Tokenizer: bert-base-cased Model: bert-base-cased
	Data split: 1k
			------------EPOCH 1---------------
Loss:  tensor(0.2655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3729, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3031}, 'overall_precision': 0.0, 'overall_recall': 0.0, 'overall_f1': 0.0, 'overall_accuracy': 0.4413991583632424}
			------------EPOCH 2---------------
Loss:  tensor(0.2239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3095, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3031}, 'overall_precision': 0.0, 'overall_recall': 0.0, 'overall_f1': 0.0, 'overall_accuracy': 0.44145772155711166}
			------------EPOCH 3---------------
Loss:  tensor(0.1957, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2731, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3031}, 'overall_precision': 0.0, 'overall_recall': 0.0, 'overall_f1': 0.0, 'overall_accuracy': 0.4435325318541944}
			------------EPOCH 4---------------
Loss:  tensor(0.1724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2469, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.017094017094017096, 'recall': 0.001128668171557562, 'f1': 0.002117522498676548, 'number': 1772}, 'P': {'precision': 0.019927536231884056, 'recall': 0.007258330583965688, 'f1': 0.01064087061668682, 'number': 3031}, 'overall_precision': 0.019656019656019656, 'overall_recall': 0.004996876951905059, 'overall_f1': 0.00796812749003984, 'overall_accuracy': 0.4804524425034929}
			------------EPOCH 5---------------
Loss:  tensor(0.1519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2176, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.04263565891472868, 'recall': 0.006207674943566591, 'f1': 0.01083743842364532, 'number': 1772}, 'P': {'precision': 0.08656575212866603, 'recall': 0.060376113493896405, 'f1': 0.07113702623906705, 'number': 3031}, 'overall_precision': 0.081787521079258, 'overall_recall': 0.04039142202789923, 'overall_f1': 0.0540766550522648, 'overall_accuracy': 0.533569259342921}
			------------EPOCH 6---------------
Loss:  tensor(0.1321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1859, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.07204610951008646, 'recall': 0.014108352144469526, 'f1': 0.023596035865974516, 'number': 1772}, 'P': {'precision': 0.1313314037626628, 'recall': 0.11976245463543385, 'f1': 0.12528041415012942, 'number': 3031}, 'overall_precision': 0.1247187399549984, 'overall_recall': 0.08078284405579846, 'overall_f1': 0.09805408137477888, 'overall_accuracy': 0.5677116013687055}
			------------EPOCH 7---------------
Loss:  tensor(0.1130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1571, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.09961685823754789, 'recall': 0.029345372460496615, 'f1': 0.045335658238884045, 'number': 1772}, 'P': {'precision': 0.18490679494888757, 'recall': 0.20290333223358628, 'f1': 0.19348749410099103, 'number': 3031}, 'overall_precision': 0.17333679833679833, 'overall_recall': 0.13887153862169477, 'overall_f1': 0.15420182637845334, 'overall_accuracy': 0.6108308443975939}
			------------EPOCH 8---------------
Loss:  tensor(0.0931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1297, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.113997113997114, 'recall': 0.044582392776523705, 'f1': 0.0640973630831643, 'number': 1772}, 'P': {'precision': 0.2463303976514545, 'recall': 0.3045199604091059, 'f1': 0.2723517261729124, 'number': 3031}, 'overall_precision': 0.22567567567567567, 'overall_recall': 0.20861961274203622, 'overall_f1': 0.21681272314183703, 'overall_accuracy': 0.6591956763630583}
			------------EPOCH 9---------------
Loss:  tensor(0.0736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1085, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12734082397003746, 'recall': 0.05756207674943566, 'f1': 0.07928488146132918, 'number': 1772}, 'P': {'precision': 0.29846938775510207, 'recall': 0.3860112174199934, 'f1': 0.3366422097539922, 'number': 3031}, 'overall_precision': 0.26943444185553905, 'overall_recall': 0.26483447845096814, 'overall_f1': 0.26711465770684584, 'overall_accuracy': 0.687406403466941}
			------------EPOCH 10---------------
Loss:  tensor(0.0572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0892, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12557077625570776, 'recall': 0.062076749435665914, 'f1': 0.08308157099697885, 'number': 1772}, 'P': {'precision': 0.3251366120218579, 'recall': 0.43187066974595845, 'f1': 0.37097916961881816, 'number': 3031}, 'overall_precision': 0.2894736842105263, 'overall_recall': 0.2954403497813866, 'overall_f1': 0.29242658423493045, 'overall_accuracy': 0.6939822135214049}
			------------EPOCH 11---------------
Loss:  tensor(0.0430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0727, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14743589743589744, 'recall': 0.09085778781038374, 'f1': 0.11243016759776536, 'number': 1772}, 'P': {'precision': 0.3525252525252525, 'recall': 0.4605740679643682, 'f1': 0.3993706193677586, 'number': 3031}, 'overall_precision': 0.3081947743467934, 'overall_recall': 0.32417239225484074, 'overall_f1': 0.31598173515981737, 'overall_accuracy': 0.7018798785232035}
			------------EPOCH 12---------------
Loss:  tensor(0.0311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0379, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0592, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16229923922231615, 'recall': 0.10835214446952596, 'f1': 0.1299492385786802, 'number': 1772}, 'P': {'precision': 0.37297160243407707, 'recall': 0.4853183767733421, 'f1': 0.4217921146953405, 'number': 3031}, 'overall_precision': 0.32436122488784863, 'overall_recall': 0.3462419321257547, 'overall_f1': 0.33494461228600203, 'overall_accuracy': 0.706096428481791}
			------------EPOCH 13---------------
Loss:  tensor(0.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0564, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17087765957446807, 'recall': 0.14503386004514673, 'f1': 0.1568986568986569, 'number': 1772}, 'P': {'precision': 0.38973577235772355, 'recall': 0.5061035961728803, 'f1': 0.4403617051815702, 'number': 3031}, 'overall_precision': 0.3292279411764706, 'overall_recall': 0.37289194253591507, 'overall_f1': 0.3497022356731427, 'overall_accuracy': 0.7143454726468054}
			------------EPOCH 14---------------
Loss:  tensor(0.0160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0513, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17322372284204346, 'recall': 0.1664785553047404, 'f1': 0.16978417266187049, 'number': 1772}, 'P': {'precision': 0.40286298568507156, 'recall': 0.5199604091059057, 'f1': 0.4539824283450958, 'number': 3031}, 'overall_precision': 0.3332146037399822, 'overall_recall': 0.38954819904226523, 'overall_f1': 0.35918602418890383, 'overall_accuracy': 0.7188548385747392}
			------------EPOCH 15---------------
Loss:  tensor(0.0119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0337, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16959887403237156, 'recall': 0.13600451467268623, 'f1': 0.15095521453178828, 'number': 1772}, 'P': {'precision': 0.39866204162537167, 'recall': 0.5308479049818542, 'f1': 0.45535587943964906, 'number': 3031}, 'overall_precision': 0.339014110317024, 'overall_recall': 0.38517593170934833, 'overall_f1': 0.3606237816764133, 'overall_accuracy': 0.7153745116247939}
			------------EPOCH 16---------------
Loss:  tensor(0.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0313, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1716826265389877, 'recall': 0.14164785553047404, 'f1': 0.1552257266542981, 'number': 1772}, 'P': {'precision': 0.4016819193668068, 'recall': 0.535796766743649, 'f1': 0.45914616906983313, 'number': 3031}, 'overall_precision': 0.3405994550408719, 'overall_recall': 0.3903810118675828, 'overall_f1': 0.3637951105937136, 'overall_accuracy': 0.7180349538605694}
			------------EPOCH 17---------------
Loss:  tensor(0.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0235, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1854265402843602, 'recall': 0.17663656884875847, 'f1': 0.18092485549132947, 'number': 1772}, 'P': {'precision': 0.4057345851306775, 'recall': 0.5275486638073243, 'f1': 0.45869191049913943, 'number': 3031}, 'overall_precision': 0.3396695683069817, 'overall_recall': 0.39808453050176973, 'overall_f1': 0.3665644171779141, 'overall_accuracy': 0.7214567176166453}
			------------EPOCH 18---------------
Loss:  tensor(0.0051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0212, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18589360430364615, 'recall': 0.1755079006772009, 'f1': 0.18055152394775034, 'number': 1772}, 'P': {'precision': 0.3964956195244055, 'recall': 0.5225998020455296, 'f1': 0.45089666951323654, 'number': 3031}, 'overall_precision': 0.33433309809456596, 'overall_recall': 0.3945450759941703, 'overall_f1': 0.36195205806513225, 'overall_accuracy': 0.7201934258631797}
			------------EPOCH 19---------------
Loss:  tensor(0.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0152, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17931497649429148, 'recall': 0.15067720090293454, 'f1': 0.16375344986200552, 'number': 1772}, 'P': {'precision': 0.38578680203045684, 'recall': 0.5265588914549654, 'f1': 0.44531250000000006, 'number': 3031}, 'overall_precision': 0.331141130465695, 'overall_recall': 0.38788257339163024, 'overall_f1': 0.35727298878128294, 'overall_accuracy': 0.716897154665395}
			------------EPOCH 20---------------
Loss:  tensor(0.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0121, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17456896551724138, 'recall': 0.1371331828442438, 'f1': 0.15360303413400758, 'number': 1772}, 'P': {'precision': 0.37721998579209093, 'recall': 0.5255691191026064, 'f1': 0.4392059553349876, 'number': 3031}, 'overall_precision': 0.3269813000890472, 'overall_recall': 0.38226108682073706, 'overall_f1': 0.35246688423881745, 'overall_accuracy': 0.7147219503216793}
			------------EPOCH 21---------------
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0113, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.17655786350148367, 'recall': 0.1343115124153499, 'f1': 0.15256410256410255, 'number': 1772}, 'P': {'precision': 0.37124765478424016, 'recall': 0.5222698779280766, 'f1': 0.4339958875942426, 'number': 3031}, 'overall_precision': 0.3244832501781896, 'overall_recall': 0.3791380387257964, 'overall_f1': 0.34968795007201153, 'overall_accuracy': 0.7143873034995691}
			------------EPOCH 22---------------
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0083, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1799709724238026, 'recall': 0.1399548532731377, 'f1': 0.15746031746031747, 'number': 1772}, 'P': {'precision': 0.36970837253057387, 'recall': 0.5186407126360937, 'f1': 0.4316902375394755, 'number': 3031}, 'overall_precision': 0.32326820603907636, 'overall_recall': 0.378929835519467, 'overall_f1': 0.3488929358765456, 'overall_accuracy': 0.7145880915928352}
			------------EPOCH 23---------------
Loss:  tensor(0.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0061, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1791988756148981, 'recall': 0.14390519187358916, 'f1': 0.15962441314553988, 'number': 1772}, 'P': {'precision': 0.37034400948991697, 'recall': 0.5150115473441108, 'f1': 0.4308584046370411, 'number': 3031}, 'overall_precision': 0.3221000354735722, 'overall_recall': 0.37809702269414946, 'overall_f1': 0.3478594004405708, 'overall_accuracy': 0.714562993081177}
			------------EPOCH 24---------------
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18626062322946177, 'recall': 0.14841986455981943, 'f1': 0.16520100502512564, 'number': 1772}, 'P': {'precision': 0.3708343181281021, 'recall': 0.5176509402837347, 'f1': 0.4321123657394657, 'number': 3031}, 'overall_precision': 0.3246500088605352, 'overall_recall': 0.3814282739954195, 'overall_f1': 0.35075627034271495, 'overall_accuracy': 0.71524065289595}
			------------EPOCH 25---------------
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0045, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19151943462897528, 'recall': 0.15293453724604966, 'f1': 0.1700658926890493, 'number': 1772}, 'P': {'precision': 0.37189496096522356, 'recall': 0.5186407126360937, 'f1': 0.43317718379718934, 'number': 3031}, 'overall_precision': 0.32665721375398793, 'overall_recall': 0.3837185092650427, 'overall_f1': 0.352896122546673, 'overall_accuracy': 0.715508370353638}
			------------EPOCH 26---------------
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0038, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19144602851323828, 'recall': 0.15914221218961624, 'f1': 0.17380585516178734, 'number': 1772}, 'P': {'precision': 0.3699312307327484, 'recall': 0.5146816232266579, 'f1': 0.4304635761589405, 'number': 3031}, 'overall_precision': 0.323725834797891, 'overall_recall': 0.3835103060587133, 'overall_f1': 0.3510912036595825, 'overall_accuracy': 0.7159517773929339}
			------------EPOCH 27---------------
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0032, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.191699604743083, 'recall': 0.16422121896162528, 'f1': 0.1768996960486322, 'number': 1772}, 'P': {'precision': 0.36649214659685864, 'recall': 0.5080831408775982, 'f1': 0.42582607493432884, 'number': 3031}, 'overall_precision': 0.3201048951048951, 'overall_recall': 0.38122007078909015, 'overall_f1': 0.3479996198802623, 'overall_accuracy': 0.7159099465401702}
			------------EPOCH 28---------------
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18994778067885118, 'recall': 0.16422121896162528, 'f1': 0.1761501210653753, 'number': 1772}, 'P': {'precision': 0.3638948116560057, 'recall': 0.5067634444077862, 'f1': 0.4236072807501379, 'number': 3031}, 'overall_precision': 0.31757343994437687, 'overall_recall': 0.38038725796377265, 'overall_f1': 0.3461538461538462, 'overall_accuracy': 0.7160019744162505}
			------------EPOCH 29---------------
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.19450033534540576, 'recall': 0.1636568848758465, 'f1': 0.17775053631627336, 'number': 1772}, 'P': {'precision': 0.3620241191771104, 'recall': 0.5051138238205213, 'f1': 0.421763085399449, 'number': 3031}, 'overall_precision': 0.3183566433566434, 'overall_recall': 0.3791380387257964, 'overall_f1': 0.3460990211916754, 'overall_accuracy': 0.7156087644002711}
			------------EPOCH 30---------------
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1943487250172295, 'recall': 0.15914221218961624, 'f1': 0.1749922432516289, 'number': 1772}, 'P': {'precision': 0.3609022556390977, 'recall': 0.5067634444077862, 'f1': 0.4215726636475916, 'number': 3031}, 'overall_precision': 0.3185561591028561, 'overall_recall': 0.37851342910680824, 'overall_f1': 0.3459562321598477, 'overall_accuracy': 0.7150984279965531}
	Data split: 6k
			------------EPOCH 1---------------
Loss:  tensor(0.8296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2994, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7276, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.019736842105263157, 'recall': 0.001693002257336343, 'f1': 0.0031185031185031187, 'number': 1772}, 'P': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3031}, 'overall_precision': 0.005199306759098787, 'overall_recall': 0.0006246096189881324, 'overall_f1': 0.0011152416356877324, 'overall_accuracy': 0.44424365635117835}
			------------EPOCH 2---------------
Loss:  tensor(0.6278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6070, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0575139146567718, 'recall': 0.017494356659142212, 'f1': 0.02682821289485071, 'number': 1772}, 'P': {'precision': 0.012135922330097087, 'recall': 0.003299241174529858, 'f1': 0.005188067444876783, 'number': 3031}, 'overall_precision': 0.03008070432868672, 'overall_recall': 0.008536331459504476, 'overall_f1': 0.013298734998378203, 'overall_accuracy': 0.4851960612069038}
			------------EPOCH 3---------------
Loss:  tensor(0.5435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3583, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5297, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1826771653543307, 'recall': 0.0654627539503386, 'f1': 0.09638554216867469, 'number': 1772}, 'P': {'precision': 0.13801224682053698, 'recall': 0.09666776641372485, 'f1': 0.11369809856422196, 'number': 3031}, 'overall_precision': 0.14829586656997826, 'overall_recall': 0.08515511138871538, 'overall_f1': 0.10818674778468458, 'overall_accuracy': 0.6654619381070702}
			------------EPOCH 4---------------
Loss:  tensor(0.4757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2952, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4455, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2253968253968254, 'recall': 0.12020316027088036, 'f1': 0.15679057784320943, 'number': 1772}, 'P': {'precision': 0.319656844461022, 'recall': 0.28274496865720883, 'f1': 0.30007002801120447, 'number': 3031}, 'overall_precision': 0.29509100937672367, 'overall_recall': 0.2227774307724339, 'overall_f1': 0.2538853956578479, 'overall_accuracy': 0.7055442612253093}
			------------EPOCH 5---------------
Loss:  tensor(0.3939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6653, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3793, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20701754385964913, 'recall': 0.1664785553047404, 'f1': 0.18454801376290272, 'number': 1772}, 'P': {'precision': 0.40686750890832524, 'recall': 0.4143846915209502, 'f1': 0.4105916966328865, 'number': 3031}, 'overall_precision': 0.34375, 'overall_recall': 0.32292317301686446, 'overall_f1': 0.33301127214170695, 'overall_accuracy': 0.7246023977444804}
			------------EPOCH 6---------------
Loss:  tensor(0.3037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3145, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23352713178294573, 'recall': 0.27200902934537247, 'f1': 0.25130344108446295, 'number': 1772}, 'P': {'precision': 0.4360587002096436, 'recall': 0.4117452985813263, 'f1': 0.42355336840319024, 'number': 3031}, 'overall_precision': 0.3511977263499797, 'overall_recall': 0.360191546949823, 'overall_f1': 0.355637783944907, 'overall_accuracy': 0.7264178567544278}
			------------EPOCH 7---------------
Loss:  tensor(0.2329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2547, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25555555555555554, 'recall': 0.27257336343115124, 'f1': 0.2637902785363189, 'number': 1772}, 'P': {'precision': 0.4427361154690932, 'recall': 0.465522929726163, 'f1': 0.45384367963975564, 'number': 3031}, 'overall_precision': 0.37305495371282255, 'overall_recall': 0.3943368727878409, 'overall_f1': 0.3834008097165992, 'overall_accuracy': 0.7445975453655598}
			------------EPOCH 8---------------
Loss:  tensor(0.1744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0945, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2123, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2734334541688244, 'recall': 0.2979683972911964, 'f1': 0.28517418309478804, 'number': 1772}, 'P': {'precision': 0.4393505253104107, 'recall': 0.45529528208512043, 'f1': 0.4471808165910564, 'number': 3031}, 'overall_precision': 0.37618296529968454, 'overall_recall': 0.39725171767645223, 'overall_f1': 0.3864303797468354, 'overall_accuracy': 0.7455010917852571}
			------------EPOCH 9---------------
Loss:  tensor(0.1192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1951, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0678, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1767, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23545290941811636, 'recall': 0.44300225733634313, 'f1': 0.30748139443791617, 'number': 1772}, 'P': {'precision': 0.4609297725024728, 'recall': 0.30748927746618276, 'f1': 0.3688897684543835, 'number': 3031}, 'overall_precision': 0.3205750560119492, 'overall_recall': 0.3574849052675411, 'overall_f1': 0.3380253962004134, 'overall_accuracy': 0.6883852454216132}
			------------EPOCH 10---------------
Loss:  tensor(0.0956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1718, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1518, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3136094674556213, 'recall': 0.17945823927765236, 'f1': 0.22828427853553482, 'number': 1772}, 'P': {'precision': 0.4517038175762234, 'recall': 0.581656219069614, 'f1': 0.5085087972310355, 'number': 3031}, 'overall_precision': 0.42322554403091317, 'overall_recall': 0.4332708723714345, 'overall_f1': 0.42818930041152264, 'overall_accuracy': 0.7506462866752002}
			------------EPOCH 11---------------
Loss:  tensor(0.1038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1166, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25778816199376947, 'recall': 0.37358916478555304, 'f1': 0.3050691244239631, 'number': 1772}, 'P': {'precision': 0.43283582089552236, 'recall': 0.4209831738700099, 'f1': 0.42682722863355077, 'number': 3031}, 'overall_precision': 0.35134155184916604, 'overall_recall': 0.40349781386633354, 'overall_f1': 0.37561779242174625, 'overall_accuracy': 0.7380802985049654}
			------------EPOCH 12---------------
Loss:  tensor(0.0485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1220, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26394849785407726, 'recall': 0.48589164785553046, 'f1': 0.3420738974970203, 'number': 1772}, 'P': {'precision': 0.4290894439967768, 'recall': 0.35136918508742987, 'f1': 0.3863595138762924, 'number': 3031}, 'overall_precision': 0.33530640668523676, 'overall_recall': 0.400999375390381, 'overall_f1': 0.3652223381056224, 'overall_accuracy': 0.7180600523722277}
			------------EPOCH 13---------------
Loss:  tensor(0.0441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1265, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.296043656207367, 'recall': 0.36738148984198643, 'f1': 0.32787710904054396, 'number': 1772}, 'P': {'precision': 0.44710695499707775, 'recall': 0.5047838997030683, 'f1': 0.47419804741980476, 'number': 3031}, 'overall_precision': 0.38800925102294964, 'overall_recall': 0.4540911930043723, 'overall_f1': 0.41845740598618575, 'overall_accuracy': 0.7604514385630265}
			------------EPOCH 14---------------
Loss:  tensor(0.0256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0805, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2793594306049822, 'recall': 0.3544018058690745, 'f1': 0.3124378109452736, 'number': 1772}, 'P': {'precision': 0.44979448032883146, 'recall': 0.5054437479379743, 'f1': 0.47599813577753614, 'number': 3031}, 'overall_precision': 0.38203042094092676, 'overall_recall': 0.4497189256714553, 'overall_f1': 0.4131203978196423, 'overall_accuracy': 0.7601586225936802}
			------------EPOCH 15---------------
Loss:  tensor(0.0167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0377, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0909, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28592739930382893, 'recall': 0.3244920993227991, 'f1': 0.30399154110494314, 'number': 1772}, 'P': {'precision': 0.45412579342181186, 'recall': 0.5193005608709996, 'f1': 0.484531322148684, 'number': 3031}, 'overall_precision': 0.3923680847179113, 'overall_recall': 0.4474286904018322, 'overall_f1': 0.4180933852140078, 'overall_accuracy': 0.7614219143471459}
			------------EPOCH 16---------------
Loss:  tensor(0.0114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0687, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28160575194727383, 'recall': 0.2652370203160271, 'f1': 0.27317640220866024, 'number': 1772}, 'P': {'precision': 0.43620414673046254, 'recall': 0.5414054767403497, 'f1': 0.48314441336670094, 'number': 3031}, 'overall_precision': 0.38869453139385013, 'overall_recall': 0.43951696856131584, 'overall_f1': 0.412546413914403, 'overall_accuracy': 0.7593554702206159}
			------------EPOCH 17---------------
Loss:  tensor(0.0084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0623, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26822481914301616, 'recall': 0.27200902934537247, 'f1': 0.27010367049593725, 'number': 1772}, 'P': {'precision': 0.42203299627461416, 'recall': 0.5232596502804355, 'f1': 0.4672263956400059, 'number': 3031}, 'overall_precision': 0.3722772277227723, 'overall_recall': 0.4305642306891526, 'overall_f1': 0.39930488511295614, 'overall_accuracy': 0.7559588049761983}
			------------EPOCH 18---------------
Loss:  tensor(0.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0576, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.271279516749039, 'recall': 0.27878103837471785, 'f1': 0.27497912607848596, 'number': 1772}, 'P': {'precision': 0.4187466808284652, 'recall': 0.5202903332233586, 'f1': 0.4640282477563631, 'number': 3031}, 'overall_precision': 0.37068194021836404, 'overall_recall': 0.43118884030814075, 'overall_f1': 0.3986525505293551, 'overall_accuracy': 0.7572137305591112}
