Tokenizer: bert-base-cased Model: bert-base-cased
	Data split: 1k
			------------EPOCH 1---------------
Loss:  tensor(0.3767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4850, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.5227272727272727, 'B-C': 0.010169491525423728, 'I-C': 0.05384615384615385, 'B-P': 0.011235955056179775, 'I-P': 0.4397924751138856, 'B-MC': 0.09090909090909091, 'I-MC': 0.05555555555555555}, 'recall': {'O': 0.0018769892005114116, 'B-C': 0.002540220152413209, 'I-C': 0.0012338425381903642, 'B-P': 0.0003299241174529858, 'I-P': 0.9940509104776433, 'B-MC': 0.001692047377326565, 'I-MC': 0.00047058823529411766}, 'f1': {'O': 0.0037405469872333506, 'B-C': 0.004065040650406504, 'I-C': 0.0024124066628374496, 'B-P': 0.000641025641025641, 'I-P': 0.6097961809515454, 'B-MC': 0.0033222591362126247, 'I-MC': 0.0009332711152589828}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.4369818203113889, 'recall': 0.4369818203113889, 'f1': 0.4369818203113889, 'support': None}, 'macro_avg': {'precision': 0.16917657067622316, 'recall': 0.14317064601411886, 'f1': 0.08927296159207429, 'support': None}, 'weighted_avg': {'precision': 0.36618202287940865, 'recall': 0.4369818203113889, 'f1': 0.2691896204315125, 'support': None}}
			------------EPOCH 2---------------
Loss:  tensor(0.3299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4144, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8428571428571429, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.0, 'I-P': 0.43908708065069785, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.0016049617801474389, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.0, 'I-P': 1.0, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.0032038228666069345, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.0, 'I-P': 0.610230036186775, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.4392574187017377, 'recall': 0.4392574187017377, 'f1': 0.4392574187017377, 'support': None}, 'macro_avg': {'precision': 0.18313488907254866, 'recall': 0.14308642311144965, 'f1': 0.08763340843619741, 'support': None}, 'weighted_avg': {'precision': 0.45187522168927435, 'recall': 0.4392574187017377, 'f1': 0.26873219034890905, 'support': None}}
			------------EPOCH 3---------------
Loss:  tensor(0.3023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3597, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8354037267080745, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.0, 'I-P': 0.4400500142658141, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.007317537607790865, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.0, 'I-P': 0.9998855944322623, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.014507995577488336, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.0, 'I-P': 0.611137980665575, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.44096411749449926, 'recall': 0.44096411749449926, 'f1': 0.44096411749449926, 'support': None}, 'macro_avg': {'precision': 0.1822076772819841, 'recall': 0.1438861617200076, 'f1': 0.08937799660615191, 'support': None}, 'weighted_avg': {'precision': 0.4500054329550665, 'recall': 0.44096411749449926, 'f1': 0.2726071482354084, 'support': None}}
			------------EPOCH 4---------------
Loss:  tensor(0.2798, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2763, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3194, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8521485797523671, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.03333333333333333, 'I-P': 0.44920758861536086, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.06365441636516961, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.0026393929396238865, 'I-P': 0.9982267137000668, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.11846001974333663, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.004891470498318556, 'I-P': 0.6195942907188676, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.457629529235583, 'recall': 0.457629529235583, 'f1': 0.457629529235583, 'support': None}, 'macro_avg': {'precision': 0.19066992881443734, 'recall': 0.15207436042926575, 'f1': 0.10613511156578896, 'support': None}, 'weighted_avg': {'precision': 0.46001856669546887, 'recall': 0.457629529235583, 'f1': 0.3084118281723784, 'support': None}}
			------------EPOCH 5---------------
Loss:  tensor(0.2578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2867, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8253125908694388, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.10835913312693499, 'I-P': 0.4939983206747834, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.3088327303392182, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.03464203233256351, 'I-P': 0.9871865764133855, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.4494724548171903, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.052500000000000005, 'I-P': 0.658484314685626, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.5290013302211178, 'recall': 0.5290013302211178, 'f1': 0.5290013302211178, 'support': None}, 'macro_avg': {'precision': 0.20395286352445102, 'recall': 0.19009447701216672, 'f1': 0.16577953850040233, 'support': None}, 'weighted_avg': {'precision': 0.4733202370407867, 'recall': 0.5290013302211178, 'f1': 0.4284850897708706, 'support': None}}
			------------EPOCH 6---------------
Loss:  tensor(0.2314, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2578, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7905222506947702, 'B-C': 0.25, 'I-C': 0.25849056603773585, 'B-P': 0.20630081300813008, 'I-P': 0.5610304984549241, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.5958216588232094, 'B-C': 0.001693480101608806, 'I-C': 0.008049353701527614, 'B-P': 0.13394919168591224, 'I-P': 0.9554580989608161, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.6794999069305702, 'B-C': 0.00336417157275021, 'I-C': 0.015612535612535613, 'B-P': 0.16243248649729947, 'I-P': 0.7069504306544114, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6070242367960913, 'recall': 0.6070242367960913, 'f1': 0.6070242367960913, 'support': None}, 'macro_avg': {'precision': 0.2951920183136515, 'recall': 0.24213882618186774, 'f1': 0.22397993303822386, 'support': None}, 'weighted_avg': {'precision': 0.5337925536685562, 'recall': 0.6070242367960913, 'f1': 0.5255389296628549, 'support': None}}
			------------EPOCH 7---------------
Loss:  tensor(0.2020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1832, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2246, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.786985226633508, 'B-C': 0.08333333333333333, 'I-C': 0.1895910780669145, 'B-P': 0.2587909917028842, 'I-P': 0.5987741230731884, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.7231032888115122, 'B-C': 0.001693480101608806, 'I-C': 0.008989424206815512, 'B-P': 0.2161002969317057, 'I-P': 0.9406616455334159, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.7536930448836089, 'B-C': 0.0033195020746887966, 'I-C': 0.017164974476917037, 'B-P': 0.23552678892484716, 'I-P': 0.7317536248006823, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6418944356599654, 'recall': 0.6418944356599654, 'f1': 0.6418944356599654, 'support': None}, 'macro_avg': {'precision': 0.27392496468711836, 'recall': 0.2700783050835797, 'f1': 0.24877970502296343, 'support': None}, 'weighted_avg': {'precision': 0.5391388291717052, 'recall': 0.6418944356599654, 'f1': 0.5613138131367006, 'support': None}}
			------------EPOCH 8---------------
Loss:  tensor(0.1730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1556, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1939, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7772621194441498, 'B-C': 0.125, 'I-C': 0.21976744186046512, 'B-P': 0.28224426958604176, 'I-P': 0.6232850365431466, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.7972851663447675, 'B-C': 0.005080440304826418, 'I-C': 0.011104582843713278, 'B-P': 0.2721873968987133, 'I-P': 0.9268757746210315, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.7871463293450965, 'B-C': 0.009764035801464606, 'I-C': 0.021140939597315434, 'B-P': 0.27712462210278804, 'I-P': 0.7453520910798482, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6604171372637603, 'recall': 0.6604171372637603, 'f1': 0.6604171372637603, 'support': None}, 'macro_avg': {'precision': 0.2896512667762576, 'recall': 0.28750476585900747, 'f1': 0.2629325739895018, 'support': None}, 'weighted_avg': {'precision': 0.5522062909919109, 'recall': 0.6604171372637603, 'f1': 0.5792534989630895, 'support': None}}
			------------EPOCH 9---------------
Loss:  tensor(0.1450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1299, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1665, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7673054070112894, 'B-C': 0.12179487179487179, 'I-C': 0.2738154613466334, 'B-P': 0.3035230352303523, 'I-P': 0.6451958986894819, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.8430945839340606, 'B-C': 0.016088060965283656, 'I-C': 0.03225616921269095, 'B-P': 0.3325635103926097, 'I-P': 0.9058823529411765, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.8034165878190089, 'B-C': 0.028421839940164548, 'I-C': 0.05771353482260183, 'B-P': 0.31738035264483627, 'I-P': 0.7536326142131978, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6699462055233458, 'recall': 0.6699462055233458, 'f1': 0.6699462055233458, 'support': None}, 'macro_avg': {'precision': 0.30166209629608975, 'recall': 0.3042692396351173, 'f1': 0.28008070420568704, 'support': None}, 'weighted_avg': {'precision': 0.5669617430866528, 'recall': 0.6699462055233458, 'f1': 0.5943033911581479, 'support': None}}
			------------EPOCH 10---------------
Loss:  tensor(0.1182, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1415, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7746923475301487, 'B-C': 0.13615023474178403, 'I-C': 0.2808090310442145, 'B-P': 0.3245883337984929, 'I-P': 0.6511822241705252, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.8545197355893474, 'B-C': 0.024555461473327687, 'I-C': 0.035076380728554644, 'B-P': 0.3837017485978225, 'I-P': 0.9063781104013728, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.812650368645712, 'B-C': 0.04160688665710187, 'I-C': 0.06236289564399875, 'B-P': 0.3516782582400968, 'I-P': 0.7578740942101193, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.67545951191761, 'recall': 0.67545951191761, 'f1': 0.67545951191761, 'support': None}, 'macro_avg': {'precision': 0.30963173875502364, 'recall': 0.31489020525577505, 'f1': 0.2894532147710041, 'support': None}, 'weighted_avg': {'precision': 0.5735320090482209, 'recall': 0.67545951191761, 'f1': 0.6006662658464754, 'support': None}}
			------------EPOCH 11---------------
Loss:  tensor(0.0935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0864, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1182, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7939757200182862, 'B-C': 0.1524390243902439, 'I-C': 0.3220883534136546, 'B-P': 0.3435155412647374, 'I-P': 0.6476462577768284, 'B-MC': 0.05555555555555555, 'I-MC': 0.11702127659574468}, 'recall': {'O': 0.8504121215418514, 'B-C': 0.021168501270110076, 'I-C': 0.023560517038777908, 'B-P': 0.42296271857472784, 'I-P': 0.9249690151587378, 'B-MC': 0.001692047377326565, 'I-MC': 0.0012941176470588236}, 'f1': {'O': 0.8212254547842648, 'B-C': 0.03717472118959107, 'I-C': 0.04390911579523679, 'B-P': 0.37912169155700126, 'I-P': 0.7618554029541333, 'B-MC': 0.003284072249589491, 'I-MC': 0.002559925529439144}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6817759706849383, 'recall': 0.6817759706849383, 'f1': 0.6817759706849383, 'support': None}, 'macro_avg': {'precision': 0.3474631041450072, 'recall': 0.32086557694408435, 'f1': 0.2927329120084652, 'support': None}, 'weighted_avg': {'precision': 0.593026240373247, 'recall': 0.6817759706849383, 'f1': 0.6032730981487566, 'support': None}}
			------------EPOCH 12---------------
Loss:  tensor(0.0727, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0995, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7954528211223792, 'B-C': 0.1443850267379679, 'I-C': 0.30201863354037267, 'B-P': 0.35604508196721313, 'I-P': 0.6510587413339066, 'B-MC': 0.03333333333333333, 'I-MC': 0.1456953642384106}, 'recall': {'O': 0.8556078452708032, 'B-C': 0.02286198137171888, 'I-C': 0.022855464159811986, 'B-P': 0.4585945232596503, 'I-P': 0.923958432643722, 'B-MC': 0.001692047377326565, 'I-MC': 0.0025882352941176473}, 'f1': {'O': 0.8244344840240098, 'B-C': 0.039473684210526314, 'I-C': 0.04249508411623334, 'B-P': 0.4008651766402307, 'I-P': 0.7638662284331575, 'B-MC': 0.00322061191626409, 'I-MC': 0.00508611721188302}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6838424148114683, 'recall': 0.6838424148114683, 'f1': 0.6838424148114683, 'support': None}, 'macro_avg': {'precision': 0.34685557175336906, 'recall': 0.3268797899110215, 'f1': 0.29706305522175785, 'support': None}, 'weighted_avg': {'precision': 0.5942873775020314, 'recall': 0.6838424148114683, 'f1': 0.6056943745738235, 'support': None}}
			------------EPOCH 13---------------
Loss:  tensor(0.0563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0544, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0840, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7888204899997527, 'B-C': 0.15671641791044777, 'I-C': 0.2981029810298103, 'B-P': 0.36945932781295665, 'I-P': 0.6591234840132304, 'B-MC': 0.06521739130434782, 'I-MC': 0.2549019607843137}, 'recall': {'O': 0.8679578901553276, 'B-C': 0.03556308213378493, 'I-C': 0.03231492361927144, 'B-P': 0.5004948861761794, 'I-P': 0.9119267804366479, 'B-MC': 0.005076142131979695, 'I-MC': 0.007647058823529412}, 'f1': {'O': 0.8264991581401372, 'B-C': 0.05797101449275363, 'I-C': 0.058309037900874626, 'B-P': 0.42510858904301524, 'I-P': 0.7651853925842965, 'B-MC': 0.009419152276295131, 'I-MC': 0.01484865790976585}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.685273029975989, 'recall': 0.685273029975989, 'f1': 0.685273029975989, 'support': None}, 'macro_avg': {'precision': 0.37033457897926564, 'recall': 0.3372829662109601, 'f1': 0.3081915717638769, 'support': None}, 'weighted_avg': {'precision': 0.6036141634763363, 'recall': 0.685273029975989, 'f1': 0.6106823574553416, 'support': None}}
			------------EPOCH 14---------------
Loss:  tensor(0.0430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0420, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0695, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7763208453410183, 'B-C': 0.16758241758241757, 'I-C': 0.31605611847233045, 'B-P': 0.37146859677795935, 'I-P': 0.6684767157559561, 'B-MC': 0.06, 'I-MC': 0.32014388489208634}, 'recall': {'O': 0.8793558390685781, 'B-C': 0.05165114309906858, 'I-C': 0.047649823736780256, 'B-P': 0.5249092708677005, 'I-P': 0.8966727047382973, 'B-MC': 0.005076142131979695, 'I-MC': 0.010470588235294117}, 'f1': {'O': 0.8246323388732287, 'B-C': 0.07896440129449837, 'I-C': 0.0828142550801593, 'B-P': 0.43505605687722176, 'I-P': 0.7659394265145407, 'B-MC': 0.009360374414976598, 'I-MC': 0.020277967646388697}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6852479314643308, 'recall': 0.6852479314643308, 'f1': 0.6852479314643308, 'support': None}, 'macro_avg': {'precision': 0.38286408268882405, 'recall': 0.34511221598252834, 'f1': 0.3167206886715735, 'support': None}, 'weighted_avg': {'precision': 0.6112021874472549, 'recall': 0.6852479314643308, 'f1': 0.6147738860605826, 'support': None}}
			------------EPOCH 15---------------
Loss:  tensor(0.0327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0569, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7660359619226701, 'B-C': 0.15982721382289417, 'I-C': 0.3083538083538084, 'B-P': 0.3600364132908512, 'I-P': 0.6733404351569454, 'B-MC': 0.05660377358490566, 'I-MC': 0.3024054982817869}, 'recall': {'O': 0.8865645657082234, 'B-C': 0.06265876375952582, 'I-C': 0.05898942420681551, 'B-P': 0.5219399538106235, 'I-P': 0.8798169510916198, 'B-MC': 0.005076142131979695, 'I-MC': 0.010352941176470589}, 'f1': {'O': 0.8219050261014299, 'B-C': 0.0900243309002433, 'I-C': 0.09903333990925231, 'B-P': 0.42612794612794613, 'I-P': 0.762854214198327, 'B-MC': 0.009316770186335402, 'I-MC': 0.020020475486292804}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6817090413205164, 'recall': 0.6817090413205164, 'f1': 0.6817090413205164, 'support': None}, 'macro_avg': {'precision': 0.375229014916266, 'recall': 0.34648553455503694, 'f1': 0.318468871844261, 'support': None}, 'weighted_avg': {'precision': 0.6074316258817557, 'recall': 0.6817090413205164, 'f1': 0.6147552490669377, 'support': None}}
			------------EPOCH 16---------------
Loss:  tensor(0.0252, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0452, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7665828614394136, 'B-C': 0.15737051792828685, 'I-C': 0.30953791469194314, 'B-P': 0.3560419924056288, 'I-P': 0.6741159747358548, 'B-MC': 0.08620689655172414, 'I-MC': 0.3018867924528302}, 'recall': {'O': 0.8874894589374609, 'B-C': 0.06689246401354784, 'I-C': 0.06139835487661575, 'B-P': 0.5258990432200594, 'I-P': 0.8771284202497854, 'B-MC': 0.008460236886632826, 'I-MC': 0.011294117647058824}, 'f1': {'O': 0.8226172465960666, 'B-C': 0.09387997623291741, 'I-C': 0.10247107275936458, 'B-P': 0.4246137453383058, 'I-P': 0.7623380066951709, 'B-MC': 0.015408320493066254, 'I-MC': 0.021773644817418916}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.681382760668959, 'recall': 0.681382760668959, 'f1': 0.681382760668959, 'support': None}, 'macro_avg': {'precision': 0.3788204214579545, 'recall': 0.34836601369016584, 'f1': 0.3204431447046158, 'support': None}, 'weighted_avg': {'precision': 0.608092630615323, 'recall': 0.681382760668959, 'f1': 0.6153917947445522, 'support': None}}
			------------EPOCH 17---------------
Loss:  tensor(0.0194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0200, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0348, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7743170308376328, 'B-C': 0.14763779527559054, 'I-C': 0.30599565082323704, 'B-P': 0.35938529088913285, 'I-P': 0.6734050283389043, 'B-MC': 0.10344827586206896, 'I-MC': 0.3125}, 'recall': {'O': 0.8859116998993498, 'B-C': 0.06350550381033022, 'I-C': 0.057873090481786134, 'B-P': 0.5400857802705378, 'I-P': 0.8835351320430928, 'B-MC': 0.01015228426395939, 'I-MC': 0.011764705882352941}, 'f1': {'O': 0.8263638670388226, 'B-C': 0.08880994671403196, 'I-C': 0.09733682494194379, 'B-P': 0.43158449775902985, 'I-P': 0.7642901323656757, 'B-MC': 0.018489984591679505, 'I-MC': 0.022675736961451247}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6835746973537803, 'recall': 0.6835746973537803, 'f1': 0.6835746973537803, 'support': None}, 'macro_avg': {'precision': 0.38238415314665236, 'recall': 0.3504040280930584, 'f1': 0.32136442719609065, 'support': None}, 'weighted_avg': {'precision': 0.6104835315514014, 'recall': 0.6835746973537803, 'f1': 0.6168755647038527, 'support': None}}
			------------EPOCH 18---------------
Loss:  tensor(0.0149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0268, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7860474154683249, 'B-C': 0.16299559471365638, 'I-C': 0.3150384193194292, 'B-P': 0.36402846668104377, 'I-P': 0.6684479785672552, 'B-MC': 0.1206896551724138, 'I-MC': 0.3366013071895425}, 'recall': {'O': 0.8802807322978157, 'B-C': 0.06265876375952582, 'I-C': 0.050587544065804936, 'B-P': 0.55691191026064, 'I-P': 0.8944036609781676, 'B-MC': 0.011844331641285956, 'I-MC': 0.01211764705882353}, 'f1': {'O': 0.8304995572893275, 'B-C': 0.09051987767584097, 'I-C': 0.08717663139776237, 'B-P': 0.44027125717266563, 'I-P': 0.7650915852484953, 'B-MC': 0.021571648690292756, 'I-MC': 0.023393141040199867}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6860259853257369, 'recall': 0.6860259853257369, 'f1': 0.6860259853257369, 'support': None}, 'macro_avg': {'precision': 0.393406976730238, 'recall': 0.3526863700088662, 'f1': 0.3226462426449407, 'support': None}, 'weighted_avg': {'precision': 0.6152724773903618, 'recall': 0.6860259853257369, 'f1': 0.6173558331409399, 'support': None}}
			------------EPOCH 19---------------
Loss:  tensor(0.0115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0272, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7782241672047253, 'B-C': 0.13272010512483573, 'I-C': 0.2819548872180451, 'B-P': 0.3538862353452019, 'I-P': 0.6773977396250577, 'B-MC': 0.140625, 'I-MC': 0.35119047619047616}, 'recall': {'O': 0.8852588340904763, 'B-C': 0.0855207451312447, 'I-C': 0.07931844888366628, 'B-P': 0.5377763114483669, 'I-P': 0.8674230145867099, 'B-MC': 0.015228426395939087, 'I-MC': 0.01388235294117647}, 'f1': {'O': 0.8282979968948052, 'B-C': 0.10401647785787847, 'I-C': 0.12380777696258255, 'B-P': 0.42686918947230584, 'I-P': 0.7607230648316917, 'B-MC': 0.02748091603053435, 'I-MC': 0.026708918062471707}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6796927942173029, 'recall': 0.6796927942173029, 'f1': 0.6796927942173029, 'support': None}, 'macro_avg': {'precision': 0.38799980152976316, 'recall': 0.35491544763965427, 'f1': 0.32827204858746706, 'support': None}, 'weighted_avg': {'precision': 0.6126621597420121, 'recall': 0.6796927942173029, 'f1': 0.6200365029523959, 'support': None}}
			------------EPOCH 20---------------
Loss:  tensor(0.0091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0546, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7743573920679753, 'B-C': 0.11974977658623771, 'I-C': 0.2774321266968326, 'B-P': 0.35055679287305125, 'I-P': 0.6863443385223085, 'B-MC': 0.171875, 'I-MC': 0.3620689655172414}, 'recall': {'O': 0.8875166616794973, 'B-C': 0.11346316680779, 'I-C': 0.11527614571092831, 'B-P': 0.5193005608709996, 'I-P': 0.8415292210887596, 'B-MC': 0.018612521150592216, 'I-MC': 0.014823529411764706}, 'f1': {'O': 0.8270844424164069, 'B-C': 0.11652173913043479, 'I-C': 0.16287564336709281, 'B-P': 0.41856136152107437, 'I-P': 0.7560557782574433, 'B-MC': 0.03358778625954198, 'I-MC': 0.02848101265822785}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.674037262923642, 'recall': 0.674037262923642, 'f1': 0.674037262923642, 'support': None}, 'macro_avg': {'precision': 0.3917691988948067, 'recall': 0.3586459723886189, 'f1': 0.3347382519443175, 'support': None}, 'weighted_avg': {'precision': 0.6154699041842274, 'recall': 0.674037262923642, 'f1': 0.6232475012628468, 'support': None}}
			------------EPOCH 21---------------
Loss:  tensor(0.0074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0256, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8045697374031251, 'B-C': 0.138353765323993, 'I-C': 0.3020217729393468, 'B-P': 0.37143456375838924, 'I-P': 0.6658090781866245, 'B-MC': 0.13114754098360656, 'I-MC': 0.31788079470198677}, 'recall': {'O': 0.872636761785588, 'B-C': 0.06689246401354784, 'I-C': 0.05705052878965922, 'B-P': 0.5842956120092379, 'I-P': 0.8980837067403947, 'B-MC': 0.01353637901861252, 'I-MC': 0.011294117647058824}, 'f1': {'O': 0.8372220482305044, 'B-C': 0.09018264840182648, 'I-C': 0.09597232517914504, 'B-P': 0.45416078984485186, 'I-P': 0.7646972870293702, 'B-MC': 0.024539877300613498, 'I-MC': 0.021813224267211998}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6868960670632231, 'recall': 0.6868960670632231, 'f1': 0.6868960670632231, 'support': None}, 'macro_avg': {'precision': 0.39017389332815317, 'recall': 0.3576842242862999, 'f1': 0.32694117146478907, 'support': None}, 'weighted_avg': {'precision': 0.6166224490198109, 'recall': 0.6868960670632231, 'f1': 0.6207539629993074, 'support': None}}
			------------EPOCH 22---------------
Loss:  tensor(0.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0228, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.828490506661072, 'B-C': 0.14423076923076922, 'I-C': 0.2852975495915986, 'B-P': 0.39264828738512947, 'I-P': 0.6538704857792793, 'B-MC': 0.125, 'I-MC': 0.28512396694214875}, 'recall': {'O': 0.8593890264138625, 'B-C': 0.03810330228619814, 'I-C': 0.02873090481786134, 'B-P': 0.6202573408116133, 'I-P': 0.9262656115930975, 'B-MC': 0.01015228426395939, 'I-MC': 0.00811764705882353}, 'f1': {'O': 0.8436569505828314, 'B-C': 0.06028131279303417, 'I-C': 0.052204547880858335, 'B-P': 0.4808799079166134, 'I-P': 0.7665893417917278, 'B-MC': 0.018779342723004692, 'I-MC': 0.015785861358956762}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6915392917200011, 'recall': 0.6915392917200011, 'f1': 0.6915392917200011, 'support': None}, 'macro_avg': {'precision': 0.38780879508428534, 'recall': 0.3558594453207736, 'f1': 0.31973960929243234, 'support': None}, 'weighted_avg': {'precision': 0.6145958190283958, 'recall': 0.6915392917200011, 'f1': 0.6172559817281086, 'support': None}}
			------------EPOCH 23---------------
Loss:  tensor(0.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0176, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8347837622711595, 'B-C': 0.1606425702811245, 'I-C': 0.29672727272727273, 'B-P': 0.39925062447960036, 'I-P': 0.6516484540336213, 'B-MC': 0.10638297872340426, 'I-MC': 0.3090128755364807}, 'recall': {'O': 0.8558798726911673, 'B-C': 0.03386960203217612, 'I-C': 0.023971797884841363, 'B-P': 0.6327944572748267, 'I-P': 0.933530365144437, 'B-MC': 0.008460236886632826, 'I-MC': 0.008470588235294117}, 'f1': {'O': 0.8452001987884649, 'B-C': 0.055944055944055944, 'I-C': 0.044359880402283225, 'B-P': 0.48959795788130184, 'I-P': 0.7675268075500093, 'B-MC': 0.01567398119122257, 'I-MC': 0.016489178976296804}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6932627228538681, 'recall': 0.6932627228538681, 'f1': 0.6932627228538681, 'support': None}, 'macro_avg': {'precision': 0.3940640768646661, 'recall': 0.356710988592768, 'f1': 0.31925600867623355, 'support': None}, 'weighted_avg': {'precision': 0.6191201845514211, 'recall': 0.6932627228538681, 'f1': 0.6172377898138574, 'support': None}}
			------------EPOCH 24---------------
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0182, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.830946311723123, 'B-C': 0.1643835616438356, 'I-C': 0.3027754415475189, 'B-P': 0.39265942177568175, 'I-P': 0.652604597762529, 'B-MC': 0.10416666666666667, 'I-MC': 0.3037974683544304}, 'recall': {'O': 0.8601507031908816, 'B-C': 0.03048264182895851, 'I-C': 0.021151586368977675, 'B-P': 0.6318046849224679, 'I-P': 0.9321002955477167, 'B-MC': 0.008460236886632826, 'I-MC': 0.008470588235294117}, 'f1': {'O': 0.8452963349105782, 'B-C': 0.05142857142857143, 'I-C': 0.03954088637486957, 'B-P': 0.48431967627718764, 'I-P': 0.7677050042795109, 'B-MC': 0.01564945226917058, 'I-MC': 0.01648162985006295}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6934886094587924, 'recall': 0.6934886094587924, 'f1': 0.6934886094587924, 'support': None}, 'macro_avg': {'precision': 0.39304763849625507, 'recall': 0.35608867671156136, 'f1': 0.31720307934142156, 'support': None}, 'weighted_avg': {'precision': 0.6187086998532947, 'recall': 0.6934886094587924, 'f1': 0.61648023630129, 'support': None}}
			------------EPOCH 25---------------
Loss:  tensor(0.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0141, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8254541674246952, 'B-C': 0.18518518518518517, 'I-C': 0.311046511627907, 'B-P': 0.3838241226300928, 'I-P': 0.6532663316582915, 'B-MC': 0.09523809523809523, 'I-MC': 0.27184466019417475}, 'recall': {'O': 0.8639862898180136, 'B-C': 0.029635901778154106, 'I-C': 0.018860164512338424, 'B-P': 0.627845595513032, 'I-P': 0.929545237868243, 'B-MC': 0.00676818950930626, 'I-MC': 0.006588235294117647}, 'f1': {'O': 0.8442808155453361, 'B-C': 0.051094890510948905, 'I-C': 0.03556392643474407, 'B-P': 0.47640505695331076, 'I-P': 0.7672936176910365, 'B-MC': 0.01263823064770932, 'I-MC': 0.01286469101768895}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6929699068845218, 'recall': 0.6929699068845218, 'f1': 0.6929699068845218, 'support': None}, 'macro_avg': {'precision': 0.38940843913692025, 'recall': 0.35474708775617214, 'f1': 0.3143058898286821, 'support': None}, 'weighted_avg': {'precision': 0.6161527745213046, 'recall': 0.6929699068845218, 'f1': 0.6149450319944945, 'support': None}}
			------------EPOCH 26---------------
Loss:  tensor(0.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0126, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8205035878706823, 'B-C': 0.18446601941747573, 'I-C': 0.315377932232841, 'B-P': 0.37858431922999797, 'I-P': 0.6555343898188303, 'B-MC': 0.15217391304347827, 'I-MC': 0.3389121338912134}, 'recall': {'O': 0.8678218764451456, 'B-C': 0.03217612193056731, 'I-C': 0.021327849588719153, 'B-P': 0.6228967337512372, 'I-P': 0.925197826294213, 'B-MC': 0.011844331641285956, 'I-MC': 0.009529411764705882}, 'f1': {'O': 0.8434996430554454, 'B-C': 0.054794520547945195, 'I-C': 0.039953772494634304, 'B-P': 0.47094038413569467, 'I-P': 0.7673646255060729, 'B-MC': 0.021978021978021976, 'I-MC': 0.01853759011328527}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6927272879384919, 'recall': 0.6927272879384919, 'f1': 0.6927272879384919, 'support': None}, 'macro_avg': {'precision': 0.4065074707863599, 'recall': 0.3558277359165535, 'f1': 0.31672407969015703, 'support': None}, 'weighted_avg': {'precision': 0.6211530024978694, 'recall': 0.6927272879384919, 'f1': 0.6157085939890758, 'support': None}}
			------------EPOCH 27---------------
Loss:  tensor(0.0030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0098, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8130741511444958, 'B-C': 0.1605351170568562, 'I-C': 0.3099940155595452, 'B-P': 0.37206030150753766, 'I-P': 0.6592444127175883, 'B-MC': 0.18181818181818182, 'I-MC': 0.3154121863799283}, 'recall': {'O': 0.8715758548461685, 'B-C': 0.04064352243861134, 'I-C': 0.030434782608695653, 'B-P': 0.6106895414054767, 'I-P': 0.9156640289827438, 'B-MC': 0.01692047377326565, 'I-MC': 0.010352941176470589}, 'f1': {'O': 0.8413092284060025, 'B-C': 0.06486486486486485, 'I-C': 0.05542774597399819, 'B-P': 0.4624031976017986, 'I-P': 0.7665796678080278, 'B-MC': 0.030959752321981424, 'I-MC': 0.020047841439799523}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6908532657346753, 'recall': 0.6908532657346753, 'f1': 0.6908532657346753, 'support': None}, 'macro_avg': {'precision': 0.40173405231201903, 'recall': 0.3566115921759189, 'f1': 0.32022747120235323, 'support': None}, 'weighted_avg': {'precision': 0.6178028354358994, 'recall': 0.6908532657346753, 'f1': 0.6169287187485846, 'support': None}}
			------------EPOCH 28---------------
Loss:  tensor(0.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0078, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.807575567540449, 'B-C': 0.15714285714285714, 'I-C': 0.3215913800248653, 'B-P': 0.37398538961038963, 'I-P': 0.6650919002026696, 'B-MC': 0.1724137931034483, 'I-MC': 0.35}, 'recall': {'O': 0.8757650771197737, 'B-C': 0.0558848433530906, 'I-C': 0.045593419506462986, 'B-P': 0.6080501484658528, 'I-P': 0.9073124225378968, 'B-MC': 0.01692047377326565, 'I-MC': 0.012352941176470587}, 'f1': {'O': 0.8402891968783441, 'B-C': 0.08244846970643348, 'I-C': 0.07986414861318375, 'B-P': 0.46312350797838925, 'I-P': 0.7675457698201467, 'B-MC': 0.03081664098613251, 'I-MC': 0.023863636363636365}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.690861631905228, 'recall': 0.690861631905228, 'f1': 0.690861631905228, 'support': None}, 'macro_avg': {'precision': 0.406828698232097, 'recall': 0.360268475133259, 'f1': 0.3268501957637523, 'support': None}, 'weighted_avg': {'precision': 0.6227572171977145, 'recall': 0.690861631905228, 'f1': 0.6209810959129441, 'support': None}}
			------------EPOCH 29---------------
Loss:  tensor(0.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0073, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8031595969647967, 'B-C': 0.1603960396039604, 'I-C': 0.3111842105263158, 'B-P': 0.37174492515890917, 'I-P': 0.6687659574468086, 'B-MC': 0.15384615384615385, 'I-MC': 0.3025936599423631}, 'recall': {'O': 0.878186121161013, 'B-C': 0.06858594411515664, 'I-C': 0.055581668625146886, 'B-P': 0.5981524249422633, 'I-P': 0.8989989512822958, 'B-MC': 0.01692047377326565, 'I-MC': 0.012352941176470587}, 'f1': {'O': 0.8389989084671761, 'B-C': 0.09608540925266904, 'I-C': 0.09431704885343968, 'B-P': 0.4585230146686899, 'I-P': 0.7669771035829029, 'B-MC': 0.030487804878048776, 'I-MC': 0.02373685995252628}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6892553271590994, 'recall': 0.6892553271590994, 'f1': 0.6892553271590994, 'support': None}, 'macro_avg': {'precision': 0.3959557919270439, 'recall': 0.3612540750108017, 'f1': 0.3298751642364932, 'support': None}, 'weighted_avg': {'precision': 0.6180415767122687, 'recall': 0.6892553271590994, 'f1': 0.6224001787944377, 'support': None}}
			------------EPOCH 30---------------
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0068, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7994711871108036, 'B-C': 0.16117216117216118, 'I-C': 0.3053839364518976, 'B-P': 0.37064522778808495, 'I-P': 0.6708351239077496, 'B-MC': 0.14084507042253522, 'I-MC': 0.328125}, 'recall': {'O': 0.8800903131035608, 'B-C': 0.07451312447078746, 'I-C': 0.06098707403055229, 'B-P': 0.5932035631804685, 'I-P': 0.8929545237868243, 'B-MC': 0.01692047377326565, 'I-MC': 0.014823529411764706}, 'f1': {'O': 0.8378458869077677, 'B-C': 0.1019108280254777, 'I-C': 0.1016700132229786, 'B-P': 0.4562293834052271, 'I-P': 0.7661199950922252, 'B-MC': 0.030211480362537766, 'I-MC': 0.02836560108059433}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6880673309406086, 'recall': 0.6880673309406086, 'f1': 0.6880673309406086, 'support': None}, 'macro_avg': {'precision': 0.39663967240760456, 'recall': 0.36192751453674626, 'f1': 0.33176474115668686, 'support': None}, 'weighted_avg': {'precision': 0.6187202680983125, 'recall': 0.6880673309406086, 'f1': 0.6230436961688122, 'support': None}}
	Data split: 6k
			------------EPOCH 1---------------
Loss:  tensor(1.0713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7568, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7465, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9246, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.457989851848621, 'B-C': 0.015184381778741865, 'I-C': 0.1523809523809524, 'B-P': 0.12306521187515859, 'I-P': 0.6500940548580428, 'B-MC': 0.0, 'I-MC': 0.1346153846153846}, 'recall': {'O': 0.8569135768885504, 'B-C': 0.0059271803556308214, 'I-C': 0.004700352526439483, 'B-P': 0.16001319696469812, 'I-P': 0.5667079797883497, 'B-MC': 0.0, 'I-MC': 0.0008235294117647059}, 'f1': {'O': 0.5969377120009096, 'B-C': 0.008526187576126673, 'I-C': 0.009119407238529494, 'B-P': 0.13912794033275963, 'I-P': 0.6055438403471777, 'B-MC': 0.0, 'I-MC': 0.0016370439663236673}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.5170377063306812, 'recall': 0.5170377063306812, 'f1': 0.5170377063306812, 'support': None}, 'macro_avg': {'precision': 0.21904711962241447, 'recall': 0.22786940227649044, 'f1': 0.1944131616374038, 'support': None}, 'weighted_avg': {'precision': 0.4606333663099841, 'recall': 0.5170377063306812, 'f1': 0.4543053764146165, 'support': None}}
			------------EPOCH 2---------------
Loss:  tensor(0.8393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9942, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3842, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7418, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.5696412948381452, 'B-C': 0.0, 'I-C': 0.1791044776119403, 'B-P': 0.25540123456790126, 'I-P': 0.6753373489921594, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.8855852669949131, 'B-C': 0.0, 'I-C': 0.0035252643948296123, 'B-P': 0.2184097657538766, 'I-P': 0.7653351129754982, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.6933160119687789, 'B-C': 0.0, 'I-C': 0.006914433880726016, 'B-P': 0.23546149742130537, 'I-P': 0.7175251834571278, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6142024111303533, 'recall': 0.6142024111303533, 'f1': 0.6142024111303533, 'support': None}, 'macro_avg': {'precision': 0.23992633657287804, 'recall': 0.2675507728741596, 'f1': 0.2361738752468483, 'support': None}, 'weighted_avg': {'precision': 0.5034855997989558, 'recall': 0.6142024111303533, 'f1': 0.5350079530969664, 'support': None}}
			------------EPOCH 3---------------
Loss:  tensor(0.7411, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4542, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2169, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6715, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.706828729281768, 'B-C': 0.14814814814814814, 'I-C': 0.22594189741261916, 'B-P': 0.38962432915921286, 'I-P': 0.7028405536753973, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.8700525012921303, 'B-C': 0.04064352243861134, 'I-C': 0.11698002350176263, 'B-P': 0.35928736390630156, 'I-P': 0.835541996377157, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.7799929277779809, 'B-C': 0.06378737541528239, 'I-C': 0.15414989160730877, 'B-P': 0.37384140061791965, 'I-P': 0.7634678374799637, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.660358574069891, 'recall': 0.660358574069891, 'f1': 0.660358574069891, 'support': None}, 'macro_avg': {'precision': 0.31048337966816364, 'recall': 0.31750077250228037, 'f1': 0.3050342046997793, 'support': None}, 'weighted_avg': {'precision': 0.5692815061887961, 'recall': 0.660358574069891, 'f1': 0.6069277588323989, 'support': None}}
			------------EPOCH 4---------------
Loss:  tensor(0.6483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0722, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6062, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7241943326997038, 'B-C': 0.15416666666666667, 'I-C': 0.2729292288162488, 'B-P': 0.4494745351657235, 'I-P': 0.6953615767066599, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.8912706400805201, 'B-C': 0.03132938187976291, 'I-C': 0.05052878965922444, 'B-P': 0.5503134279115803, 'I-P': 0.8907045476213176, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.799092716120142, 'B-C': 0.05207600281491907, 'I-C': 0.08527093351841752, 'B-P': 0.4948086621180658, 'I-P': 0.7810036531436262, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6863773644889525, 'recall': 0.6863773644889525, 'f1': 0.6863773644889525, 'support': None}, 'macro_avg': {'precision': 0.3280180485792861, 'recall': 0.3448781124503436, 'f1': 0.31603599538788146, 'support': None}, 'weighted_avg': {'precision': 0.5796085416813307, 'recall': 0.6863773644889525, 'f1': 0.6136398867981642, 'support': None}}
