Tokenizer: arg_mining/smlm_pretrained_iter2_0/tokenizer Model: arg_mining/smlm_pretrained_iter2_0/model
	Train size: 80 Test size: 20


		-------------RUN 1-----------
			------------EPOCH 1---------------
Loss:  tensor(4215.4053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3242.8340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2830.7561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3432.7129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3541.6616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1706.3022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1414.9891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1071.4996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1841.4800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2249.8745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2720.6450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2613.6152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2216.5276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2001.3414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3362.2690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1684.3855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1939.3055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1278.5603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1225.6931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1963.0508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1731.9545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1836.2091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1477.6880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1149.2926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(998.8600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1927.4984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1032.8455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(715.9668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1784.3003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1513.9890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1698.1420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2826.3208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1432.4653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1799.0807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2297.1001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1968.4326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1154.1814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2142.4080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1535.6641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1362.3975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1590.9220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1793.8384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2198.9150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1862.6973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1198.1891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1716.6163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(918.4166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2593.1118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1204.3295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1424.4092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1807.3522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1320.3696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1972.4553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1961.8293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1636.0317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2045.4338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2153.7834, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.023809523809523808, 'recall': 0.014705882352941176, 'f1': 0.018181818181818177, 'number': 272}, 'P': {'precision': 0.1873536299765808, 'recall': 0.29304029304029305, 'f1': 0.22857142857142856, 'number': 273}, 'overall_precision': 0.1411764705882353, 'overall_recall': 0.15412844036697249, 'overall_f1': 0.14736842105263157, 'overall_accuracy': 0.5453874119518292}
			------------EPOCH 2---------------
Loss:  tensor(2942.5474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2217.9670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1747.7543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2452.2661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2598.9062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1192.9077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.6107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.7419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1658.9075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1904.9370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2218.7422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2320.5447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1630.7843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1675.9147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2541.8359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1223.8010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1971.3544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1071.0360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(921.2591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1526.8113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1265.0120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1479.8479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1236.8813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(928.4666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(775.0145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1649.5610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(859.0491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.3607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1474.3369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1227.3719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1375.0646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2406.1655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1235.9025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1480.5763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2110.3154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1767.6177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1040.9316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1895.3107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1301.5874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1172.3107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1367.9845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1482.0811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1882.3459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1604.4985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1043.3840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1491.0840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(794.8972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2412.9502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.6006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1214.8765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1588.8229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.5553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1705.5679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1736.7727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1438.3998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1803.2181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1943.6335, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.052830188679245285, 'recall': 0.051470588235294115, 'f1': 0.0521415270018622, 'number': 272}, 'P': {'precision': 0.2222222222222222, 'recall': 0.336996336996337, 'f1': 0.2678311499272198, 'number': 273}, 'overall_precision': 0.1561119293078056, 'overall_recall': 0.1944954128440367, 'overall_f1': 0.17320261437908496, 'overall_accuracy': 0.5594751192910702}
			------------EPOCH 3---------------
Loss:  tensor(2708.4473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2066.7239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1617.8342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2254.1045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2342.3701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1024.1783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(798.9200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(708.1899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1645.6666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1764.0347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2060.4548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2249.5703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1439.8357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1562.8536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2195.4685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(977.3307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1575.4535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(983.7795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(794.0698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1293.0647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.9778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1319.1542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1139.5261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(783.3357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(580.5558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1433.3149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(788.7925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.6918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1317.9060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1081.4452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1117.0752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2155.4507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1169.9667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1326.8259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1791.4739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1557.3733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(965.3619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1726.6459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1244.2676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.9962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1215.3418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1328.9626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1620.3523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1375.7063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.5195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1324.0580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.1921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2105.1182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(838.0510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1087.0901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1454.4451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1040.0848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1519.6924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1538.0997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1310.8601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1669.9888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1748.1730, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.06227106227106227, 'recall': 0.0625, 'f1': 0.062385321100917435, 'number': 272}, 'P': {'precision': 0.2463768115942029, 'recall': 0.37362637362637363, 'f1': 0.29694323144104806, 'number': 273}, 'overall_precision': 0.17321688500727803, 'overall_recall': 0.21834862385321102, 'overall_f1': 0.1931818181818182, 'overall_accuracy': 0.5703817314246762}
			------------EPOCH 4---------------
Loss:  tensor(2399.1575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1871.8890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1435.8975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2076.3506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2060.7183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.3430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.1146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.0212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1623.6995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1573.1416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1710.9680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2113.5171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1249.7983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1486.2290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1907.9913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(826.6010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1433.3234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(909.0043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(670.5547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1097.6990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.9767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1246.8337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1076.6410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.4327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(450.7126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1368.0688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.9445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.1722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1032.3528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(874.3962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.4448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1880.9502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1039.4260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1119.5966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1533.3394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1166.4930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(817.9326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1465.6401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1032.3416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(875.3016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.0559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1116.0421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1383.9500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1146.7385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.9864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1120.8600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.8549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1820.7139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.2876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(950.9237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1359.7655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(934.7153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1493.5215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1500.6901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1291.4735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1608.5620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1522.6924, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.09259259259259259, 'recall': 0.14705882352941177, 'f1': 0.11363636363636363, 'number': 272}, 'P': {'precision': 0.14984709480122324, 'recall': 0.1794871794871795, 'f1': 0.16333333333333333, 'number': 273}, 'overall_precision': 0.11725955204216074, 'overall_recall': 0.163302752293578, 'overall_f1': 0.1365030674846626, 'overall_accuracy': 0.5964553510565781}
			------------EPOCH 5---------------
Loss:  tensor(1815.3475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1625.9196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.2830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1613.9323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1602.9058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.1547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.6678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(481.3900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1505.7292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1384.0664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1423.9301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1749.2012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1107.4565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1311.3142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1580.2058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.6036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.8208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.6317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.6989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.2798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1070.0806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(890.4652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.3196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.4294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1254.9954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(681.1580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.3826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.1053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.4489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.5521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1800.7842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.6409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(927.7060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1363.6324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1042.7368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(681.3561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1198.4089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(850.7034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(726.4225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(767.0900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(865.4399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1146.6628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(868.1501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.1627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.7740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.2557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1549.8691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.1835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.1309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.9834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(755.7098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.9996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1122.0964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(843.7072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1192.1455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1163.3350, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10664335664335664, 'recall': 0.22426470588235295, 'f1': 0.14454976303317535, 'number': 272}, 'P': {'precision': 0.018957345971563982, 'recall': 0.014652014652014652, 'f1': 0.016528925619834708, 'number': 273}, 'overall_precision': 0.08301404853128991, 'overall_recall': 0.11926605504587157, 'overall_f1': 0.09789156626506024, 'overall_accuracy': 0.5877073392410815}
			------------EPOCH 6---------------
Loss:  tensor(1440.5688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1336.9653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.0397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1391.6963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1600.5135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.3412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.0994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.9708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(964.8670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1047.1106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1358.7850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1348.3364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(777.3051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(856.1810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1218.4963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.7903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(901.7123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.3905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.5730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(702.5731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.1504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1163.0378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.8191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.7667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.3207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1132.1693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.6359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.4986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.8669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(748.0784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.9537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1536.3447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(736.5981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.0056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1192.0161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(789.7767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.6932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1115.4667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.4820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.7543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.7933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(986.3011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1223.9113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(947.3718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(652.8226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(786.6084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(484.7012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1714.3667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.8869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.2179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(861.3071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.5222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(896.5945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(790.3341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.5973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(936.3608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1074.5625, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16216216216216217, 'recall': 0.1323529411764706, 'f1': 0.14574898785425103, 'number': 272}, 'P': {'precision': 0.035794183445190156, 'recall': 0.05860805860805861, 'f1': 0.044444444444444446, 'number': 273}, 'overall_precision': 0.07772795216741404, 'overall_recall': 0.09541284403669725, 'overall_f1': 0.08566721581548599, 'overall_accuracy': 0.6112247216541695}
			------------EPOCH 7---------------
Loss:  tensor(1561.4543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1292.2385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(733.4006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1604.3054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1367.8645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(450.0760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.4819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.0413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(887.0468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(926.3862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1145.2632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1096.3348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(549.0519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.2225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(985.6439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.7895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(586.3363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.8304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.5204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(569.8892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.3075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.3785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.1663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.0385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.0941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(714.3541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(443.3104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.8256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.4841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(506.5178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.6790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1395.5962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.6351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.8450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1003.4056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.4352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(572.3252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1195.1179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(800.3547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.7378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.8656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.0096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1164.3708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(705.9452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.8242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.7291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.4420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1225.1385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.1711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.3811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(663.8693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.4982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(825.9142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(724.6366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(748.4573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.3964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(988.5529, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13028764805414553, 'recall': 0.28308823529411764, 'f1': 0.17844727694090387, 'number': 272}, 'P': {'precision': 0.02631578947368421, 'recall': 0.02564102564102564, 'f1': 0.025974025974025976, 'number': 273}, 'overall_precision': 0.09801633605600933, 'overall_recall': 0.15412844036697249, 'overall_f1': 0.11982881597717546, 'overall_accuracy': 0.6171892751647353}
			------------EPOCH 8---------------
Loss:  tensor(1039.4457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(837.9194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.7060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(991.5898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1047.8210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.2018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.1861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.8492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(586.6401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(668.6198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(973.6136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1034.8638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.4330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.8337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(870.7411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.1035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(461.5820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.0754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.1519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.4208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.9019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.6759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.0112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.4593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.0216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(635.6168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.8455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.6878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.8665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.1730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.9927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1129.7566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.0178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.2243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.5081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.1830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.1713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.8630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.7368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(558.8243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.1363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(412.2210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(883.4974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.1484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.4577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.0805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.6114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(857.9921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.9827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.4891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.9434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.1506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.6671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.9785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.9824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.7168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.0049, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1646525679758308, 'recall': 0.4007352941176471, 'f1': 0.23340471092077086, 'number': 272}, 'P': {'precision': 0.13714285714285715, 'recall': 0.08791208791208792, 'f1': 0.10714285714285715, 'number': 273}, 'overall_precision': 0.15890083632019117, 'overall_recall': 0.24403669724770644, 'overall_f1': 0.19247467438494936, 'overall_accuracy': 0.5710633946830266}
			------------EPOCH 9---------------
Loss:  tensor(983.7218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(823.3925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(545.4044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(958.4281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1049.4517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.7979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.6781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.3364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.1419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.6498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(939.5217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.1090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.1257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.2391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(683.3185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.6158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.6213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.0125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.5789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.9298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.2721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.0826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.0485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.7596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(500.9533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.9148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.6751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.6060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.9379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.2616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(913.3245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.0443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.1836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(834.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.4106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.7910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.1323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(759.9395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.9045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.9335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.5789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1020.8074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.1833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.9369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.7471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.8671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(757.6205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.8302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.2757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(566.4314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.4934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.2133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.0096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.6794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.8168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.5483, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1558641975308642, 'recall': 0.3713235294117647, 'f1': 0.21956521739130433, 'number': 272}, 'P': {'precision': 0.10119047619047619, 'recall': 0.06227106227106227, 'f1': 0.07709750566893424, 'number': 273}, 'overall_precision': 0.14460784313725492, 'overall_recall': 0.21651376146788992, 'overall_f1': 0.1734019103600294, 'overall_accuracy': 0.5850374914792092}
			------------EPOCH 10---------------
Loss:  tensor(779.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(665.2321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.0158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1062.5015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.8253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.5312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.6639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(597.3715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1066.2399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1155.3040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.2205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(665.9987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(978.8678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.2661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.9698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(404.4611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.3829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.2115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.1426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.7999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.5273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.1258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.1488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.5143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.7155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.6727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.7413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.2430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.2162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.8381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.7903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.4243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(634.6680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.2068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.5239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(652.0144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.2151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.8047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.3973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.6133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(859.3795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.7953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.1959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.7892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.5828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.0280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.0472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.6580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1013.8694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(565.4512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.1884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.7811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.7196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(802.3578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(619.1894, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14242424242424243, 'recall': 0.17279411764705882, 'f1': 0.15614617940199335, 'number': 272}, 'P': {'precision': 0.09468822170900693, 'recall': 0.15018315018315018, 'f1': 0.11614730878186968, 'number': 273}, 'overall_precision': 0.11533420707732635, 'overall_recall': 0.1614678899082569, 'overall_f1': 0.13455657492354742, 'overall_accuracy': 0.6356509884117246}
			------------EPOCH 11---------------
Loss:  tensor(744.1712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(613.1545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.8438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.5125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.9340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.6869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.7751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.6588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.3825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.5714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(619.5255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.5936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.3478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.9800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.2989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.4790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.0705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.4118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.8272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.5391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.7016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.4955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.8729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.0590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.6695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(951.1257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(545.7076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.5331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.8851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(892.5333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.1254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1368.5660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.1932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(539.7015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1224.6643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1081.1616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.8584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.5046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(616.1560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.5604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.6188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.0615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(635.3784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.8671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.3990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.4566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.9966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.5707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.7641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.6613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.7437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.3377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.8854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.2104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.8891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.2950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(798.6356, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2702702702702703, 'recall': 0.11029411764705882, 'f1': 0.1566579634464752, 'number': 272}, 'P': {'precision': 0.17504332755632582, 'recall': 0.36996336996337, 'f1': 0.23764705882352943, 'number': 273}, 'overall_precision': 0.19040697674418605, 'overall_recall': 0.24036697247706423, 'overall_f1': 0.21248986212489862, 'overall_accuracy': 0.5931606453078846}
			------------EPOCH 12---------------
Loss:  tensor(1567.0385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1137.9319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.7428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1427.9019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(975.7242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.7110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.2244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.1335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(580.0105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.2908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(650.1630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(697.7133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(500.8051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.6886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(662.3364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.3214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.2501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.1683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.9758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.9621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.8793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.1747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.1792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.6494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.9762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.0878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.1695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.8013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.8569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.9156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.1799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.9008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.1627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.7661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(843.5880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(722.3170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.0959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.2268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.6072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.0582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.1093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.2188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(757.8176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.5397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.9266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.5930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.2236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(712.6541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.6586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.2137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.8815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.9127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.0613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.4528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.9610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.3667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.2595, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20045558086560364, 'recall': 0.3235294117647059, 'f1': 0.24753867791842477, 'number': 272}, 'P': {'precision': 0.16445623342175067, 'recall': 0.2271062271062271, 'f1': 0.19076923076923075, 'number': 273}, 'overall_precision': 0.18382352941176472, 'overall_recall': 0.27522935779816515, 'overall_f1': 0.2204261572373255, 'overall_accuracy': 0.6366734832992502}
			------------EPOCH 13---------------
Loss:  tensor(704.9320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.6399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(384.4827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.9452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.4725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.5946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.1724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.1711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.5507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.8046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.0498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(707.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.9060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.4401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.1269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.8983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.7731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.5905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.5086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.7054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.5789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.9436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.7186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.4060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.2969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.0604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.8430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.0808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.8948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.7398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.3763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.2186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.8930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.5778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.8763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.3014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.2224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.1134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.6199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.9865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.3911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.7915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.0150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.0241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.4840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.0993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.9699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.6368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.9690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.9994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.5371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.5128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.5875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.6422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.0894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.4075, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18181818181818182, 'recall': 0.22794117647058823, 'f1': 0.2022838499184339, 'number': 272}, 'P': {'precision': 0.08970976253298153, 'recall': 0.12454212454212454, 'f1': 0.10429447852760737, 'number': 273}, 'overall_precision': 0.13333333333333333, 'overall_recall': 0.1761467889908257, 'overall_f1': 0.15177865612648223, 'overall_accuracy': 0.646955237446035}
			------------EPOCH 14---------------
Loss:  tensor(556.5670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.2933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.0637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.8440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(426.0431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.1800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.7164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.5876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.0599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.6279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.1130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.9416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.4938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.4580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.9604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.6857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.3070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.0834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.4126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.0940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.2006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.1241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.6546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.4415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.2184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.4298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.5419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.6420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.1396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.1662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(468.5699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.2816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.6039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.4798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.5475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.0897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.4256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.9476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.2102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.7623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.5841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.9295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.0914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.9565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.2278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.1298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.9465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.2336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.5992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.1813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.0103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.8003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.4313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.1428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.6964, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1514360313315927, 'recall': 0.21323529411764705, 'f1': 0.17709923664122137, 'number': 272}, 'P': {'precision': 0.1111111111111111, 'recall': 0.1794871794871795, 'f1': 0.13725490196078433, 'number': 273}, 'overall_precision': 0.12985436893203883, 'overall_recall': 0.1963302752293578, 'overall_f1': 0.15631848064280499, 'overall_accuracy': 0.6320722563053851}
			------------EPOCH 15---------------
Loss:  tensor(466.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.5439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.1748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.9392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.4264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.6632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.6938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.6098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.8046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.2442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.4694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.3524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.1523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.6721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.8334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.1614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.6634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.0653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.1378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.7332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.8419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.7620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.9984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.0764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.6200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.4792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.6741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.8738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.4801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.7665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.1436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.5533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.6042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.6753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.2211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.4953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.4608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.0614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.7873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.3888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.5613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.0429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.9303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.2274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.4270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.3992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.8593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.1788, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19658119658119658, 'recall': 0.2536764705882353, 'f1': 0.2215088282504013, 'number': 272}, 'P': {'precision': 0.15165876777251186, 'recall': 0.23443223443223443, 'f1': 0.1841726618705036, 'number': 273}, 'overall_precision': 0.17205692108667528, 'overall_recall': 0.24403669724770644, 'overall_f1': 0.20182094081942337, 'overall_accuracy': 0.6396841626902977}
			------------EPOCH 16---------------
Loss:  tensor(390.2938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.2624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.8687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.8265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.8896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.4648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.6102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.5176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.1779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.4882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.2028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.7626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.8514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.2287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.3052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.2670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.6329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.8243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.6031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.8573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.0923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.1515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.5836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.6719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.2462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.6133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.9856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.7308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.8642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.8821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.6545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.6476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.8037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.1184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.4200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.7396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.4017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.2114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.6350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.3958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.1767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.8168, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19230769230769232, 'recall': 0.23897058823529413, 'f1': 0.21311475409836067, 'number': 272}, 'P': {'precision': 0.12776412776412777, 'recall': 0.19047619047619047, 'f1': 0.15294117647058822, 'number': 273}, 'overall_precision': 0.15704697986577182, 'overall_recall': 0.21467889908256882, 'overall_f1': 0.1813953488372093, 'overall_accuracy': 0.640649852306294}
			------------EPOCH 17---------------
Loss:  tensor(325.4271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.4475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.6203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.8894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.0628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.8682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.5405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.1218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.6802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.6678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.1167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.0518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.2906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.7646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.4551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.7344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.9722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.8455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.2613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.1245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.5008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.7278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.4037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.2549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.2078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.2116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.8604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.2110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.4649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.2439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.1528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.7213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.3764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.7286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.2308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.2503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.9067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.8483, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1685082872928177, 'recall': 0.22426470588235295, 'f1': 0.19242902208201895, 'number': 272}, 'P': {'precision': 0.11894273127753303, 'recall': 0.1978021978021978, 'f1': 0.1485557083906465, 'number': 273}, 'overall_precision': 0.1409313725490196, 'overall_recall': 0.21100917431192662, 'overall_f1': 0.1689933872152829, 'overall_accuracy': 0.6386048625312429}
			------------EPOCH 18---------------
Loss:  tensor(296.5171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.5267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.6086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.6909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.0482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.3611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.6956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.0665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.0736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.6941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.9741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.5595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.6772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.1236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.9058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.6841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.7594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.5158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.3980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.8725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.9965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.0793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.2145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.6447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.5029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.8884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.6692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.3061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.8978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.1320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.7167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.1825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.0762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.1616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.6516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.8729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.1580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.5736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.3925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.3857, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18276762402088773, 'recall': 0.25735294117647056, 'f1': 0.21374045801526717, 'number': 272}, 'P': {'precision': 0.14395886889460155, 'recall': 0.20512820512820512, 'f1': 0.1691842900302115, 'number': 273}, 'overall_precision': 0.16321243523316062, 'overall_recall': 0.23119266055045873, 'overall_f1': 0.19134396355353075, 'overall_accuracy': 0.6344580777096115}
			------------EPOCH 19---------------
Loss:  tensor(292.8344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.0934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.8739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.3783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.2725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.8899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.0907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.8871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.1153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.5458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.1576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.1335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.3334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.2452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.0956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.5971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.4154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.0613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.3961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.5557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.3216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.0924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.5796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.9026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.0655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.8241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.7422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.7165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.9278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.1312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.4478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.5958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.1831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.7533, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21052631578947367, 'recall': 0.2647058823529412, 'f1': 0.23452768729641693, 'number': 272}, 'P': {'precision': 0.13921113689095127, 'recall': 0.21978021978021978, 'f1': 0.17045454545454544, 'number': 273}, 'overall_precision': 0.17076326002587322, 'overall_recall': 0.24220183486238533, 'overall_f1': 0.20030349013657056, 'overall_accuracy': 0.6353669620540786}
			------------EPOCH 20---------------
Loss:  tensor(302.7365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.8302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.9440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.9464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.2443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.6224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.7389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.6571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.9665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.9782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.8428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.3376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.1409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.5891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.4090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.9105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.0687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.1206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.2437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.5404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.9748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.5743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.0503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.0544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.0579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.8753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.0644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.4749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.4632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.3583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.2998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.2463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.7151, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18157894736842106, 'recall': 0.2536764705882353, 'f1': 0.2116564417177914, 'number': 272}, 'P': {'precision': 0.1425233644859813, 'recall': 0.22344322344322345, 'f1': 0.17403708987161198, 'number': 273}, 'overall_precision': 0.1608910891089109, 'overall_recall': 0.23853211009174313, 'overall_f1': 0.19216555801921656, 'overall_accuracy': 0.6261645080663486}
			------------EPOCH 21---------------
Loss:  tensor(289.8877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.5807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.3105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.8022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.9174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.1124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.2004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.5156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.1822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.5716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.0395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.9566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.7195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.1977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.3582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.7079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.6702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.4136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.4618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.7426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.2335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.4566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.2646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.3777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.2883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.2388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.5674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.7248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.5684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.4784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.5384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.8597, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15196078431372548, 'recall': 0.22794117647058823, 'f1': 0.18235294117647058, 'number': 272}, 'P': {'precision': 0.10918114143920596, 'recall': 0.16117216117216118, 'f1': 0.1301775147928994, 'number': 273}, 'overall_precision': 0.13070283600493218, 'overall_recall': 0.1944954128440367, 'overall_f1': 0.15634218289085547, 'overall_accuracy': 0.6250852079072938}
			------------EPOCH 22---------------
Loss:  tensor(264.1809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.3359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.4466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.9374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.7707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.3507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.7839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.9536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.6519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.3639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.2641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.4824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.5491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.1502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.6593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.0587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.5766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.5238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.8809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.9426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.4640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.7326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.0834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.9613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.1972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.1048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.1347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.3969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.2010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.3079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.6342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.2975, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21070234113712374, 'recall': 0.23161764705882354, 'f1': 0.22066549912434325, 'number': 272}, 'P': {'precision': 0.1425438596491228, 'recall': 0.23809523809523808, 'f1': 0.1783264746227709, 'number': 273}, 'overall_precision': 0.1695364238410596, 'overall_recall': 0.23486238532110093, 'overall_f1': 0.19692307692307692, 'overall_accuracy': 0.6410474892069984}
			------------EPOCH 23---------------
Loss:  tensor(259.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.4326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.7846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.8741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.1327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.4854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.1615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.9614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.2322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.4983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.6752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.2417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.1241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.0156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.1120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.5926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.8447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.4278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.2490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.2785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.5561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.7596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.9559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.9427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.3179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.0756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.5098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.4998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.3829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.2759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.4929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.1625, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19623655913978494, 'recall': 0.26838235294117646, 'f1': 0.2267080745341615, 'number': 272}, 'P': {'precision': 0.14832535885167464, 'recall': 0.2271062271062271, 'f1': 0.17945007235890015, 'number': 273}, 'overall_precision': 0.17088607594936708, 'overall_recall': 0.24770642201834864, 'overall_f1': 0.20224719101123598, 'overall_accuracy': 0.641501931379232}
			------------EPOCH 24---------------
Loss:  tensor(195.2017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.1244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.3756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.7251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.4553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.3423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.8645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.0602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.4647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.6194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.9094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.2237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.5399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.4969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.3857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.2040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.5893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.9659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.3255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.6080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.0195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.2817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.6195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.4475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.9473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.6889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.6073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.8659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.4022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.4466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.1789, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19505494505494506, 'recall': 0.2610294117647059, 'f1': 0.22327044025157233, 'number': 272}, 'P': {'precision': 0.16058394160583941, 'recall': 0.24175824175824176, 'f1': 0.19298245614035087, 'number': 273}, 'overall_precision': 0.1767741935483871, 'overall_recall': 0.25137614678899084, 'overall_f1': 0.20757575757575758, 'overall_accuracy': 0.6392865257895933}
			------------EPOCH 25---------------
Loss:  tensor(159.9848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.3221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.2106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.5969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.4668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.5479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.2529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.6136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.3971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.7296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.6344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.2910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.3910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.3498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.2508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.2663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.6319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.0851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.3965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.0443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.3554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.5178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.3026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.8656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.6184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.3382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.8334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.1256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.9737, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19935691318327975, 'recall': 0.22794117647058823, 'f1': 0.21269296740994856, 'number': 272}, 'P': {'precision': 0.12184873949579832, 'recall': 0.21245421245421245, 'f1': 0.1548731642189586, 'number': 273}, 'overall_precision': 0.15247776365946633, 'overall_recall': 0.22018348623853212, 'overall_f1': 0.1801801801801802, 'overall_accuracy': 0.6462735741876846}
			------------EPOCH 26---------------
Loss:  tensor(181.6719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.8988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.7016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.7684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.4118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.1542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.3449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.0911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.7316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.0378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.4832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.0727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.0905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.6473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.9574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.4973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.8627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.7995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.0251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.5463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.0674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.4258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.6593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.6263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.1835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.8600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.8861, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1671018276762402, 'recall': 0.23529411764705882, 'f1': 0.1954198473282443, 'number': 272}, 'P': {'precision': 0.14492753623188406, 'recall': 0.21978021978021978, 'f1': 0.17467248908296948, 'number': 273}, 'overall_precision': 0.15558343789209536, 'overall_recall': 0.22752293577981653, 'overall_f1': 0.18479880774962743, 'overall_accuracy': 0.6305385139740968}
			------------EPOCH 27---------------
Loss:  tensor(172.8487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.0907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.7390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.4555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.4744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.1664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.3061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.8730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.6801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.3631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.0617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.9255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.0993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.4357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.6051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.1864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.9463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.0838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.8853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.7920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.4516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.6380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.1432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.3247, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22330097087378642, 'recall': 0.2536764705882353, 'f1': 0.2375215146299484, 'number': 272}, 'P': {'precision': 0.1743119266055046, 'recall': 0.2783882783882784, 'f1': 0.21438645980253881, 'number': 273}, 'overall_precision': 0.19463087248322147, 'overall_recall': 0.26605504587155965, 'overall_f1': 0.2248062015503876, 'overall_accuracy': 0.6399681890479436}
			------------EPOCH 28---------------
Loss:  tensor(154.7118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.5161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.7670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.9900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.6936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.5744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.8024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.8389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.3088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.3336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.8649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.6771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.4851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.5941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.7993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.9389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.6870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.4527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.9628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.8433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.7927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.0783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.9347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.6910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.8722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.4265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.3444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.9906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.1150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.6313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.1141, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17866666666666667, 'recall': 0.24632352941176472, 'f1': 0.2071097372488408, 'number': 272}, 'P': {'precision': 0.14732142857142858, 'recall': 0.24175824175824176, 'f1': 0.18307905686546466, 'number': 273}, 'overall_precision': 0.16160388821385177, 'overall_recall': 0.24403669724770644, 'overall_f1': 0.19444444444444445, 'overall_accuracy': 0.6378095887298342}
			------------EPOCH 29---------------
Loss:  tensor(147.6328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.7354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.4198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.9474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.7437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.4339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.2375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.7688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.5938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.8612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.5980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.4342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.9295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.4417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.2901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.1944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.0699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.7726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.8391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.2440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.8183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.8021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.8557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.2241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.2176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.6588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.2076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.2141, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18604651162790697, 'recall': 0.23529411764705882, 'f1': 0.2077922077922078, 'number': 272}, 'P': {'precision': 0.11557788944723618, 'recall': 0.1684981684981685, 'f1': 0.13710879284649777, 'number': 273}, 'overall_precision': 0.14824797843665768, 'overall_recall': 0.2018348623853211, 'overall_f1': 0.17094017094017094, 'overall_accuracy': 0.6417291524653488}
			------------EPOCH 30---------------
Loss:  tensor(146.0193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.8353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.8079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.7152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.0420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.6533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.1728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.8961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.8222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.7351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.5282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.1267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.0920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.4121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.4019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.6816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.0552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.9605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.4352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.8630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.7229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.4221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.8659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.6662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.8270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.6435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.5110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.4433, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16666666666666666, 'recall': 0.22426470588235295, 'f1': 0.19122257053291536, 'number': 272}, 'P': {'precision': 0.10560344827586207, 'recall': 0.1794871794871795, 'f1': 0.13297150610583447, 'number': 273}, 'overall_precision': 0.13253012048192772, 'overall_recall': 0.2018348623853211, 'overall_f1': 0.16000000000000003, 'overall_accuracy': 0.6383208361735969}


		-------------RUN 2-----------
			------------EPOCH 1---------------
Loss:  tensor(3366.0562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2532.5400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4053.4727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4180.7266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1434.4364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2829.3687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2765.9519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2314.6943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(841.0864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1854.4502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1715.8032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2857.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3093.5540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3148.6763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2135.0225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2132.9858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1678.6746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1512.3019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1023.7139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2331.9790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1902.4923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2224.7271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1225.5984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1914.3976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1437.8079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1892.4351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2228.9814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2388.1602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2286.8896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2501.2639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1800.4932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2800.6460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1561.6453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1526.5540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3514.9473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2775.1143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1891.9775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1938.4396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3127.9971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1703.8652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2100.7476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1603.4640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1771.1517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2562.0884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2937.1445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1154.6621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.8904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.0153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1758.5811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2256.3726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2654.3562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2669.6650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1653.5754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.5383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1304.8728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2182.5889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2038.7070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1068.8821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1971.4020, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270}, 'P': {'precision': 0.01733477789815818, 'recall': 0.05161290322580645, 'f1': 0.025952960259529603, 'number': 310}, 'overall_precision': 0.01644398766700925, 'overall_recall': 0.027586206896551724, 'overall_f1': 0.020605280103026404, 'overall_accuracy': 0.5682510260823513}
			------------EPOCH 2---------------
Loss:  tensor(1877.4719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1352.2063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2396.2039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2485.5293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(996.2642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2247.1309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2133.8987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1970.7222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.5930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1274.8293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1189.1646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2081.5349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2477.6265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2477.8015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1436.7261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1609.5447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1367.3898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1192.5181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.0171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1784.6633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1445.6416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1844.2150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1008.9579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1695.2800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1325.3226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1723.8463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2084.8047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2186.3931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2083.4375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2260.3428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1452.3547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2438.7683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1367.6222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1335.4379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3265.1433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2463.5557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1617.8044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1583.6719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2671.6008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1478.1956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1872.7122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1398.1755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1560.6206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2347.4873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2730.8960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1036.9614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.9344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(797.1596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1527.2903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1875.1482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2441.4670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2300.6753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1493.3617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(967.1730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1177.2098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1846.7599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1783.0525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(879.8630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1788.2800, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.07142857142857142, 'recall': 0.040740740740740744, 'f1': 0.05188679245283019, 'number': 270}, 'P': {'precision': 0.05328596802841918, 'recall': 0.0967741935483871, 'f1': 0.06872852233676977, 'number': 310}, 'overall_precision': 0.05718270571827057, 'overall_recall': 0.0706896551724138, 'overall_f1': 0.06322282189668466, 'overall_accuracy': 0.6137958427115053}