			------------EPOCH 19---------------
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0564, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2740286298568507, 'recall': 0.30248306997742663, 'f1': 0.2875536480686695, 'number': 1772}, 'P': {'precision': 0.4211949175452825, 'recall': 0.514021774991752, 'f1': 0.46300148588410106, 'number': 3031}, 'overall_precision': 0.3702917771883289, 'overall_recall': 0.43597751405371643, 'overall_f1': 0.4004589787722318, 'overall_accuracy': 0.7579248550560952}
			------------EPOCH 20---------------
Loss:  tensor(0.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0662, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2713592233009709, 'recall': 0.3154627539503386, 'f1': 0.29175365344467646, 'number': 1772}, 'P': {'precision': 0.4326655537006121, 'recall': 0.513032002639393, 'f1': 0.46943396226415096, 'number': 3031}, 'overall_precision': 0.37389458790237, 'overall_recall': 0.44014157818030397, 'overall_f1': 0.4043224634216314, 'overall_accuracy': 0.7588618661580036}
			------------EPOCH 21---------------
Loss:  tensor(0.0030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0604, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28454031843862354, 'recall': 0.3126410835214447, 'f1': 0.29792955095455764, 'number': 1772}, 'P': {'precision': 0.4412742382271468, 'recall': 0.5255691191026064, 'f1': 0.4797470260502936, 'number': 3031}, 'overall_precision': 0.38635954651790533, 'overall_recall': 0.4470122839891734, 'overall_f1': 0.41447876447876447, 'overall_accuracy': 0.7606940575090564}
			------------EPOCH 22---------------
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0752, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26978864484044757, 'recall': 0.36738148984198643, 'f1': 0.3111111111111111, 'number': 1772}, 'P': {'precision': 0.44478433771795656, 'recall': 0.4797096667766414, 'f1': 0.4615873015873016, 'number': 3031}, 'overall_precision': 0.3704681450193594, 'overall_recall': 0.43826774932333956, 'overall_f1': 0.4015259895088221, 'overall_accuracy': 0.7554652009135858}
			------------EPOCH 23---------------
Loss:  tensor(0.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0497, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2906166219839142, 'recall': 0.3058690744920993, 'f1': 0.29804784162771514, 'number': 1772}, 'P': {'precision': 0.4389916867792974, 'recall': 0.5400857802705378, 'f1': 0.48431952662721894, 'number': 3031}, 'overall_precision': 0.3895244905255631, 'overall_recall': 0.4536747865917135, 'overall_f1': 0.41915937289602767, 'overall_accuracy': 0.7627103046122699}
			------------EPOCH 24---------------
Loss:  tensor(0.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0579, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30024067388688325, 'recall': 0.2816027088036117, 'f1': 0.2906231799650553, 'number': 1772}, 'P': {'precision': 0.41345915073255524, 'recall': 0.5493236555592214, 'f1': 0.4718050439217909, 'number': 3031}, 'overall_precision': 0.38038319564071016, 'overall_recall': 0.4505517384967728, 'overall_f1': 0.4125047655356462, 'overall_accuracy': 0.7637309774197056}
			------------EPOCH 25---------------
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0427, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2684085510688836, 'recall': 0.31884875846501126, 'f1': 0.2914624709827186, 'number': 1772}, 'P': {'precision': 0.4258849557522124, 'recall': 0.5080831408775982, 'f1': 0.4633669324507297, 'number': 3031}, 'overall_precision': 0.36794266736584513, 'overall_recall': 0.43826774932333956, 'overall_f1': 0.4000380083618396, 'overall_accuracy': 0.7576989684511708}
			------------EPOCH 26---------------
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0407, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26711668273866923, 'recall': 0.3126410835214447, 'f1': 0.2880915236609465, 'number': 1772}, 'P': {'precision': 0.42813112916783413, 'recall': 0.5041240514681623, 'f1': 0.463030303030303, 'number': 3031}, 'overall_precision': 0.3689526847421584, 'overall_recall': 0.4334790755777639, 'overall_f1': 0.39862148190695007, 'overall_accuracy': 0.755900241782329}
			------------EPOCH 27---------------
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0327, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.27481323372465316, 'recall': 0.29063205417607224, 'f1': 0.28250137136588044, 'number': 1772}, 'P': {'precision': 0.41910383686611213, 'recall': 0.5153414714615638, 'f1': 0.4622669428825096, 'number': 3031}, 'overall_precision': 0.3708266381003392, 'overall_recall': 0.432438059546117, 'overall_f1': 0.3992695117262592, 'overall_accuracy': 0.7550050615331844}
			------------EPOCH 28---------------
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0277, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26930792377131396, 'recall': 0.3030474040632054, 'f1': 0.2851832182687202, 'number': 1772}, 'P': {'precision': 0.41712104689203927, 'recall': 0.5047838997030683, 'f1': 0.4567845947156292, 'number': 3031}, 'overall_precision': 0.36506534793359235, 'overall_recall': 0.43035602748282326, 'overall_f1': 0.3950310559006211, 'overall_accuracy': 0.7543274017184114}
			------------EPOCH 29---------------
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0245, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2665036674816626, 'recall': 0.30756207674943564, 'f1': 0.2855645795127063, 'number': 1772}, 'P': {'precision': 0.41963054866280675, 'recall': 0.5021445067634444, 'f1': 0.4571943526584559, 'number': 3031}, 'overall_precision': 0.3644217207334274, 'overall_recall': 0.43035602748282326, 'overall_f1': 0.39465393794749404, 'overall_accuracy': 0.7540262195785123}
			------------EPOCH 30---------------
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0211, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.27106598984771574, 'recall': 0.3013544018058691, 'f1': 0.28540887226082307, 'number': 1772}, 'P': {'precision': 0.41549676025917925, 'recall': 0.5077532167601452, 'f1': 0.45701559020044547, 'number': 3031}, 'overall_precision': 0.36535072259428975, 'overall_recall': 0.4316052467207995, 'overall_f1': 0.3957239667843849, 'overall_accuracy': 0.7539509240435376}
	Data split: 12k
			------------EPOCH 1---------------
Loss:  tensor(3.6811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5106, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.2078822000866176, 'recall': 0.3167271527548664, 'f1': 0.25101320434043667, 'number': 3031}, 'overall_precision': 0.17378711078928313, 'overall_recall': 0.19987507807620236, 'overall_f1': 0.18592040282753944, 'overall_accuracy': 0.6077604598047336}
			------------EPOCH 2---------------
Loss:  tensor(2.8094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2682, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.28405871748647954, 'recall': 0.36390630155064335, 'f1': 0.3190627711888921, 'number': 3031}, 'overall_precision': 0.2823137957512158, 'overall_recall': 0.22964813658130334, 'overall_f1': 0.2532721010332951, 'overall_accuracy': 0.6502606062127183}
			------------EPOCH 3---------------
Loss:  tensor(2.4911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1584, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16666666666666666, 'recall': 0.001128668171557562, 'f1': 0.0022421524663677125, 'number': 1772}, 'P': {'precision': 0.37074045605944145, 'recall': 0.4774001979544705, 'f1': 0.4173637150274012, 'number': 3031}, 'overall_precision': 0.3701149425287356, 'overall_recall': 0.301686445971268, 'overall_f1': 0.3324156916724019, 'overall_accuracy': 0.6844698776029248}
			------------EPOCH 4---------------
Loss:  tensor(2.1823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0021, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25806451612903225, 'recall': 0.004514672686230248, 'f1': 0.00887409872434831, 'number': 1772}, 'P': {'precision': 0.4027072758037225, 'recall': 0.5496535796766744, 'f1': 0.46484375000000006, 'number': 3031}, 'overall_precision': 0.40163147792706333, 'overall_recall': 0.3485321673953779, 'overall_f1': 0.37320254152268423, 'overall_accuracy': 0.6958980665779853}
			------------EPOCH 5---------------
Loss:  tensor(1.9161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8772, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21200750469043153, 'recall': 0.06376975169300225, 'f1': 0.09804772234273319, 'number': 1772}, 'P': {'precision': 0.4146613190730838, 'recall': 0.6139887825800066, 'f1': 0.4950126346588642, 'number': 3031}, 'overall_precision': 0.39314877514439356, 'overall_recall': 0.41099312929419113, 'overall_f1': 0.4018729641693811, 'overall_accuracy': 0.7232303457738289}
			------------EPOCH 6---------------
Loss:  tensor(1.5996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7745, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2, 'recall': 0.14672686230248308, 'f1': 0.16927083333333337, 'number': 1772}, 'P': {'precision': 0.3835552441018454, 'recall': 0.5417354008578027, 'f1': 0.4491247264770241, 'number': 3031}, 'overall_precision': 0.340799139939079, 'overall_recall': 0.39600249843847596, 'overall_f1': 0.3663328197226502, 'overall_accuracy': 0.7406821775468715}
			------------EPOCH 7---------------
Loss:  tensor(1.3265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6437, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25789701427953265, 'recall': 0.3363431151241535, 'f1': 0.29194219936321336, 'number': 1772}, 'P': {'precision': 0.46539379474940334, 'recall': 0.5146816232266579, 'f1': 0.4887983706720978, 'number': 3031}, 'overall_precision': 0.380716934487021, 'overall_recall': 0.44888611284613783, 'overall_f1': 0.4120007643798968, 'overall_accuracy': 0.7706581666373851}
			------------EPOCH 8---------------
Loss:  tensor(1.0236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5535, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20454545454545456, 'recall': 0.345372460496614, 'f1': 0.256926952141058, 'number': 1772}, 'P': {'precision': 0.38721804511278196, 'recall': 0.40778620917189046, 'f1': 0.39723605977824195, 'number': 3031}, 'overall_precision': 0.2988357050452781, 'overall_recall': 0.38475952529668955, 'overall_f1': 0.33639756075361793, 'overall_accuracy': 0.7519681416225351}
			------------EPOCH 9---------------
Loss:  tensor(0.7531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5198, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29818181818181816, 'recall': 0.09255079006772009, 'f1': 0.1412575366063738, 'number': 1772}, 'P': {'precision': 0.42134334953601416, 'recall': 0.629165291982844, 'f1': 0.5046976313351859, 'number': 3031}, 'overall_precision': 0.40799842395587077, 'overall_recall': 0.43118884030814075, 'overall_f1': 0.4192732057900598, 'overall_accuracy': 0.7329769344677861}
			------------EPOCH 10---------------
Loss:  tensor(1.5034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4971, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.16288050885960928, 'recall': 0.404627539503386, 'f1': 0.23226433430515062, 'number': 1772}, 'P': {'precision': 0.23353846153846153, 'recall': 0.25041240514681623, 'f1': 0.24168126094570927, 'number': 3031}, 'overall_precision': 0.19289074751698904, 'overall_recall': 0.30730793254216116, 'overall_f1': 0.23701324769169008, 'overall_accuracy': 0.7095098260673142}
			------------EPOCH 11---------------
Loss:  tensor(0.6711, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1771, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1956, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5200, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.259665320253895, 'recall': 0.25395033860045146, 'f1': 0.25677603423680456, 'number': 1772}, 'P': {'precision': 0.3824007429765498, 'recall': 0.5433850214450676, 'f1': 0.4488961569910057, 'number': 3031}, 'overall_precision': 0.34718543046357614, 'overall_recall': 0.43660212367270457, 'overall_f1': 0.3867933228811215, 'overall_accuracy': 0.7677969363083436}
			------------EPOCH 12---------------
Loss:  tensor(0.4273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3910, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3318777292576419, 'recall': 0.3431151241534989, 'f1': 0.3374028856825749, 'number': 1772}, 'P': {'precision': 0.48143236074270557, 'recall': 0.5988122731771692, 'f1': 0.5337450374944861, 'number': 3031}, 'overall_precision': 0.4325240985362371, 'overall_recall': 0.5044763689360816, 'overall_f1': 0.4657376261412782, 'overall_accuracy': 0.7844205171966636}
			------------EPOCH 13---------------
Loss:  tensor(0.3109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0747, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0746, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3241, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30268389662027834, 'recall': 0.34367945823927765, 'f1': 0.3218816067653277, 'number': 1772}, 'P': {'precision': 0.46339501206757844, 'recall': 0.5701088749587595, 'f1': 0.5112426035502958, 'number': 3031}, 'overall_precision': 0.40707193868663993, 'overall_recall': 0.48657089319175517, 'overall_f1': 0.44328528072837636, 'overall_accuracy': 0.7813835972860143}
			------------EPOCH 14---------------
Loss:  tensor(0.1936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0639, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2720, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2688330871491876, 'recall': 0.30812641083521447, 'f1': 0.2871417302129897, 'number': 1772}, 'P': {'precision': 0.44631901840490795, 'recall': 0.5760475090729132, 'f1': 0.5029526141437418, 'number': 3031}, 'overall_precision': 0.3856638061585058, 'overall_recall': 0.4772017489069332, 'overall_f1': 0.42657733109994417, 'overall_accuracy': 0.7825799596750579}
			------------EPOCH 15---------------
Loss:  tensor(0.1337, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2455, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30827740492170025, 'recall': 0.3888261851015801, 'f1': 0.34389817818817076, 'number': 1772}, 'P': {'precision': 0.5002790178571429, 'recall': 0.5915539425932036, 'f1': 0.5421012849584279, 'number': 3031}, 'overall_precision': 0.4265337686887781, 'overall_recall': 0.5167603581095149, 'overall_f1': 0.4673319525513086, 'overall_accuracy': 0.7891892344117327}
			------------EPOCH 16---------------
Loss:  tensor(0.0829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2238, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.31398305084745765, 'recall': 0.41817155756207675, 'f1': 0.3586640851887705, 'number': 1772}, 'P': {'precision': 0.5142276422764228, 'recall': 0.5842956120092379, 'f1': 0.5470270270270271, 'number': 3031}, 'overall_precision': 0.4328049620951068, 'overall_recall': 0.5230064542993962, 'overall_f1': 0.47364947676062974, 'overall_accuracy': 0.7889800801479139}
			------------EPOCH 17---------------
Loss:  tensor(0.0561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2079, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3018867924528302, 'recall': 0.3972911963882618, 'f1': 0.3430799220272904, 'number': 1772}, 'P': {'precision': 0.49260396315936367, 'recall': 0.58231606730452, 'f1': 0.5337163592379801, 'number': 3031}, 'overall_precision': 0.4174133558748943, 'overall_recall': 0.514053716427233, 'overall_f1': 0.4607202836350065, 'overall_accuracy': 0.7888462214190699}
			------------EPOCH 18---------------
Loss:  tensor(0.0387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0844, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1964, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3173076923076923, 'recall': 0.40970654627539504, 'f1': 0.35763546798029555, 'number': 1772}, 'P': {'precision': 0.501429388221841, 'recall': 0.5786869020125371, 'f1': 0.5372951447388574, 'number': 3031}, 'overall_precision': 0.4286208088489457, 'overall_recall': 0.5163439516968561, 'overall_f1': 0.4684106147889319, 'overall_accuracy': 0.7882187586276134}
			------------EPOCH 19---------------
Loss:  tensor(0.0281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1866, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.315377932232841, 'recall': 0.40970654627539504, 'f1': 0.35640648011782033, 'number': 1772}, 'P': {'precision': 0.5080645161290323, 'recall': 0.581986143187067, 'f1': 0.542518837459634, 'number': 3031}, 'overall_precision': 0.43124350536889505, 'overall_recall': 0.5184259837601499, 'overall_f1': 0.47083293939680443, 'overall_accuracy': 0.7882773218214827}
			------------EPOCH 20---------------
Loss:  tensor(0.0221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1833, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3130434782608696, 'recall': 0.42663656884875845, 'f1': 0.36111774540243613, 'number': 1772}, 'P': {'precision': 0.5172824791418356, 'recall': 0.5727482678983834, 'f1': 0.543604196023172, 'number': 3031}, 'overall_precision': 0.43181424363195287, 'overall_recall': 0.5188423901728086, 'overall_f1': 0.4713448080196709, 'overall_accuracy': 0.7865036936642991}
			------------EPOCH 21---------------
Loss:  tensor(0.0185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0899, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2150, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.330201972757163, 'recall': 0.39672686230248305, 'f1': 0.3604204050243527, 'number': 1772}, 'P': {'precision': 0.5083798882681564, 'recall': 0.6004618937644342, 'f1': 0.5505974890334291, 'number': 3031}, 'overall_precision': 0.441933788754598, 'overall_recall': 0.5252966895690193, 'overall_f1': 0.48002283105022825, 'overall_accuracy': 0.7892896284583657}
			------------EPOCH 22---------------
Loss:  tensor(0.0157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1282, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2796, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3131163708086785, 'recall': 0.35835214446952596, 'f1': 0.3342105263157894, 'number': 1772}, 'P': {'precision': 0.4909090909090909, 'recall': 0.6146486308149126, 'f1': 0.5458540873132142, 'number': 3031}, 'overall_precision': 0.4289884939034862, 'overall_recall': 0.5200916094107849, 'overall_f1': 0.4701675136457746, 'overall_accuracy': 0.7902517380719324}
			------------EPOCH 23---------------
Loss:  tensor(0.0150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2141, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2982233502538071, 'recall': 0.39785553047404065, 'f1': 0.34090909090909094, 'number': 1772}, 'P': {'precision': 0.49770246984491673, 'recall': 0.5717584955460244, 'f1': 0.532166436358053, 'number': 3031}, 'overall_precision': 0.417037290455012, 'overall_recall': 0.5075994170310223, 'overall_f1': 0.4578833693304536, 'overall_accuracy': 0.7849224874298287}
			------------EPOCH 24---------------
Loss:  tensor(0.0194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2108, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.31857599269739845, 'recall': 0.3939051918735892, 'f1': 0.3522583901085037, 'number': 1772}, 'P': {'precision': 0.5177489177489177, 'recall': 0.5918838667106565, 'f1': 0.5523399014778325, 'number': 3031}, 'overall_precision': 0.4405940594059406, 'overall_recall': 0.5188423901728086, 'overall_f1': 0.47652739267616406, 'overall_accuracy': 0.7864953274937463}
			------------EPOCH 25---------------
Loss:  tensor(0.0166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1723, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.316699604743083, 'recall': 0.36173814898419865, 'f1': 0.3377239199157008, 'number': 1772}, 'P': {'precision': 0.5212171970965941, 'recall': 0.6159683272847245, 'f1': 0.5646453954332377, 'number': 3031}, 'overall_precision': 0.4473778094898323, 'overall_recall': 0.5221736414740787, 'overall_f1': 0.4818906715342492, 'overall_accuracy': 0.7888880522718336}
			------------EPOCH 26---------------
Loss:  tensor(0.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1604, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.32838114754098363, 'recall': 0.36173814898419865, 'f1': 0.3442534908700322, 'number': 1772}, 'P': {'precision': 0.5195944094272403, 'recall': 0.6255361266908611, 'f1': 0.5676646706586826, 'number': 3031}, 'overall_precision': 0.4529548294947331, 'overall_recall': 0.5282115344576307, 'overall_f1': 0.4876970396001538, 'overall_accuracy': 0.7910214257627856}
			------------EPOCH 27---------------
Loss:  tensor(0.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1510, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3139963167587477, 'recall': 0.38487584650112866, 'f1': 0.34584178498985796, 'number': 1772}, 'P': {'precision': 0.5266893810335037, 'recall': 0.6120092378752887, 'f1': 0.5661529070654663, 'number': 3031}, 'overall_precision': 0.4455567263786442, 'overall_recall': 0.5282115344576307, 'overall_f1': 0.483376202724588, 'overall_accuracy': 0.7901680763664048}
			------------EPOCH 28---------------
Loss:  tensor(0.0076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1379, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30805892547660313, 'recall': 0.40124153498871334, 'f1': 0.3485294117647059, 'number': 1772}, 'P': {'precision': 0.5300146412884333, 'recall': 0.5971626525899043, 'f1': 0.5615885820663977, 'number': 3031}, 'overall_precision': 0.44050323257033025, 'overall_recall': 0.5248802831563606, 'overall_f1': 0.479004370131104, 'overall_accuracy': 0.7881936601159552}
			------------EPOCH 29---------------
Loss:  tensor(0.0066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1271, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3106457242582897, 'recall': 0.4018058690744921, 'f1': 0.3503937007874016, 'number': 1772}, 'P': {'precision': 0.5280140803754767, 'recall': 0.5938634114153745, 'f1': 0.5590062111801243, 'number': 3031}, 'overall_precision': 0.44062445185055255, 'overall_recall': 0.5230064542993962, 'overall_f1': 0.47829398324447825, 'overall_accuracy': 0.7877669854177647}
			------------EPOCH 30---------------
Loss:  tensor(0.0059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1187, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.31387181738366987, 'recall': 0.40349887133182843, 'f1': 0.3530864197530864, 'number': 1772}, 'P': {'precision': 0.5226349390597794, 'recall': 0.5941933355328275, 'f1': 0.5561216612629304, 'number': 3031}, 'overall_precision': 0.4395527603074773, 'overall_recall': 0.5238392671247137, 'overall_f1': 0.4780089294195878, 'overall_accuracy': 0.7882438571392716}
	Data split: 21k
			------------EPOCH 1---------------
Loss:  tensor(3.5538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7920, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.07757467677218012, 'recall': 0.0981941309255079, 'f1': 0.08667496886674969, 'number': 1772}, 'P': {'precision': 0.07853881278538813, 'recall': 0.02837347410095678, 'f1': 0.04168686379059622, 'number': 3031}, 'overall_precision': 0.07789095266626722, 'overall_recall': 0.054132833645638145, 'overall_f1': 0.06387421692666749, 'overall_accuracy': 0.35448301249069264}
			------------EPOCH 2---------------
Loss:  tensor(2.6670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5313, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1691663760027904, 'recall': 0.2737020316027088, 'f1': 0.20909678810088383, 'number': 1772}, 'P': {'precision': 0.35570469798657717, 'recall': 0.10491586935004948, 'f1': 0.16203821656050954, 'number': 3031}, 'overall_precision': 0.21350704599840467, 'overall_recall': 0.16718717468249011, 'overall_f1': 0.18752919196637086, 'overall_accuracy': 0.49272561470438136}
			------------EPOCH 3---------------
Loss:  tensor(2.2525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1779, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3154, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.257679180887372, 'recall': 0.25564334085778784, 'f1': 0.25665722379603406, 'number': 1772}, 'P': {'precision': 0.45816409423233145, 'recall': 0.372154404486968, 'f1': 0.4107045330420535, 'number': 3031}, 'overall_precision': 0.3746445497630332, 'overall_recall': 0.3291692692067458, 'overall_f1': 0.350437770142968, 'overall_accuracy': 0.6801529335977043}
			------------EPOCH 4---------------
Loss:  tensor(1.8929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1611, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0293, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1372, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2951559934318555, 'recall': 0.4057562076749436, 'f1': 0.3417300380228137, 'number': 1772}, 'P': {'precision': 0.4149636300658123, 'recall': 0.39524909270867703, 'f1': 0.4048665089557283, 'number': 3031}, 'overall_precision': 0.36013526207026114, 'overall_recall': 0.39912554653341664, 'overall_f1': 0.37862927118309303, 'overall_accuracy': 0.7140359243363535}
