
			------------EPOCH 10---------------
Loss:  tensor(473.2828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(795.0986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(506.2576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.8917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.6303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.2295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.7987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.4389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.5102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.1676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.8545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.3624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.7165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.4459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.4671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.9312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.5069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.2901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.9207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.6015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.2076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.7564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.3373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.7757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.9824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.3308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.1846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.2988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.5386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.5887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.8440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.6480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.9571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.2855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.5773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.6888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.6194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.3770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.6757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.0343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.9026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.2796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.1534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.3318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.3054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.3124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.3142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.9365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.3884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.4785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.3011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.4410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.5028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.9065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.4304, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3763440860215054, 'recall': 0.2755905511811024, 'f1': 0.3181818181818182, 'number': 254}, 'P': {'precision': 0.6035242290748899, 'recall': 0.6748768472906403, 'f1': 0.6372093023255814, 'number': 406}, 'overall_precision': 0.5375, 'overall_recall': 0.5212121212121212, 'overall_f1': 0.5292307692307693, 'overall_accuracy': 0.7308945412975135}
			------------EPOCH 11---------------
Loss:  tensor(277.2549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.7243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.5663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.8545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.8318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.6570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.8883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.8017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.9065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.9762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.4421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.6319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.2201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.8246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.1418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.7566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.0121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.0126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.6117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.8973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.1587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.5392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.6956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.0161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.7000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.2992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.9454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.0881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.9556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.9072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.0273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.5095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.6945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.0129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.4017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.2887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.1934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.8139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.8231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.0339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.0978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.5695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.4781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(450.3567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.8166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.9295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.4931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.9487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(678.7162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.3392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.7415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.7303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.8308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.9748, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3795918367346939, 'recall': 0.3661417322834646, 'f1': 0.37274549098196397, 'number': 254}, 'P': {'precision': 0.5493482309124768, 'recall': 0.7266009852216748, 'f1': 0.6256627783669141, 'number': 406}, 'overall_precision': 0.4961636828644501, 'overall_recall': 0.5878787878787879, 'overall_f1': 0.5381414701803051, 'overall_accuracy': 0.7467847956559017}
			------------EPOCH 12---------------
Loss:  tensor(264.9753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.4969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.1177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.3661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.6103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.4383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.1590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.7327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.3753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.3047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.6998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.6124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.9089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.3309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.0407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.7790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.9292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.0466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.0613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.1270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.1060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.8143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.0818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.7761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.6631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.7247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.7294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.3553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.2596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(497.5296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.6087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.7724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(868.2992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(443.9200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.3971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.7805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.4440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.6600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.5449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.7465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.1469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.8089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.5317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.1628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.6976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.4954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.7958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.7472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.1583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.9213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.4621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(474.3877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.0437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(590.0767, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5753424657534246, 'recall': 0.16535433070866143, 'f1': 0.25688073394495414, 'number': 254}, 'P': {'precision': 0.536036036036036, 'recall': 0.8793103448275862, 'f1': 0.6660447761194029, 'number': 406}, 'overall_precision': 0.5399188092016238, 'overall_recall': 0.6045454545454545, 'overall_f1': 0.5704074338813439, 'overall_accuracy': 0.6935695913118034}
			------------EPOCH 13---------------
Loss:  tensor(855.1912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(846.6185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.5774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.1912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.6202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.1336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.7882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.4916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.0153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.5594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.1981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.6414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.8482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.6034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.3220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.8275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.2769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.8988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.4036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.1630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.6764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.1808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.7675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.5501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.4223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.7625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.4361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.7404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.0866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.2054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.6998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.7083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.4051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(702.4146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.9035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.3396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.1044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.9537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.2048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.3787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.5947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.6667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.7973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.4203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.2033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.2038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.2629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.7413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.5352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.1932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.4461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.7198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.1858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.1208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.4659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.3763, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.45454545454545453, 'recall': 0.0984251968503937, 'f1': 0.16181229773462785, 'number': 254}, 'P': {'precision': 0.5, 'recall': 0.7807881773399015, 'f1': 0.6096153846153846, 'number': 406}, 'overall_precision': 0.49637155297532654, 'overall_recall': 0.5181818181818182, 'overall_f1': 0.5070422535211268, 'overall_accuracy': 0.6918548156616176}
			------------EPOCH 14---------------
Loss:  tensor(481.8264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(577.4658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.3663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.6138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(934.0893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.6765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.7913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(468.9808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1082.2385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(702.0585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1053.1096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.7870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.6400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.9995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.3220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.0469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(404.5844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.4297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.0442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.7121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.6378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.3259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.0457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.4142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.1926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.4951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.8323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.6390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.0131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.1570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.0786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.5750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.3217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.2164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.3445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.8709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.9832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.1290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.4443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.0295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.6067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(503.8537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(670.7278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(618.3751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1049.8137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1293.1074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(549.0852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(618.8357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1376.7126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1285.0288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1705.8097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.7470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.9757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(707.4974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(867.3290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.3932, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.37623762376237624, 'recall': 0.5984251968503937, 'f1': 0.46200607902735563, 'number': 254}, 'P': {'precision': 0.6657534246575343, 'recall': 0.5985221674876847, 'f1': 0.6303501945525292, 'number': 406}, 'overall_precision': 0.5136540962288687, 'overall_recall': 0.5984848484848485, 'overall_f1': 0.5528341497550735, 'overall_accuracy': 0.7360960274364104}
			------------EPOCH 15---------------
Loss:  tensor(209.0196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.0837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.7371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.7355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.9768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.3499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.1118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.3689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.6735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.1039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.2790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.9307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.4352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.0074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.8661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.0391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.3916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.1842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.9539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.2687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(831.2185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.4387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.9084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.8021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.8993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.4891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.7562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(461.4080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.4897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.9995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.9059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.1667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.6379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.4870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.8893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.4301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.7167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.8906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.5119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.6592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.2204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.9404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.4669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.1478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.3722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.8906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.0556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.6959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.3313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.1711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.7987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.9211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.2770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.5626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.8530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.4710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.8904, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3882978723404255, 'recall': 0.5748031496062992, 'f1': 0.46349206349206346, 'number': 254}, 'P': {'precision': 0.6467236467236467, 'recall': 0.5591133004926109, 'f1': 0.5997357992073976, 'number': 406}, 'overall_precision': 0.5130674002751031, 'overall_recall': 0.5651515151515152, 'overall_f1': 0.5378514780100938, 'overall_accuracy': 0.7250071448985425}
			------------EPOCH 16---------------
Loss:  tensor(155.8659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.7088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.6544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.7983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.4454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.6283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.5106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.6549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.1179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.8570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.5582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.4718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.0251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.4181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.8751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.8395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.6523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.1551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.0285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.9820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.8729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.1162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.6919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.4967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.3239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.0083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.1508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.2844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.9998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.5157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.1449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.9633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.5981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.3034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.8214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.8588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.3980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.7780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.5914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.7679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.5501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.4669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.3748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.4174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.0626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.5391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.3152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.9627, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4734982332155477, 'recall': 0.5275590551181102, 'f1': 0.4990689013035381, 'number': 254}, 'P': {'precision': 0.6422018348623854, 'recall': 0.6896551724137931, 'f1': 0.665083135391924, 'number': 406}, 'overall_precision': 0.5757997218358831, 'overall_recall': 0.6272727272727273, 'overall_f1': 0.6004350978970269, 'overall_accuracy': 0.7685052872249214}
			------------EPOCH 17---------------
Loss:  tensor(105.8351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.6361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.6151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.5296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.3459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.4249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.5663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.0681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.4851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.1639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.4318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.4130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.9132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.3295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.1989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.9115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.8598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.1842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.2500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.7822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.8354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.1605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.8025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.5114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.4812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.0680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.5759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.4394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.1890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.5964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7272, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.43944636678200694, 'recall': 0.5, 'f1': 0.46777163904235725, 'number': 254}, 'P': {'precision': 0.6437346437346437, 'recall': 0.645320197044335, 'f1': 0.6445264452644527, 'number': 406}, 'overall_precision': 0.5589080459770115, 'overall_recall': 0.5893939393939394, 'overall_f1': 0.5737463126843657, 'overall_accuracy': 0.7451271791940555}
			------------EPOCH 18---------------
Loss:  tensor(54.3387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.7002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.6412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.4832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.1009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.5630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.6009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.5572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.8389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.5378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.8136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.0234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.7091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.5241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.0526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.3999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.4392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.8793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.3832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.7003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.5263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.2411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5123, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4529616724738676, 'recall': 0.5118110236220472, 'f1': 0.48059149722735667, 'number': 254}, 'P': {'precision': 0.6361386138613861, 'recall': 0.6330049261083743, 'f1': 0.6345679012345679, 'number': 406}, 'overall_precision': 0.5600578871201157, 'overall_recall': 0.5863636363636363, 'overall_f1': 0.5729089563286455, 'overall_accuracy': 0.7402114889968563}
			------------EPOCH 19---------------
Loss:  tensor(24.4210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.3585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.9491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.9564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.7762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.6243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.4376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.1239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.5585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.9632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.3813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0147, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4563758389261745, 'recall': 0.5354330708661418, 'f1': 0.4927536231884058, 'number': 254}, 'P': {'precision': 0.6419753086419753, 'recall': 0.6403940886699507, 'f1': 0.6411837237977804, 'number': 406}, 'overall_precision': 0.5633001422475107, 'overall_recall': 0.6, 'overall_f1': 0.5810711665443874, 'overall_accuracy': 0.7350100028579594}
			------------EPOCH 20---------------
Loss:  tensor(18.8724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.8717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.5077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.0801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.4155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.2962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4481, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4483870967741935, 'recall': 0.547244094488189, 'f1': 0.4929078014184397, 'number': 254}, 'P': {'precision': 0.6370370370370371, 'recall': 0.6354679802955665, 'f1': 0.6362515413070283, 'number': 406}, 'overall_precision': 0.5552447552447553, 'overall_recall': 0.6015151515151516, 'overall_f1': 0.5774545454545454, 'overall_accuracy': 0.7300943126607602}
			------------EPOCH 21---------------
Loss:  tensor(24.5210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.2730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.6549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.8856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0057, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.46229508196721314, 'recall': 0.5551181102362205, 'f1': 0.5044722719141325, 'number': 254}, 'P': {'precision': 0.6345679012345679, 'recall': 0.6330049261083743, 'f1': 0.6337854500616522, 'number': 406}, 'overall_precision': 0.5605633802816902, 'overall_recall': 0.603030303030303, 'overall_f1': 0.581021897810219, 'overall_accuracy': 0.7345527293512432}
			------------EPOCH 22---------------
Loss:  tensor(13.9172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.3535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6443, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4533333333333333, 'recall': 0.5354330708661418, 'f1': 0.4909747292418773, 'number': 254}, 'P': {'precision': 0.6356968215158925, 'recall': 0.6403940886699507, 'f1': 0.638036809815951, 'number': 406}, 'overall_precision': 0.5585331452750353, 'overall_recall': 0.6, 'overall_f1': 0.5785244704163622, 'overall_accuracy': 0.7306659045441555}
			------------EPOCH 23---------------
Loss:  tensor(10.7854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.8644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2538, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.45806451612903226, 'recall': 0.5590551181102362, 'f1': 0.5035460992907801, 'number': 254}, 'P': {'precision': 0.6393034825870647, 'recall': 0.6330049261083743, 'f1': 0.6361386138613861, 'number': 406}, 'overall_precision': 0.5603932584269663, 'overall_recall': 0.6045454545454545, 'overall_f1': 0.5816326530612245, 'overall_accuracy': 0.7404401257502143}
			------------EPOCH 24---------------
Loss:  tensor(8.2794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.3064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.7906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1812, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4630225080385852, 'recall': 0.5669291338582677, 'f1': 0.5097345132743363, 'number': 254}, 'P': {'precision': 0.6377171215880894, 'recall': 0.6330049261083743, 'f1': 0.6353522867737947, 'number': 406}, 'overall_precision': 0.561624649859944, 'overall_recall': 0.6075757575757575, 'overall_f1': 0.5836972343522561, 'overall_accuracy': 0.7412975135753073}
			------------EPOCH 25---------------
Loss:  tensor(6.8197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.3909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.2043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3770, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.47896440129449835, 'recall': 0.5826771653543307, 'f1': 0.5257548845470692, 'number': 254}, 'P': {'precision': 0.6339066339066339, 'recall': 0.6354679802955665, 'f1': 0.6346863468634687, 'number': 406}, 'overall_precision': 0.5670391061452514, 'overall_recall': 0.6151515151515151, 'overall_f1': 0.5901162790697675, 'overall_accuracy': 0.7410688768219491}


		-------------RUN 4-----------
			------------EPOCH 1---------------
Loss:  tensor(3476.7896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2981.7739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4069.9558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2515.6208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2094.8616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2218.8669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1947.0535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1828.0566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2280.8503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3652.8813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1946.3221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1506.6393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.8633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(891.2908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2507.3174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2845.2368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1356.4692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2377.9761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1911.8126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1657.8494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1554.4126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2360.7410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2927.4187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2427.2251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2312.0913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3077.4905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2259.6479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2113.6782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2011.3944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2814.2561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1368.5559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1903.1976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3176.1926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2273.0930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2472.6208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1478.3335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1848.1116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2319.1499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2407.1536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3169.3535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1920.8695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2009.9882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1788.2786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1348.5546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(714.9843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1639.3303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1160.9690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.7899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1664.4581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2165.3035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1709.8508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2006.1315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(948.8584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2194.3267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1653.7043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1287.0601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3996.5713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2393.0764, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270}, 'P': {'precision': 0.03389830508474576, 'recall': 0.11926605504587157, 'f1': 0.05279187817258884, 'number': 218}, 'overall_precision': 0.03359173126614987, 'overall_recall': 0.05327868852459016, 'overall_f1': 0.04120443740095087, 'overall_accuracy': 0.3883587786259542}
			------------EPOCH 2---------------
Loss:  tensor(2854.5828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2001.1642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2953.4038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1593.8263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1352.7249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1524.8579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1386.0277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1289.5370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1615.4155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2965.6528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1498.9990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1070.7214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(962.5804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(666.8718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1853.2961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2204.3831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.9290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1815.3271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1388.9054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.0641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1277.2698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1969.6627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2488.4714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2167.8530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1744.0518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2643.2842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1917.3486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1719.1211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1531.5774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2230.3193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1085.2971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1493.3335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2685.5215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1748.5818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2038.6584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1285.4358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1530.8865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2051.6865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2022.0641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2403.0261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1522.3419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1550.2090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1376.8970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1193.8958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.8530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1413.4148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1014.7828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(683.0934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1418.9004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1693.4690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1466.9646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1575.1147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.4272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1903.4084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1323.3406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1080.6040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3787.2820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2198.8730, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16666666666666666, 'recall': 0.014814814814814815, 'f1': 0.0272108843537415, 'number': 270}, 'P': {'precision': 0.13215258855585832, 'recall': 0.44495412844036697, 'f1': 0.20378151260504204, 'number': 218}, 'overall_precision': 0.13324538258575197, 'overall_recall': 0.2069672131147541, 'overall_f1': 0.16211878009630817, 'overall_accuracy': 0.4145197201017812}
			------------EPOCH 3---------------
Loss:  tensor(2606.3882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1739.4602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2625.0403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1320.4885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1219.9515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1406.6733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1236.5123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1108.8054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1465.4635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2463.1487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1310.8357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(946.9949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(835.5127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.8099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1686.8208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1841.5667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(943.0173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1728.6694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1204.7456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1141.5942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.1141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1657.9803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2048.7283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1912.7411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1430.4285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2358.5208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1558.8461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1377.2592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1370.0077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1853.0618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(931.1556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1241.6870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2358.2817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1498.1775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1953.2590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1272.3751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1353.8943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1958.7993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1822.0752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2140.4937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1300.4055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1321.5436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1214.4658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1012.3123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.2762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1204.7273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(872.2601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.5136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.2168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1382.5590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1206.5334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1292.4080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.4497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1699.5859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1176.3406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.7711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3500.3997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2009.1133, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2962962962962963, 'recall': 0.05925925925925926, 'f1': 0.09876543209876545, 'number': 270}, 'P': {'precision': 0.195906432748538, 'recall': 0.6146788990825688, 'f1': 0.2971175166297117, 'number': 218}, 'overall_precision': 0.2032520325203252, 'overall_recall': 0.3073770491803279, 'overall_f1': 0.24469820554649263, 'overall_accuracy': 0.4737595419847328}
			------------EPOCH 4---------------
Loss:  tensor(2097.1748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1618.3230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2270.0642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1118.5457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.3738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1250.6407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1159.1880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(998.5943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1402.6204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2044.9594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1267.6250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(901.3417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.9615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.7752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1415.8022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1653.7946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(861.4041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1460.6008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1043.6586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1053.2273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.3427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1450.9694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1801.9363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1621.5510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1301.7783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1877.5468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1252.3228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1198.6169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1044.7897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1613.4714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.8358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1014.7230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2043.8481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1338.9180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1747.2727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1129.4678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1234.9445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1835.5950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1655.6251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1896.7147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1212.9036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1207.8910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1130.9645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.9800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.4163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1138.9114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(789.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.4709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1053.3054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1125.8159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1143.0593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1106.5710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.4460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1533.6997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.6353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.4196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3006.4478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1642.9402, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3850574712643678, 'recall': 0.24814814814814815, 'f1': 0.3018018018018018, 'number': 270}, 'P': {'precision': 0.2292418772563177, 'recall': 0.5825688073394495, 'f1': 0.3290155440414508, 'number': 218}, 'overall_precision': 0.2664835164835165, 'overall_recall': 0.3975409836065574, 'overall_f1': 0.319078947368421, 'overall_accuracy': 0.5217875318066157}
			------------EPOCH 5---------------