			------------EPOCH 3---------------
Loss:  tensor(1675.1282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.6595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2152.8169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2216.9702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.9848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1920.9347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2003.4131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1926.3955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.3490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1134.9077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.6523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1859.3322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2249.2944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2120.1140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1184.6603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1380.2858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1214.7285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1009.1046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.5820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1550.4988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1139.5173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1598.1655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.0648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1418.2314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1107.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1333.2555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1622.6724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2000.7075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1874.0991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2004.9696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1366.5847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2081.7068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1169.6113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.9978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3013.3801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2183.9600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1333.5172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1336.2808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2291.3086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1306.3647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1655.8003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1284.2100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1343.3577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2092.2207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2257.9443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(870.5579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(634.5007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(676.3786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1304.1641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1602.8154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1925.1395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1944.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1323.6395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.8108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.1011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1626.1942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1673.6625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(760.2817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1532.9572, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1, 'recall': 0.04814814814814815, 'f1': 0.065, 'number': 270}, 'P': {'precision': 0.054820415879017016, 'recall': 0.0935483870967742, 'f1': 0.06912991656734208, 'number': 310}, 'overall_precision': 0.0637329286798179, 'overall_recall': 0.07241379310344828, 'overall_f1': 0.06779661016949153, 'overall_accuracy': 0.6394810009267841}
			------------EPOCH 4---------------
Loss:  tensor(1490.4498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(883.2111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1853.9817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1816.7854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(678.1580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1526.3403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1505.0762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1332.9086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(483.1774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(957.4691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(919.3575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1584.6154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1833.1770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1819.4010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(906.8276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1057.0236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1092.6599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(826.9932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.8989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1327.4901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(918.1669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1312.0841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(652.8194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1085.2512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(843.8323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.4335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1051.6267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1627.3750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1547.9064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1702.4084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1014.6028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1647.0800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(944.6671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(982.7535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2670.5708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1690.7788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.2184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1155.3423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2089.4556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1288.7581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1329.2007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1042.4540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1253.7375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1832.2600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1821.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.2399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.9880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.5432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1236.0614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1595.4095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1584.0640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1920.7710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1151.1892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(733.7697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(904.6780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1570.7817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1501.4124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.8535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1176.0510, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24107142857142858, 'recall': 0.2, 'f1': 0.21862348178137653, 'number': 270}, 'P': {'precision': 0.20388349514563106, 'recall': 0.2709677419354839, 'f1': 0.23268698060941828, 'number': 310}, 'overall_precision': 0.2169811320754717, 'overall_recall': 0.23793103448275862, 'overall_f1': 0.22697368421052636, 'overall_accuracy': 0.6846286243876605}
			------------EPOCH 5---------------
Loss:  tensor(1230.8082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.0131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1578.9707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1406.4972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(521.5719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1098.1875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1327.5099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.2461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.0117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(846.4452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(804.4337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1301.3665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1676.7830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1667.2388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.5338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(957.1178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.5497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.0837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.6104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1181.2800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(708.7865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1179.1628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.8563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(870.8984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.2661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.4998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.1046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1437.6586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1325.5667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1597.9247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(758.5532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1438.0403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(702.3691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(925.6754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2598.1050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1491.1704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(734.7003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(987.7668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1541.7961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(934.0215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1138.5801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(970.8450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1066.4592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1827.2129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2062.3804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(558.4297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.0655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.3894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1055.5857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1164.7050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1993.7950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1870.3452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1189.2371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.1216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(758.3817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1166.9148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1279.9219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(451.8627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(968.9406, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2601626016260163, 'recall': 0.11851851851851852, 'f1': 0.1628498727735369, 'number': 270}, 'P': {'precision': 0.11896551724137931, 'recall': 0.22258064516129034, 'f1': 0.1550561797752809, 'number': 310}, 'overall_precision': 0.14366998577524892, 'overall_recall': 0.17413793103448275, 'overall_f1': 0.1574434918160561, 'overall_accuracy': 0.679465113200053}
			------------EPOCH 6---------------
Loss:  tensor(1209.1841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.8426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1164.4730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1089.7610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.6258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1000.5916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1283.8079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1156.3370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(412.4105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(917.8645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(887.6644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1419.9214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1832.3232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1747.9659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(858.6030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(966.0364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(868.4025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(585.6202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.6928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1077.3057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.9600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.2551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.9642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.3887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.0792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.9269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.6372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1212.1453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.5396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1204.4939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(799.3717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1268.6204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.5291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.8116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2058.2917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1192.9965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(782.3882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(864.8804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1518.2288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(868.3011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1019.4061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(794.5535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.2469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1417.1847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1458.8447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.9599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.8629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.1118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(873.0289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(849.7107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1325.9661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1328.0746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.9952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(481.6390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.8616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1016.1830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1157.7885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.5565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.7689, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2288135593220339, 'recall': 0.2, 'f1': 0.2134387351778656, 'number': 270}, 'P': {'precision': 0.12854030501089325, 'recall': 0.19032258064516128, 'f1': 0.15344603381014305, 'number': 310}, 'overall_precision': 0.16258992805755396, 'overall_recall': 0.19482758620689655, 'overall_f1': 0.17725490196078433, 'overall_accuracy': 0.6908513173573414}
			------------EPOCH 7---------------
Loss:  tensor(934.7972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.5507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(917.7646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.4277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.0327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(693.7802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1078.7102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(817.3697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.5002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(707.7948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.6251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.7227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1444.0923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1341.6287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.9302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(566.6969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.3813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.4960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.6981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(992.9122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.5519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.7355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.4650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(739.6094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.1090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.1543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.2537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1022.9568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(871.4227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1293.5294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.8981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(986.2529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.3298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(602.0316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1698.7245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(824.3524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.2928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.1030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1070.1357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.0971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.3539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(681.5825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(648.7693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1344.4519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1566.4167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.0165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.9208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.4804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(872.5109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.1207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1509.2983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1524.1738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(965.4920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.9432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.1031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(823.0898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1041.8818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.1971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(744.4147, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26480836236933797, 'recall': 0.2814814814814815, 'f1': 0.2728904847396768, 'number': 270}, 'P': {'precision': 0.1024390243902439, 'recall': 0.13548387096774195, 'f1': 0.11666666666666668, 'number': 310}, 'overall_precision': 0.16929698708751795, 'overall_recall': 0.20344827586206896, 'overall_f1': 0.1848081440877056, 'overall_accuracy': 0.6844300278035218}
			------------EPOCH 8---------------
Loss:  tensor(809.7659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.1848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.9288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(749.0372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.0398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.5349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.4332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.0907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.4813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.3696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.3495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(823.1129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1129.8234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1101.3210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.0301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(461.3573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.3024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.6544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.6947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(769.5752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.4899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(826.9657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.5300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.8160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(613.5421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.0579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.7229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1116.1592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(958.0126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1306.6893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.4535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1033.1721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.4623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(654.1239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2059.9688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(899.5266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.8994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.4731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(986.5490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.7330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.9703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.8478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.5039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1070.5684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1097.0203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.7201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.8590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.8319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(777.1873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.3253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1147.7245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.6082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.9128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.6754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(726.8582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(858.4661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1245.9358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.9457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1223.4755, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1601489757914339, 'recall': 0.31851851851851853, 'f1': 0.21313506815365552, 'number': 270}, 'P': {'precision': 0.1568627450980392, 'recall': 0.025806451612903226, 'f1': 0.0443213296398892, 'number': 310}, 'overall_precision': 0.1598639455782313, 'overall_recall': 0.16206896551724137, 'overall_f1': 0.16095890410958905, 'overall_accuracy': 0.5459420097974315}
			------------EPOCH 9---------------
Loss:  tensor(1388.6819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.2112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1310.7708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1590.6318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(859.5336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1428.6425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.3695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(661.7761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.3020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1040.8655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(872.2844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1017.7739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.4619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.2844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.4338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.7920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.1012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(733.5035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.0268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.6931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.9199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(485.4383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(534.8608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.4755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.0500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(845.5670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(898.6595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1307.7209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.5070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1141.1581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1002.9818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(984.5161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2696.9058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1515.1333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.7442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(776.8582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1421.5154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(999.7673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(886.6345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(858.7222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1016.1160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1233., device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1042.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.7117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.2693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.9068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.0275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.7119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(912.9459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1202.7430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.3734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.5875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.3423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.3778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(895.8810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.4769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.2589, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18267419962335216, 'recall': 0.3592592592592593, 'f1': 0.24219725343320847, 'number': 270}, 'P': {'precision': 0.07317073170731707, 'recall': 0.02903225806451613, 'f1': 0.04157043879907621, 'number': 310}, 'overall_precision': 0.1620795107033639, 'overall_recall': 0.18275862068965518, 'overall_f1': 0.17179902755267423, 'overall_accuracy': 0.5775850655368727}
			------------EPOCH 10---------------
Loss:  tensor(953.8259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.5916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(851.0319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.4084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.4629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(734.5530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1017.0355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(781.0669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.5851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.4835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(654.1940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1082.4943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1313.2693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1612.7991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(342.1221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(850.0386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(749.4524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.7037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1468.6816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.2288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1027.7913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.5013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.0521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.7184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.2587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.0374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(997.7117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.8622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(807.7167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.8867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(801.3417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.3030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.7322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1366.5339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.1796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.2164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.2550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(787.3496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.7179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(586.8237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.7446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.4258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.0071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(894.0669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.2098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.5695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.6535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.2106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.8156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(917.1559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1117.6676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(913.8801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.1333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.5534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(970.2115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1181.4995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.7431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.2216, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3118279569892473, 'recall': 0.21481481481481482, 'f1': 0.2543859649122807, 'number': 270}, 'P': {'precision': 0.13883299798792756, 'recall': 0.22258064516129034, 'f1': 0.17100371747211898, 'number': 310}, 'overall_precision': 0.18594436310395315, 'overall_recall': 0.2189655172413793, 'overall_f1': 0.20110847189231984, 'overall_accuracy': 0.7129617370581226}
			------------EPOCH 11---------------
Loss:  tensor(946.8284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.4310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.4739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.3807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.7091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.1707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.3529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.5706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.5032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(500.4246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.2903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.8591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.8927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.4052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.6320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.2501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.2462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.1870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.5871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.9671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.9782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(504.9999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.7294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.7847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.5338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.8101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.7561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.5695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.5496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.3741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.2134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.6823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.1924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.7073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1142.0410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(525.0981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.8752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.3458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.9922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.0565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.8633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.5415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.3289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.7845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.5381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.3061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.2865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.6194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.3238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.9468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.4447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.1838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.5588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.0591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(749.2042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.6439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.9906, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2857142857142857, 'recall': 0.26666666666666666, 'f1': 0.2758620689655172, 'number': 270}, 'P': {'precision': 0.13973799126637554, 'recall': 0.2064516129032258, 'f1': 0.16666666666666666, 'number': 310}, 'overall_precision': 0.19154929577464788, 'overall_recall': 0.23448275862068965, 'overall_f1': 0.21085271317829457, 'overall_accuracy': 0.7046206805242949}
			------------EPOCH 12---------------
Loss:  tensor(595.8428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.6287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.5111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.5673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.1732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.9330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.6714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.6080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.9355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.2331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.2981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.7828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.9794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.0401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.9005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.7382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.8977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.0056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(545.7166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.4833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.7623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.4424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.9077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.4930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.9596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.6153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.0338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.1839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.1345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.4226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.5250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.5993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.5428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(877.6066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.0581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.2163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.7742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.8745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.9368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.5305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.1072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.2111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.9263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.3336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.7167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.7557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.1605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.5748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.2485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.0163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.7210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.6296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.3921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.5248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.5484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(645.7598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.2936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.6822, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22279792746113988, 'recall': 0.31851851851851853, 'f1': 0.2621951219512195, 'number': 270}, 'P': {'precision': 0.19727891156462585, 'recall': 0.1870967741935484, 'f1': 0.1920529801324503, 'number': 310}, 'overall_precision': 0.21176470588235294, 'overall_recall': 0.2482758620689655, 'overall_f1': 0.2285714285714286, 'overall_accuracy': 0.6876075731497419}
			------------EPOCH 13---------------
Loss:  tensor(499.8732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.9540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.6395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.2000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.2003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.3202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.4213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.3106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.1360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.3374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.8377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.6089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.8631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.6135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.5320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.3409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.1290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.6947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.5934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.7473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.8521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.6640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.3788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.8887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.1013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.9592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.3513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.5031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.0381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.6649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.7677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(760.6309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.0612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.4546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.0057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.4673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.6986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.0839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.8738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.4485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(533.5865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.9139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.4501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.1574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.0870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.4707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.7571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.0885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.4129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.6602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.0457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.4067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.3594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.1040, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23249299719887956, 'recall': 0.3074074074074074, 'f1': 0.2647527910685805, 'number': 270}, 'P': {'precision': 0.20234604105571846, 'recall': 0.22258064516129034, 'f1': 0.2119815668202765, 'number': 310}, 'overall_precision': 0.2177650429799427, 'overall_recall': 0.2620689655172414, 'overall_f1': 0.23787167449139282, 'overall_accuracy': 0.6993247716139283}
			------------EPOCH 14---------------
Loss:  tensor(400.3301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.2722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.7002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.3400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.0372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.7781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.3188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.6087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.9369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.2942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.8675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.7364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.1404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.7613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.9573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.1527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.8342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.0956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.4121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.5158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.7616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.2931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.4549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.1085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.9681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.3186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.8875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.8965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.9775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.8385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.0212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.1586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.7556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.3065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.0946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.7472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.0543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.0538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.1249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.5134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.6196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.9834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.0827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.9364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.1973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.6975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.4854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.1186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.1404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.3561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.9885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.5424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.7695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.9818, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25, 'recall': 0.2851851851851852, 'f1': 0.2664359861591696, 'number': 270}, 'P': {'precision': 0.24561403508771928, 'recall': 0.2709677419354839, 'f1': 0.25766871165644173, 'number': 310}, 'overall_precision': 0.24769230769230768, 'overall_recall': 0.2775862068965517, 'overall_f1': 0.26178861788617885, 'overall_accuracy': 0.71018138488018}
			------------EPOCH 15---------------
Loss:  tensor(338.7659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.9727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.4088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.3044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.8111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.9928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.2981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.7574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.6413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.7350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.0415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(504.8607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.7337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.0105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.2865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.3949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.3291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.3788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.6994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.9309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.3109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.9429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.0589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.8560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.3441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.3276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.0559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.6591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.4130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.8857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.5311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.2668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.3854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.6077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.9576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.0614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.2556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.7467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.3167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.8397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.8353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.8920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.6991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.5487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.5212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.3828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.7823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(573.0232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.7141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.0669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.0942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(568.8688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.9553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.8829, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.265625, 'recall': 0.18888888888888888, 'f1': 0.2207792207792208, 'number': 270}, 'P': {'precision': 0.12738853503184713, 'recall': 0.1935483870967742, 'f1': 0.15364916773367476, 'number': 310}, 'overall_precision': 0.167420814479638, 'overall_recall': 0.19137931034482758, 'overall_f1': 0.17860016090104588, 'overall_accuracy': 0.6999867602277241}
			------------EPOCH 16---------------
Loss:  tensor(321.9849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.4872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.4240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.0391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.8557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.6035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.7711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.7729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.8309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.5543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.7426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.5958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.7711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.6833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.1241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.1242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.6020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.0463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.8872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.2761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.8599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.0140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(748.8691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.2657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.3793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.1194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.4064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1115.1842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.8248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.7962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.1731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.0969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.3031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.5702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.8016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.6616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.5241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.2593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.9735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.2726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.3471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.4056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.0495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.0110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.4414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.5187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.9352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.9576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.7681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.0814, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1518987341772152, 'recall': 0.08888888888888889, 'f1': 0.11214953271028037, 'number': 270}, 'P': {'precision': 0.07507082152974505, 'recall': 0.17096774193548386, 'f1': 0.10433070866141735, 'number': 310}, 'overall_precision': 0.08912037037037036, 'overall_recall': 0.13275862068965516, 'overall_f1': 0.10664819944598337, 'overall_accuracy': 0.6459022904806038}
			------------EPOCH 17---------------
Loss:  tensor(493.6363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.6169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.7335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.9565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.4896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.0525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.3366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.2674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.2499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.3093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(277.3475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.7686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(602.0889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.2624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.4210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.7581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.2787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.3936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.1438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.4646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.1839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.1194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.0641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.5580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.3912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.2329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.0125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.3958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.8817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.0573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.0235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.9245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(682.6051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.5012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.3302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.3173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.6717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.1311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.0961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.1608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.0196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(536.6318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.5518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.6394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.9334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.6899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.5518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.0976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.5373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.2722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.0451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.2378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.3928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.7237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.2148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.4337, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28273809523809523, 'recall': 0.35185185185185186, 'f1': 0.31353135313531355, 'number': 270}, 'P': {'precision': 0.13959390862944163, 'recall': 0.1774193548387097, 'f1': 0.15625000000000003, 'number': 310}, 'overall_precision': 0.2054794520547945, 'overall_recall': 0.25862068965517243, 'overall_f1': 0.22900763358778625, 'overall_accuracy': 0.7135575268105389}
			------------EPOCH 18---------------
Loss:  tensor(313.0609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.5900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.6832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.5738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.1640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.3560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.5332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.6082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.4922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.7759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.9392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.2685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.3958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.0314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.0134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.5780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.3774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.5257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.4364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.7864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.6191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.8070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.5962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.5681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.4034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.6254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.6414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.6929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.7551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.8674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.6546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.9128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.6268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.0685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.1174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.1022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.6215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.9020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.6328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.7469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.7243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.1413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2686, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2968036529680365, 'recall': 0.24074074074074073, 'f1': 0.2658486707566462, 'number': 270}, 'P': {'precision': 0.1797752808988764, 'recall': 0.25806451612903225, 'f1': 0.2119205298013245, 'number': 310}, 'overall_precision': 0.2183734939759036, 'overall_recall': 0.25, 'overall_f1': 0.23311897106109325, 'overall_accuracy': 0.7090560042367271}
			------------EPOCH 19---------------
Loss:  tensor(214.2287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.4497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.2117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.8151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.7896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.5540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.5545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.3649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.5608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.5833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.4678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.8984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.7188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.7593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.5815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.7289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.7306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.5931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.1354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.6473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.8956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.2903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.0400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.2698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.4946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.0523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.4979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.0908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.9342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.8121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.5781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.8097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.1657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.6511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.9873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.4625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.0718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.1007, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26, 'recall': 0.28888888888888886, 'f1': 0.27368421052631575, 'number': 270}, 'P': {'precision': 0.13367609254498714, 'recall': 0.16774193548387098, 'f1': 0.14878397711015737, 'number': 310}, 'overall_precision': 0.18867924528301888, 'overall_recall': 0.22413793103448276, 'overall_f1': 0.2048857368006304, 'overall_accuracy': 0.7144181120084735}
			------------EPOCH 20---------------
Loss:  tensor(185.4332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.4498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.2951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.5477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.7688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.0809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.6456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.9645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.7738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.7511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.9138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.9007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.0859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.1833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.6521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.9818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.5850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.0267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.3277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.8243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.4367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.4519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.2926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.1993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.5986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.2160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.6231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.6379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.5253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.2554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.8494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.6245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.2808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3741, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21621621621621623, 'recall': 0.2962962962962963, 'f1': 0.25, 'number': 270}, 'P': {'precision': 0.13333333333333333, 'recall': 0.16129032258064516, 'f1': 0.145985401459854, 'number': 310}, 'overall_precision': 0.174496644295302, 'overall_recall': 0.22413793103448276, 'overall_f1': 0.19622641509433966, 'overall_accuracy': 0.7056798623063684}
			------------EPOCH 21---------------
Loss:  tensor(191.1889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.3108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.5297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.3208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.1050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.5886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.9094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.1045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.1509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.5697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.3858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.5449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.1178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.3761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.8827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.2548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.7432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.8924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(389.9865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.0816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.2368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.9501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.9319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.0977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.9910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.1215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.5607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.2663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.7803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.5495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.8730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.3252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.0702, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30493273542600896, 'recall': 0.2518518518518518, 'f1': 0.27586206896551724, 'number': 270}, 'P': {'precision': 0.1623931623931624, 'recall': 0.24516129032258063, 'f1': 0.1953727506426735, 'number': 310}, 'overall_precision': 0.20839363241678727, 'overall_recall': 0.2482758620689655, 'overall_f1': 0.22659323367427223, 'overall_accuracy': 0.7173308619091752}
			------------EPOCH 22---------------
Loss:  tensor(194.0960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.9194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.1540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.3899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.4274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.1280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.5010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.0120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.5034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.5651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.6133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.5557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.3973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.4117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.8008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.3385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.4668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.4577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.4316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.0414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.4784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.9828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.6152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.8703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.4948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.2147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.8226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.8870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.5870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.7184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.2407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.1096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.6687, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24281150159744408, 'recall': 0.2814814814814815, 'f1': 0.2607204116638079, 'number': 270}, 'P': {'precision': 0.19113573407202217, 'recall': 0.22258064516129034, 'f1': 0.20566318926974667, 'number': 310}, 'overall_precision': 0.21513353115727002, 'overall_recall': 0.25, 'overall_f1': 0.23125996810207336, 'overall_accuracy': 0.710975771216735}
			------------EPOCH 23---------------
Loss:  tensor(148.2092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.9848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.2006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.5060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.3594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.9412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.6515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.0270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.9227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.1532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.0124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.7326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.7932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.0702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.9060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.9738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.3773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.4971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.5088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.1402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.1893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.8323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.6818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.0205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.7198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.3993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.9329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.6872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.6954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.8810, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23693379790940766, 'recall': 0.2518518518518518, 'f1': 0.24416517055655293, 'number': 270}, 'P': {'precision': 0.13646055437100213, 'recall': 0.2064516129032258, 'f1': 0.16431322207958923, 'number': 310}, 'overall_precision': 0.1746031746031746, 'overall_recall': 0.22758620689655173, 'overall_f1': 0.19760479041916168, 'overall_accuracy': 0.7163378789884814}
			------------EPOCH 24---------------
Loss:  tensor(138.8885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.3264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.2048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.7967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.8414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.7157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.8231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.2946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.4738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.1302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.7814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.5332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.2214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.7325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.8978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.7944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.0284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.0424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.9187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.8406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.3148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.1458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.1180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.6381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.9590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.2142, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25675675675675674, 'recall': 0.2814814814814815, 'f1': 0.26855123674911663, 'number': 270}, 'P': {'precision': 0.18276762402088773, 'recall': 0.22580645161290322, 'f1': 0.20202020202020202, 'number': 310}, 'overall_precision': 0.21502209131075112, 'overall_recall': 0.2517241379310345, 'overall_f1': 0.23193010325655283, 'overall_accuracy': 0.7182576459684893}
			------------EPOCH 25---------------
Loss:  tensor(129.0992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.7206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.5231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.1305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.1491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.6797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.8559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.4101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.0168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.4533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.3348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.9897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.5568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.5850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.2099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.1409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.6488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.3683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.4707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.9247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.9672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.6819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.3514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.1068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.2626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4786, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.27346938775510204, 'recall': 0.24814814814814815, 'f1': 0.2601941747572815, 'number': 270}, 'P': {'precision': 0.16702819956616052, 'recall': 0.24838709677419354, 'f1': 0.19974059662775615, 'number': 310}, 'overall_precision': 0.20396600566572237, 'overall_recall': 0.2482758620689655, 'overall_f1': 0.223950233281493, 'overall_accuracy': 0.7126969416126042}
			------------EPOCH 26---------------
Loss:  tensor(123.4064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.8447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.9105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.1113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.1436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.5651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.9623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.8483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.6993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.3619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.9112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.4618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.9265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.8717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.8146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.9631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.1473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.3044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.5015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.6741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.4192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.7459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.4871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.2058, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2113095238095238, 'recall': 0.26296296296296295, 'f1': 0.23432343234323433, 'number': 270}, 'P': {'precision': 0.1549636803874092, 'recall': 0.2064516129032258, 'f1': 0.17704011065006917, 'number': 310}, 'overall_precision': 0.1802403204272363, 'overall_recall': 0.23275862068965517, 'overall_f1': 0.20316027088036118, 'overall_accuracy': 0.712101151860188}
			------------EPOCH 27---------------
Loss:  tensor(134.9087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.3050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.8194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.3977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.1555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.5383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.1371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.9660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.3719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.7403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.5947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.3289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.9182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.9509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.7030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.0185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.8406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.8181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8788, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25675675675675674, 'recall': 0.2814814814814815, 'f1': 0.26855123674911663, 'number': 270}, 'P': {'precision': 0.18181818181818182, 'recall': 0.22580645161290322, 'f1': 0.2014388489208633, 'number': 310}, 'overall_precision': 0.2143906020558003, 'overall_recall': 0.2517241379310345, 'overall_f1': 0.2315622521808089, 'overall_accuracy': 0.7187872368595261}
			------------EPOCH 28---------------
Loss:  tensor(107.8509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.3097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.6664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.8711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.5495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.1046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.2784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.3978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.7738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.5873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.1960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.8531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.0390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.5781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.1531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.1186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.1060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.8855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.2670, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2693877551020408, 'recall': 0.24444444444444444, 'f1': 0.2563106796116505, 'number': 270}, 'P': {'precision': 0.16877637130801687, 'recall': 0.25806451612903225, 'f1': 0.20408163265306123, 'number': 310}, 'overall_precision': 0.20305980528511822, 'overall_recall': 0.2517241379310345, 'overall_f1': 0.22478829869130101, 'overall_accuracy': 0.7149477028995102}
			------------EPOCH 29---------------
Loss:  tensor(129.8901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.1069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.1547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.6510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.5100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.0525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.1157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.4071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.6517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.3017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.4600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.9727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.2283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.9521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.8879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.4453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.6108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.0645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.2918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.0991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.5484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.3623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0610, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22099447513812154, 'recall': 0.2962962962962963, 'f1': 0.2531645569620253, 'number': 270}, 'P': {'precision': 0.16666666666666666, 'recall': 0.2032258064516129, 'f1': 0.18313953488372092, 'number': 310}, 'overall_precision': 0.19324324324324324, 'overall_recall': 0.24655172413793103, 'overall_f1': 0.21666666666666667, 'overall_accuracy': 0.7037600953263604}
			------------EPOCH 30---------------
Loss:  tensor(193.2065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.7270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.7684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.4426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.3739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.2615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.7162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.4568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.3635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.3014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.8690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.6864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.2668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.4376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.8386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.6310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.3877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.3875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.5947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.8043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.8943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.9020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.3555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.9810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.6287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.0341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.9342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.2411, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2226027397260274, 'recall': 0.24074074074074073, 'f1': 0.2313167259786477, 'number': 270}, 'P': {'precision': 0.15384615384615385, 'recall': 0.2064516129032258, 'f1': 0.1763085399449036, 'number': 310}, 'overall_precision': 0.18220338983050846, 'overall_recall': 0.22241379310344828, 'overall_f1': 0.20031055900621117, 'overall_accuracy': 0.7185224414140077}


		-------------RUN 3-----------
			------------EPOCH 1---------------
Loss:  tensor(1310.4542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1424.7721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5653.8052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3657.0608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2888.5420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3105.3005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1487.7344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1676.6106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1161.9797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1734.9365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2129.3667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2827.6450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1756.3254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2133.2617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3798.8079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1274.5847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1791.6206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3334.7163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2877.3057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2771.6917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2082.8799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2591.5386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1304.5044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1998.1194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1168.2074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1696.7726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2409.0059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2164.2021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1871.2803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1490.0341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1570.5695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1584.9976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2266.4041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1316.8401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1719.9406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2300.5151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2026.6045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1265.8289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2207.7031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1599.1230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1443.2047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1395.3203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2034.9041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1947.9519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1922.6573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1936.4708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2305.9294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1595.3186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2241.7673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2181.4980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2323.3804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1771.9663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1357.1389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2399.0435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2479.8274, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10847457627118644, 'recall': 0.2098360655737705, 'f1': 0.1430167597765363, 'number': 305}, 'P': {'precision': 0.1, 'recall': 0.006006006006006006, 'f1': 0.0113314447592068, 'number': 333}, 'overall_precision': 0.10819672131147541, 'overall_recall': 0.10344827586206896, 'overall_f1': 0.10576923076923077, 'overall_accuracy': 0.484430832057172}
			------------EPOCH 2---------------
Loss:  tensor(763.1453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.1501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3382.9453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2123.6069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1919.5381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2148.6128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(902.8880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1006.8431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.3619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.1647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1350.7048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1635.5776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1211.9716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1431.0232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2538.5283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1073.3462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1308.4961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2488.5188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2137.7910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1863.1238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1515.8176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2171.4001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(964.0142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1690.6055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(908.6179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1350.8213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1967.1217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1648.7252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1478.7427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1190.0574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1288.2341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.9348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1772.2129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(986.6108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1425.9805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1938.2192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1688.7596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1097.6653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1905.8158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1377.8322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.3120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1128.5337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1599.1982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1477.8622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1402.1637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1522.7003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2011.0391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1227.7853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1828.0784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1693.3998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1841.5437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1423.4985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1141.0264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2040.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2044.4171, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14678899082568808, 'recall': 0.31475409836065577, 'f1': 0.20020855057351408, 'number': 305}, 'P': {'precision': 0.05555555555555555, 'recall': 0.003003003003003003, 'f1': 0.005698005698005697, 'number': 333}, 'overall_precision': 0.14434523809523808, 'overall_recall': 0.15203761755485892, 'overall_f1': 0.1480916030534351, 'overall_accuracy': 0.4960183767228178}
			------------EPOCH 3---------------
Loss:  tensor(625.5328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.7391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2989.0061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1818.0250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1544.0579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1854.8665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(761.5564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(849.0457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.7061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(966.0895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1186.4614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1376.0098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1002.6728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1197.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2113.4473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.2333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1071.0925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2076.6489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1896.0300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1578.7439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1235.7119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1860.7208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(777.9918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1560.8934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(779.0300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1157.0137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1759.4266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1452.9077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1268.7273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(998.5115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1140.0122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1007.7500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1436.6843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(781.2305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1194.1812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1698.5685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1405.3960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.7402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1687.5073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1216.2622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1055.0366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.8366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1261.3140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1044.0770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.5930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1200.1785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1626.8170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1044.3937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1608.6882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1455.9426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1615.8257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1171.6436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.8297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1696.8706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1749.5144, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19337016574585636, 'recall': 0.45901639344262296, 'f1': 0.27210884353741494, 'number': 305}, 'P': {'precision': 0.05555555555555555, 'recall': 0.006006006006006006, 'f1': 0.010840108401084009, 'number': 333}, 'overall_precision': 0.1868421052631579, 'overall_recall': 0.2225705329153605, 'overall_f1': 0.20314735336194564, 'overall_accuracy': 0.5057172026544156}
			------------EPOCH 4---------------