			------------EPOCH 5---------------
Loss:  tensor(1.6088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2845, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0472, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3154981549815498, 'recall': 0.3860045146726862, 'f1': 0.3472081218274112, 'number': 1772}, 'P': {'precision': 0.334136546184739, 'recall': 0.4117452985813263, 'f1': 0.3689033402305646, 'number': 3031}, 'overall_precision': 0.32729120786040994, 'overall_recall': 0.40224859462835727, 'overall_f1': 0.3609191107790024, 'overall_accuracy': 0.7418450752537041}
			------------EPOCH 6---------------
Loss:  tensor(1.3757, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9180, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.32497059976479814, 'recall': 0.46783295711060946, 'f1': 0.38352995604904, 'number': 1772}, 'P': {'precision': 0.3710450623202301, 'recall': 0.3830419003629165, 'f1': 0.376948051948052, 'number': 3031}, 'overall_precision': 0.3503521126760563, 'overall_recall': 0.4143243805954612, 'overall_f1': 0.37966231040732606, 'overall_accuracy': 0.7428490157200345}
			------------EPOCH 7---------------
Loss:  tensor(1.1465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6351, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8152, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3854775828460039, 'recall': 0.4463882618510158, 'f1': 0.4137029288702929, 'number': 1772}, 'P': {'precision': 0.4325706594885599, 'recall': 0.5301880567469482, 'f1': 0.4764304773198933, 'number': 3031}, 'overall_precision': 0.4158141147910525, 'overall_recall': 0.49927128877784716, 'overall_f1': 0.4537369914853358, 'overall_accuracy': 0.782948071179379}
			------------EPOCH 8---------------
Loss:  tensor(0.9462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7154, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.413265306122449, 'recall': 0.41139954853273136, 'f1': 0.4123303167420814, 'number': 1772}, 'P': {'precision': 0.4406312625250501, 'recall': 0.5803365225998021, 'f1': 0.5009255304001138, 'number': 3031}, 'overall_precision': 0.4322446143154969, 'overall_recall': 0.5180095773474912, 'overall_f1': 0.47125674779808696, 'overall_accuracy': 0.7914648328020815}
			------------EPOCH 9---------------
Loss:  tensor(0.7629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5870, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3872340425531915, 'recall': 0.5648984198645598, 'f1': 0.4594904750975442, 'number': 1772}, 'P': {'precision': 0.4712207463630613, 'recall': 0.4915869350049489, 'f1': 0.48118843855966414, 'number': 3031}, 'overall_precision': 0.43344353575778666, 'overall_recall': 0.5186341869664793, 'overall_f1': 0.47222748815165877, 'overall_accuracy': 0.7820863556124455}
			------------EPOCH 10---------------
Loss:  tensor(0.5249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5022, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.32352116624614524, 'recall': 0.6512415349887133, 'f1': 0.4322906911406631, 'number': 1772}, 'P': {'precision': 0.4303189165574487, 'recall': 0.324975255691191, 'f1': 0.37030075187969924, 'number': 3031}, 'overall_precision': 0.36526639344262296, 'overall_recall': 0.4453466583385384, 'overall_f1': 0.4013509710104138, 'overall_accuracy': 0.7195994277539342}
			------------EPOCH 11---------------
Loss:  tensor(0.5506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6340, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.40855803048065653, 'recall': 0.39334085778781036, 'f1': 0.40080506037952845, 'number': 1772}, 'P': {'precision': 0.4741807348560079, 'recall': 0.6301550643352029, 'f1': 0.5411531378382206, 'number': 3031}, 'overall_precision': 0.45465643529822114, 'overall_recall': 0.542785758900687, 'overall_f1': 0.49482774983391853, 'overall_accuracy': 0.7962921132110199}
			------------EPOCH 12---------------
Loss:  tensor(0.3021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1961, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6574, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3987226277372263, 'recall': 0.4932279909706546, 'f1': 0.44096871846619573, 'number': 1772}, 'P': {'precision': 0.5269406392694064, 'recall': 0.5710986473111185, 'f1': 0.5481317289423686, 'number': 3031}, 'overall_precision': 0.4756253423406975, 'overall_recall': 0.5423693524880283, 'overall_f1': 0.5068093385214009, 'overall_accuracy': 0.7944766542010725}
			------------EPOCH 13---------------
Loss:  tensor(0.1607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1592, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3934, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4298245614035088, 'recall': 0.4700902934537246, 'f1': 0.449056603773585, 'number': 1772}, 'P': {'precision': 0.5086047127349749, 'recall': 0.6337842296271857, 'f1': 0.5643360752056403, 'number': 3031}, 'overall_precision': 0.4818897637795276, 'overall_recall': 0.5733916302311055, 'overall_f1': 0.5236737022247575, 'overall_accuracy': 0.8016799270469928}
			------------EPOCH 14---------------
Loss:  tensor(0.1365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3115, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4025586353944563, 'recall': 0.5327313769751693, 'f1': 0.45858634928345887, 'number': 1772}, 'P': {'precision': 0.5379825653798257, 'recall': 0.5701088749587595, 'f1': 0.5535800096107641, 'number': 3031}, 'overall_precision': 0.4808349829044448, 'overall_recall': 0.5563189673120966, 'overall_f1': 0.5158301158301158, 'overall_accuracy': 0.7952296095508203}
			------------EPOCH 15---------------
Loss:  tensor(0.0772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2946, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4129032258064516, 'recall': 0.5056433408577878, 'f1': 0.45459157787924914, 'number': 1772}, 'P': {'precision': 0.5534967124925284, 'recall': 0.6110194655229297, 'f1': 0.5808373843500078, 'number': 3031}, 'overall_precision': 0.49818709209572154, 'overall_recall': 0.5721424109931293, 'overall_f1': 0.5326097490066867, 'overall_accuracy': 0.801027365743878}
			------------EPOCH 16---------------
Loss:  tensor(0.0504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1719, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2613, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.41625124626121635, 'recall': 0.47121896162528215, 'f1': 0.44203282159872953, 'number': 1772}, 'P': {'precision': 0.5400716056182869, 'recall': 0.6469811943253052, 'f1': 0.5887120984689281, 'number': 3031}, 'overall_precision': 0.4960085151676424, 'overall_recall': 0.5821361648969394, 'overall_f1': 0.535632183908046, 'overall_accuracy': 0.8045327912054815}
			------------EPOCH 17---------------
Loss:  tensor(0.0341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0689, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2514, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3993476234855545, 'recall': 0.48363431151241537, 'f1': 0.4374680959673302, 'number': 1772}, 'P': {'precision': 0.5444380733944955, 'recall': 0.6265258990432201, 'f1': 0.582604693971468, 'number': 3031}, 'overall_precision': 0.4891728789492368, 'overall_recall': 0.5738080366437643, 'overall_f1': 0.5281211075979688, 'overall_accuracy': 0.8021735311096052}
			------------EPOCH 18---------------
Loss:  tensor(0.0227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1548, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2360, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4141463414634146, 'recall': 0.4791196388261851, 'f1': 0.4442700156985871, 'number': 1772}, 'P': {'precision': 0.5652302243211335, 'recall': 0.6318046849224679, 'f1': 0.5966661473749807, 'number': 3031}, 'overall_precision': 0.5082751011401251, 'overall_recall': 0.5754736622943993, 'overall_f1': 0.5397910360316376, 'overall_accuracy': 0.8030770775293025}
			------------EPOCH 19---------------
Loss:  tensor(0.0180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2260, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4092009685230024, 'recall': 0.47686230248307, 'f1': 0.4404482668751629, 'number': 1772}, 'P': {'precision': 0.5694444444444444, 'recall': 0.6357637743319037, 'f1': 0.6007794232268122, 'number': 3031}, 'overall_precision': 0.508717195815746, 'overall_recall': 0.5771392879450343, 'overall_f1': 0.5407725321888411, 'overall_accuracy': 0.8030352466765387}
			------------EPOCH 20---------------
Loss:  tensor(0.0142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2270, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4098116947472745, 'recall': 0.4667042889390519, 'f1': 0.43641160949868074, 'number': 1772}, 'P': {'precision': 0.5630227862705509, 'recall': 0.6440118772682283, 'f1': 0.600800246229609, 'number': 3031}, 'overall_precision': 0.5066545123062899, 'overall_recall': 0.57859671038934, 'overall_f1': 0.5402410575427683, 'overall_accuracy': 0.8039806239489998}
			------------EPOCH 21---------------
Loss:  tensor(0.0124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2506, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3998157531091663, 'recall': 0.4898419864559819, 'f1': 0.44027390311945225, 'number': 1772}, 'P': {'precision': 0.5704057279236276, 'recall': 0.6308149125701089, 'f1': 0.5990913363622121, 'number': 3031}, 'overall_precision': 0.503349628824914, 'overall_recall': 0.5788049135956693, 'overall_f1': 0.5384466395506489, 'overall_accuracy': 0.8026169381489011}
			------------EPOCH 22---------------
Loss:  tensor(0.0120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2016, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4208860759493671, 'recall': 0.4503386004514673, 'f1': 0.4351145038167939, 'number': 1772}, 'P': {'precision': 0.55, 'recall': 0.6532497525569119, 'f1': 0.5971949932136933, 'number': 3031}, 'overall_precision': 0.5054585152838428, 'overall_recall': 0.5783885071830106, 'overall_f1': 0.5394698514418876, 'overall_accuracy': 0.8043989324766375}
			------------EPOCH 23---------------
Loss:  tensor(0.0110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1723, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4034229828850856, 'recall': 0.46557562076749437, 'f1': 0.43227665706051877, 'number': 1772}, 'P': {'precision': 0.567016317016317, 'recall': 0.6420323325635104, 'f1': 0.6021971220795297, 'number': 3031}, 'overall_precision': 0.5059339054226767, 'overall_recall': 0.576931084738705, 'overall_f1': 0.5391050583657588, 'overall_accuracy': 0.8027256983660869}
			------------EPOCH 24---------------
Loss:  tensor(0.0100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1699, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.38308687615526804, 'recall': 0.46783295711060946, 'f1': 0.42123983739837395, 'number': 1772}, 'P': {'precision': 0.5680806882230792, 'recall': 0.6318046849224679, 'f1': 0.5982505467041551, 'number': 3031}, 'overall_precision': 0.4957542908762421, 'overall_recall': 0.5713095981678118, 'overall_f1': 0.5308570323079899, 'overall_accuracy': 0.8022237281329218}
			------------EPOCH 25---------------
Loss:  tensor(0.0092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1485, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.388809862494073, 'recall': 0.46275395033860045, 'f1': 0.4225715021901572, 'number': 1772}, 'P': {'precision': 0.5683899556868538, 'recall': 0.6347740019795447, 'f1': 0.5997506234413964, 'number': 3031}, 'overall_precision': 0.49945394976337826, 'overall_recall': 0.5713095981678118, 'overall_f1': 0.5329707681849082, 'overall_accuracy': 0.8031105422115136}
			------------EPOCH 26---------------
Loss:  tensor(0.0084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0923, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1413, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3895078922934076, 'recall': 0.4734762979683973, 'f1': 0.42740703005603664, 'number': 1772}, 'P': {'precision': 0.5700149925037481, 'recall': 0.627185747278126, 'f1': 0.5972353125981779, 'number': 3031}, 'overall_precision': 0.49918017853889596, 'overall_recall': 0.5704767853424942, 'overall_f1': 0.5324523902059852, 'overall_accuracy': 0.8026838675133231}
			------------EPOCH 27---------------
Loss:  tensor(0.0080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1349, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.38545111006140764, 'recall': 0.4604966139954853, 'f1': 0.4196451529956287, 'number': 1772}, 'P': {'precision': 0.5619158878504673, 'recall': 0.6347740019795447, 'f1': 0.5961270333075135, 'number': 3031}, 'overall_precision': 0.4944955784154485, 'overall_recall': 0.5704767853424942, 'overall_f1': 0.5297757153905647, 'overall_accuracy': 0.8032444009403575}
			------------EPOCH 28---------------
Loss:  tensor(0.0072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1242, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.37369614512471655, 'recall': 0.4650112866817156, 'f1': 0.4143827005280362, 'number': 1772}, 'P': {'precision': 0.5632930067866627, 'recall': 0.6298251402177499, 'f1': 0.5947040498442367, 'number': 3031}, 'overall_precision': 0.48855917053986414, 'overall_recall': 0.5690193628981887, 'overall_f1': 0.5257285755506397, 'overall_accuracy': 0.8017384902408621}
			------------EPOCH 29---------------
Loss:  tensor(0.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1159, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3761165961448049, 'recall': 0.45146726862302483, 'f1': 0.410361631187484, 'number': 1772}, 'P': {'precision': 0.5567427086341322, 'recall': 0.6360936984493566, 'f1': 0.5937788728056667, 'number': 3031}, 'overall_precision': 0.48801431127012523, 'overall_recall': 0.5679783468665417, 'overall_f1': 0.5249687289521793, 'overall_accuracy': 0.8017635887525203}
			------------EPOCH 30---------------
Loss:  tensor(0.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0856, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1350, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.37344970142397793, 'recall': 0.458803611738149, 'f1': 0.41174981007850087, 'number': 1772}, 'P': {'precision': 0.5616197183098591, 'recall': 0.6314747608050149, 'f1': 0.5945022519024694, 'number': 3031}, 'overall_precision': 0.488272157564906, 'overall_recall': 0.5677701436602124, 'overall_f1': 0.5250288794763188, 'overall_accuracy': 0.8027005998544287}
Tokenizer: ../arg_m/arg_mining/smlm_pretrained_iter2_0/tokenizer Model: ../arg_m/arg_mining/smlm_pretrained_iter2_0/model
	Data split: 1k
			------------EPOCH 1---------------
Loss:  tensor(0.2983, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4157, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.0012478257581486803, 'recall': 0.010887495875948531, 'f1': 0.002239033822980629, 'number': 3031}, 'overall_precision': 0.0012460353420933393, 'overall_recall': 0.006870705808869456, 'overall_f1': 0.0021095023492185253, 'overall_accuracy': 0.35627337298898176}
			------------EPOCH 2---------------
Loss:  tensor(0.2478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3422, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.10056081995745504, 'recall': 0.17156054107555263, 'f1': 0.12679834186783712, 'number': 3031}, 'overall_precision': 0.10056081995745504, 'overall_recall': 0.10826566729127629, 'overall_f1': 0.10427110487266894, 'overall_accuracy': 0.4757339223117402}
			------------EPOCH 3---------------
Loss:  tensor(0.2262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3075, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.16154011615401162, 'recall': 0.24777301220719233, 'f1': 0.19557291666666668, 'number': 3031}, 'overall_precision': 0.16154011615401162, 'overall_recall': 0.15636060795336248, 'overall_f1': 0.15890816758358017, 'overall_accuracy': 0.48660157785976627}
			------------EPOCH 4---------------
Loss:  tensor(0.2113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2853, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.2324773413897281, 'recall': 0.5077532167601452, 'f1': 0.31893068075847064, 'number': 3031}, 'overall_precision': 0.2324773413897281, 'overall_recall': 0.3204247345409119, 'overall_f1': 0.26945635997548806, 'overall_accuracy': 0.5197985426130897}
			------------EPOCH 5---------------
Loss:  tensor(0.1920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2608, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.2268624545332076, 'recall': 0.5555922137908281, 'f1': 0.3221733307824756, 'number': 3031}, 'overall_precision': 0.22683189655172414, 'overall_recall': 0.35061419945867167, 'overall_f1': 0.2754559581254601, 'overall_accuracy': 0.5638798952555447}
			------------EPOCH 6---------------
Loss:  tensor(0.1714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2319, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.23470383275261325, 'recall': 0.5555922137908281, 'f1': 0.3300019596315893, 'number': 3031}, 'overall_precision': 0.23454038997214485, 'overall_recall': 0.35061419945867167, 'overall_f1': 0.28106484185930064, 'overall_accuracy': 0.614076918572062}
			------------EPOCH 7---------------
Loss:  tensor(0.1517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2015, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.047619047619047616, 'recall': 0.000564334085778781, 'f1': 0.0011154489682097043, 'number': 1772}, 'P': {'precision': 0.2547961630695444, 'recall': 0.5608709996700759, 'f1': 0.35040709059053904, 'number': 3031}, 'overall_precision': 0.2541461228148812, 'overall_recall': 0.3541536539662711, 'overall_f1': 0.295929018789144, 'overall_accuracy': 0.6543265651013561}
			------------EPOCH 8---------------
Loss:  tensor(0.1320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1719, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10126582278481013, 'recall': 0.004514672686230248, 'f1': 0.008643976229065368, 'number': 1772}, 'P': {'precision': 0.2670098118063375, 'recall': 0.5476740349719564, 'f1': 0.35899653979238755, 'number': 3031}, 'overall_precision': 0.26493011435832275, 'overall_recall': 0.3472829481574016, 'overall_f1': 0.3005676187043878, 'overall_accuracy': 0.6798015544344888}
			------------EPOCH 9---------------
Loss:  tensor(0.1114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1435, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1198501872659176, 'recall': 0.01805869074492099, 'f1': 0.031387935262383516, 'number': 1772}, 'P': {'precision': 0.2580803134182174, 'recall': 0.5216100296931706, 'f1': 0.3453095992137163, 'number': 3031}, 'overall_precision': 0.2523072110120444, 'overall_recall': 0.33583177180928586, 'overall_f1': 0.2881386209360486, 'overall_accuracy': 0.6876239239013127}
			------------EPOCH 10---------------
Loss:  tensor(0.0912, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1178, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13614262560777957, 'recall': 0.04740406320541761, 'f1': 0.0703223105902051, 'number': 1772}, 'P': {'precision': 0.25560388089662095, 'recall': 0.5041240514681623, 'f1': 0.33921633921633926, 'number': 3031}, 'overall_precision': 0.2444275966641395, 'overall_recall': 0.3356235686029565, 'overall_f1': 0.28285664151605544, 'overall_accuracy': 0.6891047360891499}
			------------EPOCH 11---------------
Loss:  tensor(0.0730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0960, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12910798122065728, 'recall': 0.062076749435665914, 'f1': 0.08384146341463415, 'number': 1772}, 'P': {'precision': 0.2586652871184687, 'recall': 0.4948861761794787, 'f1': 0.33975084937712347, 'number': 3031}, 'overall_precision': 0.24206886182528942, 'overall_recall': 0.3352071621902977, 'overall_f1': 0.2811244979919678, 'overall_accuracy': 0.6889541450192004}
			------------EPOCH 12---------------
Loss:  tensor(0.0578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0773, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12805662805662807, 'recall': 0.11230248306997742, 'f1': 0.11966325917017438, 'number': 1772}, 'P': {'precision': 0.24560747663551402, 'recall': 0.43352029033322337, 'f1': 0.313566400190908, 'number': 3031}, 'overall_precision': 0.21914831981460023, 'overall_recall': 0.3150114511763481, 'overall_f1': 0.2584778337746647, 'overall_accuracy': 0.6796844280467501}
			------------EPOCH 13---------------
Loss:  tensor(0.0446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0618, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12608695652173912, 'recall': 0.14729119638826185, 'f1': 0.13586673607496094, 'number': 1772}, 'P': {'precision': 0.254411161263849, 'recall': 0.4091059056417024, 'f1': 0.3137254901960784, 'number': 3031}, 'overall_precision': 0.21615783410138248, 'overall_recall': 0.3125130127003956, 'overall_f1': 0.25555460968757976, 'overall_accuracy': 0.6769654226171055}
			------------EPOCH 14---------------
Loss:  tensor(0.0340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0516, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1196652719665272, 'recall': 0.1613995485327314, 'f1': 0.1374339259971168, 'number': 1772}, 'P': {'precision': 0.2599301615015277, 'recall': 0.3929396238865061, 'f1': 0.31288585314593453, 'number': 3031}, 'overall_precision': 0.21184738955823293, 'overall_recall': 0.3075161357484905, 'overall_f1': 0.2508704883227176, 'overall_accuracy': 0.6739786997297726}
			------------EPOCH 15---------------
Loss:  tensor(0.0245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0423, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.112697603263641, 'recall': 0.12471783295711061, 'f1': 0.11840342887757836, 'number': 1772}, 'P': {'precision': 0.2798998121477771, 'recall': 0.442428241504454, 'f1': 0.3428790590641779, 'number': 3031}, 'overall_precision': 0.23133886255924171, 'overall_recall': 0.3252134082864876, 'overall_f1': 0.27035915188230203, 'overall_accuracy': 0.6865697864116658}
			------------EPOCH 16---------------
Loss:  tensor(0.0177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0327, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1065, 'recall': 0.12020316027088036, 'f1': 0.1129374337221633, 'number': 1772}, 'P': {'precision': 0.28498727735368956, 'recall': 0.44341801385681295, 'f1': 0.3469730218148961, 'number': 3031}, 'overall_precision': 0.23183442525312686, 'overall_recall': 0.32417239225484074, 'overall_f1': 0.27033596666377296, 'overall_accuracy': 0.6881175279639251}
			------------EPOCH 17---------------
Loss:  tensor(0.0126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0230, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10740597130670802, 'recall': 0.15632054176072235, 'f1': 0.1273270512525856, 'number': 1772}, 'P': {'precision': 0.2684052619432264, 'recall': 0.3837017485978225, 'f1': 0.3158609451385117, 'number': 3031}, 'overall_precision': 0.20833333333333334, 'overall_recall': 0.29981261711430357, 'overall_f1': 0.24583866837387966, 'overall_accuracy': 0.6755766383053485}
			------------EPOCH 18---------------
Loss:  tensor(0.0089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0175, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11211340206185567, 'recall': 0.14729119638826185, 'f1': 0.1273170731707317, 'number': 1772}, 'P': {'precision': 0.29133858267716534, 'recall': 0.42725173210161665, 'f1': 0.3464419475655431, 'number': 3031}, 'overall_precision': 0.22973571534032186, 'overall_recall': 0.3239641890485113, 'overall_f1': 0.2688320663441603, 'overall_accuracy': 0.6827297141279522}
			------------EPOCH 19---------------
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0156, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11230585424133811, 'recall': 0.15914221218961624, 'f1': 0.13168339948634133, 'number': 1772}, 'P': {'precision': 0.2853896841626903, 'recall': 0.4143846915209502, 'f1': 0.3379978471474704, 'number': 3031}, 'overall_precision': 0.22251157407407407, 'overall_recall': 0.32021653133458255, 'overall_f1': 0.26256935552710203, 'overall_accuracy': 0.6802365953032319}
			------------EPOCH 20---------------
Loss:  tensor(0.0051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0127, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11209553158705701, 'recall': 0.16422121896162528, 'f1': 0.1332417582417582, 'number': 1772}, 'P': {'precision': 0.2772366930917327, 'recall': 0.4038271197624546, 'f1': 0.3287671232876712, 'number': 3031}, 'overall_precision': 0.2160890029952931, 'overall_recall': 0.3154278575890069, 'overall_f1': 0.2564753682072118, 'overall_accuracy': 0.6795673016590116}
			------------EPOCH 21---------------