Loss:  tensor(1872.6975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1456.4023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2005.5126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.5811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.6922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1111.9231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1055.2767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.4120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.4309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1823.8247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1152.4010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(744.9338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.2065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.1424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(980.8126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1295.0844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(787.1956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1401.8872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(966.6674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(995.5401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(831.5915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1303.7424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1669.0094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1438.0770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1159.8480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1632.8481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.8307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1066.7682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(814.4577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1322.2395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.7576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(786.5985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1673.5068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1007.2954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1406.2850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(926.8177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(986.3961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1519.4915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1405.9730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1499.5022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.6628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.9049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(923.8089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(757.1050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.6924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(897.1758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.4148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.6902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(799.2240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.5645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(947.2194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(752.3373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.8899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1197.1542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.7581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(634.7087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2581.2861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1298.9783, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.45320197044334976, 'recall': 0.34074074074074073, 'f1': 0.3890063424947146, 'number': 270}, 'P': {'precision': 0.285132382892057, 'recall': 0.6422018348623854, 'f1': 0.3949224259520451, 'number': 218}, 'overall_precision': 0.33429394812680113, 'overall_recall': 0.47540983606557374, 'overall_f1': 0.3925549915397631, 'overall_accuracy': 0.5336354961832062}
			------------EPOCH 6---------------
Loss:  tensor(1502.9806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1388.6958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1817.9287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.7087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.2926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.0793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(961.9056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(676.4246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1058.8794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1435.9449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1121.0370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(639.9259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.8080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.7827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(682.6804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1027.9353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.4506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1060.7039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(735.1584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.6034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.1146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1029.9633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1256.5532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.1577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(921.5336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1325.2722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(921.6409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(948.4709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.9041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1234.0203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(634.7286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(758.8787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1276.5503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.1624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1197.8540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(806.6979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(775.1878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1161.3215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1109.6339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1124.1396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(461.8155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(791.9156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.6594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.1000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.2051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.0096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.4693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.2286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.5249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(699.8604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(815.9818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.9951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.1289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1013.2612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.6368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.2822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2306.9021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1036.0692, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5122950819672131, 'recall': 0.46296296296296297, 'f1': 0.48638132295719844, 'number': 270}, 'P': {'precision': 0.33774834437086093, 'recall': 0.7018348623853211, 'f1': 0.4560357675111773, 'number': 218}, 'overall_precision': 0.3988522238163558, 'overall_recall': 0.569672131147541, 'overall_f1': 0.4691983122362869, 'overall_accuracy': 0.5837309160305344}
			------------EPOCH 7---------------
Loss:  tensor(1044.6520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1152.7512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1485.9387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(583.2869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.2896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.1270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(814.4768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(504.5710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(735.0212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1027.8259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(915.4553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.7578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.0893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.2238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.3622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(778.0912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.7991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(897.7775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.3300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(655.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.9270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.2638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(969.3810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.9641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(654.3953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1030.9714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.1835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.2103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.3163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1020.6640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.3250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.6631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1038.4242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(781.8324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1189.0389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.9005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(541.3824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.5063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(802.0405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(765.7755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.2258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.8107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.4656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.6042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.4990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.7868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.5898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.1087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.7300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(461.7210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.7581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.5921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.5999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(676.0834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.2713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.0967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1683.1768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.5156, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5550660792951542, 'recall': 0.4666666666666667, 'f1': 0.5070422535211268, 'number': 270}, 'P': {'precision': 0.3610503282275711, 'recall': 0.7568807339449541, 'f1': 0.4888888888888888, 'number': 218}, 'overall_precision': 0.42543859649122806, 'overall_recall': 0.5963114754098361, 'overall_f1': 0.4965870307167236, 'overall_accuracy': 0.589058524173028}
			------------EPOCH 8---------------
Loss:  tensor(696.8637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1025.0732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1264.3600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.6522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.0925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.5044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(708.2642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.1850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.1724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(976.8621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(742.4149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.0752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.9578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.0580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.2521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(755.0427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.5203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.2153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.1230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.2957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(404.1845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(483.9319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(654.1251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.0861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.5848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(823.7357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.3594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.9699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.9455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.5764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.7380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.8192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(698.4540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.0498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(577.8160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(822.6586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.8571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.8742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.9994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.6024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.5466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.7293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.7704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.5735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.2808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.8495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.2326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.8539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.9818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.5178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.9081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.0399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.2274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.7516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.0775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1158.2477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.7319, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5441176470588235, 'recall': 0.4111111111111111, 'f1': 0.46835443037974683, 'number': 270}, 'P': {'precision': 0.3957894736842105, 'recall': 0.8623853211009175, 'f1': 0.5425685425685425, 'number': 218}, 'overall_precision': 0.44035346097201766, 'overall_recall': 0.6127049180327869, 'overall_f1': 0.5124250214224508, 'overall_accuracy': 0.5648059796437659}
			------------EPOCH 9---------------
Loss:  tensor(588.9902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(876.6300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1086.8641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.2031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.2467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.1281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.4667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.5970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.7754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1342.6736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.4453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.1471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.9139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.4720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.1957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(889.4346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.9506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.4078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.0859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.9244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.5572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.5246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(751.8362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1042.1440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.7505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.3609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.8439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.3272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.0717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.6009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.8693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.4690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.3650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.6653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.1584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(764.5768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1400.9277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.6868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1249.4041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.5934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.7907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.7119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.1828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.2889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.4516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.9619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.6058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.4383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.0678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.3518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.9375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.3040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.8090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.1090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(820.3478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.8964, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5390070921985816, 'recall': 0.562962962962963, 'f1': 0.5507246376811594, 'number': 270}, 'P': {'precision': 0.4424083769633508, 'recall': 0.7752293577981652, 'f1': 0.5633333333333334, 'number': 218}, 'overall_precision': 0.48343373493975905, 'overall_recall': 0.6577868852459017, 'overall_f1': 0.5572916666666666, 'overall_accuracy': 0.634382951653944}
			------------EPOCH 10---------------
Loss:  tensor(300.6783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.0733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.9071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.0176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.2700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.7533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.2448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.0402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.7447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.7707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.5291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.0465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.3488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.6835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.6896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(909.1895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.1396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1003.8180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.1237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.5885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.0459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(616.6316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(887.6818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1156.1304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.4348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1062.0336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(517.2428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.6670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.6628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.4261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.6533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.2797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(694.8901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.6909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.1365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.9443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.8295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(484.7791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(451.9641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.4285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.9688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(496.9697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.8235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.1738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.5407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.5493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.8585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.2742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.1836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1051.2329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(750.5690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.2617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.2929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.7648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.2689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.1598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1276.4044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.2906, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.535483870967742, 'recall': 0.3074074074074074, 'f1': 0.3905882352941176, 'number': 270}, 'P': {'precision': 0.38396624472573837, 'recall': 0.8348623853211009, 'f1': 0.5260115606936415, 'number': 218}, 'overall_precision': 0.42130365659777425, 'overall_recall': 0.5430327868852459, 'overall_f1': 0.4744852282900627, 'overall_accuracy': 0.605041348600509}
			------------EPOCH 11---------------
Loss:  tensor(292.8845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(497.2177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.0835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.7014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.5215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.9113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.6879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.8082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.7086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.8384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.1056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.0865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.2756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.4295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.6126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(483.5457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.4263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(601.1956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.0497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.6664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.8929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.1876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.2264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(939.1630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.8561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(828.8140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.6548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(558.0594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.7747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.8419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.1473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.4838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1205.3120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.3357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(676.9045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.3313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.4377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(851.8610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.1878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.6296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.7086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.5294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.6746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.9115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.9652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.6214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.6234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.1950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.6203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.1452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.0816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.6698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.4328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.6698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.0533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.5437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(939.4344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.3146, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.46788990825688076, 'recall': 0.37777777777777777, 'f1': 0.4180327868852459, 'number': 270}, 'P': {'precision': 0.4297082228116711, 'recall': 0.7431192660550459, 'f1': 0.5445378151260504, 'number': 218}, 'overall_precision': 0.4436974789915966, 'overall_recall': 0.5409836065573771, 'overall_f1': 0.48753462603878117, 'overall_accuracy': 0.6410623409669212}
			------------EPOCH 12---------------
Loss:  tensor(194.1086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(500.9554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.1714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.4929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.4665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.7092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.9384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.8062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.8309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.2330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.1739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.3361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.3097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.6772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.4040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.1266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.7454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.0812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.6340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.0475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.5242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.5251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.4952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.8301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.6064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.9224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.0654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.3567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.8572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.2690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.4562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.4420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.5452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(639.5072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.7859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.7336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(587.7379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(412.6205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.4766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.6928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.7176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.6196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.6116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.7796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.8844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.1213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.1293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.8033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.9991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.6450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.6845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.2675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.5568, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4744525547445255, 'recall': 0.48148148148148145, 'f1': 0.47794117647058826, 'number': 270}, 'P': {'precision': 0.4465753424657534, 'recall': 0.7477064220183486, 'f1': 0.5591766723842195, 'number': 218}, 'overall_precision': 0.458528951486698, 'overall_recall': 0.6004098360655737, 'overall_f1': 0.5199645075421473, 'overall_accuracy': 0.648854961832061}
			------------EPOCH 13---------------
Loss:  tensor(78.1198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.5269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.6116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.7894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.4087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.7142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.9711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.0274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.1687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.0454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.9362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.7437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.3755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.2605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.2196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.7659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.0555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.5358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(483.5403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.0030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(802.4482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(851.1911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.6281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.5222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.0279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.9844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.5663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.2601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.1759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.1931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.5795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.6243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.6224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.3411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.0888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.0199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1290.1693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1103.4551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(908.9755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.5588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.8001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.3959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.5944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.0727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.5023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.4135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.2536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.4071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.7474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.2601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.7539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.2485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.4391, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4826388888888889, 'recall': 0.5148148148148148, 'f1': 0.49820788530465954, 'number': 270}, 'P': {'precision': 0.4553314121037464, 'recall': 0.7247706422018348, 'f1': 0.5592920353982301, 'number': 218}, 'overall_precision': 0.46771653543307085, 'overall_recall': 0.6086065573770492, 'overall_f1': 0.5289403383793411, 'overall_accuracy': 0.6613390585241731}
			------------EPOCH 14---------------
Loss:  tensor(104.8611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.6523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.2171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.9964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.6698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.2930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.1859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.0213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.4035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.9932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.0960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.7644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.5365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.0577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.0744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.1466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.1860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.2894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.2537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.8125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.2816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.8071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.8630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.8896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(587.5743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.4264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.4666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.7820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.8771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.9359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.8203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.5267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.8920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(856.6083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.9266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.5681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.5878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.3306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.3283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.6853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.7784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.0665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.1606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.3140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.0137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.1286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.6173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.6505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.4950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(684.6848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.1012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.3654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2560.0898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1246.6025, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.42047531992687387, 'recall': 0.8518518518518519, 'f1': 0.5630354957160343, 'number': 270}, 'P': {'precision': 0.6024096385542169, 'recall': 0.22935779816513763, 'f1': 0.33222591362126247, 'number': 218}, 'overall_precision': 0.4444444444444444, 'overall_recall': 0.5737704918032787, 'overall_f1': 0.5008944543828264, 'overall_accuracy': 0.6023377862595419}
			------------EPOCH 15---------------
Loss:  tensor(970.7172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2313.1997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2157.7334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1362.8225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.6089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.8412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.9723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.1620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.9822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.3820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.9300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.9731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.6618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.6721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.0133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.7455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.5319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.1915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.0657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.8546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.5090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.8063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.6488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.0327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.6897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.9646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.5202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.7693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.0886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.5474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.6213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.7466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.8088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.5336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1104.8663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.9346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(872.5551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(997.9713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.7360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(878.9781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.0061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(745.3488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(663.5599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1240.7012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.8882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.9280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.9852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.0280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.3188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.9675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.4481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.1398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.9272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.4929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.4128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(441.4976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.6259, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5290322580645161, 'recall': 0.6074074074074074, 'f1': 0.5655172413793104, 'number': 270}, 'P': {'precision': 0.4222972972972973, 'recall': 0.573394495412844, 'f1': 0.48638132295719844, 'number': 218}, 'overall_precision': 0.4768976897689769, 'overall_recall': 0.5922131147540983, 'overall_f1': 0.5283363802559414, 'overall_accuracy': 0.6556933842239185}
			------------EPOCH 16---------------
Loss:  tensor(191.7113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.1693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.7411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.7647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.4453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.2832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.6909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.7232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.3007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(497.8527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.9223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.5245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.0167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.7947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.8054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.0973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.4367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.7025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.9265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.8870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.7913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.6995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1022.9110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.3721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.9890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.5011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.6424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.0970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.2971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.5054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.6092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.7712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.7393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.7045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.8505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.7171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.3641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.5804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.7989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.9948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.9951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.3581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.5711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.9505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.9552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.5781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.3894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.7756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.2832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.4429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.1606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.6942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.0590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.4176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.3767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.2461, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5902439024390244, 'recall': 0.44814814814814813, 'f1': 0.5094736842105264, 'number': 270}, 'P': {'precision': 0.3971631205673759, 'recall': 0.7706422018348624, 'f1': 0.5241809672386896, 'number': 218}, 'overall_precision': 0.4601910828025478, 'overall_recall': 0.5922131147540983, 'overall_f1': 0.5179211469534051, 'overall_accuracy': 0.6355756997455471}
			------------EPOCH 17---------------
Loss:  tensor(272.1026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.1141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.2973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.3728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.5647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.2792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.3244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.4961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.7699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.0393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.6966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.4066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.9022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.1338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.2758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.9419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.6604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.0228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.2737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.2854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.2471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.5035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.5031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.0537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.6340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.8267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.1903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.4887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.8724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.8445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.3350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.2451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.8695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.8146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.1324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.3506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.7215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.6687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.1716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.8686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.6107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.5428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0679, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5581395348837209, 'recall': 0.5333333333333333, 'f1': 0.5454545454545454, 'number': 270}, 'P': {'precision': 0.4154727793696275, 'recall': 0.6651376146788991, 'f1': 0.5114638447971781, 'number': 218}, 'overall_precision': 0.47611202635914335, 'overall_recall': 0.5922131147540983, 'overall_f1': 0.5278538812785388, 'overall_accuracy': 0.6687340966921119}
			------------EPOCH 18---------------
Loss:  tensor(26.3881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.2562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.0192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.5794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.6829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.4097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.2316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.4413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.5098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.1755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.7618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.2891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.9482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.5305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.6839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.7738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.5806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.9796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.6571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.5927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.7313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.1832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.6879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.7711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.5067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.1282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.5123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2745, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.592, 'recall': 0.5481481481481482, 'f1': 0.5692307692307692, 'number': 270}, 'P': {'precision': 0.43567251461988304, 'recall': 0.6834862385321101, 'f1': 0.5321428571428571, 'number': 218}, 'overall_precision': 0.5016891891891891, 'overall_recall': 0.6086065573770492, 'overall_f1': 0.5499999999999999, 'overall_accuracy': 0.6785941475826972}
			------------EPOCH 19---------------
Loss:  tensor(18.4072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.1254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.2039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.5255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.0812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.1152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.1541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.4565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.4300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.5063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.3825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.6879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.1894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.4634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.7768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.9297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7975, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5918367346938775, 'recall': 0.5370370370370371, 'f1': 0.5631067961165048, 'number': 270}, 'P': {'precision': 0.423728813559322, 'recall': 0.6880733944954128, 'f1': 0.5244755244755245, 'number': 218}, 'overall_precision': 0.49248747913188645, 'overall_recall': 0.6045081967213115, 'overall_f1': 0.5427782888684453, 'overall_accuracy': 0.6766857506361323}
			------------EPOCH 20---------------
Loss:  tensor(13.3031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.0436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.4735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.4518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.6163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.5898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.1576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.8564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.6001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.9542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.4680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.5038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.3915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1815, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.6024590163934426, 'recall': 0.5444444444444444, 'f1': 0.5719844357976653, 'number': 270}, 'P': {'precision': 0.4209039548022599, 'recall': 0.6834862385321101, 'f1': 0.5209790209790209, 'number': 218}, 'overall_precision': 0.49498327759197325, 'overall_recall': 0.6065573770491803, 'overall_f1': 0.5451197053406998, 'overall_accuracy': 0.6791507633587787}
			------------EPOCH 21---------------