			------------EPOCH 5---------------
Loss:  tensor(0.5745, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2429, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5491, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8102104053176071, 'B-C': 0.19144981412639406, 'I-C': 0.2980240677462487, 'B-P': 0.4845725847243298, 'I-P': 0.7022430728632165, 'B-MC': 0.2727272727272727, 'I-MC': 0.2835820895522388}, 'recall': {'O': 0.8819945050461087, 'B-C': 0.08721422523285352, 'I-C': 0.11786133960047003, 'B-P': 0.6321346090399208, 'I-P': 0.9133377824387453, 'B-MC': 0.005076142131979695, 'I-MC': 0.002235294117647059}, 'f1': {'O': 0.8445798981492335, 'B-C': 0.11983711460151254, 'I-C': 0.168919203401962, 'B-P': 0.5486041517537581, 'I-P': 0.7939994198334094, 'B-MC': 0.009966777408637873, 'I-MC': 0.00443562507295436}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7058538095357612, 'recall': 0.7058538095357612, 'f1': 0.7058538095357612, 'support': None}, 'macro_avg': {'precision': 0.43468704386532975, 'recall': 0.37712198537253216, 'f1': 0.3557631700316382, 'support': None}, 'weighted_avg': {'precision': 0.6354284199934046, 'recall': 0.7058538095357612, 'f1': 0.6476407068226719, 'support': None}}
			------------EPOCH 6---------------
Loss:  tensor(0.4802, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2838, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5591, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7918, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4736, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7914919113241462, 'B-C': 0.21040189125295508, 'I-C': 0.309856283763123, 'B-P': 0.48675070748649346, 'I-P': 0.7292474416830865, 'B-MC': 0.3, 'I-MC': 0.5243055555555556}, 'recall': {'O': 0.8983705557520199, 'B-C': 0.15071972904318373, 'I-C': 0.17861339600470036, 'B-P': 0.6242164302210491, 'I-P': 0.8750691200305082, 'B-MC': 0.02030456852791878, 'I-MC': 0.017764705882352943}, 'f1': {'O': 0.8415513594781237, 'B-C': 0.1756290083867785, 'I-C': 0.22660355558868472, 'B-P': 0.5469788956345765, 'I-P': 0.7955311717240006, 'B-MC': 0.038034865293185414, 'I-MC': 0.03436504324078289}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7043562650068185, 'recall': 0.7043562650068185, 'f1': 0.7043562650068185, 'support': None}, 'macro_avg': {'precision': 0.47886482729505137, 'recall': 0.39500835792310474, 'f1': 0.3798134141923045, 'support': None}, 'weighted_avg': {'precision': 0.6607006954888629, 'recall': 0.7043562650068185, 'f1': 0.6583723339730779, 'support': None}}
			------------EPOCH 7---------------
Loss:  tensor(0.3995, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2398, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3852, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8132120702864345, 'B-C': 0.23377638780297108, 'I-C': 0.33103074630908846, 'B-P': 0.5137233157748822, 'I-P': 0.7546339123582417, 'B-MC': 0.31746031746031744, 'I-MC': 0.5109409190371991}, 'recall': {'O': 0.8951062267076522, 'B-C': 0.2531752751905165, 'I-C': 0.2871915393654524, 'B-P': 0.6113493896403827, 'I-P': 0.8399466107350557, 'B-MC': 0.0676818950930626, 'I-MC': 0.054941176470588236}, 'f1': {'O': 0.8521962084326117, 'B-C': 0.24308943089430898, 'I-C': 0.3075567860064179, 'B-P': 0.5583006929798132, 'I-P': 0.795008076232415, 'B-MC': 0.11157601115760112, 'I-MC': 0.09921393669003611}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7069665102192774, 'recall': 0.7069665102192774, 'f1': 0.7069665102192774, 'support': None}, 'macro_avg': {'precision': 0.49639680986130486, 'recall': 0.4299131590289586, 'f1': 0.4238487346276005, 'support': None}, 'weighted_avg': {'precision': 0.6815853047808692, 'recall': 0.7069665102192774, 'f1': 0.6788725562566148, 'support': None}}
			------------EPOCH 8---------------
Loss:  tensor(0.3183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1967, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3696, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3190, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7921585564833478, 'B-C': 0.26651735722284436, 'I-C': 0.3688073394495413, 'B-P': 0.5108213820078227, 'I-P': 0.7437502026523135, 'B-MC': 0.3263598326359833, 'I-MC': 0.5136668385765859}, 'recall': {'O': 0.8980713255896194, 'B-C': 0.20152413209144793, 'I-C': 0.2007638072855464, 'B-P': 0.6463213460903993, 'I-P': 0.8747449709219182, 'B-MC': 0.1319796954314721, 'I-MC': 0.1171764705882353}, 'f1': {'O': 0.8417966010938716, 'B-C': 0.22950819672131148, 'I-C': 0.2599961955487921, 'B-P': 0.5706379260122342, 'I-P': 0.8039464806750375, 'B-MC': 0.1879518072289157, 'I-MC': 0.19082287575438261}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7159601435634867, 'recall': 0.7159601435634867, 'f1': 0.7159601435634867, 'support': None}, 'macro_avg': {'precision': 0.503154501289777, 'recall': 0.43865453542837696, 'f1': 0.44066572614779215, 'support': None}, 'weighted_avg': {'precision': 0.6762017952727024, 'recall': 0.7159601435634867, 'f1': 0.6798945860511683, 'support': None}}
			------------EPOCH 9---------------
Loss:  tensor(0.2367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2883, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2645, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8454380508035252, 'B-C': 0.2436572522738152, 'I-C': 0.3252465797009227, 'B-P': 0.543656207366985, 'I-P': 0.8057985932406931, 'B-MC': 0.2988235294117647, 'I-MC': 0.47115642607995706}, 'recall': {'O': 0.8872718370011697, 'B-C': 0.43099068585944117, 'I-C': 0.48049353701527614, 'B-P': 0.5258990432200594, 'I-P': 0.7164839355515302, 'B-MC': 0.21489001692047377, 'I-MC': 0.20658823529411766}, 'f1': {'O': 0.8658499356260204, 'B-C': 0.3113149847094801, 'I-C': 0.38791386016506973, 'B-P': 0.5346302196880766, 'I-P': 0.7585211502164982, 'B-MC': 0.25, 'I-MC': 0.28723317248711866}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6890127082130696, 'recall': 0.6890127082130696, 'f1': 0.6890127082130696, 'support': None}, 'macro_avg': {'precision': 0.5048252341253805, 'recall': 0.4946596129802954, 'f1': 0.4850661889846092, 'support': None}, 'weighted_avg': {'precision': 0.7110572974059259, 'recall': 0.6890127082130696, 'f1': 0.6926336225151959, 'support': None}}
			------------EPOCH 10---------------
Loss:  tensor(0.1829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1260, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3559, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7653247838161251, 'B-C': 0.25, 'I-C': 0.3596132761885777, 'B-P': 0.5095976860373389, 'I-P': 0.7720688808613615, 'B-MC': 0.2661498708010336, 'I-MC': 0.4555209415022499}, 'recall': {'O': 0.9220913468077582, 'B-C': 0.23285351397121085, 'I-C': 0.21198589894242068, 'B-P': 0.6393929396238865, 'I-P': 0.8395080560587281, 'B-MC': 0.17428087986463622, 'I-MC': 0.1548235294117647}, 'f1': {'O': 0.8364259981246607, 'B-C': 0.24112231477422183, 'I-C': 0.26673566702398993, 'B-P': 0.5671641791044776, 'I-P': 0.8043774150231568, 'B-MC': 0.21063394683026584, 'I-MC': 0.23110018438844498}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7125049151251998, 'recall': 0.7125049151251998, 'f1': 0.7125049151251998, 'support': None}, 'macro_avg': {'precision': 0.48261077702952665, 'recall': 0.45356230924005786, 'f1': 0.4510799578956025, 'support': None}, 'weighted_avg': {'precision': 0.6744383200575592, 'recall': 0.7125049151251998, 'f1': 0.6823946239924279, 'support': None}}
			------------EPOCH 11---------------
Loss:  tensor(0.1403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2427, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0641, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1440, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3207, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.878624870296543, 'B-C': 0.25290697674418605, 'I-C': 0.3357321514765896, 'B-P': 0.5454272863568216, 'I-P': 0.7987935052980003, 'B-MC': 0.3712121212121212, 'I-MC': 0.5673606858542559}, 'recall': {'O': 0.8753026305051549, 'B-C': 0.4419983065198984, 'I-C': 0.44952996474735607, 'B-P': 0.6001319696469812, 'I-P': 0.7776527791019163, 'B-MC': 0.24873096446700507, 'I-MC': 0.218}, 'f1': {'O': 0.8769606039545944, 'B-C': 0.3217257318952234, 'I-C': 0.38438544047828377, 'B-P': 0.571473452717562, 'I-P': 0.7880813897315994, 'B-MC': 0.2978723404255319, 'I-MC': 0.31497535271120175}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7107312869680161, 'recall': 0.7107312869680161, 'f1': 0.7107312869680161, 'support': None}, 'macro_avg': {'precision': 0.5357225138912167, 'recall': 0.5159066592840446, 'f1': 0.5079249017019996, 'support': None}, 'weighted_avg': {'precision': 0.7270188899625728, 'recall': 0.7107312869680161, 'f1': 0.7117648823229581, 'support': None}}
			------------EPOCH 12---------------
Loss:  tensor(0.1170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2535, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8483661825726141, 'B-C': 0.22954303931987247, 'I-C': 0.33056587284247324, 'B-P': 0.5496588324488249, 'I-P': 0.753391135240256, 'B-MC': 0.3192307692307692, 'I-MC': 0.47762148337595906}, 'recall': {'O': 0.8898833002366638, 'B-C': 0.18289585097375105, 'I-C': 0.17779083431257345, 'B-P': 0.7175849554602441, 'I-P': 0.8864143388311565, 'B-MC': 0.2808798646362098, 'I-MC': 0.2636470588235294}, 'f1': {'O': 0.8686289348256129, 'B-C': 0.20358152686145145, 'I-C': 0.2312218231833117, 'B-P': 0.6224957069261592, 'I-P': 0.8145072273324573, 'B-MC': 0.29882988298829877, 'I-MC': 0.33975136446331106}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7280659923533201, 'recall': 0.7280659923533201, 'f1': 0.7280659923533201, 'support': None}, 'macro_avg': {'precision': 0.5011967592901099, 'recall': 0.48558517189630407, 'f1': 0.48271663808294324, 'support': None}, 'weighted_avg': {'precision': 0.6902941773536645, 'recall': 0.7280659923533201, 'f1': 0.7008809959997643, 'support': None}}
			------------EPOCH 13---------------
Loss:  tensor(0.0891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0868, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1906, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8136828927019663, 'B-C': 0.2406311637080868, 'I-C': 0.34186004019733235, 'B-P': 0.5283066768215283, 'I-P': 0.7626432792103347, 'B-MC': 0.315668202764977, 'I-MC': 0.5244405182567726}, 'recall': {'O': 0.9016892902804603, 'B-C': 0.20660457239627433, 'I-C': 0.2198589894242068, 'B-P': 0.6865720884196634, 'I-P': 0.8588807321956335, 'B-MC': 0.23181049069373943, 'I-MC': 0.20952941176470588}, 'f1': {'O': 0.8554285271877985, 'B-C': 0.22232346241457857, 'I-C': 0.2676106700994064, 'B-P': 0.5971305595408894, 'I-P': 0.8079061591993401, 'B-MC': 0.2673170731707317, 'I-MC': 0.2994283792871553}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7209631135540329, 'recall': 0.7209631135540329, 'f1': 0.7209631135540329, 'support': None}, 'macro_avg': {'precision': 0.5038903962372855, 'recall': 0.47356365359638336, 'f1': 0.47387783298569996, 'support': None}, 'weighted_avg': {'precision': 0.6881749929788048, 'recall': 0.7209631135540329, 'f1': 0.6956250998629346, 'support': None}}
			------------EPOCH 14---------------
Loss:  tensor(0.0637, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0430, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0804, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1576, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8583906829010058, 'B-C': 0.2829771554900516, 'I-C': 0.3751399776035834, 'B-P': 0.5386849749141801, 'I-P': 0.7672343876723439, 'B-MC': 0.330749354005168, 'I-MC': 0.5521710952689566}, 'recall': {'O': 0.8821849242403634, 'B-C': 0.32514817950889074, 'I-C': 0.33460634547591067, 'B-P': 0.673045199604091, 'I-P': 0.8477833921250835, 'B-MC': 0.21658206429780033, 'I-MC': 0.20047058823529412}, 'f1': {'O': 0.870125166016018, 'B-C': 0.3026004728132387, 'I-C': 0.353715723114189, 'B-P': 0.5984159577588736, 'I-P': 0.8055001992825827, 'B-MC': 0.261758691206544, 'I-MC': 0.2941481097876748}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7265433493127191, 'recall': 0.7265433493127191, 'f1': 0.7265433493127191, 'support': None}, 'macro_avg': {'precision': 0.5293353754078984, 'recall': 0.49711724192677625, 'f1': 0.49803775999701727, 'support': None}, 'weighted_avg': {'precision': 0.711406161952453, 'recall': 0.7265433493127191, 'f1': 0.7117728671096659, 'support': None}}
			------------EPOCH 15---------------
Loss:  tensor(0.0475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0320, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0586, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0889, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0288, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1415, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8595791863565564, 'B-C': 0.2793103448275862, 'I-C': 0.3763000520020801, 'B-P': 0.5317647058823529, 'I-P': 0.7707707882426866, 'B-MC': 0.3261390887290168, 'I-MC': 0.5460085313833029}, 'recall': {'O': 0.885721280705095, 'B-C': 0.34292972057578325, 'I-C': 0.3401292596944771, 'B-P': 0.6710656548993732, 'I-P': 0.8420059109543331, 'B-MC': 0.23011844331641285, 'I-MC': 0.21082352941176472}, 'f1': {'O': 0.8724544480171489, 'B-C': 0.30786773090079816, 'I-C': 0.3573015677076904, 'B-P': 0.5933488914819137, 'I-P': 0.804815148947028, 'B-MC': 0.2698412698412698, 'I-MC': 0.3041928365303005}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7268110667704072, 'recall': 0.7268110667704072, 'f1': 0.7268110667704072, 'support': None}, 'macro_avg': {'precision': 0.5271246710605118, 'recall': 0.5032562570796056, 'f1': 0.5014031276323071, 'support': None}, 'weighted_avg': {'precision': 0.712815771930529, 'recall': 0.7268110667704072, 'f1': 0.7133770776441655, 'support': None}}
			------------EPOCH 16---------------
Loss:  tensor(0.0354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0448, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1307, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8492123030757689, 'B-C': 0.2850678733031674, 'I-C': 0.39654073736913975, 'B-P': 0.5276532137518685, 'I-P': 0.759606954392814, 'B-MC': 0.30785123966942146, 'I-MC': 0.54004696060527}, 'recall': {'O': 0.8930116155708495, 'B-C': 0.26672311600338694, 'I-C': 0.25593419506462983, 'B-P': 0.698779280765424, 'I-P': 0.8755648774907046, 'B-MC': 0.2521150592216582, 'I-MC': 0.24352941176470588}, 'f1': {'O': 0.8705614044392584, 'B-C': 0.2755905511811024, 'I-C': 0.3110873058382432, 'B-P': 0.601277501774308, 'I-P': 0.8134743480725624, 'B-MC': 0.27720930232558144, 'I-MC': 0.3356847482364388}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7341732968568297, 'recall': 0.7341732968568297, 'f1': 0.7341732968568299, 'support': None}, 'macro_avg': {'precision': 0.5237113260239215, 'recall': 0.49795107941162275, 'f1': 0.49784073740964213, 'support': None}, 'weighted_avg': {'precision': 0.7070495431532483, 'recall': 0.7341732968568297, 'f1': 0.7121717033115895, 'support': None}}
			------------EPOCH 17---------------
Loss:  tensor(0.0264, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0472, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1277, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8534049240440021, 'B-C': 0.28312570781426954, 'I-C': 0.3946041055718475, 'B-P': 0.5314009661835749, 'I-P': 0.7404259963824612, 'B-MC': 0.31136363636363634, 'I-MC': 0.5664292350572933}, 'recall': {'O': 0.8863469437719322, 'B-C': 0.21168501270110077, 'I-C': 0.19764982373678025, 'B-P': 0.7258330583965688, 'I-P': 0.905424730670226, 'B-MC': 0.23181049069373943, 'I-MC': 0.2151764705882353}, 'f1': {'O': 0.8695640570582193, 'B-C': 0.24224806201550386, 'I-C': 0.2633783519279702, 'B-P': 0.6135824850090643, 'I-P': 0.8146546917488013, 'B-MC': 0.2657613967022308, 'I-MC': 0.3118765453150311}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7349513507182357, 'recall': 0.7349513507182357, 'f1': 0.7349513507182357, 'support': None}, 'macro_avg': {'precision': 0.5258220816310121, 'recall': 0.48198950436551186, 'f1': 0.48300936996811733, 'support': None}, 'weighted_avg': {'precision': 0.7016166274828833, 'recall': 0.7349513507182357, 'f1': 0.7038224050567536, 'support': None}}
			------------EPOCH 18---------------
Loss:  tensor(0.0196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0356, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1510, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8515781530535245, 'B-C': 0.29312288613303267, 'I-C': 0.4011655566127498, 'B-P': 0.5219047619047619, 'I-P': 0.7427347330949643, 'B-MC': 0.3012295081967213, 'I-MC': 0.5383131201764058}, 'recall': {'O': 0.8902641386251734, 'B-C': 0.2201524132091448, 'I-C': 0.1981786133960047, 'B-P': 0.7231936654569449, 'I-P': 0.8991133568500334, 'B-MC': 0.24873096446700507, 'I-MC': 0.22976470588235295}, 'f1': {'O': 0.8704915416533675, 'B-C': 0.2514506769825919, 'I-C': 0.2652980965864401, 'B-P': 0.6062785230258608, 'I-P': 0.8134768657488872, 'B-MC': 0.2724745134383688, 'I-MC': 0.3220646437994723}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7345999715550201, 'recall': 0.7345999715550201, 'f1': 0.7345999715550201, 'support': None}, 'macro_avg': {'precision': 0.5214355313103086, 'recall': 0.48705683684095125, 'f1': 0.4859335516049984, 'support': None}, 'weighted_avg': {'precision': 0.7008105560810779, 'recall': 0.7345999715550201, 'f1': 0.7045276272148722, 'support': None}}
			------------EPOCH 19---------------
Loss:  tensor(0.0149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0266, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0145, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0450, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1356, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8571653419375147, 'B-C': 0.25102880658436216, 'I-C': 0.3613159714219866, 'B-P': 0.5473946784922394, 'I-P': 0.7906082455167314, 'B-MC': 0.281767955801105, 'I-MC': 0.5087591240875913}, 'recall': {'O': 0.8888767987813172, 'B-C': 0.3615580016934801, 'I-C': 0.368448883666275, 'B-P': 0.651600131969647, 'I-P': 0.8154066164553342, 'B-MC': 0.25888324873096447, 'I-MC': 0.246}, 'f1': {'O': 0.8727331000774553, 'B-C': 0.296321998612075, 'I-C': 0.36484756807074703, 'B-P': 0.5949691218557012, 'I-P': 0.8028159759703384, 'B-MC': 0.2698412698412698, 'I-MC': 0.3316415543219667}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7224773904240812, 'recall': 0.7224773904240812, 'f1': 0.7224773904240812, 'support': None}, 'macro_avg': {'precision': 0.5140057319773615, 'recall': 0.5129676687567168, 'f1': 0.5047386555356506, 'support': None}, 'weighted_avg': {'precision': 0.7158923617900363, 'recall': 0.7224773904240812, 'f1': 0.7155390578955252, 'support': None}}
			------------EPOCH 20---------------
Loss:  tensor(0.0120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0177, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0390, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1008, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.86840130767994, 'B-C': 0.30089485458612975, 'I-C': 0.39696386088138663, 'B-P': 0.5359634351695934, 'I-P': 0.7413860396858851, 'B-MC': 0.3095723014256619, 'I-MC': 0.5307468989179203}, 'recall': {'O': 0.8815592611735263, 'B-C': 0.2277730736663844, 'I-C': 0.20587544065804936, 'B-P': 0.7350709336852523, 'I-P': 0.9054819334540948, 'B-MC': 0.2571912013536379, 'I-MC': 0.23658823529411765}, 'f1': {'O': 0.8749308171006628, 'B-C': 0.2592771084337349, 'I-C': 0.2711339807327736, 'B-P': 0.6199220923761825, 'I-P': 0.8152586310494601, 'B-MC': 0.2809611829944547, 'I-MC': 0.3272845634307104}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7367166127048665, 'recall': 0.7367166127048665, 'f1': 0.7367166127048665, 'support': None}, 'macro_avg': {'precision': 0.5262755283352167, 'recall': 0.4927914398978661, 'f1': 0.49268119658828274, 'support': None}, 'weighted_avg': {'precision': 0.7047309364368467, 'recall': 0.7367166127048665, 'f1': 0.7083421429131124, 'support': None}}
			------------EPOCH 21---------------
Loss:  tensor(0.0094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1007, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8693192532528757, 'B-C': 0.32531824611032534, 'I-C': 0.4114502743001829, 'B-P': 0.5366317792578497, 'I-P': 0.7268130944879527, 'B-MC': 0.3271461716937355, 'I-MC': 0.5452618831365426}, 'recall': {'O': 0.8778324855145399, 'B-C': 0.1947502116850127, 'I-C': 0.1718566392479436, 'B-P': 0.744308808973936, 'I-P': 0.9237296215082468, 'B-MC': 0.23857868020304568, 'I-MC': 0.21188235294117647}, 'f1': {'O': 0.8735551284480658, 'B-C': 0.24364406779661016, 'I-C': 0.2424468481909735, 'B-P': 0.6236351071181756, 'I-P': 0.8135248826606437, 'B-MC': 0.2759295499021526, 'I-MC': 0.30517665000423627}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7367919082398414, 'recall': 0.7367919082398414, 'f1': 0.7367919082398413, 'support': None}, 'macro_avg': {'precision': 0.5345629574627806, 'recall': 0.4804198285819859, 'f1': 0.48255889058869395, 'support': None}, 'weighted_avg': {'precision': 0.7020592713363051, 'recall': 0.7367919082398414, 'f1': 0.7014161872599817, 'support': None}}
			------------EPOCH 22---------------
Loss:  tensor(0.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0134, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0869, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8582695796198438, 'B-C': 0.298, 'I-C': 0.3924410065602663, 'B-P': 0.5358471843215084, 'I-P': 0.7492892593841854, 'B-MC': 0.30885529157667385, 'I-MC': 0.5328984685195689}, 'recall': {'O': 0.8880607165202252, 'B-C': 0.2523285351397121, 'I-C': 0.2354876615746181, 'B-P': 0.7126360936984494, 'I-P': 0.8895032891600725, 'B-MC': 0.24196277495769883, 'I-MC': 0.22105882352941175}, 'f1': {'O': 0.8729110404021497, 'B-C': 0.27326914259513985, 'I-C': 0.2943487680387765, 'B-P': 0.6117247238742566, 'I-P': 0.8133979634537593, 'B-MC': 0.27134724857685005, 'I-MC': 0.312489605853983}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7344159158028596, 'recall': 0.7344159158028596, 'f1': 0.7344159158028597, 'support': None}, 'macro_avg': {'precision': 0.5250858271402924, 'recall': 0.49157684208288405, 'f1': 0.4927840703992735, 'support': None}, 'weighted_avg': {'precision': 0.7045564710813365, 'recall': 0.7344159158028596, 'f1': 0.7090409135081136, 'support': None}}
			------------EPOCH 23---------------
Loss:  tensor(0.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0289, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0840, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8523603145355929, 'B-C': 0.29396092362344584, 'I-C': 0.3881698949014158, 'B-P': 0.5307206068268016, 'I-P': 0.7601003388929497, 'B-MC': 0.28169014084507044, 'I-MC': 0.508223240765705}, 'recall': {'O': 0.8934468594434319, 'B-C': 0.2802709568162574, 'I-C': 0.2625734430082256, 'B-P': 0.6925107225338172, 'I-P': 0.8724377919725427, 'B-MC': 0.23688663282571912, 'I-MC': 0.22176470588235295}, 'f1': {'O': 0.8724201131564268, 'B-C': 0.28695275249241436, 'I-C': 0.3132513230294746, 'B-P': 0.6009161179501861, 'I-P': 0.8124040091973614, 'B-MC': 0.2573529411764706, 'I-MC': 0.3087885985748218}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.732232345288591, 'recall': 0.732232345288591, 'f1': 0.7322323452885912, 'support': None}, 'macro_avg': {'precision': 0.5164607800558544, 'recall': 0.49427015892604953, 'f1': 0.49315512222530794, 'support': None}, 'weighted_avg': {'precision': 0.7048154827443134, 'recall': 0.732232345288591, 'f1': 0.7106741308835723, 'support': None}}
			------------EPOCH 24---------------
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0714, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8618301033762525, 'B-C': 0.3039106145251397, 'I-C': 0.3940491875274484, 'B-P': 0.5281468953853588, 'I-P': 0.7405483224837256, 'B-MC': 0.32387706855791965, 'I-MC': 0.552981155390794}, 'recall': {'O': 0.8867277821604418, 'B-C': 0.23031329381879762, 'I-C': 0.2108695652173913, 'B-P': 0.721214120752227, 'I-P': 0.9023548479359329, 'B-MC': 0.23181049069373943, 'I-MC': 0.21058823529411766}, 'f1': {'O': 0.8741016840072938, 'B-C': 0.26204238921001927, 'I-C': 0.27472443355786896, 'B-P': 0.60976290097629, 'I-P': 0.8134835709804125, 'B-MC': 0.2702169625246549, 'I-MC': 0.30501831813921787}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7353445607342152, 'recall': 0.7353445607342152, 'f1': 0.7353445607342152, 'support': None}, 'macro_avg': {'precision': 0.5293347638923769, 'recall': 0.48483976226752107, 'f1': 0.48705003705653677, 'support': None}, 'weighted_avg': {'precision': 0.7034108309999856, 'recall': 0.7353445607342152, 'f1': 0.7059527402435088, 'support': None}}
			------------EPOCH 25---------------
Loss:  tensor(0.0045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0653, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8648088071052492, 'B-C': 0.31014150943396224, 'I-C': 0.404392010279173, 'B-P': 0.5283109404990403, 'I-P': 0.737927721299281, 'B-MC': 0.3105022831050228, 'I-MC': 0.5476331360946746}, 'recall': {'O': 0.884687576507712, 'B-C': 0.222692633361558, 'I-C': 0.20340775558166863, 'B-P': 0.7264929066314748, 'I-P': 0.9079416531604538, 'B-MC': 0.23011844331641285, 'I-MC': 0.21776470588235294}, 'f1': {'O': 0.8746352548845591, 'B-C': 0.2592410054213899, 'I-C': 0.27066963762167234, 'B-P': 0.6117516321711349, 'I-P': 0.8141536935874091, 'B-MC': 0.26433430515063167, 'I-MC': 0.3116161616161616}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7366664156815501, 'recall': 0.7366664156815501, 'f1': 0.7366664156815501, 'support': None}, 'macro_avg': {'precision': 0.5291023439737719, 'recall': 0.4847293820630904, 'f1': 0.48662881292185123, 'support': None}, 'weighted_avg': {'precision': 0.7042691230237205, 'recall': 0.7366664156815501, 'f1': 0.7062963470782702, 'support': None}}
			------------EPOCH 26---------------
Loss:  tensor(0.0038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0023, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0581, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8641880228389324, 'B-C': 0.3091732729331823, 'I-C': 0.39841359773371104, 'B-P': 0.5268609973500361, 'I-P': 0.7400696102761, 'B-MC': 0.3080357142857143, 'I-MC': 0.5314645308924485}, 'recall': {'O': 0.8852044286064035, 'B-C': 0.23116003386960204, 'I-C': 0.20658049353701527, 'B-P': 0.7215440448696799, 'I-P': 0.9041281342358661, 'B-MC': 0.233502538071066, 'I-MC': 0.21858823529411764}, 'f1': {'O': 0.8745699849494732, 'B-C': 0.2645348837209302, 'I-C': 0.27208357515960535, 'B-P': 0.6090225563909774, 'I-P': 0.8139139688969755, 'B-MC': 0.26564003849855633, 'I-MC': 0.30976992330776926}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7356373767035614, 'recall': 0.7356373767035614, 'f1': 0.7356373767035614, 'support': None}, 'macro_avg': {'precision': 0.5254579637585892, 'recall': 0.4858154154976786, 'f1': 0.48707641870346957, 'support': None}, 'weighted_avg': {'precision': 0.7029583865837623, 'recall': 0.7356373767035614, 'f1': 0.7062306924822436, 'support': None}}
			------------EPOCH 27---------------
Loss:  tensor(0.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0532, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8670340842206645, 'B-C': 0.31774580335731417, 'I-C': 0.4007387988560534, 'B-P': 0.5269175797999047, 'I-P': 0.7331529382987831, 'B-MC': 0.32642487046632124, 'I-MC': 0.5599180607715945}, 'recall': {'O': 0.8815864639155627, 'B-C': 0.2243861134631668, 'I-C': 0.19759106933019976, 'B-P': 0.7297921478060047, 'I-P': 0.9144246353322528, 'B-MC': 0.2131979695431472, 'I-MC': 0.19294117647058823}, 'f1': {'O': 0.8742497201203144, 'B-C': 0.26302729528535984, 'I-C': 0.26467810483236265, 'B-P': 0.6119795269055195, 'I-P': 0.8138167440202958, 'B-MC': 0.2579324462640737, 'I-MC': 0.2869892379035786}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7359803896962244, 'recall': 0.7359803896962244, 'f1': 0.7359803896962244, 'support': None}, 'macro_avg': {'precision': 0.5331331622529479, 'recall': 0.47913136798013173, 'f1': 0.48181043933307205, 'support': None}, 'weighted_avg': {'precision': 0.703330453436306, 'recall': 0.7359803896962244, 'f1': 0.7034370422695684, 'support': None}}
			------------EPOCH 28---------------
Loss:  tensor(0.0030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0206, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0512, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8604964351729602, 'B-C': 0.31085714285714283, 'I-C': 0.4013334892969938, 'B-P': 0.5191529859624078, 'I-P': 0.7371074841752513, 'B-MC': 0.31476997578692495, 'I-MC': 0.5406259879860892}, 'recall': {'O': 0.8864557547400778, 'B-C': 0.23031329381879762, 'I-C': 0.20158636897767332, 'B-P': 0.719894424282415, 'I-P': 0.9059204881304224, 'B-MC': 0.21996615905245348, 'I-MC': 0.2011764705882353}, 'f1': {'O': 0.8732832201096058, 'B-C': 0.2645914396887159, 'I-C': 0.26837185654503504, 'B-P': 0.6032623721316007, 'I-P': 0.8128416352298098, 'B-MC': 0.25896414342629487, 'I-MC': 0.29323501671954044}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.734742196454417, 'recall': 0.734742196454417, 'f1': 0.734742196454417, 'support': None}, 'macro_avg': {'precision': 0.52633478589111, 'recall': 0.48075899422715346, 'f1': 0.4820785262643718, 'support': None}, 'weighted_avg': {'precision': 0.701445108622487, 'recall': 0.734742196454417, 'f1': 0.7034815752123533, 'support': None}}
			------------EPOCH 29---------------
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0696, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8601977162190738, 'B-C': 0.29651162790697677, 'I-C': 0.3815827616194801, 'B-P': 0.5277846381822672, 'I-P': 0.744581500605597, 'B-MC': 0.3154034229828851, 'I-MC': 0.5453376205787781}, 'recall': {'O': 0.8852588340904763, 'B-C': 0.25910245554614736, 'I-C': 0.232021151586369, 'B-P': 0.7050478389970307, 'I-P': 0.8908570883783011, 'B-MC': 0.2182741116751269, 'I-MC': 0.19952941176470587}, 'f1': {'O': 0.8725483624468783, 'B-C': 0.27654767284229553, 'I-C': 0.2885746647667069, 'B-P': 0.6036723163841807, 'I-P': 0.8111777625376542, 'B-MC': 0.25799999999999995, 'I-MC': 0.2921619293712317}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7318809661253755, 'recall': 0.7318809661253755, 'f1': 0.7318809661253755, 'support': None}, 'macro_avg': {'precision': 0.5244856125850083, 'recall': 0.4842986988625939, 'f1': 0.48609752976413534, 'support': None}, 'weighted_avg': {'precision': 0.7022355438156811, 'recall': 0.7318809661253755, 'f1': 0.705449697519171, 'support': None}}
			------------EPOCH 30---------------
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0396, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8604220659015179, 'B-C': 0.33187134502923976, 'I-C': 0.417298937784522, 'B-P': 0.5141203703703704, 'I-P': 0.72444904821954, 'B-MC': 0.3325242718446602, 'I-MC': 0.5537617048756861}, 'recall': {'O': 0.8850684148962216, 'B-C': 0.1922099915325995, 'I-C': 0.16157461809635723, 'B-P': 0.7327614648630815, 'I-P': 0.9201449137191343, 'B-MC': 0.23181049069373943, 'I-MC': 0.20176470588235293}, 'f1': {'O': 0.8725712370097217, 'B-C': 0.24343163538873994, 'I-C': 0.2329521389241847, 'B-P': 0.6042715276833084, 'I-P': 0.8106537204868256, 'B-MC': 0.27318045862412765, 'I-MC': 0.29576614641717686}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7349095198654719, 'recall': 0.7349095198654719, 'f1': 0.7349095198654718, 'support': None}, 'macro_avg': {'precision': 0.533492534860791, 'recall': 0.47504779995478374, 'f1': 0.4761181235048693, 'support': None}, 'weighted_avg': {'precision': 0.6992434393055049, 'recall': 0.7349095198654719, 'f1': 0.6973259432985354, 'support': None}}
	Data split: 12k
			------------EPOCH 1---------------
Loss:  tensor(4.5116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3261, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1363, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8839, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8477, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8997695852534562, 'B-C': 0.0, 'I-C': 0.05454545454545454, 'B-P': 0.12279293739967898, 'I-P': 0.4479278505475628, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.04249068306085253, 'B-C': 0.0, 'I-C': 0.00035252643948296123, 'B-P': 0.050478389970306826, 'I-P': 0.9943750595862332, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.08114918045561992, 'B-C': 0.0, 'I-C': 0.0007005253940455341, 'B-P': 0.07154547580079496, 'I-P': 0.6176348670574998, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.4506939738473508, 'recall': 0.4506939738473508, 'f1': 0.4506939738473508, 'support': None}, 'macro_avg': {'precision': 0.2178622611065932, 'recall': 0.15538523700812507, 'f1': 0.11014714981542288, 'support': None}, 'weighted_avg': {'precision': 0.4841381997263534, 'recall': 0.4506939738473508, 'f1': 0.2978671527823247, 'support': None}}
			------------EPOCH 2---------------
Loss:  tensor(3.5203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2706, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1270, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7455, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8176, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5317, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9253871761470546, 'B-C': 0.11538461538461539, 'I-C': 0.1895707288965716, 'B-P': 0.3191736979924353, 'I-P': 0.5117214002896173, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.3478414624194119, 'B-C': 0.005080440304826418, 'I-C': 0.03866039952996475, 'B-P': 0.36192675684592546, 'I-P': 0.9635427590809419, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.5056248640740229, 'B-C': 0.0097323600973236, 'I-C': 0.06422331755404813, 'B-P': 0.33920841063698204, 'I-P': 0.6684436096193022, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.5444787457437107, 'recall': 0.5444787457437107, 'f1': 0.5444787457437107, 'support': None}, 'macro_avg': {'precision': 0.2944625169586134, 'recall': 0.2452931168830101, 'f1': 0.22674750885452552, 'support': None}, 'weighted_avg': {'precision': 0.545353557176374, 'recall': 0.5444787457437107, 'f1': 0.4666358474461845, 'support': None}}
			------------EPOCH 3---------------
Loss:  tensor(3.1069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2403, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5375, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6283, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3540, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.823314740090197, 'B-C': 0.0, 'I-C': 0.1774193548387097, 'B-P': 0.40742259585810947, 'I-P': 0.6200291999703051, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.7548488887679878, 'B-C': 0.0, 'I-C': 0.0012925969447708577, 'B-P': 0.6555592213790828, 'I-P': 0.9555153017446849, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.787596679202441, 'B-C': 0.0, 'I-C': 0.0025664955669622022, 'B-P': 0.5025290844714213, 'I-P': 0.7520541469381018, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6682060420483732, 'recall': 0.6682060420483732, 'f1': 0.6682060420483732, 'support': None}, 'macro_avg': {'precision': 0.2897408415367602, 'recall': 0.33817371554807524, 'f1': 0.29210662945413235, 'support': None}, 'weighted_avg': {'precision': 0.5608503364062207, 'recall': 0.6682060420483732, 'f1': 0.5853070691623978, 'support': None}}
			------------EPOCH 4---------------
Loss:  tensor(2.7008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8879, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5594, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1581, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8187770591693837, 'B-C': 0.15283842794759825, 'I-C': 0.2539226942212017, 'B-P': 0.4400346996313164, 'I-P': 0.6728304265602018, 'B-MC': 0.20833333333333334, 'I-MC': 0.5277777777777778}, 'recall': {'O': 0.8334104077691031, 'B-C': 0.029635901778154106, 'I-C': 0.07796709753231493, 'B-P': 0.6694160343121082, 'I-P': 0.9158165697397274, 'B-MC': 0.01692047377326565, 'I-MC': 0.038}, 'f1': {'O': 0.8260289300206258, 'B-C': 0.04964539007092199, 'I-C': 0.11930234648925649, 'B-P': 0.5310128238680973, 'I-P': 0.7757409351530324, 'B-MC': 0.03129890453834116, 'I-MC': 0.0708955223880597}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6892971580118632, 'recall': 0.6892971580118632, 'f1': 0.6892971580118632, 'support': None}, 'macro_avg': {'precision': 0.4392163455201161, 'recall': 0.3687380692720962, 'f1': 0.34341783607547643, 'support': None}, 'weighted_avg': {'precision': 0.6344142669797296, 'recall': 0.6892971580118632, 'f1': 0.6305511586772649, 'support': None}}
			------------EPOCH 5---------------
Loss:  tensor(2.3537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4796, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0161, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8371108936552855, 'B-C': 0.17391304347826086, 'I-C': 0.2664576802507837, 'B-P': 0.42565311333726186, 'I-P': 0.6682825018514779, 'B-MC': 0.25688073394495414, 'I-MC': 0.4832925835370823}, 'recall': {'O': 0.8610211909360463, 'B-C': 0.010160880609652836, 'I-C': 0.014982373678025853, 'B-P': 0.7149455625206202, 'I-P': 0.9463247211364286, 'B-MC': 0.047377326565143825, 'I-MC': 0.06976470588235294}, 'f1': {'O': 0.848897709596095, 'B-C': 0.0192, 'I-C': 0.0283695833565111, 'B-P': 0.5336124107362719, 'I-P': 0.7833635861415832, 'B-MC': 0.08, 'I-MC': 0.12192865220520202}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7055777259075203, 'recall': 0.7055777259075203, 'f1': 0.7055777259075203, 'support': None}, 'macro_avg': {'precision': 0.444512935722158, 'recall': 0.38065382304689577, 'f1': 0.3450531345765233, 'support': None}, 'weighted_avg': {'precision': 0.6367623627222748, 'recall': 0.7055777259075203, 'f1': 0.6316158442475972, 'support': None}}
