{ "best_global_step": 264710, "best_metric": 0.91086109084519, "best_model_checkpoint": "T:\\laupodteam\\AIOS\\Bram\\language_modeling\\Models\\language_models\\CardioCCC\\XLMR\\multilabel_3ldense_20epochs_40splits/fold_0\\checkpoint-264710", "epoch": 10.0, "eval_steps": 500, "global_step": 264710, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.009670960673945073, "grad_norm": 0.4483267664909363, "learning_rate": 9.990366816516189e-06, "loss": 0.46, "step": 256 }, { "epoch": 0.019341921347890145, "grad_norm": 0.27363523840904236, "learning_rate": 9.980695855842243e-06, "loss": 0.3699, "step": 512 }, { "epoch": 0.029012882021835214, "grad_norm": 0.2586195766925812, "learning_rate": 9.971024895168299e-06, "loss": 0.3709, "step": 768 }, { "epoch": 0.03868384269578029, "grad_norm": 0.4198613464832306, "learning_rate": 9.961353934494353e-06, "loss": 0.3456, "step": 1024 }, { "epoch": 0.04835480336972536, "grad_norm": 1.3434170484542847, "learning_rate": 9.951682973820407e-06, "loss": 0.3085, "step": 1280 }, { "epoch": 0.05802576404367043, "grad_norm": 1.5507402420043945, "learning_rate": 9.942012013146463e-06, "loss": 0.2964, "step": 1536 }, { "epoch": 0.06769672471761551, "grad_norm": 0.48595038056373596, "learning_rate": 9.932341052472519e-06, "loss": 0.2904, "step": 1792 }, { "epoch": 0.07736768539156058, "grad_norm": 1.4576889276504517, "learning_rate": 9.922670091798573e-06, "loss": 0.2832, "step": 2048 }, { "epoch": 0.08703864606550565, "grad_norm": 0.5639153718948364, "learning_rate": 9.912999131124627e-06, "loss": 0.2796, "step": 2304 }, { "epoch": 0.09670960673945073, "grad_norm": 0.5475741624832153, "learning_rate": 9.903328170450682e-06, "loss": 0.2755, "step": 2560 }, { "epoch": 0.10638056741339579, "grad_norm": 0.27892783284187317, "learning_rate": 9.893657209776738e-06, "loss": 0.2723, "step": 2816 }, { "epoch": 0.11605152808734086, "grad_norm": 0.5712042450904846, "learning_rate": 9.883986249102794e-06, "loss": 0.2668, "step": 3072 }, { "epoch": 0.12572248876128594, "grad_norm": 0.6643363833427429, "learning_rate": 9.874315288428848e-06, "loss": 0.2646, "step": 3328 }, { "epoch": 0.13539344943523102, "grad_norm": 0.766882061958313, "learning_rate": 9.864644327754902e-06, "loss": 0.2652, "step": 3584 }, { "epoch": 0.1450644101091761, "grad_norm": 0.417940616607666, "learning_rate": 9.854973367080958e-06, "loss": 0.2629, "step": 3840 }, { "epoch": 0.15473537078312116, "grad_norm": 0.35133096575737, "learning_rate": 9.845302406407012e-06, "loss": 0.2597, "step": 4096 }, { "epoch": 0.16440633145706623, "grad_norm": 0.8354504108428955, "learning_rate": 9.835631445733066e-06, "loss": 0.2548, "step": 4352 }, { "epoch": 0.1740772921310113, "grad_norm": 0.4678943157196045, "learning_rate": 9.825960485059122e-06, "loss": 0.2522, "step": 4608 }, { "epoch": 0.18374825280495638, "grad_norm": 1.4303853511810303, "learning_rate": 9.816289524385178e-06, "loss": 0.2525, "step": 4864 }, { "epoch": 0.19341921347890145, "grad_norm": 1.0086923837661743, "learning_rate": 9.806618563711232e-06, "loss": 0.2479, "step": 5120 }, { "epoch": 0.2030901741528465, "grad_norm": 0.9458017349243164, "learning_rate": 9.796947603037287e-06, "loss": 0.2466, "step": 5376 }, { "epoch": 0.21276113482679157, "grad_norm": 1.5085747241973877, "learning_rate": 