Loss:  tensor(10.7406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.6215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.3426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.6404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.6230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.1323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.6295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.5727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.1609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.2927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.1835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.5138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.4298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.3009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.9734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6853, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5951417004048583, 'recall': 0.5444444444444444, 'f1': 0.5686653771760153, 'number': 270}, 'P': {'precision': 0.42329545454545453, 'recall': 0.6834862385321101, 'f1': 0.5228070175438596, 'number': 218}, 'overall_precision': 0.4941569282136895, 'overall_recall': 0.6065573770491803, 'overall_f1': 0.5446182152713891, 'overall_accuracy': 0.6805820610687023}
			------------EPOCH 22---------------
Loss:  tensor(9.3104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.8360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.4529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.1371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.8644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.0994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.8009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.1696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3752, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5959183673469388, 'recall': 0.5407407407407407, 'f1': 0.566990291262136, 'number': 270}, 'P': {'precision': 0.4253521126760563, 'recall': 0.6926605504587156, 'f1': 0.5270506108202444, 'number': 218}, 'overall_precision': 0.495, 'overall_recall': 0.6086065573770492, 'overall_f1': 0.5459558823529412, 'overall_accuracy': 0.6788326972010178}
			------------EPOCH 23---------------
Loss:  tensor(8.3475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.6030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.7606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.1746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.5532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.9907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2267, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.6186440677966102, 'recall': 0.5407407407407407, 'f1': 0.5770750988142292, 'number': 270}, 'P': {'precision': 0.4253521126760563, 'recall': 0.6926605504587156, 'f1': 0.5270506108202444, 'number': 218}, 'overall_precision': 0.5025380710659898, 'overall_recall': 0.6086065573770492, 'overall_f1': 0.5505097312326228, 'overall_accuracy': 0.6801844783715013}
			------------EPOCH 24---------------
Loss:  tensor(7.2497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.9059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.5600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.6433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.4086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0018, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.6170212765957447, 'recall': 0.5370370370370371, 'f1': 0.5742574257425743, 'number': 270}, 'P': {'precision': 0.4241573033707865, 'recall': 0.6926605504587156, 'f1': 0.5261324041811847, 'number': 218}, 'overall_precision': 0.5008460236886633, 'overall_recall': 0.6065573770491803, 'overall_f1': 0.5486561631139945, 'overall_accuracy': 0.6779580152671756}
			------------EPOCH 25---------------
Loss:  tensor(6.2430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.8126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.2277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.5784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.7534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8346, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.6163793103448276, 'recall': 0.5296296296296297, 'f1': 0.5697211155378487, 'number': 270}, 'P': {'precision': 0.42178770949720673, 'recall': 0.6926605504587156, 'f1': 0.5243055555555556, 'number': 218}, 'overall_precision': 0.49830508474576274, 'overall_recall': 0.6024590163934426, 'overall_f1': 0.5454545454545454, 'overall_accuracy': 0.6762881679389313}


		-------------RUN 5-----------
			------------EPOCH 1---------------
Loss:  tensor(3010.2336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2788.7749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4085.6831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1771.4453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2042.6997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2511.0786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3156.2661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2949.4919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1705.4609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2086.3933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2887.1001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3318.9106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1521.6089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1741.6633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1530.4342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1606.5083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1644.7310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2446.1040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1151.7563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2005.0955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1861.1604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2244.8706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2215.4448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1734.3914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2576.5239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2908.9919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1650.4427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.2903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2042.6257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1789.5173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2038.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2187.3711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1996.2771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(989.6352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1844.5908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1761.6453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1638.8696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2044.3949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2633.5471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.3882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1319.2708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1398.4797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1627.9867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(885.6505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1349.8829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2081.9333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1861.0106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2247.8926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1173.6986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1781.4739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1531.4357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1583.2750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1643.9454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1219.1572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.4501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1514.8673, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11433756805807622, 'recall': 0.24803149606299213, 'f1': 0.15652173913043477, 'number': 254}, 'P': {'precision': 0.15432098765432098, 'recall': 0.08561643835616438, 'f1': 0.11013215859030838, 'number': 292}, 'overall_precision': 0.12342215988779803, 'overall_recall': 0.16117216117216118, 'overall_f1': 0.13979348689436064, 'overall_accuracy': 0.5172390572390573}
			------------EPOCH 2---------------
Loss:  tensor(2181.5120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1814.8198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2820.2314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1079.5076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1341.5049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1897.9858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2159.0852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1883.6556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1105.7603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1411.5067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2017.9916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2067.5811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.9827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1230.7412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1135.1451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1166.7297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1198.7515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1758.6531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(838.2694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1425.1003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1292.2129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1728.7233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1628.1072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1335.8402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1861.9006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2494.2896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1506.2821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(972.9629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1855.6646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1278.2866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1458.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1858.0339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1582.9567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(714.5490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1342.1025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1370.1562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1330.6870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1655.4540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2257.1836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(965.9742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(920.7671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1025.4902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1299.0702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(751.7335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1043.1379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1836.9194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1369.1230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1770.3898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(945.8053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1475.3491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1183.8265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1297.0835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1294.4554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(983.5020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.8766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1055.2760, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24, 'recall': 0.23622047244094488, 'f1': 0.23809523809523808, 'number': 254}, 'P': {'precision': 0.3819951338199513, 'recall': 0.5376712328767124, 'f1': 0.4466571834992888, 'number': 292}, 'overall_precision': 0.32829046898638425, 'overall_recall': 0.3974358974358974, 'overall_f1': 0.35956917978458985, 'overall_accuracy': 0.6238383838383839}
			------------EPOCH 3---------------
Loss:  tensor(1633.3494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1485.1027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2285.1831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(801.0326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(918.2610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1384.0781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1579.8416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1432.2659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.6950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1174.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1579.0427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1491.4211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(826.2316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(855.6573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(899.2383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.6993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(879.5450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1336.3558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.0299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1176.6741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.9946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1255.6328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1091.2858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(961.2587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1355.7806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2019.8522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1055.3522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.7646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1342.1357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1070.9613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1176.4810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1562.3105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1157.4054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.6664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(921.4454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1054.8677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1109.6039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1314.3821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1825.1156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.2838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.8055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(757.4174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1112.0121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(573.2157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(823.1277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1642.3179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1035.7224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1383.4668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.6879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1140.9150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(908.6896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1069.2311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(995.8666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.2798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.8051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(798.5612, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1918238993710692, 'recall': 0.24015748031496062, 'f1': 0.2132867132867133, 'number': 254}, 'P': {'precision': 0.4525, 'recall': 0.6198630136986302, 'f1': 0.523121387283237, 'number': 292}, 'overall_precision': 0.3370473537604457, 'overall_recall': 0.4432234432234432, 'overall_f1': 0.3829113924050633, 'overall_accuracy': 0.6451851851851852}
			------------EPOCH 4---------------
Loss:  tensor(1336.6166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1257.4250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2002.1527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.2230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.0714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.4803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1341.5820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.9792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.5381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(918.8103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1217.4124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1162.3798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.3648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(741.6265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(639.7112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.1253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(700.1479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1062.0580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.8756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(885.3102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(820.0756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1013.9638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1043.7705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(814.0957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(991.1208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1333.1543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.7632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.5654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(793.9803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(993.0050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.1294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1558.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1042.9957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.6376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.5638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(969.4787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1059.5920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1117.0426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1919.8497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.2277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.2118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(525.0227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(973.3411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.7461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.3036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1151.1876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.5388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1020.2059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.9121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1356.3835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(898.5411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(973.7709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.1057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.1573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.7907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.0801, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30603448275862066, 'recall': 0.2795275590551181, 'f1': 0.2921810699588477, 'number': 254}, 'P': {'precision': 0.5260273972602739, 'recall': 0.6575342465753424, 'f1': 0.5844748858447487, 'number': 292}, 'overall_precision': 0.440536013400335, 'overall_recall': 0.4816849816849817, 'overall_f1': 0.46019247594050744, 'overall_accuracy': 0.6936700336700337}
			------------EPOCH 5---------------
Loss:  tensor(638.7607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1003.2680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1467.7021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.1198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.6763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(764.0472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1096.8789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(893.0294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.0266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.1115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1069.5405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(894.0570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(586.1849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.1113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.3005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(650.9548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.4159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.8848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(485.4434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(773.2770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(648.6342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(807.0227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.5426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.6411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(790.5898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.0881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.8747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.5820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.6957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.1569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.0914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(944.2456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.6754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.9530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.4399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.7006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(666.1582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(799.7935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1125.6061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.9535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.7748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.5969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(773.5030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.5889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.7345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.3627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.9713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(846.2863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.9772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(693.1085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.7190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(788.8312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.2576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.0983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.9688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.7562, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.285140562248996, 'recall': 0.2795275590551181, 'f1': 0.2823061630218688, 'number': 254}, 'P': {'precision': 0.6136363636363636, 'recall': 0.2773972602739726, 'f1': 0.38207547169811323, 'number': 292}, 'overall_precision': 0.3989501312335958, 'overall_recall': 0.2783882783882784, 'overall_f1': 0.32793959007551243, 'overall_accuracy': 0.5719865319865319}
			------------EPOCH 6---------------
Loss:  tensor(904.3516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1415.4056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1760.8357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(788.0870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.7278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.3119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.6609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(948.6705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.3494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.2653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(719.0762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.4427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(577.3928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.4486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.7812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.2974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(782.5765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.5224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.3235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.0984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(539.0124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.2037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.7404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.3460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(965.1018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1285.9301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.3869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.9162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.5589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.2286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.1570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1163.4106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1047.4166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.4386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.2453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.4670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.6680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(759.8668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1167.7852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.0038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.0369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.3450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.1868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.6877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.5563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.0201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.8505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.7648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.6010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(764.5592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(541.9950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(796.3011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.5952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.6046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.2369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.4507, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.373134328358209, 'recall': 0.1968503937007874, 'f1': 0.2577319587628866, 'number': 254}, 'P': {'precision': 0.4602739726027397, 'recall': 0.5753424657534246, 'f1': 0.5114155251141552, 'number': 292}, 'overall_precision': 0.43687374749499, 'overall_recall': 0.3992673992673993, 'overall_f1': 0.41722488038277517, 'overall_accuracy': 0.6773737373737374}
			------------EPOCH 7---------------
Loss:  tensor(561.0668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(926.3521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1461.7974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(613.6235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.4553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.4277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.5289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.1317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.7000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.4840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.5813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.6789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.3751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.8235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.4161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(461.5569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(583.1198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.7047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.0395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.5880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.7623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.8851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(443.5692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.7664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.6185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.0235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.9829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.2263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(681.3787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(673.5344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(712.5078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.1549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.9799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.6393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.2781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.6989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.5919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(868.5939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.1758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.3668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.8351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.0955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.1176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.4228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.7883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(601.7624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(958.5210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.7176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(601.4084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.4676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(655.3633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.8046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.8793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.7111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(481.1592, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4112903225806452, 'recall': 0.20078740157480315, 'f1': 0.2698412698412698, 'number': 254}, 'P': {'precision': 0.5131578947368421, 'recall': 0.6678082191780822, 'f1': 0.5803571428571429, 'number': 292}, 'overall_precision': 0.4880952380952381, 'overall_recall': 0.45054945054945056, 'overall_f1': 0.4685714285714285, 'overall_accuracy': 0.68996632996633}
			------------EPOCH 8---------------
Loss:  tensor(273.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.9294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.5984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.3725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.8839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.4682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(673.4903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(741.6576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.7975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(484.6328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.3203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.2106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(641.1560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.8463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.6849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.0310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.0175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.8184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.9979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.2883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.8446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.4626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.9007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.1624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.0143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(597.4645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.7712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.7542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.8008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.1269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.9795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.5929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.6117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.5292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.8284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.7094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.6415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.7086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(573.5314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.4925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.5546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.9037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(602.0886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.2299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.1181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.3058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.6965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.1929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.9201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.9774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.0241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.2654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.3903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.8461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.9117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.2608, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.41694915254237286, 'recall': 0.484251968503937, 'f1': 0.44808743169398907, 'number': 254}, 'P': {'precision': 0.5954415954415955, 'recall': 0.7157534246575342, 'f1': 0.6500777604976672, 'number': 292}, 'overall_precision': 0.5139318885448917, 'overall_recall': 0.608058608058608, 'overall_f1': 0.5570469798657718, 'overall_accuracy': 0.7101010101010101}
			------------EPOCH 9---------------
Loss:  tensor(332.8927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(782.4014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.9703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.3372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.8790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.2051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(474.4177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.3595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.8774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.7242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.2199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.5052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.1296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.2791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.3460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.5229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.0900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.7002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.4065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.0909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.7328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.6653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.9946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(576.6018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.0762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.4561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.7244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.6560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.8814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.7869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(751.1163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.8024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.0654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.4774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.5569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.4213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.1759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.8098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.3040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.0141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.2376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.7092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.5864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.8900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.5724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.7643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.8891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.1720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.9435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.5891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.9052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.6148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.1272, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.36231884057971014, 'recall': 0.5905511811023622, 'f1': 0.4491017964071856, 'number': 254}, 'P': {'precision': 0.4968944099378882, 'recall': 0.547945205479452, 'f1': 0.521172638436482, 'number': 292}, 'overall_precision': 0.421195652173913, 'overall_recall': 0.5677655677655677, 'overall_f1': 0.48361934477379087, 'overall_accuracy': 0.6322558922558923}
			------------EPOCH 10---------------
Loss:  tensor(738.5636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(565.9629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(967.4613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.5264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.9750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.8751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.4154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.1176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.6972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.5887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(652.5475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.6977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.3956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.3644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.9691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.6290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.0839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.3434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.8504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.4033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.3433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.7473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.1606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.8920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.0776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.1067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.2396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.9854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.1703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.8417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.2811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.6561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.6360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.1891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.3054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.9985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.5494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.8096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.2851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.8277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.9436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.6747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.2616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.1333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.2750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.9392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.1671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.3999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.7494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.9422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.6397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.5149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.2931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.2354, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.41368078175895767, 'recall': 0.5, 'f1': 0.4527629233511587, 'number': 254}, 'P': {'precision': 0.5466666666666666, 'recall': 0.5616438356164384, 'f1': 0.5540540540540541, 'number': 292}, 'overall_precision': 0.4794069192751236, 'overall_recall': 0.532967032967033, 'overall_f1': 0.5047701647875108, 'overall_accuracy': 0.712996632996633}
			------------EPOCH 11---------------
Loss:  tensor(84.6201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.9931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.6964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.7841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.9257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.0939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.5219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.3588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.0129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.5005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.5206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.3168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.9346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.7440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.5995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.7500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.3885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.1579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.9783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.8404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.7172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.0278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.7552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.8773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.0325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.9029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.3763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.4621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.4151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.3935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.1391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.7317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.7799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.2704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.2487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.7051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.6219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.4214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.9478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.9772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.2010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.4822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.1265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.9806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.6402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.4325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.6642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.3902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.7787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.4368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.4827, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.40359897172236503, 'recall': 0.6181102362204725, 'f1': 0.48833592534992215, 'number': 254}, 'P': {'precision': 0.527027027027027, 'recall': 0.4006849315068493, 'f1': 0.45525291828793774, 'number': 292}, 'overall_precision': 0.44844517184942717, 'overall_recall': 0.5018315018315018, 'overall_f1': 0.47363872082973213, 'overall_accuracy': 0.7061952861952862}
			------------EPOCH 12---------------
Loss:  tensor(84.6432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.8606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.1781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.3362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.4932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.5724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.3626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.1310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.5279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.4904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.9525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.3917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.4350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.3137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.4255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.0582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.7180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.0307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.2551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.4125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.7979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.1749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.2730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.4092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.0363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.5542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.4947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.5801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.4292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.3412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.5700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.7343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.8342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.3311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.8494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.3517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.3709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.6405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.6174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.3456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.5412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.2113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.0626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.7711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.9567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.3702, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3473491773308958, 'recall': 0.7480314960629921, 'f1': 0.47440699126092384, 'number': 254}, 'P': {'precision': 0.546875, 'recall': 0.11986301369863013, 'f1': 0.19662921348314605, 'number': 292}, 'overall_precision': 0.36824877250409166, 'overall_recall': 0.41208791208791207, 'overall_f1': 0.3889369057908384, 'overall_accuracy': 0.6134680134680135}
			------------EPOCH 13---------------
Loss:  tensor(816.8450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2201.1963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1854.7974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.5482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.9440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.6791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.9317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.3617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.1129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.8694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.0502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.0254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.1304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.9809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.7477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.1368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.9538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.9731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.0738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.9544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.5723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.5929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.1588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.4138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.4012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.7896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.0960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.6921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.4045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.3806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.2339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.8035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.3425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.7025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.5492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.3461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.8672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.4514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.7551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.9224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.6013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.5089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.0427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.4980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.9106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.0697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.2627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.0995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.2123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.6393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.7708, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3722334004024145, 'recall': 0.7283464566929134, 'f1': 0.492676431424767, 'number': 254}, 'P': {'precision': 0.4897959183673469, 'recall': 0.1643835616438356, 'f1': 0.24615384615384614, 'number': 292}, 'overall_precision': 0.3915966386554622, 'overall_recall': 0.4267399267399267, 'overall_f1': 0.40841367221735314, 'overall_accuracy': 0.6412121212121212}
			------------EPOCH 14---------------