			------------EPOCH 6---------------
Loss:  tensor(2.0276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4694, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9094, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.876265592660961, 'B-C': 0.22267206477732793, 'I-C': 0.3401360544217687, 'B-P': 0.47091474245115456, 'I-P': 0.7543319672828065, 'B-MC': 0.2689655172413793, 'I-MC': 0.4095744680851064}, 'recall': {'O': 0.8522619080003264, 'B-C': 0.18628281117696868, 'I-C': 0.2790834312573443, 'B-P': 0.6997690531177829, 'I-P': 0.8458384974735437, 'B-MC': 0.19796954314720813, 'I-MC': 0.24458823529411763}, 'f1': {'O': 0.864097083362063, 'B-C': 0.20285846011987094, 'I-C': 0.3065999677263192, 'B-P': 0.562972793629728, 'I-P': 0.7974688095494912, 'B-MC': 0.22807017543859648, 'I-MC': 0.30627578078962875}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7109320750612822, 'recall': 0.7109320750612822, 'f1': 0.7109320750612823, 'support': None}, 'macro_avg': {'precision': 0.4775514867029292, 'recall': 0.4722562113524703, 'f1': 0.46690615294509963, 'support': None}, 'weighted_avg': {'precision': 0.6934979378602633, 'recall': 0.7109320750612822, 'f1': 0.6984977372711823, 'support': None}}
			------------EPOCH 7---------------
Loss:  tensor(1.7062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1417, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7829, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9004010695187166, 'B-C': 0.25029239766081873, 'I-C': 0.3407880724174654, 'B-P': 0.5280979827089337, 'I-P': 0.7437219623557209, 'B-MC': 0.32779097387173395, 'I-MC': 0.46059979317476735}, 'recall': {'O': 0.8427681510296238, 'B-C': 0.18120237087214225, 'I-C': 0.2444183313748531, 'B-P': 0.7255031342791158, 'I-P': 0.8882829631042044, 'B-MC': 0.233502538071066, 'I-MC': 0.262}, 'f1': {'O': 0.8706318762382497, 'B-C': 0.21021611001964638, 'I-C': 0.2846682861737435, 'B-P': 0.6112578179291174, 'I-P': 0.8095999443884467, 'B-MC': 0.2727272727272727, 'I-MC': 0.3340082489688789}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7237155836658886, 'recall': 0.7237155836658886, 'f1': 0.7237155836658886, 'support': None}, 'macro_avg': {'precision': 0.5073846073868794, 'recall': 0.48252535553300074, 'f1': 0.4847299366350507, 'support': None}, 'weighted_avg': {'precision': 0.7020006696252834, 'recall': 0.7237155836658886, 'f1': 0.7061973355672443, 'support': None}}
			------------EPOCH 8---------------
Loss:  tensor(1.3872, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4484, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6660, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8472844782654019, 'B-C': 0.2743243243243243, 'I-C': 0.3965891809689333, 'B-P': 0.5341839191141069, 'I-P': 0.7744054049419552, 'B-MC': 0.29160063391442154, 'I-MC': 0.39671969416697495}, 'recall': {'O': 0.884415549087348, 'B-C': 0.1718882303132938, 'I-C': 0.2145123384253819, 'B-P': 0.7321016166281755, 'I-P': 0.8611116407665173, 'B-MC': 0.311336717428088, 'I-MC': 0.3784705882352941}, 'f1': {'O': 0.8654519319074175, 'B-C': 0.21134825611660593, 'I-C': 0.27842598947609243, 'B-P': 0.6176757132915797, 'I-P': 0.8154601758725918, 'B-MC': 0.3011456628477905, 'I-MC': 0.38738033596243}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7290866651607559, 'recall': 0.7290866651607559, 'f1': 0.7290866651607558, 'support': None}, 'macro_avg': {'precision': 0.5021582336708741, 'recall': 0.5076909544120142, 'f1': 0.4966982950677869, 'support': None}, 'weighted_avg': {'precision': 0.7027433165902094, 'recall': 0.7290866651607559, 'f1': 0.7103965150988792, 'support': None}}
			------------EPOCH 9---------------
Loss:  tensor(1.1180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0944, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3336, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3296, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2509, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5847, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9253740439406405, 'B-C': 0.29106438896189224, 'I-C': 0.3795594444727069, 'B-P': 0.5792243767313019, 'I-P': 0.8056913341669508, 'B-MC': 0.32474964234620884, 'I-MC': 0.45463160388533524}, 'recall': {'O': 0.8260928701613123, 'B-C': 0.37510584250635054, 'I-C': 0.4383666274970623, 'B-P': 0.6898713295941933, 'I-P': 0.8108685289350749, 'B-MC': 0.3840947546531303, 'I-MC': 0.4515294117647059}, 'f1': {'O': 0.872919601023312, 'B-C': 0.32778394376618575, 'I-C': 0.4068489789241214, 'B-P': 0.6297244390904985, 'I-P': 0.8082716413087896, 'B-MC': 0.351937984496124, 'I-MC': 0.4530751977334435}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7274719942440746, 'recall': 0.7274719942440746, 'f1': 0.7274719942440746, 'support': None}, 'macro_avg': {'precision': 0.5371849763578623, 'recall': 0.5679899093016899, 'f1': 0.5500802551917822, 'support': None}, 'weighted_avg': {'precision': 0.7436515891164625, 'recall': 0.7274719942440746, 'f1': 0.7342043809032841, 'support': None}}
			------------EPOCH 10---------------
Loss:  tensor(0.8290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2657, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5068, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8663551150860795, 'B-C': 0.2921511627906977, 'I-C': 0.37152428810720267, 'B-P': 0.5743688254665203, 'I-P': 0.7998252398304454, 'B-MC': 0.3651804670912951, 'I-MC': 0.49422361464656356}, 'recall': {'O': 0.8774788498680667, 'B-C': 0.34038950042337, 'I-C': 0.390951821386604, 'B-P': 0.6905311778290993, 'I-P': 0.8203069882734293, 'B-MC': 0.2910321489001692, 'I-MC': 0.2969411764705882}, 'f1': {'O': 0.8718815039057219, 'B-C': 0.3144309737974188, 'I-C': 0.3809905525336387, 'B-P': 0.6271161048689139, 'I-P': 0.8099366486873194, 'B-MC': 0.3239171374764595, 'I-MC': 0.3709855221577129}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7288858770674899, 'recall': 0.7288858770674899, 'f1': 0.7288858770674899, 'support': None}, 'macro_avg': {'precision': 0.5376612447169721, 'recall': 0.5296616661644753, 'f1': 0.5284654919181693, 'support': None}, 'weighted_avg': {'precision': 0.7246854176472928, 'recall': 0.7288858770674899, 'f1': 0.7247594020707009, 'support': None}}
			------------EPOCH 11---------------
Loss:  tensor(0.5328, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1647, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1606, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4998, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9124141170943685, 'B-C': 0.2804370447450572, 'I-C': 0.3539287020852811, 'B-P': 0.5708489388264669, 'I-P': 0.8494287712753555, 'B-MC': 0.2838114754098361, 'I-MC': 0.41311668631082676}, 'recall': {'O': 0.8453252087810451, 'B-C': 0.45639288738357325, 'I-C': 0.5115746180963572, 'B-P': 0.6034312108215111, 'I-P': 0.6946706073028888, 'B-MC': 0.4686971235194585, 'I-MC': 0.5772941176470588}, 'f1': {'O': 0.8775893474914924, 'B-C': 0.34740573638414435, 'I-C': 0.4183945604382403, 'B-P': 0.5866880513231757, 'I-P': 0.7642943305186972, 'B-MC': 0.35354179961710275, 'I-MC': 0.481597801550692}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7008006425218984, 'recall': 0.7008006425218984, 'f1': 0.7008006425218984, 'support': None}, 'macro_avg': {'precision': 0.5234265336781704, 'recall': 0.5939122533645561, 'f1': 0.5470730896176492, 'support': None}, 'weighted_avg': {'precision': 0.7517345370292543, 'recall': 0.7008006425218984, 'f1': 0.7191277075925633, 'support': None}}
			------------EPOCH 12---------------
Loss:  tensor(0.4073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5251, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8131833034420067, 'B-C': 0.2191780821917808, 'I-C': 0.34615384615384615, 'B-P': 0.5067035539476484, 'I-P': 0.7110077114860556, 'B-MC': 0.3688118811881188, 'I-MC': 0.5549076773566569}, 'recall': {'O': 0.9003835586627132, 'B-C': 0.013547840812870448, 'I-C': 0.011104582843713278, 'B-P': 0.7855493236555592, 'I-P': 0.9352845838497473, 'B-MC': 0.2521150592216582, 'I-MC': 0.2687058823529412}, 'f1': {'O': 0.8545647010224104, 'B-C': 0.025518341307814992, 'I-C': 0.02151884321985654, 'B-P': 0.6160413971539457, 'I-P': 0.8078693600586332, 'B-MC': 0.29949748743718596, 'I-MC': 0.3620798985415345}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7292707209129166, 'recall': 0.7292707209129166, 'f1': 0.7292707209129166, 'support': None}, 'macro_avg': {'precision': 0.5028494365380162, 'recall': 0.4523844044856004, 'f1': 0.4267271469630544, 'support': None}, 'weighted_avg': {'precision': 0.6676465140229888, 'recall': 0.7292707209129166, 'f1': 0.6634511546377729, 'support': None}}
			------------EPOCH 13---------------
Loss:  tensor(1.2494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1323, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1498, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0997, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6929, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9331214161057093, 'B-C': 0.216696269982238, 'I-C': 0.26648681055155876, 'B-P': 0.597864768683274, 'I-P': 0.902175529015313, 'B-MC': 0.2977602108036891, 'I-MC': 0.40946666666666665}, 'recall': {'O': 0.814504502053807, 'B-C': 0.7231160033869602, 'I-C': 0.8357226792009401, 'B-P': 0.3325635103926097, 'I-P': 0.34712556011059204, 'B-MC': 0.3824027072758037, 'I-MC': 0.3612941176470588}, 'f1': {'O': 0.8697875059913724, 'B-C': 0.3334634908238969, 'I-C': 0.4041138701062561, 'B-P': 0.4273902904388382, 'I-P': 0.5013494161709627, 'B-MC': 0.33481481481481484, 'I-MC': 0.383875}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.5649674974274026, 'recall': 0.5649674974274026, 'f1': 0.5649674974274026, 'support': None}, 'macro_avg': {'precision': 0.5176530959726355, 'recall': 0.5423898685811102, 'f1': 0.46497062690659163, 'support': None}, 'weighted_avg': {'precision': 0.7686600479568745, 'recall': 0.5649674974274026, 'f1': 0.5881049796834421, 'support': None}}
			------------EPOCH 14---------------
Loss:  tensor(0.6216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1873, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0976, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4298, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8757219134793506, 'B-C': 0.3865546218487395, 'I-C': 0.5152013147082991, 'B-P': 0.5505356311131812, 'I-P': 0.7108249266652358, 'B-MC': 0.3380503144654088, 'I-MC': 0.4487256371814093}, 'recall': {'O': 0.8744593455020266, 'B-C': 0.03895004233700254, 'I-C': 0.036839012925969444, 'B-P': 0.7799406136588585, 'I-P': 0.9472018304890838, 'B-MC': 0.3637901861252115, 'I-MC': 0.35211764705882354}, 'f1': {'O': 0.87509017408703, 'B-C': 0.07076923076923076, 'I-C': 0.06876130942589241, 'B-P': 0.6454607508532424, 'I-P': 0.8121638191776342, 'B-MC': 0.3504482477587612, 'I-MC': 0.39459459459459456}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7367835420692886, 'recall': 0.7367835420692886, 'f1': 0.7367835420692888, 'support': None}, 'macro_avg': {'precision': 0.5465163370659464, 'recall': 0.4847569540138537, 'f1': 0.4596125895237694, 'support': None}, 'weighted_avg': {'precision': 0.7059333138812035, 'recall': 0.7367835420692886, 'f1': 0.6821321841449954, 'support': None}}
			------------EPOCH 15---------------
Loss:  tensor(0.4877, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0304, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1714, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1996, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3945, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.889631552781307, 'B-C': 0.3257328990228013, 'I-C': 0.3924963924963925, 'B-P': 0.5873391121618072, 'I-P': 0.7958020671102931, 'B-MC': 0.3169336384439359, 'I-MC': 0.4374735057227639}, 'recall': {'O': 0.876200320992356, 'B-C': 0.2540220152413209, 'I-C': 0.2716803760282021, 'B-P': 0.7377103266248762, 'I-P': 0.8573934598150443, 'B-MC': 0.4686971235194585, 'I-MC': 0.48564705882352943}, 'f1': {'O': 0.8828648567160496, 'B-C': 0.2854424357754519, 'I-C': 0.3210999618068817, 'B-P': 0.6539923954372624, 'I-P': 0.8254504401141819, 'B-MC': 0.37815699658703067, 'I-MC': 0.46030330062444247}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7424223410218441, 'recall': 0.7424223410218441, 'f1': 0.7424223410218441, 'support': None}, 'macro_avg': {'precision': 0.5350584525341858, 'recall': 0.5644786687206839, 'f1': 0.5439014838659001, 'support': None}, 'weighted_avg': {'precision': 0.7294516100975812, 'recall': 0.7424223410218441, 'f1': 0.7334311504906086, 'support': None}}
			------------EPOCH 16---------------
Loss:  tensor(0.2485, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0158, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0674, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0934, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1773, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4001, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9020070502615419, 'B-C': 0.2969043151969981, 'I-C': 0.35684495500109753, 'B-P': 0.5982824427480916, 'I-P': 0.8548452768729642, 'B-MC': 0.32882882882882886, 'I-MC': 0.4782355510263503}, 'recall': {'O': 0.863115802072849, 'B-C': 0.5359864521591872, 'I-C': 0.573090481786134, 'B-P': 0.6205872649290664, 'I-P': 0.720583468395462, 'B-MC': 0.37055837563451777, 'I-MC': 0.3864705882352941}, 'f1': {'O': 0.8821329774663942, 'B-C': 0.3821309990944763, 'I-C': 0.43982504396446775, 'B-P': 0.6092307692307692, 'I-P': 0.7819933162964419, 'B-MC': 0.34844868735083534, 'I-MC': 0.4274838961545969}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7135674187853993, 'recall': 0.7135674187853993, 'f1': 0.7135674187853993, 'support': None}, 'macro_avg': {'precision': 0.5451354885622675, 'recall': 0.5814846333160729, 'f1': 0.553035098508283, 'support': None}, 'weighted_avg': {'precision': 0.7570373796832965, 'recall': 0.7135674187853993, 'f1': 0.728383685708838, 'support': None}}
			------------EPOCH 17---------------
Loss:  tensor(0.2051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0621, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0602, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3411, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8934711734054114, 'B-C': 0.3156668608037274, 'I-C': 0.3842277181521232, 'B-P': 0.6142116498932602, 'I-P': 0.8291117730553168, 'B-MC': 0.3360128617363344, 'I-MC': 0.4898828541001065}, 'recall': {'O': 0.872228720655042, 'B-C': 0.45893310753598643, 'I-C': 0.4837837837837838, 'B-P': 0.6644671725503134, 'I-P': 0.7907903517971208, 'B-MC': 0.3536379018612521, 'I-MC': 0.3788235294117647}, 'f1': {'O': 0.8827221671622068, 'B-C': 0.37405106970324364, 'I-C': 0.428296488946684, 'B-P': 0.638351822503962, 'I-P': 0.8094977846309996, 'B-MC': 0.34460016488046163, 'I-MC': 0.42725403038545745}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7341816630273825, 'recall': 0.7341816630273825, 'f1': 0.7341816630273825, 'support': None}, 'macro_avg': {'precision': 0.5517978415923257, 'recall': 0.5718092239421805, 'f1': 0.5578247897447164, 'support': None}, 'weighted_avg': {'precision': 0.7484734452807628, 'recall': 0.7341816630273825, 'f1': 0.7396145185431569, 'support': None}}
			------------EPOCH 18---------------
Loss:  tensor(0.1246, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0080, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0338, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0494, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0550, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2821, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8878772830105391, 'B-C': 0.33006244424620873, 'I-C': 0.40757254586653024, 'B-P': 0.5855280659749933, 'I-P': 0.7793446281830172, 'B-MC': 0.3838383838383838, 'I-MC': 0.5427728613569321}, 'recall': {'O': 0.8754386442153369, 'B-C': 0.31329381879762913, 'I-C': 0.327614571092832, 'B-P': 0.7261629825140218, 'I-P': 0.8788635713604729, 'B-MC': 0.32148900169204736, 'I-MC': 0.3247058823529412}, 'f1': {'O': 0.8816140917994165, 'B-C': 0.32145960034752386, 'I-C': 0.36324549688935215, 'B-P': 0.6483063328424152, 'I-P': 0.8261177377293054, 'B-MC': 0.3499079189686924, 'I-MC': 0.4063305115936695}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7476930284700783, 'recall': 0.7476930284700783, 'f1': 0.7476930284700783, 'support': None}, 'macro_avg': {'precision': 0.5595708874966577, 'recall': 0.5382240674321831, 'f1': 0.542425955738625, 'support': None}, 'weighted_avg': {'precision': 0.7316536378407289, 'recall': 0.7476930284700783, 'f1': 0.7355743288442221, 'support': None}}
			------------EPOCH 19---------------
Loss:  tensor(0.0911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0334, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0258, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2691, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8826270609074806, 'B-C': 0.3320079522862823, 'I-C': 0.40772316950852555, 'B-P': 0.5654252642174132, 'I-P': 0.7698704121453623, 'B-MC': 0.3881856540084388, 'I-MC': 0.5451440768409819}, 'recall': {'O': 0.8810424090748348, 'B-C': 0.28281117696867064, 'I-C': 0.2866039952996475, 'B-P': 0.7413394919168591, 'I-P': 0.891505386595481, 'B-MC': 0.311336717428088, 'I-MC': 0.3004705882352941}, 'f1': {'O': 0.8818340230886517, 'B-C': 0.3054412437128487, 'I-C': 0.33659950317416504, 'B-P': 0.641541755888651, 'I-P': 0.8262352442213897, 'B-MC': 0.34553990610328633, 'I-MC': 0.38740993553280245}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7474336771829431, 'recall': 0.7474336771829431, 'f1': 0.7474336771829431, 'support': None}, 'macro_avg': {'precision': 0.555854798559212, 'recall': 0.5278728236455535, 'f1': 0.532085944531685, 'support': None}, 'weighted_avg': {'precision': 0.7256030188337469, 'recall': 0.7474336771829431, 'f1': 0.7302024542783444, 'support': None}}
			------------EPOCH 20---------------
Loss:  tensor(0.0691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0237, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1273, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2502, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8788091446462792, 'B-C': 0.3161764705882353, 'I-C': 0.3969121140142518, 'B-P': 0.5624056366381479, 'I-P': 0.7806022682831443, 'B-MC': 0.3563636363636364, 'I-MC': 0.5181499907868067}, 'recall': {'O': 0.8856940779630587, 'B-C': 0.29127857747671465, 'I-C': 0.2945358401880141, 'B-P': 0.7373804025074233, 'I-P': 0.8753551339498522, 'B-MC': 0.3316412859560068, 'I-MC': 0.3308235294117647}, 'f1': {'O': 0.8822381791085219, 'B-C': 0.30321727633318646, 'I-C': 0.3381450252951096, 'B-P': 0.6381156316916488, 'I-P': 0.8252678507226575, 'B-MC': 0.34355828220858897, 'I-MC': 0.4038199181446112}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7451497126220415, 'recall': 0.7451497126220415, 'f1': 0.7451497126220415, 'support': None}, 'macro_avg': {'precision': 0.5442027516172144, 'recall': 0.5352441210646905, 'f1': 0.5334803090720464, 'support': None}, 'weighted_avg': {'precision': 0.7252882131881605, 'recall': 0.7451497126220415, 'f1': 0.7311706681717597, 'support': None}}
			------------EPOCH 21---------------
Loss:  tensor(0.0557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2326, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8824951118835542, 'B-C': 0.3130044843049327, 'I-C': 0.395831707126688, 'B-P': 0.5670419651995906, 'I-P': 0.7841031886245519, 'B-MC': 0.3497536945812808, 'I-MC': 0.5051165911759772}, 'recall': {'O': 0.884007507956802, 'B-C': 0.2955122777307367, 'I-C': 0.2979435957696827, 'B-P': 0.7311118442758165, 'I-P': 0.8716560205930022, 'B-MC': 0.3604060913705584, 'I-MC': 0.35423529411764704}, 'f1': {'O': 0.8832506624991506, 'B-C': 0.304006968641115, 'I-C': 0.3399818980255439, 'B-P': 0.638708747658164, 'I-P': 0.8255648059523594, 'B-MC': 0.3550000000000001, 'I-MC': 0.41643039900421824}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7451831773042525, 'recall': 0.7451831773042525, 'f1': 0.7451831773042524, 'support': None}, 'macro_avg': {'precision': 0.5424781061280822, 'recall': 0.5421246616877494, 'f1': 0.5375633545400788, 'support': None}, 'weighted_avg': {'precision': 0.7269307711236571, 'recall': 0.7451831773042525, 'f1': 0.7328500831793994, 'support': None}}
			------------EPOCH 22---------------
Loss:  tensor(0.0453, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0269, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2191, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8895324896368079, 'B-C': 0.314410480349345, 'I-C': 0.39488939740655987, 'B-P': 0.5723547717842323, 'I-P': 0.7809382766486229, 'B-MC': 0.36741767764298094, 'I-MC': 0.5190543401552575}, 'recall': {'O': 0.8814504502053807, 'B-C': 0.3048264182895851, 'I-C': 0.30417156286721503, 'B-P': 0.7281425272187397, 'I-P': 0.8747640385165412, 'B-MC': 0.3587140439932318, 'I-MC': 0.34611764705882353}, 'f1': {'O': 0.8854730283653058, 'B-C': 0.3095442820292348, 'I-C': 0.34364420843013604, 'B-P': 0.6409176709742993, 'I-P': 0.8251926864584365, 'B-MC': 0.363013698630137, 'I-MC': 0.4153020892151327}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7460783575533971, 'recall': 0.7460783575533971, 'f1': 0.7460783575533971, 'support': None}, 'macro_avg': {'precision': 0.5483710619462581, 'recall': 0.5425980983070738, 'f1': 0.5404410948718117, 'support': None}, 'weighted_avg': {'precision': 0.728799380431633, 'recall': 0.7460783575533971, 'f1': 0.7339618918969396, 'support': None}}
			------------EPOCH 23---------------
Loss:  tensor(0.0364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0121, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0217, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2018, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8938341954579403, 'B-C': 0.3156059285091543, 'I-C': 0.3959471766848816, 'B-P': 0.5744125326370757, 'I-P': 0.7804716548668059, 'B-MC': 0.36787564766839376, 'I-MC': 0.5230555072211589}, 'recall': {'O': 0.879002203422105, 'B-C': 0.3065198983911939, 'I-C': 0.3065217391304348, 'B-P': 0.7258330583965688, 'I-P': 0.8765182572218515, 'B-MC': 0.3604060913705584, 'I-MC': 0.3536470588235294}, 'f1': {'O': 0.886356155365372, 'B-C': 0.31099656357388317, 'I-C': 0.34554245595443106, 'B-P': 0.6413059320798716, 'I-P': 0.8257113090961347, 'B-MC': 0.3641025641025641, 'I-MC': 0.42198357548957677}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7469317069497778, 'recall': 0.7469317069497778, 'f1': 0.7469317069497778, 'support': None}, 'macro_avg': {'precision': 0.5501718061493444, 'recall': 0.5440640438223203, 'f1': 0.5422855079516905, 'support': None}, 'weighted_avg': {'precision': 0.7304190368282159, 'recall': 0.7469317069497778, 'f1': 0.7352360603873412, 'support': None}}
			------------EPOCH 24---------------
Loss:  tensor(0.0303, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1000, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1897, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8991542511482021, 'B-C': 0.3036734693877551, 'I-C': 0.3845771497550238, 'B-P': 0.5782620249800691, 'I-P': 0.7812042864432727, 'B-MC': 0.37272727272727274, 'I-MC': 0.5297597042513863}, 'recall': {'O': 0.8733984385626071, 'B-C': 0.31498729889923793, 'I-C': 0.318213866039953, 'B-P': 0.7179148795776972, 'I-P': 0.875717418247688, 'B-MC': 0.34686971235194586, 'I-MC': 0.3371764705882353}, 'f1': {'O': 0.8860892243580014, 'B-C': 0.3092269326683292, 'I-C': 0.3482622255087933, 'B-P': 0.6405652045922873, 'I-P': 0.82576527172203, 'B-MC': 0.3593339176161262, 'I-MC': 0.41207764198418406}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.745166444963147, 'recall': 0.745166444963147, 'f1': 0.745166444963147, 'support': None}, 'macro_avg': {'precision': 0.5499083083847116, 'recall': 0.5406111548953377, 'f1': 0.5401886312071074, 'support': None}, 'weighted_avg': {'precision': 0.7312381195123119, 'recall': 0.745166444963147, 'f1': 0.7348006356200021, 'support': None}}
			------------EPOCH 25---------------
Loss:  tensor(0.0263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0173, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1838, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8947251711616819, 'B-C': 0.3336457357075914, 'I-C': 0.413290113452188, 'B-P': 0.573753280839895, 'I-P': 0.7815186003057585, 'B-MC': 0.3483483483483483, 'I-MC': 0.5078369905956113}, 'recall': {'O': 0.8780773101928674, 'B-C': 0.30143945808636746, 'I-C': 0.299647473560517, 'B-P': 0.721214120752227, 'I-P': 0.8772618934121461, 'B-MC': 0.3925549915397631, 'I-MC': 0.4002352941176471}, 'f1': {'O': 0.886323073121173, 'B-C': 0.31672597864768687, 'I-C': 0.3474114441416894, 'B-P': 0.6390878526531208, 'I-P': 0.8266271391995689, 'B-MC': 0.3691328560063643, 'I-MC': 0.4476610303309429}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7492993332162069, 'recall': 0.7492993332162069, 'f1': 0.7492993332162069, 'support': None}, 'macro_avg': {'precision': 0.5504454629158678, 'recall': 0.5529186488087908, 'f1': 0.5475670534429352, 'support': None}, 'weighted_avg': {'precision': 0.7326046636640423, 'recall': 0.7492993332162069, 'f1': 0.7377450704306712, 'support': None}}
			------------EPOCH 26---------------
Loss:  tensor(0.0233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0659, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2866, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9107251411202779, 'B-C': 0.29328358208955224, 'I-C': 0.36648955887804274, 'B-P': 0.5795787789922687, 'I-P': 0.773396865876984, 'B-MC': 0.4318181818181818, 'I-MC': 0.5918037206794284}, 'recall': {'O': 0.8558254672070945, 'B-C': 0.3327688399661304, 'I-C': 0.34853113983548767, 'B-P': 0.7172550313427911, 'I-P': 0.8789398417389647, 'B-MC': 0.2893401015228426, 'I-MC': 0.25823529411764706}, 'f1': {'O': 0.8824222365579334, 'B-C': 0.31178103927013084, 'I-C': 0.3572848280431248, 'B-P': 0.641108817457977, 'I-P': 0.822797576017207, 'B-MC': 0.34650455927051677, 'I-MC': 0.35957080842001804}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7397535326155159, 'recall': 0.7397535326155159, 'f1': 0.7397535326155159, 'support': None}, 'macro_avg': {'precision': 0.563870832779248, 'recall': 0.5258422451044226, 'f1': 0.5316385521481297, 'support': None}, 'weighted_avg': {'precision': 0.7334305917103654, 'recall': 0.7397535326155159, 'f1': 0.729897186329801, 'support': None}}
			------------EPOCH 27---------------
Loss:  tensor(0.0335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0213, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0199, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0160, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2783, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2840, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8992042440318302, 'B-C': 0.2960062646828504, 'I-C': 0.3678362573099415, 'B-P': 0.5755377040684115, 'I-P': 0.7749873673572512, 'B-MC': 0.42, 'I-MC': 0.57733860342556}, 'recall': {'O': 0.8668425777318354, 'B-C': 0.32006773920406434, 'I-C': 0.33260869565217394, 'B-P': 0.7327614648630815, 'I-P': 0.8773190961960149, 'B-MC': 0.28426395939086296, 'I-MC': 0.25776470588235295}, 'f1': {'O': 0.8827269075748971, 'B-C': 0.307567127746135, 'I-C': 0.3493366244986115, 'B-P': 0.6447024673439767, 'I-P': 0.8229843938648661, 'B-MC': 0.33905146316851664, 'I-MC': 0.35640504270028467}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7403726292364197, 'recall': 0.7403726292364197, 'f1': 0.7403726292364197, 'support': None}, 'macro_avg': {'precision': 0.5587014915536921, 'recall': 0.5245183198457694, 'f1': 0.528967718128184, 'support': None}, 'weighted_avg': {'precision': 0.7296143120419263, 'recall': 0.7403726292364197, 'f1': 0.7287286095311, 'support': None}}
			------------EPOCH 28---------------
Loss:  tensor(0.0599, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0368, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2147, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8640431692550671, 'B-C': 0.30823737821080605, 'I-C': 0.39161714106975287, 'B-P': 0.5587934560327198, 'I-P': 0.791031704326502, 'B-MC': 0.34890965732087226, 'I-MC': 0.4780863164938106}, 'recall': {'O': 0.8929300073447404, 'B-C': 0.29466553767993225, 'I-C': 0.2942420681551116, 'B-P': 0.721214120752227, 'I-P': 0.8610925731718944, 'B-MC': 0.3790186125211506, 'I-MC': 0.3362352941176471}, 'f1': {'O': 0.8782491204131048, 'B-C': 0.30129870129870134, 'I-C': 0.33601717659688674, 'B-P': 0.6296989773872966, 'I-P': 0.8245766193454147, 'B-MC': 0.3633414436334145, 'I-MC': 0.3948059124188424}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7413180065088807, 'recall': 0.7413180065088807, 'f1': 0.7413180065088807, 'support': None}, 'macro_avg': {'precision': 0.5343884032442187, 'recall': 0.5399140305346719, 'f1': 0.5325697072990945, 'support': None}, 'weighted_avg': {'precision': 0.721513130921971, 'recall': 0.7413180065088807, 'f1': 0.7285619847752227, 'support': None}}
			------------EPOCH 29---------------
Loss:  tensor(0.0302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0143, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0125, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1958, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8782322646749535, 'B-C': 0.289195775792039, 'I-C': 0.3784492173279942, 'B-P': 0.5962559374126851, 'I-P': 0.8093766767192733, 'B-MC': 0.34062140391254314, 'I-MC': 0.4609644726584252}, 'recall': {'O': 0.8860205108674954, 'B-C': 0.30143945808636746, 'I-C': 0.3054054054054054, 'B-P': 0.7040580666446717, 'I-P': 0.8341309943750596, 'B-MC': 0.5008460236886633, 'I-MC': 0.4869411764705882}, 'f1': {'O': 0.8821091972700683, 'B-C': 0.29519071310116085, 'I-C': 0.3380263371809462, 'B-P': 0.6456883509833585, 'I-P': 0.8215674122485773, 'B-MC': 0.4054794520547945, 'I-MC': 0.473596887693804}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7399041236854654, 'recall': 0.7399041236854654, 'f1': 0.7399041236854654, 'support': None}, 'macro_avg': {'precision': 0.5361565354997019, 'recall': 0.5741202336483217, 'f1': 0.55166547864753, 'support': None}, 'weighted_avg': {'precision': 0.7315543424273431, 'recall': 0.7399041236854654, 'f1': 0.7348713778296988, 'support': None}}
			------------EPOCH 30---------------
Loss:  tensor(0.0307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1863, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9025717669618183, 'B-C': 0.2908082408874802, 'I-C': 0.3774286895411327, 'B-P': 0.6086833944178178, 'I-P': 0.8015236857307915, 'B-MC': 0.36573511543134873, 'I-MC': 0.48587173173877357}, 'recall': {'O': 0.8706781643589674, 'B-C': 0.3107535986452159, 'I-C': 0.3218566392479436, 'B-P': 0.7123061695809964, 'I-P': 0.8465630660692154, 'B-MC': 0.5093062605752962, 'I-MC': 0.4875294117647059}, 'f1': {'O': 0.8863381471276464, 'B-C': 0.3004502660663119, 'I-C': 0.34743451512653006, 'B-P': 0.6564305259957433, 'I-P': 0.8234279514452367, 'B-MC': 0.4257425742574258, 'I-MC': 0.4866991602560338}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7433677182943051, 'recall': 0.7433677182943051, 'f1': 0.743367718294305, 'support': None}, 'macro_avg': {'precision': 0.5475175178155947, 'recall': 0.5798561871774773, 'f1': 0.5609318771821327, 'support': None}, 'weighted_avg': {'precision': 0.7376754577834072, 'recall': 0.7433677182943051, 'f1': 0.7396842640667808, 'support': None}}
	Data split: 21k
			------------EPOCH 1---------------
Loss:  tensor(4.4221, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.0092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0226, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 1.0, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.0, 'I-P': 0.43994161514650737, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.008704877451647126, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.0, 'I-P': 1.0, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.01725951295811871, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.0, 'I-P': 0.61105479627623, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.44144098921600616, 'recall': 0.44144098921600616, 'f1': 0.44144098921600616, 'support': None}, 'macro_avg': {'precision': 0.20570594502092962, 'recall': 0.14410069677880674, 'f1': 0.08975918703347839, 'support': None}, 'weighted_avg': {'precision': 0.5005792569699284, 'recall': 0.44144098921600616, 'f1': 0.2734168757921533, 'support': None}}
			------------EPOCH 2---------------
Loss:  tensor(3.2391, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7200, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8769781628503227, 'B-C': 0.0, 'I-C': 0.16290726817042606, 'B-P': 0.2830065359477124, 'I-P': 0.5468039597149521, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.5396751992600854, 'B-C': 0.0, 'I-C': 0.00763807285546416, 'B-P': 0.2857142857142857, 'I-P': 0.970025741252741, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.6681710253776334, 'B-C': 0.0, 'I-C': 0.014591985632506453, 'B-P': 0.284353964866196, 'I-P': 0.6993717435833985, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.5999213579968041, 'recall': 0.5999213579968041, 'f1': 0.5999213579968041, 'support': None}, 'macro_avg': {'precision': 0.26709941809763044, 'recall': 0.25757904272608234, 'f1': 0.23806981706567631, 'support': None}, 'weighted_avg': {'precision': 0.5400045380326911, 'recall': 0.5999213579968041, 'f1': 0.5216426023735932, 'support': None}}
			------------EPOCH 3---------------
Loss:  tensor(2.8655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3577, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5203, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2344, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5035, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8696578518611355, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.3991760128175784, 'I-P': 0.6123211924510158, 'B-MC': 0.0, 'I-MC': 0.2708333333333333}, 'recall': {'O': 0.7550393079622426, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.5753876608380073, 'I-P': 0.9712842024978549, 'B-MC': 0.0, 'I-MC': 0.0015294117647058824}, 'f1': {'O': 0.8083055462527484, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.4713513513513514, 'I-P': 0.7511188115162016, 'B-MC': 0.0, 'I-MC': 0.003041647168928404}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6730751533100754, 'recall': 0.6730751533100754, 'f1': 0.6730751533100754, 'support': None}, 'macro_avg': {'precision': 0.3074269129232947, 'recall': 0.3290343690089729, 'f1': 0.2905453366127471, 'support': None}, 'weighted_avg': {'precision': 0.5655084796036455, 'recall': 0.6730751533100754, 'f1': 0.5903259142354268, 'support': None}}
			------------EPOCH 4---------------
Loss:  tensor(2.4254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1936, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2433, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9404, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0758, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3742, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8287231574334253, 'B-C': 0.16666666666666666, 'I-C': 0.23764093668690373, 'B-P': 0.4866573033707865, 'I-P': 0.6886575204812215, 'B-MC': 0.20707070707070707, 'I-MC': 0.44606281292671823}, 'recall': {'O': 0.874486548244063, 'B-C': 0.016088060965283656, 'I-C': 0.03219741480611046, 'B-P': 0.6859122401847575, 'I-P': 0.9408523214796454, 'B-MC': 0.06937394247038917, 'I-MC': 0.11529411764705882}, 'f1': {'O': 0.8509900465904279, 'B-C': 0.02934362934362934, 'I-C': 0.05671116630446031, 'B-P': 0.5693550595645626, 'I-P': 0.7952391696750903, 'B-MC': 0.10392902408111532, 'I-MC': 0.1832289426942133}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7124379857607778, 'recall': 0.7124379857607778, 'f1': 0.7124379857607777, 'support': None}, 'macro_avg': {'precision': 0.43735415780520415, 'recall': 0.3906006636853297, 'f1': 0.3698281483219284, 'support': None}, 'weighted_avg': {'precision': 0.6376008224955031, 'recall': 0.7124379857607778, 'f1': 0.6469896467363613, 'support': None}}
			------------EPOCH 5---------------
Loss:  tensor(2.1981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1701, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9715, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2398, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8802331743508214, 'B-C': 0.13636363636363635, 'I-C': 0.15208333333333332, 'B-P': 0.487892948173322, 'I-P': 0.6645162134575624, 'B-MC': 0.22285714285714286, 'I-MC': 0.4792004321988115}, 'recall': {'O': 0.8584913359266614, 'B-C': 0.005080440304826418, 'I-C': 0.004289071680376028, 'B-P': 0.7578356977895084, 'I-P': 0.9682715225474307, 'B-MC': 0.06598984771573604, 'I-MC': 0.10435294117647059}, 'f1': {'O': 0.8692263199933897, 'B-C': 0.009795918367346938, 'I-C': 0.008342857142857143, 'B-P': 0.5936167463496576, 'I-P': 0.7881393417815821, 'B-MC': 0.10182767624020889, 'I-MC': 0.17138440730364218}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7164955784788629, 'recall': 0.7164955784788629, 'f1': 0.7164955784788629, 'support': None}, 'macro_avg': {'precision': 0.43187812581923285, 'recall': 0.3949015510201442, 'f1': 0.3631904667398121, 'support': None}, 'weighted_avg': {'precision': 0.6328340745426049, 'recall': 0.7164955784788629, 'f1': 0.6421651725865696, 'support': None}}
			------------EPOCH 6---------------
Loss:  tensor(1.9335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1532, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0589, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4702, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8713, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1513, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9073147904419292, 'B-C': 0.23, 'I-C': 0.27983383685800606, 'B-P': 0.5622421742295559, 'I-P': 0.7177642742157702, 'B-MC': 0.3374233128834356, 'I-MC': 0.46701760157920713}, 'recall': {'O': 0.843883463453116, 'B-C': 0.07790008467400508, 'I-C': 0.08707403055229142, 'B-P': 0.7644341801385681, 'I-P': 0.9436933930784631, 'B-MC': 0.27918781725888325, 'I-MC': 0.334}, 'f1': {'O': 0.8744503326192355, 'B-C': 0.11638203668564201, 'I-C': 0.13281950170281412, 'B-P': 0.6479306487695748, 'I-P': 0.8153676337336695, 'B-MC': 0.3055555555555556, 'I-MC': 0.3894642979628232}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7312786018455772, 'recall': 0.7312786018455772, 'f1': 0.7312786018455772, 'support': None}, 'macro_avg': {'precision': 0.5002279986011291, 'recall': 0.4757389955936181, 'f1': 0.46885285814704497, 'support': None}, 'weighted_avg': {'precision': 0.6852276108511929, 'recall': 0.7312786018455772, 'f1': 0.6923890185254086, 'support': None}}