9.78727664236334e-06, "loss": 0.242, "step": 5632 }, { "epoch": 0.22243209550073664, "grad_norm": 0.5289145112037659, "learning_rate": 9.777605681689397e-06, "loss": 0.2404, "step": 5888 }, { "epoch": 0.23210305617468172, "grad_norm": 1.12760591506958, "learning_rate": 9.767934721015453e-06, "loss": 0.2349, "step": 6144 }, { "epoch": 0.2417740168486268, "grad_norm": 1.223703145980835, "learning_rate": 9.758263760341507e-06, "loss": 0.2338, "step": 6400 }, { "epoch": 0.2514449775225719, "grad_norm": 1.4580013751983643, "learning_rate": 9.748592799667561e-06, "loss": 0.2302, "step": 6656 }, { "epoch": 0.26111593819651696, "grad_norm": 2.0796258449554443, "learning_rate": 9.738921838993617e-06, "loss": 0.2291, "step": 6912 }, { "epoch": 0.27078689887046203, "grad_norm": 0.7907488942146301, "learning_rate": 9.729250878319671e-06, "loss": 0.2248, "step": 7168 }, { "epoch": 0.2804578595444071, "grad_norm": 1.250164270401001, "learning_rate": 9.719579917645725e-06, "loss": 0.223, "step": 7424 }, { "epoch": 0.2901288202183522, "grad_norm": 1.041308879852295, "learning_rate": 9.709908956971781e-06, "loss": 0.2169, "step": 7680 }, { "epoch": 0.29979978089229725, "grad_norm": 0.6512206196784973, "learning_rate": 9.700237996297837e-06, "loss": 0.2112, "step": 7936 }, { "epoch": 0.3094707415662423, "grad_norm": 0.91297447681427, "learning_rate": 9.690567035623891e-06, "loss": 0.2067, "step": 8192 }, { "epoch": 0.3191417022401874, "grad_norm": 0.9919409155845642, "learning_rate": 9.680896074949946e-06, "loss": 0.202, "step": 8448 }, { "epoch": 0.32881266291413247, "grad_norm": 1.4038596153259277, "learning_rate": 9.671225114276e-06, "loss": 0.1965, "step": 8704 }, { "epoch": 0.33848362358807754, "grad_norm": 1.2001526355743408, "learning_rate": 9.661554153602056e-06, "loss": 0.1934, "step": 8960 }, { "epoch": 0.3481545842620226, "grad_norm": 1.8768125772476196, "learning_rate": 9.651883192928112e-06, "loss": 0.1865, "step": 9216 }, { "epoch": 0.3578255449359677, "grad_norm": 0.7226734161376953, "learning_rate": 9.642212232254166e-06, "loss": 0.1824, "step": 9472 }, { "epoch": 0.36749650560991276, "grad_norm": 0.673274040222168, "learning_rate": 9.63254127158022e-06, "loss": 0.179, "step": 9728 }, { "epoch": 0.37716746628385783, "grad_norm": 0.698570966720581, "learning_rate": 9.622870310906276e-06, "loss": 0.1745, "step": 9984 }, { "epoch": 0.3868384269578029, "grad_norm": 0.7360045909881592, "learning_rate": 9.613237127422464e-06, "loss": 0.1729, "step": 10240 }, { "epoch": 0.396509387631748, "grad_norm": 0.860123872756958, "learning_rate": 9.603566166748518e-06, "loss": 0.1679, "step": 10496 }, { "epoch": 0.406180348305693, "grad_norm": 1.1377097368240356, "learning_rate": 9.593895206074572e-06, "loss": 0.1656, "step": 10752 }, { "epoch": 0.41585130897963807, "grad_norm": 2.3113644123077393, "learning_rate": 9.584224245400627e-06, "loss": 0.159, "step": 11008 }, { "epoch": 0.42552226965358314, "grad_norm": 2.2741150856018066, "learning_rate": 9.574553284726682e-06, "loss": 0.159, "step": 11264 }, { "epoch": 0.4351932303275282, "grad_norm": 1.4500606060028076, "learning_rate": 9.564882324052738e-06, "loss": 0.1576, "step": 11520 }, { "epoch": 0.4448641910014733, "grad_norm": 2.1410915851593018, "learning_rate": 