Loss:  tensor(0.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0090, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10628426824124843, 'recall': 0.14221218961625282, 'f1': 0.1216509775524982, 'number': 1772}, 'P': {'precision': 0.27985156079458634, 'recall': 0.42296271857472784, 'f1': 0.3368365738307935, 'number': 3031}, 'overall_precision': 0.22065592635212888, 'overall_recall': 0.31938371850926506, 'overall_f1': 0.2609953211399404, 'overall_accuracy': 0.683683457570966}
			------------EPOCH 22---------------
Loss:  tensor(0.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0069, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10320134793597305, 'recall': 0.13826185101580135, 'f1': 0.11818620356970574, 'number': 1772}, 'P': {'precision': 0.28032642258491397, 'recall': 0.41933355328274496, 'f1': 0.33602115003304694, 'number': 3031}, 'overall_precision': 0.21945570353213664, 'overall_recall': 0.31563606079533624, 'overall_f1': 0.2589018871146785, 'overall_accuracy': 0.6833571769194087}
			------------EPOCH 23---------------
Loss:  tensor(0.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0054, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10216193302246715, 'recall': 0.13600451467268623, 'f1': 0.11667877027354151, 'number': 1772}, 'P': {'precision': 0.2825990209167779, 'recall': 0.419003629165292, 'f1': 0.33754152823920264, 'number': 3031}, 'overall_precision': 0.2204873777907486, 'overall_recall': 0.3145950447636894, 'overall_f1': 0.25926561427590944, 'overall_accuracy': 0.6847794259133767}
			------------EPOCH 24---------------
Loss:  tensor(0.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0043, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10437109723461195, 'recall': 0.13205417607223477, 'f1': 0.1165919282511211, 'number': 1772}, 'P': {'precision': 0.28812056737588654, 'recall': 0.4289013526888816, 'f1': 0.3446904414689116, 'number': 3031}, 'overall_precision': 0.22712466686408053, 'overall_recall': 0.31938371850926506, 'overall_f1': 0.265466816647919, 'overall_accuracy': 0.6871637845209112}
			------------EPOCH 25---------------
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0033, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10692416391898257, 'recall': 0.1281038374717833, 'f1': 0.11655969191270861, 'number': 1772}, 'P': {'precision': 0.2959522229595222, 'recall': 0.441438469152095, 'f1': 0.3543432203389831, 'number': 3031}, 'overall_precision': 0.23555087296809152, 'overall_recall': 0.32583801790547573, 'overall_f1': 0.2734340875338516, 'overall_accuracy': 0.6905437174242234}
			------------EPOCH 26---------------
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10831721470019343, 'recall': 0.12641083521444696, 'f1': 0.11666666666666667, 'number': 1772}, 'P': {'precision': 0.30301018149623726, 'recall': 0.45166611679313756, 'f1': 0.3626970459663531, 'number': 3031}, 'overall_precision': 0.241876708168843, 'overall_recall': 0.3316677076826983, 'overall_f1': 0.27974361225744143, 'overall_accuracy': 0.6920579942942717}
			------------EPOCH 27---------------
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1084973595775324, 'recall': 0.1275395033860045, 'f1': 0.11725032425421529, 'number': 1772}, 'P': {'precision': 0.3016189842537148, 'recall': 0.4486967997360607, 'f1': 0.36074270557029176, 'number': 3031}, 'overall_precision': 0.24059466019417475, 'overall_recall': 0.3302102852383927, 'overall_f1': 0.27836770513383063, 'overall_accuracy': 0.6918153753482419}
			------------EPOCH 28---------------
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1099476439790576, 'recall': 0.13036117381489842, 'f1': 0.1192873741285825, 'number': 1772}, 'P': {'precision': 0.3030639431616341, 'recall': 0.4503464203233256, 'f1': 0.3623092236230922, 'number': 3031}, 'overall_precision': 0.24163512490537473, 'overall_recall': 0.33229231730168646, 'overall_f1': 0.2798036465638149, 'overall_accuracy': 0.6919743325887442}
			------------EPOCH 29---------------
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11105815061963775, 'recall': 0.13148984198645597, 'f1': 0.12041343669250647, 'number': 1772}, 'P': {'precision': 0.30393457117595046, 'recall': 0.4536456614978555, 'f1': 0.3639973527465255, 'number': 3031}, 'overall_precision': 0.2428269405013591, 'overall_recall': 0.33479075577763895, 'overall_f1': 0.2814879649890591, 'overall_accuracy': 0.6919910649298496}
			------------EPOCH 30---------------
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1108433734939759, 'recall': 0.12979683972911965, 'f1': 0.11957369378736679, 'number': 1772}, 'P': {'precision': 0.30533509700176364, 'recall': 0.45694490267238536, 'f1': 0.36606316902339103, 'number': 3031}, 'overall_precision': 0.24428981999697474, 'overall_recall': 0.33624817822194464, 'overall_f1': 0.2829858069038024, 'overall_accuracy': 0.6919241355654276}
	Data split: 6k
			------------EPOCH 1---------------
Loss:  tensor(0.7537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1893, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6578, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.022222222222222223, 'recall': 0.007900677200902935, 'f1': 0.011656952539550375, 'number': 1772}, 'P': {'precision': 0.008403361344537815, 'recall': 0.0003299241174529858, 'f1': 0.000634920634920635, 'number': 3031}, 'overall_precision': 0.020026702269692925, 'overall_recall': 0.003123048094940662, 'overall_f1': 0.0054034582132564835, 'overall_accuracy': 0.22733395242995424}
			------------EPOCH 2---------------
Loss:  tensor(0.5848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2630, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2890, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5800, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22962962962962963, 'recall': 0.06997742663656885, 'f1': 0.10726643598615918, 'number': 1772}, 'P': {'precision': 0.24833188279663476, 'recall': 0.28241504453975586, 'f1': 0.2642790984871874, 'number': 3031}, 'overall_precision': 0.2457988462503135, 'overall_recall': 0.20403914220278993, 'overall_f1': 0.22298065984072812, 'overall_accuracy': 0.5884513381689799}
			------------EPOCH 3---------------
Loss:  tensor(0.5233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5098, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.269, 'recall': 0.1518058690744921, 'f1': 0.19408369408369408, 'number': 1772}, 'P': {'precision': 0.43262204033908214, 'recall': 0.488287693830419, 'f1': 0.45877247365158086, 'number': 3031}, 'overall_precision': 0.39561185252205383, 'overall_recall': 0.3641474078700812, 'overall_f1': 0.3792281006071119, 'overall_accuracy': 0.6885776673443265}
			------------EPOCH 4---------------
Loss:  tensor(0.4514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4376, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.23938053097345133, 'recall': 0.30530474040632055, 'f1': 0.26835317460317465, 'number': 1772}, 'P': {'precision': 0.5131873044255699, 'recall': 0.3787528868360277, 'f1': 0.43583902809415337, 'number': 3031}, 'overall_precision': 0.37558372248165445, 'overall_recall': 0.35165521549031853, 'overall_f1': 0.36322580645161284, 'overall_accuracy': 0.6689255327159099}
			------------EPOCH 5---------------
Loss:  tensor(0.3744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1954, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4080, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3012399708242159, 'recall': 0.23306997742663657, 'f1': 0.26280623608017817, 'number': 1772}, 'P': {'precision': 0.4815470918216711, 'recall': 0.5381062355658198, 'f1': 0.5082580243066376, 'number': 3031}, 'overall_precision': 0.4295922656578394, 'overall_recall': 0.4255673537372476, 'overall_f1': 0.4275703378307708, 'overall_accuracy': 0.7197918496766476}
			------------EPOCH 6---------------
Loss:  tensor(0.3052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3221, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21283255086071987, 'recall': 0.30699774266365687, 'f1': 0.2513863216266174, 'number': 1772}, 'P': {'precision': 0.48696682464454977, 'recall': 0.4067964368195315, 'f1': 0.4432859967643358, 'number': 3031}, 'overall_precision': 0.3492531446540881, 'overall_recall': 0.36997709764730374, 'overall_f1': 0.35931655039935295, 'overall_accuracy': 0.6882681190338746}
			------------EPOCH 7---------------
Loss:  tensor(0.2737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2797, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2924281984334204, 'recall': 0.3160270880361174, 'f1': 0.30377000271223215, 'number': 1772}, 'P': {'precision': 0.5424377791959157, 'recall': 0.5608709996700759, 'f1': 0.5515004055150041, 'number': 3031}, 'overall_precision': 0.4476133887898594, 'overall_recall': 0.4705392463043931, 'overall_f1': 0.4587900933820544, 'overall_accuracy': 0.7359803896962244}
			------------EPOCH 8---------------
Loss:  tensor(0.2318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2408, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24329576369996114, 'recall': 0.35327313769751695, 'f1': 0.28814729574223247, 'number': 1772}, 'P': {'precision': 0.5461898680289485, 'recall': 0.4232926426921808, 'f1': 0.4769516728624536, 'number': 3031}, 'overall_precision': 0.3878504672897196, 'overall_recall': 0.3974599208827816, 'overall_f1': 0.39259640102827764, 'overall_accuracy': 0.7018213153293343}
			------------EPOCH 9---------------
Loss:  tensor(0.1721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2930, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1926, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30554303740423616, 'recall': 0.38261851015801357, 'f1': 0.33976447005762966, 'number': 1772}, 'P': {'precision': 0.5660445082555635, 'recall': 0.5202903332233586, 'f1': 0.542203885164174, 'number': 3031}, 'overall_precision': 0.45054945054945056, 'overall_recall': 0.4694982302727462, 'overall_f1': 0.45982871125611746, 'overall_accuracy': 0.7409582611751123}
			------------EPOCH 10---------------
Loss:  tensor(0.1295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1512, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2340, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0786, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1851, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3164319248826291, 'recall': 0.3803611738148984, 'f1': 0.3454638646847771, 'number': 1772}, 'P': {'precision': 0.5437237818651178, 'recall': 0.555922137908281, 'f1': 0.5497553017944534, 'number': 3031}, 'overall_precision': 0.45113788487282463, 'overall_recall': 0.49115136373100143, 'overall_f1': 0.47029505582137154, 'overall_accuracy': 0.7555572287896661}
			------------EPOCH 11---------------
Loss:  tensor(0.0842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0536, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1357, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2662684690348947, 'recall': 0.47799097065462753, 'f1': 0.3420149404401373, 'number': 1772}, 'P': {'precision': 0.47693685624720106, 'recall': 0.35136918508742987, 'f1': 0.40463525835866254, 'number': 3031}, 'overall_precision': 0.35315847801994826, 'overall_recall': 0.39808453050176973, 'overall_f1': 0.3742781638445728, 'overall_accuracy': 0.6944339867312534}
			------------EPOCH 12---------------
Loss:  tensor(0.0598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1568, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3109649122807018, 'recall': 0.40011286681715574, 'f1': 0.3499506416584403, 'number': 1772}, 'P': {'precision': 0.5608351331893449, 'recall': 0.514021774991752, 'f1': 0.5364090204854536, 'number': 3031}, 'overall_precision': 0.44820086990905494, 'overall_recall': 0.4719966687486987, 'overall_f1': 0.4597910962377041, 'overall_accuracy': 0.743911519380234}
			------------EPOCH 13---------------
Loss:  tensor(0.0321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2015, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3045032165832738, 'recall': 0.48081264108352145, 'f1': 0.3728665207877462, 'number': 1772}, 'P': {'precision': 0.5029985007496252, 'recall': 0.44275816562190695, 'f1': 0.4709598175118442, 'number': 3031}, 'overall_precision': 0.4013904134650567, 'overall_recall': 0.4567978346866542, 'overall_f1': 0.42730548252020645, 'overall_accuracy': 0.7337047913058755}
			------------EPOCH 14---------------
Loss:  tensor(0.0219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0553, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1241, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29890764647467727, 'recall': 0.3397291196388262, 'f1': 0.3180137348124669, 'number': 1772}, 'P': {'precision': 0.5026117237376668, 'recall': 0.5714285714285714, 'f1': 0.534815501003551, 'number': 3031}, 'overall_precision': 0.42747252747252745, 'overall_recall': 0.48594628357276703, 'overall_f1': 0.4548377667348728, 'overall_accuracy': 0.7593471040500631}
			------------EPOCH 15---------------
Loss:  tensor(0.0192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0969, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3096590909090909, 'recall': 0.3690744920993228, 'f1': 0.3367662203913491, 'number': 1772}, 'P': {'precision': 0.5466363340916477, 'recall': 0.5549323655559222, 'f1': 0.5507531106745251, 'number': 3031}, 'overall_precision': 0.45018307959144344, 'overall_recall': 0.48636268998542576, 'overall_f1': 0.46757405924739787, 'overall_accuracy': 0.75593370646454}
			------------EPOCH 16---------------
Loss:  tensor(0.0114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0359, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0828, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30443234836702954, 'recall': 0.44187358916478553, 'f1': 0.36049723756906077, 'number': 1772}, 'P': {'precision': 0.5643297380585516, 'recall': 0.4833388320686242, 'f1': 0.5207037497778567, 'number': 3031}, 'overall_precision': 0.43498452012383904, 'overall_recall': 0.46804080782844054, 'overall_f1': 0.45090763213318624, 'overall_accuracy': 0.7398204619799379}
			------------EPOCH 17---------------
Loss:  tensor(0.0076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0715, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30185873605947955, 'recall': 0.4582392776523702, 'f1': 0.3639623487225459, 'number': 1772}, 'P': {'precision': 0.5584366779406238, 'recall': 0.49026723853513693, 'f1': 0.522136331693605, 'number': 3031}, 'overall_precision': 0.42945243879648665, 'overall_recall': 0.47845096814490945, 'overall_f1': 0.45262950561355136, 'overall_accuracy': 0.740021250073204}
			------------EPOCH 18---------------
Loss:  tensor(0.0052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0631, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3053045186640472, 'recall': 0.4384875846501129, 'f1': 0.3599722029186936, 'number': 1772}, 'P': {'precision': 0.5340831629175188, 'recall': 0.5169910920488288, 'f1': 0.525398155909472, 'number': 3031}, 'overall_precision': 0.42781529476181784, 'overall_recall': 0.4880283156360608, 'overall_f1': 0.4559424236529858, 'overall_accuracy': 0.7472077905780187}
			------------EPOCH 19---------------
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0537, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3095139177399252, 'recall': 0.4204288939051919, 'f1': 0.35654462790141184, 'number': 1772}, 'P': {'precision': 0.5307820299500832, 'recall': 0.5262289673375123, 'f1': 0.528495692511597, 'number': 3031}, 'overall_precision': 0.43237250554323725, 'overall_recall': 0.4871955028107433, 'overall_f1': 0.4581497797356828, 'overall_accuracy': 0.7489061232002275}
			------------EPOCH 20---------------
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0475, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30128470783257355, 'recall': 0.4102708803611738, 'f1': 0.3474313022700119, 'number': 1772}, 'P': {'precision': 0.5319291206954196, 'recall': 0.5249092708677005, 'f1': 0.5283958817668548, 'number': 3031}, 'overall_precision': 0.4289415247964471, 'overall_recall': 0.482615032271497, 'overall_f1': 0.4541980993435878, 'overall_accuracy': 0.7480193091216357}
			------------EPOCH 21---------------
Loss:  tensor(0.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0417, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29476248477466505, 'recall': 0.40970654627539504, 'f1': 0.34285714285714286, 'number': 1772}, 'P': {'precision': 0.5279566248729244, 'recall': 0.514021774991752, 'f1': 0.5208960213975259, 'number': 3031}, 'overall_precision': 0.4218692279275951, 'overall_recall': 0.4755361232562981, 'overall_f1': 0.4470979739649603, 'overall_accuracy': 0.744187603008475}
			------------EPOCH 22---------------
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0356, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.291683569979716, 'recall': 0.4057562076749436, 'f1': 0.33939107859334433, 'number': 1772}, 'P': {'precision': 0.5224738087191618, 'recall': 0.510062685582316, 'f1': 0.5161936560934891, 'number': 3031}, 'overall_precision': 0.41758849557522126, 'overall_recall': 0.47158026233604, 'overall_f1': 0.4429451452038721, 'overall_accuracy': 0.7441206736440529}
			------------EPOCH 23---------------
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0299, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2898089171974522, 'recall': 0.4108352144469526, 'f1': 0.33986928104575165, 'number': 1772}, 'P': {'precision': 0.5248032842969552, 'recall': 0.5061035961728803, 'f1': 0.5152838427947598, 'number': 3031}, 'overall_precision': 0.41619135234590615, 'overall_recall': 0.47095565271705186, 'overall_f1': 0.4418831803086541, 'overall_accuracy': 0.7424892703862661}
			------------EPOCH 24---------------
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0295, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2917208495882098, 'recall': 0.37979683972911965, 'f1': 0.3299828389311106, 'number': 1772}, 'P': {'precision': 0.509929532351057, 'recall': 0.5252391949851534, 'f1': 0.5174711522834389, 'number': 3031}, 'overall_precision': 0.417203904954872, 'overall_recall': 0.47158026233604, 'overall_f1': 0.44272869429241596, 'overall_accuracy': 0.744287997055108}
			------------EPOCH 25---------------
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0763, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.27783155856727976, 'recall': 0.48589164785553046, 'f1': 0.3535208376103469, 'number': 1772}, 'P': {'precision': 0.5379746835443038, 'recall': 0.4206532497525569, 'f1': 0.47213478985373075, 'number': 3031}, 'overall_precision': 0.39056500274273176, 'overall_recall': 0.4447220487195503, 'overall_f1': 0.4158878504672897, 'overall_accuracy': 0.7192145839085076}
			------------EPOCH 26---------------
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1914, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26554439315775186, 'recall': 0.5519187358916479, 'f1': 0.358570119156737, 'number': 1772}, 'P': {'precision': 0.500809498111171, 'recall': 0.3061695809963708, 'f1': 0.38001638001638, 'number': 3031}, 'overall_precision': 0.3442919075144509, 'overall_recall': 0.39683531126379346, 'overall_f1': 0.36870103491633627, 'overall_accuracy': 0.6707577240669629}
			------------EPOCH 27---------------
Loss:  tensor(0.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0732, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28991060025542786, 'recall': 0.3843115124153499, 'f1': 0.3305023052657123, 'number': 1772}, 'P': {'precision': 0.48059964726631393, 'recall': 0.5394259320356318, 'f1': 0.5083164930825432, 'number': 3031}, 'overall_precision': 0.40271257172665625, 'overall_recall': 0.4821986258588382, 'overall_f1': 0.4388857305287095, 'overall_accuracy': 0.7566950279848405}
			------------EPOCH 28---------------
Loss:  tensor(0.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0746, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.31396713615023475, 'recall': 0.30191873589164786, 'f1': 0.30782508630609895, 'number': 1772}, 'P': {'precision': 0.4660931174089069, 'recall': 0.6077202243483999, 'f1': 0.5275669483030218, 'number': 3031}, 'overall_precision': 0.42026166902404527, 'overall_recall': 0.49489902144493025, 'overall_f1': 0.45453676259680653, 'overall_accuracy': 0.7628776280233249}
			------------EPOCH 29---------------
Loss:  tensor(0.0045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0579, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2919847328244275, 'recall': 0.4317155756207675, 'f1': 0.34836065573770497, 'number': 1772}, 'P': {'precision': 0.5056291390728477, 'recall': 0.5037941273507094, 'f1': 0.5047099652949927, 'number': 3031}, 'overall_precision': 0.40638297872340423, 'overall_recall': 0.4772017489069332, 'overall_f1': 0.43895432347026714, 'overall_accuracy': 0.7491571083168101}
			------------EPOCH 30---------------
Loss:  tensor(0.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0505, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2806800618238022, 'recall': 0.5124153498871332, 'f1': 0.36269223087677255, 'number': 1772}, 'P': {'precision': 0.5299823633156967, 'recall': 0.3965687891784889, 'f1': 0.4536705038686545, 'number': 3031}, 'overall_precision': 0.383427221515537, 'overall_recall': 0.4393087653549865, 'overall_f1': 0.40947021152726565, 'overall_accuracy': 0.7110659337901263}
	Data split: 12k
			------------EPOCH 1---------------
Loss:  tensor(3.0422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9331, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5603, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1961, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.1048906048906049, 'recall': 0.05377763114483669, 'f1': 0.07110141766630317, 'number': 3031}, 'overall_precision': 0.1037555697008275, 'overall_recall': 0.03393712263168853, 'overall_f1': 0.05114527769061814, 'overall_accuracy': 0.5035514393996436}
			------------EPOCH 2---------------
Loss:  tensor(2.2674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0537, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13131313131313133, 'recall': 0.007336343115124154, 'f1': 0.01389631213254944, 'number': 1772}, 'P': {'precision': 0.29750778816199375, 'recall': 0.3150775321676014, 'f1': 0.3060406986059926, 'number': 3031}, 'overall_precision': 0.2925355092172862, 'overall_recall': 0.20154070372683738, 'overall_f1': 0.23865877712031558, 'overall_accuracy': 0.6508044072986472}
			------------EPOCH 3---------------
Loss:  tensor(2.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1520, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9182, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.18181818181818182, 'recall': 0.016930022573363433, 'f1': 0.030975735673722256, 'number': 1772}, 'P': {'precision': 0.3872340425531915, 'recall': 0.48036951501154734, 'f1': 0.42880282727138863, 'number': 3031}, 'overall_precision': 0.3785987261146497, 'overall_recall': 0.3093899646054549, 'overall_f1': 0.3405132905591201, 'overall_accuracy': 0.6975545683474303}
			------------EPOCH 4---------------
Loss:  tensor(1.7245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3806, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8180, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.24619289340101522, 'recall': 0.05474040632054176, 'f1': 0.08956602031394276, 'number': 1772}, 'P': {'precision': 0.3858064516129032, 'recall': 0.4932365555922138, 'f1': 0.4329568491167101, 'number': 3031}, 'overall_precision': 0.37292105879597093, 'overall_recall': 0.33145950447636896, 'overall_f1': 0.3509700176366843, 'overall_accuracy': 0.7125132812957525}
			------------EPOCH 5---------------
Loss:  tensor(1.5002, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4990, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7254, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3026070763500931, 'recall': 0.18340857787810383, 'f1': 0.22839072382290931, 'number': 1772}, 'P': {'precision': 0.44940562481878804, 'recall': 0.511382382052128, 'f1': 0.47839506172839513, 'number': 3031}, 'overall_precision': 0.41454786646031394, 'overall_recall': 0.3903810118675828, 'overall_f1': 0.402101651297448, 'overall_accuracy': 0.7415857239665687}
			------------EPOCH 6---------------
Loss:  tensor(1.2762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2778, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6025, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29930394431554525, 'recall': 0.291196388261851, 'f1': 0.29519450800915326, 'number': 1772}, 'P': {'precision': 0.48166834846955936, 'recall': 0.4724513361926757, 'f1': 0.47701532311792144, 'number': 3031}, 'overall_precision': 0.4147328081754311, 'overall_recall': 0.4055798459296273, 'overall_f1': 0.41010526315789475, 'overall_accuracy': 0.7397368002744104}
			------------EPOCH 7---------------