			------------EPOCH 7---------------
Loss:  tensor(1.6859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1301, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8233, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9729, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3569, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2698, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7598, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9924, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8983699503897945, 'B-C': 0.3014018691588785, 'I-C': 0.36911419808767815, 'B-P': 0.6267370761534186, 'I-P': 0.7729013593701202, 'B-MC': 0.3486394557823129, 'I-MC': 0.4635752503772808}, 'recall': {'O': 0.8620548951334295, 'B-C': 0.21845893310753597, 'I-C': 0.24042303172737955, 'B-P': 0.743978884856483, 'I-P': 0.8965773667651826, 'B-MC': 0.34686971235194586, 'I-MC': 0.3975294117647059}, 'f1': {'O': 0.8798378588483537, 'B-C': 0.2533136966126656, 'I-C': 0.2911833772148296, 'B-P': 0.6803439432795294, 'I-P': 0.8301583658480606, 'B-MC': 0.3477523324851569, 'I-MC': 0.42801950725188426}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7437525621397317, 'recall': 0.7437525621397317, 'f1': 0.7437525621397318, 'support': None}, 'macro_avg': {'precision': 0.5401055941884977, 'recall': 0.5294131765295232, 'f1': 0.53008701164864, 'support': None}, 'weighted_avg': {'precision': 0.7215332214087741, 'recall': 0.7437525621397317, 'f1': 0.7282106393774048, 'support': None}}
			------------EPOCH 8---------------
Loss:  tensor(1.4421, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6853, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8124, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7906, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1434, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8898, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9093803363144337, 'B-C': 0.3470790378006873, 'I-C': 0.3738074588031223, 'B-P': 0.6250335030822836, 'I-P': 0.7616070303641175, 'B-MC': 0.37427745664739887, 'I-MC': 0.4735902926481085}, 'recall': {'O': 0.8547101547836022, 'B-C': 0.1710414902624894, 'I-C': 0.177262044653349, 'B-P': 0.7693830419003629, 'I-P': 0.922089808370674, 'B-MC': 0.43824027072758037, 'I-MC': 0.4683529411764706}, 'f1': {'O': 0.8811981153242091, 'B-C': 0.22915484968803176, 'I-C': 0.2404846359252322, 'B-P': 0.6897367642709258, 'I-P': 0.8342001535263626, 'B-MC': 0.40374123148869834, 'I-MC': 0.47095705666627236}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7493578964100762, 'recall': 0.7493578964100762, 'f1': 0.7493578964100762, 'support': None}, 'macro_avg': {'precision': 0.5521107308085932, 'recall': 0.5430113931249326, 'f1': 0.5356389724128189, 'support': None}, 'weighted_avg': {'precision': 0.7218792640731766, 'recall': 0.7493578964100762, 'f1': 0.7265129761985014, 'support': None}}
			------------EPOCH 9---------------
Loss:  tensor(1.1624, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8499, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7940, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8702148515113783, 'B-C': 0.375, 'I-C': 0.42695099818511795, 'B-P': 0.6165531691985333, 'I-P': 0.754948921855865, 'B-MC': 0.3445378151260504, 'I-MC': 0.461519146264909}, 'recall': {'O': 0.8935556704115775, 'B-C': 0.11685012701100762, 'I-C': 0.11057579318448883, 'B-P': 0.7766413724843286, 'I-P': 0.928610925731719, 'B-MC': 0.41624365482233505, 'I-MC': 0.4324705882352941}, 'f1': {'O': 0.8817308208514522, 'B-C': 0.17817947062621048, 'I-C': 0.1756580175471346, 'B-P': 0.6873996203825377, 'I-P': 0.8328231612428819, 'B-MC': 0.37701149425287356, 'I-MC': 0.4465229274218039}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7516585933120833, 'recall': 0.7516585933120833, 'f1': 0.7516585933120833, 'support': None}, 'macro_avg': {'precision': 0.5499607003059792, 'recall': 0.5249925902686787, 'f1': 0.5113322160464134, 'support': None}, 'weighted_avg': {'precision': 0.7135352307815116, 'recall': 0.7516585933120833, 'f1': 0.7144091704584931, 'support': None}}
			------------EPOCH 10---------------
Loss:  tensor(1.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0655, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4903, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7843, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7168, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5349, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6828, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9016073900392666, 'B-C': 0.41379310344827586, 'I-C': 0.45655926352128884, 'B-P': 0.6191099476439791, 'I-P': 0.7551225391723584, 'B-MC': 0.35036496350364965, 'I-MC': 0.4694403035641686}, 'recall': {'O': 0.8682027148336552, 'B-C': 0.20321761219305673, 'I-C': 0.1864864864864865, 'B-P': 0.7802705377763115, 'I-P': 0.9317761464391267, 'B-MC': 0.40609137055837563, 'I-MC': 0.40752941176470586}, 'f1': {'O': 0.8845898004434589, 'B-C': 0.272572402044293, 'I-C': 0.26480894376772907, 'B-P': 0.6904101591008612, 'I-P': 0.8341996773615343, 'B-MC': 0.3761755485893417, 'I-MC': 0.4362995150828138}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7551807511147922, 'recall': 0.7551807511147922, 'f1': 0.7551807511147923, 'support': None}, 'macro_avg': {'precision': 0.5665710729847124, 'recall': 0.5405106114359597, 'f1': 0.5370080066271474, 'support': None}, 'weighted_avg': {'precision': 0.7285223642586115, 'recall': 0.7551807511147922, 'f1': 0.7288646502750266, 'support': None}}
			------------EPOCH 11---------------
Loss:  tensor(0.6835, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0407, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6197, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5541, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6643, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9576682859125607, 'B-C': 0.3559077809798271, 'I-C': 0.40729400185904097, 'B-P': 0.650221565731167, 'I-P': 0.7949203425101491, 'B-MC': 0.2648221343873518, 'I-MC': 0.3983297022512709}, 'recall': {'O': 0.7507956802045647, 'B-C': 0.4182895850973751, 'I-C': 0.43766157461809635, 'B-P': 0.7261629825140218, 'I-P': 0.8886071122127943, 'B-MC': 0.3401015228426396, 'I-MC': 0.3871764705882353}, 'f1': {'O': 0.8417072017810036, 'B-C': 0.3845854418061503, 'I-C': 0.42193208530403015, 'B-P': 0.6860972568578554, 'I-P': 0.8391569356537709, 'B-MC': 0.2977777777777778, 'I-MC': 0.39267390526190193}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7348760551832609, 'recall': 0.7348760551832609, 'f1': 0.7348760551832609, 'support': None}, 'macro_avg': {'precision': 0.5470234019473382, 'recall': 0.564113561153961, 'f1': 0.5519900863489271, 'support': None}, 'weighted_avg': {'precision': 0.750947854818867, 'recall': 0.7348760551832609, 'f1': 0.7377317561479653, 'support': None}}
			------------EPOCH 12---------------
Loss:  tensor(0.6629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2187, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3362, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2938, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5186, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5860, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6882, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6733, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.879525542525947, 'B-C': 0.287343834872352, 'I-C': 0.34237216210481647, 'B-P': 0.6964285714285714, 'I-P': 0.8966356918943126, 'B-MC': 0.24476987447698745, 'I-MC': 0.3495731360273193}, 'recall': {'O': 0.8875166616794973, 'B-C': 0.4479254868755292, 'I-C': 0.4740305522914219, 'B-P': 0.5275486638073243, 'I-P': 0.6108303937458289, 'B-MC': 0.5939086294416244, 'I-MC': 0.7225882352941176}, 'f1': {'O': 0.8835030329289428, 'B-C': 0.35009927200529456, 'I-C': 0.3975853147714673, 'B-P': 0.6003379012577436, 'I-P': 0.726639674276706, 'B-MC': 0.3466666666666667, 'I-MC': 0.471192942079018}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6805879744664475, 'recall': 0.6805879744664475, 'f1': 0.6805879744664475, 'support': None}, 'macro_avg': {'precision': 0.5280926876186152, 'recall': 0.6091926604479063, 'f1': 0.5394321148551199, 'support': None}, 'weighted_avg': {'precision': 0.7592277208899086, 'recall': 0.6805879744664475, 'f1': 0.701060714930897, 'support': None}}
			------------EPOCH 13---------------
Loss:  tensor(0.9516, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0473, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2324, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2661, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3979, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6361, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7271, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9282392823928239, 'B-C': 0.2842696629213483, 'I-C': 0.33548268238761975, 'B-P': 0.6081930133199296, 'I-P': 0.7501914887098257, 'B-MC': 0.3867735470941884, 'I-MC': 0.5234341712824883}, 'recall': {'O': 0.8416800413481679, 'B-C': 0.21422523285351397, 'I-C': 0.21398354876615747, 'B-P': 0.7984163642362256, 'I-P': 0.9337591762799123, 'B-MC': 0.32656514382402707, 'I-MC': 0.28905882352941176}, 'f1': {'O': 0.8828430393471625, 'B-C': 0.24432641236117816, 'I-C': 0.26130004304778304, 'B-P': 0.6904422253922967, 'I-P': 0.8319699633886326, 'B-MC': 0.3541284403669725, 'I-MC': 0.37244201909959074}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7435601402170184, 'recall': 0.7435601402170184, 'f1': 0.7435601402170184, 'support': None}, 'macro_avg': {'precision': 0.5452262640154605, 'recall': 0.5168126186910594, 'f1': 0.519636020429088, 'support': None}, 'weighted_avg': {'precision': 0.7197721160319532, 'recall': 0.7435601402170184, 'f1': 0.7219211352960131, 'support': None}}
			------------EPOCH 14---------------
Loss:  tensor(0.5211, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0278, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2003, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5573, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8993175008323161, 'B-C': 0.3929824561403509, 'I-C': 0.47471464207423086, 'B-P': 0.6740646797717185, 'I-P': 0.8418653782203008, 'B-MC': 0.2720763723150358, 'I-MC': 0.3830241460541814}, 'recall': {'O': 0.8817768831098175, 'B-C': 0.3793395427603726, 'I-C': 0.3689776733254994, 'B-P': 0.7014186737050478, 'I-P': 0.8206120697873963, 'B-MC': 0.5786802030456852, 'I-MC': 0.6121176470588235}, 'f1': {'O': 0.8904608199986265, 'B-C': 0.3860404997845756, 'I-C': 0.4152203378624087, 'B-P': 0.6874696847210995, 'I-P': 0.8311028715987873, 'B-MC': 0.37012987012987014, 'I-MC': 0.471200869407716}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7517087903353997, 'recall': 0.7517087903353997, 'f1': 0.7517087903353997, 'support': None}, 'macro_avg': {'precision': 0.5625778822011621, 'recall': 0.6204175275418061, 'f1': 0.5788035647861548, 'support': None}, 'weighted_avg': {'precision': 0.7631184760146276, 'recall': 0.7517087903353997, 'f1': 0.7542275016375413, 'support': None}}
			------------EPOCH 15---------------
Loss:  tensor(0.3004, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0204, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1414, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1917, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2578, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3900, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3788, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7236, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9074163153278062, 'B-C': 0.41658722592945663, 'I-C': 0.4757037270011008, 'B-P': 0.6284302963776071, 'I-P': 0.7811072358402515, 'B-MC': 0.40076335877862596, 'I-MC': 0.5403319181783095}, 'recall': {'O': 0.872364734365224, 'B-C': 0.37002540220152413, 'I-C': 0.3554641598119859, 'B-P': 0.7555262289673376, 'I-P': 0.9095814662980265, 'B-MC': 0.3553299492385787, 'I-MC': 0.32941176470588235}, 'f1': {'O': 0.8895453662866494, 'B-C': 0.39192825112107627, 'I-C': 0.40688681148698636, 'B-P': 0.6861423220973784, 'I-P': 0.8404630184291202, 'B-MC': 0.3766816143497758, 'I-MC': 0.409296886420114}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7659982096395017, 'recall': 0.7659982096395017, 'f1': 0.7659982096395016, 'support': None}, 'macro_avg': {'precision': 0.5929057253475939, 'recall': 0.563957672226937, 'f1': 0.5715634671701572, 'support': None}, 'weighted_avg': {'precision': 0.7499904774294374, 'recall': 0.7659982096395017, 'f1': 0.7525209844856902, 'support': None}}
			------------EPOCH 16---------------
Loss:  tensor(0.2242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1035, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1247, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1766, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2795, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3389, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4022, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8962958861635568, 'B-C': 0.3886255924170616, 'I-C': 0.4615893164088325, 'B-P': 0.6749179838950193, 'I-P': 0.8227651665523837, 'B-MC': 0.38514442916093533, 'I-MC': 0.5174936809897566}, 'recall': {'O': 0.880715976170398, 'B-C': 0.4165961049957663, 'I-C': 0.41022326674500587, 'B-P': 0.7466182777961069, 'I-P': 0.8694060444274955, 'B-MC': 0.47377326565143824, 'I-MC': 0.4576470588235294}, 'f1': {'O': 0.8884376329185133, 'B-C': 0.40212505108295876, 'I-C': 0.43439308156535805, 'B-P': 0.7089598997493733, 'I-P': 0.8454428302569, 'B-MC': 0.424886191198786, 'I-MC': 0.48573390772304426}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7686753842163826, 'recall': 0.7686753842163826, 'f1': 0.7686753842163826, 'support': None}, 'macro_avg': {'precision': 0.5924045793696494, 'recall': 0.6078542849442485, 'f1': 0.5985683706421334, 'support': None}, 'weighted_avg': {'precision': 0.7620398587477014, 'recall': 0.7686753842163826, 'f1': 0.7646352634163817, 'support': None}}
			------------EPOCH 17---------------
Loss:  tensor(0.1654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0629, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0850, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0852, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1393, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2419, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3831, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9155555555555556, 'B-C': 0.40320962888665995, 'I-C': 0.45907845980344775, 'B-P': 0.6615125105425921, 'I-P': 0.7984477773456654, 'B-MC': 0.3801089918256131, 'I-MC': 0.501244400199104}, 'recall': {'O': 0.862979788362667, 'B-C': 0.34038950042337, 'I-C': 0.33484136310223267, 'B-P': 0.7763114483668756, 'I-P': 0.9003908856897702, 'B-MC': 0.4720812182741117, 'I-MC': 0.4738823529411765}, 'f1': {'O': 0.8884905686798953, 'B-C': 0.3691460055096419, 'I-C': 0.38723924712917035, 'B-P': 0.7143290831815422, 'I-P': 0.8463606545624002, 'B-MC': 0.4211320754716982, 'I-MC': 0.48717948717948717}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7672280367107563, 'recall': 0.7672280367107563, 'f1': 0.7672280367107563, 'support': None}, 'macro_avg': {'precision': 0.5884510463083769, 'recall': 0.594410936737172, 'f1': 0.587696731673405, 'support': None}, 'weighted_avg': {'precision': 0.7555597692071125, 'recall': 0.7672280367107563, 'f1': 0.7582344526530361, 'support': None}}
			------------EPOCH 18---------------
Loss:  tensor(0.1290, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0525, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0595, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0654, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0982, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3507, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9012262912371855, 'B-C': 0.41589267285861714, 'I-C': 0.4786969643174152, 'B-P': 0.6474918211559433, 'I-P': 0.7951625853071056, 'B-MC': 0.37868162692847124, 'I-MC': 0.5075034106412005}, 'recall': {'O': 0.8776420663202851, 'B-C': 0.34123624047417445, 'I-C': 0.31686251468860166, 'B-P': 0.7835697789508413, 'I-P': 0.9064353131852417, 'B-MC': 0.45685279187817257, 'I-MC': 0.4376470588235294}, 'f1': {'O': 0.8892778390297686, 'B-C': 0.3748837209302326, 'I-C': 0.38131938061231707, 'B-P': 0.7090610538886402, 'I-P': 0.8471607160359623, 'B-MC': 0.41411042944785276, 'I-MC': 0.46999368288060644}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7693697763722611, 'recall': 0.7693697763722611, 'f1': 0.7693697763722612, 'support': None}, 'macro_avg': {'precision': 0.5892364817779913, 'recall': 0.588606537760121, 'f1': 0.5836866889750543, 'support': None}, 'weighted_avg': {'precision': 0.7527127358199127, 'recall': 0.7693697763722611, 'f1': 0.7566509344857308, 'support': None}}
			------------EPOCH 19---------------
Loss:  tensor(0.1037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0665, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2477, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3345, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8988486613954779, 'B-C': 0.3988245172124265, 'I-C': 0.4693715194908512, 'B-P': 0.6545817870396803, 'I-P': 0.8045488928620548, 'B-MC': 0.4032, 'I-MC': 0.5552674230145868}, 'recall': {'O': 0.8813416392372351, 'B-C': 0.4022015241320914, 'I-C': 0.3813160987074031, 'B-P': 0.7565160013196964, 'I-P': 0.8923443607588902, 'B-MC': 0.4263959390862944, 'I-MC': 0.40305882352941175}, 'f1': {'O': 0.890009065186935, 'B-C': 0.40050590219224286, 'I-C': 0.42078646221674715, 'B-P': 0.7018671564126109, 'I-P': 0.8461754043376457, 'B-MC': 0.4144736842105263, 'I-MC': 0.4670756646216769}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7708087577073346, 'recall': 0.7708087577073346, 'f1': 0.7708087577073346, 'support': None}, 'macro_avg': {'precision': 0.5978061144307254, 'recall': 0.5918820552530032, 'f1': 0.5915561913111979, 'support': None}, 'weighted_avg': {'precision': 0.7583009900226141, 'recall': 0.7708087577073346, 'f1': 0.7619283339690128, 'support': None}}
			------------EPOCH 20---------------
Loss:  tensor(0.0827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2496, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3153, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9026001287469563, 'B-C': 0.40097799511002447, 'I-C': 0.4711431742508324, 'B-P': 0.6648983200707339, 'I-P': 0.8102557839271383, 'B-MC': 0.3997050147492625, 'I-MC': 0.5382457176609569}, 'recall': {'O': 0.8772612279317755, 'B-C': 0.4165961049957663, 'I-C': 0.3990599294947121, 'B-P': 0.744308808973936, 'I-P': 0.8854800266946324, 'B-MC': 0.45854483925549916, 'I-MC': 0.4288235294117647}, 'f1': {'O': 0.8897503103876396, 'B-C': 0.4086378737541529, 'I-C': 0.43211604529838404, 'B-P': 0.7023661270236613, 'I-P': 0.8461994005047423, 'B-MC': 0.4271079590228527, 'I-MC': 0.4773441592456784}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7708924194128621, 'recall': 0.7708924194128621, 'f1': 0.7708924194128621, 'support': None}, 'macro_avg': {'precision': 0.5982608763594149, 'recall': 0.6014392095368696, 'f1': 0.5976459821767302, 'support': None}, 'weighted_avg': {'precision': 0.7612661432026462, 'recall': 0.7708924194128621, 'f1': 0.7643582145579136, 'support': None}}
			------------EPOCH 21---------------
Loss:  tensor(0.0686, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0185, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0255, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1720, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2471, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3065, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9104605620515166, 'B-C': 0.3967437874892888, 'I-C': 0.46471984463784793, 'B-P': 0.647914917436328, 'I-P': 0.7966428547472918, 'B-MC': 0.4165232358003442, 'I-MC': 0.5660576247364723}, 'recall': {'O': 0.8663257256331438, 'B-C': 0.3920406435224386, 'I-C': 0.37961222091656877, 'B-P': 0.7637743319036622, 'I-P': 0.9058442177519306, 'B-MC': 0.40947546531302875, 'I-MC': 0.3790588235294118}, 'f1': {'O': 0.8878449958182325, 'B-C': 0.3943781942078365, 'I-C': 0.4178766613847299, 'B-P': 0.7010902483343429, 'I-P': 0.8477413253151794, 'B-MC': 0.41296928327645055, 'I-MC': 0.4540586245772266}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7701645625747726, 'recall': 0.7701645625747726, 'f1': 0.7701645625747725, 'support': None}, 'macro_avg': {'precision': 0.5998661181284415, 'recall': 0.5851616326528833, 'f1': 0.5879941904162854, 'support': None}, 'weighted_avg': {'precision': 0.7583845473895545, 'recall': 0.7701645625747726, 'f1': 0.7605221562932877, 'support': None}}
			------------EPOCH 22---------------
Loss:  tensor(0.0572, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0248, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2921, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3086, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9007789162176498, 'B-C': 0.3861646234676007, 'I-C': 0.4555455093429777, 'B-P': 0.6403054267793837, 'I-P': 0.7939926372155288, 'B-MC': 0.4175824175824176, 'I-MC': 0.5842569979334962}, 'recall': {'O': 0.8776964718043578, 'B-C': 0.37341236240474174, 'I-C': 0.3552291421856639, 'B-P': 0.7746618277796107, 'I-P': 0.9047382972638002, 'B-MC': 0.38578680203045684, 'I-MC': 0.3658823529411765}, 'f1': {'O': 0.8890879030035822, 'B-C': 0.3796814464055101, 'I-C': 0.3991813019939258, 'B-P': 0.7011048074051957, 'I-P': 0.845755536740787, 'B-MC': 0.40105540897097625, 'I-MC': 0.4499746798813572}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7687423135808047, 'recall': 0.7687423135808047, 'f1': 0.7687423135808047, 'support': None}, 'macro_avg': {'precision': 0.5969466469341507, 'recall': 0.5767724652014011, 'f1': 0.5808344406287621, 'support': None}, 'weighted_avg': {'precision': 0.7539397470653347, 'recall': 0.7687423135808047, 'f1': 0.7568768773416101, 'support': None}}
			------------EPOCH 23---------------
Loss:  tensor(0.0495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0170, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1327, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2306, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3304, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8876638855780691, 'B-C': 0.43101482326111745, 'I-C': 0.5161191904810333, 'B-P': 0.6383724063594718, 'I-P': 0.8006237393854133, 'B-MC': 0.35336538461538464, 'I-MC': 0.5017342423155124}, 'recall': {'O': 0.891406653790702, 'B-C': 0.32006773920406434, 'I-C': 0.2981786133960047, 'B-P': 0.7815902342461234, 'I-P': 0.9006768996091143, 'B-MC': 0.49746192893401014, 'I-MC': 0.4935294117647059}, 'f1': {'O': 0.8895313327089864, 'B-C': 0.36734693877551017, 'I-C': 0.37798383793244705, 'B-P': 0.7027588252743993, 'I-P': 0.8477082660349593, 'B-MC': 0.41321152494729446, 'I-MC': 0.49759800723563247}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7723314007479356, 'recall': 0.7723314007479356, 'f1': 0.7723314007479356, 'support': None}, 'macro_avg': {'precision': 0.5898419531422859, 'recall': 0.5975587829921035, 'f1': 0.5851626761298899, 'support': None}, 'weighted_avg': {'precision': 0.755649156302881, 'recall': 0.7723314007479356, 'f1': 0.7582184746996632, 'support': None}}
			------------EPOCH 24---------------
Loss:  tensor(0.0432, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1180, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2135, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2666, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9107890315783479, 'B-C': 0.38973897389738976, 'I-C': 0.45791245791245794, 'B-P': 0.6546117185309784, 'I-P': 0.7978563845026037, 'B-MC': 0.4114977307110439, 'I-MC': 0.5520708283313326}, 'recall': {'O': 0.8701069067762031, 'B-C': 0.36663844199830653, 'I-C': 0.3515863689776733, 'B-P': 0.7703728142527219, 'I-P': 0.9027361998283916, 'B-MC': 0.4602368866328257, 'I-MC': 0.4328235294117647}, 'f1': {'O': 0.8899833055091819, 'B-C': 0.37783595113438045, 'I-C': 0.39776655144908263, 'B-P': 0.7077902394665051, 'I-P': 0.8470621913690689, 'B-MC': 0.4345047923322684, 'I-MC': 0.4852281719862833}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7699637744815065, 'recall': 0.7699637744815065, 'f1': 0.7699637744815065, 'support': None}, 'macro_avg': {'precision': 0.5963538750663078, 'recall': 0.5935001639825553, 'f1': 0.591453029035253, 'support': None}, 'weighted_avg': {'precision': 0.7571298241888371, 'recall': 0.7699637744815065, 'f1': 0.7603477640915735, 'support': None}}
			------------EPOCH 25---------------
Loss:  tensor(0.0313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0123, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0149, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0166, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2496, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9093561453700819, 'B-C': 0.3965201465201465, 'I-C': 0.47104247104247104, 'B-P': 0.6461835216313034, 'I-P': 0.7978465679676985, 'B-MC': 0.39260312944523473, 'I-MC': 0.5516594516594516}, 'recall': {'O': 0.8732896275944615, 'B-C': 0.36663844199830653, 'I-C': 0.34406580493537015, 'B-P': 0.7736720554272517, 'I-P': 0.9042616073982267, 'B-MC': 0.467005076142132, 'I-MC': 0.44976470588235296}, 'f1': {'O': 0.8909580373001775, 'B-C': 0.3809942806863176, 'I-C': 0.39766399565394545, 'B-P': 0.7042042042042042, 'I-P': 0.847727577423247, 'B-MC': 0.4265842349304482, 'I-MC': 0.49552819183408947}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7718628951969815, 'recall': 0.7718628951969815, 'f1': 0.7718628951969815, 'support': None}, 'macro_avg': {'precision': 0.5950302048051982, 'recall': 0.5969567599111574, 'f1': 0.5919515031474899, 'support': None}, 'weighted_avg': {'precision': 0.7582850497358016, 'recall': 0.7718628951969815, 'f1': 0.7615584545595738, 'support': None}}
			------------EPOCH 26---------------
Loss:  tensor(0.0263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0152, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0950, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1919, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2352, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.908009941817771, 'B-C': 0.4085714285714286, 'I-C': 0.4902700889112565, 'B-P': 0.6485507246376812, 'I-P': 0.8005355659881701, 'B-MC': 0.3673469387755102, 'I-MC': 0.5321502057613169}, 'recall': {'O': 0.8745409537281358, 'B-C': 0.3632514817950889, 'I-C': 0.34341950646298475, 'B-P': 0.767733421313098, 'I-P': 0.9006387644198685, 'B-MC': 0.4873096446700508, 'I-MC': 0.4868235294117647}, 'f1': {'O': 0.8909612426732438, 'B-C': 0.3845809054235769, 'I-C': 0.40391127081749706, 'B-P': 0.7031273606284937, 'I-P': 0.8476419496087861, 'B-MC': 0.4189090909090909, 'I-MC': 0.5084787417055787}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7731178207798944, 'recall': 0.7731178207798944, 'f1': 0.7731178207798944, 'support': None}, 'macro_avg': {'precision': 0.5936335563518763, 'recall': 0.6033881859715703, 'f1': 0.5939443659666096, 'support': None}, 'weighted_avg': {'precision': 0.7604555968508852, 'recall': 0.7731178207798944, 'f1': 0.763302560676092, 'support': None}}
			------------EPOCH 27---------------
Loss:  tensor(0.0210, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0094, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0777, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2163, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9109435036288601, 'B-C': 0.4001798561151079, 'I-C': 0.4707737271189048, 'B-P': 0.6476350405821438, 'I-P': 0.798915430617968, 'B-MC': 0.3953147877013177, 'I-MC': 0.5474377745241581}, 'recall': {'O': 0.870650961616931, 'B-C': 0.37679932260795934, 'I-C': 0.35963572267920096, 'B-P': 0.7634444077862091, 'I-P': 0.901725617313376, 'B-MC': 0.45685279187817257, 'I-MC': 0.43988235294117645}, 'f1': {'O': 0.890341604539891, 'B-C': 0.3881378107283035, 'I-C': 0.40776763706615154, 'B-P': 0.700787401574803, 'I-P': 0.8472128915522353, 'B-MC': 0.423861852433281, 'I-MC': 0.4878016960208741}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7712437985760777, 'recall': 0.7712437985760777, 'f1': 0.7712437985760777, 'support': None}, 'macro_avg': {'precision': 0.5958857314697801, 'recall': 0.595570168117575, 'f1': 0.5922729848450771, 'support': None}, 'weighted_avg': {'precision': 0.7589901117911708, 'recall': 0.7712437985760777, 'f1': 0.7620027536783764, 'support': None}}
			------------EPOCH 28---------------
Loss:  tensor(0.0178, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0059, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0113, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1731, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1964, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9031537193776362, 'B-C': 0.3947841726618705, 'I-C': 0.4725474683544304, 'B-P': 0.6434878587196468, 'I-P': 0.8020063808370157, 'B-MC': 0.3695955369595537, 'I-MC': 0.5320330296127562}, 'recall': {'O': 0.8795190555207965, 'B-C': 0.37171888230313294, 'I-C': 0.3509400705052879, 'B-P': 0.7693830419003629, 'I-P': 0.8963294880350844, 'B-MC': 0.44839255499153974, 'I-MC': 0.4396470588235294}, 'f1': {'O': 0.8911797133406835, 'B-C': 0.38290449193196685, 'I-C': 0.4027646662171275, 'B-P': 0.7008264462809918, 'I-P': 0.8465486502548217, 'B-MC': 0.4051987767584098, 'I-MC': 0.4814480803916516}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7704071815208025, 'recall': 0.7704071815208025, 'f1': 0.7704071815208025, 'support': None}, 'macro_avg': {'precision': 0.5882297380747014, 'recall': 0.5937043074399619, 'f1': 0.5872672607393791, 'support': None}, 'weighted_avg': {'precision': 0.7568220260704551, 'recall': 0.7704071815208025, 'f1': 0.7606618673944323, 'support': None}}
			------------EPOCH 29---------------
Loss:  tensor(0.0156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0073, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1679, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1796, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9034965034965035, 'B-C': 0.3906111603188663, 'I-C': 0.4647821333749805, 'B-P': 0.6428571428571429, 'I-P': 0.8012877442273535, 'B-MC': 0.3645251396648045, 'I-MC': 0.5287769784172662}, 'recall': {'O': 0.8786485677756318, 'B-C': 0.37341236240474174, 'I-C': 0.34970622796709755, 'B-P': 0.76905311778291, 'I-P': 0.8945943369243969, 'B-MC': 0.4416243654822335, 'I-MC': 0.4323529411764706}, 'f1': {'O': 0.8908993118285502, 'B-C': 0.3818181818181818, 'I-C': 0.39911486622409975, 'B-P': 0.7003154574132492, 'I-P': 0.845374199302684, 'B-MC': 0.39938791124713086, 'I-MC': 0.4757281553398059}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7686586518752772, 'recall': 0.7686586518752772, 'f1': 0.7686586518752772, 'support': None}, 'macro_avg': {'precision': 0.5851909717652738, 'recall': 0.5913417027876403, 'f1': 0.5846625833105288, 'support': None}, 'weighted_avg': {'precision': 0.7551925731454787, 'recall': 0.7686586518752772, 'f1': 0.7590814405522928, 'support': None}}
			------------EPOCH 30---------------
Loss:  tensor(0.0136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0086, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0524, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1775, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.906909111443657, 'B-C': 0.38738738738738737, 'I-C': 0.46370393800411197, 'B-P': 0.6362401521325727, 'I-P': 0.7956933126809886, 'B-MC': 0.3799126637554585, 'I-MC': 0.5427791262135923}, 'recall': {'O': 0.8737520742090803, 'B-C': 0.3640982218458933, 'I-C': 0.3445358401880141, 'B-P': 0.7726822830748927, 'I-P': 0.9011535894746878, 'B-MC': 0.4416243654822335, 'I-MC': 0.42094117647058826}, 'f1': {'O': 0.8900218903266923, 'B-C': 0.3753819292885203, 'I-C': 0.39533472662307023, 'B-P': 0.6978545887961859, 'I-P': 0.8451462343863163, 'B-MC': 0.4084507042253521, 'I-MC': 0.4741584945666578}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7684829622936693, 'recall': 0.7684829622936693, 'f1': 0.7684829622936694, 'support': None}, 'macro_avg': {'precision': 0.5875179559453955, 'recall': 0.5883982215350556, 'f1': 0.5837640811732564, 'support': None}, 'weighted_avg': {'precision': 0.7545061199949641, 'recall': 0.7684829622936693, 'f1': 0.7579804976780473, 'support': None}}
Tokenizer: ../arg_m/arg_mining/smlm_pretrained_iter5_0/tokenizer Model: ../arg_m/arg_mining/smlm_pretrained_iter5_0/model
	Data split: 1k
			------------EPOCH 1---------------
Loss:  tensor(0.3805, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5162, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.49977507872244714, 'B-C': 0.027896995708154508, 'I-C': 0.14530999527432104, 'B-P': 0.04770477047704771, 'I-P': 0.5011380095178978, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.030222246402437366, 'B-C': 0.0550381033022862, 'I-C': 0.9213866039952997, 'B-P': 0.034971956450016495, 'I-P': 0.0461817141767566, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.05699774266365688, 'B-C': 0.0370264881800057, 'I-C': 0.2510304863895759, 'B-P': 0.04035789072910717, 'I-P': 0.08456999196899333, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.1621865823356675, 'recall': 0.1621865823356675, 'f1': 0.1621865823356675, 'support': None}, 'macro_avg': {'precision': 0.17454640709998115, 'recall': 0.15540008918954237, 'f1': 0.06714037141876271, 'support': None}, 'weighted_avg': {'precision': 0.3957627873478255, 'recall': 0.1621865823356675, 'f1': 0.0917698564746935, 'support': None}}
			------------EPOCH 2---------------
Loss:  tensor(0.3265, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3764, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4169, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8031265266243283, 'B-C': 0.03433835845896147, 'I-C': 0.11898016997167139, 'B-P': 0.0430786904078116, 'I-P': 0.4725359093471205, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.04472130790783711, 'B-C': 0.03471634208298052, 'I-C': 0.08143360752056404, 'B-P': 0.024744308808973936, 'I-P': 0.9271236533511298, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.0847247990105133, 'B-C': 0.03452631578947368, 'I-C': 0.09668980431825316, 'B-P': 0.03143336127409891, 'I-P': 0.6260082527053038, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.4331082833454643, 'recall': 0.4331082833454643, 'f1': 0.4331082833454643, 'support': None}, 'macro_avg': {'precision': 0.21029423640141331, 'recall': 0.15896274566735505, 'f1': 0.12476893329966325, 'support': None}, 'weighted_avg': {'precision': 0.47270576693380373, 'recall': 0.4331082833454643, 'f1': 0.31563287332798706, 'support': None}}
			------------EPOCH 3---------------
Loss:  tensor(0.2991, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3628, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9637305699481865, 'B-C': 0.047619047619047616, 'I-C': 0.027131782945736434, 'B-P': 0.10748299319727891, 'I-P': 0.45156701297581586, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.0657762302440086, 'B-C': 0.001693480101608806, 'I-C': 0.00041128084606345473, 'B-P': 0.026064005278785878, 'I-P': 0.9986652683763944, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.12314744079449962, 'B-C': 0.0032706459525756334, 'I-C': 0.0008102789674730871, 'B-P': 0.04195432819968136, 'I-P': 0.6219200854954581, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.45914380610563127, 'recall': 0.45914380610563127, 'f1': 0.45914380610563127, 'support': None}, 'macro_avg': {'precision': 0.22821877238372362, 'recall': 0.1560871806924087, 'f1': 0.11301468277281254, 'support': None}, 'weighted_avg': {'precision': 0.5015848327245892, 'recall': 0.45914380610563127, 'f1': 0.31196144119440067, 'support': None}}
			------------EPOCH 4---------------
Loss:  tensor(0.2829, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2826, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3339, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9402498642042368, 'B-C': 0.014084507042253521, 'I-C': 0.03486238532110092, 'B-P': 0.24765478424015008, 'I-P': 0.5058933364453262, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.3296156252550257, 'B-C': 0.000846740050804403, 'I-C': 0.0011163337250293772, 'B-P': 0.2612999010227648, 'I-P': 0.9918962722852512, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.48811633902674834, 'B-C': 0.001597444089456869, 'I-C': 0.0021633931113008826, 'B-P': 0.2542944292823888, 'I-P': 0.6700456615123042, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.5433744112307474, 'recall': 0.5433744112307474, 'f1': 0.5433744112307474, 'support': None}, 'macro_avg': {'precision': 0.24896355389329536, 'recall': 0.2263964103341251, 'f1': 0.2023167524317427, 'support': None}, 'weighted_avg': {'precision': 0.5225236933288242, 'recall': 0.5433744112307474, 'f1': 0.45088357975348237, 'support': None}}
			------------EPOCH 5---------------
Loss:  tensor(0.2575, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2557, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3037, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8904442864094022, 'B-C': 0.09699769053117784, 'I-C': 0.15658544896916, 'B-P': 0.3694856896922746, 'I-P': 0.6047176380049595, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.647153233045891, 'B-C': 0.03556308213378493, 'I-C': 0.05399529964747356, 'B-P': 0.5664797096667766, 'I-P': 0.9439222042139385, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.7495510255521597, 'B-C': 0.05204460966542751, 'I-C': 0.08030058106514046, 'B-P': 0.4472518885126335, 'I-P': 0.7371712779581262, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6355947092337424, 'recall': 0.6355947092337424, 'f1': 0.6355947092337424, 'support': None}, 'macro_avg': {'precision': 0.3026043933724249, 'recall': 0.32101621838683775, 'f1': 0.29518848325049823, 'support': None}, 'weighted_avg': {'precision': 0.5718075837436593, 'recall': 0.6355947092337424, 'f1': 0.5772573515269284, 'support': None}}