Loss:  tensor(507.3986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.8832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2564.1311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1469.1885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1308.6260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1664.7633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.7009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.8879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.0367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(856.4873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1027.2178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1109.5292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(923.7010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1038.9918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1884.9426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(963.2048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(959.6075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1840.1704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1749.1959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1428.4344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1111.6318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1595.4709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.9052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1378.7588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.7294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.2538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1512.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1174.8284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.2047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(814.4590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(948.4054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(850.4411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1247.7920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.5430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1015.9113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1355.6946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1117.5553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(814.4952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1514.6302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.9816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(947.0337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(760.9335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.1736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.5849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.9487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(986.7573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1335.8923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(921.5116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1388.5657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1205.0302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1400.4620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(975.8137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.9487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1378.4746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1476.4576, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17235772357723578, 'recall': 0.3475409836065574, 'f1': 0.23043478260869565, 'number': 305}, 'P': {'precision': 0.2465753424657534, 'recall': 0.10810810810810811, 'f1': 0.1503131524008351, 'number': 333}, 'overall_precision': 0.18659658344283836, 'overall_recall': 0.2225705329153605, 'overall_f1': 0.20300214438884917, 'overall_accuracy': 0.5826442062276672}
			------------EPOCH 5---------------
Loss:  tensor(396.5313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.8288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2198.7117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.1365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1053.1715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1369.2993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.5704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.6323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.7858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(729.8655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(940.3708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1007.4955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.8120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(894.7006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1721.8749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.7307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(840.9553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1617.6150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1664.8960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1408.4647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.5017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1377.9431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.5201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1244.9080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.1852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(845.8310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1292.4690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(936.5177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(933.1497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.7796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(760.9847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(778.2317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1046.4199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.2127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(855.6701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1189.0916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.9908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(739.4149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1443.6102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1037.9738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(831.8009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.1146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.7495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.6655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.3337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.4054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1112.6599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(934.4213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1265.9197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1138.9485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1365.4734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(876.1894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(693.4213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1235.9890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1519.1807, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15849056603773584, 'recall': 0.2754098360655738, 'f1': 0.20119760479041918, 'number': 305}, 'P': {'precision': 0.1437308868501529, 'recall': 0.14114114114114115, 'f1': 0.1424242424242424, 'number': 333}, 'overall_precision': 0.1528588098016336, 'overall_recall': 0.20532915360501566, 'overall_f1': 0.17525083612040132, 'overall_accuracy': 0.6759571209800919}
			------------EPOCH 6---------------
Loss:  tensor(373.4231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.8690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2104.5808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1047.3865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(950.0632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1139.3250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.8191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.9127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.5463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.4866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(870.6097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.0451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.9802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(805.2987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1378.6909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(772.9232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.7999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1513.9530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1474.4814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1227.2371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1102.6094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1454.5719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(491.3870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1067.8397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.7061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1029.2288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1562.4346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1074.6187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(892.9438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.8492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.1027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(898.4792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1042.1533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.6852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.9108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1353.7664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(794.7996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.5781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1075.7917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(828.0553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.3035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.0002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(673.6655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.2983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.8544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(639.1589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1043.0933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(797.1355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(968.1382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(946.4146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1201.0464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.0091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.0837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1066.4995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1241.3707, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.06272401433691756, 'recall': 0.11475409836065574, 'f1': 0.08111239860950173, 'number': 305}, 'P': {'precision': 0.15763546798029557, 'recall': 0.0960960960960961, 'f1': 0.11940298507462688, 'number': 333}, 'overall_precision': 0.08804204993429698, 'overall_recall': 0.10501567398119123, 'overall_f1': 0.09578270192994998, 'overall_accuracy': 0.5947932618683002}
			------------EPOCH 7---------------
Loss:  tensor(406.5258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.0513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2062.8887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1079.1245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1166.2424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1256.7336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.8083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.0689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.3742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(616.8544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(933.3580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(963.5858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.1556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(692.2585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1235.1477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.5411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.0425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1316.9396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1259.4689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(875.9664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(780.4171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1094.3079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.8923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.9414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.2802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.5537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1009.8873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(846.1633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(801.6934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(563.8886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.6716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(683.5220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(913.9357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.7888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.9557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1230.9186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(859.5145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.9662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1072.3025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.8225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(636.5201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.3076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.5814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.7406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.3546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.9464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.1769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(558.7448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(902.8267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(773.9976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1085.2791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(847.3867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.2124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1053.8221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1100.7465, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19964028776978418, 'recall': 0.3639344262295082, 'f1': 0.2578397212543554, 'number': 305}, 'P': {'precision': 0.2283464566929134, 'recall': 0.17417417417417416, 'f1': 0.19761499148211242, 'number': 333}, 'overall_precision': 0.20864197530864198, 'overall_recall': 0.26489028213166144, 'overall_f1': 0.23342541436464087, 'overall_accuracy': 0.669576314446146}
			------------EPOCH 8---------------
Loss:  tensor(227.7072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.0516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1640.3533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(772.8574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(802.7265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(887.6053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.9537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.3565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.1231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.0359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.7087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(663.4330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(716.3176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(975.9458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2023.3938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.3854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.3538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1516.6274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1425.3370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1344.5210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(721.6987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1391.5898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.6448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.4128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.9669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.5992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.3352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.3916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.4182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.0420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.2769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.0364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.5162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.7337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.6017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1198.1493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(883.1743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.7974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1351.1951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(917.7790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.0342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.3513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.8847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.3280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.3535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(848.7140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1338.6660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.5219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(910.1924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.7471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1111.0750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(926.0722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(645.9064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1386.4680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1193.2013, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2011577424023155, 'recall': 0.4557377049180328, 'f1': 0.2791164658634538, 'number': 305}, 'P': {'precision': 0.17687074829931973, 'recall': 0.07807807807807808, 'f1': 0.10833333333333334, 'number': 333}, 'overall_precision': 0.19689737470167065, 'overall_recall': 0.25862068965517243, 'overall_f1': 0.22357723577235775, 'overall_accuracy': 0.591985706993364}
			------------EPOCH 9---------------
Loss:  tensor(226.4887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.4261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1763.0981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(822.5476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.5054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1297.4303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.9215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.8039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.9158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.0754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.1027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.1298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.0051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.1071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.5272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.9664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(943.2228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1049.5957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(938.5624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.1361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1019.2681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.0075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.2092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.4595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(597.3669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(769.8853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.6013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(820.6595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.5497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.5762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.3857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.0250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.9147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.5378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(894.0381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.3017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.1087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(841.1282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(720.8736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.7245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.8754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.2714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.6438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.4686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(558.9142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.5480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.8828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1141.1078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(845.2662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1487.1401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(975.4357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.5471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1379.9636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1481.4330, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23224043715846995, 'recall': 0.2786885245901639, 'f1': 0.25335320417287627, 'number': 305}, 'P': {'precision': 0.2984054669703872, 'recall': 0.3933933933933934, 'f1': 0.3393782383419689, 'number': 333}, 'overall_precision': 0.2683229813664596, 'overall_recall': 0.3385579937304075, 'overall_f1': 0.29937629937629934, 'overall_accuracy': 0.671107708014293}
			------------EPOCH 10---------------
Loss:  tensor(223.7812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.3386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2070.6470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(787.7584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.3365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(884.6307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.2877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.8048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.9300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.2767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.6321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.0771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.2296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.1643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(832.4656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(389.7332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.9510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1189.4788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1262.3143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1180.4434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.5703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1019.3597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.5986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(796.1663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.3006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(598.5642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(876.4283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(870.2627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(765.6783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(569.0353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.4788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(748.6609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.5975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.7932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.4288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(801.4195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.3881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.4248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.9940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(619.2372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(481.4848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.3522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.6623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.8784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.1889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.0056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.8784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.3769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(791.9462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.2954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(901.7742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(665.5036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.1071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(947.5656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(913.7417, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21212121212121213, 'recall': 0.11475409836065574, 'f1': 0.14893617021276598, 'number': 305}, 'P': {'precision': 0.19497784342688332, 'recall': 0.3963963963963964, 'f1': 0.2613861386138614, 'number': 333}, 'overall_precision': 0.19833729216152018, 'overall_recall': 0.2617554858934169, 'overall_f1': 0.22567567567567567, 'overall_accuracy': 0.6505870342011231}
			------------EPOCH 11---------------
Loss:  tensor(261.2638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.2794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1992.3928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.5110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1102.1904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.4398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.6053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.6876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.1018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.4402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(795.2864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(663.2237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.9918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.7059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1047.9602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.9456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.2120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1098.0237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(971.7321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.8781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.2454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(838.3387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.1170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.0382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.0094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.5919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.7735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.2781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.9165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.8379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.7710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.6724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.5510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.0100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.7326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.6136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1054.3937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.4073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.0397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.4445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.6856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.4418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(718.9501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.0591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.0589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.8247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.3801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.2126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(715.6894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(830.4094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.9769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.7129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.5248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(744.9563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(848.6688, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21951219512195122, 'recall': 0.4131147540983607, 'f1': 0.28668941979522183, 'number': 305}, 'P': {'precision': 0.21348314606741572, 'recall': 0.17117117117117117, 'f1': 0.19, 'number': 333}, 'overall_precision': 0.21759809750297265, 'overall_recall': 0.28683385579937304, 'overall_f1': 0.24746450304259635, 'overall_accuracy': 0.6491577335375192}
			------------EPOCH 12---------------
Loss:  tensor(141.0591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1059.6915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(485.8904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(496.2289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(578.4427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.8522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.5296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.1158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.7251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.3089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.9536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.9911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.3669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(572.8442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.7197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.7057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(861.2090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.6210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.0133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.8085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.7758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.0580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.1545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.8806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(461.3184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.2231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(474.5920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.1161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.2706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.3902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(627.1476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.1530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.5413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(578.6334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.2712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.0457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.8137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(468.2877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.4936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.4641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.9794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.1394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.5699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.7090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.9241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.3467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.2358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.3000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.4809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.4390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.2852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.9830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(496.3194, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19932998324958123, 'recall': 0.3901639344262295, 'f1': 0.2638580931263858, 'number': 305}, 'P': {'precision': 0.1572700296735905, 'recall': 0.15915915915915915, 'f1': 0.15820895522388062, 'number': 333}, 'overall_precision': 0.1841541755888651, 'overall_recall': 0.26959247648902823, 'overall_f1': 0.21882951653944022, 'overall_accuracy': 0.6603369065849923}
			------------EPOCH 13---------------
Loss:  tensor(116.9578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.0579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(842.7664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.9599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.8488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.6149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.0809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.4485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.3134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.9319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.3496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.5273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.4215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.7416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.7313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.0184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.3566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(568.6487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(569.7952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.7822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.9972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(590.0156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.1107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.7850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.5152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.8181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.0476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.9445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.1676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.5072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.8156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.1193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.0772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.6943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.3658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.7074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.4847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.9298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.1505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.3870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.5739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.5392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.8842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.4889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.6920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.3169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.7512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.3037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.0122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.2494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.4138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.8027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.8903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.9547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.6006, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21507760532150777, 'recall': 0.3180327868852459, 'f1': 0.25661375661375657, 'number': 305}, 'P': {'precision': 0.22966507177033493, 'recall': 0.2882882882882883, 'f1': 0.255659121171771, 'number': 333}, 'overall_precision': 0.22209436133486765, 'overall_recall': 0.30250783699059564, 'overall_f1': 0.25613802256138024, 'overall_accuracy': 0.695048494129658}
			------------EPOCH 14---------------
Loss:  tensor(77.3444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.8817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(750.4230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.0046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.9627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.6920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.5709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.4443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.9458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.9589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.1947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.0896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.7192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.7921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.4239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.7708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.3123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.1844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.5897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.2261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.6857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.5133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.7948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.8606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.2635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.9125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.7263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.5323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.4358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.2686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.4495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.2893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.5262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.6688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.4573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.2513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.0302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.3971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.5567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.2141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.6238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.0527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.1438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.6225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.4542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.6681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.9501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.9117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.8258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.8252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.9229, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21951219512195122, 'recall': 0.3836065573770492, 'f1': 0.27923627684964203, 'number': 305}, 'P': {'precision': 0.25287356321839083, 'recall': 0.26426426426426425, 'f1': 0.2584434654919237, 'number': 333}, 'overall_precision': 0.23269012485811577, 'overall_recall': 0.3213166144200627, 'overall_f1': 0.2699144173798552, 'overall_accuracy': 0.6753956100051046}
			------------EPOCH 15---------------
Loss:  tensor(65.3778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.2000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(616.9366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.0668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.4430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.2670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.0117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.1540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.8110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.6710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.6709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.7041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.6034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.5471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.2879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.0323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.8806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.3537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(419.4326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.8860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.4046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.0102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.2847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.9280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.0547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.8925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.0425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.9250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.2043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.3709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.8202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.3327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.8292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.5464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.5274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.1068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.7346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.3718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.2686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.7801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.1198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.5496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.0377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.6727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.0654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.2740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.1943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.1641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.8892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.8923, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21169354838709678, 'recall': 0.3442622950819672, 'f1': 0.26217228464419473, 'number': 305}, 'P': {'precision': 0.21182266009852216, 'recall': 0.25825825825825827, 'f1': 0.23274695534506087, 'number': 333}, 'overall_precision': 0.21175166297117518, 'overall_recall': 0.2993730407523511, 'overall_f1': 0.24805194805194805, 'overall_accuracy': 0.6707503828483921}
			------------EPOCH 16---------------
Loss:  tensor(45.8766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.7144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.9006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.5808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.8960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.2491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.6915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.2007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.7041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.9018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.1217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.5051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.9955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.6264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.9079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.6450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.3221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.2238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.9824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.7411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.7875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.4503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.9847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.7265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.3109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.7878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.3399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.2591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.8539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.5317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.3955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.2883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.5393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.4262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.7168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.7614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.7749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.4388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.0794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.1375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.6761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.9280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.8594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.3888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.0443, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18796992481203006, 'recall': 0.32786885245901637, 'f1': 0.23894862604540024, 'number': 305}, 'P': {'precision': 0.155, 'recall': 0.18618618618618618, 'f1': 0.16916780354706684, 'number': 333}, 'overall_precision': 0.17381974248927037, 'overall_recall': 0.25391849529780564, 'overall_f1': 0.20636942675159237, 'overall_accuracy': 0.6739663093415008}
			------------EPOCH 17---------------
Loss:  tensor(42.7895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.0162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.0635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.1877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.9827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.2333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.8228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.5128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.7489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.8176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.7339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.0931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.9970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.0952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.7969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.6808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.5031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.9793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.8737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.3236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.0724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.1103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.1707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.4759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.1453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.6436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.1823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.6728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.3478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.9450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.4457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.8370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.8830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.3310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.0481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.4126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.7706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.5803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.6335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.6824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.0111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.9911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.3598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.5279, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2072936660268714, 'recall': 0.3540983606557377, 'f1': 0.26150121065375304, 'number': 305}, 'P': {'precision': 0.20911528150134048, 'recall': 0.23423423423423423, 'f1': 0.2209631728045326, 'number': 333}, 'overall_precision': 0.2080536912751678, 'overall_recall': 0.29153605015673983, 'overall_f1': 0.2428198433420366, 'overall_accuracy': 0.6758039816232772}
			------------EPOCH 18---------------
Loss:  tensor(33.2788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.7202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.9783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.0450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.1277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.1552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.7019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.2171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.6967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.7955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.9163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.2179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.6925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.5591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.9495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.3809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.8021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.6419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.0922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.4894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.2650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.7826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.1761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.5575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.0862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.5236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.2836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.7253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.9789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.7930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.2188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.4417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.5685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.4107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.6750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.6035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.5136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.8632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.5219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.6131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.4752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.1041, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2575, 'recall': 0.3377049180327869, 'f1': 0.29219858156028367, 'number': 305}, 'P': {'precision': 0.24, 'recall': 0.3063063063063063, 'f1': 0.2691292875989446, 'number': 333}, 'overall_precision': 0.24848484848484848, 'overall_recall': 0.3213166144200627, 'overall_f1': 0.28024606971975397, 'overall_accuracy': 0.6915262889229199}
			------------EPOCH 19---------------
Loss:  tensor(38.5944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.6668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.1508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.3867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.1020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.2207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.2208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.6353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.1520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.3372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.2371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.7983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(372.4683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.6087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.6338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.9173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.3445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.7079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.7599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.0841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.6935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.3676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.2078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.3763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.8168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.9990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.1926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.8554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.5431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.5958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.0705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.8478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.0170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.4528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.2324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.2318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.2720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.7319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.4155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.3464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.5546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.1263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.4533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.6476, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17647058823529413, 'recall': 0.3639344262295082, 'f1': 0.23768736616702357, 'number': 305}, 'P': {'precision': 0.19648093841642228, 'recall': 0.2012012012012012, 'f1': 0.19881305637982197, 'number': 333}, 'overall_precision': 0.18350515463917524, 'overall_recall': 0.27899686520376177, 'overall_f1': 0.22139303482587064, 'overall_accuracy': 0.65895865237366}
			------------EPOCH 20---------------
Loss:  tensor(23.8185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.8348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.2527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.1664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.4616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.7715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.4946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.4239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.3852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.1769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.1283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.1776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.5950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.2419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.9503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.9014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.7501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.4103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.2203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.7503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.8432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.5518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.6552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.9291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.9658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.2891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.0485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.8056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.1126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.1160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.0751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.3105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.3810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.8321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.7065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.6170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.1438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.6000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.4682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.6218, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23774509803921567, 'recall': 0.3180327868852459, 'f1': 0.2720897615708274, 'number': 305}, 'P': {'precision': 0.18614718614718614, 'recall': 0.25825825825825827, 'f1': 0.21635220125786164, 'number': 333}, 'overall_precision': 0.2103448275862069, 'overall_recall': 0.28683385579937304, 'overall_f1': 0.24270557029177722, 'overall_accuracy': 0.7000510464522716}
			------------EPOCH 21---------------
Loss:  tensor(34.0117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.3039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.1370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.6850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.6541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.7764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.6135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.2471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.0321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.8269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.3427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.1103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.3033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.4338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.2338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.9664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.2862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.8733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.8860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.2111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.8446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.8786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.3779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.1006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.1222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.7874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.5873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.7093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.2541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.3588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.0511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.7645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.0345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.4019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.5194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.8331, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22199170124481327, 'recall': 0.35081967213114756, 'f1': 0.2719186785260483, 'number': 305}, 'P': {'precision': 0.205607476635514, 'recall': 0.26426426426426425, 'f1': 0.23127463863337713, 'number': 333}, 'overall_precision': 0.21428571428571427, 'overall_recall': 0.3056426332288401, 'overall_f1': 0.251937984496124, 'overall_accuracy': 0.6918836140888208}
			------------EPOCH 22---------------
Loss:  tensor(17.5938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.3198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.7061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.6358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.7699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.4511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.9887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.2415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.7712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.3204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.6911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.9511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.3329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.7865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.3160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.2385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.3369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.7458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.2693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.0138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.8865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.3623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.7545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.5608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.1068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.9491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.4148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.8598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.0869, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22606924643584522, 'recall': 0.3639344262295082, 'f1': 0.27889447236180903, 'number': 305}, 'P': {'precision': 0.2265625, 'recall': 0.26126126126126126, 'f1': 0.24267782426778242, 'number': 333}, 'overall_precision': 0.22628571428571428, 'overall_recall': 0.3103448275862069, 'overall_f1': 0.26173165895571715, 'overall_accuracy': 0.6874936191934661}
			------------EPOCH 23---------------
Loss:  tensor(13.8500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.8859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.8518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.7816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.3316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.0444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.7642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.0244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.1133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.4720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.1497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.8819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.9346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.0598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.3327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.8299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.6368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.7222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.9280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.9025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.8075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.7756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.0784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.2478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.6733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.6466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.1980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.6346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.5925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.3322, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21414538310412573, 'recall': 0.35737704918032787, 'f1': 0.26781326781326775, 'number': 305}, 'P': {'precision': 0.15990990990990991, 'recall': 0.2132132132132132, 'f1': 0.18275418275418276, 'number': 333}, 'overall_precision': 0.1888772298006296, 'overall_recall': 0.28213166144200624, 'overall_f1': 0.2262727844123193, 'overall_accuracy': 0.6790709545686575}
			------------EPOCH 24---------------
Loss:  tensor(10.8946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.1650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.9902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.5717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.7289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.0640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.2836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.3073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.1956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.8873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.1272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.5298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.0946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.0138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.5340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.5659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.0800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.6953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.9000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.1346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.5758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.2617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.4905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.0360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.1324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.1250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.6177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.3639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.1122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.7215, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24018475750577367, 'recall': 0.34098360655737703, 'f1': 0.2818428184281843, 'number': 305}, 'P': {'precision': 0.22505800464037123, 'recall': 0.2912912912912913, 'f1': 0.25392670157068065, 'number': 333}, 'overall_precision': 0.2326388888888889, 'overall_recall': 0.31504702194357365, 'overall_f1': 0.26764314247669774, 'overall_accuracy': 0.693874425727412}
			------------EPOCH 25---------------
Loss:  tensor(9.0744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.8640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.4615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.9771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.1170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.0465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.0114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.8668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.4309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.8523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.2861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.7934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.6694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.5491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.4656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.1733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.2107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.8062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.2348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.2933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.9798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.1305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.2176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.5210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.7349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.8075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.8619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.8617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.4050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.8535, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2315369261477046, 'recall': 0.380327868852459, 'f1': 0.2878411910669975, 'number': 305}, 'P': {'precision': 0.21518987341772153, 'recall': 0.2552552552552553, 'f1': 0.23351648351648352, 'number': 333}, 'overall_precision': 0.22433035714285715, 'overall_recall': 0.31504702194357365, 'overall_f1': 0.26205997392438074, 'overall_accuracy': 0.6853496681980602}
			------------EPOCH 26---------------
Loss:  tensor(7.7896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.7928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.3595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.9172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.2173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.4415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.0906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.9436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.3023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.1518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.7484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.2278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.9373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.5826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.6289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.3470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.4908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.2719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.9629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.2093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.5544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.5615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.8244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.5118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.3924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.3153, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21292775665399238, 'recall': 0.36721311475409835, 'f1': 0.269554753309266, 'number': 305}, 'P': {'precision': 0.19656019656019655, 'recall': 0.24024024024024024, 'f1': 0.2162162162162162, 'number': 333}, 'overall_precision': 0.2057877813504823, 'overall_recall': 0.30094043887147337, 'overall_f1': 0.2444302991725016, 'overall_accuracy': 0.6778458397141399}
			------------EPOCH 27---------------
Loss:  tensor(6.8318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.9735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.4998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.1460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.8348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.1637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.5247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.2280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.6674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.4577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.8504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.1809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.0457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.9293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.8163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.6925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.9932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.9722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.7163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.2379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.2307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.9854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.4100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.6278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.8856, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2376470588235294, 'recall': 0.33114754098360655, 'f1': 0.27671232876712326, 'number': 305}, 'P': {'precision': 0.23708920187793428, 'recall': 0.3033033033033033, 'f1': 0.26613965744400525, 'number': 333}, 'overall_precision': 0.23736780258519388, 'overall_recall': 0.3166144200626959, 'overall_f1': 0.27132303559435866, 'overall_accuracy': 0.6947932618683001}
			------------EPOCH 28---------------
Loss:  tensor(6.0834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.7931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.8687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.6043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.6981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.7019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.3676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.6401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.0669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.6796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.2442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.1932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.2422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.8655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.3964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.7934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.5121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.7753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.3210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.0808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.6362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.9628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.8575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.4885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.1347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.3102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.6902, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22661122661122662, 'recall': 0.35737704918032787, 'f1': 0.27735368956743006, 'number': 305}, 'P': {'precision': 0.20745920745920746, 'recall': 0.2672672672672673, 'f1': 0.23359580052493437, 'number': 333}, 'overall_precision': 0.2175824175824176, 'overall_recall': 0.3103448275862069, 'overall_f1': 0.25581395348837205, 'overall_accuracy': 0.6841245533435426}
			------------EPOCH 29---------------
Loss:  tensor(5.0573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.4094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.2976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.0272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.1368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.0442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.7898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.0608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.3041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.6031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.5376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.4389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.2395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.8291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.3736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.2666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.9296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.8410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.4253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.6711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.7093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.3892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.0278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.2912, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21669980119284293, 'recall': 0.35737704918032787, 'f1': 0.26980198019801976, 'number': 305}, 'P': {'precision': 0.21890547263681592, 'recall': 0.26426426426426425, 'f1': 0.23945578231292516, 'number': 333}, 'overall_precision': 0.2176795580110497, 'overall_recall': 0.30877742946708464, 'overall_f1': 0.25534672715489304, 'overall_accuracy': 0.6830525778458397}
			------------EPOCH 30---------------
Loss:  tensor(4.2377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.0183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.3259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.8818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.6400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.1038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.1425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.8847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.9269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.8650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.0483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.2628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.2631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.5389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.0415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.3723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.7982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.2352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.7908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.9315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.0073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.4825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.2082, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24824355971896955, 'recall': 0.3475409836065574, 'f1': 0.2896174863387978, 'number': 305}, 'P': {'precision': 0.2300469483568075, 'recall': 0.29429429429429427, 'f1': 0.2582345191040843, 'number': 333}, 'overall_precision': 0.2391559202813599, 'overall_recall': 0.31974921630094044, 'overall_f1': 0.27364185110663986, 'overall_accuracy': 0.692343032159265}


		-------------RUN 4-----------
			------------EPOCH 1---------------
Loss:  tensor(2219.0391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3038.1167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1810.6499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2126.8745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3202.8647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1460.2986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2820.4385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2962.3252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2022.4175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2896.2805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1908.7329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2200.2969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2488.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2583.0586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2108.1140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2245.8276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1145.7722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1599.9543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2103.7678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1412.0298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3258.9912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2516.2515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1914.9729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(997.6207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1186.5461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2155.0308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1559.9469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1395.4005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1615.6733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1628.4783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1810.0397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2743.7944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1933.3916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1051.5281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1396.1807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1246.8611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.4465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.2137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2222.9238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1800.2737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1611.8949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1736.3359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2592.0117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1464.3335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1350.6849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1356.6604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1784.7589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1329.6816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2142.8276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2293.8291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1445.6337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1625.9362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1257.5956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1676.0793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1735.5620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1097.4443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1628.2393, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 207}, 'P': {'precision': 0.07836990595611286, 'recall': 0.08090614886731391, 'f1': 0.07961783439490445, 'number': 309}, 'overall_precision': 0.0681198910081744, 'overall_recall': 0.04844961240310078, 'overall_f1': 0.05662514156285391, 'overall_accuracy': 0.5857167620038135}
			------------EPOCH 2---------------
Loss:  tensor(1487.3805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2350.7708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1139.0905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1322.2062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2252.6025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.8511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1871.8613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2028.1364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1523.3315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2277.5122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1490.0715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1804.4054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2012.7876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1952.1002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1986.2192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1913.4526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(960.2500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1338.0426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1915.9241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1228.3235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2959.8101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2179.3066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1849.5695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(779.6982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(997.6292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1836.1108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1274.2419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1155.8142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1359.4010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1386.0870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1522.0120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2383.5989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1649.7314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(874.8582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1158.1285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1078.5911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(718.5834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(644.9119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2087.2053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1525.4971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1423.2671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1455.2627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2391.1997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1334.8806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1254.6021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1146.3186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1454.8975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1148.8591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1698.1315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1805.4597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1117.9553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1319.5765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1089.1160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1432.2437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1482.7762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.6009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1373.2241, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.045871559633027525, 'recall': 0.024154589371980676, 'f1': 0.03164556962025317, 'number': 207}, 'P': {'precision': 0.16952789699570817, 'recall': 0.255663430420712, 'f1': 0.20387096774193547, 'number': 309}, 'overall_precision': 0.14608695652173914, 'overall_recall': 0.16279069767441862, 'overall_f1': 0.153987167736022, 'overall_accuracy': 0.6681111688912001}
			------------EPOCH 3---------------
Loss:  tensor(1108.1027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1878.4478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.2662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1018.4188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2001.6161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(751.5930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1512.0656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1820.0092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1350.5511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2054.3228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1358.2957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1703.3833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1775.2249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1709.0447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1794.7598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1526.5977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.9174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(970.6722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1545.9696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.4464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2704.3323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1907.7330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1488.0560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(683.1127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.3678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1629.8690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1165.2865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1074.7238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1239.0093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1270.9379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1319.4530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2104.6162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1449.8696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(726.3350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1004.1930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(938.6303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.2263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.3211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1766.5920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1359.8721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1254.8801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1275.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2072.3906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1195.4146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1178.8270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1016.2297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1302.0270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1012.5910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1709.8086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1810.1313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.7034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1220.2269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1055.5875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1264.1541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1337.4878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.3599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1306.5398, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13559322033898305, 'recall': 0.07729468599033816, 'f1': 0.09846153846153846, 'number': 207}, 'P': {'precision': 0.23679060665362034, 'recall': 0.39158576051779936, 'f1': 0.2951219512195122, 'number': 309}, 'overall_precision': 0.2178060413354531, 'overall_recall': 0.2655038759689923, 'overall_f1': 0.2393013100436681, 'overall_accuracy': 0.6820361703357023}
			------------EPOCH 4---------------
Loss:  tensor(928.2653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1544.9100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.7213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(948.3760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1726.7246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.9005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1294.8271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1549.6648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1172.9044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1744.6287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1107.5540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1497.4822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1571.6628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1509.0912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1613.1830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1145.7805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.5183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.6172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1294.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(931.4984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2419.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1664.1141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1289.5792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.8605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(805.1149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1457.5864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1070.4956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(932.8176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1081.6599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1201.6456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1244.6599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1995.8508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1294.5718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(635.5663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(906.3042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(933.4355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.5610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.3888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1674.2986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1251.7693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1101.7188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.6448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1985.6835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1076.9070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1098.6204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(851.7976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1018.4712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.3952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1352.8367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1435.9858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(715.6246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1017.7380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.0581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1119.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1149.1967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.1790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1233.0471, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1793478260869565, 'recall': 0.15942028985507245, 'f1': 0.16879795396419436, 'number': 207}, 'P': {'precision': 0.15993537964458804, 'recall': 0.32038834951456313, 'f1': 0.21336206896551727, 'number': 309}, 'overall_precision': 0.1643835616438356, 'overall_recall': 0.2558139534883721, 'overall_f1': 0.2001516300227445, 'overall_accuracy': 0.6652221644421332}
			------------EPOCH 5---------------
Loss:  tensor(815.3625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1439.0818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(804.1923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(856.6560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1552.4513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.6628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.5649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1493.6702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.5623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1499.9758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(957.8641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1445.3982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1354.3687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1326.1926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1715.1243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.7495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.6240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.1217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1073.8008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(802.3668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2081.0129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1318.4502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1096.6477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.2040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.4713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1325.2808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.4744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(795.9169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(890.5941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1107.8420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1104.1042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1699.7349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1076.2092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.5079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.4520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.8804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.5846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.0931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1459.9504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1165.3180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1022.6697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(911.0111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1727.9661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(950.0890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.5893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(764.7863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.3998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(748.9193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1182.0830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1214.8068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(568.2113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(857.4952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.1609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(979.8357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(994.1863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.8218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.1162, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2132701421800948, 'recall': 0.21739130434782608, 'f1': 0.215311004784689, 'number': 207}, 'P': {'precision': 0.18234165067178504, 'recall': 0.3074433656957929, 'f1': 0.2289156626506024, 'number': 309}, 'overall_precision': 0.1912568306010929, 'overall_recall': 0.2713178294573643, 'overall_f1': 0.22435897435897434, 'overall_accuracy': 0.6751025596579419}
			------------EPOCH 6---------------