Loss:  tensor(1.0438, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3394, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5095, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28454680534918275, 'recall': 0.4322799097065463, 'f1': 0.3431899641577061, 'number': 1772}, 'P': {'precision': 0.5013250883392226, 'recall': 0.3744638733091389, 'f1': 0.4287063267233239, 'number': 3031}, 'overall_precision': 0.38357546408393867, 'overall_recall': 0.3957942952321466, 'overall_f1': 0.38958909724357, 'overall_accuracy': 0.7112583557128396}
			------------EPOCH 8---------------
Loss:  tensor(0.8307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4352, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3357915437561455, 'recall': 0.38544018058690743, 'f1': 0.35890698896479245, 'number': 1772}, 'P': {'precision': 0.5430637738330046, 'recall': 0.5450346420323325, 'f1': 0.5440474230199241, 'number': 3031}, 'overall_precision': 0.4600078802206462, 'overall_recall': 0.4861544867790964, 'overall_f1': 0.47271991092215815, 'overall_accuracy': 0.77015619640422}
			------------EPOCH 9---------------
Loss:  tensor(0.6400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0480, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2762, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5024, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.402555910543131, 'recall': 0.07110609480812641, 'f1': 0.12086330935251799, 'number': 1772}, 'P': {'precision': 0.4660623479991156, 'recall': 0.6954800395908941, 'f1': 0.5581149060100609, 'number': 3031}, 'overall_precision': 0.4619520264681555, 'overall_recall': 0.4651259629398293, 'overall_f1': 0.4635335615727772, 'overall_accuracy': 0.727120615080859}
			------------EPOCH 10---------------
Loss:  tensor(1.3905, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1426, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3913, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2513980063214199, 'recall': 0.5835214446952596, 'f1': 0.3514018691588785, 'number': 1772}, 'P': {'precision': 0.3070607553366174, 'recall': 0.12339161992741669, 'f1': 0.17604142151094376, 'number': 3031}, 'overall_precision': 0.2641155505533671, 'overall_recall': 0.2931501145117635, 'overall_f1': 0.27787645549634893, 'overall_accuracy': 0.5847200261024521}
			------------EPOCH 11---------------
Loss:  tensor(1.0597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1901, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4038, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3766314481044127, 'recall': 0.34198645598194133, 'f1': 0.3584738243123336, 'number': 1772}, 'P': {'precision': 0.42638522427440634, 'recall': 0.5331573738040251, 'f1': 0.4738308165958071, 'number': 3031}, 'overall_precision': 0.4115576958696055, 'overall_recall': 0.4626275244638767, 'overall_f1': 0.43560086257596553, 'overall_accuracy': 0.7715617130570824}
			------------EPOCH 12---------------
Loss:  tensor(0.5482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1489, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4353, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.43974241030358785, 'recall': 0.2697516930022573, 'f1': 0.33438265127667016, 'number': 1772}, 'P': {'precision': 0.5158371040723982, 'recall': 0.6770042890135269, 'f1': 0.585532886289057, 'number': 3031}, 'overall_precision': 0.49950641658440276, 'overall_recall': 0.526754112013325, 'overall_f1': 0.5127685447912445, 'overall_accuracy': 0.7764057258071263}
			------------EPOCH 13---------------
Loss:  tensor(0.4131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2840, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3682448589191774, 'recall': 0.4345372460496614, 'f1': 0.39865389593580114, 'number': 1772}, 'P': {'precision': 0.5515412661584356, 'recall': 0.5489937314417684, 'f1': 0.5502645502645503, 'number': 3031}, 'overall_precision': 0.4765074393108849, 'overall_recall': 0.5067666042057047, 'overall_f1': 0.49117142568862876, 'overall_accuracy': 0.779158195918982}
			------------EPOCH 14---------------
Loss:  tensor(0.2597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3084, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.34646374216651743, 'recall': 0.4367945823927765, 'f1': 0.3864203694458313, 'number': 1772}, 'P': {'precision': 0.5301990391214825, 'recall': 0.5097327614648631, 'f1': 0.5197645079899075, 'number': 3031}, 'overall_precision': 0.45046620046620045, 'overall_recall': 0.48282323547782635, 'overall_f1': 0.4660838106722942, 'overall_accuracy': 0.765889449422316}
			------------EPOCH 15---------------
Loss:  tensor(0.1931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2226, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3657908294693457, 'recall': 0.4006772009029345, 'f1': 0.3824400754107191, 'number': 1772}, 'P': {'precision': 0.5040768782760628, 'recall': 0.5710986473111185, 'f1': 0.5354988399071925, 'number': 3031}, 'overall_precision': 0.45413953488372094, 'overall_recall': 0.5082240266500104, 'overall_f1': 0.4796620161131853, 'overall_accuracy': 0.777769411607225}
			------------EPOCH 16---------------
Loss:  tensor(0.1175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0357, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0522, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0985, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2029, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3470790378006873, 'recall': 0.3989841986455982, 'f1': 0.37122604358099237, 'number': 1772}, 'P': {'precision': 0.515638963360143, 'recall': 0.5710986473111185, 'f1': 0.541953663118347, 'number': 3031}, 'overall_precision': 0.45198368557656654, 'overall_recall': 0.5075994170310223, 'overall_f1': 0.4781798568206335, 'overall_accuracy': 0.7785976624919475}
			------------EPOCH 17---------------
Loss:  tensor(0.0818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0869, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1769, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.35263895375992527, 'recall': 0.4260722347629797, 'f1': 0.385893176590851, 'number': 1772}, 'P': {'precision': 0.5603252032520325, 'recall': 0.5684592543714946, 'f1': 0.5643629217163445, 'number': 3031}, 'overall_precision': 0.4750766871165644, 'overall_recall': 0.5159275452841974, 'overall_f1': 0.49466014572312605, 'overall_accuracy': 0.7785307331275255}
			------------EPOCH 18---------------
Loss:  tensor(0.0573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0751, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1528, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3584905660377358, 'recall': 0.41817155756207675, 'f1': 0.3860380307371711, 'number': 1772}, 'P': {'precision': 0.5507109004739337, 'recall': 0.5750577367205543, 'f1': 0.5626210458360233, 'number': 3031}, 'overall_precision': 0.47477064220183485, 'overall_recall': 0.5171767645221736, 'overall_f1': 0.49506726457399103, 'overall_accuracy': 0.7808899932234018}
			------------EPOCH 19---------------
Loss:  tensor(0.0399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0681, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1464, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.35492957746478876, 'recall': 0.42663656884875845, 'f1': 0.38749359302921577, 'number': 1772}, 'P': {'precision': 0.5445420326223338, 'recall': 0.5727482678983834, 'f1': 0.5582891140054671, 'number': 3031}, 'overall_precision': 0.46859721699887175, 'overall_recall': 0.5188423901728086, 'overall_f1': 0.49244145835391756, 'overall_accuracy': 0.7820779894418928}
			------------EPOCH 20---------------
Loss:  tensor(0.0296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0666, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1297, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.34880514705882354, 'recall': 0.4283295711060948, 'f1': 0.3844984802431611, 'number': 1772}, 'P': {'precision': 0.541113219481341, 'recall': 0.5645001649620587, 'f1': 0.5525593411916679, 'number': 3031}, 'overall_precision': 0.4627201198950918, 'overall_recall': 0.5142619196335624, 'overall_f1': 0.48713144660289914, 'overall_accuracy': 0.7796768984932527}
			------------EPOCH 21---------------
Loss:  tensor(0.0230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1202, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.35283363802559414, 'recall': 0.435665914221219, 'f1': 0.3898989898989899, 'number': 1772}, 'P': {'precision': 0.5429749444973041, 'recall': 0.5648300890795117, 'f1': 0.5536869340232858, 'number': 3031}, 'overall_precision': 0.4650814454222056, 'overall_recall': 0.5171767645221736, 'overall_f1': 0.4897476340694006, 'overall_accuracy': 0.7802123334086288}
			------------EPOCH 22---------------
Loss:  tensor(0.0185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0571, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1106, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3549862763037511, 'recall': 0.43792325056433407, 'f1': 0.3921172309247094, 'number': 1772}, 'P': {'precision': 0.5491514569324367, 'recall': 0.5658198614318707, 'f1': 0.5573610659733507, 'number': 3031}, 'overall_precision': 0.46920323978150313, 'overall_recall': 0.5186341869664793, 'overall_f1': 0.4926819620253165, 'overall_accuracy': 0.7801454040442068}
			------------EPOCH 23---------------
Loss:  tensor(0.0152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1074, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.345446584938704, 'recall': 0.4452595936794582, 'f1': 0.38905325443786987, 'number': 1772}, 'P': {'precision': 0.5491404476159585, 'recall': 0.5585615308479049, 'f1': 0.5538109257441937, 'number': 3031}, 'overall_precision': 0.46245574809018075, 'overall_recall': 0.5167603581095149, 'overall_f1': 0.48810226155358905, 'overall_accuracy': 0.7796434338110416}
			------------EPOCH 24---------------
Loss:  tensor(0.0129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1328, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3583602026715799, 'recall': 0.43905191873589167, 'f1': 0.39462338321075324, 'number': 1772}, 'P': {'precision': 0.5537512179278987, 'recall': 0.5625206202573408, 'f1': 0.55810147299509, 'number': 3031}, 'overall_precision': 0.47295238095238096, 'overall_recall': 0.5169685613158442, 'overall_f1': 0.4939818959514573, 'overall_accuracy': 0.7792000267717458}
			------------EPOCH 25---------------
Loss:  tensor(0.0119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1927, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.35296742525658187, 'recall': 0.4463882618510158, 'f1': 0.3942187889359581, 'number': 1772}, 'P': {'precision': 0.5492866407263295, 'recall': 0.558891454965358, 'f1': 0.5540474243663124, 'number': 3031}, 'overall_precision': 0.4666666666666667, 'overall_recall': 0.5173849677285031, 'overall_f1': 0.4907187993680885, 'overall_accuracy': 0.7790661680429017}
			------------EPOCH 26---------------
Loss:  tensor(0.0112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0744, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1838, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.31245011971268954, 'recall': 0.44187358916478553, 'f1': 0.36605890603085556, 'number': 1772}, 'P': {'precision': 0.5015862944162437, 'recall': 0.5216100296931706, 'f1': 0.5114022319262495, 'number': 3031}, 'overall_precision': 0.4178154825026511, 'overall_recall': 0.49219237976264835, 'overall_f1': 0.45196443934614283, 'overall_accuracy': 0.7751089693714496}
			------------EPOCH 27---------------
Loss:  tensor(0.0193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0671, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1263, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3626794258373206, 'recall': 0.42776523702031605, 'f1': 0.3925427239772139, 'number': 1772}, 'P': {'precision': 0.541256157635468, 'recall': 0.580006598482349, 'f1': 0.5599617773530817, 'number': 3031}, 'overall_precision': 0.4713375796178344, 'overall_recall': 0.5238392671247137, 'overall_f1': 0.4962035302238438, 'overall_accuracy': 0.7829899020321428}
			------------EPOCH 28---------------
Loss:  tensor(0.0124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0660, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1456, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3836734693877551, 'recall': 0.42437923250564336, 'f1': 0.4030010718113612, 'number': 1772}, 'P': {'precision': 0.5807888040712468, 'recall': 0.6024414384691521, 'f1': 0.5914170040485829, 'number': 3031}, 'overall_precision': 0.5050940438871473, 'overall_recall': 0.5367478659171351, 'overall_f1': 0.5204400928636317, 'overall_accuracy': 0.7849726844531453}
			------------EPOCH 29---------------
Loss:  tensor(0.0173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1171, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3726437892701788, 'recall': 0.4351015801354402, 'f1': 0.4014579536579016, 'number': 1772}, 'P': {'precision': 0.5669138987423412, 'recall': 0.580006598482349, 'f1': 0.5733855185909981, 'number': 3031}, 'overall_precision': 0.4891682785299807, 'overall_recall': 0.5265459088069956, 'overall_f1': 0.5071693572646145, 'overall_accuracy': 0.7839269131340512}
			------------EPOCH 30---------------
Loss:  tensor(0.0119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0874, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.34951456310679613, 'recall': 0.42663656884875845, 'f1': 0.38424396442185516, 'number': 1772}, 'P': {'precision': 0.5370835952231301, 'recall': 0.5638403167271527, 'f1': 0.550136809914695, 'number': 3031}, 'overall_precision': 0.46117867165575305, 'overall_recall': 0.5132209036019155, 'overall_f1': 0.4858100118249902, 'overall_accuracy': 0.7798525880748605}
	Data split: 21k
			------------EPOCH 1---------------
Loss:  tensor(3.7561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3841, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7412, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.0822339489885664, 'recall': 0.061695809963708347, 'f1': 0.07049952874646559, 'number': 3031}, 'overall_precision': 0.08219780219780219, 'overall_recall': 0.03893399958359359, 'overall_f1': 0.05283978525007064, 'overall_accuracy': 0.4958796610027692}
			------------EPOCH 2---------------
Loss:  tensor(2.7189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4546, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1631, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5569, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3157894736842105, 'recall': 0.010158013544018058, 'f1': 0.019682886823400764, 'number': 1772}, 'P': {'precision': 0.31191902499483576, 'recall': 0.49818541735400856, 'f1': 0.3836382113821138, 'number': 3031}, 'overall_precision': 0.3119640669661086, 'overall_recall': 0.3181344992712888, 'overall_f1': 0.31501907019894854, 'overall_accuracy': 0.6836667252298605}
			------------EPOCH 3---------------
Loss:  tensor(2.3884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1231, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3439, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25, 'recall': 0.006207674943566591, 'f1': 0.01211453744493392, 'number': 1772}, 'P': {'precision': 0.37204081632653063, 'recall': 0.6014516661167931, 'f1': 0.4597150422393141, 'number': 3031}, 'overall_precision': 0.3709546925566343, 'overall_recall': 0.3818446804080783, 'overall_f1': 0.3763209192572073, 'overall_accuracy': 0.703017677718378}
			------------EPOCH 4---------------
Loss:  tensor(1.9929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9928, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2607, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8831, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1726, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2214765100671141, 'recall': 0.055869074492099324, 'f1': 0.08922938260477693, 'number': 1772}, 'P': {'precision': 0.3654570692048384, 'recall': 0.6080501484658528, 'f1': 0.45652712410205604, 'number': 3031}, 'overall_precision': 0.3537340619307832, 'overall_recall': 0.40433062669165104, 'overall_f1': 0.37734382590109783, 'overall_accuracy': 0.7244936375272947}
			------------EPOCH 5---------------
Loss:  tensor(1.7308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1435, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3785, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7633, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0772, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1916243654822335, 'recall': 0.08521444695259593, 'f1': 0.11796874999999998, 'number': 1772}, 'P': {'precision': 0.39449161317042863, 'recall': 0.6285054437479379, 'f1': 0.48473282442748084, 'number': 3031}, 'overall_precision': 0.3660316895139754, 'overall_recall': 0.42806579221320007, 'overall_f1': 0.39462571976967364, 'overall_accuracy': 0.7388918170485823}
			------------EPOCH 6---------------
Loss:  tensor(1.5033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1866, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9790, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2723112128146453, 'recall': 0.2686230248306998, 'f1': 0.27045454545454545, 'number': 1772}, 'P': {'precision': 0.4467818682694716, 'recall': 0.5885846255361267, 'f1': 0.5079726651480638, 'number': 3031}, 'overall_precision': 0.3936596411774952, 'overall_recall': 0.4705392463043931, 'overall_f1': 0.4286798179059181, 'overall_accuracy': 0.7727915401283371}
			------------EPOCH 7---------------
Loss:  tensor(1.2133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6825, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0418, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8261, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.31390728476821195, 'recall': 0.5349887133182845, 'f1': 0.3956594323873122, 'number': 1772}, 'P': {'precision': 0.4408499841420869, 'recall': 0.4585945232596503, 'f1': 0.44954721862871927, 'number': 3031}, 'overall_precision': 0.3787461526000324, 'overall_recall': 0.48677909639808453, 'overall_f1': 0.42602040816326536, 'overall_accuracy': 0.759112851274586}
			------------EPOCH 8---------------
Loss:  tensor(1.0578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5874, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7425, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.25927962606543853, 'recall': 0.5321670428893905, 'f1': 0.3486781290441856, 'number': 1772}, 'P': {'precision': 0.33283075763286846, 'recall': 0.29132299571098647, 'f1': 0.3106966924700915, 'number': 3031}, 'overall_precision': 0.290302066772655, 'overall_recall': 0.3801790547574433, 'overall_f1': 0.3292166230956459, 'overall_accuracy': 0.7068912146843026}
			------------EPOCH 9---------------
Loss:  tensor(1.0179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7428, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6683, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8293, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3130779392338177, 'recall': 0.26749435665914223, 'f1': 0.288496652465003, 'number': 1772}, 'P': {'precision': 0.46615523465703973, 'recall': 0.6816232266578687, 'f1': 0.5536647460806646, 'number': 3031}, 'overall_precision': 0.42717793474604776, 'overall_recall': 0.5288361440766188, 'overall_f1': 0.4726021025211648, 'overall_accuracy': 0.7815090898443056}
			------------EPOCH 10---------------
Loss:  tensor(0.9360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0597, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7780, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3394173394173394, 'recall': 0.5457110609480813, 'f1': 0.418524128976412, 'number': 1772}, 'P': {'precision': 0.5159410353102503, 'recall': 0.49653579676674364, 'f1': 0.5060524546065905, 'number': 3031}, 'overall_precision': 0.4287200832466181, 'overall_recall': 0.5146783260462211, 'overall_f1': 0.46778313936985527, 'overall_accuracy': 0.784780262530432}
			------------EPOCH 11---------------
Loss:  tensor(0.5347, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5305, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.32488917036098797, 'recall': 0.2895033860045147, 'f1': 0.306177260519248, 'number': 1772}, 'P': {'precision': 0.47935669707153145, 'recall': 0.6588584625536127, 'f1': 0.554953452827567, 'number': 3031}, 'overall_precision': 0.43690165361183636, 'overall_recall': 0.5225900478867375, 'overall_f1': 0.4759196056124384, 'overall_accuracy': 0.7850730784997783}
			------------EPOCH 12---------------
Loss:  tensor(0.4612, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2517, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4376, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.33116438356164385, 'recall': 0.5457110609480813, 'f1': 0.41219096334185856, 'number': 1772}, 'P': {'precision': 0.5655986509274874, 'recall': 0.5532827449686573, 'f1': 0.5593729152768512, 'number': 3031}, 'overall_precision': 0.44927782497875957, 'overall_recall': 0.5504892775348741, 'overall_f1': 0.49476047904191617, 'overall_accuracy': 0.7933555873470036}
			------------EPOCH 13---------------
Loss:  tensor(0.2673, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1947, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2693, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3509, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3600464576074332, 'recall': 0.34988713318284426, 'f1': 0.35489410417859185, 'number': 1772}, 'P': {'precision': 0.5084574602373139, 'recall': 0.6644671725503134, 'f1': 0.5760869565217391, 'number': 3031}, 'overall_precision': 0.4634875945803273, 'overall_recall': 0.5484072454715803, 'overall_f1': 0.5023841312225825, 'overall_accuracy': 0.800860042332823}
			------------EPOCH 14---------------
Loss:  tensor(0.1929, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1490, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3078, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.355857832382624, 'recall': 0.45767494356659144, 'f1': 0.4003949642063688, 'number': 1772}, 'P': {'precision': 0.5157090291536938, 'recall': 0.6011217419993401, 'f1': 0.5551492992078001, 'number': 3031}, 'overall_precision': 0.45302821748107364, 'overall_recall': 0.5481990422652508, 'overall_f1': 0.49609043805934994, 'overall_accuracy': 0.8012950832015662}
			------------EPOCH 15---------------
Loss:  tensor(0.1158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0415, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0925, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5430, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.33838575217885564, 'recall': 0.5039503386004515, 'f1': 0.4048968487871231, 'number': 1772}, 'P': {'precision': 0.5611581001951854, 'recall': 0.5691191026064005, 'f1': 0.5651105651105651, 'number': 3031}, 'overall_precision': 0.4582531069490635, 'overall_recall': 0.5450759941703103, 'overall_f1': 0.49790794979079506, 'overall_accuracy': 0.7951292155041872}
			------------EPOCH 16---------------
Loss:  tensor(0.0898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3306, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3434917355371901, 'recall': 0.3752821670428894, 'f1': 0.3586839266450917, 'number': 1772}, 'P': {'precision': 0.566079295154185, 'recall': 0.6783239854833388, 'f1': 0.6171394266846765, 'number': 3031}, 'overall_precision': 0.4886853448275862, 'overall_recall': 0.5665209244222361, 'overall_f1': 0.5247324269597917, 'overall_accuracy': 0.8009520702089032}
			------------EPOCH 17---------------
Loss:  tensor(0.0843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2813, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.38013318534961155, 'recall': 0.38656884875846503, 'f1': 0.38332400671516514, 'number': 1772}, 'P': {'precision': 0.504950495049505, 'recall': 0.6562190696139888, 'f1': 0.5707317073170731, 'number': 3031}, 'overall_precision': 0.46577251349939036, 'overall_recall': 0.5567353737247553, 'overall_f1': 0.5072078907435508, 'overall_accuracy': 0.8022404604740272}
			------------EPOCH 18---------------
Loss:  tensor(0.0552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0343, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2541, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.35216089002995293, 'recall': 0.46444695259593677, 'f1': 0.40058408371866633, 'number': 1772}, 'P': {'precision': 0.5193145512634331, 'recall': 0.5899043220059387, 'f1': 0.5523632993512512, 'number': 3031}, 'overall_precision': 0.45173010380622836, 'overall_recall': 0.5436185717260046, 'overall_f1': 0.4934328640272134, 'overall_accuracy': 0.7989190907645843}
			------------EPOCH 19---------------
Loss:  tensor(0.0454, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0943, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2321, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3981399468556244, 'recall': 0.5073363431151241, 'f1': 0.4461538461538461, 'number': 1772}, 'P': {'precision': 0.5978056426332289, 'recall': 0.629165291982844, 'f1': 0.6130847130686385, 'number': 3031}, 'overall_precision': 0.5150513950073421, 'overall_recall': 0.5842181969602331, 'overall_f1': 0.5474587845088285, 'overall_accuracy': 0.8087911720168327}