9.555211363378793e-06, "loss": 0.1528, "step": 11776 }, { "epoch": 0.45453515167541836, "grad_norm": 1.3274767398834229, "learning_rate": 9.54557817989498e-06, "loss": 0.1522, "step": 12032 }, { "epoch": 0.46420611234936343, "grad_norm": 0.747814953327179, "learning_rate": 9.535907219221036e-06, "loss": 0.1503, "step": 12288 }, { "epoch": 0.4738770730233085, "grad_norm": 0.8059080839157104, "learning_rate": 9.52623625854709e-06, "loss": 0.147, "step": 12544 }, { "epoch": 0.4835480336972536, "grad_norm": 0.7596678733825684, "learning_rate": 9.516565297873145e-06, "loss": 0.1472, "step": 12800 }, { "epoch": 0.49321899437119865, "grad_norm": 0.9714409708976746, "learning_rate": 9.506894337199199e-06, "loss": 0.1446, "step": 13056 }, { "epoch": 0.5028899550451438, "grad_norm": 0.9929206967353821, "learning_rate": 9.497223376525255e-06, "loss": 0.1418, "step": 13312 }, { "epoch": 0.5125609157190888, "grad_norm": 0.7590793371200562, "learning_rate": 9.48755241585131e-06, "loss": 0.1402, "step": 13568 }, { "epoch": 0.5222318763930339, "grad_norm": 0.6554539203643799, "learning_rate": 9.477881455177365e-06, "loss": 0.1395, "step": 13824 }, { "epoch": 0.5319028370669789, "grad_norm": 1.0402601957321167, "learning_rate": 9.46821049450342e-06, "loss": 0.1374, "step": 14080 }, { "epoch": 0.5415737977409241, "grad_norm": 0.8854435682296753, "learning_rate": 9.458539533829475e-06, "loss": 0.1349, "step": 14336 }, { "epoch": 0.5512447584148691, "grad_norm": 0.7135526537895203, "learning_rate": 9.44886857315553e-06, "loss": 0.1343, "step": 14592 }, { "epoch": 0.5609157190888142, "grad_norm": 1.573095679283142, "learning_rate": 9.439197612481584e-06, "loss": 0.1307, "step": 14848 }, { "epoch": 0.5705866797627592, "grad_norm": 0.6763337850570679, "learning_rate": 9.42952665180764e-06, "loss": 0.1318, "step": 15104 }, { "epoch": 0.5802576404367044, "grad_norm": 0.7201740145683289, "learning_rate": 9.419855691133695e-06, "loss": 0.1305, "step": 15360 }, { "epoch": 0.5899286011106494, "grad_norm": 0.6054624915122986, "learning_rate": 9.41018473045975e-06, "loss": 0.129, "step": 15616 }, { "epoch": 0.5995995617845945, "grad_norm": 1.1510297060012817, "learning_rate": 9.400513769785804e-06, "loss": 0.1284, "step": 15872 }, { "epoch": 0.6092705224585395, "grad_norm": 0.8782651424407959, "learning_rate": 9.390880586301992e-06, "loss": 0.1276, "step": 16128 }, { "epoch": 0.6189414831324846, "grad_norm": 0.8709959387779236, "learning_rate": 9.381209625628046e-06, "loss": 0.1241, "step": 16384 }, { "epoch": 0.6286124438064297, "grad_norm": 0.9368120431900024, "learning_rate": 9.371538664954102e-06, "loss": 0.1243, "step": 16640 }, { "epoch": 0.6382834044803748, "grad_norm": 0.7291781902313232, "learning_rate": 9.36190548147029e-06, "loss": 0.1249, "step": 16896 }, { "epoch": 0.6479543651543198, "grad_norm": 0.7002192139625549, "learning_rate": 9.352234520796344e-06, "loss": 0.1241, "step": 17152 }, { "epoch": 0.6576253258282649, "grad_norm": 1.0329126119613647, "learning_rate": 9.342563560122398e-06, "loss": 0.1216, "step": 17408 }, { "epoch": 0.66729628650221, "grad_norm": 1.4908815622329712, "learning_rate": 9.332892599448454e-06, "loss": 0.1197, "step": 17664 }, { "epoch": 0.6769672471761551, "grad_norm": 1.4585503339767456, "learning_rate": 