			------------EPOCH 6---------------
Loss:  tensor(0.2262, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2722, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8679733964315406, 'B-C': 0.12711182622687048, 'I-C': 0.19567747298420615, 'B-P': 0.3979470040582478, 'I-P': 0.6739942573095804, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.7384184325780039, 'B-C': 0.13378492802709568, 'I-C': 0.20746180963572267, 'B-P': 0.5499835037941273, 'I-P': 0.8324911812374869, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.7979716322481076, 'B-C': 0.13036303630363036, 'I-C': 0.2013974048196207, 'B-P': 0.4617728531855956, 'I-P': 0.7449050101089377, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6371759154682127, 'recall': 0.6371759154682127, 'f1': 0.6371759154682127, 'support': None}, 'macro_avg': {'precision': 0.3232434224300636, 'recall': 0.3517342650389195, 'f1': 0.3337728480951275, 'support': None}, 'weighted_avg': {'precision': 0.601878421781212, 'recall': 0.6371759154682127, 'f1': 0.61392762026074, 'support': None}}
			------------EPOCH 7---------------
Loss:  tensor(0.1969, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1968, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2386, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8704563504184739, 'B-C': 0.1446311176040906, 'I-C': 0.2081515436019219, 'B-P': 0.4015842534805569, 'I-P': 0.683858810115758, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.775196539811213, 'B-C': 0.1676545300592718, 'I-C': 0.22144535840188015, 'B-P': 0.5519630484988453, 'I-P': 0.8234340737915912, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.8200693535158778, 'B-C': 0.1552941176470588, 'I-C': 0.21459276340137215, 'B-P': 0.46491593719605395, 'I-P': 0.747184109901898, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6468890394799588, 'recall': 0.6468890394799588, 'f1': 0.6468890394799588, 'support': None}, 'macro_avg': {'precision': 0.32981172503154305, 'recall': 0.3628133643661145, 'f1': 0.343150897380323, 'support': None}, 'weighted_avg': {'precision': 0.609011802060999, 'recall': 0.6468890394799588, 'f1': 0.6239286829144056, 'support': None}}
			------------EPOCH 8---------------
Loss:  tensor(0.1705, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1684, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2050, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.870355078447564, 'B-C': 0.15121512151215122, 'I-C': 0.20741975823259692, 'B-P': 0.4088769334229993, 'I-P': 0.6740088753049049, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.8028073229781562, 'B-C': 0.14225232853513972, 'I-C': 0.14618096357226792, 'B-P': 0.6017815902342462, 'I-P': 0.8746114977595576, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.8352177050757758, 'B-C': 0.1465968586387435, 'I-C': 0.17149750129243496, 'B-P': 0.48691938067271756, 'I-P': 0.7613175213072307, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6681307465133984, 'recall': 0.6681307465133984, 'f1': 0.6681307465133984, 'support': None}, 'macro_avg': {'precision': 0.33026796670288805, 'recall': 0.366804814725624, 'f1': 0.3430784238552718, 'support': None}, 'weighted_avg': {'precision': 0.6048046401543258, 'recall': 0.6681307465133984, 'f1': 0.6291243670248802, 'support': None}}
			------------EPOCH 9---------------
Loss:  tensor(0.1458, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1400, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1733, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8682942313796785, 'B-C': 0.15836653386454183, 'I-C': 0.22072760623662488, 'B-P': 0.40948651000870323, 'I-P': 0.6733368843844925, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.8185033051331574, 'B-C': 0.13463166807790009, 'I-C': 0.127262044653349, 'B-P': 0.6209171890465193, 'I-P': 0.891829535704071, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.8426639034363012, 'B-C': 0.14553775743707092, 'I-C': 0.16144299929191666, 'B-P': 0.493509899042874, 'I-P': 0.7673327427240214, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6782287143705712, 'recall': 0.6782287143705712, 'f1': 0.6782287143705712, 'support': None}, 'macro_avg': {'precision': 0.332887395124863, 'recall': 0.37044910608785664, 'f1': 0.3443553288474549, 'support': None}, 'weighted_avg': {'precision': 0.6058570345921981, 'recall': 0.6782287143705712, 'f1': 0.632778672036608, 'support': None}}
			------------EPOCH 10---------------
Loss:  tensor(0.1219, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1434, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8631620397716085, 'B-C': 0.16517857142857142, 'I-C': 0.22286363206208007, 'B-P': 0.4071895424836601, 'I-P': 0.6805945450784552, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.8347977476129594, 'B-C': 0.15664690939881457, 'I-C': 0.13836662749706227, 'B-P': 0.6166281755196305, 'I-P': 0.8783296787110306, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.8487429819951877, 'B-C': 0.16079965232507604, 'I-C': 0.17073259143799616, 'B-P': 0.4904868127542317, 'I-P': 0.7669216745610896, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6790067682319771, 'recall': 0.6790067682319771, 'f1': 0.6790067682319771, 'support': None}, 'macro_avg': {'precision': 0.33414119011776794, 'recall': 0.37496701981992814, 'f1': 0.34824053043908304, 'support': None}, 'weighted_avg': {'precision': 0.6077762473918915, 'recall': 0.6790067682319771, 'f1': 0.6358648245079448, 'support': None}}
			------------EPOCH 11---------------
Loss:  tensor(0.0999, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1175, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8522957368795491, 'B-C': 0.16539923954372623, 'I-C': 0.23314575747544963, 'B-P': 0.39846906230065915, 'I-P': 0.6813332157658055, 'B-MC': 0.07142857142857142, 'I-MC': 0.37142857142857144}, 'recall': {'O': 0.8473110089497021, 'B-C': 0.14733276883996613, 'I-C': 0.12414806110458285, 'B-P': 0.6182777961068954, 'I-P': 0.8840118219086662, 'B-MC': 0.001692047377326565, 'I-MC': 0.004588235294117647}, 'f1': {'O': 0.849796063131761, 'B-C': 0.15584415584415584, 'I-C': 0.16202123988804967, 'B-P': 0.48461339539694853, 'I-P': 0.7695512527906648, 'B-MC': 0.003305785123966942, 'I-MC': 0.009064497385241139}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6836081620359913, 'recall': 0.6836081620359913, 'f1': 0.6836081620359913, 'support': None}, 'macro_avg': {'precision': 0.3962143078317618, 'recall': 0.37533739136875094, 'f1': 0.3477423413658268, 'support': None}, 'weighted_avg': {'precision': 0.6327699407599036, 'recall': 0.6836081620359913, 'f1': 0.636565077333288, 'support': None}}
			------------EPOCH 12---------------
Loss:  tensor(0.0803, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0938, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8391334470262204, 'B-C': 0.18342541436464088, 'I-C': 0.25329853559518634, 'B-P': 0.3959633791094465, 'I-P': 0.6804816699433329, 'B-MC': 0.037037037037037035, 'I-MC': 0.2578947368421053}, 'recall': {'O': 0.8566415494681864, 'B-C': 0.14055884843353092, 'I-C': 0.10264394829612221, 'B-P': 0.627845595513032, 'I-P': 0.8975688816855754, 'B-MC': 0.001692047377326565, 'I-MC': 0.005764705882352941}, 'f1': {'O': 0.8477971166659937, 'B-C': 0.15915627996164908, 'I-C': 0.14608855625705566, 'B-P': 0.4856450172259793, 'I-P': 0.7740932898101478, 'B-MC': 0.0032362459546925564, 'I-MC': 0.011277330264672036}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6896234386634206, 'recall': 0.6896234386634206, 'f1': 0.6896234386634206, 'support': None}, 'macro_avg': {'precision': 0.37817631713113853, 'recall': 0.3761022252365895, 'f1': 0.3467562623057415, 'support': None}, 'weighted_avg': {'precision': 0.6230887188099224, 'recall': 0.6896234386634206, 'f1': 0.635890396136523, 'support': None}}
			------------EPOCH 13---------------
Loss:  tensor(0.0623, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0554, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0735, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.842085581494738, 'B-C': 0.18480492813141683, 'I-C': 0.26772530993174537, 'B-P': 0.39104416013206766, 'I-P': 0.6838237434151169, 'B-MC': 0.06818181818181818, 'I-MC': 0.3575757575757576}, 'recall': {'O': 0.8575936454394603, 'B-C': 0.15241320914479256, 'I-C': 0.11292596944770858, 'B-P': 0.6252062025734081, 'I-P': 0.8960053389264945, 'B-MC': 0.005076142131979695, 'I-MC': 0.01388235294117647}, 'f1': {'O': 0.8497688648094989, 'B-C': 0.16705336426914152, 'I-C': 0.15884953923715855, 'B-P': 0.4811476450425289, 'I-P': 0.7756658385810848, 'B-MC': 0.009448818897637795, 'I-MC': 0.026727066817667046}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6913385036267349, 'recall': 0.6913385036267349, 'f1': 0.6913385036267349, 'support': None}, 'macro_avg': {'precision': 0.39932018555180865, 'recall': 0.3804432658007172, 'f1': 0.35266587680781675, 'support': None}, 'weighted_avg': {'precision': 0.6346487289544384, 'recall': 0.6913385036267349, 'f1': 0.6400972162128677, 'support': None}}
			------------EPOCH 14---------------
Loss:  tensor(0.0470, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0408, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0595, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.845324030591708, 'B-C': 0.1786492374727669, 'I-C': 0.2616504102802291, 'B-P': 0.3904761904761905, 'I-P': 0.6811097346662441, 'B-MC': 0.09836065573770492, 'I-MC': 0.3837953091684435}, 'recall': {'O': 0.8569135768885504, 'B-C': 0.1388653683319221, 'I-C': 0.09929494712103408, 'B-P': 0.6357637743319037, 'I-P': 0.9015921441510153, 'B-MC': 0.01015228426395939, 'I-MC': 0.021176470588235293}, 'f1': {'O': 0.8510793504984736, 'B-C': 0.15626488804192473, 'I-C': 0.14395843093828528, 'B-P': 0.4838061762490585, 'I-P': 0.7759935011118677, 'B-MC': 0.01840490797546012, 'I-MC': 0.040138253985951604}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.692317345581407, 'recall': 0.692317345581407, 'f1': 0.692317345581407, 'support': None}, 'macro_avg': {'precision': 0.4056236526276124, 'recall': 0.38053693795380283, 'f1': 0.3528065012572888, 'support': None}, 'weighted_avg': {'precision': 0.6355274122964627, 'recall': 0.692317345581407, 'f1': 0.6394824475778967, 'support': None}}
			------------EPOCH 15---------------
Loss:  tensor(0.0354, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0599, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8406077641069156, 'B-C': 0.1778496362166532, 'I-C': 0.269742883379247, 'B-P': 0.3739324928832859, 'I-P': 0.6919464202117217, 'B-MC': 0.10344827586206896, 'I-MC': 0.37732919254658387}, 'recall': {'O': 0.8623541252958298, 'B-C': 0.18628281117696868, 'I-C': 0.13807285546415982, 'B-P': 0.6067304519960409, 'I-P': 0.8736771856230336, 'B-MC': 0.015228426395939087, 'I-MC': 0.028588235294117647}, 'f1': {'O': 0.8513420971358747, 'B-C': 0.18196856906534326, 'I-C': 0.18265195087828384, 'B-P': 0.46269971065542836, 'I-P': 0.7722645452706802, 'B-MC': 0.02654867256637168, 'I-MC': 0.0531496062992126}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6875486283663379, 'recall': 0.6875486283663379, 'f1': 0.6875486283663379, 'support': None}, 'macro_avg': {'precision': 0.4049795236009252, 'recall': 0.3872762987494413, 'f1': 0.361517878838742, 'support': None}, 'weighted_avg': {'precision': 0.6391219015756376, 'recall': 0.6875486283663379, 'f1': 0.6441210646418353, 'support': None}}
			------------EPOCH 16---------------
Loss:  tensor(0.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0576, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8398051827734985, 'B-C': 0.17366628830874006, 'I-C': 0.26589084481107755, 'B-P': 0.3706521739130435, 'I-P': 0.7098926745886955, 'B-MC': 0.11864406779661017, 'I-MC': 0.42470588235294116}, 'recall': {'O': 0.8630613965887761, 'B-C': 0.25910245554614736, 'I-C': 0.21210340775558167, 'B-P': 0.5625206202573408, 'I-P': 0.8235675469539517, 'B-MC': 0.023688663282571912, 'I-MC': 0.04247058823529412}, 'f1': {'O': 0.8512744834987925, 'B-C': 0.20795107033639146, 'I-C': 0.23597084681504724, 'B-P': 0.44686148604376885, 'I-P': 0.7625167714144482, 'B-MC': 0.03949224259520451, 'I-MC': 0.0772192513368984}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.676948690276, 'recall': 0.676948690276, 'f1': 0.676948690276, 'support': None}, 'macro_avg': {'precision': 0.41475101636351525, 'recall': 0.3980735255170948, 'f1': 0.37446945029150724, 'support': None}, 'weighted_avg': {'precision': 0.6495204267676974, 'recall': 0.676948690276, 'f1': 0.64904624072422, 'support': None}}
			------------EPOCH 17---------------
Loss:  tensor(0.0212, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0195, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0501, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8445139055862787, 'B-C': 0.16393442622950818, 'I-C': 0.2656573848787961, 'B-P': 0.37632840175036464, 'I-P': 0.7005823103556814, 'B-MC': 0.1366906474820144, 'I-MC': 0.39879759519038077}, 'recall': {'O': 0.8599058785125541, 'B-C': 0.21168501270110077, 'I-C': 0.17320799059929495, 'B-P': 0.5958429561200924, 'I-P': 0.8487939746400992, 'B-MC': 0.032148900169204735, 'I-MC': 0.04682352941176471}, 'f1': {'O': 0.8521403924951477, 'B-C': 0.18477457501847747, 'I-C': 0.20969520219084545, 'B-P': 0.46130268199233715, 'I-P': 0.7675992585248093, 'B-MC': 0.05205479452054794, 'I-MC': 0.08380711728785008}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6822361100653398, 'recall': 0.6822361100653398, 'f1': 0.6822361100653398, 'support': None}, 'macro_avg': {'precision': 0.412357810210432, 'recall': 0.3954868917363016, 'f1': 0.3730534317185736, 'support': None}, 'weighted_avg': {'precision': 0.6451449047123335, 'recall': 0.6822361100653398, 'f1': 0.6484689113592509, 'support': None}}
			------------EPOCH 18---------------
Loss:  tensor(0.0165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0387, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8493113764385629, 'B-C': 0.1522140221402214, 'I-C': 0.2539149888143177, 'B-P': 0.3805379746835443, 'I-P': 0.6841973490427099, 'B-MC': 0.17763157894736842, 'I-MC': 0.4436229205175601}, 'recall': {'O': 0.8572128070509507, 'B-C': 0.1397121083827265, 'I-C': 0.10669800235017626, 'B-P': 0.6347740019795447, 'I-P': 0.8858232433978454, 'B-MC': 0.04568527918781726, 'I-MC': 0.05647058823529412}, 'f1': {'O': 0.8532437994151412, 'B-C': 0.14569536423841056, 'I-C': 0.1502564951183187, 'B-P': 0.4758253987881786, 'I-P': 0.7720636503386098, 'B-MC': 0.07267833109017496, 'I-MC': 0.10018785222291798}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6892134963063357, 'recall': 0.6892134963063357, 'f1': 0.6892134963063357, 'support': None}, 'macro_avg': {'precision': 0.42020431579775497, 'recall': 0.38948229008347923, 'f1': 0.36713584160167884, 'support': None}, 'weighted_avg': {'precision': 0.6411402173396682, 'recall': 0.6892134963063357, 'f1': 0.6435524571081813, 'support': None}}
			------------EPOCH 19---------------
Loss:  tensor(0.0132, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0290, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.847084117172803, 'B-C': 0.13375, 'I-C': 0.22244814965433102, 'B-P': 0.3861788617886179, 'I-P': 0.6757160753943398, 'B-MC': 0.15789473684210525, 'I-MC': 0.4177093358999038}, 'recall': {'O': 0.8574304289872419, 'B-C': 0.09060118543607112, 'I-C': 0.06427732079905993, 'B-P': 0.6581986143187067, 'I-P': 0.9050433787777672, 'B-MC': 0.04060913705583756, 'I-MC': 0.05105882352941177}, 'f1': {'O': 0.8522258723013072, 'B-C': 0.10802624936900555, 'I-C': 0.09973561856140033, 'B-P': 0.48676345004269855, 'I-P': 0.7737449975140396, 'B-MC': 0.0646029609690444, 'I-MC': 0.09099486319320683}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.691371968308946, 'recall': 0.691371968308946, 'f1': 0.691371968308946, 'support': None}, 'macro_avg': {'precision': 0.40582589667887153, 'recall': 0.38103126984344227, 'f1': 0.3537277159929575, 'support': None}, 'weighted_avg': {'precision': 0.6302735598663624, 'recall': 0.691371968308946, 'f1': 0.6359948432503105, 'support': None}}
			------------EPOCH 20---------------
Loss:  tensor(0.0105, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0260, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8402186314309215, 'B-C': 0.13031161473087818, 'I-C': 0.22621313035204568, 'B-P': 0.38396299151888974, 'I-P': 0.6744291397103583, 'B-MC': 0.14383561643835616, 'I-MC': 0.4043887147335423}, 'recall': {'O': 0.8614292320665923, 'B-C': 0.07790008467400508, 'I-C': 0.055875440658049357, 'B-P': 0.6572088419663478, 'I-P': 0.9083992754314043, 'B-MC': 0.03553299492385787, 'I-MC': 0.04552941176470588}, 'f1': {'O': 0.850691739422431, 'B-C': 0.09750927397986221, 'I-C': 0.08961552958914436, 'B-P': 0.48473050249422067, 'I-P': 0.774121738000065, 'B-MC': 0.05698778833107192, 'I-MC': 0.08184413661837792}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6923089794108542, 'recall': 0.6923089794108542, 'f1': 0.6923089794108542, 'support': None}, 'macro_avg': {'precision': 0.40047997698785603, 'recall': 0.3774107544978519, 'f1': 0.3479286726335961, 'support': None}, 'weighted_avg': {'precision': 0.6270265926224997, 'recall': 0.6923089794108542, 'f1': 0.6334034539376947, 'support': None}}
			------------EPOCH 21---------------
Loss:  tensor(0.0082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0238, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8322093266415725, 'B-C': 0.13753213367609254, 'I-C': 0.2333694474539545, 'B-P': 0.37579617834394907, 'I-P': 0.6772970722111339, 'B-MC': 0.1619718309859155, 'I-MC': 0.4179431072210066}, 'recall': {'O': 0.8660536982127799, 'B-C': 0.09060118543607112, 'I-C': 0.06327849588719153, 'B-P': 0.6423622566809634, 'I-P': 0.8993993707693775, 'B-MC': 0.038917089678511, 'I-MC': 0.044941176470588234}, 'f1': {'O': 0.8487942732980525, 'B-C': 0.10923940786115366, 'I-C': 0.09956089669516986, 'B-P': 0.474184120798831, 'I-P': 0.7727049341458618, 'B-MC': 0.06275579809004093, 'I-MC': 0.08115572551519012}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6905604497653289, 'recall': 0.6905604497653289, 'f1': 0.6905604497653289, 'support': None}, 'macro_avg': {'precision': 0.4051598709333749, 'recall': 0.37793618187649747, 'f1': 0.3497707366291856, 'support': None}, 'weighted_avg': {'precision': 0.6277584973886946, 'recall': 0.6905604497653289, 'f1': 0.6334424212376648, 'support': None}}
			------------EPOCH 22---------------
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0198, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8271240815481734, 'B-C': 0.1423982869379015, 'I-C': 0.2526114206128134, 'B-P': 0.37025440313111546, 'I-P': 0.6825700213188267, 'B-MC': 0.1564625850340136, 'I-MC': 0.43473570658036675}, 'recall': {'O': 0.8696716629036206, 'B-C': 0.1126164267569856, 'I-C': 0.08525264394829613, 'B-P': 0.6242164302210491, 'I-P': 0.8852130803699113, 'B-MC': 0.038917089678511, 'I-MC': 0.047411764705882355}, 'f1': {'O': 0.8478644265577553, 'B-C': 0.12576832151300235, 'I-C': 0.12748198910560535, 'B-P': 0.46480776317405725, 'I-P': 0.770795284741823, 'B-MC': 0.06233062330623307, 'I-MC': 0.08549909833457091}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6885107379799045, 'recall': 0.6885107379799045, 'f1': 0.6885107379799045, 'support': None}, 'macro_avg': {'precision': 0.40945092930903015, 'recall': 0.3804712997977509, 'f1': 0.35493535810472104, 'support': None}, 'weighted_avg': {'precision': 0.6323224980978729, 'recall': 0.6885107379799045, 'f1': 0.6365266236616822, 'support': None}}
			------------EPOCH 23---------------
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0159, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8255568158383172, 'B-C': 0.15018315018315018, 'I-C': 0.2619047619047619, 'B-P': 0.3664806695894779, 'I-P': 0.6863960381181061, 'B-MC': 0.14965986394557823, 'I-MC': 0.4207650273224044}, 'recall': {'O': 0.8711678137156226, 'B-C': 0.1388653683319221, 'I-C': 0.10663924794359576, 'B-P': 0.6067304519960409, 'I-P': 0.8721136428639528, 'B-MC': 0.03722504230118443, 'I-MC': 0.045294117647058825}, 'f1': {'O': 0.8477492621073948, 'B-C': 0.14430268367795862, 'I-C': 0.15156576200417538, 'B-P': 0.4569511740588893, 'I-P': 0.7681894524689286, 'B-MC': 0.05962059620596206, 'I-MC': 0.08178438661710039}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6859255912791038, 'recall': 0.6859255912791038, 'f1': 0.6859255912791038, 'support': None}, 'macro_avg': {'precision': 0.4087066181288281, 'recall': 0.3825765263999111, 'f1': 0.358594759591487, 'support': None}, 'weighted_avg': {'precision': 0.6337966041335558, 'recall': 0.6859255912791038, 'f1': 0.6384835417762484, 'support': None}}
			------------EPOCH 24---------------
Loss:  tensor(0.0044, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0133, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8277279425070444, 'B-C': 0.15102389078498293, 'I-C': 0.2638888888888889, 'B-P': 0.3660839863371509, 'I-P': 0.6882977110807943, 'B-MC': 0.1476510067114094, 'I-MC': 0.42389006342494717}, 'recall': {'O': 0.8710045972634042, 'B-C': 0.14987298899237933, 'I-C': 0.11833137485311399, 'B-P': 0.6011217419993401, 'I-P': 0.8658022690437601, 'B-MC': 0.03722504230118443, 'I-MC': 0.04717647058823529}, 'f1': {'O': 0.8488150151105457, 'B-C': 0.1504462388440289, 'I-C': 0.16339445075450265, 'B-P': 0.455044955044955, 'I-P': 0.7669129755520838, 'B-MC': 0.059459459459459456, 'I-MC': 0.0849036629261063}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6848714537894569, 'recall': 0.6848714537894569, 'f1': 0.6848714537894569, 'support': None}, 'macro_avg': {'precision': 0.40979478424788823, 'recall': 0.3843620692916311, 'f1': 0.3612823939559545, 'support': None}, 'weighted_avg': {'precision': 0.6357917852797736, 'recall': 0.6848714537894569, 'f1': 0.6401689403189013, 'support': None}}
			------------EPOCH 25---------------
Loss:  tensor(0.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0118, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8307892341698089, 'B-C': 0.15547703180212014, 'I-C': 0.26311497689589564, 'B-P': 0.3702144718380437, 'I-P': 0.6872075000376205, 'B-MC': 0.16025641025641027, 'I-MC': 0.4259634888438134}, 'recall': {'O': 0.8690732025788199, 'B-C': 0.14902624894157493, 'I-C': 0.11374853113983549, 'B-P': 0.6093698449356648, 'I-P': 0.8707598436457241, 'B-MC': 0.04230118443316413, 'I-MC': 0.04941176470588235}, 'f1': {'O': 0.8495001063603489, 'B-C': 0.15218331171638566, 'I-C': 0.1588317335302322, 'B-P': 0.46059850374064837, 'I-P': 0.7681710373597538, 'B-MC': 0.06693440428380187, 'I-MC': 0.0885515496521189}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6861849425662392, 'recall': 0.6861849425662392, 'f1': 0.6861849425662392, 'support': None}, 'macro_avg': {'precision': 0.41328901626338743, 'recall': 0.3862415171972379, 'f1': 0.3635386638061842, 'support': None}, 'weighted_avg': {'precision': 0.6365032495535884, 'recall': 0.6861849425662392, 'f1': 0.6407362943710674, 'support': None}}
			------------EPOCH 26---------------
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0098, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8338741756516278, 'B-C': 0.14575289575289574, 'I-C': 0.2558246474555487, 'B-P': 0.37023127100217434, 'I-P': 0.68397113945805, 'B-MC': 0.15294117647058825, 'I-MC': 0.4277400581959263}, 'recall': {'O': 0.8667881722477626, 'B-C': 0.12785774767146485, 'I-C': 0.09806110458284371, 'B-P': 0.6179478719894425, 'I-P': 0.8802745733625703, 'B-MC': 0.043993231810490696, 'I-MC': 0.05188235294117647}, 'f1': {'O': 0.8500126712283088, 'B-C': 0.13622011727559766, 'I-C': 0.14177709819911655, 'B-P': 0.4630407911001236, 'I-P': 0.7698054059462073, 'B-MC': 0.06833114323258871, 'I-MC': 0.09254013220018886}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6876155577307599, 'recall': 0.6876155577307599, 'f1': 0.6876155577307599, 'support': None}, 'macro_avg': {'precision': 0.41004790914097305, 'recall': 0.38382929351510725, 'f1': 0.36024676559744734, 'support': None}, 'weighted_avg': {'precision': 0.6349884493466155, 'recall': 0.6876155577307599, 'f1': 0.6393773390465969, 'support': None}}
			------------EPOCH 27---------------
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0078, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.836466412514789, 'B-C': 0.15128755364806867, 'I-C': 0.260242251514072, 'B-P': 0.3711620676253401, 'I-P': 0.6816788768570679, 'B-MC': 0.17318435754189945, 'I-MC': 0.4287011807447775}, 'recall': {'O': 0.8654552378879791, 'B-C': 0.11939034716342083, 'I-C': 0.08584018801410105, 'B-P': 0.6301550643352029, 'I-P': 0.8906473448374488, 'B-MC': 0.05245346869712352, 'I-MC': 0.05552941176470588}, 'f1': {'O': 0.850713941922028, 'B-C': 0.13345953620444864, 'I-C': 0.1290978174427852, 'B-P': 0.4671639965757613, 'I-P': 0.7722767366306513, 'B-MC': 0.08051948051948053, 'I-MC': 0.0983230913446516}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6905437174242234, 'recall': 0.6905437174242234, 'f1': 0.6905437174242234, 'support': None}, 'macro_avg': {'precision': 0.41467467149228787, 'recall': 0.3856387232428546, 'f1': 0.3616506572342581, 'support': None}, 'weighted_avg': {'precision': 0.6356556854609614, 'recall': 0.6905437174242234, 'f1': 0.6394206979039524, 'support': None}}
			------------EPOCH 28---------------
Loss:  tensor(0.0023, 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>)
				 {'precision': {'O': 0.8360591081194784, 'B-C': 0.14536928487690504, 'I-C': 0.2562536931258617, 'B-P': 0.37024952015355084, 'I-P': 0.6804700291232595, 'B-MC': 0.1711229946524064, 'I-MC': 0.41457068516912404}, 'recall': {'O': 0.864965588531324, 'B-C': 0.10499576629974598, 'I-C': 0.07643948296122209, 'B-P': 0.6364236225668096, 'I-P': 0.8954905138716751, 'B-MC': 0.05414551607445008, 'I-MC': 0.05623529411764706}, 'f1': {'O': 0.8502667361918896, 'B-C': 0.12192723697148475, 'I-C': 0.11775354120468841, 'B-P': 0.4681470695303967, 'I-P': 0.7733118176878366, 'B-MC': 0.08226221079691516, 'I-MC': 0.09903656894229773}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6912548419212075, 'recall': 0.6912548419212075, 'f1': 0.6912548419212075, 'support': None}, 'macro_avg': {'precision': 0.4105850450315122, 'recall': 0.38409939777469626, 'f1': 0.3589578830465013, 'support': None}, 'weighted_avg': {'precision': 0.6333354193773378, 'recall': 0.6912548419212075, 'f1': 0.6380923179838609, 'support': None}}
			------------EPOCH 29---------------
Loss:  tensor(0.0021, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0052, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8345510252180062, 'B-C': 0.1475609756097561, 'I-C': 0.25908437692465613, 'B-P': 0.3666158536585366, 'I-P': 0.6806392720528573, 'B-MC': 0.1875, 'I-MC': 0.42594142259414225}, 'recall': {'O': 0.8669241859579445, 'B-C': 0.10245554614733277, 'I-C': 0.07414806110458284, 'B-P': 0.6347740019795447, 'I-P': 0.8957002574125275, 'B-MC': 0.06091370558375635, 'I-MC': 0.05988235294117647}, 'f1': {'O': 0.8504296312109729, 'B-C': 0.12093953023488255, 'I-C': 0.1152985245077886, 'B-P': 0.46479043362724964, 'I-P': 0.7734993125365345, 'B-MC': 0.09195402298850573, 'I-MC': 0.10500257864878802}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6918488400304529, 'recall': 0.6918488400304529, 'f1': 0.6918488400304529, 'support': None}, 'macro_avg': {'precision': 0.4145561322939935, 'recall': 0.3849711587324093, 'f1': 0.3602734333935317, 'support': None}, 'weighted_avg': {'precision': 0.6341680237665608, 'recall': 0.6918488400304529, 'f1': 0.6382524085508972, 'support': None}}
			------------EPOCH 30---------------
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0042, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8315285297792586, 'B-C': 0.14792176039119803, 'I-C': 0.263911620294599, 'B-P': 0.365003808073115, 'I-P': 0.6819445050707873, 'B-MC': 0.19387755102040816, 'I-MC': 0.42288961038961037}, 'recall': {'O': 0.8689643916106744, 'B-C': 0.10245554614733277, 'I-C': 0.07579318448883667, 'B-P': 0.6324645331573738, 'I-P': 0.893660024787873, 'B-MC': 0.06429780033840947, 'I-MC': 0.061294117647058825}, 'f1': {'O': 0.8498343908376232, 'B-C': 0.12106053026513255, 'I-C': 0.11776519992696734, 'B-P': 0.46287576964867805, 'I-P': 0.7735780543359853, 'B-MC': 0.09656925031766199, 'I-MC': 0.1070694615700781}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6918739385421111, 'recall': 0.6918739385421111, 'f1': 0.6918739385421111, 'support': None}, 'macro_avg': {'precision': 0.4152967692884252, 'recall': 0.38556137116822276, 'f1': 0.3612503795574466, 'support': None}, 'weighted_avg': {'precision': 0.6342757079145915, 'recall': 0.6918739385421111, 'f1': 0.6385775719559376, 'support': None}}
	Data split: 6k
			------------EPOCH 1---------------
Loss:  tensor(0.9708, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6691, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1106, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5648, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8283, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.6155051055814414, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.2109375, 'I-P': 0.6287747468296688, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.8444547210358804, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.23160673045199603, 'I-P': 0.7884831728477453, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.712028074682325, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.2207894323006762, 'I-P': 0.6996303220512474, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6115419688945779, 'recall': 0.6115419688945779, 'f1': 0.6115419688945779, 'support': None}, 'macro_avg': {'precision': 0.2078881932015872, 'recall': 0.26636351776223166, 'f1': 0.23320683271917836, 'support': None}, 'weighted_avg': {'precision': 0.4705303846452438, 'recall': 0.6115419688945779, 'f1': 0.5315545939703166, 'support': None}}
			------------EPOCH 2---------------
Loss:  tensor(0.7563, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2818, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3789, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7140, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.5798509717047629, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.2854539933191619, 'I-P': 0.6847484554280671, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.939881940099562, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.31012867040580666, 'I-P': 0.7396510630184002, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.7172200483668407, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.297280202403542, 'I-P': 0.7111416655208763, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.62145588099959, 'recall': 0.62145588099959, 'f1': 0.62145588099959, 'support': None}, 'macro_avg': {'precision': 0.22143620292171312, 'recall': 0.284237381931967, 'f1': 0.2465202737558941, 'support': None}, 'weighted_avg': {'precision': 0.486013815639001, 'recall': 0.62145588099959, 'f1': 0.540141782661454, 'support': None}}
			------------EPOCH 3---------------
Loss:  tensor(0.6836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4216, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1573, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3156, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3345, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6313, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7152242766649546, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.4193138500635324, 'I-P': 0.6785496471408242, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.9091428415984332, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.5443747937974266, 'I-P': 0.8910096291352846, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.8006084633903867, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.4737295434969854, 'I-P': 0.770400046162343, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6843527512151862, 'recall': 0.6843527512151862, 'f1': 0.6843527512151862, 'support': None}, 'macro_avg': {'precision': 0.2590125391241873, 'recall': 0.3349324663615921, 'f1': 0.2921054361499594, 'support': None}, 'weighted_avg': {'precision': 0.5283222996789356, 'recall': 0.6843527512151862, 'f1': 0.5962626006242624, 'support': None}}
			------------EPOCH 4---------------
Loss:  tensor(0.6009, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6955, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0141, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2876, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5628, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8017401650925857, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.46832740213523133, 'I-P': 0.6649635133873184, 'B-MC': 0.5, 'I-MC': 1.0}, 'recall': {'O': 0.8798182856831969, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.651270207852194, 'I-P': 0.9504242539803603, 'B-MC': 0.001692047377326565, 'I-MC': 0.001411764705882353}, 'f1': {'O': 0.8389665637726648, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.5448523323212807, 'I-P': 0.7824715079589337, 'B-MC': 0.0033726812816188873, 'I-MC': 0.002819548872180451}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7042224062779744, 'recall': 0.7042224062779744, 'f1': 0.7042224062779744, 'support': None}, 'macro_avg': {'precision': 0.4907187258021622, 'recall': 0.3549452227998514, 'f1': 0.3103546620295255, 'support': None}, 'weighted_avg': {'precision': 0.6237965851336358, 'recall': 0.7042224062779744, 'f1': 0.6153768116948186, 'support': None}}
			------------EPOCH 5---------------
Loss:  tensor(0.5136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3091, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5935, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2561, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4925, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8032301812353594, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.45836200963523743, 'I-P': 0.6680790578042507, 'B-MC': 0.19767441860465115, 'I-MC': 0.5022761760242792}, 'recall': {'O': 0.8861293218356411, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.6591883866710656, 'I-P': 0.9410048622366288, 'B-MC': 0.028764805414551606, 'I-MC': 0.038941176470588236}, 'f1': {'O': 0.8426457654301827, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.5407307171853857, 'I-P': 0.7813957170565649, 'B-MC': 0.050221565731166914, 'I-MC': 0.07227863303854133}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7050339248215914, 'recall': 0.7050339248215914, 'f1': 0.7050339248215914, 'support': None}, 'macro_avg': {'precision': 0.3756602633291112, 'recall': 0.36486122180406794, 'f1': 0.3267531997774059, 'support': None}, 'weighted_avg': {'precision': 0.588479943844114, 'recall': 0.7050339248215914, 'f1': 0.6211028578334471, 'support': None}}
			------------EPOCH 6---------------
Loss:  tensor(0.4405, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2707, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7505, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4178, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8187397811596026, 'B-C': 0.3333333333333333, 'I-C': 0.3333333333333333, 'B-P': 0.4581181226139681, 'I-P': 0.6741945608121939, 'B-MC': 0.19724770642201836, 'I-MC': 0.4389291689905187}, 'recall': {'O': 0.8854220505426947, 'B-C': 0.002540220152413209, 'I-C': 0.00035252643948296123, 'B-P': 0.673045199604091, 'I-P': 0.9420726475355133, 'B-MC': 0.0727580372250423, 'I-MC': 0.09258823529411765}, 'f1': {'O': 0.8507763082231167, 'B-C': 0.0050420168067226885, 'I-C': 0.0007043080173729311, 'B-P': 0.5451630144307856, 'I-P': 0.7859347162127768, 'B-MC': 0.10630407911001237, 'I-MC': 0.15291945982706695}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7097440788427913, 'recall': 0.7097440788427913, 'f1': 0.7097440788427913, 'support': None}, 'macro_avg': {'precision': 0.464842286666424, 'recall': 0.3812541309704793, 'f1': 0.3495491289468363, 'support': None}, 'weighted_avg': {'precision': 0.6421776656506908, 'recall': 0.7097440788427913, 'f1': 0.6318693055132837, 'support': None}}
			------------EPOCH 7---------------
Loss:  tensor(0.3827, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4280, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1616, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3486, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.781772259465584, 'B-C': 0.0684931506849315, 'I-C': 0.21768707482993196, 'B-P': 0.4791318864774624, 'I-P': 0.6992257819017372, 'B-MC': 0.1792452830188679, 'I-MC': 0.34302023871302545}, 'recall': {'O': 0.9009276135034412, 'B-C': 0.004233700254022015, 'I-C': 0.0037602820211515863, 'B-P': 0.6628175519630485, 'I-P': 0.910973400705501, 'B-MC': 0.12859560067681894, 'I-MC': 0.1555294117647059}, 'f1': {'O': 0.8371311216429701, 'B-C': 0.007974481658692184, 'I-C': 0.0073928612683377614, 'B-P': 0.5562015503875969, 'I-P': 0.7911767628258205, 'B-MC': 0.14975369458128077, 'I-MC': 0.21401975068803628}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7058621757063139, 'recall': 0.7058621757063139, 'f1': 0.7058621757063139, 'support': None}, 'macro_avg': {'precision': 0.39551081072736294, 'recall': 0.39526250869838414, 'f1': 0.3662357461503906, 'support': None}, 'weighted_avg': {'precision': 0.6163308094759711, 'recall': 0.7058621757063139, 'f1': 0.6357938748279837, 'support': None}}
			------------EPOCH 8---------------
Loss:  tensor(0.3259, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1915, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2881, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8203208290977612, 'B-C': 0.2290836653386454, 'I-C': 0.384, 'B-P': 0.5224151334542627, 'I-P': 0.7349239810910949, 'B-MC': 0.1900121802679659, 'I-MC': 0.34413775639402383}, 'recall': {'O': 0.9000299230162401, 'B-C': 0.09737510584250635, 'I-C': 0.07896592244418331, 'B-P': 0.6651270207852193, 'I-P': 0.8774525693583755, 'B-MC': 0.2639593908629442, 'I-MC': 0.31976470588235295}, 'f1': {'O': 0.8583287934210185, 'B-C': 0.13666072489601902, 'I-C': 0.1309941520467836, 'B-P': 0.5851959361393322, 'I-P': 0.7998887546605714, 'B-MC': 0.2209631728045326, 'I-MC': 0.331503841931943}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7149143722443926, 'recall': 0.7149143722443926, 'f1': 0.7149143722443926, 'support': None}, 'macro_avg': {'precision': 0.46069907794910764, 'recall': 0.4575249483131173, 'f1': 0.43764791084288573, 'support': None}, 'weighted_avg': {'precision': 0.6703481029117423, 'recall': 0.7149143722443926, 'f1': 0.6744489460386142, 'support': None}}