			------------EPOCH 20---------------
Loss:  tensor(0.0319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0198, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2270, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.38193548387096776, 'recall': 0.5011286681715575, 'f1': 0.4334879179887723, 'number': 1772}, 'P': {'precision': 0.5905292479108635, 'recall': 0.6294952161002969, 'f1': 0.60938997125519, 'number': 3031}, 'overall_precision': 0.5032397408207343, 'overall_recall': 0.5821361648969394, 'overall_f1': 0.539820445988995, 'overall_accuracy': 0.8088413690401492}
			------------EPOCH 21---------------
Loss:  tensor(0.0241, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2139, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3710350584307179, 'recall': 0.5016930022573364, 'f1': 0.4265834932821497, 'number': 1772}, 'P': {'precision': 0.5861111111111111, 'recall': 0.6265258990432201, 'f1': 0.6056450326901611, 'number': 3031}, 'overall_precision': 0.49467707594038324, 'overall_recall': 0.5804705392463044, 'overall_f1': 0.5341507807261232, 'overall_accuracy': 0.8069840791774381}
			------------EPOCH 22---------------
Loss:  tensor(0.0160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0530, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1506, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2028, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3874887488748875, 'recall': 0.48589164785553046, 'f1': 0.43114672008012017, 'number': 1772}, 'P': {'precision': 0.5789001793185894, 'recall': 0.6390630155064335, 'f1': 0.607495687627411, 'number': 3031}, 'overall_precision': 0.5025143678160919, 'overall_recall': 0.5825525713095981, 'overall_f1': 0.539581525407386, 'overall_accuracy': 0.807394021534523}
			------------EPOCH 23---------------
Loss:  tensor(0.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2076, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.36744386873920554, 'recall': 0.4802483069977427, 'f1': 0.4163405088062622, 'number': 1772}, 'P': {'precision': 0.5806354009077156, 'recall': 0.6331243813922798, 'f1': 0.6057449494949495, 'number': 3031}, 'overall_precision': 0.4927948763565202, 'overall_recall': 0.5767228815323756, 'overall_f1': 0.5314658480429777, 'overall_accuracy': 0.806448644262062}
			------------EPOCH 24---------------
Loss:  tensor(0.0108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2070, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.36380090497737555, 'recall': 0.45372460496614, 'f1': 0.40381717729784034, 'number': 1772}, 'P': {'precision': 0.5715959004392387, 'recall': 0.6440118772682283, 'f1': 0.6056469128141484, 'number': 3031}, 'overall_precision': 0.48995555555555553, 'overall_recall': 0.5738080366437643, 'overall_f1': 0.5285769083237438, 'overall_accuracy': 0.8078876255971355}
			------------EPOCH 25---------------
Loss:  tensor(0.0084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2212, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3819475322365496, 'recall': 0.4847629796839729, 'f1': 0.4272569012683412, 'number': 1772}, 'P': {'precision': 0.6007485963817841, 'recall': 0.6354338502144506, 'f1': 0.6176046176046176, 'number': 3031}, 'overall_precision': 0.5105407882676444, 'overall_recall': 0.5798459296273163, 'overall_f1': 0.5429908364203548, 'overall_accuracy': 0.8061558282927156}
			------------EPOCH 26---------------
Loss:  tensor(0.0077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1741, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.37693798449612403, 'recall': 0.43905191873589167, 'f1': 0.4056308654848801, 'number': 1772}, 'P': {'precision': 0.5697507877399026, 'recall': 0.6562190696139888, 'f1': 0.6099356025758969, 'number': 3031}, 'overall_precision': 0.49810981098109813, 'overall_recall': 0.5760982719133875, 'overall_f1': 0.5342730256806334, 'overall_accuracy': 0.8100209990880874}
			------------EPOCH 27---------------
Loss:  tensor(0.0071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1546, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3721787194841087, 'recall': 0.45598194130925507, 'f1': 0.4098402231803195, 'number': 1772}, 'P': {'precision': 0.5871641791044776, 'recall': 0.648960739030023, 'f1': 0.6165177871806926, 'number': 3031}, 'overall_precision': 0.5026263358087303, 'overall_recall': 0.5777638975640225, 'overall_f1': 0.537582332429291, 'overall_accuracy': 0.8091676496917066}
			------------EPOCH 28---------------
Loss:  tensor(0.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1418, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3857412653446648, 'recall': 0.46106094808126413, 'f1': 0.42005141388174805, 'number': 1772}, 'P': {'precision': 0.5966666666666667, 'recall': 0.6496205872649291, 'f1': 0.6220186384457431, 'number': 3031}, 'overall_precision': 0.5142118863049095, 'overall_recall': 0.5800541328336456, 'overall_f1': 0.5451521377556011, 'overall_accuracy': 0.8084397928536171}
			------------EPOCH 29---------------
Loss:  tensor(0.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1453, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3776765375854214, 'recall': 0.46783295711060946, 'f1': 0.41794807159062264, 'number': 1772}, 'P': {'precision': 0.5957120980091883, 'recall': 0.6417024084460574, 'f1': 0.6178526048284625, 'number': 3031}, 'overall_precision': 0.508058608058608, 'overall_recall': 0.5775556943576932, 'overall_f1': 0.5405826756309071, 'overall_accuracy': 0.8075697111161309}
			------------EPOCH 30---------------
Loss:  tensor(0.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1294, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2262, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3375544123466561, 'recall': 0.4813769751693002, 'f1': 0.3968364735985113, 'number': 1772}, 'P': {'precision': 0.5837612323491655, 'recall': 0.6001319696469812, 'f1': 0.5918334146738247, 'number': 3031}, 'overall_precision': 0.4735069998227893, 'overall_recall': 0.5563189673120966, 'overall_f1': 0.5115833811985449, 'overall_accuracy': 0.8003329735879996}
Tokenizer: ../arg_m/arg_mining/smlm_pretrained_iter4_0/tokenizer Model: ../arg_m/arg_mining/smlm_pretrained_iter4_0/model
	Data split: 1k
			------------EPOCH 1---------------
Loss:  tensor(0.3114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4533, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.00015354693417954756, 'recall': 0.001693002257336343, 'f1': 0.0002815579540122009, 'number': 1772}, 'P': {'precision': 0.00017110591456111332, 'recall': 0.0009897723523589574, 'f1': 0.0002917720287881735, 'number': 3031}, 'overall_precision': 0.000161851582099215, 'overall_recall': 0.0012492192379762648, 'overall_f1': 0.0002865740077374982, 'overall_accuracy': 0.2637686251871931}
			------------EPOCH 2---------------
Loss:  tensor(0.2622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3719, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3031}, 'overall_precision': 0.0, 'overall_recall': 0.0, 'overall_f1': 0.0, 'overall_accuracy': 0.45322055735428224}
			------------EPOCH 3---------------
Loss:  tensor(0.2413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3280, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.020048115477145148, 'recall': 0.008248102936324645, 'f1': 0.01168770453482936, 'number': 3031}, 'overall_precision': 0.0188821752265861, 'overall_recall': 0.005205080158234437, 'overall_f1': 0.008160600620205648, 'overall_accuracy': 0.48342243304972016}
			------------EPOCH 4---------------
Loss:  tensor(0.2286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2989, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.01020408163265306, 'recall': 0.000564334085778781, 'f1': 0.0010695187165775401, 'number': 1772}, 'P': {'precision': 0.11810532876285447, 'recall': 0.12504124051468163, 'f1': 0.12147435897435897, 'number': 3031}, 'overall_precision': 0.1149077713940127, 'overall_recall': 0.07911721840516343, 'overall_f1': 0.09371146732429099, 'overall_accuracy': 0.5731245137163367}
			------------EPOCH 5---------------
Loss:  tensor(0.2074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2689, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.02973977695167286, 'recall': 0.004514672686230248, 'f1': 0.007839294463498283, 'number': 1772}, 'P': {'precision': 0.22549691569568198, 'recall': 0.325635103926097, 'f1': 0.2664686825053995, 'number': 3031}, 'overall_precision': 0.2141627206198881, 'overall_recall': 0.2071621902977306, 'overall_f1': 0.21060429675097894, 'overall_accuracy': 0.6346660643023869}
			------------EPOCH 6---------------
Loss:  tensor(0.1823, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1837, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2382, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.07560627674750357, 'recall': 0.029909706546275394, 'f1': 0.04286291953093409, 'number': 1772}, 'P': {'precision': 0.2823285780027612, 'recall': 0.4048168921148136, 'f1': 0.3326555510370069, 'number': 3031}, 'overall_precision': 0.25361600951060037, 'overall_recall': 0.2665001041016032, 'overall_f1': 0.2598984771573604, 'overall_accuracy': 0.6739117703653507}
			------------EPOCH 7---------------
Loss:  tensor(0.1582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2023, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0979431929480901, 'recall': 0.056433408577878104, 'f1': 0.07160759040458288, 'number': 1772}, 'P': {'precision': 0.30271299381247024, 'recall': 0.41966347740019794, 'f1': 0.35172127747822485, 'number': 3031}, 'overall_precision': 0.2626842810645223, 'overall_recall': 0.2856547990839059, 'overall_f1': 0.27368841013365247, 'overall_accuracy': 0.6866785466288515}
			------------EPOCH 8---------------
Loss:  tensor(0.1339, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1654, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.09734513274336283, 'recall': 0.055869074492099324, 'f1': 0.07099318752240948, 'number': 1772}, 'P': {'precision': 0.3187966417910448, 'recall': 0.4510062685582316, 'f1': 0.3735482989479437, 'number': 3031}, 'overall_precision': 0.2763430725730443, 'overall_recall': 0.3052259004788674, 'overall_f1': 0.29006727344677485, 'overall_accuracy': 0.6939654811802993}
			------------EPOCH 9---------------
Loss:  tensor(0.1086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1319, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10069444444444445, 'recall': 0.08182844243792325, 'f1': 0.09028642590286426, 'number': 1772}, 'P': {'precision': 0.32595010491956167, 'recall': 0.4612339161992742, 'f1': 0.38196721311475407, 'number': 3031}, 'overall_precision': 0.26933147146098796, 'overall_recall': 0.3212575473662294, 'overall_f1': 0.2930117736422332, 'overall_accuracy': 0.7005078265525521}
			------------EPOCH 10---------------
Loss:  tensor(0.0833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0830, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1071, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11954674220963173, 'recall': 0.1190744920993228, 'f1': 0.11931014984450097, 'number': 1772}, 'P': {'precision': 0.3408880666049954, 'recall': 0.4863081491257011, 'f1': 0.4008157715839565, 'number': 3031}, 'overall_precision': 0.2767285268516998, 'overall_recall': 0.35082240266500103, 'overall_f1': 0.30940139551964746, 'overall_accuracy': 0.7036953375331509}
			------------EPOCH 11---------------
Loss:  tensor(0.0627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0628, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0890, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12030716723549488, 'recall': 0.15914221218961624, 'f1': 0.13702623906705538, 'number': 1772}, 'P': {'precision': 0.32919109026963655, 'recall': 0.46321346090399207, 'f1': 0.3848684210526315, 'number': 3031}, 'overall_precision': 0.25510667271901954, 'overall_recall': 0.3510306058713304, 'overall_f1': 0.29547844374342797, 'overall_accuracy': 0.6969354717265266}
			------------EPOCH 12---------------
Loss:  tensor(0.0457, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0712, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11539823008849558, 'recall': 0.18397291196388263, 'f1': 0.14183162932347185, 'number': 1772}, 'P': {'precision': 0.2879395798914326, 'recall': 0.4025074232926427, 'f1': 0.33571821684094666, 'number': 3031}, 'overall_precision': 0.21891815349759275, 'overall_recall': 0.32188215698521755, 'overall_f1': 0.260598398651496, 'overall_accuracy': 0.6914472638439207}
			------------EPOCH 13---------------
Loss:  tensor(0.0330, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0360, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0560, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10403481012658228, 'recall': 0.14841986455981943, 'f1': 0.12232558139534884, 'number': 1772}, 'P': {'precision': 0.2734375, 'recall': 0.41570438799076215, 'f1': 0.32988611074748003, 'number': 3031}, 'overall_precision': 0.21342488789237668, 'overall_recall': 0.31709348323964187, 'overall_f1': 0.2551302454141888, 'overall_accuracy': 0.6938148901103498}
			------------EPOCH 14---------------
Loss:  tensor(0.0238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0452, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.09872611464968153, 'recall': 0.1399548532731377, 'f1': 0.1157796451914099, 'number': 1772}, 'P': {'precision': 0.26517571884984026, 'recall': 0.4107555262289673, 'f1': 0.32228837690913803, 'number': 3031}, 'overall_precision': 0.20715970584154295, 'overall_recall': 0.31084738704976056, 'overall_f1': 0.24862614487926726, 'overall_accuracy': 0.6933714830710539}
			------------EPOCH 15---------------
Loss:  tensor(0.0174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0371, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10323501427212178, 'recall': 0.12246049661399548, 'f1': 0.1120289106866288, 'number': 1772}, 'P': {'precision': 0.2801882930822759, 'recall': 0.45166611679313756, 'f1': 0.34583806997600103, 'number': 3031}, 'overall_precision': 0.226960503720664, 'overall_recall': 0.3302102852383927, 'overall_f1': 0.2690187431091511, 'overall_accuracy': 0.6972533862075312}
			------------EPOCH 16---------------
Loss:  tensor(0.0124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0328, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.09899947340705635, 'recall': 0.10609480812641084, 'f1': 0.10242440751838736, 'number': 1772}, 'P': {'precision': 0.286598761733573, 'recall': 0.47344110854503463, 'f1': 0.3570539935307291, 'number': 3031}, 'overall_precision': 0.23501303214596003, 'overall_recall': 0.33791380387257963, 'overall_f1': 0.27722264924417117, 'overall_accuracy': 0.6981234679450176}
			------------EPOCH 17---------------
Loss:  tensor(0.0089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0203, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10341463414634146, 'recall': 0.11963882618510158, 'f1': 0.1109366823652538, 'number': 1772}, 'P': {'precision': 0.27756653992395436, 'recall': 0.4576047509072913, 'f1': 0.3455406078724464, 'number': 3031}, 'overall_precision': 0.22690506598552576, 'overall_recall': 0.3329169269206746, 'overall_f1': 0.269873417721519, 'overall_accuracy': 0.696651021927733}
			------------EPOCH 18---------------
Loss:  tensor(0.0066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0159, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10248283148441627, 'recall': 0.10948081264108352, 'f1': 0.1058663028649386, 'number': 1772}, 'P': {'precision': 0.27244401168451804, 'recall': 0.46156384031672715, 'f1': 0.3426402155277982, 'number': 3031}, 'overall_precision': 0.22666476949345477, 'overall_recall': 0.3316677076826983, 'overall_f1': 0.26929253655650415, 'overall_accuracy': 0.6958562357252215}
			------------EPOCH 19---------------
Loss:  tensor(0.0051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0123, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.10919540229885058, 'recall': 0.1072234762979684, 'f1': 0.10820045558086562, 'number': 1772}, 'P': {'precision': 0.27559661277906083, 'recall': 0.4724513361926757, 'f1': 0.34812203719460316, 'number': 3031}, 'overall_precision': 0.23385236447520186, 'overall_recall': 0.33770560066625027, 'overall_f1': 0.27634381122753215, 'overall_accuracy': 0.6972533862075312}
			------------EPOCH 20---------------
Loss:  tensor(0.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0080, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11129848229342328, 'recall': 0.11173814898419865, 'f1': 0.11151788228667982, 'number': 1772}, 'P': {'precision': 0.2759223300970874, 'recall': 0.46882217090069284, 'f1': 0.3473902945850141, 'number': 3031}, 'overall_precision': 0.23365565016596912, 'overall_recall': 0.33708099104726214, 'overall_f1': 0.27599727241732014, 'overall_accuracy': 0.6966928527804968}
			------------EPOCH 21---------------
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0072, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.11348684210526316, 'recall': 0.11681715575620767, 'f1': 0.11512791991101225, 'number': 1772}, 'P': {'precision': 0.27931644077784323, 'recall': 0.4691520950181458, 'f1': 0.35016005909874415, 'number': 3031}, 'overall_precision': 0.23557483731019524, 'overall_recall': 0.3391630231105559, 'overall_f1': 0.2780337941628264, 'overall_accuracy': 0.6958060387019049}
			------------EPOCH 22---------------
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0064, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12069937958262832, 'recall': 0.12076749435665914, 'f1': 0.12073342736248237, 'number': 1772}, 'P': {'precision': 0.28473042109405744, 'recall': 0.4774001979544705, 'f1': 0.3567114507580426, 'number': 3031}, 'overall_precision': 0.24230488694383662, 'overall_recall': 0.345825525713096, 'overall_f1': 0.2849545376565448, 'overall_accuracy': 0.6970693304553707}
			------------EPOCH 23---------------
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12322274881516587, 'recall': 0.11738148984198646, 'f1': 0.12023121387283238, 'number': 1772}, 'P': {'precision': 0.2847411444141689, 'recall': 0.48267898383371827, 'f1': 0.35818337617823476, 'number': 3031}, 'overall_precision': 0.24479929680632875, 'overall_recall': 0.34790755777638976, 'overall_f1': 0.2873849858113337, 'overall_accuracy': 0.6978808489989877}
			------------EPOCH 24---------------
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12561881188118812, 'recall': 0.11455981941309255, 'f1': 0.11983471074380166, 'number': 1772}, 'P': {'precision': 0.2857418111753372, 'recall': 0.48927746618277795, 'f1': 0.36078335968860237, 'number': 3031}, 'overall_precision': 0.24772259770790478, 'overall_recall': 0.3510306058713304, 'overall_f1': 0.2904642949435783, 'overall_accuracy': 0.6981820311388868}
			------------EPOCH 25---------------
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1287779237844941, 'recall': 0.11060948081264109, 'f1': 0.11900425015179114, 'number': 1772}, 'P': {'precision': 0.2823977164605138, 'recall': 0.4896073903002309, 'f1': 0.3581945450156891, 'number': 3031}, 'overall_precision': 0.2478972996901284, 'overall_recall': 0.3497813866333542, 'overall_f1': 0.2901554404145078, 'overall_accuracy': 0.6980314400689372}
			------------EPOCH 26---------------
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.13172043010752688, 'recall': 0.11060948081264109, 'f1': 0.12024539877300613, 'number': 1772}, 'P': {'precision': 0.27876273104488875, 'recall': 0.48762784559551303, 'f1': 0.3547341893675748, 'number': 3031}, 'overall_precision': 0.24653902798232696, 'overall_recall': 0.3485321673953779, 'overall_f1': 0.2887949624773571, 'overall_accuracy': 0.6983409883793891}
			------------EPOCH 27---------------
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1264591439688716, 'recall': 0.1100451467268623, 'f1': 0.11768255884127943, 'number': 1772}, 'P': {'precision': 0.27378933484077633, 'recall': 0.47937974265918837, 'f1': 0.3485248260973855, 'number': 3031}, 'overall_precision': 0.24061906847714995, 'overall_recall': 0.3431188840308141, 'overall_f1': 0.2828698935805012, 'overall_accuracy': 0.6972450200369785}
			------------EPOCH 28---------------
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12709237445753255, 'recall': 0.11568848758465011, 'f1': 0.12112259970457903, 'number': 1772}, 'P': {'precision': 0.26912878787878786, 'recall': 0.46882217090069284, 'f1': 0.3419564432679581, 'number': 3031}, 'overall_precision': 0.23589148411431887, 'overall_recall': 0.33853841349156777, 'overall_f1': 0.2780437756497948, 'overall_accuracy': 0.6962829104234118}
			------------EPOCH 29---------------
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.1268028846153846, 'recall': 0.1190744920993228, 'f1': 0.12281722933643771, 'number': 1772}, 'P': {'precision': 0.2655775075987842, 'recall': 0.4612339161992742, 'f1': 0.33707052441229657, 'number': 3031}, 'overall_precision': 0.2322459584295612, 'overall_recall': 0.33499895898396836, 'overall_f1': 0.2743159150967522, 'overall_accuracy': 0.6954211948564784}
			------------EPOCH 30---------------
Loss:  tensor(0.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.12558139534883722, 'recall': 0.12189616252821671, 'f1': 0.12371134020618556, 'number': 1772}, 'P': {'precision': 0.26503723505823945, 'recall': 0.45793467502474433, 'f1': 0.33575229801644896, 'number': 3031}, 'overall_precision': 0.23055914905850222, 'overall_recall': 0.33395794295232145, 'overall_f1': 0.2727891156462585, 'overall_accuracy': 0.6951200127165792}
	Data split: 6k
			------------EPOCH 1---------------
Loss:  tensor(0.8030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5774, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2784, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7042, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.07223208999407933, 'recall': 0.08050148465852854, 'f1': 0.07614292401310657, 'number': 3031}, 'overall_precision': 0.06933788007956806, 'overall_recall': 0.0508015823443681, 'overall_f1': 0.058639750060081715, 'overall_accuracy': 0.5728567962586485}
			------------EPOCH 2---------------
Loss:  tensor(0.5962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6048, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.08823529411764706, 'recall': 0.005079006772009029, 'f1': 0.0096051227321238, 'number': 1772}, 'P': {'precision': 0.20420242675347736, 'recall': 0.22764764104256022, 'f1': 0.21528861154446177, 'number': 3031}, 'overall_precision': 0.20080436656133294, 'overall_recall': 0.14553404122423486, 'overall_f1': 0.16875905359729598, 'overall_accuracy': 0.6646002225401367}
			------------EPOCH 3---------------
Loss:  tensor(0.5281, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5368, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2581967213114754, 'recall': 0.035553047404063204, 'f1': 0.0625, 'number': 1772}, 'P': {'precision': 0.3532212885154062, 'recall': 0.4160343121082151, 'f1': 0.38206332373882745, 'number': 3031}, 'overall_precision': 0.3471421080230729, 'overall_recall': 0.27566104518009577, 'overall_f1': 0.30729952419635603, 'overall_accuracy': 0.7015786963833045}
			------------EPOCH 4---------------
Loss:  tensor(0.4563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2847, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4614, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26795580110497236, 'recall': 0.10948081264108352, 'f1': 0.15544871794871795, 'number': 1772}, 'P': {'precision': 0.4165159734779988, 'recall': 0.4559551303200264, 'f1': 0.4353441486848323, 'number': 3031}, 'overall_precision': 0.3899059871350816, 'overall_recall': 0.3281282531750989, 'overall_f1': 0.35635952515545505, 'overall_accuracy': 0.7117017627521355}
			------------EPOCH 5---------------
Loss:  tensor(0.3941, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6963, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1867, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4135, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3059360730593607, 'recall': 0.18905191873589164, 'f1': 0.2336937565399372, 'number': 1772}, 'P': {'precision': 0.44499707431246344, 'recall': 0.5018145826459914, 'f1': 0.471701038920763, 'number': 3031}, 'overall_precision': 0.4112563704852648, 'overall_recall': 0.3864251509473246, 'overall_f1': 0.39845427221983687, 'overall_accuracy': 0.7404060939186307}
			------------EPOCH 6---------------
Loss:  tensor(0.2975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3688, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1576, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3364, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22963367960634226, 'recall': 0.23702031602708803, 'f1': 0.233268536517634, 'number': 1772}, 'P': {'precision': 0.4670144216017183, 'recall': 0.5021445067634444, 'f1': 0.48394276629570737, 'number': 3031}, 'overall_precision': 0.3816823899371069, 'overall_recall': 0.40433062669165104, 'overall_f1': 0.39268021433626527, 'overall_accuracy': 0.7383229174509952}