9.323221638774508e-06, "loss": 0.1216, "step": 17920 }, { "epoch": 0.6866382078501001, "grad_norm": 1.023125410079956, "learning_rate": 9.313550678100564e-06, "loss": 0.1191, "step": 18176 }, { "epoch": 0.6963091685240452, "grad_norm": 0.608613133430481, "learning_rate": 9.303879717426618e-06, "loss": 0.1187, "step": 18432 }, { "epoch": 0.7059801291979902, "grad_norm": 0.5891420245170593, "learning_rate": 9.294208756752674e-06, "loss": 0.1181, "step": 18688 }, { "epoch": 0.7156510898719354, "grad_norm": 0.6835005879402161, "learning_rate": 9.284537796078728e-06, "loss": 0.1165, "step": 18944 }, { "epoch": 0.7253220505458804, "grad_norm": 0.7221260070800781, "learning_rate": 9.274866835404783e-06, "loss": 0.1149, "step": 19200 }, { "epoch": 0.7349930112198255, "grad_norm": 1.2140177488327026, "learning_rate": 9.265195874730839e-06, "loss": 0.1149, "step": 19456 }, { "epoch": 0.7446639718937705, "grad_norm": 0.5597007274627686, "learning_rate": 9.255524914056894e-06, "loss": 0.1156, "step": 19712 }, { "epoch": 0.7543349325677157, "grad_norm": 0.6929481625556946, "learning_rate": 9.245853953382949e-06, "loss": 0.1134, "step": 19968 }, { "epoch": 0.7640058932416607, "grad_norm": 1.0174293518066406, "learning_rate": 9.236182992709003e-06, "loss": 0.1123, "step": 20224 }, { "epoch": 0.7736768539156058, "grad_norm": 0.8737180829048157, "learning_rate": 9.226512032035057e-06, "loss": 0.1128, "step": 20480 }, { "epoch": 0.7833478145895508, "grad_norm": 0.6421831250190735, "learning_rate": 9.216841071361113e-06, "loss": 0.1114, "step": 20736 }, { "epoch": 0.793018775263496, "grad_norm": 1.8787974119186401, "learning_rate": 9.207207887877301e-06, "loss": 0.1118, "step": 20992 }, { "epoch": 0.802689735937441, "grad_norm": 0.6608098149299622, "learning_rate": 9.197536927203355e-06, "loss": 0.1112, "step": 21248 }, { "epoch": 0.812360696611386, "grad_norm": 1.6153572797775269, "learning_rate": 9.18786596652941e-06, "loss": 0.1103, "step": 21504 }, { "epoch": 0.8220316572853311, "grad_norm": 1.121106505393982, "learning_rate": 9.178195005855465e-06, "loss": 0.1086, "step": 21760 }, { "epoch": 0.8317026179592761, "grad_norm": 0.6411628127098083, "learning_rate": 9.168524045181521e-06, "loss": 0.109, "step": 22016 }, { "epoch": 0.8413735786332213, "grad_norm": 0.8473471403121948, "learning_rate": 9.158853084507575e-06, "loss": 0.1067, "step": 22272 }, { "epoch": 0.8510445393071663, "grad_norm": 1.0375288724899292, "learning_rate": 9.14918212383363e-06, "loss": 0.1086, "step": 22528 }, { "epoch": 0.8607154999811114, "grad_norm": 0.7472453117370605, "learning_rate": 9.139511163159684e-06, "loss": 0.1079, "step": 22784 }, { "epoch": 0.8703864606550564, "grad_norm": 0.7984833121299744, "learning_rate": 9.129877979675873e-06, "loss": 0.1061, "step": 23040 }, { "epoch": 0.8800574213290016, "grad_norm": 1.120253324508667, "learning_rate": 9.120207019001928e-06, "loss": 0.1062, "step": 23296 }, { "epoch": 0.8897283820029466, "grad_norm": 1.1492326259613037, "learning_rate": 9.110536058327982e-06, "loss": 0.1064, "step": 23552 }, { "epoch": 0.8993993426768917, "grad_norm": 1.4023070335388184, "learning_rate": 9.100865097654038e-06, "loss": 0.1049, "step": 23808 }, { "epoch": 0.9090703033508367, "grad_norm": 0.7418458461761475, "learning_rate": 