			------------EPOCH 9---------------
Loss:  tensor(0.2483, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1409, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2675, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0898, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2440, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8831794010635321, 'B-C': 0.26579925650557623, 'I-C': 0.38375973303670746, 'B-P': 0.5292368681863231, 'I-P': 0.7020288125479499, 'B-MC': 0.284037558685446, 'I-MC': 0.4775395610005105}, 'recall': {'O': 0.8584097277005522, 'B-C': 0.12108382726502964, 'I-C': 0.10135135135135136, 'B-P': 0.7047179148795777, 'I-P': 0.942187053103251, 'B-MC': 0.20473773265651438, 'I-MC': 0.22011764705882353}, 'f1': {'O': 0.8706184215971637, 'B-C': 0.1663757998836533, 'I-C': 0.16035324192423892, 'B-P': 0.6044997877458611, 'I-P': 0.804568879191735, 'B-MC': 0.23795476892822026, 'I-MC': 0.30133676920599134}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7275640221201549, 'recall': 0.7275640221201549, 'f1': 0.7275640221201548, 'support': None}, 'macro_avg': {'precision': 0.5036544558608637, 'recall': 0.4503721791450142, 'f1': 0.44938680978240914, 'support': None}, 'weighted_avg': {'precision': 0.6856999391608043, 'recall': 0.7275640221201549, 'f1': 0.6831844433242328, 'support': None}}
			------------EPOCH 10---------------
Loss:  tensor(0.1953, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1959, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2193, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7177587404491781, 'B-C': 0.20634920634920634, 'I-C': 0.4340344168260038, 'B-P': 0.47317201472908993, 'I-P': 0.7606557956916982, 'B-MC': 0.15940054495912806, 'I-MC': 0.33239901071723}, 'recall': {'O': 0.9276135034411469, 'B-C': 0.12108382726502964, 'I-C': 0.10669800235017626, 'B-P': 0.5935334872979214, 'I-P': 0.8200781771379541, 'B-MC': 0.19796954314720813, 'I-MC': 0.2371764705882353}, 'f1': {'O': 0.8093034294529489, 'B-C': 0.15261472785485594, 'I-C': 0.17128843614412376, 'B-P': 0.5265622713303088, 'I-P': 0.7892500940479138, 'B-MC': 0.17660377358490564, 'I-MC': 0.2768280123583934}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6943921558784898, 'recall': 0.6943921558784898, 'f1': 0.6943921558784898, 'support': None}, 'macro_avg': {'precision': 0.44053853281736205, 'recall': 0.42916471588966737, 'f1': 0.4146358206819215, 'support': None}, 'weighted_avg': {'precision': 0.6547605028034327, 'recall': 0.6943921558784898, 'f1': 0.6550043329139327, 'support': None}}
			------------EPOCH 11---------------
Loss:  tensor(0.1817, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1643, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0463, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0895, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1729, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.935856640428739, 'B-C': 0.24753173483779972, 'I-C': 0.3640357299751062, 'B-P': 0.5417335473515249, 'I-P': 0.745922034835499, 'B-MC': 0.24145785876993167, 'I-MC': 0.3674791004356529}, 'recall': {'O': 0.7600446124969397, 'B-C': 0.2972057578323455, 'I-C': 0.29212690951821385, 'B-P': 0.6680963378422963, 'I-P': 0.8745542949756888, 'B-MC': 0.3587140439932318, 'I-MC': 0.36717647058823527}, 'f1': {'O': 0.8388375165125495, 'B-C': 0.2701038861100423, 'I-C': 0.3241410782971511, 'B-P': 0.5983158516767617, 'I-P': 0.8051327961802448, 'B-MC': 0.28863172226004086, 'I-MC': 0.36732772318013296}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7068326514904333, 'recall': 0.7068326514904333, 'f1': 0.7068326514904333, 'support': None}, 'macro_avg': {'precision': 0.49200237809060765, 'recall': 0.5168454896067073, 'f1': 0.49892722488813185, 'support': None}, 'weighted_avg': {'precision': 0.7104501711637085, 'recall': 0.7068326514904333, 'f1': 0.7027912190650245, 'support': None}}
			------------EPOCH 12---------------
Loss:  tensor(0.1369, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1699, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0468, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1532, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8328358963982193, 'B-C': 0.23598130841121495, 'I-C': 0.43842975206611573, 'B-P': 0.4852292768959436, 'I-P': 0.7205543071161049, 'B-MC': 0.24332810047095763, 'I-MC': 0.4760628111834546}, 'recall': {'O': 0.8957046870324529, 'B-C': 0.0855207451312447, 'I-C': 0.062338425381903644, 'B-P': 0.7261629825140218, 'I-P': 0.9170940985794642, 'B-MC': 0.2622673434856176, 'I-MC': 0.2924705882352941}, 'f1': {'O': 0.8631269905763005, 'B-C': 0.12554381603480422, 'I-C': 0.10915637860082304, 'B-P': 0.5817364873794106, 'I-P': 0.8070304962456478, 'B-MC': 0.252442996742671, 'I-MC': 0.3623378516251275}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7280910908649784, 'recall': 0.7280910908649784, 'f1': 0.7280910908649784, 'support': None}, 'macro_avg': {'precision': 0.4903459217917158, 'recall': 0.463079838622857, 'f1': 0.4430535738863978, 'support': None}, 'weighted_avg': {'precision': 0.6844129045696634, 'recall': 0.7280910908649784, 'f1': 0.6780994012318098, 'support': None}}
			------------EPOCH 13---------------
Loss:  tensor(0.0710, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0439, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1162, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0321, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0680, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1607, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7346306848725943, 'B-C': 0.2057142857142857, 'I-C': 0.4023396699394193, 'B-P': 0.4669750706759188, 'I-P': 0.7796348340747082, 'B-MC': 0.22348484848484848, 'I-MC': 0.45617631983598156}, 'recall': {'O': 0.9293544789314763, 'B-C': 0.2438611346316681, 'I-C': 0.2263219741480611, 'B-P': 0.5994721214120752, 'I-P': 0.7987224711602632, 'B-MC': 0.1996615905245347, 'I-MC': 0.20941176470588235}, 'f1': {'O': 0.8205990440275743, 'B-C': 0.22316931421929487, 'I-C': 0.2896894036248778, 'B-P': 0.5249927766541461, 'I-P': 0.7890632358204457, 'B-MC': 0.21090259159964253, 'I-MC': 0.28705047572972103}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7019886387403894, 'recall': 0.7019886387403894, 'f1': 0.7019886387403894, 'support': None}, 'macro_avg': {'precision': 0.4669936733711081, 'recall': 0.4581150765019944, 'f1': 0.4493524059536718, 'support': None}, 'weighted_avg': {'precision': 0.6727192307868893, 'recall': 0.7019886387403894, 'f1': 0.6768095194577557, 'support': None}}
			------------EPOCH 14---------------
Loss:  tensor(0.0502, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0372, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0809, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0732, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1875, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8280269227860546, 'B-C': 0.23661567877629064, 'I-C': 0.3489424628069547, 'B-P': 0.5768600458865946, 'I-P': 0.8067397895850715, 'B-MC': 0.30939226519337015, 'I-MC': 0.5089717046238785}, 'recall': {'O': 0.8935284676695411, 'B-C': 0.4191363251481795, 'I-C': 0.4575205640423032, 'B-P': 0.580666446717255, 'I-P': 0.7559157212317666, 'B-MC': 0.1895093062605753, 'I-MC': 0.17352941176470588}, 'f1': {'O': 0.8595315975402329, 'B-C': 0.30247479376718606, 'I-C': 0.39592231035184056, 'B-P': 0.5787569878329496, 'I-P': 0.7805012501722679, 'B-MC': 0.23504721930745015, 'I-MC': 0.25881733637480264}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7037622668975729, 'recall': 0.7037622668975729, 'f1': 0.7037622668975729, 'support': None}, 'macro_avg': {'precision': 0.5165069813797449, 'recall': 0.4956866061191895, 'f1': 0.48729307076381856, 'support': None}, 'weighted_avg': {'precision': 0.7130033960298414, 'recall': 0.7037622668975729, 'f1': 0.7004118019226017, 'support': None}}
			------------EPOCH 15---------------
Loss:  tensor(0.0364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0253, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0510, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0596, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1039, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.869513287548522, 'B-C': 0.2691029900332226, 'I-C': 0.42668621700879766, 'B-P': 0.5243961352657005, 'I-P': 0.7116941029984508, 'B-MC': 0.31494252873563217, 'I-MC': 0.5291553133514987}, 'recall': {'O': 0.8713582329098774, 'B-C': 0.1371718882303133, 'I-C': 0.11968272620446534, 'B-P': 0.7162652589904323, 'I-P': 0.9372866812851559, 'B-MC': 0.23181049069373943, 'I-MC': 0.22847058823529412}, 'f1': {'O': 0.8704347826086957, 'B-C': 0.18171620863712845, 'I-C': 0.18693218316967974, 'B-P': 0.6054943522521267, 'I-P': 0.8090590384647036, 'B-MC': 0.267056530214425, 'I-MC': 0.31914543960558756}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7331860887316048, 'recall': 0.7331860887316048, 'f1': 0.7331860887316048, 'support': None}, 'macro_avg': {'precision': 0.5207843678488321, 'recall': 0.4631494095070397, 'f1': 0.4628340764217639, 'support': None}, 'weighted_avg': {'precision': 0.6955833406454064, 'recall': 0.7331860887316048, 'f1': 0.6904698185661092, 'support': None}}
			------------EPOCH 16---------------
Loss:  tensor(0.0326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0226, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0445, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0564, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0879, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8575669214805475, 'B-C': 0.24781849912739964, 'I-C': 0.41608910891089107, 'B-P': 0.49787993751394777, 'I-P': 0.7211784224922649, 'B-MC': 0.29692832764505117, 'I-MC': 0.49026439844230374}, 'recall': {'O': 0.8880335137781888, 'B-C': 0.12023708721422523, 'I-C': 0.09876615746180964, 'B-P': 0.7360607060376113, 'I-P': 0.9199923729621509, 'B-MC': 0.29441624365482233, 'I-MC': 0.28141176470588236}, 'f1': {'O': 0.8725343454321912, 'B-C': 0.16191562143671606, 'I-C': 0.15963912630579297, 'B-P': 0.593982960596379, 'I-P': 0.8085430840902235, 'B-MC': 0.29566694987255737, 'I-MC': 0.35757530458180736}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7321570497536163, 'recall': 0.7321570497536163, 'f1': 0.7321570497536163, 'support': None}, 'macro_avg': {'precision': 0.5039608022303437, 'recall': 0.476988263687813, 'f1': 0.46426534175938106, 'support': None}, 'weighted_avg': {'precision': 0.690824288401046, 'recall': 0.7321570497536163, 'f1': 0.689389595881113, 'support': None}}
			------------EPOCH 17---------------
Loss:  tensor(0.0224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0147, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0298, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0396, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0084, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0333, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0730, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8314027670060794, 'B-C': 0.23800195886385897, 'I-C': 0.4138120032885722, 'B-P': 0.4716896007218588, 'I-P': 0.7466295880697988, 'B-MC': 0.2492063492063492, 'I-MC': 0.47491995731056563}, 'recall': {'O': 0.904001523353554, 'B-C': 0.20575783234546993, 'I-C': 0.17743830787309048, 'B-P': 0.6898713295941933, 'I-P': 0.875412336733721, 'B-MC': 0.2656514382402707, 'I-MC': 0.26176470588235295}, 'f1': {'O': 0.8661836000625553, 'B-C': 0.22070844686648503, 'I-C': 0.24837568879019653, 'B-P': 0.5602893890675241, 'I-P': 0.805908580255582, 'B-MC': 0.2571662571662572, 'I-MC': 0.3375047402351157}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7268445314526182, 'recall': 0.7268445314526182, 'f1': 0.7268445314526183, 'support': None}, 'macro_avg': {'precision': 0.4893803177810119, 'recall': 0.48284249628895043, 'f1': 0.4708766717776737, 'support': None}, 'weighted_avg': {'precision': 0.6915320821133744, 'recall': 0.7268445314526182, 'f1': 0.6970247755825738, 'support': None}}
			------------EPOCH 18---------------
Loss:  tensor(0.0172, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0307, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0621, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.825160443045816, 'B-C': 0.23341946597760552, 'I-C': 0.4106755057720882, 'B-P': 0.4798883980469658, 'I-P': 0.7483540240427135, 'B-MC': 0.27896995708154504, 'I-MC': 0.5187663660168752}, 'recall': {'O': 0.9058785125540655, 'B-C': 0.22946655376799321, 'I-C': 0.21110458284371328, 'B-P': 0.6809633784229627, 'I-P': 0.8712556011059205, 'B-MC': 0.21996615905245348, 'I-MC': 0.20976470588235294}, 'f1': {'O': 0.8636375424673876, 'B-C': 0.2314261315115286, 'I-C': 0.27886219876595914, 'B-P': 0.563011456628478, 'I-P': 0.8051417143159212, 'B-MC': 0.24597918637653737, 'I-MC': 0.29873502555080844}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.726476419948297, 'recall': 0.726476419948297, 'f1': 0.7264764199482971, 'support': None}, 'macro_avg': {'precision': 0.4993191657119443, 'recall': 0.47548564194706594, 'f1': 0.4695418936595172, 'support': None}, 'weighted_avg': {'precision': 0.6933500859669773, 'recall': 0.726476419948297, 'f1': 0.6976089060531351, 'support': None}}
			------------EPOCH 19---------------
Loss:  tensor(0.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0076, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0476, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8306261593222038, 'B-C': 0.23649906890130354, 'I-C': 0.39653379549393414, 'B-P': 0.49928639391056134, 'I-P': 0.7431013196081261, 'B-MC': 0.3139240506329114, 'I-MC': 0.5302721088435374}, 'recall': {'O': 0.9014172628600963, 'B-C': 0.21507197290431837, 'I-C': 0.20164512338425383, 'B-P': 0.6925107225338172, 'I-P': 0.8836876728000763, 'B-MC': 0.2098138747884941, 'I-MC': 0.18341176470588236}, 'f1': {'O': 0.8645750440284391, 'B-C': 0.22527716186252772, 'I-C': 0.26734177215189875, 'B-P': 0.5802349689011749, 'I-P': 0.8073197923561998, 'B-MC': 0.2515212981744422, 'I-MC': 0.27255244755244756}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7274385295618636, 'recall': 0.7274385295618636, 'f1': 0.7274385295618636, 'support': None}, 'macro_avg': {'precision': 0.5071775566732254, 'recall': 0.4696511991395626, 'f1': 0.46697464071816147, 'support': None}, 'weighted_avg': {'precision': 0.6922260426206857, 'recall': 0.7274385295618636, 'f1': 0.695753968292144, 'support': None}}
			------------EPOCH 20---------------
Loss:  tensor(0.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0057, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0201, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0371, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8319439897247337, 'B-C': 0.2535885167464115, 'I-C': 0.4063179581091908, 'B-P': 0.5091575091575091, 'I-P': 0.7437812934909539, 'B-MC': 0.31343283582089554, 'I-MC': 0.524092409240924}, 'recall': {'O': 0.8986153804303474, 'B-C': 0.2243861134631668, 'I-C': 0.20857814336075206, 'B-P': 0.6878917848894754, 'I-P': 0.88656687958814, 'B-MC': 0.2131979695431472, 'I-MC': 0.1868235294117647}, 'f1': {'O': 0.8639953967672752, 'B-C': 0.23809523809523808, 'I-C': 0.275653220483752, 'B-P': 0.5851810272242491, 'I-P': 0.8089215191635206, 'B-MC': 0.2537764350453173, 'I-MC': 0.2754553339115351}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7290615666490977, 'recall': 0.7290615666490977, 'f1': 0.7290615666490977, 'support': None}, 'macro_avg': {'precision': 0.511759216041517, 'recall': 0.47229425724097046, 'f1': 0.47158259581298395, 'support': None}, 'weighted_avg': {'precision': 0.6943001558071629, 'recall': 0.7290615666490977, 'f1': 0.6979316153133809, 'support': None}}
			------------EPOCH 21---------------
Loss:  tensor(0.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0136, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0164, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0287, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8321651875756353, 'B-C': 0.2632084534101825, 'I-C': 0.41880050073972913, 'B-P': 0.5158808933002481, 'I-P': 0.7463293826286928, 'B-MC': 0.3060747663551402, 'I-MC': 0.5206124852767963}, 'recall': {'O': 0.8978809063953647, 'B-C': 0.23200677392040644, 'I-C': 0.21621621621621623, 'B-P': 0.6859122401847575, 'I-P': 0.8849079988559443, 'B-MC': 0.22165820642978004, 'I-MC': 0.208}, 'f1': {'O': 0.8637749427543342, 'B-C': 0.24662466246624662, 'I-C': 0.2851939396287829, 'B-P': 0.5888684322333947, 'I-P': 0.8097323516069371, 'B-MC': 0.25711481844946027, 'I-MC': 0.29724277067921995}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7307682654418592, 'recall': 0.7307682654418592, 'f1': 0.7307682654418591, 'support': None}, 'macro_avg': {'precision': 0.5147245241837748, 'recall': 0.47808319171463853, 'f1': 0.47836455968833935, 'support': None}, 'weighted_avg': {'precision': 0.6972453039668955, 'recall': 0.7307682654418592, 'f1': 0.7013217466560319, 'support': None}}
			------------EPOCH 22---------------
Loss:  tensor(0.0066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0150, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0235, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8318809187991134, 'B-C': 0.25783348254252464, 'I-C': 0.4095337873232059, 'B-P': 0.5174054595542199, 'I-P': 0.7501101088038106, 'B-MC': 0.2986425339366516, 'I-MC': 0.5159124087591241}, 'recall': {'O': 0.8984793667201654, 'B-C': 0.2438611346316681, 'I-C': 0.22967097532314923, 'B-P': 0.6816232266578687, 'I-P': 0.8768042711411955, 'B-MC': 0.2233502538071066, 'I-MC': 0.20788235294117646}, 'f1': {'O': 0.8638985156607598, 'B-C': 0.25065274151436034, 'I-C': 0.2942970073404856, 'B-P': 0.5882687927107061, 'I-P': 0.8085241059183458, 'B-MC': 0.2555663117134559, 'I-MC': 0.2963522012578616}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.729320917936233, 'recall': 0.729320917936233, 'f1': 0.729320917936233, 'support': None}, 'macro_avg': {'precision': 0.5116169571026643, 'recall': 0.4802387973174757, 'f1': 0.4796513823022822, 'support': None}, 'weighted_avg': {'precision': 0.6971117860538589, 'recall': 0.729320917936233, 'f1': 0.7020794295390823, 'support': None}}
			------------EPOCH 23---------------
Loss:  tensor(0.0056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0120, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0191, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8334132371123615, 'B-C': 0.25823686553873554, 'I-C': 0.4090015519917227, 'B-P': 0.5127443702053947, 'I-P': 0.748756138011772, 'B-MC': 0.31143552311435524, 'I-MC': 0.5228136882129277}, 'recall': {'O': 0.8984793667201654, 'B-C': 0.2455546147332769, 'I-C': 0.23225616921269096, 'B-P': 0.6836027713625866, 'I-P': 0.8780627323863095, 'B-MC': 0.21658206429780033, 'I-MC': 0.19411764705882353}, 'f1': {'O': 0.8647240548748559, 'B-C': 0.2517361111111111, 'I-C': 0.296271313471988, 'B-P': 0.5859728506787331, 'I-P': 0.8082705117291373, 'B-MC': 0.25548902195608786, 'I-MC': 0.28311599176389846}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7292958194245748, 'recall': 0.7292958194245748, 'f1': 0.7292958194245749, 'support': None}, 'macro_avg': {'precision': 0.5137716248838956, 'recall': 0.478379337967379, 'f1': 0.4779399793694017, 'support': None}, 'weighted_avg': {'precision': 0.6973530001144349, 'recall': 0.7292958194245748, 'f1': 0.7015140235740369, 'support': None}}
			------------EPOCH 24---------------
Loss:  tensor(0.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0029, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0104, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0167, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8363862075954498, 'B-C': 0.2506350550381033, 'I-C': 0.4056556805735338, 'B-P': 0.5127569977706218, 'I-P': 0.7507069188146647, 'B-MC': 0.3076923076923077, 'I-MC': 0.52}, 'recall': {'O': 0.8980441228475831, 'B-C': 0.2506350550381033, 'I-C': 0.23936545240893067, 'B-P': 0.6829429231276807, 'I-P': 0.8757555534369339, 'B-MC': 0.21658206429780033, 'I-MC': 0.19576470588235295}, 'f1': {'O': 0.8661192150278098, 'B-C': 0.2506350550381033, 'I-C': 0.3010752688172043, 'B-P': 0.5857385398981325, 'I-P': 0.8084241282804991, 'B-MC': 0.2542204568023833, 'I-MC': 0.28444444444444444}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7293125517656803, 'recall': 0.7293125517656803, 'f1': 0.7293125517656804, 'support': None}, 'macro_avg': {'precision': 0.5119761667835259, 'recall': 0.4798699824341979, 'f1': 0.47866530118693945, 'support': None}, 'weighted_avg': {'precision': 0.6983534542420825, 'recall': 0.7293125517656803, 'f1': 0.7027659273377685, 'support': None}}
			------------EPOCH 25---------------
Loss:  tensor(0.0043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0133, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8367920942607373, 'B-C': 0.25205254515599346, 'I-C': 0.40937138449672195, 'B-P': 0.5114656031904287, 'I-P': 0.7542321095311235, 'B-MC': 0.29490022172949004, 'I-MC': 0.5034662045060658}, 'recall': {'O': 0.8983433530099834, 'B-C': 0.25994919559695173, 'I-C': 0.24947121034077555, 'B-P': 0.6770042890135269, 'I-P': 0.870778911240347, 'B-MC': 0.22504230118443316, 'I-MC': 0.20505882352941177}, 'f1': {'O': 0.8664760055624064, 'B-C': 0.255939974989579, 'I-C': 0.31001752336448596, 'B-P': 0.5827062331392873, 'I-P': 0.8083261058109279, 'B-MC': 0.2552783109404991, 'I-MC': 0.29142283899013544}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7293041855951276, 'recall': 0.7293041855951276, 'f1': 0.7293041855951276, 'support': None}, 'macro_avg': {'precision': 0.5088971661243659, 'recall': 0.4836640119879186, 'f1': 0.4814524275424744, 'support': None}, 'weighted_avg': {'precision': 0.6992963481168256, 'recall': 0.7293041855951276, 'f1': 0.7045829599819888, 'support': None}}
			------------EPOCH 26---------------
Loss:  tensor(0.0038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0022, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0109, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8382039032323643, 'B-C': 0.25367965367965367, 'I-C': 0.41049825712528193, 'B-P': 0.508893280632411, 'I-P': 0.7504620467444104, 'B-MC': 0.29475982532751094, 'I-MC': 0.495995581331124}, 'recall': {'O': 0.897282446070564, 'B-C': 0.2480948348856901, 'I-C': 0.23525264394829612, 'B-P': 0.6796436819531507, 'I-P': 0.8748975116789017, 'B-MC': 0.22842639593908629, 'I-MC': 0.21129411764705883}, 'f1': {'O': 0.8667376138110442, 'B-C': 0.2508561643835616, 'I-C': 0.2990961380443714, 'B-P': 0.5820031077835852, 'I-P': 0.8079164685788742, 'B-MC': 0.25738798856053385, 'I-MC': 0.2963451860407557}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7291703268662835, 'recall': 0.7291703268662835, 'f1': 0.7291703268662835, 'support': None}, 'macro_avg': {'precision': 0.5074989354389652, 'recall': 0.4821273760175354, 'f1': 0.4800489524575324, 'support': None}, 'weighted_avg': {'precision': 0.697655738500142, 'recall': 0.7291703268662835, 'f1': 0.7032209741389688, 'support': None}}
			------------EPOCH 27---------------
Loss:  tensor(0.0034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0020, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0077, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0013, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0115, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8386932627722369, 'B-C': 0.2560553633217993, 'I-C': 0.4108865644358688, 'B-P': 0.5089596814335491, 'I-P': 0.7527627943691619, 'B-MC': 0.2839756592292089, 'I-MC': 0.48449910325390727}, 'recall': {'O': 0.8967111884877995, 'B-C': 0.2506350550381033, 'I-C': 0.23772032902467685, 'B-P': 0.674694820191356, 'I-P': 0.8728000762703785, 'B-MC': 0.23688663282571912, 'I-MC': 0.22247058823529411}, 'f1': {'O': 0.8667323999211201, 'B-C': 0.2533162173727, 'I-C': 0.30118733018200766, 'B-P': 0.5802241452688326, 'I-P': 0.8083494476967498, 'B-MC': 0.25830258302583026, 'I-MC': 0.3049262275255986}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7291619606957307, 'recall': 0.7291619606957307, 'f1': 0.7291619606957307, 'support': None}, 'macro_avg': {'precision': 0.5051189184022474, 'recall': 0.4845598128676182, 'f1': 0.4818626215704055, 'support': None}, 'weighted_avg': {'precision': 0.6980253100162319, 'recall': 0.7291619606957307, 'f1': 0.7043010524242398, 'support': None}}
			------------EPOCH 28---------------
Loss:  tensor(0.0031, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0018, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0072, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0047, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0064, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0164, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8404572945109348, 'B-C': 0.2615803814713896, 'I-C': 0.41665775686945367, 'B-P': 0.5066732575383095, 'I-P': 0.7497350442679884, 'B-MC': 0.28600405679513186, 'I-MC': 0.4815828770532603}, 'recall': {'O': 0.895922308968744, 'B-C': 0.2438611346316681, 'I-C': 0.22896592244418332, 'B-P': 0.6763444407786209, 'I-P': 0.8767661359519496, 'B-MC': 0.23857868020304568, 'I-MC': 0.22764705882352942}, 'f1': {'O': 0.8673039448043398, 'B-C': 0.252410166520596, 'I-C': 0.29552951882607215, 'B-P': 0.579341528896425, 'I-P': 0.8082899732808325, 'B-MC': 0.2601476014760148, 'I-MC': 0.3091548170634287}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7297643249755289, 'recall': 0.7297643249755289, 'f1': 0.729764324975529, 'support': None}, 'macro_avg': {'precision': 0.5060986669294955, 'recall': 0.4840122402573916, 'f1': 0.4817396501239584, 'support': None}, 'weighted_avg': {'precision': 0.6978604016490073, 'recall': 0.7297643249755289, 'f1': 0.7039236012377137, 'support': None}}
			------------EPOCH 29---------------
Loss:  tensor(0.0028, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0061, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0333, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8419489464116547, 'B-C': 0.25770308123249297, 'I-C': 0.41494050242397534, 'B-P': 0.5050036612155235, 'I-P': 0.746251069393553, 'B-MC': 0.2890792291220557, 'I-MC': 0.49396325459317586}, 'recall': {'O': 0.8945349691248878, 'B-C': 0.23370025402201525, 'I-C': 0.22126909518213866, 'B-P': 0.6826129990102277, 'I-P': 0.8815139670130613, 'B-MC': 0.22842639593908629, 'I-MC': 0.22141176470588236}, 'f1': {'O': 0.867445725289509, 'B-C': 0.24511545293072826, 'I-C': 0.2886266094420601, 'B-P': 0.5805274971941639, 'I-P': 0.8082625266617713, 'B-MC': 0.25519848771266546, 'I-MC': 0.3057676685621446}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7298898175338202, 'recall': 0.7298898175338202, 'f1': 0.7298898175338202, 'support': None}, 'macro_avg': {'precision': 0.5069842491989187, 'recall': 0.4804956349996142, 'f1': 0.4787062811132918, 'support': None}, 'weighted_avg': {'precision': 0.6973609486331581, 'recall': 0.7298898175338202, 'f1': 0.7026649021891861, 'support': None}}
			------------EPOCH 30---------------
Loss:  tensor(0.0026, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0015, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0065, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0058, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0550, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8425591810620602, 'B-C': 0.2501906941266209, 'I-C': 0.39567463444532003, 'B-P': 0.5158610271903323, 'I-P': 0.7611688202009965, 'B-MC': 0.2783300198807157, 'I-MC': 0.48367144977733795}, 'recall': {'O': 0.8955958760643072, 'B-C': 0.2777307366638442, 'I-C': 0.2655111633372503, 'B-P': 0.676014516661168, 'I-P': 0.8592811516827152, 'B-MC': 0.23688663282571912, 'I-MC': 0.23}, 'f1': {'O': 0.8682683685848409, 'B-C': 0.26324237560192615, 'I-C': 0.31778066875285677, 'B-P': 0.585177780951021, 'I-P': 0.8072548141513659, 'B-MC': 0.25594149908592323, 'I-MC': 0.3117525115611545}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7276811485078934, 'recall': 0.7276811485078934, 'f1': 0.7276811485078934, 'support': None}, 'macro_avg': {'precision': 0.503922260954769, 'recall': 0.4915742967478577, 'f1': 0.4870597169555841, 'support': None}, 'weighted_avg': {'precision': 0.7007667549862989, 'recall': 0.7276811485078934, 'f1': 0.7073533626297162, 'support': None}}
	Data split: 12k
			------------EPOCH 1---------------
Loss:  tensor(5.0271, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3476, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3793, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.3181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8752, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8586, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7851614282659825, 'B-C': 0.0196078431372549, 'I-C': 0.1976254308693987, 'B-P': 0.23220268006700168, 'I-P': 0.5401579986833444, 'B-MC': 0.0, 'I-MC': 0.005988023952095809}, 'recall': {'O': 0.49946954653029024, 'B-C': 0.007620660457239628, 'I-C': 0.030317273795534665, 'B-P': 0.36588584625536125, 'I-P': 0.9074077605110116, 'B-MC': 0.0, 'I-MC': 0.00011764705882352942}, 'f1': {'O': 0.6105476673427992, 'B-C': 0.01097560975609756, 'I-C': 0.052569914930467115, 'B-P': 0.2841040092224926, 'I-P': 0.6771969519093257, 'B-MC': 0.0, 'I-MC': 0.00023076035537094726}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.565427636807804, 'recall': 0.565427636807804, 'f1': 0.565427636807804, 'support': None}, 'macro_avg': {'precision': 0.25439191499643965, 'recall': 0.258688390658323, 'f1': 0.23366070193093616, 'support': None}, 'weighted_avg': {'precision': 0.51312528113221, 'recall': 0.565427636807804, 'f1': 0.4997173891213494, 'support': None}}
			------------EPOCH 2---------------
Loss:  tensor(3.3664, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2538, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6348, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6816, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7635, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3560, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.87917690642996, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.3772439281942978, 'I-P': 0.5815117882411447, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.6520225238704062, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.47146156384031673, 'I-P': 0.9810468109447993, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.7487504685742846, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.4191230385687051, 'I-P': 0.730200180240273, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6429318408085067, 'recall': 0.6429318408085067, 'f1': 0.6429318408085067, 'support': None}, 'macro_avg': {'precision': 0.2625618032664861, 'recall': 0.30064727123650314, 'f1': 0.2711533839118947, 'support': None}, 'weighted_avg': {'precision': 0.5351022290652102, 'recall': 0.6429318408085067, 'f1': 0.5612907859838377, 'support': None}}
			------------EPOCH 3---------------
Loss:  tensor(2.9193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9523, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4406, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0234, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6781, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1813, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7757507188987884, 'B-C': 0.5, 'I-C': 0.7922077922077922, 'B-P': 0.4647488799811365, 'I-P': 0.6741779909039696, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.8952966459019069, 'B-C': 0.002540220152413209, 'I-C': 0.003584018801410106, 'B-P': 0.650280435499835, 'I-P': 0.9355705977690915, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.8312475532600048, 'B-C': 0.005054759898904802, 'I-C': 0.007135754810785518, 'B-P': 0.5420792079207921, 'I-P': 0.7836516961604804, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7028670866484285, 'recall': 0.7028670866484285, 'f1': 0.7028670866484285, 'support': None}, 'macro_avg': {'precision': 0.45812648314166954, 'recall': 0.3553245597320938, 'f1': 0.3098812817215668, 'support': None}, 'weighted_avg': {'precision': 0.6639155969597043, 'recall': 0.7028670866484285, 'f1': 0.6142991810192967, 'support': None}}
			------------EPOCH 4---------------
Loss:  tensor(2.5891, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5112, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5822, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0922, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8501856650548981, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.48763405559203327, 'I-P': 0.6562862818958177, 'B-MC': 1.0, 'I-MC': 1.0}, 'recall': {'O': 0.8657272653083431, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.7350709336852523, 'I-P': 0.9700448088473639, 'B-MC': 0.001692047377326565, 'I-MC': 0.0009411764705882353}, 'f1': {'O': 0.8578860824325417, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.5863157894736841, 'I-P': 0.7828997483899264, 'B-MC': 0.0033783783783783786, 'I-MC': 0.0018805829807240246}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7105890620686194, 'recall': 0.7105890620686194, 'f1': 0.7105890620686194, 'support': None}, 'macro_avg': {'precision': 0.5705865717918213, 'recall': 0.36763946166983924, 'f1': 0.31890865452217926, 'support': None}, 'weighted_avg': {'precision': 0.6378504639845454, 'recall': 0.7105890620686194, 'f1': 0.6223680639465308, 'support': None}}
			------------EPOCH 5---------------
Loss:  tensor(2.2309, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1884, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7155, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0552, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4622, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5272, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9497, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8320018260671079, 'B-C': 0.2535211267605634, 'I-C': 0.3368200836820084, 'B-P': 0.4793999577435031, 'I-P': 0.6765183062030177, 'B-MC': 0.2, 'I-MC': 0.5894428152492669}, 'recall': {'O': 0.8923859525040124, 'B-C': 0.015241320914479255, 'I-C': 0.01891891891891892, 'B-P': 0.7485978225008248, 'I-P': 0.9541042997425875, 'B-MC': 0.011844331641285956, 'I-MC': 0.023647058823529413}, 'f1': {'O': 0.8611366321039506, 'B-C': 0.02875399361022364, 'I-C': 0.03582554517133957, 'B-P': 0.5844925296239052, 'I-P': 0.7916841364143377, 'B-MC': 0.022364217252396165, 'I-MC': 0.045469969460468274}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7166461695488124, 'recall': 0.7166461695488124, 'f1': 0.7166461695488123, 'support': None}, 'macro_avg': {'precision': 0.4811005879579239, 'recall': 0.3806771007208055, 'f1': 0.3385324319480887, 'support': None}, 'weighted_avg': {'precision': 0.6582405372201018, 'recall': 0.7166461695488124, 'f1': 0.6357548073052844, 'support': None}}
			------------EPOCH 6---------------
Loss:  tensor(1.9769, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1737, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6209, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6672, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3962, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8454, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8781278962001854, 'B-C': 0.19689119170984457, 'I-C': 0.291361043194784, 'B-P': 0.5068493150684932, 'I-P': 0.6918925650711943, 'B-MC': 0.33793103448275863, 'I-MC': 0.5454545454545454}, 'recall': {'O': 0.876336334702538, 'B-C': 0.03217612193056731, 'I-C': 0.04200940070505288, 'B-P': 0.7568459254371495, 'I-P': 0.9533987987415388, 'B-MC': 0.1658206429780034, 'I-MC': 0.19976470588235293}, 'f1': {'O': 0.877231200729778, 'B-C': 0.05531295487627364, 'I-C': 0.07343124165554073, 'B-P': 0.6071192272065634, 'I-P': 0.8018634934889988, 'B-MC': 0.22247446083995462, 'I-MC': 0.29243089640919656}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7283504421521138, 'recall': 0.7283504421521138, 'f1': 0.7283504421521138, 'support': None}, 'macro_avg': {'precision': 0.49264394159740077, 'recall': 0.4323359900538861, 'f1': 0.4185519250294723, 'support': None}, 'weighted_avg': {'precision': 0.6703896106524267, 'recall': 0.7283504421521138, 'f1': 0.6699133668167705, 'support': None}}
			------------EPOCH 7---------------
Loss:  tensor(1.6537, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1385, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5329, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3529, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4287, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7490, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9123248398326653, 'B-C': 0.27712854757929883, 'I-C': 0.3545392022008253, 'B-P': 0.5782224532224532, 'I-P': 0.726943995731879, 'B-MC': 0.37994722955145116, 'I-MC': 0.5116925214169947}, 'recall': {'O': 0.8483447131470853, 'B-C': 0.14055884843353092, 'I-C': 0.18172737955346652, 'B-P': 0.7340811613328935, 'I-P': 0.9353036514443703, 'B-MC': 0.2436548223350254, 'I-MC': 0.26}, 'f1': {'O': 0.879172304916554, 'B-C': 0.18651685393258427, 'I-C': 0.240288999378496, 'B-P': 0.6468963512138394, 'I-P': 0.8180650756324944, 'B-MC': 0.29690721649484536, 'I-MC': 0.34480068648100476}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7368588376042634, 'recall': 0.7368588376042634, 'f1': 0.7368588376042634, 'support': None}, 'macro_avg': {'precision': 0.5343998270765097, 'recall': 0.4776672251780531, 'f1': 0.4875210697214025, 'support': None}, 'weighted_avg': {'precision': 0.7056917135575703, 'recall': 0.7368588376042634, 'f1': 0.7077754520414806, 'support': None}}
			------------EPOCH 8---------------