Loss:  tensor(76.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.5695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.5849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.2135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.6489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.1552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.1843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(636.3915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.5783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.5715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(848.0726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1505.9844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.9315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.1777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.8953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.8278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.8169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.2338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.0110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.2439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.5372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.9430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.5464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.6194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.5241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.9281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.6999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.7379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.5411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.6244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.6281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.6765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.4304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.8568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.0543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1918.7343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2089.4758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.9034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1093.2133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(938.5353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1092.6273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.6617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.7787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.1636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.4663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.2614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.8285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.1628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.4150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.4908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.5460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.3508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.0475, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3464566929133858, 'recall': 0.6929133858267716, 'f1': 0.4619422572178478, 'number': 254}, 'P': {'precision': 0.5230769230769231, 'recall': 0.2328767123287671, 'f1': 0.32227488151658773, 'number': 292}, 'overall_precision': 0.3824451410658307, 'overall_recall': 0.4468864468864469, 'overall_f1': 0.4121621621621622, 'overall_accuracy': 0.6564309764309765}
			------------EPOCH 15---------------
Loss:  tensor(126.1772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.1384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.5576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.5335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.3983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.4265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.9539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(496.1260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.8054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.3035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.3253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(798.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.5157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1120.2966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.9430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(412.5305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.4014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(586.7799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.1503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.4104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.3743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(692.0476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(863.1437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.5298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.9380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.7229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.8868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.1150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.8034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.2101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.6240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.9827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.3227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.3482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.2565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.9904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.9322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.6235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.8299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.7190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.2319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.7025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.7595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.0399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.8887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.0667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.7296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.4935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.5193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.3585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.3301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.9363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.5439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.3225, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.475, 'recall': 0.44881889763779526, 'f1': 0.4615384615384615, 'number': 254}, 'P': {'precision': 0.48507462686567165, 'recall': 0.6678082191780822, 'f1': 0.5619596541786743, 'number': 292}, 'overall_precision': 0.48130841121495327, 'overall_recall': 0.5659340659340659, 'overall_f1': 0.5202020202020202, 'overall_accuracy': 0.7177104377104377}
			------------EPOCH 16---------------
Loss:  tensor(379.5713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.5993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(710.3564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.4368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.9926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.1365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.6574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.3285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.0172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.0421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.4202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.5747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.7418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.6667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.7997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.8937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.3221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.7677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.0686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.4416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.8201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.5748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.2841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.6557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.3078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.5818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.8085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.4311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.4415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.0741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.0867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.7382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.0840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.2025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.3113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.0717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.5677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.5581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.2371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.9536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.2712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.1667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.3502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.4360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.9707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.4177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.2166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.1008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.4227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.2430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.4435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.6589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.8954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.5552, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3935483870967742, 'recall': 0.48031496062992124, 'f1': 0.43262411347517726, 'number': 254}, 'P': {'precision': 0.5171232876712328, 'recall': 0.5171232876712328, 'f1': 0.5171232876712328, 'number': 292}, 'overall_precision': 0.45348837209302323, 'overall_recall': 0.5, 'overall_f1': 0.475609756097561, 'overall_accuracy': 0.6903703703703704}
			------------EPOCH 17---------------
Loss:  tensor(59.3127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.7716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.2565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.4855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.4357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.9542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.7826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.1980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.5848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.5864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.3640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.3079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.2839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.9381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.0983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.4955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.2542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.9400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.8828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.9600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.3022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.0478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.0961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.3287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.2592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.7368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.6560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.0283, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.48344370860927155, 'recall': 0.5748031496062992, 'f1': 0.525179856115108, 'number': 254}, 'P': {'precision': 0.5516129032258065, 'recall': 0.5856164383561644, 'f1': 0.5681063122923589, 'number': 292}, 'overall_precision': 0.5179738562091504, 'overall_recall': 0.5805860805860806, 'overall_f1': 0.5474956822107082, 'overall_accuracy': 0.718047138047138}
			------------EPOCH 18---------------
Loss:  tensor(43.3271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.8894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.8369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.4340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.1791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.4160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.7868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.2220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.7635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.3766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.7341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.5626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.9880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.7045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.2588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.1040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.6564, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.46511627906976744, 'recall': 0.5511811023622047, 'f1': 0.5045045045045045, 'number': 254}, 'P': {'precision': 0.54, 'recall': 0.5547945205479452, 'f1': 0.5472972972972973, 'number': 292}, 'overall_precision': 0.502495840266223, 'overall_recall': 0.5531135531135531, 'overall_f1': 0.5265911072362686, 'overall_accuracy': 0.7177104377104377}
			------------EPOCH 19---------------
Loss:  tensor(26.3262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.7365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.6614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.6897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.8033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.3087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.3797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.9546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.2843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.7834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.2929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.0474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2558, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4897959183673469, 'recall': 0.5669291338582677, 'f1': 0.5255474452554745, 'number': 254}, 'P': {'precision': 0.5394736842105263, 'recall': 0.5616438356164384, 'f1': 0.5503355704697986, 'number': 292}, 'overall_precision': 0.5150501672240803, 'overall_recall': 0.5641025641025641, 'overall_f1': 0.5384615384615385, 'overall_accuracy': 0.7185185185185186}
			------------EPOCH 20---------------
Loss:  tensor(22.9455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.3116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.8866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.3715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2005, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.47157190635451507, 'recall': 0.5551181102362205, 'f1': 0.5099457504520796, 'number': 254}, 'P': {'precision': 0.5397350993377483, 'recall': 0.5582191780821918, 'f1': 0.5488215488215489, 'number': 292}, 'overall_precision': 0.5058236272878536, 'overall_recall': 0.5567765567765568, 'overall_f1': 0.5300784655623365, 'overall_accuracy': 0.7185185185185186}
			------------EPOCH 21---------------
Loss:  tensor(19.9048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.5694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.2454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.8079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.6823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.9913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.7237, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.46229508196721314, 'recall': 0.5551181102362205, 'f1': 0.5044722719141325, 'number': 254}, 'P': {'precision': 0.531986531986532, 'recall': 0.541095890410959, 'f1': 0.5365025466893039, 'number': 292}, 'overall_precision': 0.49667774086378735, 'overall_recall': 0.5476190476190477, 'overall_f1': 0.5209059233449477, 'overall_accuracy': 0.7156902356902357}
			------------EPOCH 22---------------
Loss:  tensor(18.2483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.7721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.7994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.2083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1251, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.45806451612903226, 'recall': 0.5590551181102362, 'f1': 0.5035460992907801, 'number': 254}, 'P': {'precision': 0.5395189003436426, 'recall': 0.5376712328767124, 'f1': 0.5385934819897084, 'number': 292}, 'overall_precision': 0.49750415973377704, 'overall_recall': 0.5476190476190477, 'overall_f1': 0.5213600697471665, 'overall_accuracy': 0.7191245791245792}
			------------EPOCH 23---------------
Loss:  tensor(16.8127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.2322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.3096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.0464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4172, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4565916398713826, 'recall': 0.5590551181102362, 'f1': 0.5026548672566372, 'number': 254}, 'P': {'precision': 0.5344827586206896, 'recall': 0.5308219178082192, 'f1': 0.5326460481099656, 'number': 292}, 'overall_precision': 0.49417637271214643, 'overall_recall': 0.5439560439560439, 'overall_f1': 0.5178727114210986, 'overall_accuracy': 0.7197979797979798}
			------------EPOCH 24---------------
Loss:  tensor(15.6557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.6819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.3471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.2651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9212, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4536741214057508, 'recall': 0.5590551181102362, 'f1': 0.5008818342151675, 'number': 254}, 'P': {'precision': 0.5344827586206896, 'recall': 0.5308219178082192, 'f1': 0.5326460481099656, 'number': 292}, 'overall_precision': 0.4925373134328358, 'overall_recall': 0.5439560439560439, 'overall_f1': 0.5169712793733681, 'overall_accuracy': 0.7191245791245792}
			------------EPOCH 25---------------
Loss:  tensor(14.8089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.3036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.1791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3295, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4536741214057508, 'recall': 0.5590551181102362, 'f1': 0.5008818342151675, 'number': 254}, 'P': {'precision': 0.5379310344827586, 'recall': 0.5342465753424658, 'f1': 0.5360824742268041, 'number': 292}, 'overall_precision': 0.494195688225539, 'overall_recall': 0.5457875457875457, 'overall_f1': 0.5187119234116623, 'overall_accuracy': 0.7194612794612795}
	Train size: 50 Test size: 50


		-------------RUN 1-----------
			------------EPOCH 1---------------
Loss:  tensor(2054.5264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2605.6228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1530.2118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2868.6125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3657.2385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3168.1155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2426.2065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2264.4551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3324.8896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2296.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2988.9268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1856.9265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1640.9009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1635.4227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2091.1260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2236.9375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1296.6460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2076.9197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1587.5548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2266.8391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1572.5706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2129.2427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1558.1152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2540.1995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2428.5647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1663.0693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1125.9064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2161.2024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1219.6868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1244.1719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1090.4885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1176.9879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1157.4922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1858.1455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2311.5049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2457.4958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2247.3547, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.008361204013377926, 'recall': 0.006443298969072165, 'f1': 0.007278020378457059, 'number': 776}, 'P': {'precision': 0.036818851251840944, 'recall': 0.057208237986270026, 'f1': 0.04480286738351255, 'number': 874}, 'overall_precision': 0.028118609406952964, 'overall_recall': 0.03333333333333333, 'overall_f1': 0.030504714364947307, 'overall_accuracy': 0.48324324324324325}
			------------EPOCH 2---------------
Loss:  tensor(1399.1001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1778.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(977.4614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1846.9927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2609.0200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2005.6052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1652.4421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1567.3691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2398.8203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1568.3348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2248.6787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1296.2998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1187.1558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1273.0396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1664.0791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1706.9064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(972.7714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1546.6270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1128.2256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1793.9995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1186.9136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1607.1515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1191.8105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2069.5493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2014.9409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1494.5314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(972.1206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1999.6445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(943.5804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1037.9104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(923.2682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(995.5961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(921.1956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1502.2112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2049.2646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2202.0630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1921.8978, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.03890784982935153, 'recall': 0.07345360824742268, 'f1': 0.05087014725568942, 'number': 776}, 'P': {'precision': 0.12318840579710146, 'recall': 0.17505720823798626, 'f1': 0.14461247637051042, 'number': 874}, 'overall_precision': 0.07757665312153676, 'overall_recall': 0.12727272727272726, 'overall_f1': 0.09639660316731696, 'overall_accuracy': 0.581990171990172}
			------------EPOCH 3---------------
Loss:  tensor(1190.4032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1507.9045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.1016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1493.3845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2193.4226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1610.8938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1363.3203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1298.8665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1894.0958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1196.9336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1952.4004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1063.1552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(961.5891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1118.2083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1468.8632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1478.2880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(843.1592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1283.5149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(916.4863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1493.2676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(988.4575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1365.7145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.8616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1957.6141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1769.4546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1248.8359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(821.7513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1765.3975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.3362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(800.3590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(837.0919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.6813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1243.3525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1701.7141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1870.4972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1625.6387, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0775473399458972, 'recall': 0.11082474226804123, 'f1': 0.09124668435013263, 'number': 776}, 'P': {'precision': 0.29102564102564105, 'recall': 0.2597254004576659, 'f1': 0.2744860943168077, 'number': 874}, 'overall_precision': 0.1656961355214399, 'overall_recall': 0.1896969696969697, 'overall_f1': 0.17688612602430065, 'overall_accuracy': 0.5883292383292383}
			------------EPOCH 4---------------
Loss:  tensor(1149.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1375.4343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(864.5236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1251.3899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1790.7220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1195.8623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1058.7953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.9377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1529.3416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.1122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1624.8569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(857.4481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.4054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(980.8535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1312.7493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1275.6846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.0685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1111.3494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(814.8379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1240.5859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(795.6758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1096.7263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.4331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1825.5876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1439.1956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(811.0731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.3730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1243.7468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(720.2710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(590.1332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(665.8713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.9801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.5466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(901.8668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1375.3208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1607.8667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1399.6450, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2106552357624005, 'recall': 0.44329896907216493, 'f1': 0.2855956828559568, 'number': 776}, 'P': {'precision': 0.3232758620689655, 'recall': 0.2574370709382151, 'f1': 0.28662420382165604, 'number': 874}, 'overall_precision': 0.24431086303134392, 'overall_recall': 0.34484848484848485, 'overall_f1': 0.286001507916562, 'overall_accuracy': 0.6125798525798526}
			------------EPOCH 5---------------
Loss:  tensor(989.3809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1165.0698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(665.1518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1091.5575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1524.6311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(945.2161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(877.6024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(951.4650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1585.0139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1063.3918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1791.5688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(838.4788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(748.4091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(788.2374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1105.7036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1041.3169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.1906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(919.6610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.0474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(953.5931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.6808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(824.5848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(779.0244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1675.6130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1329.1494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.1182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.8533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1091.5664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(740.6482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(498.4598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.7013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(566.6588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.7772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(670.5217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1286.4764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1556.4851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1335.8192, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28317836010143704, 'recall': 0.43170103092783507, 'f1': 0.34201123021949975, 'number': 776}, 'P': {'precision': 0.3695450324976787, 'recall': 0.45537757437070936, 'f1': 0.4079958995386981, 'number': 874}, 'overall_precision': 0.32433628318584073, 'overall_recall': 0.4442424242424242, 'overall_f1': 0.3749360613810742, 'overall_accuracy': 0.635036855036855}
			------------EPOCH 6---------------
Loss:  tensor(1201.1038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1345.5977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.2893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1195.6316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1574.1857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(834.8464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(835.8473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.7982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1380.9404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.8519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1339.3708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.8457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(757.3596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(760.1336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.6956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1007.4839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(876.6282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1357.6969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1071.8179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1791.8647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1108.5895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1372.7827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.7485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1751.3375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1141.8970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.4652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.1586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1113.6594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.9982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.5592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.7294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.4211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.6564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.3107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.8168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1124.7930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.4763, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23459715639810427, 'recall': 0.2551546391752577, 'f1': 0.24444444444444444, 'number': 776}, 'P': {'precision': 0.31091877496671105, 'recall': 0.534324942791762, 'f1': 0.39309764309764306, 'number': 874}, 'overall_precision': 0.283461210571185, 'overall_recall': 0.403030303030303, 'overall_f1': 0.3328328328328329, 'overall_accuracy': 0.5908599508599509}
			------------EPOCH 7---------------
Loss:  tensor(1283.7784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1409.1868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.1494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1042.9763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2041.4176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(928.0439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1039.9490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1359.8657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2313.9692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1062.3199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1509.9731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(744.1056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.9004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(917.3943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1274.3829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(987.5562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.2590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1004.7921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.5950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1095.4427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(670.3064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(987.1553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(710.4908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1595.8711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1171.9266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(533.2185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.4976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(919.6647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.8529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.5946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.5621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(474.3880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.2031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.3471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(876.9314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1130.1787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1140.9861, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2528473804100228, 'recall': 0.2860824742268041, 'f1': 0.26844014510278114, 'number': 776}, 'P': {'precision': 0.4476650563607085, 'recall': 0.6361556064073226, 'f1': 0.5255198487712665, 'number': 874}, 'overall_precision': 0.36698113207547167, 'overall_recall': 0.4715151515151515, 'overall_f1': 0.41273209549071616, 'overall_accuracy': 0.6583292383292383}
			------------EPOCH 8---------------
Loss:  tensor(876.3372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1101.5297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.5487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.9395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1151.5847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(699.3816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.4690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.6781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1154.6411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.0256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1190.1613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.9700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.3220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.0382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1059.3988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(909.2462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(498.1921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.3798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.9935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(718.3589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.7819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(666.8751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.9081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1261.5165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(855.0143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.9843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.3497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.8558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.5262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.7151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.9569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.5285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.2511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.7152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.0676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(859.5181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.6752, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.37112403100775193, 'recall': 0.49355670103092786, 'f1': 0.42367256637168144, 'number': 776}, 'P': {'precision': 0.5014577259475219, 'recall': 0.5903890160183066, 'f1': 0.5423016290068313, 'number': 874}, 'overall_precision': 0.43619602134885976, 'overall_recall': 0.5448484848484848, 'overall_f1': 0.4845055241174886, 'overall_accuracy': 0.6763636363636364}
			------------EPOCH 9---------------
Loss:  tensor(778.8685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.0449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.1794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(468.4978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.2623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.3658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.8431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(676.7275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1068.8699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.8201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(965.9471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.5132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.7941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(533.6493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(942.0126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(700.1222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.8910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.0226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.0670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.9777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.7144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.7637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.9437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.9153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.7181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.7863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.9886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.7816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.2962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.8370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.9403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.6953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(468.9115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(549.0133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(666.3726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.3025, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3169181890389198, 'recall': 0.5141752577319587, 'f1': 0.3921375921375921, 'number': 776}, 'P': {'precision': 0.5076923076923077, 'recall': 0.49084668192219677, 'f1': 0.4991273996509598, 'number': 874}, 'overall_precision': 0.3935361216730038, 'overall_recall': 0.5018181818181818, 'overall_f1': 0.44112946190729885, 'overall_accuracy': 0.6723095823095823}
			------------EPOCH 10---------------
Loss:  tensor(569.7633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(713.5714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.2508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.2185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(673.6057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.2628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.0676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.4319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.6931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.0163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.8891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.3328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.0862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.9562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(778.2936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.4992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.7496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.9900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.7174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(443.0266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.0185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.0989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.3672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1062.2568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.8943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.3328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.4120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.5311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.0117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.3369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.2298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.0055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.5549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.2211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.3817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.9158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.0225, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30471271788250487, 'recall': 0.6082474226804123, 'f1': 0.40602150537634407, 'number': 776}, 'P': {'precision': 0.46122448979591835, 'recall': 0.2585812356979405, 'f1': 0.3313782991202346, 'number': 874}, 'overall_precision': 0.3423246689553703, 'overall_recall': 0.42303030303030303, 'overall_f1': 0.3784223366766061, 'overall_accuracy': 0.6265356265356266}
			------------EPOCH 11---------------
Loss:  tensor(434.1275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(601.2054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.7632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.4450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.7271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.8236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.7756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.4021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.3126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.9753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.9001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.2222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.6104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.6769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.1886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(483.6270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.7989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.8046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.3616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.5080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.5787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.2540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.7497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.4427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(684.8456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.7697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.3944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.9705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.6987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.7963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.4778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.4146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.3732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.9590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(504.3650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.1377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.3979, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.36867862969004894, 'recall': 0.5824742268041238, 'f1': 0.4515484515484515, 'number': 776}, 'P': {'precision': 0.5260303687635575, 'recall': 0.5549199084668193, 'f1': 0.5400890868596881, 'number': 874}, 'overall_precision': 0.436219739292365, 'overall_recall': 0.5678787878787879, 'overall_f1': 0.4934175882043181, 'overall_accuracy': 0.6844226044226044}
			------------EPOCH 12---------------
Loss:  tensor(453.9242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.1066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.8792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.0148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(498.8088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.2032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.1634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.3022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.6128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.4049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(886.2802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.9265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.7623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.7762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(644.1063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(643.6162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.8083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.6647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(587.4011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(603.4716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.6784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.2874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.3959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.9022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.3055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.4210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.9947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.5219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.6917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.6256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.3447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.1720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.4120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.9253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.0177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1068.6351, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2572463768115942, 'recall': 0.09149484536082474, 'f1': 0.13498098859315588, 'number': 776}, 'P': {'precision': 0.4864864864864865, 'recall': 0.782608695652174, 'f1': 0.6000000000000001, 'number': 874}, 'overall_precision': 0.44887039239001186, 'overall_recall': 0.4575757575757576, 'overall_f1': 0.4531812725090036, 'overall_accuracy': 0.6486240786240787}
			------------EPOCH 13---------------