Loss:  tensor(721.5880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1159.7898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.0139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(740.5603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1300.8213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.3195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(842.5552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1250.2910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(797.1660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1234.1763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(830.8608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1307.5753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1187.0176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1230.8979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1672.6704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(835.5939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.5304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.9149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1070.3246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.2248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2063.0874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1092.9464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1079.6912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.3638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.5447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1214.2191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(851.2650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(698.7834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.5980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.3356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(894.2891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1383.1853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.0533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(481.9108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(739.5160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(681.4164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.0323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.6847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1381.9607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1137.5327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1033.1456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(917.5352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1843.3602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.0764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(838.5736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.5560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(815.1372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.7716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(936.8336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(942.6307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.9559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(815.2177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.5511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(908.3843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(899.6063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.6345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(944.8326, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19923371647509577, 'recall': 0.25120772946859904, 'f1': 0.2222222222222222, 'number': 207}, 'P': {'precision': 0.2102803738317757, 'recall': 0.2912621359223301, 'f1': 0.24423337856173677, 'number': 309}, 'overall_precision': 0.20609579100145137, 'overall_recall': 0.2751937984496124, 'overall_f1': 0.23568464730290453, 'overall_accuracy': 0.6925521465303056}
			------------EPOCH 7---------------
Loss:  tensor(554.5311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1123.4187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(461.2571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(642.4037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1230.4080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.4557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.4269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1047.4114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.5121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1089.5325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(796.4738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1039.6272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1043.9739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1107.4725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1236.2751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.5121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.2924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.2739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(951.4913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(765.1561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2088.1099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1152.4919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1150.4720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.6158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.9249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1356.9219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(950.2538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.8992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.5152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(654.7963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(939.0805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1549.5762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(858.8010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.3820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.1501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.7722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.2060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.9649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1043.3801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.4518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(861.5377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.6255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.0610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(616.0927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(747.7578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(635.4142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(700.7498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.5824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(893.2772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(911.3989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.4378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(734.2346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.5729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.6410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(976.1763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(594.7164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1249.3777, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10246679316888045, 'recall': 0.2608695652173913, 'f1': 0.14713896457765666, 'number': 207}, 'P': {'precision': 0.07947019867549669, 'recall': 0.038834951456310676, 'f1': 0.05217391304347826, 'number': 309}, 'overall_precision': 0.09734513274336283, 'overall_recall': 0.12790697674418605, 'overall_f1': 0.11055276381909548, 'overall_accuracy': 0.5463107413185416}
			------------EPOCH 8---------------
Loss:  tensor(759.6816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1423.9570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(566.3369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.5952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1362.9700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.1479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.0344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.4839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(705.1691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1203.2793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.7598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(956.1102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(874.7170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(950.2787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.3745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.6616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.1857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.4669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(665.9147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.9470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1800.2302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(800.9976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(880.9338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.1942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.3839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1452.9011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(959.0920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(767.4543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(740.8795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.3453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.6327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1763.3296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(964.4526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.8153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(752.9897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.8433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.1520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.8856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1153.5061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(963.0236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(801.3262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(740.8418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1059.9464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.4108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(560.8376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.4755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(719.7896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(565.5709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(985.1622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(957.1987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.4497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(602.3694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(683.2970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.4542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(714.0981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.6209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(832.8572, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1111111111111111, 'recall': 0.3188405797101449, 'f1': 0.16479400749063672, 'number': 207}, 'P': {'precision': 0.09900990099009901, 'recall': 0.06472491909385113, 'f1': 0.07827788649706459, 'number': 309}, 'overall_precision': 0.10804020100502512, 'overall_recall': 0.16666666666666666, 'overall_f1': 0.13109756097560973, 'overall_accuracy': 0.566764892817935}
			------------EPOCH 9---------------
Loss:  tensor(657.7571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.6720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.0886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(618.7561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1178.1497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.4923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.7415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.2845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(641.1688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.0703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(585.7152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(850.3389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1232.0446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1415.8212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(857.8518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.8071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.0281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.7301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(726.6547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(678.2228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1472.3394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(726.4003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(753.6899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.1683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.3229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(721.6207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.8219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.7073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.9133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.1880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.0585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(957.3420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(572.3859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.5374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.3695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.5641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.4277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.3237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.3124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.0306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(759.9487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.4235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(841.9988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.7264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(592.5231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(629.6101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.5151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.6927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(938.0155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.0371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.5804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(572.7880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.5422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.6135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.5542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.9980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.9379, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17303822937625754, 'recall': 0.41545893719806765, 'f1': 0.2443181818181818, 'number': 207}, 'P': {'precision': 0.16826923076923078, 'recall': 0.11326860841423948, 'f1': 0.13539651837524178, 'number': 309}, 'overall_precision': 0.17163120567375886, 'overall_recall': 0.23449612403100775, 'overall_f1': 0.19819819819819817, 'overall_accuracy': 0.5934015138383313}
			------------EPOCH 10---------------
Loss:  tensor(477.0551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1004.4225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.8757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.9166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(975.5417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.1581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.0826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(994.3359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(463.0298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.3345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(744.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.6677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(878.9991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(928.0651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(678.9222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.1709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.7426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.0853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.5786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.1675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1172.2106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(506.6008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.3840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.9620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.7274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.9594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.9390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.5140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.2638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.1398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.7563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1174.3274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.5020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.8179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.7291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.1608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.1765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.1613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(928.6694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.9414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(533.6852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.0472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(776.2810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.3704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.2452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.1016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.3926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.5425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.4979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.2178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.4879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.9485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.6404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.5615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.7575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.0828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.0367, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19414893617021275, 'recall': 0.3526570048309179, 'f1': 0.2504288164665523, 'number': 207}, 'P': {'precision': 0.10643015521064302, 'recall': 0.1553398058252427, 'f1': 0.12631578947368421, 'number': 309}, 'overall_precision': 0.14631197097944376, 'overall_recall': 0.23449612403100775, 'overall_f1': 0.18019359642591212, 'overall_accuracy': 0.6804183278442248}
			------------EPOCH 11---------------
Loss:  tensor(328.1629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.5671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.0397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.4764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(722.5045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.2493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.1955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.0503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.3164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.0405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.7349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(578.9839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(748.9825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(857.9331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(697.5936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.2375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.3396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.2418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.7824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(503.3927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1275.7756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.9225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(814.6366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.3057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.4794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.8330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.7171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.8090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.0202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.8307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.4565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(831.4139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.2281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.2121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.0812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.7478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.9208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.0542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.2151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.1775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.2961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.1380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.0930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.7242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.9308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.1033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.2850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.4616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.7646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.6592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(478.1286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.9825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(578.4841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(777.0813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.6117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(699.6376, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2074074074074074, 'recall': 0.13526570048309178, 'f1': 0.16374269005847952, 'number': 207}, 'P': {'precision': 0.10610932475884244, 'recall': 0.21359223300970873, 'f1': 0.14178302900107412, 'number': 309}, 'overall_precision': 0.12417437252311757, 'overall_recall': 0.1821705426356589, 'overall_f1': 0.1476826394344069, 'overall_accuracy': 0.6780493441959901}
			------------EPOCH 12---------------
Loss:  tensor(276.3896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(825.1879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.8026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.9958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(920.8303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.5981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.2614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(707.7699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.8531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.2379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.3758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.6600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(414.9708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.3451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.4573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.0836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.3940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.0530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.2010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(798.7040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.9608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.1397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.8428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.6241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.8730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.2681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.5308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.2906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.6770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.3569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(834.6326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.0776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.2995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.3754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.5051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.5649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.1191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.1145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.8861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(485.5041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.6658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.1020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.9553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.3600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.8203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.4920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.8912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.4922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.6520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.1615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.9237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.2849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.4938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.9012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.8750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(450.0828, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18617021276595744, 'recall': 0.16908212560386474, 'f1': 0.17721518987341772, 'number': 207}, 'P': {'precision': 0.13846153846153847, 'recall': 0.2621359223300971, 'f1': 0.18120805369127516, 'number': 309}, 'overall_precision': 0.1500646830530401, 'overall_recall': 0.2248062015503876, 'overall_f1': 0.17998448409619858, 'overall_accuracy': 0.688160859767724}
			------------EPOCH 13---------------
Loss:  tensor(187.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.8904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.5933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.8256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.0364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.9118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.2889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(497.5393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.3948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.7760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.8004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.3046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.0492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.7729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.2085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.9487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.8592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.2253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.8427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(769.5502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.5628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.7073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.8843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.8500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.5021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.0108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.2415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.8904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.6185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.4421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.6975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.2644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.4020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.2121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.8139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.2914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.2268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.8171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.8249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.2014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.6251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.8521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.4585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.6230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.8188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.2196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.9635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.4609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.4124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.8636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.9012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.2941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.9648, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15246636771300448, 'recall': 0.3285024154589372, 'f1': 0.2082695252679939, 'number': 207}, 'P': {'precision': 0.12462908011869436, 'recall': 0.13592233009708737, 'f1': 0.13003095975232196, 'number': 309}, 'overall_precision': 0.140485312899106, 'overall_recall': 0.2131782945736434, 'overall_f1': 0.1693610469591994, 'overall_accuracy': 0.6290518287398162}
			------------EPOCH 14---------------
Loss:  tensor(170.1944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.4120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.7026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.5673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.6569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.3773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.7898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.4117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.9227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.3780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.4747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.1144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(318.1122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.8520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.2501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.2504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.1858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.2776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.4563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(590.6440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.5308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.0422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.0361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.5904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.2712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.9030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.8442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.4581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.6581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.3843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.8999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.4841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.8245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.1452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.0882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.8714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.6769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.5054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.4117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.7810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.3702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.8583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.1199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.1686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.2918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.8561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.5218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.2516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.8354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.3515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.6742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.5222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.5671, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14385964912280702, 'recall': 0.19806763285024154, 'f1': 0.16666666666666666, 'number': 207}, 'P': {'precision': 0.15021459227467812, 'recall': 0.22653721682847897, 'f1': 0.18064516129032257, 'number': 309}, 'overall_precision': 0.1478029294274301, 'overall_recall': 0.21511627906976744, 'overall_f1': 0.17521704814522496, 'overall_accuracy': 0.688680880568556}
			------------EPOCH 15---------------
Loss:  tensor(113.5037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.9978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.2493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.7408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.7924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.4078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.7050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.2823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.5149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.0973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.4244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.3362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.9733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.3341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.4847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.4146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.2539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.1138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.4396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.6350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.9982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.3834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.4225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.7438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.4478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(366.8294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.1135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.1910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.5540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.4203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.6313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.7855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.6006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.2455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.4618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.8273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.7551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.5703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.2864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.3215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.5317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.1793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.3301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.1428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.1539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.0321, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16723549488054607, 'recall': 0.23671497584541062, 'f1': 0.19599999999999998, 'number': 207}, 'P': {'precision': 0.10896309314586995, 'recall': 0.20064724919093851, 'f1': 0.14123006833712984, 'number': 309}, 'overall_precision': 0.12877030162412992, 'overall_recall': 0.21511627906976744, 'overall_f1': 0.16110304789550073, 'overall_accuracy': 0.6833073322932918}
			------------EPOCH 16---------------
Loss:  tensor(67.3535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.5196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.2457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.9898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.7652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.9670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.0767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.6237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.3817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.5275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.6255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.0789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.8268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.7614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.3343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.2253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.1615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.4427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.6816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.9483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.4439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.9749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.0707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.7313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.6267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.9724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.6888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.6722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.4397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.9929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.4080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.9428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.0816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.9218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.7522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.6121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.2845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.8999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.5690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.1240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.3027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.3939, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18339100346020762, 'recall': 0.2560386473429952, 'f1': 0.21370967741935484, 'number': 207}, 'P': {'precision': 0.1368421052631579, 'recall': 0.21035598705501618, 'f1': 0.16581632653061223, 'number': 309}, 'overall_precision': 0.1544502617801047, 'overall_recall': 0.22868217054263565, 'overall_f1': 0.18437499999999998, 'overall_accuracy': 0.6863696770093026}
			------------EPOCH 17---------------
Loss:  tensor(52.3168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.5237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.3747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.0546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.3442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.7008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.9526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.7546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.3186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.3859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.4317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.3109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.1856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.7374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.4280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.7339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.4092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.1225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.6776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.5638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.3347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.0912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.5201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.1530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.2128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.8163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.5062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.0857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.8243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.8698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.3327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.8015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.7285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.6613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.0617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.0639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.9097, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15593220338983052, 'recall': 0.2222222222222222, 'f1': 0.18326693227091634, 'number': 207}, 'P': {'precision': 0.1864801864801865, 'recall': 0.2588996763754045, 'f1': 0.21680216802168023, 'number': 309}, 'overall_precision': 0.17403314917127072, 'overall_recall': 0.2441860465116279, 'overall_f1': 0.2032258064516129, 'overall_accuracy': 0.6790893857976541}
			------------EPOCH 18---------------
Loss:  tensor(42.8025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.3237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.4805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.4837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.3991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.8991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.2547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.6645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.8965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.2365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.8054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.0003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.5681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.7373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.5485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.4018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.1598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.3160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.4648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.7764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.5564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.4764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.5597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.6888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.4142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.2130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.4289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.0169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.2245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.3780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.6463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.9948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.6707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.5574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.9313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.8777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.8966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.0529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.8341, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15, 'recall': 0.21739130434782608, 'f1': 0.17751479289940827, 'number': 207}, 'P': {'precision': 0.13409961685823754, 'recall': 0.22653721682847897, 'f1': 0.1684717208182912, 'number': 309}, 'overall_precision': 0.13990267639902676, 'overall_recall': 0.22286821705426357, 'overall_f1': 0.171898355754858, 'overall_accuracy': 0.6807650083781129}
			------------EPOCH 19---------------
Loss:  tensor(34.6002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.1618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.7575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.3811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.3723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.9863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.0227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.4156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.1987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.1372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.9980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.9050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.4571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.7722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.3441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.3781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.9300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.3148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.8303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.3054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.7534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.5164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.7829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.6352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.8584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.1012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.6531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.2512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.2715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.6079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.4085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.2918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.0437, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1457725947521866, 'recall': 0.24154589371980675, 'f1': 0.18181818181818185, 'number': 207}, 'P': {'precision': 0.17848970251716248, 'recall': 0.2524271844660194, 'f1': 0.20911528150134048, 'number': 309}, 'overall_precision': 0.1641025641025641, 'overall_recall': 0.24806201550387597, 'overall_f1': 0.19753086419753088, 'overall_accuracy': 0.6755648003697926}
			------------EPOCH 20---------------
Loss:  tensor(49.5043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.1835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.8661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.8196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.4606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.9949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.5814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.6823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.8987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.6731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.9579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.7642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.1795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.0228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.9948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.3746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.8980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.9250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.4991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.4051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.0241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.8130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.4087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.5114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.4285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.8881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.3583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.4039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.3379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.0413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.1007, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18055555555555555, 'recall': 0.25120772946859904, 'f1': 0.2101010101010101, 'number': 207}, 'P': {'precision': 0.16559139784946236, 'recall': 0.24919093851132687, 'f1': 0.19896640826873388, 'number': 309}, 'overall_precision': 0.17131474103585656, 'overall_recall': 0.25, 'overall_f1': 0.20330969267139481, 'overall_accuracy': 0.682325070780609}
			------------EPOCH 21---------------
Loss:  tensor(27.0778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.8540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.3689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.2456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.3052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.9983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.8898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.4921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.5497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.4078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.9691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.6641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.9283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.6665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.6072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.8525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.6026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.0823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.5540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.6172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.2318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.3166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.3339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.8717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.6556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.9041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.0089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.2818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.8985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.0746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.7915, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20557491289198607, 'recall': 0.28502415458937197, 'f1': 0.23886639676113358, 'number': 207}, 'P': {'precision': 0.19036697247706422, 'recall': 0.2686084142394822, 'f1': 0.22281879194630874, 'number': 309}, 'overall_precision': 0.19640387275242047, 'overall_recall': 0.2751937984496124, 'overall_f1': 0.22921711057304275, 'overall_accuracy': 0.6841162535390305}
			------------EPOCH 22---------------
Loss:  tensor(18.2385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.8487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.4236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.5987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.9919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.7172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.1865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.5829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.9617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.5585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.6866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.1255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.5637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.1558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.7023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.4609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.0435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.2488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.3133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.0376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.4868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.2697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.1272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.3901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.0466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.5840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.0928, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1806853582554517, 'recall': 0.28019323671497587, 'f1': 0.21969696969696967, 'number': 207}, 'P': {'precision': 0.1328125, 'recall': 0.22006472491909385, 'f1': 0.1656516443361754, 'number': 309}, 'overall_precision': 0.15126050420168066, 'overall_recall': 0.2441860465116279, 'overall_f1': 0.1868050407709414, 'overall_accuracy': 0.6860229964754145}
			------------EPOCH 23---------------
Loss:  tensor(22.3194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.9893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.1422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.5935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.7796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.7472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.5242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.9331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.9041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.8394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.8518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.0850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.6042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.8364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.6191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.5955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.9740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.5884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.5912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.4947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.7350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.8521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.5397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.6580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.2340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.5088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.0528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.4277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.0988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.3403, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14285714285714285, 'recall': 0.20772946859903382, 'f1': 0.16929133858267717, 'number': 207}, 'P': {'precision': 0.1407563025210084, 'recall': 0.2168284789644013, 'f1': 0.17070063694267515, 'number': 309}, 'overall_precision': 0.14157014157014158, 'overall_recall': 0.2131782945736434, 'overall_f1': 0.17014694508894046, 'overall_accuracy': 0.677355983128214}
			------------EPOCH 24---------------
Loss:  tensor(20.0366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.5081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.6242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.5231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.7065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.6512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.3222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.4503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.9235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.7661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.9577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.7594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.3859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.5113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.6235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.8287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.3302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.6073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.6075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.2521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.8443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.7956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.8317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.4557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.5129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.5202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6582, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14950166112956811, 'recall': 0.21739130434782608, 'f1': 0.17716535433070865, 'number': 207}, 'P': {'precision': 0.16033755274261605, 'recall': 0.2459546925566343, 'f1': 0.194125159642401, 'number': 309}, 'overall_precision': 0.15612903225806452, 'overall_recall': 0.23449612403100775, 'overall_f1': 0.18745158791634392, 'overall_accuracy': 0.6801872074882995}
			------------EPOCH 25---------------
Loss:  tensor(22.0873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.2981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.3778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.7365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.6598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.6602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.9660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.6010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.4610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.4358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.3408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.3214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.3814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.9508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.8854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.2217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.0447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.9226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.4827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.0636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.8429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.8211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.4259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.9522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.9200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.6273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.1443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.7505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.1126, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18446601941747573, 'recall': 0.2753623188405797, 'f1': 0.22093023255813954, 'number': 207}, 'P': {'precision': 0.1522633744855967, 'recall': 0.23948220064724918, 'f1': 0.1861635220125786, 'number': 309}, 'overall_precision': 0.16477987421383647, 'overall_recall': 0.25387596899224807, 'overall_f1': 0.1998474446987033, 'overall_accuracy': 0.6795516265095048}
			------------EPOCH 26---------------
Loss:  tensor(18.7398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.2527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.1042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.2313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.9357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.8545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.4100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.0192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.8012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.0284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.8131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.5961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.4242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.8090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.9621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.0261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.4898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.0561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.7143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.4722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.4102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.4834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.7367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.4070, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1597222222222222, 'recall': 0.2222222222222222, 'f1': 0.18585858585858586, 'number': 207}, 'P': {'precision': 0.18834080717488788, 'recall': 0.27184466019417475, 'f1': 0.22251655629139072, 'number': 309}, 'overall_precision': 0.1771117166212534, 'overall_recall': 0.25193798449612403, 'overall_f1': 0.20800000000000002, 'overall_accuracy': 0.6831917721153291}
			------------EPOCH 27---------------
Loss:  tensor(6.9637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.1902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.4394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.0400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.7504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.2338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.7640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.0529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.5323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.5291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.1994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.7298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.7477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.1229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.2280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.8468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.6396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.9938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.9854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.6741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.3036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7567, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14285714285714285, 'recall': 0.21256038647342995, 'f1': 0.170873786407767, 'number': 207}, 'P': {'precision': 0.14770459081836326, 'recall': 0.23948220064724918, 'f1': 0.18271604938271604, 'number': 309}, 'overall_precision': 0.14585908529048208, 'overall_recall': 0.22868217054263565, 'overall_f1': 0.17811320754716983, 'overall_accuracy': 0.6840584734500491}
			------------EPOCH 28---------------
Loss:  tensor(6.1580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.1979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.5107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.4732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.2002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.3103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.7671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.1662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.2308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.6109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.6286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.5869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.2249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.0665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.2622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.8041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.4069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.6441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.1730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.5697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.3215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.4046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.4121, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16149068322981366, 'recall': 0.25120772946859904, 'f1': 0.19659735349716448, 'number': 207}, 'P': {'precision': 0.16367713004484305, 'recall': 0.23624595469255663, 'f1': 0.1933774834437086, 'number': 309}, 'overall_precision': 0.16276041666666666, 'overall_recall': 0.24224806201550386, 'overall_f1': 0.19470404984423675, 'overall_accuracy': 0.6781649043739527}
			------------EPOCH 29---------------
Loss:  tensor(7.7840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.1477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.7013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.2196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.9760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.7439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.6276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.6631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.3783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.1901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.7720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.5357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.4653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.1825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.0508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.9914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.6801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.4680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.9119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.4402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.8024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.0391, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16723549488054607, 'recall': 0.23671497584541062, 'f1': 0.19599999999999998, 'number': 207}, 'P': {'precision': 0.18284424379232506, 'recall': 0.2621359223300971, 'f1': 0.2154255319148936, 'number': 309}, 'overall_precision': 0.1766304347826087, 'overall_recall': 0.25193798449612403, 'overall_f1': 0.20766773162939298, 'overall_accuracy': 0.6842318137169932}
			------------EPOCH 30---------------
Loss:  tensor(6.3137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.7911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.4813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.1188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.5046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.3062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.7173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.2131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.0944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.3763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.7656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.7083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.8295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.2628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.9175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.5961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.0894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.8244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.5694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.7165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.9563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.3200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.7746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3180, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16932907348242812, 'recall': 0.2560386473429952, 'f1': 0.20384615384615387, 'number': 207}, 'P': {'precision': 0.14951456310679612, 'recall': 0.24919093851132687, 'f1': 0.18689320388349512, 'number': 309}, 'overall_precision': 0.1570048309178744, 'overall_recall': 0.25193798449612403, 'overall_f1': 0.19345238095238096, 'overall_accuracy': 0.6793205061535795}


		-------------RUN 5-----------
			------------EPOCH 1---------------
Loss:  tensor(3138.6021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2349.0815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4046.2061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2469.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1498.0825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1093.0503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1782.7863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3222.1641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2568.6812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2039.8728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2090.4321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1607.7124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2413.3730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2476.8293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2281.5054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1484.6680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.4037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1609.4280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1650.7212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1294.5039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2326.8384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1619.0447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1402.3730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1753.2286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1592.9751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2383.3108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2051.4746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1859.1678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1972.6868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1347.5352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2483.8801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(990.0189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2136.9258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1382.3329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1737.0505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2744.1926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1192.5306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1719.9102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1495.8400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1164.1624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2023.9617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2034.9619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2384.5837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1399.7000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1987.9037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1817.4202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1560.4706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1417.5664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1086.1244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1137.7083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(995.7216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1110.7251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1170.8020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2327.8838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2622.1558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1666.3938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1988.1923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1196.7854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(804.6056, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.05555555555555555, 'recall': 0.0391304347826087, 'f1': 0.04591836734693878, 'number': 230}, 'P': {'precision': 0.12742382271468145, 'recall': 0.14556962025316456, 'f1': 0.13589364844903987, 'number': 316}, 'overall_precision': 0.10516252390057361, 'overall_recall': 0.10073260073260074, 'overall_f1': 0.1028999064546305, 'overall_accuracy': 0.6057940706113913}
			------------EPOCH 2---------------
Loss:  tensor(1629.7178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1169.7360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2069.9561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1349.1877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(992.3376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.0679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.1351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2203.5168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1913.3018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1508.9310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1404.1865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1060.2529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1856.5784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2145.8787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2136.4919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1495.0798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(950.7916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1488.2158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1499.9568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1009.6531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1849.6068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1204.2794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1087.0708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1389.2834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1180.2698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1778.5303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1579.5190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1581.3888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1659.4512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1136.3112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2039.0703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(765.1329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1592.1335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1140.8939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1385.4355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2099.2656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(997.6313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1430.8680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1266.5249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(993.2322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1745.2933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1692.4355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2060.3359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1225.1016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1775.0215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1588.3859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1365.5518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1295.3313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(923.2645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(948.0287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(847.0358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(936.4810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(988.8092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1963.9482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2241.7058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1465.2437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1593.0649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(992.4401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.7070, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13829787234042554, 'recall': 0.11304347826086956, 'f1': 0.1244019138755981, 'number': 230}, 'P': {'precision': 0.1792717086834734, 'recall': 0.20253164556962025, 'f1': 0.1901931649331352, 'number': 316}, 'overall_precision': 0.1651376146788991, 'overall_recall': 0.16483516483516483, 'overall_f1': 0.16498625114573787, 'overall_accuracy': 0.6324271128060032}
			------------EPOCH 3---------------
Loss:  tensor(1421.5073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(963.0701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1838.8440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1216.5303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.2767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.9555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1035.2820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1852.9806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1610.6465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1367.3926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1267.4087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.5654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1602.4805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1826.9539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1883.7463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1067.6604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.3005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.3774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1141.3557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(889.4700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1580.4817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1041.9766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(959.5984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1173.6934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(972.6420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1460.9623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1235.9418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1356.8818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1404.0098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(958.6797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1685.3152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(645.3794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1329.7708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1032.5028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1187.1396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1807.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(868.5042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1222.1534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1109.9415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(892.1626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1604.4558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1534.0914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1863.9539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1079.0386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1568.3372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1357.5724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1208.4564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1149.0853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(797.5544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(777.0541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.7090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(788.9233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.1902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1681.8173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1933.8560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1290.1758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1228.8188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(813.0894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.7312, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10497237569060773, 'recall': 0.08260869565217391, 'f1': 0.09245742092457421, 'number': 230}, 'P': {'precision': 0.10163339382940109, 'recall': 0.17721518987341772, 'f1': 0.12918108419838523, 'number': 316}, 'overall_precision': 0.10245901639344263, 'overall_recall': 0.13736263736263737, 'overall_f1': 0.11737089201877934, 'overall_accuracy': 0.645097798007135}
			------------EPOCH 4---------------
Loss:  tensor(1271.6187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.5352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1544.8890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1125.0969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(760.0965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.3683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(860.9276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1522.6833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1369.8646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1256.6564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1097.5115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(856.2696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1385.8772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1621.4379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1694.5745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(694.4963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.7231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(712.6116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(863.8895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(782.6029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1367.5913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(909.7227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(804.9562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(952.3774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.3252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1232.1783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1036.0486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1105.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1200.7395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(802.0942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1319.9187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.8900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.7876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.2820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1006.6368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1525.9241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(758.2003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.1675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(897.2199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.4902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1416.9551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1344.1161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1625.7024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.7449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1481.2817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1176.9502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.6757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(946.4133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.6848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.4384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.6329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.1237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(741.9979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1484.8951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1699.3159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1206.9065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1017.2926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(634.0496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.9819, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22330097087378642, 'recall': 0.2, 'f1': 0.21100917431192662, 'number': 230}, 'P': {'precision': 0.15602836879432624, 'recall': 0.2088607594936709, 'f1': 0.1786197564276049, 'number': 316}, 'overall_precision': 0.178060413354531, 'overall_recall': 0.20512820512820512, 'overall_f1': 0.1906382978723404, 'overall_accuracy': 0.685877721736991}
			------------EPOCH 5---------------
Loss:  tensor(1091.9828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.2265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1219.3950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1013.8733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(682.8455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.0817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(684.9106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1205.1057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.4695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1146.8665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(959.9912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(764.9078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1188.6204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1369.1438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1601.4172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.9976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.4248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.8138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(724.9083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(671.9401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1224.8765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(878.5443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.2745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(805.6429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(703.1663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1003.3058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(989.2122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1000.5319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1000.8416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.4822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.1541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.4592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(834.8881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(834.2301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(855.2780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1335.3759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(655.4442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(829.3822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(759.1632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.8923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1286.7703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1242.7688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1458.6604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(789.9243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1368.8619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.0334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(938.4249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(810.4640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.3789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(549.9169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.3773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.5208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(701.5565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1385.3959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1496.1158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1172.2379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(965.7543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.9553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.8668, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24110671936758893, 'recall': 0.26521739130434785, 'f1': 0.25258799171842655, 'number': 230}, 'P': {'precision': 0.12210526315789473, 'recall': 0.18354430379746836, 'f1': 0.1466498103666245, 'number': 316}, 'overall_precision': 0.16346153846153846, 'overall_recall': 0.21794871794871795, 'overall_f1': 0.18681318681318684, 'overall_accuracy': 0.7024849304957559}
			------------EPOCH 6---------------
Loss:  tensor(947.5568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.1585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.0347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.4501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.1332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.7085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(521.5898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.5017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(951.0839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1058.8828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(825.6364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(636.4685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1094.0884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1323.4927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1477.6096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.6131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.5013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.7719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(624.9414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.2012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1221.6595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(938.3190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.1022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(697.0374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(636.7280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.5812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(898.6426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(830.1852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(865.2241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(586.7848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.3575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.5609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(751.3425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(624.2461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.2563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1240.0286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(576.2947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.2410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.8995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.7318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(967.7087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(964.2664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1296.5005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.9466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1244.0134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.4207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.3282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.9382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(547.1569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.8379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.9238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.8268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.7112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1680.6509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1702.6742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1421.6248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1204.3625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(485.7635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.3972, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14230019493177387, 'recall': 0.3173913043478261, 'f1': 0.19650067294751009, 'number': 230}, 'P': {'precision': 0.14556962025316456, 'recall': 0.07278481012658228, 'f1': 0.0970464135021097, 'number': 316}, 'overall_precision': 0.14307004470938897, 'overall_recall': 0.17582417582417584, 'overall_f1': 0.15776499589153659, 'overall_accuracy': 0.5586172961003814}
			------------EPOCH 7---------------
Loss:  tensor(875.1447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.0742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(928.7926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(798.2064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(412.0654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.1067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.5223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(915.8469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.7498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1063.8074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(737.9345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.4169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1151.6018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1259.2235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1184.6282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.0236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.4064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.0520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.8956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.9344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1237.0598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(960.5874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.1987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.2697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.9053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.9119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1034.0759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(878.3241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(872.8398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.0118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1084.5195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.0879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(843.1591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.6525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.0714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1417.7612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.2911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.5793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.1018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(871.1605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.9030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1496.7422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(610.4251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1039.8677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(866.1211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(763.7496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.5242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.1550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.6211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.7148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.4779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.2263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1205.1523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1259.9272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(895.7068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1128.3914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.0998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.5203, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.150390625, 'recall': 0.3347826086956522, 'f1': 0.20754716981132076, 'number': 230}, 'P': {'precision': 0.2, 'recall': 0.0379746835443038, 'f1': 0.06382978723404255, 'number': 316}, 'overall_precision': 0.1555944055944056, 'overall_recall': 0.163003663003663, 'overall_f1': 0.15921288014311272, 'overall_accuracy': 0.5156845860499446}
			------------EPOCH 8---------------
Loss:  tensor(964.0209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.0863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1127.7417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(857.9866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.4696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(364.9174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(645.3001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1448.0708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(972.3378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1062.1294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(968.9486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.7596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.9857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1244.7236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1016.6129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.6772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.7227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.4626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.7099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.5483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(831.7382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.7793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.4201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(451.5251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.6555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(781.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.8291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(713.2841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(708.3817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.6036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(765.5546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.3669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.9335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.5781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.2642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1213.6638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.4729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(772.0103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.6334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(480.3283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1012.8188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1166.1360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1193.5532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(698.0472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.6333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(885.5294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(813.2457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.1303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.6624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.8278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.4837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.9126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.8927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(962.9410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1287.6824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.7063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.3470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.4962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.7178, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1536643026004728, 'recall': 0.2826086956521739, 'f1': 0.1990811638591118, 'number': 230}, 'P': {'precision': 0.1840277777777778, 'recall': 0.16772151898734178, 'f1': 0.17549668874172186, 'number': 316}, 'overall_precision': 0.1659634317862166, 'overall_recall': 0.21611721611721613, 'overall_f1': 0.1877486077963405, 'overall_accuracy': 0.6668716939352934}