9.091194136980092e-06, "loss": 0.1043, "step": 24064 }, { "epoch": 0.9187412640247818, "grad_norm": 0.9623353481292725, "learning_rate": 9.081523176306148e-06, "loss": 0.1032, "step": 24320 }, { "epoch": 0.9284122246987269, "grad_norm": 1.3711186647415161, "learning_rate": 9.071852215632202e-06, "loss": 0.1018, "step": 24576 }, { "epoch": 0.938083185372672, "grad_norm": 0.7474396228790283, "learning_rate": 9.062181254958256e-06, "loss": 0.1032, "step": 24832 }, { "epoch": 0.947754146046617, "grad_norm": 1.064741611480713, "learning_rate": 9.052548071474444e-06, "loss": 0.1018, "step": 25088 }, { "epoch": 0.9574251067205621, "grad_norm": 0.7454499006271362, "learning_rate": 9.0428771108005e-06, "loss": 0.1012, "step": 25344 }, { "epoch": 0.9670960673945072, "grad_norm": 1.3356425762176514, "learning_rate": 9.033206150126554e-06, "loss": 0.1, "step": 25600 }, { "epoch": 0.9767670280684523, "grad_norm": 0.6388442516326904, "learning_rate": 9.023535189452608e-06, "loss": 0.1014, "step": 25856 }, { "epoch": 0.9864379887423973, "grad_norm": 1.12908935546875, "learning_rate": 9.013864228778664e-06, "loss": 0.102, "step": 26112 }, { "epoch": 0.9961089494163424, "grad_norm": 0.6535469889640808, "learning_rate": 9.00419326810472e-06, "loss": 0.1012, "step": 26368 }, { "epoch": 1.0, "eval_f1_B-DISEASE": 0.796882405603244, "eval_f1_B-MEDICATION": 0.912161182780113, "eval_f1_B-PROCEDURE": 0.8136030994403788, "eval_f1_B-SYMPTOM": 0.7656342473860722, "eval_f1_I-DISEASE": 0.8505514375770186, "eval_f1_I-MEDICATION": 0.924679449751267, "eval_f1_I-PROCEDURE": 0.8341577368574741, "eval_f1_I-SYMPTOM": 0.7911674791374039, "eval_f1_O": 0.9244581521679408, "eval_f1_macro": 0.845921687855657, "eval_f1_micro": 0.8836774851512066, "eval_loss": 0.05375870317220688, "eval_precision_B-DISEASE": 0.8129656160458453, "eval_precision_B-MEDICATION": 0.8941460642227905, "eval_precision_B-PROCEDURE": 0.8691471571906354, "eval_precision_B-SYMPTOM": 0.8429626411815813, "eval_precision_I-DISEASE": 0.8241559111719139, "eval_precision_I-MEDICATION": 0.8882308071970206, "eval_precision_I-PROCEDURE": 0.8932063672541216, "eval_precision_I-SYMPTOM": 0.8226425051700121, "eval_precision_O": 0.9300109444266337, "eval_precision_macro": 0.8641631126511727, "eval_precision_micro": 0.8951563259355256, "eval_rauc_macro": 0.9061602751686828, "eval_rauc_micro": 0.9297292248575753, "eval_recall_B-DISEASE": 0.7814232106585878, "eval_recall_B-MEDICATION": 0.9309171597633136, "eval_recall_B-PROCEDURE": 0.7647318472743324, "eval_recall_B-SYMPTOM": 0.7013010480664981, "eval_recall_I-DISEASE": 0.8786936634360106, "eval_recall_I-MEDICATION": 0.964247442766683, "eval_recall_I-PROCEDURE": 0.7824322305406617, "eval_recall_I-SYMPTOM": 0.7620122211169532, "eval_recall_O": 0.9189712741824484, "eval_recall_macro": 0.8316366775339432, "eval_recall_micro": 0.8724893098751061, "eval_roc_auc_B-DISEASE": 0.8887628709990285, "eval_roc_auc_B-MEDICATION": 0.9651851113239337, "eval_roc_auc_B-PROCEDURE": 0.8811994973363028, "eval_roc_auc_B-SYMPTOM": 0.8490266405934911, "eval_roc_auc_I-DISEASE": 0.927262640706473, "eval_roc_auc_I-MEDICATION": 0.981200007333469, "eval_roc_auc_I-PROCEDURE": 0.8867019696658054, "eval_roc_auc_I-SYMPTOM": 0.8688926052280648, "eval_roc_auc_O": 0.9072111333315773, "eval_runtime": 