Loss:  tensor(969.6226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1025.7812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.8121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.3816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1056.3613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.0628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.4570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.3868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(504.9529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.7949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.4962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.1024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.8083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.9348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.4633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.0325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.8237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.4856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.0527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.2227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.4651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.9909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.0351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(755.6346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.3828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.9355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.4868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.7075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.3845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.0477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.0251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.4296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.2418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.9411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(461.9629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(848.3565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.9186, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3680297397769517, 'recall': 0.6378865979381443, 'f1': 0.4667609618104668, 'number': 776}, 'P': {'precision': 0.5802631578947368, 'recall': 0.5045766590389016, 'f1': 0.5397796817625459, 'number': 874}, 'overall_precision': 0.44465558194774346, 'overall_recall': 0.5672727272727273, 'overall_f1': 0.4985352862849534, 'overall_accuracy': 0.6947665847665848}
			------------EPOCH 14---------------
Loss:  tensor(230.6995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.3451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.4790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.3091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.1179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.5118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.0242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.4763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.9345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.6118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.7136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.4484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.4381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.9342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.5366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.2098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.5758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.2001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.4422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.9982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.2933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.0608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.0489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.4962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.5968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.2062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.2910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.6384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.4122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.1331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.5086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.5252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.1211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.0871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.4824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.5466, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.36376210235131395, 'recall': 0.3389175257731959, 'f1': 0.3509006004002669, 'number': 776}, 'P': {'precision': 0.5324232081911263, 'recall': 0.7139588100686499, 'f1': 0.6099706744868035, 'number': 874}, 'overall_precision': 0.46807387862796834, 'overall_recall': 0.5375757575757576, 'overall_f1': 0.500423131170663, 'overall_accuracy': 0.7085503685503686}
			------------EPOCH 15---------------
Loss:  tensor(125.9123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.0140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.1469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.7795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.2893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.8081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.1042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.6936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.0794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.5395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.0692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.5934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.7716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.1300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.2971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.7663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.6481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.5257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.0422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.0897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.4557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.9115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.7399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.2422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.5105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.1233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.4882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.3921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.4633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.8446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.2237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.6238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.4171, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.40522875816993464, 'recall': 0.5592783505154639, 'f1': 0.4699512723335138, 'number': 776}, 'P': {'precision': 0.5675392670157068, 'recall': 0.620137299771167, 'f1': 0.5926735921268453, 'number': 874}, 'overall_precision': 0.4817374136229023, 'overall_recall': 0.5915151515151515, 'overall_f1': 0.5310119695321002, 'overall_accuracy': 0.7101719901719902}
			------------EPOCH 16---------------
Loss:  tensor(77.0406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.4723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.5058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.9467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.4911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.6603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.1767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.7657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.2351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.7838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.3213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.4493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.5653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.4189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.5624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.8564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.3082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.0219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.9093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.6888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.9622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.4186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.3200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.4587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.9936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.9400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0200, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.40344827586206894, 'recall': 0.452319587628866, 'f1': 0.4264884568651276, 'number': 776}, 'P': {'precision': 0.5366931918656057, 'recall': 0.6945080091533181, 'f1': 0.6054862842892769, 'number': 874}, 'overall_precision': 0.47876061969015493, 'overall_recall': 0.5806060606060606, 'overall_f1': 0.5247877293892084, 'overall_accuracy': 0.7130958230958231}
			------------EPOCH 17---------------
Loss:  tensor(55.2315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.5839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.9358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.3406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.1792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.8285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.7393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.4802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.1852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.9681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.8491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.0842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.4991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.2642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.3396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.1281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.7632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.4610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.1183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.5847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.9028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.9930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1998, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.41830065359477125, 'recall': 0.4948453608247423, 'f1': 0.45336481700118064, 'number': 776}, 'P': {'precision': 0.5571428571428572, 'recall': 0.6693363844393593, 'f1': 0.6081081081081082, 'number': 874}, 'overall_precision': 0.4923780487804878, 'overall_recall': 0.5872727272727273, 'overall_f1': 0.5356550580431179, 'overall_accuracy': 0.7171007371007371}
			------------EPOCH 18---------------
Loss:  tensor(39.7818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.9406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.6693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.8110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.7974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.1421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.2916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.9631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.6638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.9247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.7785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.4313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.4365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.8042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.6337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.1633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.9860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.7470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.9342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9508, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4340425531914894, 'recall': 0.5257731958762887, 'f1': 0.4755244755244755, 'number': 776}, 'P': {'precision': 0.5533790401567091, 'recall': 0.6464530892448512, 'f1': 0.5963060686015831, 'number': 874}, 'overall_precision': 0.4961754207037226, 'overall_recall': 0.5896969696969697, 'overall_f1': 0.5389088895042924, 'overall_accuracy': 0.7214742014742015}
			------------EPOCH 19---------------
Loss:  tensor(36.5975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.9123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.6433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.0387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.0966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.0264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.1457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.0528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.0514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.5779, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.45120551090700345, 'recall': 0.5064432989690721, 'f1': 0.4772313296903461, 'number': 776}, 'P': {'precision': 0.5408921933085502, 'recall': 0.665903890160183, 'f1': 0.596923076923077, 'number': 874}, 'overall_precision': 0.5007704160246533, 'overall_recall': 0.5909090909090909, 'overall_f1': 0.5421184320266889, 'overall_accuracy': 0.7231449631449631}
			------------EPOCH 20---------------
Loss:  tensor(36.3405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.9809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.6607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.7860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.3187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.8754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.7409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.9131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.2150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.8574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5038, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4407744874715262, 'recall': 0.49871134020618557, 'f1': 0.467956469165659, 'number': 776}, 'P': {'precision': 0.5297450424929179, 'recall': 0.6418764302059496, 'f1': 0.5804449042938438, 'number': 874}, 'overall_precision': 0.4894166236448116, 'overall_recall': 0.5745454545454546, 'overall_f1': 0.5285754112071369, 'overall_accuracy': 0.7226044226044226}
			------------EPOCH 21---------------
Loss:  tensor(30.3801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.1734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.1124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.8851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.3671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.1180, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4379977246871445, 'recall': 0.4961340206185567, 'f1': 0.4652567975830816, 'number': 776}, 'P': {'precision': 0.5357142857142857, 'recall': 0.6350114416475973, 'f1': 0.581151832460733, 'number': 874}, 'overall_precision': 0.4908616187989556, 'overall_recall': 0.5696969696969697, 'overall_f1': 0.5273492286115008, 'overall_accuracy': 0.7216953316953317}
			------------EPOCH 22---------------
Loss:  tensor(23.4111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.2833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.8737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.5517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.1760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2931, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4406392694063927, 'recall': 0.49742268041237114, 'f1': 0.46731234866828086, 'number': 776}, 'P': {'precision': 0.5386819484240688, 'recall': 0.6453089244851259, 'f1': 0.5871941697032795, 'number': 874}, 'overall_precision': 0.49401976079043164, 'overall_recall': 0.5757575757575758, 'overall_f1': 0.531766022949902, 'overall_accuracy': 0.7208108108108108}
			------------EPOCH 23---------------
Loss:  tensor(19.1584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.7095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.8296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.8397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3256, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.44329896907216493, 'recall': 0.49871134020618557, 'f1': 0.4693753790175864, 'number': 776}, 'P': {'precision': 0.5402521823472357, 'recall': 0.6372997711670481, 'f1': 0.5847769028871391, 'number': 874}, 'overall_precision': 0.4957983193277311, 'overall_recall': 0.5721212121212121, 'overall_f1': 0.5312324141812043, 'overall_accuracy': 0.7212285012285012}
			------------EPOCH 24---------------
Loss:  tensor(16.2447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.2696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.2274, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.43958573072497126, 'recall': 0.49226804123711343, 'f1': 0.4644376899696049, 'number': 776}, 'P': {'precision': 0.5425531914893617, 'recall': 0.6418764302059496, 'f1': 0.5880503144654087, 'number': 874}, 'overall_precision': 0.4955333683657383, 'overall_recall': 0.5715151515151515, 'overall_f1': 0.5308190261750633, 'overall_accuracy': 0.7193120393120394}
			------------EPOCH 25---------------
Loss:  tensor(14.4870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1740, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4391891891891892, 'recall': 0.5025773195876289, 'f1': 0.46874999999999994, 'number': 776}, 'P': {'precision': 0.5458984375, 'recall': 0.6395881006864989, 'f1': 0.5890410958904109, 'number': 874}, 'overall_precision': 0.4963389121338912, 'overall_recall': 0.5751515151515152, 'overall_f1': 0.5328467153284671, 'overall_accuracy': 0.7186732186732187}


		-------------RUN 2-----------
			------------EPOCH 1---------------
Loss:  tensor(2108.7402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1515.7219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3095.3442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1721.4688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1642.2439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3281.0642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2869.3318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(829.2974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1348.2535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2053.7881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3471.4160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2105.9106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1770.2638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1677.7264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1804.9901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1588.2568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1928.1141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1472.5034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1433.0430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1134.7290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1260.4180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(937.7478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1576.6851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2080.0518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1960.3199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1180.5256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2083.4661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1746.8911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1412.6558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1444.5922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2791.0391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1203.9443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2255.3459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1975.8759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2855.0242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3624.7793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2746.4087, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.010615711252653927, 'recall': 0.01288659793814433, 'f1': 0.011641443538998835, 'number': 776}, 'P': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1018}, 'overall_precision': 0.01023541453428864, 'overall_recall': 0.005574136008918618, 'overall_f1': 0.0072176109707686766, 'overall_accuracy': 0.32727727500113696}
			------------EPOCH 2---------------
Loss:  tensor(1353.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.6074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2125.8564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1269.7809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1272.7013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2438.4749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2155.3252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.2880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1090.1788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1708.7911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2767.2419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1709.6586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1501.1559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1420.9839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1494.9900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1326.1484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1624.4807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1241.8969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1159.2932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(931.2815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.5210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(801.5886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1341.5356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1714.7694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1594.4536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.0277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1822.5327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1441.9207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1232.5364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1181.2114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2232.0386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(963.2453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1840.5948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1552.2640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2285.7192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3137.6887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2270.9441, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1990604815032296, 'recall': 0.4368556701030928, 'f1': 0.2734973779749899, 'number': 776}, 'P': {'precision': 0.15538847117794485, 'recall': 0.060903732809430254, 'f1': 0.08750882145377557, 'number': 1018}, 'overall_precision': 0.1907706945765937, 'overall_recall': 0.22352285395763657, 'overall_f1': 0.20585215605749488, 'overall_accuracy': 0.43053344854245307}
			------------EPOCH 3---------------
Loss:  tensor(1093.3708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(855.6887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1762.9456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1095.0950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.0584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2001.3613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1757.3550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.3315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(901.4658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1465.1251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2141.4392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1561.3198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1294.2991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1238.5636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1186.2462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1013.0134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1415.5540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1108.7310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(949.9567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(786.1904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(904.8781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.0225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1166.2048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1425.3290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1205.4646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.3384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1534.6326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1127.8904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.6567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(961.3816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1756.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.4104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1561.1530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1301.4153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1832.3508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2743.3770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1962.8103, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24342105263157895, 'recall': 0.38144329896907214, 'f1': 0.2971887550200803, 'number': 776}, 'P': {'precision': 0.21266233766233766, 'recall': 0.25736738703339884, 'f1': 0.2328888888888889, 'number': 1018}, 'overall_precision': 0.22794117647058823, 'overall_recall': 0.3110367892976589, 'overall_f1': 0.2630834512022631, 'overall_accuracy': 0.5954795579607985}
			------------EPOCH 4---------------
Loss:  tensor(889.8718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.9338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1563.0438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(985.1077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.1838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1540.4993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1452.0542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.8660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.5789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.8401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1639.3406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(925.0632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(722.4749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.7455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(953.2975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.1865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1163.7848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(909.8101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.2062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(583.4442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.9716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.6858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1007.8851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.3237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1000.1211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(702.0621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1248.7775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(893.6525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(835.9202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.1248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1430.3201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.4567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1236.1481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.1497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1400.8429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2263.0254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1470.9098, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26841659610499574, 'recall': 0.40850515463917525, 'f1': 0.3239652529381707, 'number': 776}, 'P': {'precision': 0.38733705772811916, 'recall': 0.4086444007858546, 'f1': 0.3977055449330784, 'number': 1018}, 'overall_precision': 0.32505543237250556, 'overall_recall': 0.40858416945373466, 'overall_f1': 0.3620647073351445, 'overall_accuracy': 0.6232207012597207}
			------------EPOCH 5---------------
Loss:  tensor(609.5052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.3503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1265.0640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.1608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(624.9597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1115.9697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1218.9044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.1031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.7128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(958.4279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1428.3112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.9132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.9370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.3051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.2882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.1075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(877.9047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(662.0626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.0512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.5169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(468.6323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.1298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(825.1691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.6138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(858.9334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.7695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1268.0735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(823.5896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.4299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.1645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1179.0981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.7193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(962.5849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(880.2737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1086.4534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1776.2979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1203.2084, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.356, 'recall': 0.3440721649484536, 'f1': 0.34993446920052423, 'number': 776}, 'P': {'precision': 0.3406113537117904, 'recall': 0.5363457760314342, 'f1': 0.41663487218618844, 'number': 1018}, 'overall_precision': 0.3455163620909477, 'overall_recall': 0.4531772575250836, 'overall_f1': 0.3920906679527369, 'overall_accuracy': 0.6499840829505662}
			------------EPOCH 6---------------
Loss:  tensor(455.8215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.5457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1108.1306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.0906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.1086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(969.3155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1103.6582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.9301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(587.6061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(928.1046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1469.2805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.1075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.9486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(863.9866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.7464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.2592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.9768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(481.5161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.4178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.9341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.0577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(893.8545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.9498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.4172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.3517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(932.8352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(641.1759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(702.1626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(627.9761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1456.1965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.9844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1138.7494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(797.8113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1671.3005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3522.6821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(875.5560, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.44153846153846155, 'recall': 0.3698453608247423, 'f1': 0.40252454417952316, 'number': 776}, 'P': {'precision': 0.43861977438619776, 'recall': 0.6493123772102161, 'f1': 0.5235643564356436, 'number': 1018}, 'overall_precision': 0.43949930458970793, 'overall_recall': 0.5284280936454849, 'overall_f1': 0.4798785117691724, 'overall_accuracy': 0.6792487152667243}
			------------EPOCH 7---------------
Loss:  tensor(321.8746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.9428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(813.0496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.9527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.0297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.2150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.1407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.1682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(688.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(900.5989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1260.0717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(635.7047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.7671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.2210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.6929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.0731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.0247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(645.5721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.1244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(485.5959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.9349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.8165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1296.0618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.5668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(846.3049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(841.5054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1478.1685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(684.6919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(740.3876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.4211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1326.1404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.5810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(838.2003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(916.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1172.0806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1714.5468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(699.4831, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4174107142857143, 'recall': 0.48195876288659795, 'f1': 0.44736842105263164, 'number': 776}, 'P': {'precision': 0.5133437990580848, 'recall': 0.6424361493123772, 'f1': 0.5706806282722513, 'number': 1018}, 'overall_precision': 0.4737327188940092, 'overall_recall': 0.5730211817168339, 'overall_f1': 0.5186680121089808, 'overall_accuracy': 0.6916412751830461}
			------------EPOCH 8---------------
Loss:  tensor(282.0584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.6509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(729.1202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.8513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.2457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.7802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(744.5265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.6154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.9406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(769.8926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.4900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.0625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.2206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.4832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(729.5753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.7215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1098.1128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.4435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.1233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(474.2236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.7338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.6546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1230.1436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.6664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(791.9171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(652.7794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1356.6541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(914.7941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.8444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.6842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(925.0579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.0302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.0674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.4780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1363.2687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.0726, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3157894736842105, 'recall': 0.7190721649484536, 'f1': 0.4388517499016909, 'number': 776}, 'P': {'precision': 0.5361702127659574, 'recall': 0.1237721021611002, 'f1': 0.20111731843575417, 'number': 1018}, 'overall_precision': 0.34165834165834164, 'overall_recall': 0.38127090301003347, 'overall_f1': 0.3603793466807166, 'overall_accuracy': 0.5233298467415526}
			------------EPOCH 9---------------
Loss:  tensor(365.3763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.7263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1086.2488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.3408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(826.1069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1119.1433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1372.0764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.1837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(539.0267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.0833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1105.1931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.5864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.3001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.2169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(616.9412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.7115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.0154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.9080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.5622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.4044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.2753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.3435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(636.4045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.2571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.4012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(484.4432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1107.6965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.7133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.4823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.0508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(889.2528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.4699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(670.1042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(739.3460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(901.6399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1593.2375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.7382, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4671814671814672, 'recall': 0.4677835051546392, 'f1': 0.46748229233741145, 'number': 776}, 'P': {'precision': 0.5683229813664596, 'recall': 0.7190569744597249, 'f1': 0.6348655680832611, 'number': 1018}, 'overall_precision': 0.5302663438256658, 'overall_recall': 0.6103678929765887, 'overall_f1': 0.567504534853589, 'overall_accuracy': 0.6959161398881258}
			------------EPOCH 10---------------
Loss:  tensor(237.8199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.6990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.5696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.5437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.3738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.9418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.0181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.2527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.9079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.6427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.3504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.6691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.6360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.8642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.6331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.3167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.3304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.4146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.6875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.0248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.9726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.3396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.4443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.2910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.8666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.6256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.9539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.9666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.5176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.5602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.4025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.0813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.5394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.4395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.7554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.1890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.6437, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.407312925170068, 'recall': 0.6172680412371134, 'f1': 0.4907786885245901, 'number': 776}, 'P': {'precision': 0.655421686746988, 'recall': 0.5343811394891945, 'f1': 0.5887445887445889, 'number': 1018}, 'overall_precision': 0.5099700897308076, 'overall_recall': 0.5702341137123745, 'overall_f1': 0.538421052631579, 'overall_accuracy': 0.6834553640456592}
			------------EPOCH 11---------------
Loss:  tensor(109.9662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.7653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.5743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.4641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.8711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.9439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.6542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.8967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.5947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.4129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.2068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.9054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.2545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.1126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.5537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.5259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.0952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.9135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.0445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.4003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.7280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.0697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.7714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.9677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.7655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.4254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.1036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.6981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.3901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(450.0319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.4955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.4157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.9377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.0669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.0922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.9012, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3753687315634218, 'recall': 0.6559278350515464, 'f1': 0.4774859287054409, 'number': 776}, 'P': {'precision': 0.6376068376068376, 'recall': 0.3664047151277014, 'f1': 0.46537741734248284, 'number': 1018}, 'overall_precision': 0.45440494590417313, 'overall_recall': 0.4916387959866221, 'overall_f1': 0.472289156626506, 'overall_accuracy': 0.6591250170539815}
			------------EPOCH 12---------------
Loss:  tensor(59.5798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.8706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.3044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.4678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.8183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.5810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.9129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.4591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.0352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.7405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.6877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.5253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.6646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.0532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.5112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.9584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.6422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.6760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.5986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.7192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.1468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.8060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.0302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.0976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.7396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.5068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.5267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.9013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.0322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.9802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.4558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.4367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.4242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.0415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.9432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.2608, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.44069529652351735, 'recall': 0.5554123711340206, 'f1': 0.49144811858608894, 'number': 776}, 'P': {'precision': 0.5901486988847584, 'recall': 0.6237721021611002, 'f1': 0.606494746895893, 'number': 1018}, 'overall_precision': 0.5189873417721519, 'overall_recall': 0.5942028985507246, 'overall_f1': 0.5540540540540541, 'overall_accuracy': 0.7110600754922916}
			------------EPOCH 13---------------
Loss:  tensor(67.6211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.8074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.5766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.9033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.5857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.4007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.5625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.4896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.3421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.5039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.6563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.6455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.7077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.0390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.0467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.8641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.5477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.6472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.9559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.8979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.7566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.1027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.2681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.5233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.8038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.3452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.0949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.1899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.2410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6210, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.46551724137931033, 'recall': 0.452319587628866, 'f1': 0.45882352941176474, 'number': 776}, 'P': {'precision': 0.5694779116465863, 'recall': 0.6964636542239686, 'f1': 0.6266018559434379, 'number': 1018}, 'overall_precision': 0.5302651325662832, 'overall_recall': 0.5908584169453734, 'overall_f1': 0.5589243343000264, 'overall_accuracy': 0.7259084087498294}
			------------EPOCH 14---------------