			------------EPOCH 9---------------
Loss:  tensor(710.4169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.5310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.2303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.3015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.9524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.4301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.6154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(722.4457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.2750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(758.5288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(673.7881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.4009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.7876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(947.2673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(835.8901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.9177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.4060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.6219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.5022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.8830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(682.0879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.0941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.8165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.9152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.4830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(847.6837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(646.3547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(650.4343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.7711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.6032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.6702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.3821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(404.1517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.1785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(506.0132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.4624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.3056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.9266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.2809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.5260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.1558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.3719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(921.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.5912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.6217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.3381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.4091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.9636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.0880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.9895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.3471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.6082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.4927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.3944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1061.6733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.5821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.3331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.0526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.5518, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2420091324200913, 'recall': 0.23043478260869565, 'f1': 0.23608017817371937, 'number': 230}, 'P': {'precision': 0.11969111969111969, 'recall': 0.1962025316455696, 'f1': 0.1486810551558753, 'number': 316}, 'overall_precision': 0.1560379918588874, 'overall_recall': 0.21062271062271062, 'overall_f1': 0.1792673421667966, 'overall_accuracy': 0.6945503751999016}
			------------EPOCH 10---------------
Loss:  tensor(733.3454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.5207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.5253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.2695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.8557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.5802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.5389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.5887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.3592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.2750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.2974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.1776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(491.1002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.0582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.9598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.9699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.6412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.4469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.2665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.7641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(503.8344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(536.7335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.3762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.1994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.1197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.3862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.7507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.2172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.7253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.6432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.7391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.8366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.0242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.7708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.3843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(817.9987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.9263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.0446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.4776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.7064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.2797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.5070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.5602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.5201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.7301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.0716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.7107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.4340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.7227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.2024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.6858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.0340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.6229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.9749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(730.1168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.1868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.6218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.6206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.4053, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18888888888888888, 'recall': 0.2956521739130435, 'f1': 0.2305084745762712, 'number': 230}, 'P': {'precision': 0.22039473684210525, 'recall': 0.2120253164556962, 'f1': 0.21612903225806454, 'number': 316}, 'overall_precision': 0.2033132530120482, 'overall_recall': 0.24725274725274726, 'overall_f1': 0.22314049586776863, 'overall_accuracy': 0.6770205437323163}
			------------EPOCH 11---------------
Loss:  tensor(476.3143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.2861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.2027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.6291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.2701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.9165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.6820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.3271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.9521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.7419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(451.4038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.8587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.2859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.3446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.2117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.6501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.0612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.6895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.4979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.9040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.6169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.2948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.6529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.0158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.0205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.8787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.1182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.0260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.9073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.4243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.3718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.3973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.9014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.6385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.3367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.6561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.4657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.1935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.7054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.4798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.3868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.1333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(663.9151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.0880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.6712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.5797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.6624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.9622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.8731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.9049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.9795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.6450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.1400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(668.5974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.1876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.8678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.0989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.8988, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19724770642201836, 'recall': 0.3739130434782609, 'f1': 0.25825825825825827, 'number': 230}, 'P': {'precision': 0.19230769230769232, 'recall': 0.15822784810126583, 'f1': 0.1736111111111111, 'number': 316}, 'overall_precision': 0.19540229885057472, 'overall_recall': 0.2490842490842491, 'overall_f1': 0.21900161030595816, 'overall_accuracy': 0.6578914995694427}
			------------EPOCH 12---------------
Loss:  tensor(401.4141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.9756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.2777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.3968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.1245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.9307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.2740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.7040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.3402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.7682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.2907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.2357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.4524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.1828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.8210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.4545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.2710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.9889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.9385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.0241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(419.2110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.7231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.6105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.3654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.4829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.4651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.1907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.8599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.4812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.7204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.2323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.5591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.2066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.4864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(496.9330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.0453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.9941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.8898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.7275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.0967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.8975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.2739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.5776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.8894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.4282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.2598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.4703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.9090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.4583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.3799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.7251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.6156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(726.8541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.9129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.5144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.1072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.6295, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21172638436482086, 'recall': 0.2826086956521739, 'f1': 0.24208566108007445, 'number': 230}, 'P': {'precision': 0.12401574803149606, 'recall': 0.19936708860759494, 'f1': 0.15291262135922332, 'number': 316}, 'overall_precision': 0.1570552147239264, 'overall_recall': 0.23443223443223443, 'overall_f1': 0.18809698750918444, 'overall_accuracy': 0.7178004674621725}
			------------EPOCH 13---------------
Loss:  tensor(418.1867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.4411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.8745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.3249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.4568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.3861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.8721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.3336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.4030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.4132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.5968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.6623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.4246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.2684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.4031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.8970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.5144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.8644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.1725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.7430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.2065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.8633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.2258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.5692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.8399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.3566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.2339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.1293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.6010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.6952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.7933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.0775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.3710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(506.1565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.4518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.5269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.4138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.4033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.3769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.0330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.8064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.0671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.9736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.0301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.4339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.1894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.4655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.2418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.3932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.6816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.7594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.0857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.6420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.4699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.4983, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2857142857142857, 'recall': 0.1391304347826087, 'f1': 0.18713450292397663, 'number': 230}, 'P': {'precision': 0.2017167381974249, 'recall': 0.2974683544303797, 'f1': 0.24040920716112532, 'number': 316}, 'overall_precision': 0.2179930795847751, 'overall_recall': 0.23076923076923078, 'overall_f1': 0.22419928825622776, 'overall_accuracy': 0.699409521466355}
			------------EPOCH 14---------------
Loss:  tensor(619.4906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.9026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.5930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.4425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.1994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.3967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.7982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.7510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.3972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.3053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.0358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.2807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.5049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.2767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(517.9135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.5655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.7005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.4429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.7156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.2914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.9533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.5958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.0811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.5290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.2733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.1681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.6721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.2881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.1484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.6945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.7885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.6927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.6949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.5041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.8022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.2215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.2012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.9594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.7068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(608.1653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(842.3875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.6664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(734.9806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(448.8607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.0447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.3467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.2618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.1951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.1589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.5077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.7317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.1490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.6246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.1031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.7842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.4070, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.248, 'recall': 0.26956521739130435, 'f1': 0.2583333333333333, 'number': 230}, 'P': {'precision': 0.16704805491990846, 'recall': 0.2310126582278481, 'f1': 0.1938911022576361, 'number': 316}, 'overall_precision': 0.1965065502183406, 'overall_recall': 0.24725274725274726, 'overall_f1': 0.218978102189781, 'overall_accuracy': 0.7279493172591954}
			------------EPOCH 15---------------
Loss:  tensor(339.1683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.5740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.8393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.3085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.2575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.1889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.7292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.3764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.1702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.1136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.6364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.3496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.2142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.9553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.5694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.1108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.4165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.5059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.0353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.1991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.7418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.1475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.7791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.7780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.9862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.0732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.8506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.7633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.7528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.3228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.2310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.0750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.3249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.9455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.0721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.7812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.1388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.0794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.4056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.2991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.9952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.0673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.5559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.6350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.2191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.1398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.3673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.0599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.1982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.0241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.3434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(400.7953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.2174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.4246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.6028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.8816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.1072, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1487603305785124, 'recall': 0.3130434782608696, 'f1': 0.2016806722689076, 'number': 230}, 'P': {'precision': 0.13857677902621723, 'recall': 0.11708860759493671, 'f1': 0.12692967409948544, 'number': 316}, 'overall_precision': 0.14513981358189082, 'overall_recall': 0.19963369963369965, 'overall_f1': 0.16808018504240554, 'overall_accuracy': 0.6457128798130152}
			------------EPOCH 16---------------
Loss:  tensor(434.8510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.1893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.3768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.0749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.9275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.2496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.3285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.0773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.4220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.6696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.9471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.5229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.9167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.3905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.1127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.2956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.8697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.0483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.0821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.7833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.4184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.7498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.9569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.4647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.9175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.7395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.8051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.7495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.4226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.8665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.7971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.4139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.1710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.1339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.3413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.3159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.4868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.2698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.7311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.3309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.7889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.2008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.9662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.4289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.1363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.4456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.3688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.8854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.3391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2736, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24074074074074073, 'recall': 0.22608695652173913, 'f1': 0.23318385650224213, 'number': 230}, 'P': {'precision': 0.18480492813141683, 'recall': 0.2848101265822785, 'f1': 0.224159402241594, 'number': 316}, 'overall_precision': 0.2019914651493599, 'overall_recall': 0.2600732600732601, 'overall_f1': 0.22738190552441956, 'overall_accuracy': 0.7429573133226719}
			------------EPOCH 17---------------
Loss:  tensor(211.9319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.8832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.5613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.5015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.5746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.6491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.7746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.5964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.5454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.8985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.0928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.5165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.8270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.4045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.0526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.9177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.7042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.9229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.3473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.4600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.4679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.8028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.5772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.8046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.7110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.2903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.3197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.8988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.9502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.7329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.2280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.7645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.5095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.8826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.7857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.5901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.0761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9992, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22549019607843138, 'recall': 0.3, 'f1': 0.25746268656716415, 'number': 230}, 'P': {'precision': 0.2016348773841962, 'recall': 0.23417721518987342, 'f1': 0.21669106881405564, 'number': 316}, 'overall_precision': 0.212481426448737, 'overall_recall': 0.2619047619047619, 'overall_f1': 0.23461853978671043, 'overall_accuracy': 0.713125845737483}
			------------EPOCH 18---------------
Loss:  tensor(155.6001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.2570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.5025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.3270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.8736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.7754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.9810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.3574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.4625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.1291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.8455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.5229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.6547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.8330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.2479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.1526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.1350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.4154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.5479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.3876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.5638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.5764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.3323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.4995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.0756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.2880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.7245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.3119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.3684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.7188, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22950819672131148, 'recall': 0.30434782608695654, 'f1': 0.26168224299065423, 'number': 230}, 'P': {'precision': 0.20147420147420148, 'recall': 0.25949367088607594, 'f1': 0.2268326417704011, 'number': 316}, 'overall_precision': 0.21348314606741572, 'overall_recall': 0.2783882783882784, 'overall_f1': 0.24165341812400637, 'overall_accuracy': 0.7156476811415918}
			------------EPOCH 19---------------
Loss:  tensor(132.5201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.6469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.0103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.5224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.2726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.4258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.0209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.6301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.1029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.0553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.9010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.1038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.3845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.7511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.4730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.0521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.2200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.2952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.8466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.1981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.4159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.8419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.1697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.7811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.6180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3425, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22258064516129034, 'recall': 0.3, 'f1': 0.25555555555555554, 'number': 230}, 'P': {'precision': 0.21680216802168023, 'recall': 0.25316455696202533, 'f1': 0.23357664233576644, 'number': 316}, 'overall_precision': 0.21944035346097202, 'overall_recall': 0.27289377289377287, 'overall_f1': 0.24326530612244898, 'overall_accuracy': 0.7150325993357116}
			------------EPOCH 20---------------
Loss:  tensor(118.2807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.4809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.0074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.2059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.4317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.7529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.0937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.3129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.4475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.4664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.5025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.1406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.1366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.8648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.5247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.7413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.6079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.0563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.6840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.8111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.5488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.5491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.1822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.1430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.7637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.9309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4155, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.250936329588015, 'recall': 0.29130434782608694, 'f1': 0.2696177062374245, 'number': 230}, 'P': {'precision': 0.16735537190082644, 'recall': 0.2563291139240506, 'f1': 0.2025, 'number': 316}, 'overall_precision': 0.1970705725699068, 'overall_recall': 0.27106227106227104, 'overall_f1': 0.22821896684656898, 'overall_accuracy': 0.7387132488620987}
			------------EPOCH 21---------------
Loss:  tensor(107.8915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.1752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.7345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.4699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.5399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.9359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.5277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.8348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.8499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.9647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.4820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.5218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.0247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.8450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.4153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.3522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.9077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.9519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.9614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.8402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.9606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.9112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3274, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20615384615384616, 'recall': 0.29130434782608694, 'f1': 0.24144144144144145, 'number': 230}, 'P': {'precision': 0.20054945054945056, 'recall': 0.2310126582278481, 'f1': 0.2147058823529412, 'number': 316}, 'overall_precision': 0.20319303338171263, 'overall_recall': 0.2564102564102564, 'overall_f1': 0.22672064777327933, 'overall_accuracy': 0.7106040103333744}
			------------EPOCH 22---------------
Loss:  tensor(109.4461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.6109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.6075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.3546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.5056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.0427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.4886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.5377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.5971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.8056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.0133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.2051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.8244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.7521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.0629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.5595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.6880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.5553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.0505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.5863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.5274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.0300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.7103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.4037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.9727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8634, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18696883852691218, 'recall': 0.28695652173913044, 'f1': 0.22641509433962265, 'number': 230}, 'P': {'precision': 0.19873817034700317, 'recall': 0.19936708860759494, 'f1': 0.1990521327014218, 'number': 316}, 'overall_precision': 0.1925373134328358, 'overall_recall': 0.23626373626373626, 'overall_f1': 0.21217105263157893, 'overall_accuracy': 0.699040472382827}
			------------EPOCH 23---------------
Loss:  tensor(96.0926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.9242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.4025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.6072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.4460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.9243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.8937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.4672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.3407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.9604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.7672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.7846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.7966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.4380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.3227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.8207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.8150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.2154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.6483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.0997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.4347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.1205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.7086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.2157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.4461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1929, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26605504587155965, 'recall': 0.25217391304347825, 'f1': 0.2589285714285714, 'number': 230}, 'P': {'precision': 0.13948919449901767, 'recall': 0.22468354430379747, 'f1': 0.17212121212121212, 'number': 316}, 'overall_precision': 0.17744154057771663, 'overall_recall': 0.23626373626373626, 'overall_f1': 0.20267085624509035, 'overall_accuracy': 0.7317628244556525}
			------------EPOCH 24---------------
Loss:  tensor(133.1280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.8668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.1463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.2143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.3594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.9140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.1280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.2200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.1675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.3098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.9075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.3075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.9110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.9492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.7516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.7207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.2655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.3829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.9676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.9296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.9884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.3589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.1363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.2329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.8218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.9675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.8822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9797, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23863636363636365, 'recall': 0.3652173913043478, 'f1': 0.288659793814433, 'number': 230}, 'P': {'precision': 0.18478260869565216, 'recall': 0.21518987341772153, 'f1': 0.19883040935672516, 'number': 316}, 'overall_precision': 0.2111111111111111, 'overall_recall': 0.2783882783882784, 'overall_f1': 0.2401263823064771, 'overall_accuracy': 0.7186615819904048}
			------------EPOCH 25---------------
Loss:  tensor(99.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.4393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.8369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.5418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.6975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.4332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.7919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.1575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.9574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.0086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.7116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.6401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.7527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.1953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.7101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.0690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.4822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.2030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.3538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.1391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.3441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.4645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.7087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.0189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2596, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22916666666666666, 'recall': 0.28695652173913044, 'f1': 0.2548262548262548, 'number': 230}, 'P': {'precision': 0.21428571428571427, 'recall': 0.2563291139240506, 'f1': 0.23342939481268013, 'number': 316}, 'overall_precision': 0.22072072072072071, 'overall_recall': 0.2692307692307692, 'overall_f1': 0.24257425742574254, 'overall_accuracy': 0.7280108254397835}
			------------EPOCH 26---------------
Loss:  tensor(94.5187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.3702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.5738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.8052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9250, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.7516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.4169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.6274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.2108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.8431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.4155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.7640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.7797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.7841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.8991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.7703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.4915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.8770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.6417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.3645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.2122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.8183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.7012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5040, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20189274447949526, 'recall': 0.2782608695652174, 'f1': 0.23400365630712977, 'number': 230}, 'P': {'precision': 0.17336683417085427, 'recall': 0.21835443037974683, 'f1': 0.19327731092436976, 'number': 316}, 'overall_precision': 0.18601398601398603, 'overall_recall': 0.24358974358974358, 'overall_f1': 0.21094369547977795, 'overall_accuracy': 0.7234592200762702}
			------------EPOCH 27---------------
Loss:  tensor(96.0492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.3039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.6826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.4276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.1372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.7350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.8163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.1115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.5074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.0516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.8167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.2951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.7536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0684, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2540322580645161, 'recall': 0.27391304347826084, 'f1': 0.2635983263598326, 'number': 230}, 'P': {'precision': 0.17634408602150536, 'recall': 0.25949367088607594, 'f1': 0.20998719590268886, 'number': 316}, 'overall_precision': 0.20336605890603085, 'overall_recall': 0.26556776556776557, 'overall_f1': 0.23034154090548056, 'overall_accuracy': 0.7401279370156231}
			------------EPOCH 28---------------
Loss:  tensor(76.9291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.6554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.0392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.7256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.3129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.6588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.0677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.9794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.6248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.2093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.2566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.1630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.2246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.0362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.9533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9349, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19642857142857142, 'recall': 0.28695652173913044, 'f1': 0.23321554770318023, 'number': 230}, 'P': {'precision': 0.17403314917127072, 'recall': 0.19936708860759494, 'f1': 0.18584070796460178, 'number': 316}, 'overall_precision': 0.18481375358166188, 'overall_recall': 0.23626373626373626, 'overall_f1': 0.2073954983922829, 'overall_accuracy': 0.7146020420715955}
			------------EPOCH 29---------------
Loss:  tensor(73.3796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.1186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.4063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.3967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.8683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.6794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.2385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.5562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.5895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.0663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.1322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.9526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.8858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.0667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.7497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.7496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.6202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4177, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25925925925925924, 'recall': 0.27391304347826084, 'f1': 0.26638477801268495, 'number': 230}, 'P': {'precision': 0.17802197802197803, 'recall': 0.2563291139240506, 'f1': 0.21011673151750973, 'number': 316}, 'overall_precision': 0.20630372492836677, 'overall_recall': 0.26373626373626374, 'overall_f1': 0.23151125401929262, 'overall_accuracy': 0.7427112806003199}
			------------EPOCH 30---------------
Loss:  tensor(71.4560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.9650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.9927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.3277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.9561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.0089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.0327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.4613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.8734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.0220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.2523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.6422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.9262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.8257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0072, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21140939597315436, 'recall': 0.27391304347826084, 'f1': 0.23863636363636365, 'number': 230}, 'P': {'precision': 0.16341463414634147, 'recall': 0.2120253164556962, 'f1': 0.18457300275482094, 'number': 316}, 'overall_precision': 0.18361581920903955, 'overall_recall': 0.23809523809523808, 'overall_f1': 0.20733652312599682, 'overall_accuracy': 0.7245663673268544}
	Train size: 50 Test size: 50


		-------------RUN 1-----------
			------------EPOCH 1---------------
Loss:  tensor(1884.1414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3293.5828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1671.3113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2734.7705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3102.8608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2793.3303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3134.9829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3561.7795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2013.6493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1923.3906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1446.4070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1498.8392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1229.9888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2234.8352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1565.3298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.3582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1677.8042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1653.8474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3076.6641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3104.4138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1731.2388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2565.7847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2206.7720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1692.6683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1364.8047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1531.0859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1748.0916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2258.5330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(875.5789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2354.3589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2025.8774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1242.9124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1685.6753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1176.5193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1532.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1382.2816, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.06371191135734072, 'recall': 0.09299191374663072, 'f1': 0.07561643835616437, 'number': 742}, 'P': {'precision': 0.14665249734325186, 'recall': 0.17579617834394903, 'f1': 0.15990730011587484, 'number': 785}, 'overall_precision': 0.10227272727272728, 'overall_recall': 0.13555992141453832, 'overall_f1': 0.11658687693607435, 'overall_accuracy': 0.5290964623070855}
			------------EPOCH 2---------------
Loss:  tensor(1224.1238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1938.8817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.2819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1746.7351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2347.3672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1940.0056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2352.1440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2748.5342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1640.5027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1472.6602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1030.4907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1144.7195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1164.9114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2255.5132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1399.1493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(767.2499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1269.8862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1348.4204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2586.7559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2272.8484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1446.3364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2111.2058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1911.0608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1431.7080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1197.8862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1325.2576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1560.7793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2041.4280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.0598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2243.2007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1964.4514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1113.1903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1520.2927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1010.9340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1324.7601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1306.8555, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.016643550624133148, 'recall': 0.016172506738544475, 'f1': 0.016404647983595356, 'number': 742}, 'P': {'precision': 0.1110236220472441, 'recall': 0.17961783439490445, 'f1': 0.13722627737226276, 'number': 785}, 'overall_precision': 0.07684580612757408, 'overall_recall': 0.10019646365422397, 'overall_f1': 0.0869812393405344, 'overall_accuracy': 0.5677501567588341}
			------------EPOCH 3---------------
Loss:  tensor(1125.1656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1616.7917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(783.5571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1519.1675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1888.3661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1452.8932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2130.3684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2301.8994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1437.8273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1307.5701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.2953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(978.7422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1023.7974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1947.7297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1171.3649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(676.6746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1110.6333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1167.8792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2303.2815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2075.6924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1300.6699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1868.5410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1715.3947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1347.6311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1048.7961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1137.0269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1218.7546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1745.5328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(622.8247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1830.9965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1633.6323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(934.8831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1263.8008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.7109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1174.6106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.7441, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.06561679790026247, 'recall': 0.1347708894878706, 'f1': 0.08826125330979699, 'number': 742}, 'P': {'precision': 0.13266239707227814, 'recall': 0.18471337579617833, 'f1': 0.15441959531416402, 'number': 785}, 'overall_precision': 0.09361864730607566, 'overall_recall': 0.160445317616241, 'overall_f1': 0.11824324324324326, 'overall_accuracy': 0.6023989158356763}
			------------EPOCH 4---------------
Loss:  tensor(954.2621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1327.2848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.9344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1275.2332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1649.5781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1244.4470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1795.3317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2054.3188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1260.8813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1153.3621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(739.2401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(826.5746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.9810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1782.1387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(922.4900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.1279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(968.6339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(997.2736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2019.2599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1861.6415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1087.0575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1539.9126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1458.5637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1135.8389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(887.2164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(981.8380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1027.9968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1576.5850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.3148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1552.7926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1425.1805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(781.1899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.0232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(758.7246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(986.6052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(962.8671, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.07108498129342597, 'recall': 0.1792452830188679, 'f1': 0.10179869881362417, 'number': 742}, 'P': {'precision': 0.11812865497076024, 'recall': 0.1286624203821656, 'f1': 0.12317073170731709, 'number': 785}, 'overall_precision': 0.08584005869405723, 'overall_recall': 0.15324165029469547, 'overall_f1': 0.11003997178462262, 'overall_accuracy': 0.5931552013592508}
			------------EPOCH 5---------------
Loss:  tensor(831.3936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1029.2515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.3389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(994.7825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1436.9452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.1683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1476.4343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1805.6479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1092.5586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(963.2087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(574.2365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(652.0457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(802.6133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1565.1221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(717.3171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(415.6164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(815.8723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(788.0506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1638.1841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1616.7756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.0006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1252.8069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1182.6198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.8809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.7452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.4545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(787.7004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1418.0284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.4688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1294.6525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1205.9280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(650.4641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(840.1714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(613.2424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.1815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(842.1041, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.08883693746347165, 'recall': 0.20485175202156333, 'f1': 0.1239298817774154, 'number': 742}, 'P': {'precision': 0.1471264367816092, 'recall': 0.16305732484076432, 'f1': 0.15468277945619338, 'number': 785}, 'overall_precision': 0.1084850833010461, 'overall_recall': 0.183366077275704, 'overall_f1': 0.13631937682570594, 'overall_accuracy': 0.6280871376848237}
			------------EPOCH 6---------------
Loss:  tensor(705.5009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.8713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.6239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(722.6013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1108.8562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.5933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1187.6033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1477.0122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(900.7830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.8839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.6436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.1849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(613.3782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1147.5814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.8078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.7086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(655.4165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.5405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1313.9045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1421.8276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.1337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1039.7449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.9988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.6011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.3849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(863.4335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(775.2846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1418.8932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.5369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1003.0188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.5384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.5408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(662.6872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.3615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.8711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.2897, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.06880733944954129, 'recall': 0.2223719676549865, 'f1': 0.1050955414012739, 'number': 742}, 'P': {'precision': 0.04559270516717325, 'recall': 0.01910828025477707, 'f1': 0.026929982046678635, 'number': 785}, 'overall_precision': 0.066006600660066, 'overall_recall': 0.11787819253438114, 'overall_f1': 0.0846262341325811, 'overall_accuracy': 0.5966140091830336}
			------------EPOCH 7---------------
Loss:  tensor(766.2349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(891.3522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.2534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(742.2967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1326.8506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1091.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1230.8882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1595.1188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.6383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(583.9537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.8688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.4122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.3456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(944.6018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.4832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.6958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.9609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.8575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1248.2964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1324.9946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.1398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(894.8137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(692.0542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.6975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.6168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.0159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.9888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1180.9664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(906.9974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.3148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(506.8243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(601.1443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.7883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.2859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.9781, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10011709601873536, 'recall': 0.23045822102425875, 'f1': 0.13959183673469386, 'number': 742}, 'P': {'precision': 0.16365824308062576, 'recall': 0.1732484076433121, 'f1': 0.1683168316831683, 'number': 785}, 'overall_precision': 0.1209137455691217, 'overall_recall': 0.20104780615586115, 'overall_f1': 0.15100836202656173, 'overall_accuracy': 0.6358947389712575}
			------------EPOCH 8---------------
Loss:  tensor(551.2509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.2880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.2372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.3419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.4337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.4022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1105.8127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(751.3452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.0432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.3799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.5468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.5543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.5725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.2985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.8673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.4915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(652.4525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1594.5938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1618.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(781.1615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1233.3184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.8703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(643.6797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.1181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.7708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.7928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(964.1227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.8289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.0468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(764.0734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.8264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(861.5699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(523.1855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(967.2594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(817.3711, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15991902834008098, 'recall': 0.10646900269541779, 'f1': 0.12783171521035597, 'number': 742}, 'P': {'precision': 0.2218284904323175, 'recall': 0.39872611464968155, 'f1': 0.28506375227686703, 'number': 785}, 'overall_precision': 0.2057742782152231, 'overall_recall': 0.25671250818598557, 'overall_f1': 0.22843822843822842, 'overall_accuracy': 0.5718359999190922}
			------------EPOCH 9---------------
Loss:  tensor(996.5786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(904.5189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.7288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(944.7651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1335.7046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1661.6398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1586.3823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(735.1817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(676.8976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.9002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.8201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.8202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(737.9896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.1769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.8958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.5666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.4357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(932.1083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1101.2312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(805.8361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1246.2809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.0767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(748.4971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.2433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(638.6439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(506.9267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1071.1750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.2515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1036.4879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1132.8268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.7414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(742.5981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.9534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(451.6687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(631.3715, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11604938271604938, 'recall': 0.12668463611859837, 'f1': 0.1211340206185567, 'number': 742}, 'P': {'precision': 0.09387121799844841, 'recall': 0.15414012738853503, 'f1': 0.11668273866923819, 'number': 785}, 'overall_precision': 0.10242972844211529, 'overall_recall': 0.14079895219384414, 'overall_f1': 0.11858797573083286, 'overall_accuracy': 0.6498108780517405}
			------------EPOCH 10---------------
Loss:  tensor(564.7383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.1138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.8223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.7534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(790.4553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.9388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(946.3456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(986.7117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.9980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.6363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.9883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.7955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.0790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.5504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.4075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.4801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.8029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.4975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(840.1995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1015.7462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.5013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(749.6945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.3233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.8267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.9283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.1624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.2968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(947.9468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.7376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(779.5981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(760.9271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.9685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(541.6418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.9557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.1383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.4506, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18337850045167117, 'recall': 0.27358490566037735, 'f1': 0.21957815035154135, 'number': 742}, 'P': {'precision': 0.222117202268431, 'recall': 0.29936305732484075, 'f1': 0.2550189907759089, 'number': 785}, 'overall_precision': 0.2023094688221709, 'overall_recall': 0.2868369351669941, 'overall_f1': 0.23726977248104011, 'overall_accuracy': 0.6473431905985153}
			------------EPOCH 11---------------
Loss:  tensor(463.5041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.6978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.6249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.7610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(578.1033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.9517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(661.0477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(865.9862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.3176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(412.1031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.5507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.3451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.9624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(514.2314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.1987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.4533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.2056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.4249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(688.5078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(883.9084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.0760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(668.7506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.2760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.2231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.9016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.6552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.0291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.1885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.4287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.8593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.2721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.8157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.8884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.6958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.0728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.1552, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12375, 'recall': 0.2668463611859838, 'f1': 0.1690862510674637, 'number': 742}, 'P': {'precision': 0.19581151832460733, 'recall': 0.23821656050955414, 'f1': 0.21494252873563216, 'number': 785}, 'overall_precision': 0.1506849315068493, 'overall_recall': 0.25212835625409297, 'overall_f1': 0.18863302302792748, 'overall_accuracy': 0.6401423977022189}
			------------EPOCH 12---------------
Loss:  tensor(324.3150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.8808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.2957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.0717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.4423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.2176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.9344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(657.9954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.7949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.9862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.0970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.3577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.5120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.7770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.5738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.9948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.8380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.9527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(474.1599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(659.5062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.0668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.4134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.8167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.2641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.5441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.6904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(583.0845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(330.7321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(443.4829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.1793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.1490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.3210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.3995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.7027, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15875, 'recall': 0.1711590296495957, 'f1': 0.1647211413748379, 'number': 742}, 'P': {'precision': 0.16085578446909668, 'recall': 0.2585987261146497, 'f1': 0.1983390327308256, 'number': 785}, 'overall_precision': 0.1600387972841901, 'overall_recall': 0.21611001964636542, 'overall_f1': 0.1838952354416272, 'overall_accuracy': 0.6616638686057565}
			------------EPOCH 13---------------
Loss:  tensor(272.2805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.3706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.9887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.7992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.9323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.3194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.8517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(444.5779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.9062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.3752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.0175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.6224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.4412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.2829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.6376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.1319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.9031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(615.6066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.7348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.5983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.6946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.8945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.2867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.3708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.8658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.0972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.4133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.9298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.5786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.5854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.8348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.2581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.9482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.1151, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15031645569620253, 'recall': 0.2560646900269542, 'f1': 0.18943170488534397, 'number': 742}, 'P': {'precision': 0.19528301886792454, 'recall': 0.26369426751592356, 'f1': 0.22439024390243903, 'number': 785}, 'overall_precision': 0.17082616179001722, 'overall_recall': 0.2599869024230517, 'overall_f1': 0.20618021293170605, 'overall_accuracy': 0.6643742794150367}
			------------EPOCH 14---------------
Loss:  tensor(198.1513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.6748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.5034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.1645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.9510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.1512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.8507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.6344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.9694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.3606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.3860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.2669, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.0510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(288.2532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.6165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.5560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.4362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.5562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.9212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(516.3937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.2614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.3079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.1319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.2686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.2225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.1935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.3737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.1734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.1912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.9301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.1791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.2855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.1281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.2026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.3689, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16959669079627715, 'recall': 0.2210242587601078, 'f1': 0.1919251023990638, 'number': 742}, 'P': {'precision': 0.18120805369127516, 'recall': 0.2751592356687898, 'f1': 0.21851289833080423, 'number': 785}, 'overall_precision': 0.17600741083835109, 'overall_recall': 0.24885396201702684, 'overall_f1': 0.20618556701030927, 'overall_accuracy': 0.6719391573454155}
			------------EPOCH 15---------------
Loss:  tensor(154.4761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.9273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.7143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.8945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.7360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.4954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.8411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.6894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.1441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.5475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.1332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.2838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.3134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.2219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.0840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.9627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(462.9653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.0102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.8933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.2803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.0376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.6510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.9174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.4242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.1831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.7818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.4212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.2077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.6364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.8478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.7643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.3595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.7349, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1671794871794872, 'recall': 0.2196765498652291, 'f1': 0.18986604542807223, 'number': 742}, 'P': {'precision': 0.14071146245059288, 'recall': 0.2267515923566879, 'f1': 0.17365853658536584, 'number': 785}, 'overall_precision': 0.15223214285714284, 'overall_recall': 0.22331368696791093, 'overall_f1': 0.18104592513936818, 'overall_accuracy': 0.6663969740488278}
			------------EPOCH 16---------------
Loss:  tensor(121.3806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.3660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.3470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.6167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.2317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.7879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.3506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.7365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.4313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.1073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.2368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.9668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.9273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.9320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.8498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.6772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.5710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.4325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.4160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.6216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.4759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.9361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.3317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.4530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.9262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.7205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.1861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.3685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.2549, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1656441717791411, 'recall': 0.25471698113207547, 'f1': 0.2007434944237918, 'number': 742}, 'P': {'precision': 0.16856060606060605, 'recall': 0.2267515923566879, 'f1': 0.19337316675719718, 'number': 785}, 'overall_precision': 0.1670459717796996, 'overall_recall': 0.24034053700065489, 'overall_f1': 0.1970998925886144, 'overall_accuracy': 0.6625538542446247}
			------------EPOCH 17---------------
Loss:  tensor(95.0572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.3143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.0744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.0348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.8254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.1625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.7294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.5409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.9966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.4421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.2678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.6647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.2346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.5640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.9845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.2533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.1875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.6289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.4216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.8953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.2131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.3149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.3769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.6176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.8232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.8713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(358.3967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.9865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.7066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.9264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2281, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1829393627954779, 'recall': 0.2398921832884097, 'f1': 0.20758017492711367, 'number': 742}, 'P': {'precision': 0.16951788491446346, 'recall': 0.27770700636942675, 'f1': 0.2105263157894737, 'number': 785}, 'overall_precision': 0.1752988047808765, 'overall_recall': 0.2593320235756385, 'overall_f1': 0.20919175911251983, 'overall_accuracy': 0.6571330326260645}