Loss:  tensor(1.3770, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6493, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4416, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2855, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6056, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.7812012838147638, 'B-C': 0.2591928251121076, 'I-C': 0.41997075073123175, 'B-P': 0.585202446839499, 'I-P': 0.8200274505318541, 'B-MC': 0.29044117647058826, 'I-MC': 0.408362254172864}, 'recall': {'O': 0.9269606376322733, 'B-C': 0.2447078746824725, 'I-C': 0.3037015276145711, 'B-P': 0.6628175519630485, 'I-P': 0.8202307178949375, 'B-MC': 0.2673434856175973, 'I-MC': 0.2907058823529412}, 'f1': {'O': 0.8478620569537577, 'B-C': 0.25174216027874563, 'I-C': 0.3524959083469722, 'B-P': 0.6215965346534652, 'I-P': 0.8201290716185429, 'B-MC': 0.27841409691629954, 'I-MC': 0.3396330149130644}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7294380443239716, 'recall': 0.7294380443239716, 'f1': 0.7294380443239716, 'support': None}, 'macro_avg': {'precision': 0.5091997410961299, 'recall': 0.5023525253939775, 'f1': 0.5016961205258353, 'support': None}, 'weighted_avg': {'precision': 0.707732579152294, 'recall': 0.7294380443239716, 'f1': 0.7145730035609723, 'support': None}}
			------------EPOCH 9---------------
Loss:  tensor(1.2184, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0937, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3397, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3240, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5240, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9562124839526734, 'B-C': 0.263681592039801, 'I-C': 0.35467433737415244, 'B-P': 0.6426799007444168, 'I-P': 0.8025950961381635, 'B-MC': 0.2581967213114754, 'I-MC': 0.39358137894551226}, 'recall': {'O': 0.7496803677810724, 'B-C': 0.4038950042337002, 'I-C': 0.5071092831962397, 'B-P': 0.6836027713625866, 'I-P': 0.8444656306606921, 'B-MC': 0.2131979695431472, 'I-MC': 0.2625882352941176}, 'f1': {'O': 0.8404440242749537, 'B-C': 0.31906354515050167, 'I-C': 0.4174102285092492, 'B-P': 0.6625099920063949, 'I-P': 0.8229981602958393, 'B-MC': 0.23354958294717332, 'I-MC': 0.3150095264977772}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7143454726468054, 'recall': 0.7143454726468054, 'f1': 0.7143454726468053, 'support': None}, 'macro_avg': {'precision': 0.524517358643742, 'recall': 0.5235056088673652, 'f1': 0.5158550085259842, 'support': None}, 'weighted_avg': {'precision': 0.7449019977105601, 'recall': 0.7143454726468054, 'f1': 0.7225235214354784, 'support': None}}
			------------EPOCH 10---------------
Loss:  tensor(0.9617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0742, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2584, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4238, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2441, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2797, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5160, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8327299962551492, 'B-C': 0.34105960264900664, 'I-C': 0.48379970544919, 'B-P': 0.5062906724511931, 'I-P': 0.7214761660686827, 'B-MC': 0.535483870967742, 'I-MC': 0.7068594278683482}, 'recall': {'O': 0.9073474606240309, 'B-C': 0.08721422523285352, 'I-C': 0.0772032902467685, 'B-P': 0.7700428901352689, 'I-P': 0.939384116693679, 'B-MC': 0.2808798646362098, 'I-MC': 0.2703529411764706}, 'f1': {'O': 0.8684388669027286, 'B-C': 0.13890761968981793, 'I-C': 0.13315768139440615, 'B-P': 0.6109148017275227, 'I-P': 0.8161351776691792, 'B-MC': 0.3684794672586016, 'I-MC': 0.3911156497319377}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7432171272243556, 'recall': 0.7432171272243556, 'f1': 0.7432171272243557, 'support': None}, 'macro_avg': {'precision': 0.5896713488156161, 'recall': 0.47606068410646873, 'f1': 0.475307037767742, 'support': None}, 'weighted_avg': {'precision': 0.7106744842850167, 'recall': 0.7432171272243556, 'f1': 0.6906375972957627, 'support': None}}
			------------EPOCH 11---------------
Loss:  tensor(0.8610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1848, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2820, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1981, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1342, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2638, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4168, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8614668524995398, 'B-C': 0.2630410654827969, 'I-C': 0.33199617448594654, 'B-P': 0.6926987060998152, 'I-P': 0.9101302764990824, 'B-MC': 0.39330543933054396, 'I-MC': 0.5560818491852975}, 'recall': {'O': 0.8911346263703381, 'B-C': 0.6020321761219306, 'I-C': 0.7342538190364277, 'B-P': 0.49455625206202575, 'I-P': 0.5767947373438841, 'B-MC': 0.31810490693739424, 'I-MC': 0.3452941176470588}, 'f1': {'O': 0.8760496336310639, 'B-C': 0.3661174047373841, 'I-C': 0.4572463502981962, 'B-P': 0.5770933589990376, 'I-P': 0.7060992974020214, 'B-MC': 0.3517305893358279, 'I-MC': 0.4260415154594281}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6763128613139907, 'recall': 0.6763128613139907, 'f1': 0.6763128613139907, 'support': None}, 'macro_avg': {'precision': 0.5726743376547174, 'recall': 0.5660243765027227, 'f1': 0.5371968785518513, 'support': None}, 'weighted_avg': {'precision': 0.7732023250819792, 'recall': 0.6763128613139907, 'f1': 0.6946343682458599, 'support': None}}
			------------EPOCH 12---------------
Loss:  tensor(0.7565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1676, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2810, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1382, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1138, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3497, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6772, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8604114746274988, 'B-C': 0.3360655737704918, 'I-C': 0.39331639942848073, 'B-P': 0.6221374045801527, 'I-P': 0.7778520753486097, 'B-MC': 0.5168539325842697, 'I-MC': 0.6896551724137931}, 'recall': {'O': 0.8828105873072005, 'B-C': 0.2777307366638442, 'I-C': 0.2911280846063455, 'B-P': 0.7528868360277137, 'I-P': 0.90940985794642, 'B-MC': 0.233502538071066, 'I-MC': 0.24235294117647058}, 'f1': {'O': 0.8714671249613984, 'B-C': 0.30412610106629573, 'I-C': 0.3345938280775204, 'B-P': 0.6812957157784744, 'I-P': 0.8385021097046413, 'B-MC': 0.32167832167832167, 'I-MC': 0.35866631844694}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7522023943980122, 'recall': 0.7522023943980122, 'f1': 0.7522023943980122, 'support': None}, 'macro_avg': {'precision': 0.5994702903933281, 'recall': 0.512831654542723, 'f1': 0.5300470742447988, 'support': None}, 'weighted_avg': {'precision': 0.732612211131123, 'recall': 0.7522023943980122, 'f1': 0.7309438622663957, 'support': None}}
			------------EPOCH 13---------------
Loss:  tensor(0.3933, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0335, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1171, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1875, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2305, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4684, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8321662637992474, 'B-C': 0.2987106017191977, 'I-C': 0.41181694393463975, 'B-P': 0.6001142530705512, 'I-P': 0.8326820258578789, 'B-MC': 0.40655105973025046, 'I-MC': 0.585719335454224}, 'recall': {'O': 0.9084083675634504, 'B-C': 0.35309060118543606, 'I-C': 0.40869565217391307, 'B-P': 0.6931705707687232, 'I-P': 0.8166460101058252, 'B-MC': 0.3570219966159052, 'I-MC': 0.38988235294117646}, 'f1': {'O': 0.8686175055273768, 'B-C': 0.3236321303841676, 'I-C': 0.4102503612397157, 'B-P': 0.6432945499081445, 'I-P': 0.8245860608394301, 'B-MC': 0.3801801801801801, 'I-MC': 0.4681452182511654}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7464464690577182, 'recall': 0.7464464690577182, 'f1': 0.7464464690577183, 'support': None}, 'macro_avg': {'precision': 0.5668229262237128, 'recall': 0.5609879359077757, 'f1': 0.5598151437614544, 'support': None}, 'weighted_avg': {'precision': 0.7417531043073802, 'recall': 0.7464464690577182, 'f1': 0.7420381781667416, 'support': None}}
			------------EPOCH 14---------------
Loss:  tensor(0.3504, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0267, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0836, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1254, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0824, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0750, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3178, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8671234326226126, 'B-C': 0.2705047318611987, 'I-C': 0.3886606409202958, 'B-P': 0.598466825270949, 'I-P': 0.782321703310338, 'B-MC': 0.5141843971631206, 'I-MC': 0.698046875}, 'recall': {'O': 0.8916786812110661, 'B-C': 0.2904318374259102, 'I-C': 0.3056991774383079, 'B-P': 0.7469482019135599, 'I-P': 0.9016874821241301, 'B-MC': 0.24534686971235195, 'I-MC': 0.21023529411764705}, 'f1': {'O': 0.8792296447299599, 'B-C': 0.2801143323805635, 'I-C': 0.3422238300391357, 'B-P': 0.6645142353977106, 'I-P': 0.8377741558303512, 'B-MC': 0.3321878579610539, 'I-MC': 0.32314647377938516}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7513657773427369, 'recall': 0.7513657773427369, 'f1': 0.7513657773427369, 'support': None}, 'macro_avg': {'precision': 0.5884726580212164, 'recall': 0.5131467919918533, 'f1': 0.5227415043025944, 'support': None}, 'weighted_avg': {'precision': 0.735310182442434, 'recall': 0.7513657773427369, 'f1': 0.7309615397511783, 'support': None}}
			------------EPOCH 15---------------
Loss:  tensor(0.2263, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0183, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0960, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0685, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0728, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1467, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2806, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8682283652570701, 'B-C': 0.2924982794218858, 'I-C': 0.4251447997985394, 'B-P': 0.6324659964518037, 'I-P': 0.8099105984394718, 'B-MC': 0.4488888888888889, 'I-MC': 0.6136724960254372}, 'recall': {'O': 0.8902641386251734, 'B-C': 0.3598645215918713, 'I-C': 0.39676850763807286, 'B-P': 0.7057076872319367, 'I-P': 0.8688721517780532, 'B-MC': 0.34179357021996615, 'I-MC': 0.31788235294117645}, 'f1': {'O': 0.8791081861527097, 'B-C': 0.322703113135915, 'I-C': 0.41046681254558715, 'B-P': 0.6670824886948385, 'I-P': 0.8383559627626301, 'B-MC': 0.38808837656099904, 'I-MC': 0.41881732930326276}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7572722937529804, 'recall': 0.7572722937529804, 'f1': 0.7572722937529806, 'support': None}, 'macro_avg': {'precision': 0.5844013463261567, 'recall': 0.5544504185751786, 'f1': 0.5606603241651346, 'support': None}, 'weighted_avg': {'precision': 0.7477066085697748, 'recall': 0.7572722937529804, 'f1': 0.7484624365404601, 'support': None}}
			------------EPOCH 16---------------
Loss:  tensor(0.1579, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0456, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0670, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0399, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2445, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8658690176322418, 'B-C': 0.2874382885353812, 'I-C': 0.4155068601322673, 'B-P': 0.6514339741569493, 'I-P': 0.8383756108913195, 'B-MC': 0.46559633027522934, 'I-MC': 0.6393363789372445}, 'recall': {'O': 0.8976904872011099, 'B-C': 0.4436917866215072, 'I-C': 0.4946533490011751, 'B-P': 0.6819531507753217, 'I-P': 0.8242921155496234, 'B-MC': 0.34348561759729274, 'I-MC': 0.3128235294117647}, 'f1': {'O': 0.8814926609058005, 'B-C': 0.34886817576564577, 'I-C': 0.45163886057614927, 'B-P': 0.6663442940038685, 'I-P': 0.831274216654328, 'B-MC': 0.3953261927945472, 'I-MC': 0.4200963741211786}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7538086991441407, 'recall': 0.7538086991441407, 'f1': 0.7538086991441407, 'support': None}, 'macro_avg': {'precision': 0.5947937800800904, 'recall': 0.5712271480225422, 'f1': 0.5707201106887883, 'support': None}, 'weighted_avg': {'precision': 0.7604366662183614, 'recall': 0.7538086991441407, 'f1': 0.7523176905828458, 'support': None}}
			------------EPOCH 17---------------
Loss:  tensor(0.1139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0300, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0412, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0312, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0316, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2158, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8747575652913202, 'B-C': 0.29177057356608477, 'I-C': 0.41342003798123955, 'B-P': 0.621675155631013, 'I-P': 0.8141882772148937, 'B-MC': 0.4932975871313673, 'I-MC': 0.6727802037845706}, 'recall': {'O': 0.8956502815483801, 'B-C': 0.39627434377646065, 'I-C': 0.4220916568742656, 'B-P': 0.7248432860442098, 'I-P': 0.8626561159309754, 'B-MC': 0.311336717428088, 'I-MC': 0.27188235294117646}, 'f1': {'O': 0.8850806451612904, 'B-C': 0.3360861759425494, 'I-C': 0.41771084687618104, 'B-P': 0.6693069306930693, 'I-P': 0.837721734622079, 'B-MC': 0.3817427385892116, 'I-MC': 0.3872643485546711}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7572304629002167, 'recall': 0.7572304629002167, 'f1': 0.7572304629002167, 'support': None}, 'macro_avg': {'precision': 0.5974127715143557, 'recall': 0.5549621077919366, 'f1': 0.5592733457770074, 'support': None}, 'weighted_avg': {'precision': 0.754064077779557, 'recall': 0.7572304629002167, 'f1': 0.7489659294798877, 'support': None}}
			------------EPOCH 18---------------
Loss:  tensor(0.0849, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0066, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0207, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0295, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0245, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0242, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2010, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8806703730561598, 'B-C': 0.28790786948176583, 'I-C': 0.4068349233184398, 'B-P': 0.6282232927174837, 'I-P': 0.8064793376832947, 'B-MC': 0.5127478753541076, 'I-MC': 0.6920964296612756}, 'recall': {'O': 0.8919779113734665, 'B-C': 0.3810330228619814, 'I-C': 0.39588719153936547, 'B-P': 0.7314417683932696, 'I-P': 0.8767089331680809, 'B-MC': 0.3062605752961083, 'I-MC': 0.2668235294117647}, 'f1': {'O': 0.886288077411682, 'B-C': 0.32798833819241985, 'I-C': 0.40128640343040917, 'B-P': 0.6759146341463415, 'I-P': 0.8401290004293923, 'B-MC': 0.3834745762711864, 'I-MC': 0.38515751040163027}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.758167474002125, 'recall': 0.758167474002125, 'f1': 0.758167474002125, 'support': None}, 'macro_avg': {'precision': 0.6021371573246467, 'recall': 0.5500189902920053, 'f1': 0.5571769343261516, 'support': None}, 'weighted_avg': {'precision': 0.7531601576532684, 'recall': 0.758167474002125, 'f1': 0.7480010693984626, 'support': None}}
			------------EPOCH 19---------------
Loss:  tensor(0.0682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0048, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0146, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0224, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0196, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1949, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8765073097855085, 'B-C': 0.30338733431516934, 'I-C': 0.4279254590298712, 'B-P': 0.619988864142539, 'I-P': 0.8024313481358512, 'B-MC': 0.486784140969163, 'I-MC': 0.6580507469765235}, 'recall': {'O': 0.8937460896058322, 'B-C': 0.3488569009314141, 'I-C': 0.3669800235017626, 'B-P': 0.7347410095677994, 'I-P': 0.8847935932882067, 'B-MC': 0.3739424703891709, 'I-MC': 0.3264705882352941}, 'f1': {'O': 0.8850427638224796, 'B-C': 0.3245372193777078, 'I-C': 0.39511639676113364, 'B-P': 0.6725049071417786, 'I-P': 0.8416022054356007, 'B-MC': 0.42296650717703355, 'I-MC': 0.43642368483132815}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7624844180073455, 'recall': 0.7624844180073455, 'f1': 0.7624844180073456, 'support': None}, 'macro_avg': {'precision': 0.5964393147649466, 'recall': 0.5613615250742114, 'f1': 0.5683133835067231, 'support': None}, 'weighted_avg': {'precision': 0.750501518847758, 'recall': 0.7624844180073455, 'f1': 0.7511062682216239, 'support': None}}
			------------EPOCH 20---------------
Loss:  tensor(0.0540, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0036, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0163, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0202, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1235, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2181, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8774312318241242, 'B-C': 0.28413524057217165, 'I-C': 0.4116697703289882, 'B-P': 0.6226203807390818, 'I-P': 0.8059381428920116, 'B-MC': 0.5278592375366569, 'I-MC': 0.6919143496324704}, 'recall': {'O': 0.894616577350997, 'B-C': 0.37002540220152413, 'I-C': 0.38965922444183315, 'B-P': 0.7337512372154404, 'I-P': 0.8814376966345695, 'B-MC': 0.30456852791878175, 'I-MC': 0.25470588235294117}, 'f1': {'O': 0.8859405727216401, 'B-C': 0.32144170650974624, 'I-C': 0.4003622094778147, 'B-P': 0.6736331970316523, 'I-P': 0.8419988524903692, 'B-MC': 0.3862660944206009, 'I-MC': 0.3723449995700404}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7592467100034301, 'recall': 0.7592467100034301, 'f1': 0.7592467100034301, 'support': None}, 'macro_avg': {'precision': 0.6030811933607865, 'recall': 0.5469663640165839, 'f1': 0.5545696617459807, 'support': None}, 'weighted_avg': {'precision': 0.752497367019331, 'recall': 0.7592467100034301, 'f1': 0.7475631574908924, 'support': None}}
			------------EPOCH 21---------------
Loss:  tensor(0.0460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0093, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0192, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1726, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2398, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8786883494886378, 'B-C': 0.2814526588845655, 'I-C': 0.41168191414496835, 'B-P': 0.6097691894793345, 'I-P': 0.8015014808182381, 'B-MC': 0.5469255663430421, 'I-MC': 0.7042203147353362}, 'recall': {'O': 0.8951334294496885, 'B-C': 0.3674851820491109, 'I-C': 0.3780846063454759, 'B-P': 0.7495875948531837, 'I-P': 0.8875583945085328, 'B-MC': 0.2859560067681895, 'I-MC': 0.2316470588235294}, 'f1': {'O': 0.8868346584018326, 'B-C': 0.3187660668380463, 'I-C': 0.3941686318948884, 'B-P': 0.6724877904395442, 'I-P': 0.8423376552872306, 'B-MC': 0.3755555555555556, 'I-MC': 0.34861898016997167}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7590877527629278, 'recall': 0.7590877527629278, 'f1': 0.7590877527629278, 'support': None}, 'macro_avg': {'precision': 0.6048913534134461, 'recall': 0.5422074675425301, 'f1': 0.5483956197981528, 'support': None}, 'weighted_avg': {'precision': 0.7515560696084238, 'recall': 0.7590877527629278, 'f1': 0.7453092153907056, 'support': None}}
			------------EPOCH 22---------------
Loss:  tensor(0.0459, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0027, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0133, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0130, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2054, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8700741831956648, 'B-C': 0.30196936542669583, 'I-C': 0.4374691749453956, 'B-P': 0.6064516129032258, 'I-P': 0.8035875060599764, 'B-MC': 0.48072562358276644, 'I-MC': 0.6569162121963312}, 'recall': {'O': 0.8997306928538397, 'B-C': 0.3505503810330229, 'I-C': 0.36480611045828437, 'B-P': 0.744308808973936, 'I-P': 0.8849652016398132, 'B-MC': 0.3587140439932318, 'I-MC': 0.31176470588235294}, 'f1': {'O': 0.884653961885657, 'B-C': 0.3244514106583072, 'I-C': 0.3978470509082754, 'B-P': 0.6683454303066213, 'I-P': 0.8423154054863387, 'B-MC': 0.4108527131782945, 'I-MC': 0.42284984841231854}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7632290071865405, 'recall': 0.7632290071865405, 'f1': 0.7632290071865405, 'support': None}, 'macro_avg': {'precision': 0.593884811187151, 'recall': 0.5592628492620687, 'f1': 0.5644736886908304, 'support': None}, 'weighted_avg': {'precision': 0.7499213284460404, 'recall': 0.7632290071865405, 'f1': 0.7505569553857927, 'support': None}}
			------------EPOCH 23---------------
Loss:  tensor(0.0381, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0025, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0078, 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(0.0127, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1101, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1621, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8738487671523741, 'B-C': 0.3181818181818182, 'I-C': 0.429142464555618, 'B-P': 0.6385684708666075, 'I-P': 0.8201754385964912, 'B-MC': 0.43728813559322033, 'I-MC': 0.6106870229007634}, 'recall': {'O': 0.8956230788063437, 'B-C': 0.37341236240474174, 'I-C': 0.40370152761457107, 'B-P': 0.7123061695809964, 'I-P': 0.8557536466774717, 'B-MC': 0.4365482233502538, 'I-MC': 0.41411764705882353}, 'f1': {'O': 0.8846019506166205, 'B-C': 0.3435917413322945, 'I-C': 0.4160334231479519, 'B-P': 0.6734248284466624, 'I-P': 0.8375868987076004, 'B-MC': 0.43691786621507195, 'I-MC': 0.49355019629837354}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7617649273398087, 'recall': 0.7617649273398087, 'f1': 0.7617649273398087, 'support': None}, 'macro_avg': {'precision': 0.5896988739781275, 'recall': 0.5844946650704574, 'f1': 0.5836724149663679, 'support': None}, 'weighted_avg': {'precision': 0.754647080612065, 'recall': 0.7617649273398087, 'f1': 0.7565303290441683, 'support': None}}
			------------EPOCH 24---------------
Loss:  tensor(0.0370, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0108, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1549, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8839498161367078, 'B-C': 0.3261703760552571, 'I-C': 0.43459686715942225, 'B-P': 0.6327635327635328, 'I-P': 0.8037478587372173, 'B-MC': 0.4707070707070707, 'I-MC': 0.6350862252501597}, 'recall': {'O': 0.8893120426538995, 'B-C': 0.3598645215918713, 'I-C': 0.37655699177438307, 'B-P': 0.7327614648630815, 'I-P': 0.8857088378301078, 'B-MC': 0.3942470389170897, 'I-MC': 0.35094117647058826}, 'f1': {'O': 0.8866228218862295, 'B-C': 0.3421900161030596, 'I-C': 0.40350048792772375, 'B-P': 0.6791010548845742, 'I-P': 0.842740252907346, 'B-MC': 0.42909760589318596, 'I-MC': 0.4520724407062211}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7647851149093525, 'recall': 0.7647851149093525, 'f1': 0.7647851149093525, 'support': None}, 'macro_avg': {'precision': 0.5981459638299097, 'recall': 0.569913153443003, 'f1': 0.5764749543297628, 'support': None}, 'weighted_avg': {'precision': 0.7531545365297961, 'recall': 0.7647851149093525, 'f1': 0.7547701943551265, 'support': None}}
			------------EPOCH 25---------------
Loss:  tensor(0.0302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0095, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0098, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0811, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1391, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8872094603778714, 'B-C': 0.3190045248868778, 'I-C': 0.4297056810403833, 'B-P': 0.6191524490919097, 'I-P': 0.7960241859208215, 'B-MC': 0.5181347150259067, 'I-MC': 0.6843575418994413}, 'recall': {'O': 0.8877886890998613, 'B-C': 0.35817104149026247, 'I-C': 0.36886016451233844, 'B-P': 0.7423292642692181, 'I-P': 0.8986748021737058, 'B-MC': 0.338409475465313, 'I-MC': 0.28823529411764703}, 'f1': {'O': 0.88749898023006, 'B-C': 0.3374551256481851, 'I-C': 0.39696490673411317, 'B-P': 0.6751687921980494, 'I-P': 0.8442406384064914, 'B-MC': 0.4094165813715456, 'I-MC': 0.40562913907284764}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7644002710639259, 'recall': 0.7644002710639259, 'f1': 0.764400271063926, 'support': None}, 'macro_avg': {'precision': 0.6076555083204589, 'recall': 0.5546383901611922, 'f1': 0.5651963090944704, 'support': None}, 'weighted_avg': {'precision': 0.7533940569626641, 'recall': 0.7644002710639259, 'f1': 0.7512208501730364, 'support': None}}
			------------EPOCH 26---------------
Loss:  tensor(0.0256, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0052, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0090, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0782, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1245, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8852201683401445, 'B-C': 0.3046495489243581, 'I-C': 0.4204703502339107, 'B-P': 0.6212290502793296, 'I-P': 0.8023083293078462, 'B-MC': 0.5217391304347826, 'I-MC': 0.6870049867996479}, 'recall': {'O': 0.8897472865264818, 'B-C': 0.37171888230313294, 'I-C': 0.3907755581668625, 'B-P': 0.7337512372154404, 'I-P': 0.8867384879397464, 'B-MC': 0.3248730964467005, 'I-MC': 0.27552941176470586}, 'f1': {'O': 0.8874779541446208, 'B-C': 0.3348588863463005, 'I-C': 0.4050794810889823, 'B-P': 0.6728180305551353, 'I-P': 0.8424132090681014, 'B-MC': 0.4004171011470281, 'I-MC': 0.393315979511294}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7618318567042308, 'recall': 0.7618318567042308, 'f1': 0.7618318567042308, 'support': None}, 'macro_avg': {'precision': 0.6060887949028599, 'recall': 0.5533048514804386, 'f1': 0.5623400916944946, 'support': None}, 'weighted_avg': {'precision': 0.7543413806059072, 'recall': 0.7618318567042308, 'f1': 0.7505626477091999, 'support': None}}
			------------EPOCH 27---------------
Loss:  tensor(0.0189, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0014, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0045, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0071, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0083, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0723, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1153, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8822356902356903, 'B-C': 0.3094202898550725, 'I-C': 0.42791732077446365, 'B-P': 0.6174832962138085, 'I-P': 0.8027262531274264, 'B-MC': 0.5061425061425061, 'I-MC': 0.6686938127974617}, 'recall': {'O': 0.8909714099181197, 'B-C': 0.3615580016934801, 'I-C': 0.3843713278495887, 'B-P': 0.7317716925107225, 'I-P': 0.8870626370483363, 'B-MC': 0.34856175972927245, 'I-MC': 0.2975294117647059}, 'f1': {'O': 0.8865820317786862, 'B-C': 0.3334634908238969, 'I-C': 0.4049770954562338, 'B-P': 0.6697871055412955, 'I-P': 0.8427898550724637, 'B-MC': 0.41282565130260523, 'I-MC': 0.41182217879824135}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7629696558994051, 'recall': 0.7629696558994051, 'f1': 0.7629696558994051, 'support': None}, 'macro_avg': {'precision': 0.6020884527352042, 'recall': 0.5574037486448893, 'f1': 0.5660353441104891, 'support': None}, 'weighted_avg': {'precision': 0.7532401527382896, 'recall': 0.7629696558994051, 'f1': 0.751724516756773, 'support': None}}
			------------EPOCH 28---------------
Loss:  tensor(0.0165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0067, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1062, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8795700654015225, 'B-C': 0.31407407407407406, 'I-C': 0.43912689804772237, 'B-P': 0.614404432132964, 'I-P': 0.803536175665847, 'B-MC': 0.4796573875802998, 'I-MC': 0.6554934823091247}, 'recall': {'O': 0.8926579799243763, 'B-C': 0.3590177815410669, 'I-C': 0.38061104582843713, 'B-P': 0.7317716925107225, 'I-P': 0.8847554580989608, 'B-MC': 0.3790186125211506, 'I-MC': 0.33129411764705885}, 'f1': {'O': 0.8860656955001418, 'B-C': 0.3350454365863295, 'I-C': 0.40778043560367616, 'B-P': 0.66797169101039, 'I-P': 0.8421921935548276, 'B-MC': 0.42344045368620037, 'I-MC': 0.44013754298218194}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7644672004283479, 'recall': 0.7644672004283479, 'f1': 0.764467200428348, 'support': None}, 'macro_avg': {'precision': 0.5979803593159364, 'recall': 0.5655895268673962, 'f1': 0.5718047784176782, 'support': None}, 'weighted_avg': {'precision': 0.7532701113767952, 'recall': 0.7644672004283479, 'f1': 0.7537383138550166, 'support': None}}
			------------EPOCH 29---------------
Loss:  tensor(0.0144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0037, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0056, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0074, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0060, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0617, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0967, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8798048571275398, 'B-C': 0.31054131054131057, 'I-C': 0.43735209045490403, 'B-P': 0.6162433714764164, 'I-P': 0.80600868852173, 'B-MC': 0.47629310344827586, 'I-MC': 0.6521329248173462}, 'recall': {'O': 0.8928483991186311, 'B-C': 0.3691786621507197, 'I-C': 0.3908930669800235, 'B-P': 0.7284724513361927, 'I-P': 0.8808847363905044, 'B-MC': 0.3739424703891709, 'I-MC': 0.3255294117647059}, 'f1': {'O': 0.8862786396100827, 'B-C': 0.33733075435203097, 'I-C': 0.41281955820302807, 'B-P': 0.6676746295736317, 'I-P': 0.8417849528980886, 'B-MC': 0.418957345971564, 'I-MC': 0.4342776426273249}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7638732023191025, 'recall': 0.7638732023191025, 'f1': 0.7638732023191025, 'support': None}, 'macro_avg': {'precision': 0.596910906626789, 'recall': 0.5659641711614211, 'f1': 0.5713033604622502, 'support': None}, 'weighted_avg': {'precision': 0.7539305660861361, 'recall': 0.7638732023191025, 'f1': 0.753918822904826, 'support': None}}
			------------EPOCH 30---------------
Loss:  tensor(0.0128, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0033, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0070, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0580, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0863, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8812093872509532, 'B-C': 0.31063829787234043, 'I-C': 0.4384680739820927, 'B-P': 0.611542730299667, 'I-P': 0.8055318035075474, 'B-MC': 0.4900662251655629, 'I-MC': 0.6585192216421453}, 'recall': {'O': 0.8927395881504856, 'B-C': 0.37087214225232856, 'I-C': 0.39418331374853116, 'B-P': 0.7271527548663808, 'I-P': 0.8801792353894556, 'B-MC': 0.3756345177664975, 'I-MC': 0.3264705882352941}, 'f1': {'O': 0.8869370160669162, 'B-C': 0.3380934002315708, 'I-C': 0.41514804616193807, 'B-P': 0.6643556895252449, 'I-P': 0.8412027334851937, 'B-MC': 0.42528735632183906, 'I-MC': 0.43652666352052855}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.764057258071263, 'recall': 0.764057258071263, 'f1': 0.764057258071263, 'support': None}, 'macro_avg': {'precision': 0.5994251056743298, 'recall': 0.5667474486298534, 'f1': 0.5725072721876046, 'support': None}, 'weighted_avg': {'precision': 0.7547162003130405, 'recall': 0.764057258071263, 'f1': 0.7543120131439088, 'support': None}}
	Data split: 21k
			------------EPOCH 1---------------
Loss:  tensor(4.9549, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3442, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.9780, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2896, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.3367, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(3.1948, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1707, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9222520107238605, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.27804159161617814, 'I-P': 0.5053148237046036, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.2807322978156198, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.5602111514351699, 'I-P': 0.9834874630565354, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.4304394068945381, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.3716349310571241, 'I-P': 0.6676115404030598, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.5320633486434254, 'recall': 0.5320633486434254, 'f1': 0.5320633486434254, 'support': None}, 'macro_avg': {'precision': 0.243658346577806, 'recall': 0.26063298747247504, 'f1': 0.209955125479246, 'support': None}, 'weighted_avg': {'precision': 0.5124018954362238, 'recall': 0.5320633486434254, 'f1': 0.4347287750196415, 'support': None}}
			------------EPOCH 2---------------
Loss:  tensor(3.5286, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2604, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6585, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2857, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9422, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.8610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.7318, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5986, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.8806, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8243537838679539, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.3587509077705156, 'I-P': 0.6283735705209657, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.7920622398737793, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.6519300560871, 'I-P': 0.9429497568881685, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.8078854637773648, 'B-C': 0.0, 'I-C': 0.0, 'B-P': 0.4628176601475583, 'I-P': 0.7541728620992032, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.6738615733420341, 'recall': 0.6738615733420341, 'f1': 0.6738615733420341, 'support': None}, 'macro_avg': {'precision': 0.25878260887991933, 'recall': 0.34099172183557824, 'f1': 0.2892679980034466, 'support': None}, 'weighted_avg': {'precision': 0.5383337546218435, 'recall': 0.6738615733420341, 'f1': 0.5911040301066659, 'support': None}}
			------------EPOCH 3---------------
Loss:  tensor(3.2034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2383, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4975, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.0139, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7129, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.5326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.4144, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6380, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8072264785456017, 'B-C': 0.18421052631578946, 'I-C': 0.24484536082474226, 'B-P': 0.44407415121849614, 'I-P': 0.6642988053671522, 'B-MC': 0.0, 'I-MC': 0.0}, 'recall': {'O': 0.8684475395119828, 'B-C': 0.0059271803556308214, 'I-C': 0.005581668625146886, 'B-P': 0.7033982184097658, 'I-P': 0.946839546191248, 'B-MC': 0.0, 'I-MC': 0.0}, 'f1': {'O': 0.8367186476215437, 'B-C': 0.011484823625922888, 'I-C': 0.01091452205882353, 'B-P': 0.5444330949948928, 'I-P': 0.7807949935532564, 'B-MC': 0.0, 'I-MC': 0.0}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7012189510495361, 'recall': 0.7012189510495361, 'f1': 0.7012189510495361, 'support': None}, 'macro_avg': {'precision': 0.33495076032454024, 'recall': 0.3614563075848249, 'f1': 0.31204944026491993, 'support': None}, 'weighted_avg': {'precision': 0.5876767382848889, 'recall': 0.7012189510495361, 'f1': 0.6153896802883736, 'support': None}}
			------------EPOCH 4---------------
Loss:  tensor(2.7609, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2111, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3165, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6880, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4424, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.2355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(2.1284, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2175, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4608, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8327620234756414, 'B-C': 0.19642857142857142, 'I-C': 0.26475849731663686, 'B-P': 0.45576407506702415, 'I-P': 0.6693283672074921, 'B-MC': 0.17475728155339806, 'I-MC': 0.3411042944785276}, 'recall': {'O': 0.8723375316231876, 'B-C': 0.009314140558848433, 'I-C': 0.008695652173913044, 'B-P': 0.7291322995710986, 'I-P': 0.9525788921727524, 'B-MC': 0.030456852791878174, 'I-MC': 0.032705882352941175}, 'f1': {'O': 0.8520905020659236, 'B-C': 0.017784963621665317, 'I-C': 0.016838272939302578, 'B-P': 0.5609137055837563, 'I-P': 0.7862201378615717, 'B-MC': 0.05187319884726225, 'I-MC': 0.059688674181427794}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7085393502831949, 'recall': 0.7085393502831949, 'f1': 0.708539350283195, 'support': None}, 'macro_avg': {'precision': 0.4192718729324702, 'recall': 0.3764601787492313, 'f1': 0.3350584935858443, 'support': None}, 'weighted_avg': {'precision': 0.6261104141954251, 'recall': 0.7085393502831949, 'f1': 0.6283223799809662, 'support': None}}
			------------EPOCH 5---------------
Loss:  tensor(2.4225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1974, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1677, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4626, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2885, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9946, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.9078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0833, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3697, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8689892991050658, 'B-C': 0.14149139579349904, 'I-C': 0.23779683377308708, 'B-P': 0.47397031151996655, 'I-P': 0.7071489461771363, 'B-MC': 0.168, 'I-MC': 0.3713751169317119}, 'recall': {'O': 0.8637414651396861, 'B-C': 0.06265876375952582, 'I-C': 0.08472385428907168, 'B-P': 0.7479379742659188, 'I-P': 0.9173991800934312, 'B-MC': 0.1065989847715736, 'I-MC': 0.14011764705882354}, 'f1': {'O': 0.8663574351978172, 'B-C': 0.08685446009389672, 'I-C': 0.12493501992722232, 'B-P': 0.5802405938059892, 'I-P': 0.7986686918486425, 'B-MC': 0.13043478260869565, 'I-MC': 0.20346801059195355}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7103046122698258, 'recall': 0.7103046122698258, 'f1': 0.7103046122698258, 'support': None}, 'macro_avg': {'precision': 0.42411027190006667, 'recall': 0.41759683848257584, 'f1': 0.3987084277248882, 'support': None}, 'weighted_avg': {'precision': 0.6520453284478902, 'recall': 0.7103046122698258, 'f1': 0.6653497365678668, 'support': None}}