Loss:  tensor(20.3125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.5694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.0267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.0665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.8300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.2871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.6853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.0919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.0364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.8433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.6700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.7207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.8779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.2104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.8519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.0336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.0405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.0162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.5531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.9612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.9167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.2368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.4173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.7033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.1750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3926, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3880918220946915, 'recall': 0.6971649484536082, 'f1': 0.49861751152073736, 'number': 776}, 'P': {'precision': 0.6455906821963394, 'recall': 0.381139489194499, 'f1': 0.4793082149474984, 'number': 1018}, 'overall_precision': 0.4656641604010025, 'overall_recall': 0.5178372352285395, 'overall_f1': 0.49036685141198205, 'overall_accuracy': 0.656168993587703}
			------------EPOCH 15---------------
Loss:  tensor(26.9328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.1325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.7163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.3674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.0613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.2845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.1256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.0551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.8897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.3357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.2541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.4952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.0407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.4071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.5758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.8895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.7114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.7314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9293, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4705188679245283, 'recall': 0.5141752577319587, 'f1': 0.49137931034482757, 'number': 776}, 'P': {'precision': 0.5793163891323401, 'recall': 0.6493123772102161, 'f1': 0.6123205187586845, 'number': 1018}, 'overall_precision': 0.5329311211664153, 'overall_recall': 0.5908584169453734, 'overall_f1': 0.5604017975151995, 'overall_accuracy': 0.7156305425439993}
			------------EPOCH 16---------------
Loss:  tensor(12.5128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.8200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.8977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.0600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.6007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.6629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.1005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.3414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.4458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.5540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.8988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.6503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.7756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.2595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.3424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6263, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4547325102880658, 'recall': 0.5695876288659794, 'f1': 0.505720823798627, 'number': 776}, 'P': {'precision': 0.6050830889540567, 'recall': 0.6080550098231827, 'f1': 0.6065654091131798, 'number': 1018}, 'overall_precision': 0.5318295739348371, 'overall_recall': 0.5914158305462653, 'overall_f1': 0.5600422275006598, 'overall_accuracy': 0.712469871299286}
			------------EPOCH 17---------------
Loss:  tensor(11.0197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.3979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.1691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.3262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.7378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.2915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.4916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7316, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.44518589132507147, 'recall': 0.6018041237113402, 'f1': 0.5117808219178082, 'number': 776}, 'P': {'precision': 0.6293478260869565, 'recall': 0.568762278978389, 'f1': 0.5975232198142415, 'number': 1018}, 'overall_precision': 0.5312341289994922, 'overall_recall': 0.5830546265328874, 'overall_f1': 0.5559394100451768, 'overall_accuracy': 0.7037609713947883}
			------------EPOCH 18---------------
Loss:  tensor(8.8839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.1495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.8976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0735, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4723726977248104, 'recall': 0.5618556701030928, 'f1': 0.5132430841671571, 'number': 776}, 'P': {'precision': 0.6140684410646388, 'recall': 0.6345776031434185, 'f1': 0.6241545893719808, 'number': 1018}, 'overall_precision': 0.5478481012658228, 'overall_recall': 0.6031215161649944, 'overall_f1': 0.5741576014858053, 'overall_accuracy': 0.7170858156350902}
			------------EPOCH 19---------------
Loss:  tensor(7.6721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4703, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4722222222222222, 'recall': 0.5695876288659794, 'f1': 0.516355140186916, 'number': 776}, 'P': {'precision': 0.6159769008662175, 'recall': 0.6286836935166994, 'f1': 0.6222654350996597, 'number': 1018}, 'overall_precision': 0.5478481012658228, 'overall_recall': 0.6031215161649944, 'overall_f1': 0.5741576014858053, 'overall_accuracy': 0.7159716221747238}
			------------EPOCH 20---------------
Loss:  tensor(6.5876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.3340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5137, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4534769833496572, 'recall': 0.5966494845360825, 'f1': 0.5153032832498609, 'number': 776}, 'P': {'precision': 0.6121593291404612, 'recall': 0.5736738703339882, 'f1': 0.5922920892494928, 'number': 1018}, 'overall_precision': 0.530126582278481, 'overall_recall': 0.5836120401337793, 'overall_f1': 0.5555850358185195, 'overall_accuracy': 0.7090363363499932}
			------------EPOCH 21---------------
Loss:  tensor(16.1702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.4730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8898, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.45617529880478086, 'recall': 0.5902061855670103, 'f1': 0.5146067415730338, 'number': 776}, 'P': {'precision': 0.5865191146881288, 'recall': 0.5726915520628684, 'f1': 0.5795228628230616, 'number': 1018}, 'overall_precision': 0.521021021021021, 'overall_recall': 0.580267558528428, 'overall_f1': 0.5490506329113923, 'overall_accuracy': 0.7145845650097776}
			------------EPOCH 22---------------
Loss:  tensor(12.2882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.7992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1882, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.45699481865284974, 'recall': 0.5682989690721649, 'f1': 0.5066053991958644, 'number': 776}, 'P': {'precision': 0.6297405189620758, 'recall': 0.6198428290766208, 'f1': 0.6247524752475248, 'number': 1018}, 'overall_precision': 0.5449923741738688, 'overall_recall': 0.5975473801560758, 'overall_f1': 0.570061153948418, 'overall_accuracy': 0.7113556778389195}
			------------EPOCH 23---------------
Loss:  tensor(4.5585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.7640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.8041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6452, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4517937219730942, 'recall': 0.5193298969072165, 'f1': 0.4832134292565948, 'number': 776}, 'P': {'precision': 0.5745098039215686, 'recall': 0.5756385068762279, 'f1': 0.5750736015701667, 'number': 1018}, 'overall_precision': 0.5172594142259415, 'overall_recall': 0.5512820512820513, 'overall_f1': 0.5337290879654615, 'overall_accuracy': 0.7107872117877121}
			------------EPOCH 24---------------
Loss:  tensor(3.9614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.7164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0736, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4533898305084746, 'recall': 0.5515463917525774, 'f1': 0.4976744186046511, 'number': 776}, 'P': {'precision': 0.6158357771260997, 'recall': 0.618860510805501, 'f1': 0.6173444390004899, 'number': 1018}, 'overall_precision': 0.5378749364514489, 'overall_recall': 0.5897435897435898, 'overall_f1': 0.5626163254453603, 'overall_accuracy': 0.7132884624130247}
			------------EPOCH 25---------------
Loss:  tensor(2.5013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3369, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.44557477110885046, 'recall': 0.5644329896907216, 'f1': 0.4980102330869813, 'number': 776}, 'P': {'precision': 0.6107723577235772, 'recall': 0.5903732809430255, 'f1': 0.6003996003996005, 'number': 1018}, 'overall_precision': 0.5282155566853076, 'overall_recall': 0.5791527313266444, 'overall_f1': 0.552512629619782, 'overall_accuracy': 0.7083086998044477}


		-------------RUN 3-----------
			------------EPOCH 1---------------
Loss:  tensor(2200.8181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3073.5991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3406.7124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1413.4434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2462.6555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2526.2446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2452.3398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2159.6460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2751.5518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2166.9836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1413.9023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2844.3682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1620.6624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1288.2787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1943.8866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1317.3102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1076.8171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(915.3591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1526.5464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1079.0787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1441.0880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2123.7222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3492.2217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2660.3691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2541.8179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1785.9572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1627.3501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2201.6221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2030.5155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1504.9753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1362.4556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1274.8496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1350.1777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1903.1471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(805.9594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1776.9067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1019.5773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(776.9340, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0582010582010582, 'recall': 0.07006369426751592, 'f1': 0.06358381502890174, 'number': 628}, 'P': {'precision': 0.07975460122699386, 'recall': 0.050518134715025906, 'f1': 0.061855670103092786, 'number': 772}, 'overall_precision': 0.06666666666666667, 'overall_recall': 0.05928571428571429, 'overall_f1': 0.06275992438563328, 'overall_accuracy': 0.4813027744270205}
			------------EPOCH 2---------------
Loss:  tensor(1610.2572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2217.5430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2582.2021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1080.9402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1979.8246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2091.0620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1931.8984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1682.9943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2269.9827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1886.2762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1107.1053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2352.9824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1314.4377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1012.9547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1566.3563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1085.5679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(900.9225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(815.1520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1466.8717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(938.6074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1339.2174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1876.4448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2891.6357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2165.4924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2366.2351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1387.5782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1422.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1793.9949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1650.3300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1260.2971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1177.7507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1072.7821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1161.8217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1661.0610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.5103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1492.7545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(901.7706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.0037, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11221945137157108, 'recall': 0.07165605095541401, 'f1': 0.08746355685131196, 'number': 628}, 'P': {'precision': 0.279874213836478, 'recall': 0.34585492227979275, 'f1': 0.309385863267671, 'number': 772}, 'overall_precision': 0.23025830258302582, 'overall_recall': 0.22285714285714286, 'overall_f1': 0.226497277676951, 'overall_accuracy': 0.5904978616076324}
			------------EPOCH 3---------------
Loss:  tensor(1281.7793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1881.6721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2219.7896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(923.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1720.7585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1866.3129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1682.2101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1297.1356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1993.3218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1651.7268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.1158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1884.8418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1084.6580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(890.4147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1358.7983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(944.1079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(791.2299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(757.0852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1251.8553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(806.5552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1100.3673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1570.5007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2520.2693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1808.2562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1950.8744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1146.6145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1299.5681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1567.2744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1386.3392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1046.5306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1035.3672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(897.3351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(982.6954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1455.7124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.3336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1318.7871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(801.5894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.4219, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2144638403990025, 'recall': 0.13694267515923567, 'f1': 0.16715257531584063, 'number': 628}, 'P': {'precision': 0.398488120950324, 'recall': 0.47797927461139894, 'f1': 0.43462897526501765, 'number': 772}, 'overall_precision': 0.34287867370007535, 'overall_recall': 0.325, 'overall_f1': 0.3337000366703337, 'overall_accuracy': 0.6152538655554337}
			------------EPOCH 4---------------
Loss:  tensor(1104.6581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1588.2280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1941.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(835.5789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1612.0427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1645.9045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1445.6055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1029.2966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1682.2465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1426.0215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(769.4073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1469.1960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(871.4574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(757.9643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1125.4631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(790.3042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(654.2558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(665.6189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(901.4936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.4902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.2230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1184.0260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2226.5208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1535.9099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1621.7700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(959.9755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1196.6747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1321.6250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1077.5259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.9607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(914.6854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(781.2886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(805.5112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1222.2764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(450.1140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1053.8368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.5510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.6298, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23617021276595745, 'recall': 0.1767515923566879, 'f1': 0.20218579234972678, 'number': 628}, 'P': {'precision': 0.33530106257378983, 'recall': 0.36787564766839376, 'f1': 0.3508338480543546, 'number': 772}, 'overall_precision': 0.2999240698557327, 'overall_recall': 0.28214285714285714, 'overall_f1': 0.2907618697092381, 'overall_accuracy': 0.6068099572321527}
			------------EPOCH 5---------------
Loss:  tensor(948.2222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1251.0757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1537.3379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.7770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1569.3213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1585.5491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1302.9167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(958.9928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1410.9409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1091.3710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(652.2761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1203.2971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(700.3947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(603.6095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(931.4954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(619.0889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.3298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.9984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(643.5914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.7032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.6849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(965.6365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2085.4429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1353.4642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1720.0558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(837.6945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1224.9846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1185.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(898.9733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(787.0352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(879.8507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.8442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.1877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1079.4976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.9863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(969.8155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(627.3588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.4391, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3562005277044855, 'recall': 0.4299363057324841, 'f1': 0.38961038961038963, 'number': 628}, 'P': {'precision': 0.5148188803512623, 'recall': 0.6075129533678757, 'f1': 0.5573380867498514, 'number': 772}, 'overall_precision': 0.4427801078490114, 'overall_recall': 0.5278571428571428, 'overall_f1': 0.48159009449332024, 'overall_accuracy': 0.6669865116789122}
			------------EPOCH 6---------------
Loss:  tensor(800.1503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1010.3027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1358.5439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(634.9908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1230.1803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1235.2565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(989.0266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(692.7576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1503.4363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1089.0092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(654.8278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.5376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(668.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.6414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(925.4203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.9229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.5784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(468.7288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.4892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.5086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.9444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(863.1969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1934.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1127.8569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1072.3433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.5443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(931.9646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.2557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.8740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.6898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(745.3646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(565.3275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.2943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(959.7726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.9175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(824.9707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.5564, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3905579399141631, 'recall': 0.5796178343949044, 'f1': 0.4666666666666667, 'number': 628}, 'P': {'precision': 0.5225653206650831, 'recall': 0.5699481865284974, 'f1': 0.5452292441140024, 'number': 772}, 'overall_precision': 0.4532130777903044, 'overall_recall': 0.5742857142857143, 'overall_f1': 0.5066162570888469, 'overall_accuracy': 0.6422853383046386}
			------------EPOCH 7---------------
Loss:  tensor(834.3251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1016.7457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1670.4290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(776.4536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1627.0828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1772.2581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1214.4784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(968.4294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1262.2217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1432.4707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.1197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1076.8042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.8801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.2213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.2103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.7358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.8602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(389.3094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.0493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.9410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.1378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(590.8337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1449.0859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(805.2710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.3393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.6898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(866.5500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(848.2507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.9052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.9108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(715.9640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(646.7646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(663.7795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(950.0494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.0857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.5787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(541.2867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.2549, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4261744966442953, 'recall': 0.40445859872611467, 'f1': 0.4150326797385621, 'number': 628}, 'P': {'precision': 0.5106382978723404, 'recall': 0.6528497409326425, 'f1': 0.573052870949403, 'number': 772}, 'overall_precision': 0.47883765003158557, 'overall_recall': 0.5414285714285715, 'overall_f1': 0.508213208179685, 'overall_accuracy': 0.6810505537887926}
			------------EPOCH 8---------------
Loss:  tensor(634.6245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.2224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(910.5069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.9731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(933.8536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(915.8264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.3032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.2629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(918.6539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(739.1078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.1307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.8382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.5365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.8989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.8401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.9593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.4280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.3815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.5477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.6970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.1298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1049.9158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(560.5709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.8966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.5363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(745.0100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(568.8870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.5248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.2340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.1355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.6573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(389.4605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.3149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.4998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.2860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.8925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.1800, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4387186629526462, 'recall': 0.5015923566878981, 'f1': 0.4680534918276374, 'number': 628}, 'P': {'precision': 0.5564705882352942, 'recall': 0.6126943005181347, 'f1': 0.5832305795314426, 'number': 772}, 'overall_precision': 0.5025510204081632, 'overall_recall': 0.5628571428571428, 'overall_f1': 0.5309973045822103, 'overall_accuracy': 0.673867748656651}
			------------EPOCH 9---------------
Loss:  tensor(469.9757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.6307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.9186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.4222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(654.4969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(627.0179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.1011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.5447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.0856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.9071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.2411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.2310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.8814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.7976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.8472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.5871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.4211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.7967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.9600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.1358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.3720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1059.6830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(681.7091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.6092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.3521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.7302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.8191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.3278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.9765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(636.6473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(539.4465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.6151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(815.3712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.2143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.6510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.6514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.8870, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.44505494505494503, 'recall': 0.5159235668789809, 'f1': 0.4778761061946903, 'number': 628}, 'P': {'precision': 0.5488180883864338, 'recall': 0.6917098445595855, 'f1': 0.6120343839541548, 'number': 772}, 'overall_precision': 0.5044091710758377, 'overall_recall': 0.6128571428571429, 'overall_f1': 0.5533698806836505, 'overall_accuracy': 0.6884526812150455}
			------------EPOCH 10---------------
Loss:  tensor(355.8094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.2960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.2852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.4125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.2621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.0500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.1497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.9427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(764.7213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.0073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.0942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.4879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.0327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.6909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.5551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.9126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.1401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.8639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.4489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.0246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.0780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(572.9415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(389.4418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.1319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.7364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.5035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.3622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(474.5985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.5833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.4901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(573.2871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.0262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.9791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.1024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.0499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.7650, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.5550660792951542, 'recall': 0.20063694267515925, 'f1': 0.2947368421052632, 'number': 628}, 'P': {'precision': 0.4519774011299435, 'recall': 0.8290155440414507, 'f1': 0.5850091407678245, 'number': 772}, 'overall_precision': 0.4662203286670724, 'overall_recall': 0.5471428571428572, 'overall_f1': 0.5034505422280643, 'overall_accuracy': 0.6374054172606646}
			------------EPOCH 11---------------
Loss:  tensor(623.2377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1006.5931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(863.5294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.1602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.0388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(750.4512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.3167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.5979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.9474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(724.5132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.2408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.0308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.7776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.6564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.1132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.4563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.8207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.0827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.9236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.2794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.0860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.8045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1598.2104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.0635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1580.0846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.7399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1280.0167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1208.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.7347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(565.9514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(602.7509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.4811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.4006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.2706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.8881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.5160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.1783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.9899, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3722397476340694, 'recall': 0.18789808917197454, 'f1': 0.24973544973544975, 'number': 628}, 'P': {'precision': 0.4624889673433363, 'recall': 0.6787564766839378, 'f1': 0.5501312335958005, 'number': 772}, 'overall_precision': 0.44275862068965516, 'overall_recall': 0.4585714285714286, 'overall_f1': 0.4505263157894737, 'overall_accuracy': 0.6666301129509815}
			------------EPOCH 12---------------
Loss:  tensor(350.8620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.2371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.2068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.6767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.9047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.6892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.3953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.7372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(989.5937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.0854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.9421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.8630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.3226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.0924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(697.0341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.3875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.8474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.3755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.6231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.0574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.3569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.2402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2166.8086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1339.1570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(698.3231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.9222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(597.0507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.6490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.9880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.5559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.1560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.7796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.1551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.1179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.2502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.2773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.7087, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.38720829732065687, 'recall': 0.7133757961783439, 'f1': 0.5019607843137255, 'number': 628}, 'P': {'precision': 0.5732217573221757, 'recall': 0.3549222797927461, 'f1': 0.43839999999999996, 'number': 772}, 'overall_precision': 0.4415902140672783, 'overall_recall': 0.5157142857142857, 'overall_f1': 0.4757825370675453, 'overall_accuracy': 0.6321965127755236}
			------------EPOCH 13---------------
Loss:  tensor(575.3820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.1304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.6693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.8099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.8699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.1344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.5816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.5312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(887.6388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.8641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.2570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.4810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.2742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.6581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.0235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.2760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.7023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.7365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.3651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.9454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.5102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.9905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.0834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.0150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.5431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.7357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.5864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.1628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.9879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.5734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.8556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.9666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.9589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.0698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.7349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.6634, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4718934911242604, 'recall': 0.5079617834394905, 'f1': 0.48926380368098166, 'number': 628}, 'P': {'precision': 0.539568345323741, 'recall': 0.6800518134715026, 'f1': 0.6017191977077363, 'number': 772}, 'overall_precision': 0.5118253486961795, 'overall_recall': 0.6028571428571429, 'overall_f1': 0.5536241390619876, 'overall_accuracy': 0.705504989582191}
			------------EPOCH 14---------------
Loss:  tensor(225.5863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.1147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.9540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.2850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.3268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.0071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.6066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.2635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.9187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.4322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.6800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.2430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.0442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.1125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.0547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.9143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.6873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.5901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.9149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.9844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.7887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(583.9704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.3260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.7240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.9250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.9372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.4136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.9267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.4676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.3641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.3126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.3949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.2883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.3379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.4340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.6189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.3760, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.47761194029850745, 'recall': 0.5605095541401274, 'f1': 0.5157509157509157, 'number': 628}, 'P': {'precision': 0.5815028901734104, 'recall': 0.6515544041450777, 'f1': 0.6145387904703726, 'number': 772}, 'overall_precision': 0.5337078651685393, 'overall_recall': 0.6107142857142858, 'overall_f1': 0.569620253164557, 'overall_accuracy': 0.7229136966772672}
			------------EPOCH 15---------------
Loss:  tensor(158.1114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.8899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.2930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.5827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.3126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.3945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.6399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.9294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.7126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.8466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.7718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.8293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.0818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.2461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.7634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.2723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.4132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.2916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.5774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.1778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.3242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.3416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.4878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.1899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.3086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.3654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.0510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.7165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.5122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.8851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.6052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.2862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.3091, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4695752009184845, 'recall': 0.6512738853503185, 'f1': 0.5456971314209473, 'number': 628}, 'P': {'precision': 0.6180371352785146, 'recall': 0.6036269430051814, 'f1': 0.6107470511140235, 'number': 772}, 'overall_precision': 0.5384615384615384, 'overall_recall': 0.625, 'overall_f1': 0.578512396694215, 'overall_accuracy': 0.71013817304529}
			------------EPOCH 16---------------
Loss:  tensor(159.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.3386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.5036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.9951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.6815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.1527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.2046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.3835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.7650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.3950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.9582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.8237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.7427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.7320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.3444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.7111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.3878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.1815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.3186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.9637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.7999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.6355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.6485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.1574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.8894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.5614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.9323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.4678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.6933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.3429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2018, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.47089262613195343, 'recall': 0.5796178343949044, 'f1': 0.5196288365453248, 'number': 628}, 'P': {'precision': 0.5876662636033857, 'recall': 0.6295336787564767, 'f1': 0.6078799249530956, 'number': 772}, 'overall_precision': 0.53125, 'overall_recall': 0.6071428571428571, 'overall_f1': 0.5666666666666667, 'overall_accuracy': 0.7168549183024454}
			------------EPOCH 17---------------