			------------EPOCH 18---------------
Loss:  tensor(81.2280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.9227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.4773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(292.9444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.5208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.5910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.4330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.9904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.9914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.7849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.6006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.5267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.7794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.3857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.0391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.5402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.1558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.9586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.5394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.3834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.1664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.0385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.7155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.9937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.1839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0425, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17106652587117213, 'recall': 0.2183288409703504, 'f1': 0.19182948490230906, 'number': 742}, 'P': {'precision': 0.14147130153597412, 'recall': 0.2229299363057325, 'f1': 0.1730959446092977, 'number': 785}, 'overall_precision': 0.1543040293040293, 'overall_recall': 0.22069417157825802, 'overall_f1': 0.18162220425761252, 'overall_accuracy': 0.6672465057950201}
			------------EPOCH 19---------------
Loss:  tensor(68.6802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.8789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.1690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.0594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.2699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.0454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.5686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.1363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.5578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.9333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.3317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.1538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.5801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.1357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.9422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.7954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.8634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.1039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.8086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.1366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.8274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2419, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16982836495031617, 'recall': 0.25336927223719674, 'f1': 0.20335316387236343, 'number': 742}, 'P': {'precision': 0.16394849785407725, 'recall': 0.24331210191082803, 'f1': 0.1958974358974359, 'number': 785}, 'overall_precision': 0.16681338028169015, 'overall_recall': 0.24819908316961362, 'overall_f1': 0.19952619110292183, 'overall_accuracy': 0.6660935698537592}
			------------EPOCH 20---------------
Loss:  tensor(50.1257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.8675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.7432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.0853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.2381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.9893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.4404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.0486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.0175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.1391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.6655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.4831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.9608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.4518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.7300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.6262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.9237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.1529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.5918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.5626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.1576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.0510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.7824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.7013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3748, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1945945945945946, 'recall': 0.24258760107816713, 'f1': 0.21595680863827235, 'number': 742}, 'P': {'precision': 0.1746031746031746, 'recall': 0.2802547770700637, 'f1': 0.21515892420537897, 'number': 785}, 'overall_precision': 0.18306636155606407, 'overall_recall': 0.26195153896529144, 'overall_f1': 0.21551724137931036, 'overall_accuracy': 0.6565059972895891}
			------------EPOCH 21---------------
Loss:  tensor(40.0485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.0537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.5766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.4758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.8084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.4344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.0530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.2264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.4300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.3814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.6860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.2984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(319.4213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.4395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.5184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.6288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.5996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.8530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.8856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.3343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.5346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.3077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.0728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6603, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16248839368616527, 'recall': 0.2358490566037736, 'f1': 0.19241341396371633, 'number': 742}, 'P': {'precision': 0.1478405315614618, 'recall': 0.2267515923566879, 'f1': 0.17898441427853193, 'number': 785}, 'overall_precision': 0.15475668566418238, 'overall_recall': 0.2311722331368697, 'overall_f1': 0.18539915966386555, 'overall_accuracy': 0.6675903638827646}
			------------EPOCH 22---------------
Loss:  tensor(35.1556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.1498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.8628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.0285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.1232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.4532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.0664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.9953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.5729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.9081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.2595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.0712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.1889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.6344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.9857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.0346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.7982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.1151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.7539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.9951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.6053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.2788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0643, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1921182266009852, 'recall': 0.2628032345013477, 'f1': 0.22196926579396697, 'number': 742}, 'P': {'precision': 0.1661392405063291, 'recall': 0.267515923566879, 'f1': 0.2049780380673499, 'number': 785}, 'overall_precision': 0.17770952172005267, 'overall_recall': 0.26522593320235754, 'overall_f1': 0.21282186022070415, 'overall_accuracy': 0.6635247476688444}
			------------EPOCH 23---------------
Loss:  tensor(27.7541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.2935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.8322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.9192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.5796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.5611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.3387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.1148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.3330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.4816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.3867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.5231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.7996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.1843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.7350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.3562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.4014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.5604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.5314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.1884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.4513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3551, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18675352877307275, 'recall': 0.23180592991913745, 'f1': 0.2068550811785929, 'number': 742}, 'P': {'precision': 0.15608263198163733, 'recall': 0.25987261146496815, 'f1': 0.1950286806883365, 'number': 785}, 'overall_precision': 0.1687612208258528, 'overall_recall': 0.24623444662737393, 'overall_f1': 0.20026631158455394, 'overall_accuracy': 0.6610166063229435}
			------------EPOCH 24---------------
Loss:  tensor(22.1093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.6096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.8793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.1803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.1508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.3541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.2464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.3209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.0224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.0050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.4362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.8625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.4649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.4379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.3647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.4254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.7860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0394, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15599639314697927, 'recall': 0.23315363881401618, 'f1': 0.18692598595353865, 'number': 742}, 'P': {'precision': 0.14467408585055644, 'recall': 0.2318471337579618, 'f1': 0.17816935878609885, 'number': 785}, 'overall_precision': 0.14997887621461767, 'overall_recall': 0.23248199083169613, 'overall_f1': 0.18233179250128403, 'overall_accuracy': 0.6612997835716742}
			------------EPOCH 25---------------
Loss:  tensor(19.4613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.5343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.8214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.7564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.7512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.8879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.6546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.3253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.6362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.4008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.8289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.0735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.8616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.5913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.9494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.3249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.9042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.0520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5619, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1903765690376569, 'recall': 0.24528301886792453, 'f1': 0.21436984687868077, 'number': 742}, 'P': {'precision': 0.163312693498452, 'recall': 0.26878980891719745, 'f1': 0.20317766008666346, 'number': 785}, 'overall_precision': 0.1748220640569395, 'overall_recall': 0.25736738703339884, 'overall_f1': 0.20821192052980134, 'overall_accuracy': 0.6535933170169299}
			------------EPOCH 26---------------
Loss:  tensor(16.0680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.6181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.8629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.0218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.1080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.8700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.3732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.3417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.0852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.9328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.6550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.8131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.5494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.7353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.1390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.1482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.8560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.1931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6071, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16109422492401215, 'recall': 0.21428571428571427, 'f1': 0.1839213418160786, 'number': 742}, 'P': {'precision': 0.13505535055350554, 'recall': 0.23312101910828026, 'f1': 0.1710280373831776, 'number': 785}, 'overall_precision': 0.14602903501280956, 'overall_recall': 0.22396856581532418, 'overall_f1': 0.17678986818299305, 'overall_accuracy': 0.6629179392787071}
			------------EPOCH 27---------------
Loss:  tensor(12.9668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.9621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.0257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.0246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.4725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.0182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.8704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.9379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.7206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.2675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.5257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.6271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.6179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.0496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.9877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.2319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.2399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.2789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5048, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20041109969167523, 'recall': 0.2628032345013477, 'f1': 0.22740524781341107, 'number': 742}, 'P': {'precision': 0.17764804003336113, 'recall': 0.2713375796178344, 'f1': 0.21471774193548385, 'number': 785}, 'overall_precision': 0.1878453038674033, 'overall_recall': 0.26719056974459726, 'overall_f1': 0.2206001622060016, 'overall_accuracy': 0.6593782236695725}
			------------EPOCH 28---------------
Loss:  tensor(10.2596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.3678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.6319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.7116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.5143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.1415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.4943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.4082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.5180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.9451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.8751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.7043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.0599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.7676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.5714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8811, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15077424612876936, 'recall': 0.24932614555256064, 'f1': 0.18791264601320465, 'number': 742}, 'P': {'precision': 0.15403225806451612, 'recall': 0.24331210191082803, 'f1': 0.188641975308642, 'number': 785}, 'overall_precision': 0.15241183623834617, 'overall_recall': 0.24623444662737393, 'overall_f1': 0.18828242363545317, 'overall_accuracy': 0.6606322943425231}
			------------EPOCH 29---------------
Loss:  tensor(8.2794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.6971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.8980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.3089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.9286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.0462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.8252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.7155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.1778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.7456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.3047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.1544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.9581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.8183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.7706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.6188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.0863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0193, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18488529014844804, 'recall': 0.18463611859838275, 'f1': 0.18476062036412674, 'number': 742}, 'P': {'precision': 0.16189111747851004, 'recall': 0.2878980891719745, 'f1': 0.20724438331040806, 'number': 785}, 'overall_precision': 0.16986429574169395, 'overall_recall': 0.23772102161100198, 'overall_f1': 0.19814410480349345, 'overall_accuracy': 0.6515099415441251}
			------------EPOCH 30---------------
Loss:  tensor(8.3541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.6133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.9819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.6452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.6298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.1546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.1460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.4738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.0720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.6173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.8946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.3267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.2796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.7991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.4019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.0808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.3857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8674, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14893617021276595, 'recall': 0.2641509433962264, 'f1': 0.1904761904761905, 'number': 742}, 'P': {'precision': 0.16544789762340037, 'recall': 0.23057324840764332, 'f1': 0.19265566790846195, 'number': 785}, 'overall_precision': 0.15643153526970954, 'overall_recall': 0.24688932547478717, 'overall_f1': 0.19151638303276608, 'overall_accuracy': 0.6473836444911911}


		-------------RUN 2-----------
			------------EPOCH 1---------------
Loss:  tensor(1694.3630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1818.7612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2133.4814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2681.6069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1040.4023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2542.4446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1258.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2506.2236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1432.9175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1430.8583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2792.0500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2264.2217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1686.6183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1858.6493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1423.3611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2368.0950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2364.9915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1330.5815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1483.3064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2453.3350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1885.6466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1745.3624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1040.5815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2521.2153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2714.5200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1296.2133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1431.9274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2547.3848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2260.5918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2141.7351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2005.3040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1969.0393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2625.2874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(875.8505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1886.1208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1690.1615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1447.9113, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 631}, 'P': {'precision': 0.21808088818398097, 'recall': 0.34591194968553457, 'f1': 0.26750972762645914, 'number': 795}, 'overall_precision': 0.21450858034321374, 'overall_recall': 0.19284712482468444, 'overall_f1': 0.20310192023633677, 'overall_accuracy': 0.569957221240584}
			------------EPOCH 2---------------
Loss:  tensor(1178.2559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1261.6223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1411.9487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1852.2789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(731.9215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1818.7673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(869.7993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1764.3568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1121.6459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1147.2673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2424.4722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1803.7068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1395.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1585.9990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1206.9233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2061.3943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2002.9763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1115.9420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1294.9080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2210.7114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1794.7856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1591.5626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(856.2426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2248.4783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2471.5742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1126.6177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1216.8621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2204.7827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1951.2190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2071.8677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1660.7705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1845.9010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2362.6895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(769.2321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1719.9097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1390.2736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1311.7280, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.06097560975609756, 'recall': 0.00792393026941363, 'f1': 0.014025245441795233, 'number': 631}, 'P': {'precision': 0.21810699588477367, 'recall': 0.3333333333333333, 'f1': 0.263681592039801, 'number': 795}, 'overall_precision': 0.2081727062451812, 'overall_recall': 0.18934081346423562, 'overall_f1': 0.19831068674256333, 'overall_accuracy': 0.5991816237329117}
			------------EPOCH 3---------------
Loss:  tensor(1074.2461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1128.3442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1265.8745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1707.9211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.2387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1652.8324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(772.7824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1559.2407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.3876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1089.6497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2339.5974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1703.0211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1268.4412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1481.3828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1110.7891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1983.7061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1933.8921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(958.2753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1283.3309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2124.3535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1666.7062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1347.4915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(787.3572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2057.9683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2225.1289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1001.5847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1063.9639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1912.4229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1686.8494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1896.3888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1390.7992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1731.9841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2158.0759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(699.4814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1630.8447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1212.1212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1273.4680, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11554921540656206, 'recall': 0.12836767036450078, 'f1': 0.1216216216216216, 'number': 631}, 'P': {'precision': 0.24407582938388625, 'recall': 0.2591194968553459, 'f1': 0.25137278828554, 'number': 795}, 'overall_precision': 0.18576051779935276, 'overall_recall': 0.20126227208976158, 'overall_f1': 0.1932009424436217, 'overall_accuracy': 0.6465637496512601}
			------------EPOCH 4---------------
Loss:  tensor(977.7325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(981.2542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1016.1461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1485.2386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.5369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1486.5554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.9473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1331.9622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(958.7452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(878.5607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2067.3423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1492.2808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1122.5012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1226.3645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(971.6320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1714.5419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1705.7389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(867.4913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1008.9819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1835.2153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1514.2981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1195.4512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(709.2705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1854.1685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1877.4579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(860.7921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(837.7304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1659.3192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1399.6987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1515.2637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1079.9617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1441.9453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1881.9279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.8680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1422.6626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1135.8397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1107.6296, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15, 'recall': 0.13787638668779714, 'f1': 0.14368290668868705, 'number': 631}, 'P': {'precision': 0.20932539682539683, 'recall': 0.26540880503144654, 'f1': 0.23405435385468665, 'number': 795}, 'overall_precision': 0.18765743073047858, 'overall_recall': 0.20897615708274894, 'overall_f1': 0.1977438619774386, 'overall_accuracy': 0.657955919278341}
			------------EPOCH 5---------------
Loss:  tensor(823.6361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(874.8042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(849.7483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1361.8264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.7091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1231.5458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(529.5798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1079.0194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(863.5988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(734.8579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1731.4333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1271.7700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(996.8566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1040.7649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(846.7593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1564.5643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1566.2692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.4457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(861.0178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1665.1084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1273.8503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(972.3472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(569.1732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1573.7810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1646.3096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(748.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(648.1171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1429.6530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1187.4331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1271.1278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(778.7103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1199.6179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1552.5054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.5435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1156.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(973.9895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.7791, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20408163265306123, 'recall': 0.12678288431061807, 'f1': 0.15640273704789834, 'number': 631}, 'P': {'precision': 0.17007534983853606, 'recall': 0.19874213836477989, 'f1': 0.18329466357308588, 'number': 795}, 'overall_precision': 0.1801665404996215, 'overall_recall': 0.16690042075736325, 'overall_f1': 0.17327994175464143, 'overall_accuracy': 0.6523063331163397}
			------------EPOCH 6---------------
Loss:  tensor(691.2410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(815.7772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(703.0909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1319.1222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.2660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1012.7350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.3911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.8526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(724.9635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(621.7317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1445.9196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1069.5243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(848.4673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(900.4996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(741.1417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1352.2397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1397.4762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(673.3318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(653.9594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1460.8793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1174.1042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.7725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.8492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1496.7543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1553.3011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(686.6953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.6500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1574.5311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1117.8213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1126.5916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(697.3637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1137.9663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1245.8535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.8616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(927.6671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.2002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(777.7983, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1529745042492918, 'recall': 0.08557844690966719, 'f1': 0.10975609756097561, 'number': 631}, 'P': {'precision': 0.10479573712255773, 'recall': 0.07421383647798742, 'f1': 0.08689248895434462, 'number': 795}, 'overall_precision': 0.12336244541484716, 'overall_recall': 0.07924263674614306, 'overall_f1': 0.0964987190435525, 'overall_accuracy': 0.5460569143494839}
			------------EPOCH 7---------------
Loss:  tensor(659.9202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(869.0333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.6593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1596.1362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(496.0696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1234.3340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.1447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1065.6301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(607.1389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.4035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1887.5499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1215.6104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(773.3511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(920.1422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(712.8296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1221.6331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1126.0415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.9036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.0850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1228.2930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1045.9124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(906.5419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.4491, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1341.4310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1716.1013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(752.5272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(566.5555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1838.2817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1797.1992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1356.3628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1441.1191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1430.7205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1670.5643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.2555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1148.5966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(943.0931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1067.2144, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2291296625222025, 'recall': 0.20443740095087162, 'f1': 0.21608040201005024, 'number': 631}, 'P': {'precision': 0.2646502835538752, 'recall': 0.3522012578616352, 'f1': 0.3022126281705342, 'number': 795}, 'overall_precision': 0.2523133867982727, 'overall_recall': 0.2868162692847125, 'overall_f1': 0.2684607810961601, 'overall_accuracy': 0.6477029666139682}
			------------EPOCH 8---------------
Loss:  tensor(730.7520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(819.6318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.4335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1290.3833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.3777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(863.7355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.8690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(927.3297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.8229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.3676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1268.6511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(775.9387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.7737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(790.8376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.3975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1055.0530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1125.8713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(504.9430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.0676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1290.6866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1189.3700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(732.7169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.7174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1369.0453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1370.0632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.1313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.3875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1233.2493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(885.7487, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1076.0684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(520.8639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(922.9493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1080.9778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.4288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(791.8254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.3293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.2698, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2275449101796407, 'recall': 0.12044374009508717, 'f1': 0.15751295336787566, 'number': 631}, 'P': {'precision': 0.22552166934189405, 'recall': 0.3534591194968553, 'f1': 0.2753552180303772, 'number': 795}, 'overall_precision': 0.2259493670886076, 'overall_recall': 0.2503506311360449, 'overall_f1': 0.2375249500998004, 'overall_accuracy': 0.659350878824514}
			------------EPOCH 9---------------
Loss:  tensor(514.3534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.3478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(587.7454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1176.3951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.2048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.3204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(697.8517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.7589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(511.6676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1067.4971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(698.7646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(546.3396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.4258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.7838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.0125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.7446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.1977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(498.9392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1036.6100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.1240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(597.1700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.7192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1000.7755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1197.1082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.9614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.7656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1070.3396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.1705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1007.8030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(440.9063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(867.5455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(873.8997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.3126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(715.2525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.1266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(496.4870, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3547008547008547, 'recall': 0.13153724247226625, 'f1': 0.19190751445086707, 'number': 631}, 'P': {'precision': 0.23857868020304568, 'recall': 0.35471698113207545, 'f1': 0.28528072837632773, 'number': 795}, 'overall_precision': 0.2577683615819209, 'overall_recall': 0.255960729312763, 'overall_f1': 0.2568613652357495, 'overall_accuracy': 0.6671859016088534}
			------------EPOCH 10---------------
Loss:  tensor(394.6474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.7695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.9464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1056.2024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.4804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(540.2139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.7671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(579.6628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.1650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(441.9283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1034.9723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.9515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.6276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.8510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(460.4027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(974.7540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.3231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.3668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.1207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(843.9482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(665.2289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.5148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.5932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(828.1838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(913.5470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.7331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.8716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(834.9756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(708.9906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(941.1741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.7676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(688.7376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1118.1809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.4634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(851.6519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.2263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.1171, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19680851063829788, 'recall': 0.2931854199683043, 'f1': 0.23551877784850414, 'number': 631}, 'P': {'precision': 0.23258426966292134, 'recall': 0.26037735849056604, 'f1': 0.2456973293768546, 'number': 795}, 'overall_precision': 0.21420765027322405, 'overall_recall': 0.27489481065918653, 'overall_f1': 0.24078624078624078, 'overall_accuracy': 0.6982470008369758}
			------------EPOCH 11---------------
Loss:  tensor(397.7794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(413.2784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.7518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(830.4265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.7128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(378.6747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.0971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.5275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.2520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.1707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.1720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.2430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.8264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.6655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.5575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.1637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.6858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.5173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.7447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(888.4412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(784.3439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.8623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.3106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1335.9963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1120.4741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.7975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.4520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(866.0765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(662.2122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.2007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.4234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.3079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.1593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.2247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(549.0943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.9454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.8294, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.151931330472103, 'recall': 0.2805071315372425, 'f1': 0.19710467706013363, 'number': 631}, 'P': {'precision': 0.24253731343283583, 'recall': 0.16352201257861634, 'f1': 0.19534184823441023, 'number': 795}, 'overall_precision': 0.18048206937095826, 'overall_recall': 0.2152875175315568, 'overall_f1': 0.19635433322673487, 'overall_accuracy': 0.6532363061471217}
			------------EPOCH 12---------------
Loss:  tensor(340.9312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.0350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.2239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.2703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.0788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(648.9257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.8239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(566.5445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(541.4330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(491.4812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1362.7141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(850.7744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(667.7871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.9791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(644.3721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.9877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(985.2500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.4385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.5205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1065.1237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(506.2729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(344.8705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.3388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(678.9681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.8926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.9820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.9010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(633.9691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(548.7209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(606.3336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.3473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.2773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(669.7712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.1962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(573.6310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(500.9886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(453.8644, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2507462686567164, 'recall': 0.13312202852614896, 'f1': 0.17391304347826086, 'number': 631}, 'P': {'precision': 0.24322230828814873, 'recall': 0.3949685534591195, 'f1': 0.30105465004793863, 'number': 795}, 'overall_precision': 0.24477244772447723, 'overall_recall': 0.2791023842917251, 'overall_f1': 0.2608125819134994, 'overall_accuracy': 0.6703013112619735}
			------------EPOCH 13---------------
Loss:  tensor(351.4660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(469.6162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.6575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1038.6139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.8938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.6836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.2384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.3691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.6467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(673.3248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.4037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.8375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(386.7358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.5738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.3974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.0947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.5464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.1498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.1494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.3341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.3518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.6321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.0661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.6594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.7733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.4209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.3931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.1898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.5485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.4357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(325.8977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.0704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.3600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.9812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.8201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(314.6840, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20600858369098712, 'recall': 0.22820919175911253, 'f1': 0.21654135338345865, 'number': 631}, 'P': {'precision': 0.23761375126390294, 'recall': 0.29559748427672955, 'f1': 0.2634529147982063, 'number': 795}, 'overall_precision': 0.2245260663507109, 'overall_recall': 0.2657784011220196, 'overall_f1': 0.24341682723185615, 'overall_accuracy': 0.7056170371059239}
			------------EPOCH 14---------------
Loss:  tensor(201.2554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.4935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.4328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(580.1005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.0506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.8870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.3401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.5047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.8075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.3528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.1876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.3118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.8278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.4126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.8834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.2282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.8770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.2905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.6493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.9794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.9990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.2476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.7077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(496.0764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.7653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.1607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.2437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(484.5585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.2344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.5312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.2136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.5898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.4006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.1547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.0969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.7624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.0555, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21160409556313994, 'recall': 0.196513470681458, 'f1': 0.2037797863599014, 'number': 631}, 'P': {'precision': 0.23236889692585896, 'recall': 0.3232704402515723, 'f1': 0.27038400841662286, 'number': 795}, 'overall_precision': 0.225177304964539, 'overall_recall': 0.26718092566619916, 'overall_f1': 0.24438742783835796, 'overall_accuracy': 0.7059890263182368}
			------------EPOCH 15---------------
Loss:  tensor(150.6084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.3356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.5673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.3785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.1596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.5084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.5546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.7514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.8226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.7638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.8086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.6064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.9887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.9742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.5345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.2624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.7036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.4911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.8544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.9993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.5386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.6700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.6974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.7587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.1057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.9944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.1378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.8013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.0676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(380.3208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.5602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.1903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.9041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.7245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.2169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.8369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(202.4617, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2016260162601626, 'recall': 0.196513470681458, 'f1': 0.19903691813804172, 'number': 631}, 'P': {'precision': 0.2252650176678445, 'recall': 0.32075471698113206, 'f1': 0.2646600934094447, 'number': 795}, 'overall_precision': 0.2169433314253005, 'overall_recall': 0.2657784011220196, 'overall_f1': 0.23889063977308542, 'overall_accuracy': 0.7091741839486655}
			------------EPOCH 16---------------
Loss:  tensor(111.4803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.2007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.0519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.2919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.7685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.0513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.7936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.8930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.7148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.1826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.3975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.1137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.9061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.3822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.7956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.2387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.2091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.8679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.5568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.4714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.3154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.8213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.3069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.9538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(320.5166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.8698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.9929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.9052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.1317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.4721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.0508, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20516962843295639, 'recall': 0.20126782884310618, 'f1': 0.2032, 'number': 631}, 'P': {'precision': 0.21280432822362488, 'recall': 0.2968553459119497, 'f1': 0.24789915966386555, 'number': 795}, 'overall_precision': 0.21006944444444445, 'overall_recall': 0.25455820476858343, 'overall_f1': 0.23018389346861126, 'overall_accuracy': 0.7060355249697758}
			------------EPOCH 17---------------
Loss:  tensor(87.3867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.3818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.7343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.2093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.9837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.8922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.8000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.9350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.5895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.4339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.0102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.1475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.2907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.9342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.3182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.4288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.3439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.5352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.0207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.1243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.0202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.6667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.4713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.8714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.5757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.7128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.2044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.5189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.7245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.6751, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1969465648854962, 'recall': 0.20443740095087162, 'f1': 0.20062208398133746, 'number': 631}, 'P': {'precision': 0.21825023518344308, 'recall': 0.2918238993710692, 'f1': 0.24973089343379976, 'number': 795}, 'overall_precision': 0.210128055878929, 'overall_recall': 0.25315568022440393, 'overall_f1': 0.22964376590330787, 'overall_accuracy': 0.7049195573328374}
			------------EPOCH 18---------------
Loss:  tensor(70.8541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.0666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.4158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.3687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.2261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.6238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.6438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.3566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.6820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.5617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.6757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.8772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.4844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.5619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.4716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.3382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.1822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.8103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.2049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.0323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.8456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.9336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.0315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.7378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.5731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.5241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.6961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.1662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.3257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.1828, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20745542949756887, 'recall': 0.20285261489698891, 'f1': 0.2051282051282051, 'number': 631}, 'P': {'precision': 0.20304114490161002, 'recall': 0.28553459119496855, 'f1': 0.23732357553580763, 'number': 795}, 'overall_precision': 0.20461095100864554, 'overall_recall': 0.24894810659186536, 'overall_f1': 0.22461246440999685, 'overall_accuracy': 0.7053612945224589}
			------------EPOCH 19---------------
Loss:  tensor(54.5816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.8816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.4876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.9849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.0448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.1666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.5284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.8423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.5568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.5475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.9127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.9987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.6086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.1066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.5462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(138.1029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.6118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.2626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.1107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.4788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.9280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.5462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.8447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.0730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.5789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.4342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.7516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.8166, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21052631578947367, 'recall': 0.20285261489698891, 'f1': 0.20661824051654562, 'number': 631}, 'P': {'precision': 0.20232766338406447, 'recall': 0.2842767295597484, 'f1': 0.2364016736401674, 'number': 795}, 'overall_precision': 0.20521739130434782, 'overall_recall': 0.2482468443197756, 'overall_f1': 0.22469057442081877, 'overall_accuracy': 0.7041523295824421}
			------------EPOCH 20---------------
Loss:  tensor(39.2417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.6615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.1726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.9251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.6713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.1196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.1520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.4214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.8148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.5910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.3203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.8553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.1895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.4821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.4427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.9810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.2548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.6034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.1982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.4927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.2246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.8613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.3344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.4397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.8069, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17780580075662042, 'recall': 0.22345483359746435, 'f1': 0.19803370786516852, 'number': 631}, 'P': {'precision': 0.1791320406278855, 'recall': 0.2440251572327044, 'f1': 0.2066027689030884, 'number': 795}, 'overall_precision': 0.17857142857142858, 'overall_recall': 0.23492286115007013, 'overall_f1': 0.20290732889158086, 'overall_accuracy': 0.7002464428531573}
			------------EPOCH 21---------------
Loss:  tensor(31.8823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.5081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.3146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2646, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.8315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.5140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.7483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.7558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.3893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.4901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.3281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.6050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.1927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.9503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.1755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.3433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.1725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.0835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.4503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.6736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.7219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.8321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.8334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.8122, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2275132275132275, 'recall': 0.20443740095087162, 'f1': 0.21535893155258762, 'number': 631}, 'P': {'precision': 0.21694036300777875, 'recall': 0.31572327044025156, 'f1': 0.25717213114754095, 'number': 795}, 'overall_precision': 0.22041763341067286, 'overall_recall': 0.2664796633941094, 'overall_f1': 0.2412698412698413, 'overall_accuracy': 0.7010136706035525}
			------------EPOCH 22---------------
Loss:  tensor(30.5590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.4091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.6109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.6392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.1221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.1448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.4702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.9052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.8038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.7371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.7131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.6020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.4075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6690, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.4072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.9273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.6537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.6549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.2570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.1494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.1926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.3914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.9066, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2034805890227577, 'recall': 0.24088748019017434, 'f1': 0.22060957910014514, 'number': 631}, 'P': {'precision': 0.20419847328244276, 'recall': 0.2691823899371069, 'f1': 0.23223005968529573, 'number': 795}, 'overall_precision': 0.20389972144846796, 'overall_recall': 0.25666199158485276, 'overall_f1': 0.2272586153368519, 'overall_accuracy': 0.7028968659908863}
			------------EPOCH 23---------------
Loss:  tensor(24.1244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.9901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.3192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.7089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.0300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.6735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.9911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.6110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.0988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.5248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.7947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.0879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.8400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.7003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.7466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.1076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.2678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.9264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.6711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.2063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.8558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.2864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(187.1818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.4574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.5112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.0249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.3542, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20907617504051865, 'recall': 0.20443740095087162, 'f1': 0.20673076923076922, 'number': 631}, 'P': {'precision': 0.16120906801007556, 'recall': 0.24150943396226415, 'f1': 0.1933534743202417, 'number': 795}, 'overall_precision': 0.17754424778761063, 'overall_recall': 0.22510518934081347, 'overall_f1': 0.1985157699443414, 'overall_accuracy': 0.6976890170185065}
			------------EPOCH 24---------------
Loss:  tensor(18.4003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.6354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.6222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.8623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.8437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.2136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.0200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.1120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.5638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.9383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.4452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.3869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.5497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.5956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.5742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.0369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.8522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.1886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.3330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.0294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.9582, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1948249619482496, 'recall': 0.20285261489698891, 'f1': 0.1987577639751553, 'number': 631}, 'P': {'precision': 0.1969286359530262, 'recall': 0.2742138364779874, 'f1': 0.2292323869610936, 'number': 795}, 'overall_precision': 0.1961451247165533, 'overall_recall': 0.2426367461430575, 'overall_f1': 0.21692789968652038, 'overall_accuracy': 0.6981540035338976}
			------------EPOCH 25---------------
Loss:  tensor(12.5350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.4128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.6965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.5371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.6029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.8533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.6799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.5486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.7366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.4470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(254.8665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.4808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.8115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.6536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.9595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.5075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.8698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.7315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.8190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.0148, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1907514450867052, 'recall': 0.2091917591125198, 'f1': 0.19954648526077096, 'number': 631}, 'P': {'precision': 0.1989247311827957, 'recall': 0.2792452830188679, 'f1': 0.23233908948194662, 'number': 795}, 'overall_precision': 0.19579646017699115, 'overall_recall': 0.2482468443197756, 'overall_f1': 0.21892393320964748, 'overall_accuracy': 0.7007579280200874}
			------------EPOCH 26---------------
Loss:  tensor(9.6986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.5303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.5178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.0477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.1328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.7641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.9881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(172.2387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.8638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.6953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.2336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.0357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.4330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.1102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.3892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.0837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.0533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.1922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.2924, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19821162444113263, 'recall': 0.21077654516640254, 'f1': 0.20430107526881724, 'number': 631}, 'P': {'precision': 0.1717948717948718, 'recall': 0.2528301886792453, 'f1': 0.20458015267175572, 'number': 795}, 'overall_precision': 0.18142313959804454, 'overall_recall': 0.23422159887798036, 'overall_f1': 0.204468931741659, 'overall_accuracy': 0.6980610062308193}
			------------EPOCH 27---------------
Loss:  tensor(6.8893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.1598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.9661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.1229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.4993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.9963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.0894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.7798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.3507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.3974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.6731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.7324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.9290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.4301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.7946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.6281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.8881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.9198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.5581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.9759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5166, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18349928876244664, 'recall': 0.20443740095087162, 'f1': 0.19340329835082457, 'number': 631}, 'P': {'precision': 0.193923145665773, 'recall': 0.2729559748427673, 'f1': 0.22675026123301986, 'number': 795}, 'overall_precision': 0.18990120746432493, 'overall_recall': 0.2426367461430575, 'overall_f1': 0.21305418719211822, 'overall_accuracy': 0.7005486840881614}
			------------EPOCH 28---------------
Loss:  tensor(6.5347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.9887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.2060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.0918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.9604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.8457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.2724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.4212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.3361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.4349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.7098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.0279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.2630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.2590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.3063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.7303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.7503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.5448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.0455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.4365, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2009132420091324, 'recall': 0.2091917591125198, 'f1': 0.20496894409937888, 'number': 631}, 'P': {'precision': 0.18930762489044697, 'recall': 0.27169811320754716, 'f1': 0.22314049586776857, 'number': 795}, 'overall_precision': 0.1935483870967742, 'overall_recall': 0.24403927068723702, 'overall_f1': 0.21588089330024815, 'overall_accuracy': 0.7011996652097089}
			------------EPOCH 29---------------
Loss:  tensor(4.9088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.9064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.4313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.0685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.8126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.0143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.1439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.4662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.2124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.9181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.6375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.9292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.5978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.4810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.1567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.3883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6504, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18421052631578946, 'recall': 0.21077654516640254, 'f1': 0.19660014781966, 'number': 631}, 'P': {'precision': 0.17600700525394045, 'recall': 0.2528301886792453, 'f1': 0.20753742901393907, 'number': 795}, 'overall_precision': 0.1791845493562232, 'overall_recall': 0.23422159887798036, 'overall_f1': 0.20303951367781156, 'overall_accuracy': 0.699688459034688}
			------------EPOCH 30---------------
Loss:  tensor(4.1861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.5441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.6698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.8517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.3053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.1586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.7346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.2626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.5137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.6133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.4510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.5139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.8906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.1358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.9305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.4153, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19578313253012047, 'recall': 0.20602218700475436, 'f1': 0.20077220077220076, 'number': 631}, 'P': {'precision': 0.20173913043478262, 'recall': 0.2918238993710692, 'f1': 0.238560411311054, 'number': 795}, 'overall_precision': 0.19955898566703417, 'overall_recall': 0.2538569424964937, 'overall_f1': 0.2234567901234568, 'overall_accuracy': 0.699479215102762}


		-------------RUN 3-----------
			------------EPOCH 1---------------
Loss:  tensor(2218.3765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3698.2378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2151.6313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2645.1067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1384.9507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2335.5876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2927.0342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2529.9255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3301.7715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1421.8530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2783.8647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2538.9888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1810.7939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1799.8374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2385.3716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2112.9648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2541.4707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2177.9126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2214.2517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2022.1748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2131.2671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2351.5435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1277.1545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1855.2761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2343.8862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1126.7664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(845.1067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1029.3350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1264.5027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(991.8983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2284.4597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3667.1516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2289.7495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1827.9187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1463.2096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1714.7162, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 777}, 'P': {'precision': 0.002175489485134155, 'recall': 0.007822685788787484, 'f1': 0.0034042553191489357, 'number': 767}, 'overall_precision': 0.0021684134441633538, 'overall_recall': 0.0038860103626943004, 'overall_f1': 0.0027835768963117608, 'overall_accuracy': 0.4754007370898273}
			------------EPOCH 2---------------
Loss:  tensor(1282.5293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2231.8005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1329.4417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1677.9834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(982.2866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1582.4753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2106.9192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1859.8821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2389.7769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(938.0955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1874.2922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1922.6219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1465.8557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1364.3337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1987.4636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1614.0957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2251.4514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1842.8574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1852.0560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1745.4196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2057.6040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2103.0742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1136.8383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1562.6614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2039.9961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(943.7142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(710.0792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(865.5195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1071.7714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.3601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2025.6545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3343.3616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2128.7788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1696.4017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1317.1970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1558.1760, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 777}, 'P': {'precision': 0.027190332326283987, 'recall': 0.0938722294654498, 'f1': 0.04216691068814055, 'number': 767}, 'overall_precision': 0.02666666666666667, 'overall_recall': 0.046632124352331605, 'overall_f1': 0.033930254476908575, 'overall_accuracy': 0.561409351272146}
			------------EPOCH 3---------------
Loss:  tensor(1137.0757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2027.5000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1216.2664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1521.9534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.9253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1450.8638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1986.6649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1584.4663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2194.7764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(849.4069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1699.1494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1717.9609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1290.0386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1273.9463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1704.9717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1377.1030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2137.7495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1621.9453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1675.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1559.9131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1850.1339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1827.6575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1037.3982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1326.6344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1670.7456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(849.0613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.6890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(772.4800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.6710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(640.3785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1772.8777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3060.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1902.9709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1497.7952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1176.7552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1400.2168, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.041791044776119404, 'recall': 0.018018018018018018, 'f1': 0.025179856115107917, 'number': 777}, 'P': {'precision': 0.01999310582557739, 'recall': 0.07561929595827901, 'f1': 0.03162486368593239, 'number': 767}, 'overall_precision': 0.022249690976514216, 'overall_recall': 0.046632124352331605, 'overall_f1': 0.0301255230125523, 'overall_accuracy': 0.5854313751609609}
			------------EPOCH 4---------------
Loss:  tensor(951.1195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1768.1377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1109.1011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1391.8945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(848.1616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1304.0404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1861.8887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1462.4409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1935.2838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(705.2361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1423.2747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1608.5962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1153.0961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1068.6075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1527.6270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1181.7673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1805.4180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1313.0881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1348.0179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1279.1182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1528.3513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1675.4972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(832.4922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1123.8870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1380.2966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(700.4304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(543.8482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.9613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(827.4996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.1473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1586.7896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2954.3926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1741.5813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1199.4824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1056.4617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1251.9172, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11635220125786164, 'recall': 0.09523809523809523, 'f1': 0.10474168435951875, 'number': 777}, 'P': {'precision': 0.015865384615384615, 'recall': 0.04302477183833116, 'f1': 0.023182297154899893, 'number': 767}, 'overall_precision': 0.03939617083946981, 'overall_recall': 0.06930051813471502, 'overall_f1': 0.050234741784037557, 'overall_accuracy': 0.6088539585275965}