			------------EPOCH 7---------------
Loss:  tensor(0.2278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2710, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29235237173281703, 'recall': 0.34085778781038373, 'f1': 0.31474726420010424, 'number': 1772}, 'P': {'precision': 0.5117162761241292, 'recall': 0.5331573738040251, 'f1': 0.5222168363225076, 'number': 3031}, 'overall_precision': 0.42496171516079634, 'overall_recall': 0.462211118051218, 'overall_f1': 0.4428044280442805, 'overall_accuracy': 0.7592383438328774}
			------------EPOCH 8---------------
Loss:  tensor(0.1707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2224, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2111913357400722, 'recall': 0.19808126410835214, 'f1': 0.20442632498543972, 'number': 1772}, 'P': {'precision': 0.4015251117538785, 'recall': 0.5037941273507094, 'f1': 0.44688323090430204, 'number': 3031}, 'overall_precision': 0.3436413540713632, 'overall_recall': 0.3910056214865709, 'overall_f1': 0.3657966497857421, 'overall_accuracy': 0.7387830568313966}
			------------EPOCH 9---------------
Loss:  tensor(0.1061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0807, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0808, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1757, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26681982277650146, 'recall': 0.458803611738149, 'f1': 0.3374144013280764, 'number': 1772}, 'P': {'precision': 0.4677860210855135, 'recall': 0.39524909270867703, 'f1': 0.42846924177396284, 'number': 3031}, 'overall_precision': 0.35859486447931527, 'overall_recall': 0.4186966479283781, 'overall_f1': 0.3863221592546345, 'overall_accuracy': 0.7308519271473868}
			------------EPOCH 10---------------
Loss:  tensor(0.0812, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0543, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2691, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2923420905533818, 'recall': 0.2951467268623025, 'f1': 0.2937377141252457, 'number': 1772}, 'P': {'precision': 0.4336917562724014, 'recall': 0.558891454965358, 'f1': 0.4883955600403633, 'number': 3031}, 'overall_precision': 0.38928884986830553, 'overall_recall': 0.46158650843222987, 'overall_f1': 0.42236616498380647, 'overall_accuracy': 0.7663914196554811}
			------------EPOCH 11---------------
Loss:  tensor(0.0449, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0332, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0922, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2243, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22620904836193448, 'recall': 0.327313769751693, 'f1': 0.2675276752767528, 'number': 1772}, 'P': {'precision': 0.3085968121243794, 'recall': 0.38964038271197626, 'f1': 0.3444152814231554, 'number': 3031}, 'overall_precision': 0.27554373337505866, 'overall_recall': 0.36664584634603375, 'overall_f1': 0.31463283902090405, 'overall_accuracy': 0.7402722351897866}
			------------EPOCH 12---------------
Loss:  tensor(0.0325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1097, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2899505766062603, 'recall': 0.1986455981941309, 'f1': 0.23576691225720026, 'number': 1772}, 'P': {'precision': 0.43335643335643337, 'recall': 0.6189376443418014, 'f1': 0.5097826086956522, 'number': 3031}, 'overall_precision': 0.40194840339166515, 'overall_recall': 0.463876743701853, 'overall_f1': 0.4306978542431858, 'overall_accuracy': 0.7565193384032327}
			------------EPOCH 13---------------
Loss:  tensor(0.0264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0508, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0935, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.27846425419240955, 'recall': 0.3560948081264108, 'f1': 0.3125309559187716, 'number': 1772}, 'P': {'precision': 0.45544267053701015, 'recall': 0.5176509402837347, 'f1': 0.48455836936380475, 'number': 3031}, 'overall_precision': 0.3852215023638592, 'overall_recall': 0.45804705392463047, 'overall_f1': 0.4184896328704585, 'overall_accuracy': 0.7633210350626208}
			------------EPOCH 14---------------
Loss:  tensor(0.0145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0119, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0387, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0922, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.27412988876928596, 'recall': 0.43115124153498874, 'f1': 0.3351612195656942, 'number': 1772}, 'P': {'precision': 0.4554118447923758, 'recall': 0.441438469152095, 'f1': 0.44831630088792096, 'number': 3031}, 'overall_precision': 0.36716157205240174, 'overall_recall': 0.4376431397043514, 'overall_f1': 0.39931610942249235, 'overall_accuracy': 0.7461118222356081}
			------------EPOCH 15---------------
Loss:  tensor(0.0109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0743, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3078947368421053, 'recall': 0.3301354401805869, 'f1': 0.31862745098039214, 'number': 1772}, 'P': {'precision': 0.45703544575725025, 'recall': 0.5615308479049819, 'f1': 0.5039230199851961, 'number': 3031}, 'overall_precision': 0.40665007112375534, 'overall_recall': 0.47616073287528626, 'overall_f1': 0.4386688405102138, 'overall_accuracy': 0.7658476185695522}
			------------EPOCH 16---------------
Loss:  tensor(0.0066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0669, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.31644736842105264, 'recall': 0.2714446952595937, 'f1': 0.2922235722964763, 'number': 1772}, 'P': {'precision': 0.44615009746588696, 'recall': 0.604091059056417, 'f1': 0.5132445690259285, 'number': 3031}, 'overall_precision': 0.41109530583214793, 'overall_recall': 0.4813658130335207, 'overall_f1': 0.44346408362904005, 'overall_accuracy': 0.7670858118113596}
			------------EPOCH 17---------------
Loss:  tensor(0.0051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0622, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30995323981295925, 'recall': 0.2618510158013544, 'f1': 0.28387886203732027, 'number': 1772}, 'P': {'precision': 0.44906394359348406, 'recall': 0.6093698449356648, 'f1': 0.5170772676371781, 'number': 3031}, 'overall_precision': 0.4119429590017825, 'overall_recall': 0.48115760982719136, 'overall_f1': 0.4438682416210506, 'overall_accuracy': 0.7660149419806073}
			------------EPOCH 18---------------
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0545, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3126865671641791, 'recall': 0.23645598194130926, 'f1': 0.269280205655527, 'number': 1772}, 'P': {'precision': 0.44171779141104295, 'recall': 0.6176179478719894, 'f1': 0.5150639702847709, 'number': 3031}, 'overall_precision': 0.4107206884187881, 'overall_recall': 0.4769935457006038, 'overall_f1': 0.4413832964068972, 'overall_accuracy': 0.7610621690133775}
			------------EPOCH 19---------------
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0482, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3037800687285223, 'recall': 0.24943566591422123, 'f1': 0.27393864270220014, 'number': 1772}, 'P': {'precision': 0.44069823051171686, 'recall': 0.6080501484658528, 'f1': 0.5110217662553722, 'number': 3031}, 'overall_precision': 0.4053574596416534, 'overall_recall': 0.47574432646262754, 'overall_f1': 0.43773946360153254, 'overall_accuracy': 0.7620493771386023}
			------------EPOCH 20---------------
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0415, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3060257278266757, 'recall': 0.255079006772009, 'f1': 0.2782394582948599, 'number': 1772}, 'P': {'precision': 0.44244172074020666, 'recall': 0.6073903002309469, 'f1': 0.5119577308120133, 'number': 3031}, 'overall_precision': 0.40670450514366796, 'overall_recall': 0.47740995211326254, 'overall_f1': 0.43922995881620536, 'overall_accuracy': 0.7634214291092538}
			------------EPOCH 21---------------
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0314, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2993421052631579, 'recall': 0.2567720090293454, 'f1': 0.27642770352369384, 'number': 1772}, 'P': {'precision': 0.44180982337285263, 'recall': 0.6024414384691521, 'f1': 0.5097710776102736, 'number': 3031}, 'overall_precision': 0.40350256500972936, 'overall_recall': 0.47491151363731, 'overall_f1': 0.4363045141545524, 'overall_accuracy': 0.7638648361485497}
			------------EPOCH 22---------------
Loss:  tensor(0.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0315, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29546946815495734, 'recall': 0.25395033860045146, 'f1': 0.27314112291350534, 'number': 1772}, 'P': {'precision': 0.44071051368218916, 'recall': 0.605740679643682, 'f1': 0.5102125885785743, 'number': 3031}, 'overall_precision': 0.401828089295131, 'overall_recall': 0.4759525296689569, 'overall_f1': 0.43576057948913455, 'overall_accuracy': 0.7638899346602079}
			------------EPOCH 23---------------
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0238, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3123759099933819, 'recall': 0.26636568848758463, 'f1': 0.2875418824246116, 'number': 1772}, 'P': {'precision': 0.4559113300492611, 'recall': 0.6106895414054767, 'f1': 0.5220702298688478, 'number': 3031}, 'overall_precision': 0.41698079339436367, 'overall_recall': 0.48365604830314385, 'overall_f1': 0.4478503952188163, 'overall_accuracy': 0.765546436429653}
			------------EPOCH 24---------------
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0191, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3122049898853675, 'recall': 0.2612866817155756, 'f1': 0.28448540706605224, 'number': 1772}, 'P': {'precision': 0.45043731778425655, 'recall': 0.6116793137578357, 'f1': 0.5188190849307401, 'number': 3031}, 'overall_precision': 0.41382389712448653, 'overall_recall': 0.48240682906516763, 'overall_f1': 0.4454912516823688, 'overall_accuracy': 0.765546436429653}
			------------EPOCH 25---------------
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0208, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2909286097691895, 'recall': 0.3058690744920993, 'f1': 0.2982118294360386, 'number': 1772}, 'P': {'precision': 0.4538679002827037, 'recall': 0.5826459914219729, 'f1': 0.5102571511123953, 'number': 3031}, 'overall_precision': 0.4011122697254084, 'overall_recall': 0.4805330002082032, 'overall_f1': 0.4372454295727953, 'overall_accuracy': 0.7689514678446234}
			------------EPOCH 26---------------
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0518, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0685, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2635197066911091, 'recall': 0.3244920993227991, 'f1': 0.29084471421345476, 'number': 1772}, 'P': {'precision': 0.43986254295532645, 'recall': 0.5489937314417684, 'f1': 0.488406222483123, 'number': 3031}, 'overall_precision': 0.37535624476110646, 'overall_recall': 0.4661669789714762, 'overall_f1': 0.4158618127786033, 'overall_accuracy': 0.7662910256088481}
			------------EPOCH 27---------------
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0851, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28892835997631733, 'recall': 0.27539503386004516, 'f1': 0.28199942213233165, 'number': 1772}, 'P': {'precision': 0.41303328645100795, 'recall': 0.581326294952161, 'f1': 0.4829381937782651, 'number': 3031}, 'overall_precision': 0.3778337531486146, 'overall_recall': 0.4684572142410993, 'overall_f1': 0.4182933630786392, 'overall_accuracy': 0.7648436781032218}
			------------EPOCH 28---------------
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0578, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.27007299270072993, 'recall': 0.3340857787810384, 'f1': 0.29868819374369326, 'number': 1772}, 'P': {'precision': 0.42232004142931123, 'recall': 0.5381062355658198, 'f1': 0.47323371536341213, 'number': 3031}, 'overall_precision': 0.367195242814668, 'overall_recall': 0.46283572767020614, 'overall_f1': 0.4095053882287925, 'overall_accuracy': 0.7660484066628183}
			------------EPOCH 29---------------
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0354, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28611422172452405, 'recall': 0.2883747178329571, 'f1': 0.2872400224845419, 'number': 1772}, 'P': {'precision': 0.4366093366093366, 'recall': 0.5862751567139558, 'f1': 0.500492888325588, 'number': 3031}, 'overall_precision': 0.3907103825136612, 'overall_recall': 0.4763689360816157, 'overall_f1': 0.4293085655314757, 'overall_accuracy': 0.7667511649892494}
			------------EPOCH 30---------------
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0229, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0278, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2900232018561485, 'recall': 0.28216704288939054, 'f1': 0.28604118993135014, 'number': 1772}, 'P': {'precision': 0.46184738955823296, 'recall': 0.607060376113494, 'f1': 0.5245901639344263, 'number': 3031}, 'overall_precision': 0.4099509460406447, 'overall_recall': 0.4871955028107433, 'overall_f1': 0.4452478356007991, 'overall_accuracy': 0.7673116984162839}
	Data split: 12k
			------------EPOCH 1---------------
Loss:  tensor(3.5800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2590, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0392, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1482, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5270, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.029153494906919566, 'recall': 0.027383701748597822, 'f1': 0.02824089826471589, 'number': 3031}, 'overall_precision': 0.029153494906919566, 'overall_recall': 0.01728086612533833, 'overall_f1': 0.021699346405228755, 'overall_accuracy': 0.43137648604104445}
			------------EPOCH 2---------------
Loss:  tensor(2.8760, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8851, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9980, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6274, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3429, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.22352274872569378, 'recall': 0.3906301550643352, 'f1': 0.2843419788664745, 'number': 3031}, 'overall_precision': 0.22352274872569378, 'overall_recall': 0.24651259629398292, 'overall_f1': 0.23445544554455444, 'overall_accuracy': 0.6653615440604372}
			------------EPOCH 3---------------
Loss:  tensor(2.5451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8740, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5531, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1722, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1772}, 'P': {'precision': 0.24321686511809487, 'recall': 0.4110854503464203, 'f1': 0.30561687515329905, 'number': 3031}, 'overall_precision': 0.24307452204447913, 'overall_recall': 0.2594211950864043, 'overall_f1': 0.2509819720012086, 'overall_accuracy': 0.6728241681934928}
			------------EPOCH 4---------------
Loss:  tensor(2.2097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0200, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3023255813953488, 'recall': 0.007336343115124154, 'f1': 0.014325068870523417, 'number': 1772}, 'P': {'precision': 0.3597612958226769, 'recall': 0.55691191026064, 'f1': 0.4371358280460961, 'number': 3031}, 'overall_precision': 0.35923970432946145, 'overall_recall': 0.3541536539662711, 'overall_f1': 0.35667854896204654, 'overall_accuracy': 0.700850839545215}
			------------EPOCH 5---------------
Loss:  tensor(1.9070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8814, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9285, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22310305775764439, 'recall': 0.11117381489841986, 'f1': 0.14839924670433144, 'number': 1772}, 'P': {'precision': 0.32611004886339495, 'recall': 0.5064335202903332, 'f1': 0.39674334453347115, 'number': 3031}, 'overall_precision': 0.30983899821109123, 'overall_recall': 0.3606079533624818, 'overall_f1': 0.33330126046377373, 'overall_accuracy': 0.7249454107371432}
			------------EPOCH 6---------------
Loss:  tensor(1.5870, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3534, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7922, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2652714932126697, 'recall': 0.2646726862302483, 'f1': 0.26497175141242935, 'number': 1772}, 'P': {'precision': 0.4352078239608802, 'recall': 0.5285384361596833, 'f1': 0.47735399284862934, 'number': 3031}, 'overall_precision': 0.38006973756652596, 'overall_recall': 0.43118884030814075, 'overall_f1': 0.4040187280530628, 'overall_accuracy': 0.7527378293133884}
			------------EPOCH 7---------------
Loss:  tensor(1.2371, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3800, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5503, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3736, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2790, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2965, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6492, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2479633401221996, 'recall': 0.2748306997742664, 'f1': 0.2607066381156317, 'number': 1772}, 'P': {'precision': 0.45647258338044094, 'recall': 0.5328274496865721, 'f1': 0.49170345562490486, 'number': 3031}, 'overall_precision': 0.3820428934932752, 'overall_recall': 0.4376431397043514, 'overall_f1': 0.4079573022804464, 'overall_accuracy': 0.7635552878380979}
			------------EPOCH 8---------------
Loss:  tensor(0.8696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2478, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2488, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5307, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.26603575184016826, 'recall': 0.4283295711060948, 'f1': 0.3282162162162162, 'number': 1772}, 'P': {'precision': 0.43890784982935155, 'recall': 0.42428241504453973, 'f1': 0.43147122965945306, 'number': 3031}, 'overall_precision': 0.35362268718658135, 'overall_recall': 0.42577555694357694, 'overall_f1': 0.38635934252786697, 'overall_accuracy': 0.7493829949217344}
			------------EPOCH 9---------------
Loss:  tensor(0.5694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1315, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2223, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6443, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2330316742081448, 'recall': 0.05812641083521445, 'f1': 0.0930442637759711, 'number': 1772}, 'P': {'precision': 0.43541102077687444, 'recall': 0.6360936984493566, 'f1': 0.5169593779326987, 'number': 3031}, 'overall_precision': 0.41704312114989733, 'overall_recall': 0.42286071205496567, 'overall_f1': 0.4199317688411041, 'overall_accuracy': 0.7196747232889089}
			------------EPOCH 10---------------
Loss:  tensor(2.0159, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1608, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7021, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.20472988638998377, 'recall': 0.4983069977426637, 'f1': 0.2902218570254725, 'number': 1772}, 'P': {'precision': 0.26558407543216345, 'recall': 0.1672715275486638, 'f1': 0.20526315789473684, 'number': 3031}, 'overall_precision': 0.22340083574413372, 'overall_recall': 0.28940245679783466, 'overall_f1': 0.25215419501133784, 'overall_accuracy': 0.6347413598373617}
			------------EPOCH 11---------------
Loss:  tensor(0.9617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0582, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3920, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6641, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.32166446499339496, 'recall': 0.2748306997742664, 'f1': 0.2964090079123555, 'number': 1772}, 'P': {'precision': 0.4190777576853526, 'recall': 0.6116793137578357, 'f1': 0.49738430583501014, 'number': 3031}, 'overall_precision': 0.3942404850117885, 'overall_recall': 0.48740370601707267, 'overall_f1': 0.4358998231077181, 'overall_accuracy': 0.7689263693329652}
			------------EPOCH 12---------------
Loss:  tensor(0.5095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6154, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3361244019138756, 'recall': 0.31715575620767494, 'f1': 0.32636469221835074, 'number': 1772}, 'P': {'precision': 0.4598840019333011, 'recall': 0.627845595513032, 'f1': 0.5308969172827451, 'number': 3031}, 'overall_precision': 0.4242685025817556, 'overall_recall': 0.5132209036019155, 'overall_f1': 0.46452463959295204, 'overall_accuracy': 0.7807645006651106}
			------------EPOCH 13---------------
Loss:  tensor(0.3728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0285, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1446, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3564, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2891566265060241, 'recall': 0.40632054176072235, 'f1': 0.337869544814641, 'number': 1772}, 'P': {'precision': 0.5039569484013928, 'recall': 0.5252391949851534, 'f1': 0.5143780290791599, 'number': 3031}, 'overall_precision': 0.40927597804921223, 'overall_recall': 0.4813658130335207, 'overall_f1': 0.44240336777650213, 'overall_accuracy': 0.770390449179697}
			------------EPOCH 14---------------
Loss:  tensor(0.2473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1469, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3394, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29369747899159665, 'recall': 0.39446952595936796, 'f1': 0.33670520231213874, 'number': 1772}, 'P': {'precision': 0.5143307086614173, 'recall': 0.5387660838007259, 'f1': 0.5262649049307122, 'number': 3031}, 'overall_precision': 0.4198019801980198, 'overall_recall': 0.48552987716010826, 'overall_f1': 0.45027997682950377, 'overall_accuracy': 0.7761631068610965}
			------------EPOCH 15---------------
Loss:  tensor(0.1541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0479, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2783, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29134615384615387, 'recall': 0.34198645598194133, 'f1': 0.3146417445482867, 'number': 1772}, 'P': {'precision': 0.5, 'recall': 0.5826459914219729, 'f1': 0.5381685204936767, 'number': 3031}, 'overall_precision': 0.42266571632216676, 'overall_recall': 0.49385800541328334, 'overall_f1': 0.45549687950072015, 'overall_accuracy': 0.7819608630541542}
			------------EPOCH 16---------------
Loss:  tensor(0.0938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2693, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28961504028648166, 'recall': 0.36512415349887134, 'f1': 0.32301547678482273, 'number': 1772}, 'P': {'precision': 0.5088947214931467, 'recall': 0.5757175849554602, 'f1': 0.5402476780185759, 'number': 3031}, 'overall_precision': 0.4223909588557302, 'overall_recall': 0.49802206953987094, 'overall_f1': 0.45709917829161095, 'overall_accuracy': 0.7822453128529478}
			------------EPOCH 17---------------
Loss:  tensor(0.0586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2396, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29932829554995805, 'recall': 0.4023702031602709, 'f1': 0.3432835820895523, 'number': 1772}, 'P': {'precision': 0.521686381558993, 'recall': 0.5674694820191356, 'f1': 0.5436156763590392, 'number': 3031}, 'overall_precision': 0.4284204965662969, 'overall_recall': 0.5065584009993754, 'overall_f1': 0.4642243846594162, 'overall_accuracy': 0.7826719875511382}
			------------EPOCH 18---------------
Loss:  tensor(0.0419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0179, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2156, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28736141906873613, 'recall': 0.3656884875846501, 'f1': 0.32182766327290785, 'number': 1772}, 'P': {'precision': 0.49155937052932763, 'recall': 0.5668096337842297, 'f1': 0.5265093472264787, 'number': 3031}, 'overall_precision': 0.41147826086956524, 'overall_recall': 0.4926087861753071, 'overall_f1': 0.4484032976404815, 'overall_accuracy': 0.781391963456567}
			------------EPOCH 19---------------
Loss:  tensor(0.0325, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2104, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3096774193548387, 'recall': 0.3792325056433409, 'f1': 0.34094368340943687, 'number': 1772}, 'P': {'precision': 0.51145923991877, 'recall': 0.581656219069614, 'f1': 0.5443037974683544, 'number': 3031}, 'overall_precision': 0.4335054299448104, 'overall_recall': 0.5069748074120342, 'overall_f1': 0.4673704414587332, 'overall_accuracy': 0.7817266102786772}
			------------EPOCH 20---------------