Loss:  tensor(98.7976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.4521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.2089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.1317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.4721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.6897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.6126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.0869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.6910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.5119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.5720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.9306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.1102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.8935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.2136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.0351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.1503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.8181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.9798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.8148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.2256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.2369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.1888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.7353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.2647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1258, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4796437659033079, 'recall': 0.6003184713375797, 'f1': 0.5332390381895332, 'number': 628}, 'P': {'precision': 0.5919117647058824, 'recall': 0.6256476683937824, 'f1': 0.6083123425692696, 'number': 772}, 'overall_precision': 0.5368289637952559, 'overall_recall': 0.6142857142857143, 'overall_f1': 0.5729513657561626, 'overall_accuracy': 0.7148261870819169}
			------------EPOCH 18---------------
Loss:  tensor(76.9599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.0761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.7201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.2866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.3158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.0995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.3030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.8176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.4655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.8549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.0807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.2241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.1353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.2206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.6583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.6478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3270, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.48129675810473815, 'recall': 0.6146496815286624, 'f1': 0.5398601398601399, 'number': 628}, 'P': {'precision': 0.5907960199004975, 'recall': 0.6152849740932642, 'f1': 0.6027918781725888, 'number': 772}, 'overall_precision': 0.5361145703611457, 'overall_recall': 0.615, 'overall_f1': 0.5728542914171658, 'overall_accuracy': 0.7132909310231385}
			------------EPOCH 19---------------
Loss:  tensor(62.9902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.9325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.9869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.9833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.0935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.5168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.8725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.8788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.3925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.1322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.3783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4748, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.46074646074646075, 'recall': 0.5700636942675159, 'f1': 0.509608540925267, 'number': 628}, 'P': {'precision': 0.5829268292682926, 'recall': 0.6191709844559585, 'f1': 0.6005025125628141, 'number': 772}, 'overall_precision': 0.5234815278647464, 'overall_recall': 0.5971428571428572, 'overall_f1': 0.5578912245578912, 'overall_accuracy': 0.7100285118982345}
			------------EPOCH 20---------------
Loss:  tensor(53.7515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.3298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.1412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.1896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.3651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.3012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.3783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.7453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.8774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.9882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.3234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0601, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.46382428940568476, 'recall': 0.571656050955414, 'f1': 0.5121255349500714, 'number': 628}, 'P': {'precision': 0.5829326923076923, 'recall': 0.6282383419689119, 'f1': 0.6047381546134662, 'number': 772}, 'overall_precision': 0.5255292652552926, 'overall_recall': 0.6028571428571429, 'overall_f1': 0.5615435795076513, 'overall_accuracy': 0.7097543590305955}
			------------EPOCH 21---------------
Loss:  tensor(48.6730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.6908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.3077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.5098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.2188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8877, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.45525291828793774, 'recall': 0.5589171974522293, 'f1': 0.5017869907076483, 'number': 628}, 'P': {'precision': 0.5797619047619048, 'recall': 0.6308290155440415, 'f1': 0.6042183622828784, 'number': 772}, 'overall_precision': 0.5201738050900062, 'overall_recall': 0.5985714285714285, 'overall_f1': 0.5566257057455994, 'overall_accuracy': 0.709068976861498}
			------------EPOCH 22---------------
Loss:  tensor(44.3293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.2829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.4328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.4522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.3356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.8164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3888, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4524421593830334, 'recall': 0.5605095541401274, 'f1': 0.5007112375533429, 'number': 628}, 'P': {'precision': 0.5775656324582339, 'recall': 0.6269430051813472, 'f1': 0.6012422360248447, 'number': 772}, 'overall_precision': 0.5173267326732673, 'overall_recall': 0.5971428571428572, 'overall_f1': 0.5543766578249337, 'overall_accuracy': 0.7077530430968308}
			------------EPOCH 23---------------
Loss:  tensor(40.9465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.3713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.6023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.7210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.6304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.8775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2738, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4553686934023286, 'recall': 0.5605095541401274, 'f1': 0.502498215560314, 'number': 628}, 'P': {'precision': 0.5785714285714286, 'recall': 0.6295336787564767, 'f1': 0.6029776674937964, 'number': 772}, 'overall_precision': 0.5195288282703038, 'overall_recall': 0.5985714285714285, 'overall_f1': 0.5562562230335213, 'overall_accuracy': 0.7077256278100669}
			------------EPOCH 24---------------
Loss:  tensor(38.0403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.1832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.1179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.3183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.2110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4649, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4553686934023286, 'recall': 0.5605095541401274, 'f1': 0.502498215560314, 'number': 628}, 'P': {'precision': 0.5788849347568209, 'recall': 0.6321243523316062, 'f1': 0.6043343653250774, 'number': 772}, 'overall_precision': 0.5198019801980198, 'overall_recall': 0.6, 'overall_f1': 0.5570291777188329, 'overall_accuracy': 0.7069031692071499}
			------------EPOCH 25---------------
Loss:  tensor(35.5915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.6014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.4650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.7616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.5472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8335, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.46143790849673205, 'recall': 0.5621019108280255, 'f1': 0.5068198133524767, 'number': 628}, 'P': {'precision': 0.5790094339622641, 'recall': 0.6360103626943006, 'f1': 0.6061728395061728, 'number': 772}, 'overall_precision': 0.523248605083695, 'overall_recall': 0.6028571428571429, 'overall_f1': 0.560238964487222, 'overall_accuracy': 0.7086851628468034}


		-------------RUN 4-----------
			------------EPOCH 1---------------
Loss:  tensor(4846.0879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3629.6367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2808.8503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2579.2378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1519.8641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1479.6394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2860.7949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4034.8333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3952.9668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2777.0601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3159.8105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2049.9360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1341.0239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2568.3857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2189.8118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2157.2168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2905.2966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3338.1560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2851.4788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3053.8013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2279.5532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2426.8315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1290.6409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2151.5908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2212.3010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3102.4023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2336.4827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3338.9182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2127.5635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1120.2042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1285.1028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(961.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1171.2358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1567.5862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1983.4999, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.013262599469496022, 'recall': 0.02040816326530612, 'f1': 0.01607717041800643, 'number': 735}, 'P': {'precision': 0.022031473533619457, 'recall': 0.08690744920993228, 'f1': 0.03515179182834969, 'number': 886}, 'overall_precision': 0.01988759187202767, 'overall_recall': 0.0567550894509562, 'overall_f1': 0.029454137986233392, 'overall_accuracy': 0.5102793352528161}
			------------EPOCH 2---------------
Loss:  tensor(3425.7412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2466.9092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1934.0706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1800.1985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1098.9136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1068.8455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2062.1128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2911.2566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3053.1575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2229.4146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2601.4189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1657.0687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1067.6508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2101.2268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1752.6019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1775.1196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2344.3760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2652.2637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2357.6333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2452.6143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1932.1465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2056.7378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1014.5046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1721.1622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1899.3745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2584.8945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1896.1930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2672.8962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1837.3414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(961.5211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1098.5137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.3820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.3853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1327.1115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1712.9299, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0745814307458143, 'recall': 0.06666666666666667, 'f1': 0.07040229885057472, 'number': 735}, 'P': {'precision': 0.11024643320363164, 'recall': 0.2878103837471783, 'f1': 0.1594248202563301, 'number': 886}, 'overall_precision': 0.10235690235690235, 'overall_recall': 0.1875385564466379, 'overall_f1': 0.1324330211282945, 'overall_accuracy': 0.5737485477597616}
			------------EPOCH 3---------------
Loss:  tensor(3066.0723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2194.7051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1674.4515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1538.2288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(971.2527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(934.8521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1837.9712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2555.2690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2648.4238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1913.2788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2297.2705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1465.5999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(911.2801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1833.9592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1439.3842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1561.7594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1935.1777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2254.1042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2048.5500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2022.7648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1762.3055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1800.5928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(868.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1428.0767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1654.2861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2185.6377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1536.2338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2219.7319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1686.8538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.6063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(969.7738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.8406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(831.7934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1155.1431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1487.1052, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11242603550295859, 'recall': 0.1292517006802721, 'f1': 0.12025316455696203, 'number': 735}, 'P': {'precision': 0.17672183662573412, 'recall': 0.37358916478555304, 'f1': 0.23994200797390358, 'number': 886}, 'overall_precision': 0.15673289183222958, 'overall_recall': 0.2628007402837754, 'overall_f1': 0.19635860797418755, 'overall_accuracy': 0.6010759205940294}
			------------EPOCH 4---------------
Loss:  tensor(2737.7412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1965.6323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1471.9719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1364.9454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.4960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(847.2589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1566.3580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2334.0913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2271.8291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1708.1448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2056.5125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1204.8531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.9998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1507.4529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1240.0591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1479.4473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1610.1504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1852.3875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1732.3643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1694.9810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1604.9131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1529.3951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.2145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1166.6289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1527.5220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1975.1877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1207.9436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1835.1090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1506.3540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(697.2257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(870.2903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(627.9258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.9320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1022.2566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1351.1558, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1720183486238532, 'recall': 0.20408163265306123, 'f1': 0.18668326073428748, 'number': 735}, 'P': {'precision': 0.2032, 'recall': 0.43002257336343114, 'f1': 0.2759869612459254, 'number': 886}, 'overall_precision': 0.1933017837641063, 'overall_recall': 0.32757557063541026, 'overall_f1': 0.24313186813186816, 'overall_accuracy': 0.6156740920341466}
			------------EPOCH 5---------------
Loss:  tensor(2281.6643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1711.9678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1252.9524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1258.0378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.4437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.3224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1290.0314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2096.6548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2101.4131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1563.0474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1689.1082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.5330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.9770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(944.2897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1049.2758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1351.4833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1359.1837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1460.7131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1513.5400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1406.6130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1419.1976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1220.0308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.3258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1075.2112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1329.3127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1622.6311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(973.7175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1537.8054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1229.7588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(545.6764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(707.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.3983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.2024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(837.2575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1162.0742, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2283702213279678, 'recall': 0.308843537414966, 'f1': 0.2625795257374205, 'number': 735}, 'P': {'precision': 0.26591230551626593, 'recall': 0.42437923250564336, 'f1': 0.3269565217391305, 'number': 886}, 'overall_precision': 0.2504152823920266, 'overall_recall': 0.37199259716224553, 'overall_f1': 0.2993298585256888, 'overall_accuracy': 0.6402485225034096}
			------------EPOCH 6---------------
Loss:  tensor(1852.5068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1429.8120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1010.0583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1113.6287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.2328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.1130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1019.6996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1875.7488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1734.1130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1349.2349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1415.1252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.9014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.8110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.0492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(865.9897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1322.4850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1111.4402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1212.8745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1299.0354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1173.4924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1090.6029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1093.6906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.5256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(724.8493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.2954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1343.0901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(791.9080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1254.4270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1096.7234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(549.2430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.5350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.4831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.6863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.0848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1027.2312, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24914675767918087, 'recall': 0.39727891156462586, 'f1': 0.30624016780283164, 'number': 735}, 'P': {'precision': 0.31312217194570136, 'recall': 0.3905191873589165, 'f1': 0.347564038171773, 'number': 886}, 'overall_precision': 0.28019323671497587, 'overall_recall': 0.39358420727945714, 'overall_f1': 0.3273473576192919, 'overall_accuracy': 0.6577764307723393}
			------------EPOCH 7---------------
Loss:  tensor(1596.8894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1284.6351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(764.6030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(953.0167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(450.2789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.1482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(663.6627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1397.0605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1499.9871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1140.2061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1165.9141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.6608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.3604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.3214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.1185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1373.4829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1220.6665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1279.4723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1381.7200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1157.5486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1149.9830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1738.7153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(572.0393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(868.9281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1101.1932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1459.7661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(824.4883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1189.8796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(837.9607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.9056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.8619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.2637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.8735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(682.6215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(878.6205, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17436489607390301, 'recall': 0.2054421768707483, 'f1': 0.18863210493441598, 'number': 735}, 'P': {'precision': 0.11180773249738767, 'recall': 0.12076749435665914, 'f1': 0.11611502984264785, 'number': 886}, 'overall_precision': 0.14152495885902358, 'overall_recall': 0.1591610117211598, 'overall_f1': 0.14982578397212545, 'overall_accuracy': 0.5428347729453957}
			------------EPOCH 8---------------
Loss:  tensor(1830.0638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1437.8751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(813.6536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1126.4971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.4899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(533.6362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(883.8806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1512.0332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1547.6360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1140.1157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1122.9153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.6436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.7912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.7745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.1254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.3863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(782.8334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(807.8865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.6157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(798.8035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(887.7720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1072.7048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.8845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.3652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1045.3583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1178.3818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.5765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(987.3040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(755.8556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.7744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.7151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.4454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.2530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(534.6328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(713.7526, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26270456503014644, 'recall': 0.41496598639455784, 'f1': 0.32172995780590713, 'number': 735}, 'P': {'precision': 0.4661432777232581, 'recall': 0.536117381489842, 'f1': 0.4986876640419948, 'number': 886}, 'overall_precision': 0.3577981651376147, 'overall_recall': 0.4811844540407156, 'overall_f1': 0.4104183109707972, 'overall_accuracy': 0.6720462696368137}
			------------EPOCH 9---------------
Loss:  tensor(1103.2876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(934.2836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.4998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.4414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.7937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.1339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.3109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(926.2238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(801.7294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.0975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(603.9337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.5968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.1353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.5807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.4423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(799.5735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.9023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(965.1613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(789.4032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(707.9869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.1945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.5597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.0871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.3026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(627.8682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.6649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.7901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(474.7191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.7158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.9046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.2715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.6360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.0999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(503.2214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.1602, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3064295485636115, 'recall': 0.3047619047619048, 'f1': 0.305593451568895, 'number': 735}, 'P': {'precision': 0.4, 'recall': 0.6568848758465011, 'f1': 0.4972234087996582, 'number': 886}, 'overall_precision': 0.3687099725526075, 'overall_recall': 0.4972239358420728, 'overall_f1': 0.4234305227213029, 'overall_accuracy': 0.6680305096731828}
			------------EPOCH 10---------------
Loss:  tensor(955.6979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(710.4535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.9710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.5052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.1699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.6231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.5353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(749.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.0688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.1331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.6633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.7315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.1437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.5215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.0103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(865.3529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(721.0740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(991.4629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(863.9233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1060.5624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.8988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.3885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.4584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.5610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.8351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(525.9170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.3518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.0282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.3675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.0525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.8058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.3392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.6076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.1063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(861.8789, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24043715846994534, 'recall': 0.11972789115646258, 'f1': 0.1598546775658492, 'number': 735}, 'P': {'precision': 0.36538461538461536, 'recall': 0.6433408577878104, 'f1': 0.4660670482420277, 'number': 886}, 'overall_precision': 0.34164070612668745, 'overall_recall': 0.405922270203578, 'overall_f1': 0.3710177614885819, 'overall_accuracy': 0.6547204121836642}
			------------EPOCH 11---------------
Loss:  tensor(1327.2383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(922.6921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.1106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(749.6655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.7236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.3793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.7675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.8715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.3763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.9954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.5306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.4403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.7085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.4060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.0736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.6324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.8943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(745.5224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.0986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(804.6198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1318.2034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.0161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.3017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(773.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(956.4425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1006.5844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.4891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(947.0462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.8455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.1178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.0898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.4839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.0411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.2886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.5573, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3526315789473684, 'recall': 0.27346938775510204, 'f1': 0.3080459770114943, 'number': 735}, 'P': {'precision': 0.4231578947368421, 'recall': 0.6805869074492099, 'f1': 0.5218520121159671, 'number': 886}, 'overall_precision': 0.4030075187969925, 'overall_recall': 0.4959901295496607, 'overall_f1': 0.44469026548672563, 'overall_accuracy': 0.6713643481335556}
			------------EPOCH 12---------------
Loss:  tensor(502.0498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.0245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.3053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.7906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.4362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.8295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.7957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(814.1932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1708.7191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1332.4434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1169.8978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.3589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.2853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.6703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.7733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(969.1951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.8438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.1468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.0394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.9422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.6501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.6025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.3535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.3697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.9709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.3705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.7293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.4639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.8881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.9294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.0658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.1029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.2033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.5776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(585.4844, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30448717948717946, 'recall': 0.6462585034013606, 'f1': 0.4139433551198257, 'number': 735}, 'P': {'precision': 0.4295942720763723, 'recall': 0.20316027088036118, 'f1': 0.27586206896551724, 'number': 886}, 'overall_precision': 0.3309752400202122, 'overall_recall': 0.4040715607649599, 'overall_f1': 0.36388888888888893, 'overall_accuracy': 0.6078446229226651}
			------------EPOCH 13---------------
Loss:  tensor(1067.7034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(868.7917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.2856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(764.9535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.4810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.0324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.5258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1162.2688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(673.0421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.4039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.5383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.6822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.5769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.7197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.5205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.8584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.9215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.0728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.4155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.7570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.4286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.0537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.9385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.5892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.2133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.6377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.5833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.0281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.9553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.5543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.5046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.8870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.9607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.6806, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4279475982532751, 'recall': 0.4, 'f1': 0.4135021097046414, 'number': 735}, 'P': {'precision': 0.47344461305007585, 'recall': 0.7042889390519187, 'f1': 0.5662431941923776, 'number': 886}, 'overall_precision': 0.45785536159601, 'overall_recall': 0.5663170882171499, 'overall_f1': 0.5063430777716492, 'overall_accuracy': 0.7046522200333384}
			------------EPOCH 14---------------
Loss:  tensor(437.4927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.2556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.7297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.4914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.4383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.3811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.0836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.3901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.2028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.9571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.6956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.4919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.0133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.1980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.3642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.7531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.7068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.1933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.4164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.2770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.7116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.7887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.2868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.8852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.3579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.5276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.6176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.5379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.1327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.5558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.3319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.6024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.9169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.2942, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3968095712861416, 'recall': 0.5414965986394558, 'f1': 0.4579976985040276, 'number': 735}, 'P': {'precision': 0.536046511627907, 'recall': 0.5203160270880361, 'f1': 0.5280641466208478, 'number': 886}, 'overall_precision': 0.46108427267847557, 'overall_recall': 0.5299198025909932, 'overall_f1': 0.49311136624569457, 'overall_accuracy': 0.7039197858261352}
			------------EPOCH 15---------------
Loss:  tensor(373.5479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.7609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.3947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.1323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.0689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.1818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.0850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.5887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.9240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.0848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.6310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.6124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.8215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.5020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.5527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.1285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.6050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.7558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.5645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.3395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.5808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.1180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.8278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.0256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.6936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.8217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.9716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.8466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.7384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.4673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.1443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.9216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.2612, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.40592930444697833, 'recall': 0.48435374149659866, 'f1': 0.44168734491315137, 'number': 735}, 'P': {'precision': 0.5373134328358209, 'recall': 0.6501128668171557, 'f1': 0.5883554647599591, 'number': 886}, 'overall_precision': 0.47819394561313494, 'overall_recall': 0.5749537322640346, 'overall_f1': 0.5221288515406163, 'overall_accuracy': 0.7097034904278426}
			------------EPOCH 16---------------
Loss:  tensor(138.9218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.7906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.2090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.9975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.1217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.9578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.0594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.1140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.9604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.2350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.3824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.2458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.0768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.5273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.8930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.7518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.4838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.4979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.1610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.0709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.5347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.7825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.6336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.2473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.9109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.7468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.1240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.9380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.1820, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.40836408364083643, 'recall': 0.45170068027210886, 'f1': 0.4289405684754522, 'number': 735}, 'P': {'precision': 0.5301645338208409, 'recall': 0.654627539503386, 'f1': 0.5858585858585859, 'number': 886}, 'overall_precision': 0.47823807026743576, 'overall_recall': 0.5626156693399136, 'overall_f1': 0.5170068027210883, 'overall_accuracy': 0.7093751578521998}
			------------EPOCH 17---------------
Loss:  tensor(93.7257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.6670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.7936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.5424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.6750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.2678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.8247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.8528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.3483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.3805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.0657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.1500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.1087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.5104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.3141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.6302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.9111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.3814, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.40786516853932586, 'recall': 0.49387755102040815, 'f1': 0.44676923076923075, 'number': 735}, 'P': {'precision': 0.5399802566633761, 'recall': 0.6173814898419865, 'f1': 0.5760926803580831, 'number': 886}, 'overall_precision': 0.47819232790331057, 'overall_recall': 0.5613818630475016, 'overall_f1': 0.5164585698070375, 'overall_accuracy': 0.7159670657170278}
			------------EPOCH 18---------------
Loss:  tensor(79.8706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.1216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.1905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.6325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.7660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.8242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.5254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.5071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.7007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.2046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.4473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.6728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.0774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.3113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2825, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.41647597254004576, 'recall': 0.49523809523809526, 'f1': 0.45245494095711625, 'number': 735}, 'P': {'precision': 0.5459940652818991, 'recall': 0.6230248306997742, 'f1': 0.5819715340010544, 'number': 886}, 'overall_precision': 0.48594164456233424, 'overall_recall': 0.5650832819247378, 'overall_f1': 0.522532800912721, 'overall_accuracy': 0.7106632318027984}
			------------EPOCH 19---------------