			------------EPOCH 5---------------
Loss:  tensor(809.0854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1450.8112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(939.2159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1101.5375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(761.4950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1105.8322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1531.8099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1314.6389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1645.4260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.1561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1165.6531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1435.0205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1061.1680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.3331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1353.3267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.9961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1499.0829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1090.1343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1063.4974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1013.8725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1296.0889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1595.1194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(639.9743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(969.1163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1169.4736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.4558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.1944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(505.3734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.0865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.4841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1219.8132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2434.1328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1469.3839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1004.4824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(874.3356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1053.2974, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17219917012448133, 'recall': 0.10682110682110682, 'f1': 0.1318506751389992, 'number': 777}, 'P': {'precision': 0.0248015873015873, 'recall': 0.03259452411994785, 'f1': 0.02816901408450704, 'number': 767}, 'overall_precision': 0.07248322147651007, 'overall_recall': 0.06994818652849741, 'overall_f1': 0.07119314436387607, 'overall_accuracy': 0.5714222281426224}
			------------EPOCH 6---------------
Loss:  tensor(738.3088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1342.3652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(882.7147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1006.1595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.6699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(980.6108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1420.8618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1090.6523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1388.1619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(470.3901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(916.0167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1079.9021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(870.1773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(724.3403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.2488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.4586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1284.5303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(912.7700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(877.7621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(871.7615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1158.9269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1572.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.5562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(985.9110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1240.6066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.4075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.7560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.8939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(542.4978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.6884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.6477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2112.9814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1113.7684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(776.7217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(697.1693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(845.5631, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13355048859934854, 'recall': 0.05276705276705277, 'f1': 0.07564575645756458, 'number': 777}, 'P': {'precision': 0.022919179734620022, 'recall': 0.024771838331160364, 'f1': 0.02380952380952381, 'number': 767}, 'overall_precision': 0.0528169014084507, 'overall_recall': 0.038860103626943004, 'overall_f1': 0.04477611940298507, 'overall_accuracy': 0.5139647440166956}
			------------EPOCH 7---------------
Loss:  tensor(670.5949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1185.8455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.4871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(773.4852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(589.5217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1029.3713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1485.7539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1114.6147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1556.9158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(471.0134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(970.7173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.2351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(708.3404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(648.4061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1066.1208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(885.5930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(995.7244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.9393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(665.9796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.8277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(808.2112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1170.2041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(425.6228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(721.6711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1080.1167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.2367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.9153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.3698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.5488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.0875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1064.0278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2349.2395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1298.7893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.5170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.6958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(848.9814, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19530284301606923, 'recall': 0.20334620334620335, 'f1': 0.1992433795712484, 'number': 777}, 'P': {'precision': 0.09270334928229665, 'recall': 0.20208604954367665, 'f1': 0.1271012710127101, 'number': 767}, 'overall_precision': 0.12615880693268844, 'overall_recall': 0.202720207253886, 'overall_f1': 0.15552795031055902, 'overall_accuracy': 0.6303894143244083}
			------------EPOCH 8---------------
Loss:  tensor(482.2954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1083.0930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(718.0439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.3916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(551.3369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(805.4062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1481.5795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(890.9569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1106.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(356.4173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(647.1247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(942.6517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(627.0083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(501.6013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(877.9688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(712.3464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(970.3057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(702.7681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(635.4047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(567.5400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(842.5403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(973.0776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.1624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(727.7462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(799.1520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.5214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.1457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.6712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.7489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.5078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(752.6018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1509.5637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(907.5002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(632.6492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.7050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(643.5085, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21393034825870647, 'recall': 0.055341055341055344, 'f1': 0.08793456032719837, 'number': 777}, 'P': {'precision': 0.06137968495382944, 'recall': 0.14732724902216426, 'f1': 0.08665644171779141, 'number': 767}, 'overall_precision': 0.07639569049951028, 'overall_recall': 0.10103626943005181, 'overall_f1': 0.08700501952035694, 'overall_accuracy': 0.6094756005505972}
			------------EPOCH 9---------------
Loss:  tensor(606.2964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1213.6063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.6110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(760.4103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(535.9208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(789.1959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1274.6342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(900.0818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1033.8795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.1997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.4330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(704.8000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.0681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.8611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(738.4788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(646.5601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1293.3882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(844.4138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(904.9721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(645.4874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(692.7986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(934.3503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(617.1375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.4374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(713.7115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.5513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.9319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.9464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.0548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.8878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.4401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1283.6963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.7015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.7211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(452.0191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(565.7314, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3113207547169811, 'recall': 0.04247104247104247, 'f1': 0.07474518686296716, 'number': 777}, 'P': {'precision': 0.07729941291585127, 'recall': 0.20599739243807041, 'f1': 0.11241551049448595, 'number': 767}, 'overall_precision': 0.08883720930232558, 'overall_recall': 0.12370466321243523, 'overall_f1': 0.10341093665403356, 'overall_accuracy': 0.5925136539230051}
			------------EPOCH 10---------------
Loss:  tensor(533.6360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1104.4895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.5270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(623.5952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.5048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(876.6898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1153.7377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.3676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1779.3988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(588.6787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1039.7825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(993.4333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(712.4368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(891.0952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(988.5807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(768.9128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(978.3873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(628.3447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(713.4477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.6232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.1970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(833.5322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.0381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(613.3784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(643.7192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.8878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.3422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.4288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(402.1357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.4447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(859.0764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1415.1781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(989.4205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(797.5600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(684.0792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(925.4397, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14681440443213298, 'recall': 0.2728442728442728, 'f1': 0.19090499774876182, 'number': 777}, 'P': {'precision': 0.02924791086350975, 'recall': 0.027379400260756193, 'f1': 0.02828282828282828, 'number': 767}, 'overall_precision': 0.10777058279370953, 'overall_recall': 0.15090673575129535, 'overall_f1': 0.12574203993524016, 'overall_accuracy': 0.6066782114470938}
			------------EPOCH 11---------------
Loss:  tensor(594.3506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1050.5751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(600.7672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(837.9717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.5522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(661.0735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1102.7607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(839.3550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(936.0332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(327.7800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(497.4366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.3113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.6074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.9539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.3054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.7029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.9231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(474.2742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.7760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.6451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.1422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(734.1443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(251.6559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.1121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.4008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.1042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.2917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.0438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.1573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.3323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1179.1876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(605.0985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(398.5599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(418.8603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.5671, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17733990147783252, 'recall': 0.09266409266409266, 'f1': 0.12172442941673713, 'number': 777}, 'P': {'precision': 0.07480550568521843, 'recall': 0.16297262059973924, 'f1': 0.10254306808859721, 'number': 767}, 'overall_precision': 0.09484833895040924, 'overall_recall': 0.12759067357512954, 'overall_f1': 0.10880972107152721, 'overall_accuracy': 0.6484836374938946}
			------------EPOCH 12---------------
Loss:  tensor(251.3861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(549.1865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.1232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(412.2078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.0950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.8768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(643.6270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(550.3341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(879.9982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.5681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.5370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(477.8120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.9058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.2925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(575.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(446.6816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.1977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.7625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.6096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.9355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.5556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(539.8569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.2743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.8747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.0110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.3998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.4201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.7478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(479.5187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(811.4739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(419.5368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.1161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.1284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.1729, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1955193482688391, 'recall': 0.2471042471042471, 'f1': 0.2183058555997726, 'number': 777}, 'P': {'precision': 0.10043668122270742, 'recall': 0.14993481095176012, 'f1': 0.12029288702928871, 'number': 767}, 'overall_precision': 0.14433474377056887, 'overall_recall': 0.19883419689119172, 'overall_f1': 0.1672568782348134, 'overall_accuracy': 0.6623151725056614}
			------------EPOCH 13---------------
Loss:  tensor(189.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(472.3633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(268.1928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.8516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.9324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.6621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(611.6505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(442.2476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.7865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.7663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.3797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(397.6374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.4158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.9067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.8282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.9393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.9600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.9739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.0875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.6478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.2134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.9720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.5857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.9364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.8643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.9722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.8324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.9293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.8710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.3551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(407.0643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.8885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(351.5548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.8792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.7804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.8264, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16931982633863965, 'recall': 0.15057915057915058, 'f1': 0.1594005449591281, 'number': 777}, 'P': {'precision': 0.08844011142061281, 'recall': 0.16558018252933507, 'f1': 0.11529732183386292, 'number': 767}, 'overall_precision': 0.1147155618241655, 'overall_recall': 0.15803108808290156, 'overall_f1': 0.13293380550258785, 'overall_accuracy': 0.6677545402069179}
			------------EPOCH 14---------------
Loss:  tensor(127.3639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.1494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.3917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.9171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.9323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.7736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(424.2928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.6564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.1619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.4501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.2531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.4937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.1754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.3319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.3564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.7335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.1758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.6288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.7265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(368.7450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.7118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.0510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.0103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.5210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.0958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.2343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.8586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.6131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(581.3410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.8147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.4358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.6404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.1255, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17752234993614305, 'recall': 0.1788931788931789, 'f1': 0.17820512820512824, 'number': 777}, 'P': {'precision': 0.1056081573197378, 'recall': 0.18904823989569752, 'f1': 0.13551401869158877, 'number': 767}, 'overall_precision': 0.13172541743970315, 'overall_recall': 0.18393782383419688, 'overall_f1': 0.1535135135135135, 'overall_accuracy': 0.6677545402069179}
			------------EPOCH 15---------------
Loss:  tensor(94.3123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(270.6732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.5465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.5892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.6126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.8812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(343.7057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.0714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(393.2327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.4908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.0419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.8301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.8399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.5048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(304.4502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.6522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.1295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.5737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.2363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.5447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.2772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.1862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.1316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.2812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.1632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.8897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.4754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.7288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(282.0382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.2452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.5088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.4436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.4041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.8937, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19949811794228356, 'recall': 0.20463320463320464, 'f1': 0.20203303684879287, 'number': 777}, 'P': {'precision': 0.1621174524400331, 'recall': 0.25554106910039115, 'f1': 0.19838056680161942, 'number': 767}, 'overall_precision': 0.1769690927218345, 'overall_recall': 0.22992227979274613, 'overall_f1': 0.2, 'overall_accuracy': 0.6729052883974956}
			------------EPOCH 16---------------
Loss:  tensor(64.2391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.9523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.1426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.1389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.5863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.6391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.4224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.7211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.1544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.9500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.0201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.6671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.3309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.6536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.8920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.9569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.0660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.1621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.0320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.8255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.8929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.8963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.1923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.8290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.3192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.5026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.8364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.1954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.1079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.3840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.6227, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19917582417582416, 'recall': 0.1866151866151866, 'f1': 0.19269102990033224, 'number': 777}, 'P': {'precision': 0.129565816678153, 'recall': 0.24511082138200782, 'f1': 0.16952209197475204, 'number': 767}, 'overall_precision': 0.15282239559430932, 'overall_recall': 0.21567357512953367, 'overall_f1': 0.17888799355358584, 'overall_accuracy': 0.6759024910083922}
			------------EPOCH 17---------------
Loss:  tensor(49.8207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.0670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.9864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.5951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.9860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.7648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(252.9889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.2280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.4726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.7197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.9881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.1119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.3106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.4054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.7289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.9039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.8088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.3721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.1168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.3913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.4106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.9132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.1124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.4303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.1445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.4324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.8278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.7265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.1006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.9482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.4379, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1747700394218134, 'recall': 0.17117117117117117, 'f1': 0.17295188556566973, 'number': 777}, 'P': {'precision': 0.09180790960451977, 'recall': 0.1694915254237288, 'f1': 0.11910215300045808, 'number': 767}, 'overall_precision': 0.1208084519981626, 'overall_recall': 0.17033678756476683, 'overall_f1': 0.14135984950282182, 'overall_accuracy': 0.6670662936814529}
			------------EPOCH 18---------------
Loss:  tensor(43.1372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.5633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.9886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.2412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.6549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.1578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.3019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.4533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.6621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.4369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.4443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.5054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.7460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.3295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.8642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.1840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.7710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.2900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.2076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.5223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.8505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(258.6252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.8766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.5139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.3354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(532.5511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.1596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.5079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.5923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(269.5472, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1971223021582734, 'recall': 0.17631917631917632, 'f1': 0.1861413043478261, 'number': 777}, 'P': {'precision': 0.11183261183261184, 'recall': 0.20208604954367665, 'f1': 0.14398513701811425, 'number': 767}, 'overall_precision': 0.1403171552138395, 'overall_recall': 0.18911917098445596, 'overall_f1': 0.16110344827586207, 'overall_accuracy': 0.6695750632742773}
			------------EPOCH 19---------------
Loss:  tensor(34.2616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.4554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.6688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(226.1827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.3936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.4129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.8162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(339.9353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.1751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.0609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.6385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(279.2180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.8170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(250.2915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.0180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.9720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.9316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.4409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.7066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.9668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.4247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.6100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.5389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.9145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.3937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.4622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.5097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.4949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.8134, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.27739251040221913, 'recall': 0.2574002574002574, 'f1': 0.267022696929239, 'number': 777}, 'P': {'precision': 0.1857707509881423, 'recall': 0.30638852672750977, 'f1': 0.23129921259842523, 'number': 767}, 'overall_precision': 0.2190332326283988, 'overall_recall': 0.2817357512953368, 'overall_f1': 0.24645892351274787, 'overall_accuracy': 0.6710403623284934}
			------------EPOCH 20---------------
Loss:  tensor(28.5739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.4671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.9797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.1571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.1347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.2848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.8783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(306.1942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.7409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.3486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.1344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.6062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.7353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.7206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.4069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.4137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.9737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.3816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.2253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.3114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.1587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.2317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.8467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.6067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.4611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.0550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.8012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.4583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.0659, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24623803009575923, 'recall': 0.23166023166023167, 'f1': 0.23872679045092837, 'number': 777}, 'P': {'precision': 0.1451831750339213, 'recall': 0.2790091264667536, 'f1': 0.19098616688978134, 'number': 767}, 'overall_precision': 0.17868480725623584, 'overall_recall': 0.2551813471502591, 'overall_f1': 0.21018938383568952, 'overall_accuracy': 0.6727498778917455}
			------------EPOCH 21---------------
Loss:  tensor(20.8119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.9677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.9609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.3101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.6217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.1360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.8431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.9756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.1617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.8619, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.0260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.9686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.0125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.9408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.3819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.6550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.5501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.2769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.1798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.4887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.1633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.5138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.4662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.0042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.9995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.7702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.1984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.8864, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16856780735107732, 'recall': 0.17117117117117117, 'f1': 0.1698595146871009, 'number': 777}, 'P': {'precision': 0.08449612403100776, 'recall': 0.1421121251629726, 'f1': 0.1059795819154108, 'number': 767}, 'overall_precision': 0.1164021164021164, 'overall_recall': 0.1567357512953368, 'overall_f1': 0.13359094672922991, 'overall_accuracy': 0.6719062208605302}
			------------EPOCH 22---------------
Loss:  tensor(39.7968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.8524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.2806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.4382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.7873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.6725, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.2912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.0490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.3987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.1667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.3534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.0655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.4211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.0389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.3484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.2944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.9137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.4573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.4132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.7786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.5240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.5898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.7716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.2032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.3918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.1383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.6926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.7131, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23232323232323232, 'recall': 0.2072072072072072, 'f1': 0.21904761904761905, 'number': 777}, 'P': {'precision': 0.16323633782824698, 'recall': 0.29986962190352023, 'f1': 0.2113970588235294, 'number': 767}, 'overall_precision': 0.18601332064700285, 'overall_recall': 0.25323834196891193, 'overall_f1': 0.21448162369720244, 'overall_accuracy': 0.6708183473202789}
			------------EPOCH 23---------------
Loss:  tensor(15.5297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.1279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.4536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.9362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.5027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.9632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.2259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(201.9454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.1551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.0093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.8712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.6156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.9813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.7275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.8445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.9078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.6463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.4500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.0867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.0780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.8945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.5346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.0488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.8307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.2001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.3423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.0500, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18532818532818532, 'recall': 0.18532818532818532, 'f1': 0.18532818532818532, 'number': 777}, 'P': {'precision': 0.12529002320185614, 'recall': 0.21121251629726207, 'f1': 0.15728155339805824, 'number': 767}, 'overall_precision': 0.14782608695652175, 'overall_recall': 0.19818652849740934, 'overall_f1': 0.1693414499169895, 'overall_accuracy': 0.6650459571067004}
			------------EPOCH 24---------------
Loss:  tensor(13.1054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.2774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7567, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.8791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.1354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.8285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.2856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.1365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.6215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.7319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.8437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.9559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.9977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.3547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.6215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.2744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.9207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.2708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.3673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.0994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.5086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.4430, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20400500625782228, 'recall': 0.2097812097812098, 'f1': 0.20685279187817257, 'number': 777}, 'P': {'precision': 0.1466252909231963, 'recall': 0.24641460234680573, 'f1': 0.18385214007782102, 'number': 767}, 'overall_precision': 0.1685823754789272, 'overall_recall': 0.22797927461139897, 'overall_f1': 0.19383259911894274, 'overall_accuracy': 0.6720172283646374}
			------------EPOCH 25---------------
Loss:  tensor(8.0781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.7475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.8451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.6062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.7918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.6234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.2813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(173.6299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.5828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.0131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.6499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.9024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.8294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.4262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.9444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5366, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.3143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.4228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.0379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.9140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.2379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.3679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.7253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.4539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.7171, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20140845070422536, 'recall': 0.18404118404118405, 'f1': 0.1923335574983188, 'number': 777}, 'P': {'precision': 0.15155910079767948, 'recall': 0.27249022164276404, 'f1': 0.19478098788443615, 'number': 767}, 'overall_precision': 0.1685016754427956, 'overall_recall': 0.22797927461139897, 'overall_f1': 0.19377924580236716, 'overall_accuracy': 0.6696416677767417}
			------------EPOCH 26---------------
Loss:  tensor(5.8555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.0057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.3988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.2551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.7699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.0452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.1908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.7889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.4009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.1739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.1338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.8930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.0196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.9135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.7375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.9885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.8311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.8217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.2825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.5206, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.202275600505689, 'recall': 0.2059202059202059, 'f1': 0.2040816326530612, 'number': 777}, 'P': {'precision': 0.16382806163828062, 'recall': 0.2633637548891786, 'f1': 0.202, 'number': 767}, 'overall_precision': 0.17885375494071146, 'overall_recall': 0.2344559585492228, 'overall_f1': 0.202914798206278, 'overall_accuracy': 0.6709515563252075}
			------------EPOCH 27---------------
Loss:  tensor(4.9778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2700, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.0456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.7772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.2768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.4937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.2217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.0713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1977, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.8339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.3438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.8034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.9192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.3271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.6292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.8502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.7538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.3583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(230.1122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.0756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.5259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.8907, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.187422934648582, 'recall': 0.1956241956241956, 'f1': 0.19143576826196473, 'number': 777}, 'P': {'precision': 0.1338181818181818, 'recall': 0.23989569752281617, 'f1': 0.17180205415499533, 'number': 767}, 'overall_precision': 0.1537053979871912, 'overall_recall': 0.21761658031088082, 'overall_f1': 0.1801608579088472, 'overall_accuracy': 0.6750810354779984}
			------------EPOCH 28---------------
Loss:  tensor(4.6492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.2439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.6957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.0819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.5094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.1279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.9198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.3538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.0052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.5683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.8443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.2025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.5280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.2286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.2983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.3546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(225.1894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.9140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.6257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.7951, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2388268156424581, 'recall': 0.22007722007722008, 'f1': 0.22906898861352984, 'number': 777}, 'P': {'precision': 0.16314639475600873, 'recall': 0.2920469361147327, 'f1': 0.20934579439252335, 'number': 767}, 'overall_precision': 0.1890856869315462, 'overall_recall': 0.25582901554404147, 'overall_f1': 0.21745114230663365, 'overall_accuracy': 0.6705519293104214}
			------------EPOCH 29---------------
Loss:  tensor(3.6613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.0284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.6524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.7627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.6971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.0274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.0868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.0331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.4379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.9546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.8513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.2600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.1110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.4795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.0889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.9512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.8858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.1079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.1897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.8244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.6575, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20451527224435592, 'recall': 0.1981981981981982, 'f1': 0.20130718954248367, 'number': 777}, 'P': {'precision': 0.14523449319213314, 'recall': 0.2503259452411995, 'f1': 0.18382000957395883, 'number': 767}, 'overall_precision': 0.16674698795180723, 'overall_recall': 0.22409326424870465, 'overall_f1': 0.19121304227687205, 'overall_accuracy': 0.6704409218063141}
			------------EPOCH 30---------------
Loss:  tensor(3.5180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.5745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.0197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.6199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.8537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.1939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.4853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.8744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.1010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.2511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.5575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.8219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.4742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.9050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.2317, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18974358974358974, 'recall': 0.19047619047619047, 'f1': 0.1901091843288375, 'number': 777}, 'P': {'precision': 0.1527777777777778, 'recall': 0.258148631029987, 'f1': 0.19195346582646633, 'number': 767}, 'overall_precision': 0.16666666666666666, 'overall_recall': 0.22409326424870465, 'overall_f1': 0.19116022099447513, 'overall_accuracy': 0.6755028639936059}


		-------------RUN 4-----------
			------------EPOCH 1---------------
Loss:  tensor(1941.3154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1995.8896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2500.3354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2731.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3299.4478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1795.6312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1634.1965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1339.9622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1396.9426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3553.4246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1776.4003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2454.4507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3595.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1995.6277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3733.5264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3282.0244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1426.1870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2726.9829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2561.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1607.8179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2069.1907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1850.2927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2528.2361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1401.5662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1319.5035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1921.2174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1676.8552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1627.4072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1858.6802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1752.9236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2900.0046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1972.2466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1254.5084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(927.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2343.9893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1997.7184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1929.0569, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.007232401157184185, 'recall': 0.0186799501867995, 'f1': 0.010427528675703858, 'number': 803}, 'P': {'precision': 0.04040404040404041, 'recall': 0.04656084656084656, 'f1': 0.043264503441494594, 'number': 945}, 'overall_precision': 0.018653177363262725, 'overall_recall': 0.033752860411899316, 'overall_f1': 0.02402769293422928, 'overall_accuracy': 0.5894722211190977}
			------------EPOCH 2---------------
Loss:  tensor(1256.3348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1261.3217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1546.6128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1688.7421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2519.4326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1333.8232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1119.6833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1046.6782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1118.3932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2747.4160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1271.6245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1716.8060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2867.5942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1558.6016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3086.4751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2599.4580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1132.1902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2397.1987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2191.6216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1274.8252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1730.0215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1589.8579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2217.9106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.2067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1131.0317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1614.5840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1480.2706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1404.2649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1592.5035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1426.1599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2442.7456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1790.9270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1094.4159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(816.0377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1991.1790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1645.2019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1561.8961, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.012940330697340043, 'recall': 0.0224159402241594, 'f1': 0.016408386508659983, 'number': 803}, 'P': {'precision': 0.09710610932475884, 'recall': 0.15978835978835979, 'f1': 0.12079999999999999, 'number': 945}, 'overall_precision': 0.05736591989137814, 'overall_recall': 0.09668192219679633, 'overall_f1': 0.07200681721346401, 'overall_accuracy': 0.6131607164131686}
			------------EPOCH 3---------------
Loss:  tensor(1123.4351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1104.4465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1402.8242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1365.1626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2344.5220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1133.8721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(948.8463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(885.3741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.9500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2302.1709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1091.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1424.0321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2526.6082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1346.8296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2707.7178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2209.0181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(982.9290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2158.2065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1896.4539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1119.4706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1518.5264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1400.5232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1883.8796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(972.4840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1005.5724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1452.0178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1332.0984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1301.7378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1454.1450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1257.8430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2217.2288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1653.9109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(903.7156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(626.8160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1517.7235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1139.0066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1058.3152, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.028609447771124417, 'recall': 0.053549190535491904, 'f1': 0.03729401561144839, 'number': 803}, 'P': {'precision': 0.1847041847041847, 'recall': 0.2708994708994709, 'f1': 0.21964821964821965, 'number': 945}, 'overall_precision': 0.10349601938386985, 'overall_recall': 0.17105263157894737, 'overall_f1': 0.1289626913952987, 'overall_accuracy': 0.6257694293316389}
			------------EPOCH 4---------------
Loss:  tensor(949.4468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.4227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1212.8793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1127.5093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2310.9509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(919.8177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(772.8175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(762.5090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(938.1721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1938.4694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(891.1497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1076.4478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2235.5312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1157.0974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2343.7129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1915.5374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(786.3447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1978.2717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1623.7075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.0779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1239.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1178.3353, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1600.2352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(751.4137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(853.1635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1242.4468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1189.1108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1136.0641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1309.8296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1044.9127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1880.1558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1420.1506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.7917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.6034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1203.6316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.8092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(655.5100, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0409967845659164, 'recall': 0.06351183063511831, 'f1': 0.049829018075232046, 'number': 803}, 'P': {'precision': 0.12656641604010024, 'recall': 0.21375661375661376, 'f1': 0.15899252262888625, 'number': 945}, 'overall_precision': 0.08908450704225353, 'overall_recall': 0.14473684210526316, 'overall_f1': 0.11028770706190062, 'overall_accuracy': 0.6482665501767205}
			------------EPOCH 5---------------
Loss:  tensor(765.4185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.8658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1008.4249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(824.4767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1691.6168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(743.0584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(612.8456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(601.4332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(752.0227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1663.1398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(756.2101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(813.3342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1932.8157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(955.1296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1960.8323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1623.2416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.5341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1892.7960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1484.4290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(851.5549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1062.5908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1118.7458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1624.8826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(639.9200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(728.9784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(995.3090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1026.1702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(920.8479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(977.6501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(852.9005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1385.2773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1093.3746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.2356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.2074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(933.4153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.0928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(485.5765, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0186219739292365, 'recall': 0.012453300124533, 'f1': 0.014925373134328358, 'number': 803}, 'P': {'precision': 0.07750188111361926, 'recall': 0.10899470899470899, 'f1': 0.09058927000879508, 'number': 945}, 'overall_precision': 0.060557341907824226, 'overall_recall': 0.06464530892448513, 'overall_f1': 0.06253458771444384, 'overall_accuracy': 0.5916762638497279}
			------------EPOCH 6---------------
Loss:  tensor(711.2963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(561.2211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1046.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.2296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1580.0962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(725.8677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(545.5122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(568.0866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.0951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1690.2729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(719.4204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(776.2300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1578.3728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(783.4562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1761.2518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1411.9281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(438.3470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1383.3208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1099.3552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(664.6761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(856.7589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(911.8071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1306.6792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(475.5254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(630.3815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(893.4467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(916.8361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.2980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(975.8778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.2917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1346.8213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1110.0742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(536.6371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.3777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1041.0844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.9167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.4111, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.08663366336633663, 'recall': 0.08717310087173101, 'f1': 0.08690254500310367, 'number': 803}, 'P': {'precision': 0.18992989165073296, 'recall': 0.31534391534391537, 'f1': 0.23707239459029436, 'number': 945}, 'overall_precision': 0.15481699621371478, 'overall_recall': 0.21052631578947367, 'overall_f1': 0.1784242424242424, 'overall_accuracy': 0.642150828005242}
			------------EPOCH 7---------------
Loss:  tensor(609.6863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.8555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(685.7534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(678.5455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1616.8074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.7065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.2737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.1908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.9375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1281.4727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.9075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(468.1449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1372.4325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(564.8560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1419.5466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1181.2026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(392.3273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1039.5479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(907.2216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(587.3777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.0142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(856.0237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1040.5732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.6096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.1243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.6352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(760.8875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(658.8940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(604.4519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.7682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1054.7595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(893.2075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.6431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(317.2145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(675.6905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.0814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.5672, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11206896551724138, 'recall': 0.19427148194271482, 'f1': 0.14214123006833712, 'number': 803}, 'P': {'precision': 0.13590733590733592, 'recall': 0.18624338624338624, 'f1': 0.15714285714285714, 'number': 945}, 'overall_precision': 0.12355787123185709, 'overall_recall': 0.18993135011441648, 'overall_f1': 0.14971815107102593, 'overall_accuracy': 0.6559112028910686}
			------------EPOCH 8---------------
Loss:  tensor(392.5585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(385.6101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(526.9139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(489.3456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1159.2800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.3600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.9056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.1414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.7326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(916.6904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.3508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(302.6533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1230.1541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.7642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1221.0514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1056.1312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.5284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1119.8094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1002.9323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.4115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.6003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(663.3015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(814.2572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.4030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(316.4477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.3853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(566.1982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(465.9901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.5660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(510.8293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(954.1668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(773.2761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.8036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(362.9149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(753.7183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.8704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.2037, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.110740122426266, 'recall': 0.24782067247820672, 'f1': 0.15307692307692308, 'number': 803}, 'P': {'precision': 0.10436893203883495, 'recall': 0.0455026455026455, 'f1': 0.06337509211495947, 'number': 945}, 'overall_precision': 0.10955183340878226, 'overall_recall': 0.13844393592677345, 'overall_f1': 0.12231488501389941, 'overall_accuracy': 0.5927882133354513}
			------------EPOCH 9---------------
Loss:  tensor(475.5957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(596.8878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(797.7875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(750.8271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1093.8234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(429.2986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.9140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.9044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.1245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1218.1655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(466.1813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(350.6107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1035.8870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(357.4454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(972.6661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(911.3710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.1379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(929.5968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(755.4586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(487.9008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(735.5337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(879.5704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1249.7314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.4565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(893.5698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(896.0325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1240.0574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(858.1937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(778.2169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(634.7502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.0638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(885.6077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.1465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.7383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(538.6942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.8258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.7408, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.09376401973979363, 'recall': 0.2602739726027397, 'f1': 0.1378627968337731, 'number': 803}, 'P': {'precision': 0.12992125984251968, 'recall': 0.06984126984126984, 'f1': 0.09084652443220922, 'number': 945}, 'overall_precision': 0.10047497259773475, 'overall_recall': 0.15732265446224256, 'overall_f1': 0.12263099219620956, 'overall_accuracy': 0.5980699733926373}
			------------EPOCH 10---------------
Loss:  tensor(340.0650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.3130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.8779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(573.9579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1498.3689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.6485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.1747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.8612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.4973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2007.0811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(797.9391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(624.3739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1986.9033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1150.9783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2308.1025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2609.9609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(509.6581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.1156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1196.7417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(766.5007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(735.8221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(584.9286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(677.4573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.4972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(287.1168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(525.5876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(573.8796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.5316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(497.0584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.0245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(846.5460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(721.4421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(347.9609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(370.1734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(792.7004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(456.3107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.3287, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2247191011235955, 'recall': 0.074719800747198, 'f1': 0.11214953271028037, 'number': 803}, 'P': {'precision': 0.16219178082191782, 'recall': 0.31322751322751324, 'f1': 0.21371841155234658, 'number': 945}, 'overall_precision': 0.1701720841300191, 'overall_recall': 0.2036613272311213, 'overall_f1': 0.18541666666666667, 'overall_accuracy': 0.6463206385767046}
			------------EPOCH 11---------------
Loss:  tensor(522.5099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(381.6671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(881.3421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(473.0442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(969.4933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.1736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.2328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.1772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.6934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1216.4438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.9901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.1654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1177.7360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.1563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1136.7349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(985.3835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.4667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(714.9290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(645.8935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.6524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(519.2939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.4744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.8594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.8773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.6020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.1263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.8959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.0362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.5885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.9241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(659.0165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.8728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.0256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.7170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(432.1143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.1997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.8921, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12540822991508818, 'recall': 0.23910336239103364, 'f1': 0.16452442159383032, 'number': 803}, 'P': {'precision': 0.11574468085106383, 'recall': 0.1439153439153439, 'f1': 0.12830188679245283, 'number': 945}, 'overall_precision': 0.12121212121212122, 'overall_recall': 0.18764302059496568, 'overall_f1': 0.14728334081724295, 'overall_accuracy': 0.6672292601564672}
			------------EPOCH 12---------------
Loss:  tensor(205.3933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.6634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.9481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.3799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(656.7444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.0902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.0496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.4400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.1618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(699.8447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(299.9883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.8530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(933.7374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.6316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(975.0004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(902.7114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(278.0864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.9013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(572.1506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.1082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(431.9828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.5247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.5046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.6280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(361.8708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(352.1652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.7284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.4801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.9518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(502.0233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.9013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.3676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.7189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.8456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.5507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.1750, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18425460636515914, 'recall': 0.136986301369863, 'f1': 0.15714285714285714, 'number': 803}, 'P': {'precision': 0.14750150511739915, 'recall': 0.25925925925925924, 'f1': 0.18802762854950114, 'number': 945}, 'overall_precision': 0.15721877767936226, 'overall_recall': 0.2030892448512586, 'overall_f1': 0.17723414877683474, 'overall_accuracy': 0.6752511814463286}
			------------EPOCH 13---------------
Loss:  tensor(181.0980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.7354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.0499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.8159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(527.8356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.0409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.6471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.0280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(241.6709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(595.2697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.3439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.9234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(679.4897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.4443, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(582.8171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.5651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.2819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(430.1982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.4480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.6642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(371.1232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(360.4724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(391.6916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.0865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.3774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.5654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.4468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.0136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.6326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.4025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(447.3935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(408.4311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.8520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.3260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(290.2372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.1425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.8324, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1888745148771022, 'recall': 0.18181818181818182, 'f1': 0.18527918781725886, 'number': 803}, 'P': {'precision': 0.12285883047844064, 'recall': 0.2201058201058201, 'f1': 0.15769522365428357, 'number': 945}, 'overall_precision': 0.1435523114355231, 'overall_recall': 0.20251716247139587, 'overall_f1': 0.1680113906027527, 'overall_accuracy': 0.6860728326913149}
			------------EPOCH 14---------------
Loss:  tensor(129.1032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.2922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.2791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.0214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(455.9729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.7106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.4182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(382.9065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.6014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.6509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(530.2913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.6975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.5121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.2415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.0535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(301.9517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(355.0200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.9532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.2421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.7446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.0536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.2108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.7536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(232.0959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.1804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.3036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.5849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(228.0410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.9570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.6277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.7588, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.0703, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(247.0464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.1278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.5337, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2028811524609844, 'recall': 0.21046077210460773, 'f1': 0.20660146699266502, 'number': 803}, 'P': {'precision': 0.14932992980216975, 'recall': 0.24761904761904763, 'f1': 0.18630573248407645, 'number': 945}, 'overall_precision': 0.16791666666666666, 'overall_recall': 0.2305491990846682, 'overall_f1': 0.19431051108968178, 'overall_accuracy': 0.68847543783011}
			------------EPOCH 15---------------
Loss:  tensor(100.3216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.3753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.7627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.0267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(394.4727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.4616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.1723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.0205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.5826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(315.5785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.4140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.9566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(437.6218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.9264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.7818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(556.0757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.5810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(245.3627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(297.8681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.8670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(267.1424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(224.4014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.1913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.2165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.0789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.7600, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.7709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.5177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(135.7157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.3744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.1269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.1898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.7705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.4857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.8712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.6599, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19347037484885127, 'recall': 0.199252801992528, 'f1': 0.19631901840490798, 'number': 803}, 'P': {'precision': 0.15181932245922208, 'recall': 0.2560846560846561, 'f1': 0.19062623079952737, 'number': 945}, 'overall_precision': 0.16604708798017348, 'overall_recall': 0.2299771167048055, 'overall_f1': 0.1928520028783881, 'overall_accuracy': 0.6934394980342321}
			------------EPOCH 16---------------
Loss:  tensor(74.5129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.5433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.9238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.5541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.0229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.7044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.8446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.0707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.3375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.6831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.6607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(379.0118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.5135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.8885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(528.9458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.7141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.1844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(281.7458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.3087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.3653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.8982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.2305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(43.7762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.6991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.9377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.3860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.6601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.0105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.2391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.9349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.9638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.9528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.3198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.5853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.8145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1328, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2217453505007153, 'recall': 0.1930261519302615, 'f1': 0.20639147802929425, 'number': 803}, 'P': {'precision': 0.14344991108476585, 'recall': 0.2560846560846561, 'f1': 0.18389057750759877, 'number': 945}, 'overall_precision': 0.1663872590108969, 'overall_recall': 0.22711670480549198, 'overall_f1': 0.19206579583938074, 'overall_accuracy': 0.6813867598586235}