Loss:  tensor(0.0257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2077, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2973708068902992, 'recall': 0.37020316027088035, 'f1': 0.3298139768728004, 'number': 1772}, 'P': {'precision': 0.5139173747436273, 'recall': 0.5786869020125371, 'f1': 0.5443823711980138, 'number': 3031}, 'overall_precision': 0.42890193984694786, 'overall_recall': 0.5017697272537998, 'overall_f1': 0.46248320859719827, 'overall_accuracy': 0.7818772013486267}
			------------EPOCH 21---------------
Loss:  tensor(0.0216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2120, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2928123492522914, 'recall': 0.3425507900677201, 'f1': 0.3157347204161249, 'number': 1772}, 'P': {'precision': 0.5042662116040956, 'recall': 0.5849554602441438, 'f1': 0.5416221170001527, 'number': 3031}, 'overall_precision': 0.42583646448380746, 'overall_recall': 0.4955236310639184, 'overall_f1': 0.4580446497305619, 'overall_accuracy': 0.7819022998602849}
			------------EPOCH 22---------------
Loss:  tensor(0.0188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0913, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2157, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2993006993006993, 'recall': 0.3623024830699774, 'f1': 0.32780188920091907, 'number': 1772}, 'P': {'precision': 0.5134345794392523, 'recall': 0.580006598482349, 'f1': 0.5446940356312936, 'number': 3031}, 'overall_precision': 0.4309570838570659, 'overall_recall': 0.49968769519050593, 'overall_f1': 0.4627844195912071, 'overall_accuracy': 0.7813083017510395}
			------------EPOCH 23---------------
Loss:  tensor(0.0152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2643, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.28736695974086074, 'recall': 0.35045146726862303, 'f1': 0.31578947368421056, 'number': 1772}, 'P': {'precision': 0.5004245683555052, 'recall': 0.5833058396568789, 'f1': 0.5386959171237051, 'number': 3031}, 'overall_precision': 0.41956445381102914, 'overall_recall': 0.4973974599208828, 'overall_f1': 0.455177669810422, 'overall_accuracy': 0.7809820210994821}
			------------EPOCH 24---------------
Loss:  tensor(0.0148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0055, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1956, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.31385281385281383, 'recall': 0.327313769751693, 'f1': 0.3204419889502762, 'number': 1772}, 'P': {'precision': 0.49335812964930925, 'recall': 0.6126690861101947, 'f1': 0.5465783664459162, 'number': 3031}, 'overall_precision': 0.434248039914469, 'overall_recall': 0.5073912138246929, 'overall_f1': 0.4679788766202592, 'overall_accuracy': 0.782136552635762}
			------------EPOCH 25---------------
Loss:  tensor(0.0139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1612, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.316836487142164, 'recall': 0.36851015801354403, 'f1': 0.3407252804591704, 'number': 1772}, 'P': {'precision': 0.5171135196805476, 'recall': 0.5981524249422633, 'f1': 0.5546886951200857, 'number': 3031}, 'overall_precision': 0.44296748697682775, 'overall_recall': 0.5134291068082448, 'overall_f1': 0.475602700096432, 'overall_accuracy': 0.7838097867463126}
			------------EPOCH 26---------------
Loss:  tensor(0.0128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1518, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30493883099229724, 'recall': 0.37979683972911965, 'f1': 0.3382759487308369, 'number': 1772}, 'P': {'precision': 0.516176041970271, 'recall': 0.5842956120092379, 'f1': 0.5481275147013307, 'number': 3031}, 'overall_precision': 0.43348705214615113, 'overall_recall': 0.5088486362689986, 'overall_f1': 0.4681543913418255, 'overall_accuracy': 0.7830066343732484}
			------------EPOCH 27---------------
Loss:  tensor(0.0120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0007, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1293, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3005591798695247, 'recall': 0.3639954853273138, 'f1': 0.32924961715160794, 'number': 1772}, 'P': {'precision': 0.5048268029528676, 'recall': 0.5866050808314087, 'f1': 0.5426522203570883, 'number': 3031}, 'overall_precision': 0.42748764996471417, 'overall_recall': 0.5044763689360816, 'overall_f1': 0.4628020246394804, 'overall_accuracy': 0.7830150005438011}
			------------EPOCH 28---------------
Loss:  tensor(0.0112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0687, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1223, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.30040964952207555, 'recall': 0.3724604966139955, 'f1': 0.3325774754346183, 'number': 1772}, 'P': {'precision': 0.5064599483204134, 'recall': 0.581986143187067, 'f1': 0.5416027018728891, 'number': 3031}, 'overall_precision': 0.4267605633802817, 'overall_recall': 0.504684572142411, 'overall_f1': 0.4624630353906325, 'overall_accuracy': 0.7834165767303333}
			------------EPOCH 29---------------
Loss:  tensor(0.0105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0649, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1096, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29977628635346754, 'recall': 0.3781038374717833, 'f1': 0.33441477414524584, 'number': 1772}, 'P': {'precision': 0.5081065431383903, 'recall': 0.5790168261299901, 'f1': 0.5412490362374711, 'number': 3031}, 'overall_precision': 0.4262612058358235, 'overall_recall': 0.5048927753487403, 'overall_f1': 0.46225695768204345, 'overall_accuracy': 0.7831990562959616}
			------------EPOCH 30---------------
Loss:  tensor(0.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0593, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0933, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2991840435176791, 'recall': 0.3724604966139955, 'f1': 0.33182503770739064, 'number': 1772}, 'P': {'precision': 0.5037079292641187, 'recall': 0.5826459914219729, 'f1': 0.5403090102493497, 'number': 3031}, 'overall_precision': 0.42471988795518206, 'overall_recall': 0.5051009785550697, 'overall_f1': 0.461436043747028, 'overall_accuracy': 0.7831572254431979}
	Data split: 21k
			------------EPOCH 1---------------
Loss:  tensor(3.9919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4535, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8992, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5801, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0021, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.025, 'recall': 0.001128668171557562, 'f1': 0.002159827213822894, 'number': 1772}, 'P': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3031}, 'overall_precision': 0.00038632412594166504, 'overall_recall': 0.00041640641265875496, 'overall_f1': 0.0004008016032064128, 'overall_accuracy': 0.3304972015159501}
			------------EPOCH 2---------------
Loss:  tensor(3.0496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9574, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4846, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3772, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7647, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.14322438486962907, 'recall': 0.2200902934537246, 'f1': 0.1735261401557286, 'number': 1772}, 'P': {'precision': 0.019966722129783693, 'recall': 0.01979544704717915, 'f1': 0.019880715705765405, 'number': 3031}, 'overall_precision': 0.07856145251396648, 'overall_recall': 0.09369144284821987, 'overall_f1': 0.08546196942360651, 'overall_accuracy': 0.4674681458056204}
			------------EPOCH 3---------------
Loss:  tensor(2.6733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3632, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4498, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.21095890410958903, 'recall': 0.2172686230248307, 'f1': 0.21406727828746178, 'number': 1772}, 'P': {'precision': 0.15886034966544355, 'recall': 0.24282415044539757, 'f1': 0.19206680584551147, 'number': 3031}, 'overall_precision': 0.17358315267884794, 'overall_recall': 0.23339579429523213, 'overall_f1': 0.19909421898588045, 'overall_accuracy': 0.6473993758836768}
			------------EPOCH 4---------------
Loss:  tensor(2.2513, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1651, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7519, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3294, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22569879015435962, 'recall': 0.30530474040632055, 'f1': 0.2595346605900695, 'number': 1772}, 'P': {'precision': 0.19479991874873046, 'recall': 0.3163972286374134, 'f1': 0.24113653507669094, 'number': 3031}, 'overall_precision': 0.20491803278688525, 'overall_recall': 0.3123048094940662, 'overall_f1': 0.24746349913387772, 'overall_accuracy': 0.7218164629504137}
			------------EPOCH 5---------------
Loss:  tensor(1.9272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8613, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2052, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.22245875465673232, 'recall': 0.23589164785553046, 'f1': 0.22897836209257738, 'number': 1772}, 'P': {'precision': 0.1903824060397177, 'recall': 0.38271197624546355, 'f1': 0.2542744410346339, 'number': 3031}, 'overall_precision': 0.19794279979929755, 'overall_recall': 0.32854465958775764, 'overall_f1': 0.2470450097847358, 'overall_accuracy': 0.7550636247270537}
			------------EPOCH 6---------------
Loss:  tensor(1.6542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3352, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7174, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0540, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.2738048202291584, 'recall': 0.39108352144469527, 'f1': 0.3221008598652103, 'number': 1772}, 'P': {'precision': 0.21018099547511312, 'recall': 0.30649950511382384, 'f1': 0.24936250167762716, 'number': 3031}, 'overall_precision': 0.23334771975255358, 'overall_recall': 0.33770560066625027, 'overall_f1': 0.27599115194827295, 'overall_accuracy': 0.7378376795589355}
			------------EPOCH 7---------------
Loss:  tensor(1.3697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6515, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7662, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5926, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8915, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.33317025440313114, 'recall': 0.3843115124153499, 'f1': 0.3569182389937108, 'number': 1772}, 'P': {'precision': 0.3228033472803347, 'recall': 0.5090729132299571, 'f1': 0.3950838561003712, 'number': 3031}, 'overall_precision': 0.32590855803048063, 'overall_recall': 0.4630439308765355, 'overall_f1': 0.3825578395114819, 'overall_accuracy': 0.7891725020706272}
			------------EPOCH 8---------------
Loss:  tensor(1.0999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4734, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7416, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.36333802156586964, 'recall': 0.4373589164785553, 'f1': 0.39692701664532654, 'number': 1772}, 'P': {'precision': 0.35796269727403157, 'recall': 0.49389640382711975, 'f1': 0.4150838763343962, 'number': 3031}, 'overall_precision': 0.359778305621536, 'overall_recall': 0.47303768478034564, 'overall_f1': 0.40870660190681773, 'overall_accuracy': 0.7980908398798617}
			------------EPOCH 9---------------
Loss:  tensor(0.7310, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0425, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3775, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3733, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6685, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.29116068907088394, 'recall': 0.5818284424379232, 'f1': 0.38810464897421415, 'number': 1772}, 'P': {'precision': 0.2714138286893705, 'recall': 0.2603101286704058, 'f1': 0.2657460424385315, 'number': 3031}, 'overall_precision': 0.28225806451612906, 'overall_recall': 0.378929835519467, 'overall_f1': 0.3235267976179896, 'overall_accuracy': 0.7122957608613809}
			------------EPOCH 10---------------
Loss:  tensor(0.8676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0447, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4191, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7324, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3440797186400938, 'recall': 0.3312641083521445, 'f1': 0.3375503162737205, 'number': 1772}, 'P': {'precision': 0.4299022949329698, 'recall': 0.6242164302210491, 'f1': 0.5091496232508074, 'number': 3031}, 'overall_precision': 0.4059276240379892, 'overall_recall': 0.5161357484905268, 'overall_f1': 0.45444546287809356, 'overall_accuracy': 0.7964008734282058}
			------------EPOCH 11---------------
Loss:  tensor(0.5429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1966, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3413, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6270, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3528064146620848, 'recall': 0.5214446952595937, 'f1': 0.42086085174219995, 'number': 1772}, 'P': {'precision': 0.43492063492063493, 'recall': 0.49719564500164964, 'f1': 0.4639778325123153, 'number': 3031}, 'overall_precision': 0.3995726495726496, 'overall_recall': 0.5061419945867166, 'overall_f1': 0.44658767337191146, 'overall_accuracy': 0.7918747751591664}
			------------EPOCH 12---------------
Loss:  tensor(0.2828, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0218, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1346, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1636, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1815, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4476, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3571104043616538, 'recall': 0.4435665914221219, 'f1': 0.39567077774981124, 'number': 1772}, 'P': {'precision': 0.4255209673269874, 'recall': 0.5456944902672385, 'f1': 0.47817288233593525, 'number': 3031}, 'overall_precision': 0.4007884362680683, 'overall_recall': 0.508015823443681, 'overall_f1': 0.4480763933523092, 'overall_accuracy': 0.7943093307900175}
			------------EPOCH 13---------------
Loss:  tensor(0.1978, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0989, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4468, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.38557435440783616, 'recall': 0.4887133182844244, 'f1': 0.4310602289696366, 'number': 1772}, 'P': {'precision': 0.515979081929111, 'recall': 0.5859452325965028, 'f1': 0.5487409238374787, 'number': 3031}, 'overall_precision': 0.46448663853727146, 'overall_recall': 0.5500728711222153, 'overall_f1': 0.5036698122199981, 'overall_accuracy': 0.8020396723807611}
			------------EPOCH 14---------------
Loss:  tensor(0.1279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0748, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0908, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1319, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3333, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3638104356151269, 'recall': 0.4288939051918736, 'f1': 0.3936803936803937, 'number': 1772}, 'P': {'precision': 0.5120746432491767, 'recall': 0.6156384031672715, 'f1': 0.5591011235955057, 'number': 3031}, 'overall_precision': 0.4580498866213152, 'overall_recall': 0.5467416198209453, 'overall_f1': 0.49848139711465445, 'overall_accuracy': 0.803060345188197}
			------------EPOCH 15---------------
Loss:  tensor(0.0940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0739, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1215, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3236, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.385, 'recall': 0.47799097065462753, 'f1': 0.42648539778449146, 'number': 1772}, 'P': {'precision': 0.5314904531205472, 'recall': 0.6153084790498186, 'f1': 0.570336391437309, 'number': 3031}, 'overall_precision': 0.4750394114555964, 'overall_recall': 0.5646470955652717, 'overall_f1': 0.5159817351598174, 'overall_accuracy': 0.8067247278903028}
			------------EPOCH 16---------------
Loss:  tensor(0.0620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0462, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1927, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3161, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3901192504258944, 'recall': 0.5169300225733634, 'f1': 0.4446601941747573, 'number': 1772}, 'P': {'precision': 0.5577797998180164, 'recall': 0.6067304519960409, 'f1': 0.5812262958280657, 'number': 3031}, 'overall_precision': 0.48804251550044286, 'overall_recall': 0.5735998334374349, 'overall_f1': 0.5273736600306279, 'overall_accuracy': 0.8044240309882957}
			------------EPOCH 17---------------
Loss:  tensor(0.0474, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0721, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1704, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2824, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.38016528925619836, 'recall': 0.4672686230248307, 'f1': 0.4192405063291139, 'number': 1772}, 'P': {'precision': 0.5443993035403366, 'recall': 0.6189376443418014, 'f1': 0.5792805311100818, 'number': 3031}, 'overall_precision': 0.48079658605974396, 'overall_recall': 0.5629814699146367, 'overall_f1': 0.5186534957322335, 'overall_accuracy': 0.8050514937797522}
			------------EPOCH 18---------------
Loss:  tensor(0.0341, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0110, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1545, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2674, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.38029465930018413, 'recall': 0.46613995485327314, 'f1': 0.4188640973630831, 'number': 1772}, 'P': {'precision': 0.5538461538461539, 'recall': 0.6176179478719894, 'f1': 0.5839962564342537, 'number': 3031}, 'overall_precision': 0.48595100864553314, 'overall_recall': 0.5617322506766604, 'overall_f1': 0.5211009174311926, 'overall_accuracy': 0.804005722460658}
			------------EPOCH 19---------------
Loss:  tensor(0.0267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0140, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2520, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.38977635782747605, 'recall': 0.481941309255079, 'f1': 0.4309866262932122, 'number': 1772}, 'P': {'precision': 0.56006006006006, 'recall': 0.6153084790498186, 'f1': 0.5863857883980506, 'number': 3031}, 'overall_precision': 0.49248324578880637, 'overall_recall': 0.5661045180095774, 'overall_f1': 0.5267338240991863, 'overall_accuracy': 0.8058546461528164}
			------------EPOCH 20---------------
Loss:  tensor(0.0208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2405, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.37943421643466546, 'recall': 0.47686230248307, 'f1': 0.4226056514128532, 'number': 1772}, 'P': {'precision': 0.5506776664702416, 'recall': 0.6166281755196305, 'f1': 0.5817898832684826, 'number': 3031}, 'overall_precision': 0.4828322362568938, 'overall_recall': 0.5650635019779304, 'overall_f1': 0.5207214121258634, 'overall_accuracy': 0.8067414602314082}
			------------EPOCH 21---------------
Loss:  tensor(0.0154, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0317, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2216, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.38708220415537486, 'recall': 0.48363431151241537, 'f1': 0.4300050175614651, 'number': 1772}, 'P': {'precision': 0.5572541966426858, 'recall': 0.6133289343451006, 'f1': 0.5839484843725459, 'number': 3031}, 'overall_precision': 0.48936936936936937, 'overall_recall': 0.5654799083905893, 'overall_f1': 0.5246788370520622, 'overall_accuracy': 0.8061558282927156}
			------------EPOCH 22---------------
Loss:  tensor(0.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2141, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.3886058360352015, 'recall': 0.4734762979683973, 'f1': 0.4268633935385398, 'number': 1772}, 'P': {'precision': 0.556935817805383, 'recall': 0.6212471131639723, 'f1': 0.5873362445414847, 'number': 3031}, 'overall_precision': 0.49133574007220215, 'overall_recall': 0.5667291276285655, 'overall_f1': 0.5263463211834092, 'overall_accuracy': 0.80613909595161}
			------------EPOCH 23---------------
Loss:  tensor(0.0096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2351, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.35057699960206923, 'recall': 0.4971783295711061, 'f1': 0.4112018669778296, 'number': 1772}, 'P': {'precision': 0.5347692307692308, 'recall': 0.5734081161332893, 'f1': 0.5534150612959721, 'number': 3031}, 'overall_precision': 0.45445080687142114, 'overall_recall': 0.5452841973766396, 'overall_f1': 0.4957410562180579, 'overall_accuracy': 0.7996887784554376}
			------------EPOCH 24---------------
Loss:  tensor(0.0137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3555, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6328, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.36119631901840493, 'recall': 0.5316027088036117, 'f1': 0.43013698630136993, 'number': 1772}, 'P': {'precision': 0.5406516925023727, 'recall': 0.5638403167271527, 'f1': 0.5520025839793281, 'number': 3031}, 'overall_precision': 0.4595250476685734, 'overall_recall': 0.5519466999791797, 'overall_f1': 0.5015134317063943, 'overall_accuracy': 0.7964008734282058}
			------------EPOCH 25---------------
Loss:  tensor(0.0240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1907, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2979, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.4325505188421628, 'recall': 0.4469525959367946, 'f1': 0.43963363863447125, 'number': 1772}, 'P': {'precision': 0.5397970085470085, 'recall': 0.6667766413724844, 'f1': 0.5966051660516605, 'number': 3031}, 'overall_precision': 0.5045739910313901, 'overall_recall': 0.5856756194045388, 'overall_f1': 0.5421083060319908, 'overall_accuracy': 0.8033196964753323}
			------------EPOCH 26---------------
Loss:  tensor(0.0395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0042, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2682, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.380440097799511, 'recall': 0.43905191873589167, 'f1': 0.40764998690070736, 'number': 1772}, 'P': {'precision': 0.46580218662598527, 'recall': 0.60442098317387, 'f1': 0.5261344055140723, 'number': 3031}, 'overall_precision': 0.43660086985613916, 'overall_recall': 0.5434103685196752, 'overall_f1': 0.4841851405249976, 'overall_accuracy': 0.8071932334412569}
			------------EPOCH 27---------------
Loss:  tensor(0.0240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0103, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2207, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.36131231359181937, 'recall': 0.4785553047404063, 'f1': 0.411750424860403, 'number': 1772}, 'P': {'precision': 0.5069301091123563, 'recall': 0.5671395579016826, 'f1': 0.5353472438492682, 'number': 3031}, 'overall_precision': 0.4473684210526316, 'overall_recall': 0.534457630647512, 'overall_f1': 0.48705056446257466, 'overall_accuracy': 0.799437793338855}
			------------EPOCH 28---------------
Loss:  tensor(0.0158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2014, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.375, 'recall': 0.5028216704288939, 'f1': 0.4296046287367406, 'number': 1772}, 'P': {'precision': 0.5629722921914357, 'recall': 0.5899043220059387, 'f1': 0.5761237312711456, 'number': 3031}, 'overall_precision': 0.482528818443804, 'overall_recall': 0.5577763897564022, 'overall_f1': 0.5174311926605504, 'overall_accuracy': 0.8040810179956328}
			------------EPOCH 29---------------
Loss:  tensor(0.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0931, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1800, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.38849241748438895, 'recall': 0.4915349887133183, 'f1': 0.4339810662680618, 'number': 1772}, 'P': {'precision': 0.5702075702075702, 'recall': 0.6162982514021775, 'f1': 0.5923576977960995, 'number': 3031}, 'overall_precision': 0.49637549836897427, 'overall_recall': 0.5702685821361649, 'overall_f1': 0.5307625230113361, 'overall_accuracy': 0.8101130269641676}
			------------EPOCH 30---------------
Loss:  tensor(0.0076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0005, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1814, device='cuda:0', grad_fn=<DivBackward0>)
				 {'C': {'precision': 0.38714028776978415, 'recall': 0.48589164785553046, 'f1': 0.4309309309309309, 'number': 1772}, 'P': {'precision': 0.5632081097197377, 'recall': 0.6232266578686902, 'f1': 0.5916992952231794, 'number': 3031}, 'overall_precision': 0.49300824668339904, 'overall_recall': 0.5725588174057881, 'overall_f1': 0.5298140834216357, 'overall_accuracy': 0.810782320608388}