Loss:  tensor(67.1711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.9364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.6488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.8215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.3729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.9005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.4224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.6100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.1208, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.419811320754717, 'recall': 0.48435374149659866, 'f1': 0.4497789008212255, 'number': 735}, 'P': {'precision': 0.5537270087124879, 'recall': 0.6455981941309256, 'f1': 0.5961438249088067, 'number': 886}, 'overall_precision': 0.4933545986177565, 'overall_recall': 0.5724861196792104, 'overall_f1': 0.529982866933181, 'overall_accuracy': 0.7131130979441329}
			------------EPOCH 20---------------
Loss:  tensor(57.8269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.4429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.1533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.3307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.8447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9562, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4200700116686114, 'recall': 0.4897959183673469, 'f1': 0.4522613065326633, 'number': 735}, 'P': {'precision': 0.5537270087124879, 'recall': 0.6455981941309256, 'f1': 0.5961438249088067, 'number': 886}, 'overall_precision': 0.4931216931216931, 'overall_recall': 0.5749537322640346, 'overall_f1': 0.5309028766733125, 'overall_accuracy': 0.7116987422336718}
			------------EPOCH 21---------------
Loss:  tensor(51.7808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.7211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.2838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.0734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.6277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.4766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.9441, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4224037339556593, 'recall': 0.4925170068027211, 'f1': 0.45477386934673364, 'number': 735}, 'P': {'precision': 0.5581622678396871, 'recall': 0.6444695259593679, 'f1': 0.5982189628077527, 'number': 886}, 'overall_precision': 0.49627659574468086, 'overall_recall': 0.5755706354102406, 'overall_f1': 0.5329905741216795, 'overall_accuracy': 0.7111178461383038}
			------------EPOCH 22---------------
Loss:  tensor(45.9018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.6747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.2202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.2471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3476, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4243845252051583, 'recall': 0.4925170068027211, 'f1': 0.45591939546599497, 'number': 735}, 'P': {'precision': 0.5569620253164557, 'recall': 0.6455981941309256, 'f1': 0.5980135912179823, 'number': 886}, 'overall_precision': 0.4968085106382979, 'overall_recall': 0.5761875385564467, 'overall_f1': 0.5335618394744359, 'overall_accuracy': 0.7087942617568318}
			------------EPOCH 23---------------
Loss:  tensor(41.1641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.9882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.7183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4714, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4221165279429251, 'recall': 0.48299319727891155, 'f1': 0.45050761421319796, 'number': 735}, 'P': {'precision': 0.554368932038835, 'recall': 0.6444695259593679, 'f1': 0.5960334029227559, 'number': 886}, 'overall_precision': 0.4949225013361839, 'overall_recall': 0.5712523133867983, 'overall_f1': 0.5303550973654066, 'overall_accuracy': 0.709526695964035}
			------------EPOCH 24---------------
Loss:  tensor(36.1659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.5071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.3943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.7856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3017, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4165680473372781, 'recall': 0.47891156462585033, 'f1': 0.44556962025316454, 'number': 735}, 'P': {'precision': 0.5530671859785784, 'recall': 0.6410835214446953, 'f1': 0.5938316779926816, 'number': 886}, 'overall_precision': 0.49145299145299143, 'overall_recall': 0.567550894509562, 'overall_f1': 0.5267678213569996, 'overall_accuracy': 0.7070010607667828}
			------------EPOCH 25---------------
Loss:  tensor(31.6992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.9987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.8083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.0310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.7954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4379, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.42303030303030303, 'recall': 0.4748299319727891, 'f1': 0.4474358974358974, 'number': 735}, 'P': {'precision': 0.5524271844660195, 'recall': 0.6422121896162528, 'f1': 0.593945720250522, 'number': 886}, 'overall_precision': 0.4948787061994609, 'overall_recall': 0.5663170882171499, 'overall_f1': 0.52819332566168, 'overall_accuracy': 0.7083143910693539}


		-------------RUN 5-----------
			------------EPOCH 1---------------
Loss:  tensor(1515.5305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1818.7803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1433.7274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1093.8293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2167.1064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1507.4761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2578.4463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2428.2373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1245.8098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2292.4102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1808.4236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1983.8235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2935.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3730.4814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1979.3044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1309.2129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1969.9714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2084.5039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2368.6372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3414.4404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1346.9771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2555.4653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2331.9521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1517.8120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1835.8516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1533.2864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3032.4292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2129.4421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2706.2661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1564.8606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1961.9485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2830.3970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2774.2148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2935.3462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1564.4301, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 693}, 'P': {'precision': 0.17253774263120059, 'recall': 0.26936026936026936, 'f1': 0.21034180543383, 'number': 891}, 'overall_precision': 0.16348773841961853, 'overall_recall': 0.15151515151515152, 'overall_f1': 0.15727391874180865, 'overall_accuracy': 0.45245196642852187}
			------------EPOCH 2---------------
Loss:  tensor(1110.8083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1331.3551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1093.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.0396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1677.9421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1213.9375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2209.6648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1945.1921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(959.1454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1740.2927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1481.2595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1421.4888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2106.2446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2582.9390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1819.3777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1150.1829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1764.1271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1861.7529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2036.6211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2995.3770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1098.1477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2128.6099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1971.1691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1315.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1523.3153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1282.1482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2378.0588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1695.2404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2285.8152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1280.8219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1675.3267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2413.3223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2319.4053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2499.3984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1279.5828, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.06149341142020498, 'recall': 0.06060606060606061, 'f1': 0.061046511627906974, 'number': 693}, 'P': {'precision': 0.2780487804878049, 'recall': 0.5757575757575758, 'f1': 0.37500000000000006, 'number': 891}, 'overall_precision': 0.21954113924050633, 'overall_recall': 0.3503787878787879, 'overall_f1': 0.2699416342412451, 'overall_accuracy': 0.541629095281034}
			------------EPOCH 3---------------
Loss:  tensor(964.0530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1041.9119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(937.0613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.1136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1321.4734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1003.8927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1779.9817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1540.3174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(800.8951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1498.6692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1251.8792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1229.7583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1758.3501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2162.7231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1370.7659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(907.3925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1315.5465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1531.6299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1767.3335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2555.8914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.2639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1755.7124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1631.7057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1137.1951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1302.3622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1052.1565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1787.9513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1304.1528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1856.3408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1003.3395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1451.3479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2067.3726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1883.1904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2111.4741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.2935, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10245310245310245, 'recall': 0.10245310245310245, 'f1': 0.10245310245310243, 'number': 693}, 'P': {'precision': 0.27262813522355506, 'recall': 0.5611672278338945, 'f1': 0.36697247706422015, 'number': 891}, 'overall_precision': 0.2259596359319351, 'overall_recall': 0.36047979797979796, 'overall_f1': 0.27779129165653127, 'overall_accuracy': 0.5902291276502277}
			------------EPOCH 4---------------
Loss:  tensor(770.3350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.4637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.2932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(602.5238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1068.2831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(883.0204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1585.4854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1362.2332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.2521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1294.0968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1066.2325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(938.5558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1447.7489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1835.1846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.8141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.0076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.2986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1116.0869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1412.6172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2067.7715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.7546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1450.5146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1444.0975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1002.3372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1137.5684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(822.5525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1351., device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1080.1366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1555.2776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(760.4251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1262.7224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1782.8582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1541.9180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1694.0759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(877.3755, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14385964912280702, 'recall': 0.1774891774891775, 'f1': 0.15891472868217055, 'number': 693}, 'P': {'precision': 0.3406520292747838, 'recall': 0.574635241301908, 'f1': 0.42773600668337514, 'number': 891}, 'overall_precision': 0.2692960135708227, 'overall_recall': 0.4008838383838384, 'overall_f1': 0.3221714865550482, 'overall_accuracy': 0.6379505676169337}
			------------EPOCH 5---------------
Loss:  tensor(619.3199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.6954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.2039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.5147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.6534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(791.8412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1280.3851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.6293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.2754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1163.7113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(894.9734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.4326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1207.1324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1572.5343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.0559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.2783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.4628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(856.1492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1172.9714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1741.5830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(659.6257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1243.1833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1234.3589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.2224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(958.7664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(702.1686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1037.4774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.6387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1319.1681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.0565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1160.1534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1499.2981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1184.0291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1355.6434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.8462, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11961206896551724, 'recall': 0.16017316017316016, 'f1': 0.13695249845774213, 'number': 693}, 'P': {'precision': 0.3510235026535254, 'recall': 0.5196408529741863, 'f1': 0.41900452488687784, 'number': 891}, 'overall_precision': 0.2554517133956386, 'overall_recall': 0.36237373737373735, 'overall_f1': 0.29966066301226835, 'overall_accuracy': 0.6655799865899055}
			------------EPOCH 6---------------
Loss:  tensor(468.1924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.0641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(624.3890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.5650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(683.0714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.3659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.0464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1048.9639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.2018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(957.2760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.5942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.9269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1072.6353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1467.2498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.9649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.8701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.7025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(734.9858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(952.3152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1491.8427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(539.3483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(989.0587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(975.8240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(783.6105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.6636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.7831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.8813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.1286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1125.7124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.2920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(923.1431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.0278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.5400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1106.1267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.0901, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24758842443729903, 'recall': 0.5555555555555556, 'f1': 0.3425266903914591, 'number': 693}, 'P': {'precision': 0.4156804733727811, 'recall': 0.3153759820426487, 'f1': 0.3586470963624761, 'number': 891}, 'overall_precision': 0.2985208426714478, 'overall_recall': 0.42045454545454547, 'overall_f1': 0.3491480996068152, 'overall_accuracy': 0.611800883216573}
			------------EPOCH 7---------------
Loss:  tensor(482.9862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.6680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.7316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.5955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(644.8446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.8741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(875.8323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.4887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.0790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.3254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(500.6820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.4756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(897.5184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1199.4922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.1423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.2461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.1739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.3667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(699.9229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1019.0870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.9363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(883.6884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.5471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(694.0066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.3821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.2203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.8466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.2287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(912.0637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.9695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(878.3733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1053.3611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(778.0785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(996.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.1783, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29666924864446165, 'recall': 0.5526695526695526, 'f1': 0.3860887096774194, 'number': 693}, 'P': {'precision': 0.4519906323185012, 'recall': 0.4332210998877666, 'f1': 0.4424068767908309, 'number': 891}, 'overall_precision': 0.3585081585081585, 'overall_recall': 0.48547979797979796, 'overall_f1': 0.4124430142129257, 'overall_accuracy': 0.6515918707081917}
			------------EPOCH 8---------------
Loss:  tensor(306.2489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.1067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.2786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.8623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(497.3649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.2575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.4303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.8514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.5689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.3074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.9840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(801.0651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1058.3459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1699.6821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.0438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.4199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.5007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.4526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.3480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(925.4434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(441.1465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(726.2782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.1355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(525.4371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(712.0103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.8779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.9508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.4788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.4236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.1529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(830.6783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1075.8722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1237.9185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1057.2539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.2336, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28012048192771083, 'recall': 0.1341991341991342, 'f1': 0.18146341463414634, 'number': 693}, 'P': {'precision': 0.330672748004561, 'recall': 0.6509539842873177, 'f1': 0.43856332703213613, 'number': 891}, 'overall_precision': 0.32262703739213805, 'overall_recall': 0.42487373737373735, 'overall_f1': 0.3667574931880109, 'overall_accuracy': 0.621557883054727}
			------------EPOCH 9---------------
Loss:  tensor(364.1495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.7132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.2018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.7930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(503.3792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.7880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(977.0156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(911.0766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.7807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.6616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.2614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.9519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(828.9594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1017.5353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.5710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.6138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.9081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.4566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.1708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1159.1934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.6505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(959.0874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(794.6526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(865.7296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.3323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.4092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(887.9976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.8994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.9755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.3000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(716.1973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.0167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.5038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.7819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.0981, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2752902155887231, 'recall': 0.23953823953823955, 'f1': 0.25617283950617287, 'number': 693}, 'P': {'precision': 0.3967065868263473, 'recall': 0.5948372615039281, 'f1': 0.47597665020206553, 'number': 891}, 'overall_precision': 0.35894791129448167, 'overall_recall': 0.4393939393939394, 'overall_f1': 0.39511779733181945, 'overall_accuracy': 0.7022727798201198}
			------------EPOCH 10---------------
Loss:  tensor(219.2598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.9822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.5793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.6460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.6366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.8755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.4608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.0723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.2125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.3976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.7634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(420.8217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(942.8992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1056.1794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.1344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.8214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.9237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.2307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(873.2830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.2679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(618.1688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.5858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.1343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.9571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.6812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.5132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.7090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.4182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.4992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(586.8500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.9214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(483.9923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(560.1083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.1259, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.359192348565356, 'recall': 0.48773448773448774, 'f1': 0.4137086903304774, 'number': 693}, 'P': {'precision': 0.4348607367475292, 'recall': 0.5432098765432098, 'f1': 0.4830339321357285, 'number': 891}, 'overall_precision': 0.40019474196689386, 'overall_recall': 0.5189393939393939, 'overall_f1': 0.4518966465090709, 'overall_accuracy': 0.6928625927724215}
			------------EPOCH 11---------------
Loss:  tensor(158.0540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.1521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.7332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.5816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.2848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.3608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.9641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.4495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.8489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.4955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.2265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.8654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.9341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.9140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.4047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.1626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.7603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.6657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.6146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.1569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.9838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.9077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.9779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.4783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.0549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.1594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.2135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.4770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.2652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.7700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.1961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.5208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.2155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.0326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.9071, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4084507042253521, 'recall': 0.4184704184704185, 'f1': 0.413399857448325, 'number': 693}, 'P': {'precision': 0.44836272040302266, 'recall': 0.5993265993265994, 'f1': 0.5129682997118157, 'number': 891}, 'overall_precision': 0.4334560757496055, 'overall_recall': 0.5202020202020202, 'overall_f1': 0.4728837876614061, 'overall_accuracy': 0.7078217844674112}
			------------EPOCH 12---------------
Loss:  tensor(88.1631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.4720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.7090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.9797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.4094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.5355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.5369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.6617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.2885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.9215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.3120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.4409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.1322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.7054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.7550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.5196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.3431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.5273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.9227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.1628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.3215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.7350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.5593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.7195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.7878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.0349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.5534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.0701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.1156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.0596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.3235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.8753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.8601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.0587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.3632, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.40867279894875164, 'recall': 0.44877344877344877, 'f1': 0.42778541953232463, 'number': 693}, 'P': {'precision': 0.453537936913896, 'recall': 0.5970819304152637, 'f1': 0.5155038759689922, 'number': 891}, 'overall_precision': 0.43588417786970013, 'overall_recall': 0.5321969696969697, 'overall_f1': 0.4792495736213758, 'overall_accuracy': 0.70916279392384}
			------------EPOCH 13---------------
Loss:  tensor(68.2166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.5160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.5679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.4411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.6342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.0369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.8484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.6094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.2287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.2884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.4427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.2356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.5564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.3267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.5795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.0945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.5312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.9345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.9000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.6647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.6665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.9705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.9259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.4420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.8171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.8818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.4986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.0319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.8020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.5269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.4735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.4375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.7923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.5637, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4090909090909091, 'recall': 0.4675324675324675, 'f1': 0.4363636363636364, 'number': 693}, 'P': {'precision': 0.46617238183503246, 'recall': 0.5645342312008979, 'f1': 0.5106598984771574, 'number': 891}, 'overall_precision': 0.44200962052378406, 'overall_recall': 0.5220959595959596, 'overall_f1': 0.47872648335745294, 'overall_accuracy': 0.7049085570275831}
			------------EPOCH 14---------------
Loss:  tensor(49.1711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.4839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.6204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.3860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.9292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.4184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.9885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.8610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.7917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.0864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.3399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.7914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.1952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.2188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.0371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.6493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.9747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.4516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.1668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.1114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.3326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.3252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.7864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.8947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.2408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.6244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.2546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.9630, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.446676970633694, 'recall': 0.417027417027417, 'f1': 0.43134328358208956, 'number': 693}, 'P': {'precision': 0.4725184577522559, 'recall': 0.6464646464646465, 'f1': 0.5459715639810426, 'number': 891}, 'overall_precision': 0.46355841371918544, 'overall_recall': 0.5460858585858586, 'overall_f1': 0.5014492753623189, 'overall_accuracy': 0.711151187255786}
			------------EPOCH 15---------------
Loss:  tensor(45.6218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.2319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.1464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.8766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.8457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.3231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.4779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.9155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.7064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.4554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.1449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.2181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.3432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.7008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.9316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.6867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.6573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.2532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.9076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.8145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.5039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.9769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.3197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4702, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.413472706155633, 'recall': 0.5137085137085137, 'f1': 0.4581724581724581, 'number': 693}, 'P': {'precision': 0.48484848484848486, 'recall': 0.5566778900112234, 'f1': 0.5182863113897597, 'number': 891}, 'overall_precision': 0.45222929936305734, 'overall_recall': 0.5378787878787878, 'overall_f1': 0.4913494809688581, 'overall_accuracy': 0.7026889551686666}
			------------EPOCH 16---------------
Loss:  tensor(42.4662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.8839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.2631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.0431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.9310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.1539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.6074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.0395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.5238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.5113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.5594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.9621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.1641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.3201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.0911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.9524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.8314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.0555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.0712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.0915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0986, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4328767123287671, 'recall': 0.455988455988456, 'f1': 0.44413211524947294, 'number': 693}, 'P': {'precision': 0.4763157894736842, 'recall': 0.6094276094276094, 'f1': 0.534711964549483, 'number': 891}, 'overall_precision': 0.45935828877005347, 'overall_recall': 0.5422979797979798, 'overall_f1': 0.4973943254198031, 'overall_accuracy': 0.7129083720607616}
			------------EPOCH 17---------------
Loss:  tensor(39.4716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.2037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.3403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.0237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.2260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.7507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.1816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.6178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.3679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.3885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.8141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.8221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.6410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.5492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.4437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.3122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.8809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.3029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.6288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7686, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.43859649122807015, 'recall': 0.5050505050505051, 'f1': 0.4694835680751174, 'number': 693}, 'P': {'precision': 0.496309963099631, 'recall': 0.6038159371492705, 'f1': 0.5448101265822786, 'number': 891}, 'overall_precision': 0.4718384697130712, 'overall_recall': 0.5606060606060606, 'overall_f1': 0.5124062319676861, 'overall_accuracy': 0.70775242190932}
			------------EPOCH 18---------------
Loss:  tensor(28.1862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.3562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.1582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.5911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.8483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.2648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.4847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.3530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.7406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.4245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.4902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.1418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.1949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.2218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.8482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.3264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.8327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8390, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.45806451612903226, 'recall': 0.5122655122655123, 'f1': 0.48365122615803813, 'number': 693}, 'P': {'precision': 0.5054249547920434, 'recall': 0.6273849607182941, 'f1': 0.5598397596394592, 'number': 891}, 'overall_precision': 0.4859117490696438, 'overall_recall': 0.577020202020202, 'overall_f1': 0.5275613275613276, 'overall_accuracy': 0.7099257820628425}
			------------EPOCH 19---------------
Loss:  tensor(26.6130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.9419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.7633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.0263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.3074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.1652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.5272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.9907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.5874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0291, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4522207267833109, 'recall': 0.48484848484848486, 'f1': 0.467966573816156, 'number': 693}, 'P': {'precision': 0.5044563279857398, 'recall': 0.6352413019079686, 'f1': 0.5623447590660706, 'number': 891}, 'overall_precision': 0.4836461126005362, 'overall_recall': 0.5694444444444444, 'overall_f1': 0.523050159466512, 'overall_accuracy': 0.709671452683175}
			------------EPOCH 20---------------
Loss:  tensor(26.4554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.7739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.7287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.9921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.5573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.8757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.2948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.0824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.7640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.5425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2963, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.44471445929526127, 'recall': 0.5281385281385281, 'f1': 0.48284960422163586, 'number': 693}, 'P': {'precision': 0.5103578154425612, 'recall': 0.6083052749719416, 'f1': 0.5550435227854583, 'number': 891}, 'overall_precision': 0.4816976127320955, 'overall_recall': 0.5732323232323232, 'overall_f1': 0.5234938022484866, 'overall_accuracy': 0.7083766849321403}
			------------EPOCH 21---------------
Loss:  tensor(24.4064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.2371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.9591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.8032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1258, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4294478527607362, 'recall': 0.5050505050505051, 'f1': 0.4641909814323607, 'number': 693}, 'P': {'precision': 0.5042016806722689, 'recall': 0.6060606060606061, 'f1': 0.5504587155963303, 'number': 891}, 'overall_precision': 0.471898197242842, 'overall_recall': 0.5618686868686869, 'overall_f1': 0.5129682997118156, 'overall_accuracy': 0.708214838963261}
			------------EPOCH 22---------------
Loss:  tensor(24.6053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.8895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.1543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.6166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0865, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4473358116480793, 'recall': 0.5209235209235209, 'f1': 0.4813333333333333, 'number': 693}, 'P': {'precision': 0.5112149532710281, 'recall': 0.6139169472502806, 'f1': 0.5578786333503314, 'number': 891}, 'overall_precision': 0.4837506659563133, 'overall_recall': 0.5732323232323232, 'overall_f1': 0.5247038428199943, 'overall_accuracy': 0.7094171233035075}
			------------EPOCH 23---------------
Loss:  tensor(23.0564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.7457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.2159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.7994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6506, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4490566037735849, 'recall': 0.5151515151515151, 'f1': 0.4798387096774194, 'number': 693}, 'P': {'precision': 0.5197792088316467, 'recall': 0.6341189674523008, 'f1': 0.5712841253791708, 'number': 891}, 'overall_precision': 0.48990435706695007, 'overall_recall': 0.5820707070707071, 'overall_f1': 0.5320253894979804, 'overall_accuracy': 0.7096483318304779}
			------------EPOCH 24---------------
Loss:  tensor(20.1305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.1076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.0106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8156, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.43818849449204406, 'recall': 0.5165945165945166, 'f1': 0.4741721854304635, 'number': 693}, 'P': {'precision': 0.5357142857142857, 'recall': 0.6397306397306397, 'f1': 0.5831202046035806, 'number': 891}, 'overall_precision': 0.4933545986177565, 'overall_recall': 0.5858585858585859, 'overall_f1': 0.5356421356421356, 'overall_accuracy': 0.7060414788097386}
			------------EPOCH 25---------------
Loss:  tensor(14.3266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.9824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.7563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2256, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.43995098039215685, 'recall': 0.5180375180375181, 'f1': 0.4758117958913188, 'number': 693}, 'P': {'precision': 0.5244487056567594, 'recall': 0.6139169472502806, 'f1': 0.5656670113753879, 'number': 891}, 'overall_precision': 0.48735879505110274, 'overall_recall': 0.571969696969697, 'overall_f1': 0.5262852163810631, 'overall_accuracy': 0.7073362465607732}