38.4794, "eval_samples_per_second": 282.567, "eval_steps_per_second": 35.344, "step": 26471 }, { "epoch": 1.0057799100902876, "grad_norm": 0.8509446978569031, "learning_rate": 8.994522307430774e-06, "loss": 0.0994, "step": 26624 }, { "epoch": 1.0154508707642325, "grad_norm": 1.0466867685317993, "learning_rate": 8.984851346756829e-06, "loss": 0.0955, "step": 26880 }, { "epoch": 1.0251218314381776, "grad_norm": 0.966174304485321, "learning_rate": 8.975218163273016e-06, "loss": 0.0973, "step": 27136 }, { "epoch": 1.0347927921121227, "grad_norm": 1.0255135297775269, "learning_rate": 8.965547202599072e-06, "loss": 0.0946, "step": 27392 }, { "epoch": 1.0444637527860678, "grad_norm": 1.3129340410232544, "learning_rate": 8.955876241925127e-06, "loss": 0.0947, "step": 27648 }, { "epoch": 1.0541347134600128, "grad_norm": 0.9895825386047363, "learning_rate": 8.94620528125118e-06, "loss": 0.0951, "step": 27904 }, { "epoch": 1.0638056741339579, "grad_norm": 0.9932656288146973, "learning_rate": 8.936534320577237e-06, "loss": 0.0954, "step": 28160 }, { "epoch": 1.073476634807903, "grad_norm": 0.6559327244758606, "learning_rate": 8.926863359903291e-06, "loss": 0.0956, "step": 28416 }, { "epoch": 1.0831475954818481, "grad_norm": 0.8931130766868591, "learning_rate": 8.917192399229347e-06, "loss": 0.0946, "step": 28672 }, { "epoch": 1.092818556155793, "grad_norm": 0.9144744277000427, "learning_rate": 8.907521438555401e-06, "loss": 0.0937, "step": 28928 }, { "epoch": 1.1024895168297382, "grad_norm": 1.6046475172042847, "learning_rate": 8.897888255071589e-06, "loss": 0.0921, "step": 29184 }, { "epoch": 1.1121604775036833, "grad_norm": 0.7940915822982788, "learning_rate": 8.888217294397643e-06, "loss": 0.0932, "step": 29440 }, { "epoch": 1.1218314381776284, "grad_norm": 1.1314773559570312, "learning_rate": 8.878546333723699e-06, "loss": 0.0921, "step": 29696 }, { "epoch": 1.1315023988515733, "grad_norm": 0.9032577872276306, "learning_rate": 8.868875373049753e-06, "loss": 0.0924, "step": 29952 }, { "epoch": 1.1411733595255185, "grad_norm": 0.9383903741836548, "learning_rate": 8.859204412375807e-06, "loss": 0.0924, "step": 30208 }, { "epoch": 1.1508443201994636, "grad_norm": 1.0855649709701538, "learning_rate": 8.849533451701863e-06, "loss": 0.0907, "step": 30464 }, { "epoch": 1.1605152808734087, "grad_norm": 0.6509905457496643, "learning_rate": 8.83986249102792e-06, "loss": 0.0918, "step": 30720 }, { "epoch": 1.1701862415473536, "grad_norm": 1.1610795259475708, "learning_rate": 8.830191530353974e-06, "loss": 0.0903, "step": 30976 }, { "epoch": 1.1798572022212988, "grad_norm": 0.7398936748504639, "learning_rate": 8.820558346870161e-06, "loss": 0.0918, "step": 31232 }, { "epoch": 1.1895281628952439, "grad_norm": 0.6893290877342224, "learning_rate": 8.810887386196216e-06, "loss": 0.0916, "step": 31488 }, { "epoch": 1.199199123569189, "grad_norm": 0.7305893301963806, "learning_rate": 8.80121642552227e-06, "loss": 0.0898, "step": 31744 }, { "epoch": 1.208870084243134, "grad_norm": 2.0140328407287598, "learning_rate": 8.791545464848326e-06, "loss": 0.0871, "step": 32000 }, { "epoch": 1.218541044917079, "grad_norm": 1.0492117404937744, "learning_rate": 8.78187450417438e-06, "loss": 0.0903, "step": 32256 }, { "epoch": 1.2282120055910242, "grad_norm": 