			------------EPOCH 6---------------
Loss:  tensor(2.1378, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1717, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0257, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2881, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1507, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.7902, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.6049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9514, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.2200, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9242627137118121, 'B-C': 0.17223650385604114, 'I-C': 0.270743766122098, 'B-P': 0.5258386219401632, 'I-P': 0.7240988809584121, 'B-MC': 0.24504504504504504, 'I-MC': 0.35431723088626854}, 'recall': {'O': 0.8073501808982345, 'B-C': 0.11346316680779, 'I-C': 0.14800235017626323, 'B-P': 0.7654239524909271, 'I-P': 0.9265897607016875, 'B-MC': 0.23011844331641285, 'I-MC': 0.2191764705882353}, 'f1': {'O': 0.8618596817284236, 'B-C': 0.1368044920877999, 'I-C': 0.19138428810211214, 'B-P': 0.6234045411796317, 'I-P': 0.812924487269564, 'B-MC': 0.23734729493891796, 'I-MC': 0.270824247710423}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7131825749399727, 'recall': 0.7131825749399727, 'f1': 0.7131825749399727, 'support': None}, 'macro_avg': {'precision': 0.4595061089314057, 'recall': 0.4585891892827929, 'f1': 0.4477927190024103, 'support': None}, 'weighted_avg': {'precision': 0.681959964429816, 'recall': 0.7131825749399727, 'f1': 0.6865898041871634, 'support': None}}
			------------EPOCH 7---------------
Loss:  tensor(1.9050, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1511, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9118, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9910, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.5088, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.4225, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8859, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0950, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9128069358780403, 'B-C': 0.25477707006369427, 'I-C': 0.3552687441623503, 'B-P': 0.5876261972560186, 'I-P': 0.7654791852633287, 'B-MC': 0.310192023633678, 'I-MC': 0.44325958936813625}, 'recall': {'O': 0.8534860313919643, 'B-C': 0.20321761219305673, 'I-C': 0.24582843713278496, 'B-P': 0.7489277466182778, 'I-P': 0.8993231003908857, 'B-MC': 0.3553299492385787, 'I-MC': 0.3276470588235294}, 'f1': {'O': 0.882150338099054, 'B-C': 0.2260951483749411, 'I-C': 0.2905858249123172, 'B-P': 0.6585436611546271, 'I-P': 0.8270208662107662, 'B-MC': 0.3312302839116719, 'I-MC': 0.3767841439491308}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7381388616988346, 'recall': 0.7381388616988346, 'f1': 0.7381388616988346, 'support': None}, 'macro_avg': {'precision': 0.5184871065178924, 'recall': 0.5191085622555824, 'f1': 0.5132014666589299, 'support': None}, 'weighted_avg': {'precision': 0.7176579941756059, 'recall': 0.7381388616988346, 'f1': 0.7229132275501383, 'support': None}}
			------------EPOCH 8---------------
Loss:  tensor(1.5565, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1228, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7743, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9365, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8652, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.3034, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1730, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7401, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9379, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8187224616569957, 'B-C': 0.28190338860850755, 'I-C': 0.4423051030025582, 'B-P': 0.6060880048221821, 'I-P': 0.84800317486841, 'B-MC': 0.24625468164794007, 'I-MC': 0.4018750658379859}, 'recall': {'O': 0.9250020402056527, 'B-C': 0.3310753598645216, 'I-C': 0.38601645123384254, 'B-P': 0.6634774001979544, 'I-P': 0.7741252740966728, 'B-MC': 0.4450084602368866, 'I-MC': 0.44882352941176473}, 'f1': {'O': 0.8686233938743709, 'B-C': 0.3045171339563863, 'I-C': 0.4122482273953692, 'B-P': 0.633485588281619, 'I-P': 0.8093818841518725, 'B-MC': 0.3170584689572031, 'I-MC': 0.4240537986994943}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7333199474604489, 'recall': 0.7333199474604489, 'f1': 0.7333199474604489, 'support': None}, 'macro_avg': {'precision': 0.5207359829206542, 'recall': 0.5676469307496135, 'f1': 0.5384812136166165, 'support': None}, 'weighted_avg': {'precision': 0.7348013535885819, 'recall': 0.7333199474604489, 'f1': 0.7317682798669225, 'support': None}}
			------------EPOCH 9---------------
Loss:  tensor(1.4821, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0940, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6046, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7551, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6932, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.0916, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(1.1410, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7756, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8731, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9411670918367347, 'B-C': 0.28595744680851065, 'I-C': 0.36736709464291795, 'B-P': 0.6714593817397556, 'I-P': 0.8738974970202622, 'B-MC': 0.2965779467680608, 'I-MC': 0.41023238380809596}, 'recall': {'O': 0.8028889312042654, 'B-C': 0.5690093141405589, 'I-C': 0.6337837837837837, 'B-P': 0.6162982514021775, 'I-P': 0.6990180188769187, 'B-MC': 0.5279187817258884, 'I-MC': 0.5150588235294118}, 'f1': {'O': 0.8665462926263561, 'B-C': 0.3806287170773152, 'I-C': 0.46512730957462867, 'B-P': 0.6426974023739894, 'I-P': 0.7767360559351659, 'B-MC': 0.37979306147291536, 'I-MC': 0.45670769872731065}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7043646311773711, 'recall': 0.7043646311773711, 'f1': 0.7043646311773711, 'support': None}, 'macro_avg': {'precision': 0.5495226918034769, 'recall': 0.6234251292375721, 'f1': 0.5668909339696687, 'support': None}, 'weighted_avg': {'precision': 0.7756908164939312, 'recall': 0.7043646311773711, 'f1': 0.7279531243940294, 'support': None}}
			------------EPOCH 10---------------
Loss:  tensor(1.1716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0813, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6082, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5858, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9863, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.9634, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6911, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7249, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9031213937909877, 'B-C': 0.31, 'I-C': 0.40803124618576836, 'B-P': 0.6374825174825175, 'I-P': 0.8017065737919025, 'B-MC': 0.4274193548387097, 'I-MC': 0.6076727426875795}, 'recall': {'O': 0.8728543837218792, 'B-C': 0.3674851820491109, 'I-C': 0.39283196239717977, 'B-P': 0.7518970636753547, 'I-P': 0.8778339212508343, 'B-MC': 0.3587140439932318, 'I-MC': 0.3372941176470588}, 'f1': {'O': 0.8877299764836076, 'B-C': 0.33630375823324293, 'I-C': 0.400287373525714, 'B-P': 0.6899788071450197, 'I-P': 0.8380449622280877, 'B-MC': 0.3900643974241031, 'I-MC': 0.43380239067937654}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.75800015059107, 'recall': 0.75800015059107, 'f1': 0.7580001505910701, 'support': None}, 'macro_avg': {'precision': 0.5850619755396379, 'recall': 0.5655586678192356, 'f1': 0.5680302379598788, 'support': None}, 'weighted_avg': {'precision': 0.7521687731997442, 'recall': 0.75800015059107, 'f1': 0.7513185058818862, 'support': None}}
			------------EPOCH 11---------------
Loss:  tensor(0.8914, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0527, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4122, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4765, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4886, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.8102, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.7615, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6222, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6933, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.905262261096754, 'B-C': 0.3258317025440313, 'I-C': 0.41254876462938883, 'B-P': 0.6051697921946275, 'I-P': 0.7773807192741988, 'B-MC': 0.45588235294117646, 'I-MC': 0.6276840490797546}, 'recall': {'O': 0.8671418078942358, 'B-C': 0.2819644369178662, 'I-C': 0.2982373678025852, 'B-P': 0.7878587924777302, 'I-P': 0.9083992754314043, 'B-MC': 0.4196277495769882, 'I-MC': 0.3851764705882353}, 'f1': {'O': 0.8857920915886294, 'B-C': 0.30231502496595547, 'I-C': 0.34620106397490114, 'B-P': 0.6845349003869858, 'I-P': 0.8377986265596287, 'B-MC': 0.4370044052863436, 'I-MC': 0.47739865850102076}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7599578345004141, 'recall': 0.7599578345004141, 'f1': 0.7599578345004141, 'support': None}, 'macro_avg': {'precision': 0.5871085202514188, 'recall': 0.5640579858127207, 'f1': 0.567292110180495, 'support': None}, 'weighted_avg': {'precision': 0.7436979774374244, 'recall': 0.7599578345004141, 'f1': 0.7457714168612035, 'support': None}}
			------------EPOCH 12---------------
Loss:  tensor(0.7236, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0452, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3658, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3887, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.6754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5627, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4735, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5542, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8971557836078237, 'B-C': 0.2833178005591799, 'I-C': 0.4026799221958072, 'B-P': 0.6571923743500867, 'I-P': 0.8861630200018781, 'B-MC': 0.34458259325044405, 'I-MC': 0.4999122191011236}, 'recall': {'O': 0.8846603737656756, 'B-C': 0.514817950889077, 'I-C': 0.5473560517038778, 'B-P': 0.6255361266908611, 'I-P': 0.7197444942320527, 'B-MC': 0.6565143824027073, 'I-MC': 0.67}, 'f1': {'O': 0.890864265169155, 'B-C': 0.3654944394349263, 'I-C': 0.4640019922799153, 'B-P': 0.6409736308316429, 'I-P': 0.7943308677307688, 'B-MC': 0.45195107746068724, 'I-MC': 0.5725919967826262}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7376536238067749, 'recall': 0.7376536238067749, 'f1': 0.7376536238067749, 'support': None}, 'macro_avg': {'precision': 0.5672862447237634, 'recall': 0.6598041970977502, 'f1': 0.5971726099556746, 'support': None}, 'weighted_avg': {'precision': 0.7787919768848096, 'recall': 0.7376536238067749, 'f1': 0.7513961681774513, 'support': None}}
			------------EPOCH 13---------------
Loss:  tensor(0.6277, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0313, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2475, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3358, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2749, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4063, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4539, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4754, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5582, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9227062955330451, 'B-C': 0.3051299133910726, 'I-C': 0.3911607518164895, 'B-P': 0.6502824858757063, 'I-P': 0.7966113170500516, 'B-MC': 0.5390070921985816, 'I-MC': 0.7188144329896907}, 'recall': {'O': 0.8647751693370692, 'B-C': 0.3878069432684166, 'I-C': 0.3827262044653349, 'B-P': 0.7594853183767734, 'I-P': 0.897378205739346, 'B-MC': 0.38578680203045684, 'I-MC': 0.3281176470588235}, 'f1': {'O': 0.8928019771393266, 'B-C': 0.3415361670395228, 'I-C': 0.3868975143289876, 'B-P': 0.7006543905037285, 'I-P': 0.8439977045299666, 'B-MC': 0.44970414201183434, 'I-MC': 0.4505654281098546}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7625262488601092, 'recall': 0.7625262488601092, 'f1': 0.7625262488601092, 'support': None}, 'macro_avg': {'precision': 0.6176731841220909, 'recall': 0.5722966128966028, 'f1': 0.5808796176661745, 'support': None}, 'weighted_avg': {'precision': 0.7622859989040546, 'recall': 0.7625262488601092, 'f1': 0.7553929820154563, 'support': None}}
			------------EPOCH 14---------------
Loss:  tensor(0.4364, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0227, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1620, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1787, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2006, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2964, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3897, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.4402, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.5366, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8896833780233472, 'B-C': 0.31615336266499056, 'I-C': 0.424995603493757, 'B-P': 0.6381653454133636, 'I-P': 0.8303267973856209, 'B-MC': 0.399702823179792, 'I-MC': 0.5703691762050621}, 'recall': {'O': 0.8935556704115775, 'B-C': 0.4259102455546147, 'I-C': 0.42596944770857814, 'B-P': 0.74364896073903, 'I-P': 0.8478215273143292, 'B-MC': 0.45516074450084604, 'I-MC': 0.41623529411764704}, 'f1': {'O': 0.8916153198881682, 'B-C': 0.3629148629148629, 'I-C': 0.4254819683676164, 'B-P': 0.686880999542892, 'I-P': 0.8389829708948535, 'B-MC': 0.4256329113924051, 'I-MC': 0.48126232741617353}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7623756577901597, 'recall': 0.7623756577901597, 'f1': 0.7623756577901597, 'support': None}, 'macro_avg': {'precision': 0.5813423551951333, 'recall': 0.6011859843352318, 'f1': 0.587538765773853, 'support': None}, 'weighted_avg': {'precision': 0.7602973618901392, 'recall': 0.7623756577901597, 'f1': 0.760247750596037, 'support': None}}
			------------EPOCH 15---------------
Loss:  tensor(0.2526, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0148, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1308, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1558, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2040, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2724, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3038, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3437, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3829, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9158772154419504, 'B-C': 0.3286467486818981, 'I-C': 0.4386462064909373, 'B-P': 0.6552139843279083, 'I-P': 0.8457111537407509, 'B-MC': 0.38203463203463206, 'I-MC': 0.5483796296296296}, 'recall': {'O': 0.8757650771197737, 'B-C': 0.47502116850127013, 'I-C': 0.482021151586369, 'B-P': 0.7172550313427911, 'I-P': 0.823796358089427, 'B-MC': 0.5972927241962775, 'I-MC': 0.5574117647058824}, 'f1': {'O': 0.8953721214818111, 'B-C': 0.3885041551246538, 'I-C': 0.45931192788959496, 'B-P': 0.6848322570483539, 'I-P': 0.834609923597763, 'B-MC': 0.46600660066006605, 'I-MC': 0.5528588098016336}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7649022412970911, 'recall': 0.7649022412970911, 'f1': 0.7649022412970911, 'support': None}, 'macro_avg': {'precision': 0.5877870814782439, 'recall': 0.6469376107916844, 'f1': 0.6116422565148395, 'support': None}, 'weighted_avg': {'precision': 0.7759517516698585, 'recall': 0.7649022412970911, 'f1': 0.7697934457426917, 'support': None}}
			------------EPOCH 16---------------
Loss:  tensor(0.2043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0973, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1292, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2039, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2244, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2972, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3458, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9296863517446133, 'B-C': 0.3201238390092879, 'I-C': 0.41914101018954747, 'B-P': 0.6733031674208145, 'I-P': 0.8162511377224135, 'B-MC': 0.44745222929936307, 'I-MC': 0.6361871138570168}, 'recall': {'O': 0.8603411223851364, 'B-C': 0.4377646062658764, 'I-C': 0.44952996474735607, 'B-P': 0.7363906301550643, 'I-P': 0.8720945752693298, 'B-MC': 0.4754653130287648, 'I-MC': 0.424}, 'f1': {'O': 0.8936705283978525, 'B-C': 0.3698140200286123, 'I-C': 0.43380393490956515, 'B-P': 0.7034352347935707, 'I-P': 0.8432493224432602, 'B-MC': 0.461033634126333, 'I-MC': 0.5088598658665726}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7667511649892494, 'recall': 0.7667511649892494, 'f1': 0.7667511649892494, 'support': None}, 'macro_avg': {'precision': 0.606020692749008, 'recall': 0.6079408874073611, 'f1': 0.601980934366538, 'support': None}, 'weighted_avg': {'precision': 0.7714375070266197, 'recall': 0.7667511649892494, 'f1': 0.7665622424188161, 'support': None}}
			------------EPOCH 17---------------
Loss:  tensor(0.1460, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0682, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1017, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0862, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1767, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2644, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3347, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.8943981318054688, 'B-C': 0.3345145287030475, 'I-C': 0.4430701343852377, 'B-P': 0.6381084840055633, 'I-P': 0.8179886940553776, 'B-MC': 0.412, 'I-MC': 0.6306068601583114}, 'recall': {'O': 0.8960039171948533, 'B-C': 0.39966130397967825, 'I-C': 0.38936545240893067, 'B-P': 0.7568459254371495, 'I-P': 0.8663552292878254, 'B-MC': 0.5228426395939086, 'I-MC': 0.478}, 'f1': {'O': 0.8952003043974561, 'B-C': 0.36419753086419754, 'I-C': 0.4144854113894361, 'B-P': 0.6924237850890431, 'I-P': 0.841477530534952, 'B-MC': 0.46085011185682323, 'I-MC': 0.5437997724687145}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7708505885600984, 'recall': 0.7708505885600984, 'f1': 0.7708505885600984, 'support': None}, 'macro_avg': {'precision': 0.5958124047304294, 'recall': 0.6155820668431923, 'f1': 0.6017763495143748, 'support': None}, 'weighted_avg': {'precision': 0.7634319642516598, 'recall': 0.7708505885600984, 'f1': 0.7656535521869638, 'support': None}}
			------------EPOCH 18---------------
Loss:  tensor(0.1032, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0373, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0464, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0642, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0799, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1466, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2618, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3374, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.902808849117574, 'B-C': 0.34387617765814266, 'I-C': 0.4379737909149674, 'B-P': 0.6580720773513038, 'I-P': 0.832439628018599, 'B-MC': 0.38661710037174724, 'I-MC': 0.573729863692689}, 'recall': {'O': 0.8892032316857539, 'B-C': 0.43268416596104997, 'I-C': 0.43789659224441835, 'B-P': 0.7410095677994062, 'I-P': 0.8465821336638383, 'B-MC': 0.5279187817258884, 'I-MC': 0.49023529411764705}, 'f1': {'O': 0.8959543909659029, 'B-C': 0.38320209973753283, 'I-C': 0.43793518817757154, 'B-P': 0.6970825574177529, 'I-P': 0.8394513192350234, 'B-MC': 0.44635193133047213, 'I-MC': 0.5287064645054875}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7678136686494491, 'recall': 0.7678136686494491, 'f1': 0.7678136686494492, 'support': None}, 'macro_avg': {'precision': 0.5907882124464318, 'recall': 0.6236471095997145, 'f1': 0.6040977073385347, 'support': None}, 'weighted_avg': {'precision': 0.7680621028804135, 'recall': 0.7678136686494491, 'f1': 0.7674964113930244, 'support': None}}
			------------EPOCH 19---------------
Loss:  tensor(0.0761, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0051, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0249, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0311, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0374, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0451, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2302, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2882, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9226437976437977, 'B-C': 0.3196314670446492, 'I-C': 0.421936633159435, 'B-P': 0.6509671993271657, 'I-P': 0.8019662680369919, 'B-MC': 0.4444444444444444, 'I-MC': 0.6438767843726522}, 'recall': {'O': 0.8692092162890019, 'B-C': 0.38187976291278575, 'I-C': 0.38965922444183315, 'B-P': 0.766083800725833, 'I-P': 0.8912384402707598, 'B-MC': 0.4467005076142132, 'I-MC': 0.4032941176470588}, 'f1': {'O': 0.8951297746277647, 'B-C': 0.3479938271604938, 'I-C': 0.4051560877268007, 'B-P': 0.703849651409518, 'I-P': 0.8442489704501119, 'B-MC': 0.44556962025316454, 'I-MC': 0.4959490740740741}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7679391612077404, 'recall': 0.7679391612077404, 'f1': 0.7679391612077404, 'support': None}, 'macro_avg': {'precision': 0.6007809420041622, 'recall': 0.5925807242716408, 'f1': 0.591128143671704, 'support': None}, 'weighted_avg': {'precision': 0.7633626713712308, 'recall': 0.7679391612077404, 'f1': 0.7621707476173614, 'support': None}}
			------------EPOCH 20---------------
Loss:  tensor(0.0645, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0041, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0194, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0251, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0291, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0326, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0861, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1939, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2576, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9172478578951863, 'B-C': 0.3418745785569791, 'I-C': 0.4467091295116773, 'B-P': 0.6734571599760335, 'I-P': 0.8263846817572653, 'B-MC': 0.3704128440366973, 'I-MC': 0.5607018449232357}, 'recall': {'O': 0.8765267538967928, 'B-C': 0.42929720575783237, 'I-C': 0.4326674500587544, 'B-P': 0.7416694160343121, 'I-P': 0.8583087043569454, 'B-MC': 0.5465313028764806, 'I-MC': 0.5112941176470588}, 'f1': {'O': 0.8964250938934484, 'B-C': 0.38063063063063063, 'I-C': 0.4395761826593046, 'B-P': 0.7059192965928718, 'I-P': 0.8420442216319354, 'B-MC': 0.44155844155844154, 'I-MC': 0.5348593932681066}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7698884789465318, 'recall': 0.7698884789465318, 'f1': 0.7698884789465317, 'support': None}, 'macro_avg': {'precision': 0.5909697280938678, 'recall': 0.6280421358040252, 'f1': 0.6058590371763913, 'support': None}, 'weighted_avg': {'precision': 0.7704537369589791, 'recall': 0.7698884789465318, 'f1': 0.7696250345393418, 'support': None}}
			------------EPOCH 21---------------
Loss:  tensor(0.0423, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0030, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0181, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0232, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0243, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0663, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1697, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2315, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9184180468303826, 'B-C': 0.3393453573814295, 'I-C': 0.44391167939383175, 'B-P': 0.670346062052506, 'I-P': 0.8239701057236603, 'B-MC': 0.4053708439897698, 'I-MC': 0.6009824561403508}, 'recall': {'O': 0.8749217921166453, 'B-C': 0.43014394580863674, 'I-C': 0.440599294947121, 'B-P': 0.7413394919168591, 'I-P': 0.8619124797406807, 'B-MC': 0.5363790186125211, 'I-MC': 0.5037647058823529}, 'f1': {'O': 0.8961424332344214, 'B-C': 0.3793876026885736, 'I-C': 0.4422492849349807, 'B-P': 0.7040576531411562, 'I-P': 0.8425143283164811, 'B-MC': 0.4617625637290605, 'I-MC': 0.5480959999999999}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7715198822043187, 'recall': 0.7715198822043187, 'f1': 0.7715198822043186, 'support': None}, 'macro_avg': {'precision': 0.6003349359302758, 'recall': 0.6270086755749739, 'f1': 0.6106014094349533, 'support': None}, 'weighted_avg': {'precision': 0.7722892823049773, 'recall': 0.7715198822043187, 'f1': 0.7711066933287462, 'support': None}}
			------------EPOCH 22---------------
Loss:  tensor(0.0355, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0024, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0109, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0142, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0188, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0190, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0566, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1692, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2350, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9175448590145258, 'B-C': 0.34131326949384405, 'I-C': 0.4436239193083574, 'B-P': 0.6669624371487726, 'I-P': 0.8221120674002251, 'B-MC': 0.4075520833333333, 'I-MC': 0.6110483187341057}, 'recall': {'O': 0.876336334702538, 'B-C': 0.4225232853513971, 'I-C': 0.43413631022326676, 'B-P': 0.743978884856483, 'I-P': 0.8633234817427782, 'B-MC': 0.5296108291032149, 'I-MC': 0.5088235294117647}, 'f1': {'O': 0.896467281657414, 'B-C': 0.3776012107453651, 'I-C': 0.43882883952963536, 'B-P': 0.7033686837180287, 'I-P': 0.8422139342813828, 'B-MC': 0.46063281824871233, 'I-MC': 0.5552702529207858}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7719716554141672, 'recall': 0.7719716554141672, 'f1': 0.7719716554141672, 'support': None}, 'macro_avg': {'precision': 0.6014509934904521, 'recall': 0.6255332364844917, 'f1': 0.6106261458716177, 'support': None}, 'weighted_avg': {'precision': 0.771824755100654, 'recall': 0.7719716554141672, 'f1': 0.7710572248478695, 'support': None}}
			------------EPOCH 23---------------
Loss:  tensor(0.0279, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0089, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0115, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0167, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0161, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0640, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1840, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.3021, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.915472211206164, 'B-C': 0.341796875, 'I-C': 0.44059091696000924, 'B-P': 0.6662725391664204, 'I-P': 0.828322609274462, 'B-MC': 0.3854818523153942, 'I-MC': 0.5941375422773394}, 'recall': {'O': 0.8791382171322869, 'B-C': 0.4445385266723116, 'I-C': 0.44858989424206813, 'B-P': 0.74364896073903, 'I-P': 0.8542091715130137, 'B-MC': 0.5211505922165821, 'I-MC': 0.496}, 'f1': {'O': 0.8969374019954761, 'B-C': 0.38645564961354434, 'I-C': 0.44455442662086236, 'B-P': 0.702837542874961, 'I-P': 0.8410667517765116, 'B-MC': 0.4431654676258993, 'I-MC': 0.5406514490895101}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7701478302336672, 'recall': 0.7701478302336672, 'f1': 0.7701478302336672, 'support': None}, 'macro_avg': {'precision': 0.5960106494571128, 'recall': 0.6267536232164702, 'f1': 0.6079526699423949, 'support': None}, 'weighted_avg': {'precision': 0.7721559928207592, 'recall': 0.7701478302336672, 'f1': 0.7704618192742956, 'support': None}}
			------------EPOCH 24---------------
Loss:  tensor(0.0230, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0016, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0081, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0097, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0157, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0151, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0610, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1716, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2573, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9149345868494082, 'B-C': 0.34432515337423314, 'I-C': 0.4369638322695766, 'B-P': 0.6171976171976172, 'I-P': 0.7946664423319593, 'B-MC': 0.4691848906560636, 'I-MC': 0.674741246421493}, 'recall': {'O': 0.8789205951959957, 'B-C': 0.38018628281117695, 'I-C': 0.37408930669800233, 'B-P': 0.7862091718904652, 'I-P': 0.9005815616359997, 'B-MC': 0.3993231810490694, 'I-MC': 0.3604705882352941}, 'f1': {'O': 0.8965660770031217, 'B-C': 0.36136820925553315, 'I-C': 0.40308948751226614, 'B-P': 0.6915264074289033, 'I-P': 0.844315337861995, 'B-MC': 0.43144424131627057, 'I-MC': 0.46990261483015106}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7700223376753759, 'recall': 0.7700223376753759, 'f1': 0.7700223376753759, 'support': None}, 'macro_avg': {'precision': 0.6074305384429073, 'recall': 0.5828258125022863, 'f1': 0.5854589107440343, 'support': None}, 'weighted_avg': {'precision': 0.7616334043564345, 'recall': 0.7700223376753759, 'f1': 0.7602449171085247, 'support': None}}
			------------EPOCH 25---------------
Loss:  tensor(0.0297, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0019, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0079, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0092, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0131, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0495, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1395, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.2117, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9144591923185541, 'B-C': 0.3403205918618989, 'I-C': 0.42720336753485927, 'B-P': 0.6819299323909035, 'I-P': 0.832410622126302, 'B-MC': 0.41, 'I-MC': 0.5984327522789061}, 'recall': {'O': 0.88085198988058, 'B-C': 0.4674005080440305, 'I-C': 0.47702702702702704, 'B-P': 0.7321016166281755, 'I-P': 0.845743159500429, 'B-MC': 0.4856175972927242, 'I-MC': 0.44023529411764706}, 'f1': {'O': 0.8973410372587328, 'B-C': 0.39386371744559395, 'I-C': 0.45074253990284524, 'B-P': 0.7061256961018296, 'I-P': 0.8390239288754375, 'B-MC': 0.4446165762974438, 'I-MC': 0.5072866535619874}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.766801362012566, 'recall': 0.766801362012566, 'f1': 0.766801362012566, 'support': None}, 'macro_avg': {'precision': 0.6006794940730605, 'recall': 0.6184253132129448, 'f1': 0.6055714499205529, 'support': None}, 'weighted_avg': {'precision': 0.7725409515692092, 'recall': 0.766801362012566, 'f1': 0.7683618773414284, 'support': None}}
			------------EPOCH 26---------------
Loss:  tensor(0.0208, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0012, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0078, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0126, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0114, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0386, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1220, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1858, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9098422448694681, 'B-C': 0.34081902245706736, 'I-C': 0.4414103613612443, 'B-P': 0.6717995169082126, 'I-P': 0.8283964365256125, 'B-MC': 0.37824474660074164, 'I-MC': 0.5823587431309004}, 'recall': {'O': 0.8864285519980414, 'B-C': 0.43691786621507195, 'I-C': 0.4435370152761457, 'B-P': 0.7340811613328935, 'I-P': 0.8510630184002288, 'B-MC': 0.5177664974619289, 'I-MC': 0.48623529411764704}, 'f1': {'O': 0.8979828042328042, 'B-C': 0.38293135435992576, 'I-C': 0.4424711329933767, 'B-P': 0.7015607756582058, 'I-P': 0.8395767693392899, 'B-MC': 0.4371428571428571, 'I-MC': 0.5299737128935051}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7692610161550754, 'recall': 0.7692610161550754, 'f1': 0.7692610161550754, 'support': None}, 'macro_avg': {'precision': 0.5932672959790352, 'recall': 0.6222899149717083, 'f1': 0.6045199152314237, 'support': None}, 'weighted_avg': {'precision': 0.7698306669571812, 'recall': 0.7692610161550754, 'f1': 0.7689766403687287, 'support': None}}
			------------EPOCH 27---------------
Loss:  tensor(0.0193, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0011, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0054, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0069, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0116, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0099, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0322, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1085, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1686, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9140464171907166, 'B-C': 0.34538745387453873, 'I-C': 0.4500527148128624, 'B-P': 0.6537800687285223, 'I-P': 0.8134491770855408, 'B-MC': 0.40482573726541554, 'I-MC': 0.6056063558686854}, 'recall': {'O': 0.8817224776257446, 'B-C': 0.39627434377646065, 'I-C': 0.4012925969447709, 'B-P': 0.7532167601451666, 'I-P': 0.8783296787110306, 'B-MC': 0.5109983079526227, 'I-MC': 0.4752941176470588}, 'f1': {'O': 0.8975935310570187, 'B-C': 0.36908517350157727, 'I-C': 0.42427630761585294, 'B-P': 0.6999846696305381, 'I-P': 0.8446453292748893, 'B-MC': 0.4517576664173523, 'I-MC': 0.5325950827236174}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7730341590743669, 'recall': 0.7730341590743669, 'f1': 0.7730341590743668, 'support': None}, 'macro_avg': {'precision': 0.5981639892608974, 'recall': 0.6138754689718364, 'f1': 0.6028482514601209, 'support': None}, 'weighted_avg': {'precision': 0.7671687678108552, 'recall': 0.7730341590743669, 'f1': 0.7685719193851649, 'support': None}}
			------------EPOCH 28---------------
Loss:  tensor(0.0137, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0010, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0049, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0062, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0107, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0087, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0276, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0988, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1439, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9177431286632902, 'B-C': 0.3459343794579173, 'I-C': 0.44612889138436584, 'B-P': 0.6631609699094362, 'I-P': 0.8179703298079848, 'B-MC': 0.39197930142302717, 'I-MC': 0.5954909090909091}, 'recall': {'O': 0.8774244443839939, 'B-C': 0.4106689246401355, 'I-C': 0.4201527614571093, 'B-P': 0.7489277466182778, 'I-P': 0.8715606826198875, 'B-MC': 0.5126903553299492, 'I-MC': 0.48164705882352943}, 'f1': {'O': 0.8971310164518058, 'B-C': 0.37553232675183895, 'I-C': 0.4327513691790977, 'B-P': 0.7034397273008988, 'I-P': 0.8439155881321198, 'B-MC': 0.4442815249266862, 'I-MC': 0.5325528455284553}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7719214583908508, 'recall': 0.7719214583908508, 'f1': 0.7719214583908508, 'support': None}, 'macro_avg': {'precision': 0.5969154156767045, 'recall': 0.6175817105532689, 'f1': 0.6042291997529861, 'support': None}, 'weighted_avg': {'precision': 0.769191114518501, 'recall': 0.7719214583908508, 'f1': 0.7694276173846397, 'support': None}}
			------------EPOCH 29---------------
Loss:  tensor(0.0117, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0008, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0043, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0053, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0075, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0239, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0871, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1315, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9160537301564763, 'B-C': 0.3420074349442379, 'I-C': 0.44887382898146305, 'B-P': 0.6455944055944056, 'I-P': 0.8105217086834734, 'B-MC': 0.3925233644859813, 'I-MC': 0.6048486720197653}, 'recall': {'O': 0.8774788498680667, 'B-C': 0.3895004233700254, 'I-C': 0.3969447708578143, 'B-P': 0.7614648630814913, 'I-P': 0.8827724282581753, 'B-MC': 0.49746192893401014, 'I-MC': 0.4608235294117647}, 'f1': {'O': 0.8963514602495345, 'B-C': 0.3642121931908155, 'I-C': 0.4213152068847245, 'B-P': 0.6987587042082954, 'I-P': 0.845105645050883, 'B-MC': 0.4388059701492537, 'I-MC': 0.5231036324786325}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7721055141430113, 'recall': 0.7721055141430113, 'f1': 0.7721055141430113, 'support': None}, 'macro_avg': {'precision': 0.5943461635522576, 'recall': 0.6094923991116211, 'f1': 0.5982361160303056, 'support': None}, 'weighted_avg': {'precision': 0.7659781074053702, 'recall': 0.7721055141430113, 'f1': 0.7671520203728383, 'support': None}}
			------------EPOCH 30---------------
Loss:  tensor(0.0100, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0007, 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(0.0096, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0068, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0205, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.0776, device='cuda:0', grad_fn=<DivBackward0>)
Loss:  tensor(0.1178, device='cuda:0', grad_fn=<DivBackward0>)
				 {'precision': {'O': 0.9176134741650014, 'B-C': 0.34015525758645027, 'I-C': 0.4430703891074886, 'B-P': 0.6516533637400228, 'I-P': 0.8137096917001647, 'B-MC': 0.3991769547325103, 'I-MC': 0.6104038975326104}, 'recall': {'O': 0.8744049400179538, 'B-C': 0.40812870448772226, 'I-C': 0.41680376028202115, 'B-P': 0.7542065324975256, 'I-P': 0.8761750405186386, 'B-MC': 0.49238578680203043, 'I-MC': 0.45694117647058824}, 'f1': {'O': 0.8954882924043404, 'B-C': 0.37105465742879135, 'I-C': 0.42953589052708063, 'B-P': 0.6991894785135342, 'I-P': 0.8437878732234015, 'B-MC': 0.4409090909090909, 'I-MC': 0.5226401130323622}, 'support': {'O': 36761, 'B-C': 1181, 'I-C': 17020, 'B-P': 3031, 'I-P': 52445, 'B-MC': 591, 'I-MC': 8500}, 'micro_avg': {'precision': 0.7707920253662291, 'recall': 0.7707920253662291, 'f1': 0.7707920253662291, 'support': None}, 'macro_avg': {'precision': 0.5965404326520354, 'recall': 0.6112922772966399, 'f1': 0.6003721994340859, 'support': None}, 'weighted_avg': {'precision': 0.7675934973235276, 'recall': 0.7707920253662291, 'f1': 0.7675348917697666, 'support': None}}