			------------EPOCH 17---------------
Loss:  tensor(55.4337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.1743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.2974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.0852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.5265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.2709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.5471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.2077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.9163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.1025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.3247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.7905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.4211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.9921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(257.2807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.7293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.1190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.9710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.1488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.1685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(134.4752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.4418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.7386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.4671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.5955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(265.4888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.4864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.2581, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.0453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.9656, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19976635514018692, 'recall': 0.2129514321295143, 'f1': 0.2061482820976492, 'number': 803}, 'P': {'precision': 0.16513157894736843, 'recall': 0.2656084656084656, 'f1': 0.2036511156186613, 'number': 945}, 'overall_precision': 0.1776094276094276, 'overall_recall': 0.2414187643020595, 'overall_f1': 0.2046556741028128, 'overall_accuracy': 0.6935586354791311}
			------------EPOCH 18---------------
Loss:  tensor(40.9262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.4060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8998, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.6005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.4705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.2820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(212.1183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.1328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.3404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.4325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.8589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(305.0688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(476.8449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(142.0405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.0453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.2462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.5882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.3283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.3346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.9675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.5862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.1030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.1056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.4069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.9456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.8404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.4902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.4602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.2883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.1165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.5377, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21904761904761905, 'recall': 0.20049813200498132, 'f1': 0.2093628088426528, 'number': 803}, 'P': {'precision': 0.1725955204216074, 'recall': 0.27724867724867724, 'f1': 0.21274868047097037, 'number': 945}, 'overall_precision': 0.1877496671105193, 'overall_recall': 0.2419908466819222, 'overall_f1': 0.21144713821544614, 'overall_accuracy': 0.6871053572137723}
			------------EPOCH 19---------------
Loss:  tensor(31.3033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.5348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.6272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(255.9105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.7668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.0071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.6751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.7388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(233.7041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.8270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.2367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.3908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(246.2723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.6719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(244.5397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.3578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.8162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.2040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.7065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.8928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.6200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.3506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.2312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.6743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.2123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2712, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.1946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.5658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5738, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21777221526908636, 'recall': 0.21668742216687423, 'f1': 0.21722846441947566, 'number': 803}, 'P': {'precision': 0.14971572962728996, 'recall': 0.2507936507936508, 'f1': 0.1875, 'number': 945}, 'overall_precision': 0.172544080604534, 'overall_recall': 0.2351258581235698, 'overall_f1': 0.1990314769975787, 'overall_accuracy': 0.6860926889321314}
			------------EPOCH 20---------------
Loss:  tensor(24.3677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.7092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.3603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.8130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.2238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.2238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.6758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.8834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(240.2163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.9167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(207.7182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(395.9518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6533, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.6667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.8475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.5965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.9022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.6158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.4668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.0193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.1411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.9140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.9823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.7748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.2361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.6154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.1806, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2229299363057325, 'recall': 0.21793275217932753, 'f1': 0.22040302267002518, 'number': 803}, 'P': {'precision': 0.14398064125831822, 'recall': 0.2518518518518518, 'f1': 0.18321785989222478, 'number': 945}, 'overall_precision': 0.1694011484823626, 'overall_recall': 0.23627002288329518, 'overall_f1': 0.19732441471571904, 'overall_accuracy': 0.6879988880505142}
			------------EPOCH 21---------------
Loss:  tensor(21.0503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.7852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(248.6293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.5656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.6505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(178.2194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.6176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(237.1562, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.9663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(180.9276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(377.6144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.0126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.1862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(218.3964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.5498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.3293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.3221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.0990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.4345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.2375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.7891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.5409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(122.7322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.9874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.9025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.6197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.2055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.4682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9922, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2220873786407767, 'recall': 0.22789539227895392, 'f1': 0.22495390288875233, 'number': 803}, 'P': {'precision': 0.17684210526315788, 'recall': 0.26666666666666666, 'f1': 0.21265822784810126, 'number': 945}, 'overall_precision': 0.19341929746554024, 'overall_recall': 0.2488558352402746, 'overall_f1': 0.2176632474355767, 'overall_accuracy': 0.6847027520749772}
			------------EPOCH 22---------------
Loss:  tensor(18.3691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.3380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.0406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(349.5279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.6697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.4501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.3699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.7184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.7861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(169.8211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.4066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.3214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.0220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(183.7068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.6113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.3296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.1418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.6292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.7664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.5105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.7018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(229.1708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.3018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.0119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.8060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.1570, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2122905027932961, 'recall': 0.23661270236612703, 'f1': 0.2237926972909305, 'number': 803}, 'P': {'precision': 0.16524590163934427, 'recall': 0.26666666666666666, 'f1': 0.20404858299595144, 'number': 945}, 'overall_precision': 0.18264462809917356, 'overall_recall': 0.2528604118993135, 'overall_f1': 0.21209213051823414, 'overall_accuracy': 0.6823200031769985}
			------------EPOCH 23---------------
Loss:  tensor(23.3775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.8205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.9041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.3138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(239.5683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.8884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.0695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.4036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(181.7140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.9972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.4515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.9995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.2709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(303.3983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.8127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.3492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.7789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2738, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.5140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.2467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(223.2155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.7493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.0200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.0658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.0825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.6418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.4080, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2095730918499353, 'recall': 0.20174346201743462, 'f1': 0.20558375634517767, 'number': 803}, 'P': {'precision': 0.1353904282115869, 'recall': 0.2275132275132275, 'f1': 0.16975917883932096, 'number': 945}, 'overall_precision': 0.15967810249894113, 'overall_recall': 0.21567505720823799, 'overall_f1': 0.18349963494767582, 'overall_accuracy': 0.6904213494301259}
			------------EPOCH 24---------------
Loss:  tensor(27.3650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.5429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.5110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.9589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.4485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.8705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.8914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(186.2435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.0092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.1436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(291.8378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.8235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.8392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.9827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.2568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.0846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.2079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.3836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.6733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.9668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.1193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.8881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.1622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.6133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(170.7668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.0622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.6006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.7402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1728, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2018842530282638, 'recall': 0.18679950186799502, 'f1': 0.19404915912031045, 'number': 803}, 'P': {'precision': 0.13267203967761934, 'recall': 0.22645502645502646, 'f1': 0.1673182173573104, 'number': 945}, 'overall_precision': 0.15449915110356535, 'overall_recall': 0.20823798627002288, 'overall_f1': 0.17738791423001946, 'overall_accuracy': 0.6836900837933363}
			------------EPOCH 25---------------
Loss:  tensor(17.0412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.4378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.7450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.5772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.1637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.8667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.4750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.2437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.9883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(217.7854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(242.4149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.6249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(73.5858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.3077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.8140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.9557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.4224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.4256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.9995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.1539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.4328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.5561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.7793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0894, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22676991150442477, 'recall': 0.25529265255292655, 'f1': 0.2401874633860574, 'number': 803}, 'P': {'precision': 0.19790888722927558, 'recall': 0.2804232804232804, 'f1': 0.23204903677758318, 'number': 945}, 'overall_precision': 0.20954079358002675, 'overall_recall': 0.26887871853546913, 'overall_f1': 0.23552994237033326, 'overall_accuracy': 0.6812676224137246}
			------------EPOCH 26---------------
Loss:  tensor(38.6915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.8137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.2961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(204.1385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.8606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.4120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.1386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.8886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.7289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(175.2323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.9765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.3464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.3796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.1623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.9115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.0145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.4333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.6978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.8210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.8352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.4546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.9241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.9026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7856, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20698924731182797, 'recall': 0.1917808219178082, 'f1': 0.19909502262443438, 'number': 803}, 'P': {'precision': 0.13615560640732266, 'recall': 0.2518518518518518, 'f1': 0.17675454883030078, 'number': 945}, 'overall_precision': 0.15730337078651685, 'overall_recall': 0.2242562929061785, 'overall_f1': 0.1849056603773585, 'overall_accuracy': 0.6881378817362297}
			------------EPOCH 27---------------
Loss:  tensor(13.5318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.6360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(198.1659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.3401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5001, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(22.2984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.0072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.9992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.9950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.2437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.8465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.0855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.2493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(285.8071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.0338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.0927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.7624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.3667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.4107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.2620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.8633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.0469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.7090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.7857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.8921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.9550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.0186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.2936, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20316027088036118, 'recall': 0.22415940224159403, 'f1': 0.21314387211367675, 'number': 803}, 'P': {'precision': 0.16158940397350993, 'recall': 0.2582010582010582, 'f1': 0.19877800407331972, 'number': 945}, 'overall_precision': 0.17696160267111852, 'overall_recall': 0.2425629290617849, 'overall_f1': 0.20463320463320464, 'overall_accuracy': 0.6862118263770303}
			------------EPOCH 28---------------
Loss:  tensor(6.4180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.6860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.5026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.4837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(154.5229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(126.2085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.6101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(145.6431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.8704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.3613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.9745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.7625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.6949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.2511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.1495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.0103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.7424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.6404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.4088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.6060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.5146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6388, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.7190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6670, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24110671936758893, 'recall': 0.22789539227895392, 'f1': 0.23431498079385404, 'number': 803}, 'P': {'precision': 0.16934404283801874, 'recall': 0.2677248677248677, 'f1': 0.2074620746207462, 'number': 945}, 'overall_precision': 0.1935197514425211, 'overall_recall': 0.2494279176201373, 'overall_f1': 0.21794551362159462, 'overall_accuracy': 0.6868075136015249}
			------------EPOCH 29---------------
Loss:  tensor(5.1220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.1605, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(165.7901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.8104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.5917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6904, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.3624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.9885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.1853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(276.8426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.5554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.5244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.0934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.9408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.2101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.9465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.4550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.2815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6461, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.5344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7231, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2014388489208633, 'recall': 0.24408468244084683, 'f1': 0.22072072072072071, 'number': 803}, 'P': {'precision': 0.15514905149051492, 'recall': 0.24232804232804234, 'f1': 0.1891780256092524, 'number': 945}, 'overall_precision': 0.1735402204981625, 'overall_recall': 0.2431350114416476, 'overall_f1': 0.2025256135334763, 'overall_accuracy': 0.6952861284301656}
			------------EPOCH 30---------------
Loss:  tensor(4.8555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(185.4155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.7037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.6287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.9706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.2297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.3151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.0277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.9413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.3206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.9447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.0775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.3884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.3717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.3195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.1880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.2317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.2880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.9926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.5572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.0859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.7042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4388, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22744599745870395, 'recall': 0.22291407222914073, 'f1': 0.2251572327044025, 'number': 803}, 'P': {'precision': 0.15968586387434555, 'recall': 0.2582010582010582, 'f1': 0.19733117670845124, 'number': 945}, 'overall_precision': 0.18272138228941684, 'overall_recall': 0.2419908466819222, 'overall_f1': 0.2082205267044056, 'overall_accuracy': 0.68587427028315}


		-------------RUN 5-----------
			------------EPOCH 1---------------
Loss:  tensor(2974.6179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2778.8179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2106.4824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2154.1194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3157.8696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2730.0979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2153.5779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1940.0206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1758.8403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1801.4473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2604.7397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1306.0121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2143.2900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2046.8135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2538.0867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2237.0161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1876.6213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(854.6818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(924.2438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1584.9730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1780.0538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1252.2249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2438.7710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1322.1768, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1602.8779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2077.4614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2042.4060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1450.8483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2428.8809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1385.0280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2271.6025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.4587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2360.1094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1343.1572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3787.6589, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.043219076005961254, 'recall': 0.037371134020618556, 'f1': 0.040082930200414646, 'number': 776}, 'P': {'precision': 0.09176984705025491, 'recall': 0.13861386138613863, 'f1': 0.11042944785276074, 'number': 909}, 'overall_precision': 0.07583170254403131, 'overall_recall': 0.09198813056379822, 'overall_f1': 0.08313220702601233, 'overall_accuracy': 0.5893334873068115}
			------------EPOCH 2---------------
Loss:  tensor(1746.8689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1643.5474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1225.9613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1162.7118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2139.9517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1883.5029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1525.4260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1321.9038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1285.2341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1337.5317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1917.4502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(918.6894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1626.4135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1577.0295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2096.8057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1633.5994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1585.2739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(722.7907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(714.5201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.5160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1325.9817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1043.8704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1889.4668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1288.4753, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1468.9548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1720.7014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1590.1952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1074.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2067.5747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1209.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1798.3082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(832.9887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2090.3293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1151.9238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3446.3188, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.03802672147995889, 'recall': 0.04768041237113402, 'f1': 0.04230989136649514, 'number': 776}, 'P': {'precision': 0.07472712006717044, 'recall': 0.09790979097909791, 'f1': 0.08476190476190476, 'number': 909}, 'overall_precision': 0.05822550831792976, 'overall_recall': 0.07477744807121661, 'overall_f1': 0.06547155105222136, 'overall_accuracy': 0.5934715245298997}
			------------EPOCH 3---------------
Loss:  tensor(1528.1006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1393.4568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1081.1459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1014.6469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1926.8326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1602.4106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1333.1606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1197.4437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1112.2095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1100.5315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1595.2902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(790.2014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1366.7622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1377.8621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1861.8926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1410.8431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1276.8356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(620.4781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(649.2350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1024.2555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1115.7441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(847.5809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1636.2583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1155.6489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1320.8512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1515.4377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1491.4103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(899.0459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1832.4475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1073.9419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1526.4890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(692.6215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1729.0403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1028.5178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3212.8992, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.03758020164986251, 'recall': 0.05283505154639175, 'f1': 0.04392072844134976, 'number': 776}, 'P': {'precision': 0.05611775528978841, 'recall': 0.0671067106710671, 'f1': 0.061122244488977955, 'number': 909}, 'overall_precision': 0.046831955922865015, 'overall_recall': 0.060534124629080116, 'overall_f1': 0.05280869790318406, 'overall_accuracy': 0.5838866755201416}
			------------EPOCH 4---------------
Loss:  tensor(1351.3188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1198.9587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(928.4893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(862.6715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1805.1436, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1421.7208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1239.0466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1109.6978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(978.0816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(913.0459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1404.0225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(740.6589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1219.1715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1123.6503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1657.2518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1203.0631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1092.8164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.1144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(583.4147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(836.0449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(898.3312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.9399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1373.8914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1127.7607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1178.9447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1267.1013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1412.5999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(714.9902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1626.5382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(970.8740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1230.4155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(537.1685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1522.6440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(905.6624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2971.4121, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.05036726128016789, 'recall': 0.061855670103092786, 'f1': 0.05552342394447658, 'number': 776}, 'P': {'precision': 0.04883227176220807, 'recall': 0.07590759075907591, 'f1': 0.05943152454780362, 'number': 909}, 'overall_precision': 0.04945054945054945, 'overall_recall': 0.06943620178041543, 'overall_f1': 0.05776351518143668, 'overall_accuracy': 0.6060781030467502}
			------------EPOCH 5---------------
Loss:  tensor(1144.1328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1031.0698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(793.9855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(687.4532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1439.1135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1214.4431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1042.2285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(966.1456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(904.4290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(771.8909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1341.7568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(713.0780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1260.5511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1014.1293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1760.8713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1465.4968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1034.2734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.7559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(493.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(770.7394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(754.7579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(557.5958, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1209.7162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(999.4146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1007.5743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(998.6263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1149.0623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(499.8439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1517.0549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(930.6173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1094.1479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(492.8835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1574.5225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(912.9429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3079.2200, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0736196319018405, 'recall': 0.030927835051546393, 'f1': 0.04355716878402904, 'number': 776}, 'P': {'precision': 0.132857779759251, 'recall': 0.3278327832783278, 'f1': 0.18908629441624367, 'number': 909}, 'overall_precision': 0.12534059945504086, 'overall_recall': 0.1910979228486647, 'overall_f1': 0.15138692994828395, 'overall_accuracy': 0.626421848836538}
			------------EPOCH 6---------------
Loss:  tensor(1216.9255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1240.5918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1011.4280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(809.9092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1430.0144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1241.2543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.9375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(919.5571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(937.3399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(818.1819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1346.3684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(562.0973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(996.0548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1127.0840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1549.0431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1179.2380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1019.1409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(482.2028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.4892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(803.6796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(651.4523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(495.5858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1175.4727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(879.8970, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.1741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1254.9192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1255.0325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(544.5127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1601.2360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(824.1110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1159.6279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.3016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1228.7504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(843.3112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2635.1372, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12561819980217606, 'recall': 0.163659793814433, 'f1': 0.14213766088416338, 'number': 776}, 'P': {'precision': 0.20016680567139283, 'recall': 0.264026402640264, 'f1': 0.22770398481973436, 'number': 909}, 'overall_precision': 0.16606334841628959, 'overall_recall': 0.2178041543026706, 'overall_f1': 0.1884467265725289, 'overall_accuracy': 0.606944203860885}
			------------EPOCH 7---------------
Loss:  tensor(1042.6730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(943.9490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(706.1852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(609.4934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1332.2478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1039.2656, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1021.9419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(886.3853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(935.7389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(815.3480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1358.2245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(486.4312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(934.3413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1268.4026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1604.3198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.1021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(793.7963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(335.5734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(422.9367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(637.8033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(680.6781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(457.2710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1014.8899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(697.9485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(913.4371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(907.5000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1042.9758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(416.6847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1298.7534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(660.2668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(943.5239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.1283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1088.5608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(691.5316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1992.1675, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10952804986642921, 'recall': 0.15850515463917525, 'f1': 0.12954186413902055, 'number': 776}, 'P': {'precision': 0.05431502715751358, 'recall': 0.09900990099009901, 'f1': 0.07014809041309432, 'number': 909}, 'overall_precision': 0.07661870503597122, 'overall_recall': 0.12640949554896141, 'overall_f1': 0.09540873460246359, 'overall_accuracy': 0.642897010989857}
			------------EPOCH 8---------------
Loss:  tensor(836.3088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.1994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(503.5258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(428.4909, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(981.0170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(871.8165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(769.9104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(688.4708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(711.8589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(524.9401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1045.6855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.6106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(696.2537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(674.7593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1084.6416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(714.9963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(695.4066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.2256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.4897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(403.5044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(454.6635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.7702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(785.2340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(703.6206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(735.6994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(723.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(807.1854, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.3771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1039.3284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(490.5826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(599.7812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.2505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(786.0906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(522.8851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1680.1134, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15468940316686966, 'recall': 0.163659793814433, 'f1': 0.15904821540388228, 'number': 776}, 'P': {'precision': 0.1181462140992167, 'recall': 0.19911991199119913, 'f1': 0.14829987709954937, 'number': 909}, 'overall_precision': 0.13089672758181045, 'overall_recall': 0.1827893175074184, 'overall_f1': 0.15255076770678555, 'overall_accuracy': 0.6583713455357315}
			------------EPOCH 9---------------
Loss:  tensor(730.2105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(616.5427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(396.3754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(340.3711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(746.6167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(690.7974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(593.5658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(571.6262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(655.9666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(434.1627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1018.6421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(329.7076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(464.7986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(531.5037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(774.7109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(508.5137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(467.8303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(222.2791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.3019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.6704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.2924, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(213.5851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(602.8771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(417.4057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(634.3928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(591.0375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(659.1414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(195.3157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(835.3077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(367.2295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(445.2282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(216.9431, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(652.4415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.1138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1418.2728, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16801437556154536, 'recall': 0.24097938144329897, 'f1': 0.19798835362625727, 'number': 776}, 'P': {'precision': 0.1469090909090909, 'recall': 0.2222222222222222, 'f1': 0.17688266199649738, 'number': 909}, 'overall_precision': 0.15635048231511253, 'overall_recall': 0.2308605341246291, 'overall_f1': 0.1864366163431584, 'overall_accuracy': 0.6442057855534384}
			------------EPOCH 10---------------
Loss:  tensor(603.1561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(536.8716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(324.3968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(256.4759, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(614.0870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(521.1242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(518.3927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.7420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(507.4815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.1153, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(812.1142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.8435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(346.3838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.0528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(625.1144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.7010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(390.8765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.4087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.9031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.1783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(294.0590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.6288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(436.1660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(309.2031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(568.1477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(494.3911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.8433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(152.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(689.6681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(280.1173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(333.2524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.1550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(559.7182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(363.5118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1113.2759, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17454545454545456, 'recall': 0.24742268041237114, 'f1': 0.20469083155650322, 'number': 776}, 'P': {'precision': 0.13402061855670103, 'recall': 0.2002200220022002, 'f1': 0.16056462284958095, 'number': 909}, 'overall_precision': 0.15215622457282343, 'overall_recall': 0.22195845697329378, 'overall_f1': 0.1805454984310886, 'overall_accuracy': 0.6590449795022807}
			------------EPOCH 11---------------
Loss:  tensor(467.5559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(406.9887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.0601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.6116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(459.7234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.5939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(373.7587, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.1355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.2172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(263.4595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(672.2830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(177.4365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(284.9124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(409.5360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(555.9710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(311.9141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(326.8224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(147.3915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(184.9090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.7834, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(238.5247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.9505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(321.3792, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.3419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(512.7373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(411.5840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(435.4805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(94.7089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(554.0959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(203.9214, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.0359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(504.1489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(307.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(913.5349, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14973821989528796, 'recall': 0.18427835051546393, 'f1': 0.16522241478913924, 'number': 776}, 'P': {'precision': 0.08037825059101655, 'recall': 0.1496149614961496, 'f1': 0.10457516339869281, 'number': 909}, 'overall_precision': 0.10540234227427277, 'overall_recall': 0.1655786350148368, 'overall_f1': 0.128808864265928, 'overall_accuracy': 0.6519621995111342}
			------------EPOCH 12---------------
Loss:  tensor(378.1235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(348.6732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.1526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.7532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(369.8232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(383.3978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(331.4034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.1575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(295.8005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.1981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(553.4380, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.6458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.4018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(323.5988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(423.9695, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(261.9174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(273.9261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.7182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.4216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.6927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.8986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.2899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.3546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(208.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(405.1589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(332.1565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(399.0536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.6371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(515.1074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(196.9285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(219.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.4790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.0383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(271.0791, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(828.2221, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18551042810098792, 'recall': 0.21778350515463918, 'f1': 0.20035566093657378, 'number': 776}, 'P': {'precision': 0.13102595797280595, 'recall': 0.23322332233223322, 'f1': 0.16778789077958053, 'number': 909}, 'overall_precision': 0.1506524317912218, 'overall_recall': 0.22611275964391692, 'overall_f1': 0.18082581869957282, 'overall_accuracy': 0.6677829743826625}
			------------EPOCH 13---------------
Loss:  tensor(309.4771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(313.4427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.7434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(124.3577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.9076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(354.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(283.5607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(199.2051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(272.5036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(179.5782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(496.1074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.2878, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.2680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(341.1614, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(433.4056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(310.9946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.1078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.4557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.2048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.6994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.0085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.5457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.3847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.6270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(359.7199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(296.8048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(336.5856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.2347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.7074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(157.6296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.6200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(328.1189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(312.5473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1056.3916, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18314255983350677, 'recall': 0.2268041237113402, 'f1': 0.20264824409902132, 'number': 776}, 'P': {'precision': 0.1810070108349267, 'recall': 0.3124312431243124, 'f1': 0.22921711057304278, 'number': 909}, 'overall_precision': 0.18181818181818182, 'overall_recall': 0.27299703264094954, 'overall_f1': 0.21826809015421114, 'overall_accuracy': 0.6530977539118886}
			------------EPOCH 14---------------
Loss:  tensor(315.6855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(365.7519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(136.4168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.2556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(308.4802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(275.4145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(300.8685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(249.3384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(259.3585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.5368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(552.0101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.0645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.3203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(322.0803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(401.2416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(262.2281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.7521, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(99.1230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.6193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.2040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.2391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(190.6870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.9182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(410.1481, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(338.5158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(439.3578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(449.1288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(209.7874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(221.8726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.9741, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(345.4246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(253.1682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(772.1794, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1745362563237774, 'recall': 0.2667525773195876, 'f1': 0.2110091743119266, 'number': 776}, 'P': {'precision': 0.10175438596491228, 'recall': 0.15951595159515952, 'f1': 0.12425021422450729, 'number': 909}, 'overall_precision': 0.1348142474147836, 'overall_recall': 0.20890207715133532, 'overall_f1': 0.1638733705772812, 'overall_accuracy': 0.6542140616278846}
			------------EPOCH 15---------------
Loss:  tensor(248.0926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(274.7020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.9911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.4400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.5492, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.3793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(227.6171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.7915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(162.3962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.4840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(376.3317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.6880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.2342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(266.1640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(374.2449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(236.2163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(164.7493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.1403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(125.0874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(159.6089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.6398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(243.8518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(205.3073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(404.2620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.3243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(491.5486, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.1952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(298.4230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.2278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(144.4746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(234.1564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(176.4453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(662.2928, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1723834652594547, 'recall': 0.25257731958762886, 'f1': 0.20491374803972817, 'number': 776}, 'P': {'precision': 0.1072463768115942, 'recall': 0.1628162816281628, 'f1': 0.1293141109654871, 'number': 909}, 'overall_precision': 0.13667063965037743, 'overall_recall': 0.20415430267062315, 'overall_f1': 0.16373155640171347, 'overall_accuracy': 0.664684258136536}
			------------EPOCH 16---------------
Loss:  tensor(182.0508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(214.3433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.6900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(60.1292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.9457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(211.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.2821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.5360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.6174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(458.2021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.9291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.0439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.3187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(387.1865, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(289.9911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(103.9095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(54.6500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.7831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.4165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.3835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.4622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.5445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.4732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.4766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(188.2500, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(337.3628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.7302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.6378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(83.4098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.7894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.6224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(193.5965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.2790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(570.7205, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19558359621451105, 'recall': 0.15979381443298968, 'f1': 0.17588652482269504, 'number': 776}, 'P': {'precision': 0.13561924257932445, 'recall': 0.2915291529152915, 'f1': 0.18512050296891372, 'number': 909}, 'overall_precision': 0.15030911901081917, 'overall_recall': 0.2308605341246291, 'overall_f1': 0.18207348467119122, 'overall_accuracy': 0.6681294147083164}
			------------EPOCH 17---------------
Loss:  tensor(176.8829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(231.2569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(82.5028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.4110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.1136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(189.3675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.0699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.2563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.3772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(105.7039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(264.6675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.6004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.6861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.4917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(220.4644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.7888, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.1599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(46.6048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.3984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.2572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.6390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.4764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(182.8640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.0341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(286.2106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.4313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(197.7952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.4774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(158.1505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.8929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(513.1888, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17346053772766695, 'recall': 0.25773195876288657, 'f1': 0.20736132711249353, 'number': 776}, 'P': {'precision': 0.11740890688259109, 'recall': 0.19141914191419143, 'f1': 0.14554579673776666, 'number': 909}, 'overall_precision': 0.14193548387096774, 'overall_recall': 0.22195845697329378, 'overall_f1': 0.17314814814814816, 'overall_accuracy': 0.6586215524375926}
			------------EPOCH 18---------------
Loss:  tensor(112.5746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(174.6972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.2597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.7841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(114.8293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.0988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.3628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.7232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.3434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(210.9613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.0975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.0452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(146.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(168.8430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(127.8689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.2330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(34.5146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.9024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.9345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.4282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.0528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(191.6798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(167.8901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(192.3893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(171.9126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.2826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.5427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.8552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.2913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(488.2386, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18729817007534985, 'recall': 0.22422680412371135, 'f1': 0.20410557184750736, 'number': 776}, 'P': {'precision': 0.13217703349282298, 'recall': 0.24312431243124313, 'f1': 0.17125145292522279, 'number': 909}, 'overall_precision': 0.1518646674356017, 'overall_recall': 0.2344213649851632, 'overall_f1': 0.1843210452636491, 'overall_accuracy': 0.6670900937313547}
			------------EPOCH 19---------------
Loss:  tensor(84.8560, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.7350, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.5523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.1457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(118.9536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.2384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.9943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.3054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.4984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(194.8084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.4490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.4227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(143.9586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(161.6362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(107.2812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.2971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.7992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.7554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.0913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1547, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.9981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.0089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.7864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.4372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.5559, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.5317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(156.0525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.6347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(44.6847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.8482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.0138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(421.3889, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15515515515515516, 'recall': 0.19974226804123713, 'f1': 0.17464788732394368, 'number': 776}, 'P': {'precision': 0.115995115995116, 'recall': 0.20902090209020902, 'f1': 0.14919513152728703, 'number': 909}, 'overall_precision': 0.13083048919226395, 'overall_recall': 0.20474777448071216, 'overall_f1': 0.15964831096714485, 'overall_accuracy': 0.6631060299863348}
			------------EPOCH 20---------------
Loss:  tensor(67.6384, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.4634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.9059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.9102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.4969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(62.6794, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(163.9528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.0256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(49.0776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(140.9776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(148.4505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(96.6273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.3971, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.6535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.2616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.3981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.8805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(130.2722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.2167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(141.0763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(137.3405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.1256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.5204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.0260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(79.1381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(388.8467, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18127490039840638, 'recall': 0.2345360824742268, 'f1': 0.20449438202247192, 'number': 776}, 'P': {'precision': 0.14544319600499375, 'recall': 0.2563256325632563, 'f1': 0.18558343289526083, 'number': 909}, 'overall_precision': 0.15924788948580199, 'overall_recall': 0.24629080118694363, 'overall_f1': 0.19342810533675134, 'overall_accuracy': 0.6632022634101276}
			------------EPOCH 21---------------
Loss:  tensor(65.3316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(119.9247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.0850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.2716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.6144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.9684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.4518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.1145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.0736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.4773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.5421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.5308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(102.4807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.4835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.3543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.0074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.4716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.0397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.9678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.1440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(131.2809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(116.8051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(155.7991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.2152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.9056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(33.1541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.4156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(80.4247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(76.8644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(375.0782, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17114695340501793, 'recall': 0.24613402061855671, 'f1': 0.2019027484143763, 'number': 776}, 'P': {'precision': 0.11630847029077118, 'recall': 0.20242024202420242, 'f1': 0.1477318346045765, 'number': 909}, 'overall_precision': 0.13899184581171237, 'overall_recall': 0.22255192878338279, 'overall_f1': 0.17111567419575635, 'overall_accuracy': 0.6563311969513251}
			------------EPOCH 22---------------
Loss:  tensor(55.3326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.1495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.2732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.9698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.1611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.1984, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.8364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.9319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(21.8286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(128.3927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.4154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.6570, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(87.5277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(121.3800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(70.6761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.8612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.6531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.9673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.4286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.0906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.8166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.3552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(150.5157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(153.6746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(133.3140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.8138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(61.3325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(334.4385, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18339529120198264, 'recall': 0.19072164948453607, 'f1': 0.18698673404927352, 'number': 776}, 'P': {'precision': 0.13485714285714287, 'recall': 0.25962596259625964, 'f1': 0.17751034223392256, 'number': 909}, 'overall_precision': 0.15017598748533437, 'overall_recall': 0.22789317507418397, 'overall_f1': 0.18104667609618105, 'overall_accuracy': 0.6680524279692823}
			------------EPOCH 23---------------
Loss:  tensor(48.6889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(100.3893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.0928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.5197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.3727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5987, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(15.7404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.5848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(123.8107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.5238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.2087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(108.7007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(149.5371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.9093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(16.7664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.2665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.1014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3949, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(27.7370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(120.1173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(111.8936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(132.4463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.6146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.7735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1444, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.8853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.2915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(353.2953, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16456692913385826, 'recall': 0.2693298969072165, 'f1': 0.20430107526881722, 'number': 776}, 'P': {'precision': 0.1405367231638418, 'recall': 0.21892189218921893, 'f1': 0.17118279569892472, 'number': 909}, 'overall_precision': 0.1518987341772152, 'overall_recall': 0.24213649851632046, 'overall_f1': 0.18668496911461907, 'overall_accuracy': 0.649017456743076}
			------------EPOCH 24---------------
Loss:  tensor(47.0447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(98.2885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.7601, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.1146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.9896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.3647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.1300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.5212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(112.7010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(67.0602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(115.5047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(151.3957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(52.9671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.8438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.6553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(24.3268, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8709, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(97.4686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.1580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(109.1219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5501, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(101.0895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(28.6339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.4467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.9179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.3470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(427.5147, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1863013698630137, 'recall': 0.17525773195876287, 'f1': 0.1806108897742364, 'number': 776}, 'P': {'precision': 0.10922587486744433, 'recall': 0.22662266226622663, 'f1': 0.1474060822898032, 'number': 909}, 'overall_precision': 0.13073394495412843, 'overall_recall': 0.2029673590504451, 'overall_f1': 0.15903278307370378, 'overall_accuracy': 0.6622399291722001}
			------------EPOCH 25---------------
Loss:  tensor(64.6180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(129.2647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.4637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.1101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(88.7650, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.6531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.7694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.8894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.7736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.4508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(65.4336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.7931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(55.2457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(12.5398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.9532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.6509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.8554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.3438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.8898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(139.3089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.7276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.5983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(36.8551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(56.2467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.0906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(293.1981, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17959895379250218, 'recall': 0.2654639175257732, 'f1': 0.21424856994279773, 'number': 776}, 'P': {'precision': 0.14342629482071714, 'recall': 0.2376237623762376, 'f1': 0.17888198757763976, 'number': 909}, 'overall_precision': 0.15906520919713532, 'overall_recall': 0.25044510385756674, 'overall_f1': 0.1945597049331489, 'overall_accuracy': 0.659333679773659}
			------------EPOCH 26---------------
Loss:  tensor(37.1901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(81.7367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.3722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(90.6205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.4573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.9274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.9530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(104.5732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(39.4911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(63.0641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(91.6313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.3211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0275, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.6528, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.0441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.4974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.9101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(47.8755, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.0589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(166.3805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(160.6341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(110.3219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(106.4204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.5948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(18.6142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.8537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(38.0884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(260.2289, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1720881427072403, 'recall': 0.211340206185567, 'f1': 0.18970503181029497, 'number': 776}, 'P': {'precision': 0.12990196078431374, 'recall': 0.23322332233223322, 'f1': 0.16686343959071234, 'number': 909}, 'overall_precision': 0.14545454545454545, 'overall_recall': 0.22314540059347182, 'overall_f1': 0.17611241217798596, 'overall_accuracy': 0.6662817329714956}
			------------EPOCH 27---------------
Loss:  tensor(32.4109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(92.5894, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.8093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.0396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.7247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.8884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(8.0323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.1228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.8993, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(64.8410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(93.4234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.7450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.7997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(26.3754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.8837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(117.1599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.2667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(85.6827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(113.0824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.3234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(50.0599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.7283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(235.6243, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.15780141843971632, 'recall': 0.22938144329896906, 'f1': 0.1869747899159664, 'number': 776}, 'P': {'precision': 0.11717296962182269, 'recall': 0.2079207920792079, 'f1': 0.14988104678826328, 'number': 909}, 'overall_precision': 0.13389273987595768, 'overall_recall': 0.2178041543026706, 'overall_f1': 0.16583822864889292, 'overall_accuracy': 0.6543872817907116}
			------------EPOCH 28---------------
Loss:  tensor(30.2190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(95.0103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.1204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.9376, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(66.6203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.6125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(7.1686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.3760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.9378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.9161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(40.8976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(68.6425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(35.7423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.0688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.4400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.0727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.6440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(13.4686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.0642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(78.9146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.2063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(84.0819, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(89.0425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.0546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(45.7931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(215.5133, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18596491228070175, 'recall': 0.20489690721649484, 'f1': 0.19497240956468426, 'number': 776}, 'P': {'precision': 0.13872491145218419, 'recall': 0.2585258525852585, 'f1': 0.18056089127929312, 'number': 909}, 'overall_precision': 0.15457041977245978, 'overall_recall': 0.2338278931750742, 'overall_f1': 0.1861124232404346, 'overall_accuracy': 0.669091748946244}
			------------EPOCH 29---------------
Loss:  tensor(25.8886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(59.6046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(37.1271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.2523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.7625, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.5627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.7308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(74.6892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(19.3757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(31.3776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(57.7991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.5849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(6.4798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.7931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.2265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(20.5731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(71.5992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.0788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(86.8935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(72.2726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.9078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(11.3257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(42.1975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.2668, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(206.8389, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16740088105726872, 'recall': 0.24484536082474226, 'f1': 0.19884877027734169, 'number': 776}, 'P': {'precision': 0.13102998696219034, 'recall': 0.22112211221122113, 'f1': 0.16455178059762585, 'number': 909}, 'overall_precision': 0.1464968152866242, 'overall_recall': 0.23204747774480713, 'overall_f1': 0.1796049609554433, 'overall_accuracy': 0.6576977115691822}
			------------EPOCH 30---------------
Loss:  tensor(21.8905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(48.0531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(29.3784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(25.6686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(14.3627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.3770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(4.6999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.8583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(75.7121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(17.5242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(32.4546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(58.3061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(23.7283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(5.8579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3892, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.5514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(10.1667, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.6115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(53.9628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(51.7261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(77.2751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(69.7722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.2448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(9.8149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(41.8483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(30.9745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(200.0934, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17819706498951782, 'recall': 0.2190721649484536, 'f1': 0.19653179190751446, 'number': 776}, 'P': {'precision': 0.13273809523809524, 'recall': 0.24532453245324531, 'f1': 0.17226728466589417, 'number': 909}, 'overall_precision': 0.1492027334851936, 'overall_recall': 0.23323442136498515, 'overall_f1': 0.18198657096550128, 'overall_accuracy': 0.6673210539484574}