1.0894112586975098, "learning_rate": 8.772203543500434e-06, "loss": 0.0897, "step": 32512 }, { "epoch": 1.2378829662649693, "grad_norm": 0.6491110324859619, "learning_rate": 8.76253258282649e-06, "loss": 0.089, "step": 32768 }, { "epoch": 1.2475539269389142, "grad_norm": 0.8689417839050293, "learning_rate": 8.752861622152546e-06, "loss": 0.0879, "step": 33024 }, { "epoch": 1.2572248876128593, "grad_norm": 1.2077029943466187, "learning_rate": 8.743228438668732e-06, "loss": 0.0868, "step": 33280 }, { "epoch": 1.2668958482868045, "grad_norm": 0.9607778191566467, "learning_rate": 8.733557477994788e-06, "loss": 0.0892, "step": 33536 }, { "epoch": 1.2765668089607494, "grad_norm": 0.8975256681442261, "learning_rate": 8.723886517320842e-06, "loss": 0.0877, "step": 33792 }, { "epoch": 1.2862377696346945, "grad_norm": 0.7996318936347961, "learning_rate": 8.714215556646898e-06, "loss": 0.0866, "step": 34048 }, { "epoch": 1.2959087303086396, "grad_norm": 1.0175564289093018, "learning_rate": 8.704544595972952e-06, "loss": 0.0872, "step": 34304 }, { "epoch": 1.3055796909825848, "grad_norm": 0.9664493203163147, "learning_rate": 8.694873635299007e-06, "loss": 0.0872, "step": 34560 }, { "epoch": 1.3152506516565299, "grad_norm": 0.9043084383010864, "learning_rate": 8.685202674625062e-06, "loss": 0.0862, "step": 34816 }, { "epoch": 1.3249216123304748, "grad_norm": 1.0987842082977295, "learning_rate": 8.675531713951117e-06, "loss": 0.0871, "step": 35072 }, { "epoch": 1.33459257300442, "grad_norm": 0.7009199261665344, "learning_rate": 8.665898530467305e-06, "loss": 0.0852, "step": 35328 }, { "epoch": 1.344263533678365, "grad_norm": 0.9774173498153687, "learning_rate": 8.656227569793359e-06, "loss": 0.0843, "step": 35584 }, { "epoch": 1.35393449435231, "grad_norm": 1.5407440662384033, "learning_rate": 8.646556609119415e-06, "loss": 0.0867, "step": 35840 }, { "epoch": 1.363605455026255, "grad_norm": 0.9832726716995239, "learning_rate": 8.636885648445469e-06, "loss": 0.0848, "step": 36096 }, { "epoch": 1.3732764157002002, "grad_norm": 1.5583031177520752, "learning_rate": 8.627214687771525e-06, "loss": 0.0855, "step": 36352 }, { "epoch": 1.3829473763741453, "grad_norm": 1.3294652700424194, "learning_rate": 8.617543727097579e-06, "loss": 0.0838, "step": 36608 }, { "epoch": 1.3926183370480905, "grad_norm": 0.6503511071205139, "learning_rate": 8.607872766423633e-06, "loss": 0.0851, "step": 36864 }, { "epoch": 1.4022892977220354, "grad_norm": 1.2358441352844238, "learning_rate": 8.59820180574969e-06, "loss": 0.0852, "step": 37120 }, { "epoch": 1.4119602583959805, "grad_norm": 1.1809601783752441, "learning_rate": 8.588530845075745e-06, "loss": 0.0825, "step": 37376 }, { "epoch": 1.4216312190699256, "grad_norm": 0.7880055904388428, "learning_rate": 8.578897661591931e-06, "loss": 0.0835, "step": 37632 }, { "epoch": 1.4313021797438705, "grad_norm": 1.590612530708313, "learning_rate": 8.569226700917987e-06, "loss": 0.0833, "step": 37888 }, { "epoch": 1.4409731404178157, "grad_norm": 0.774364709854126, "learning_rate": 8.559555740244041e-06, "loss": 0.0838, "step": 38144 }, { "epoch": 1.4506441010917608, "grad_norm": 1.1419059038162231, "learning_rate": 8.549884779570097e-06, "loss": 0.0844, "step": 38400 }, { "epoch": 1.460315061765706, "grad_norm": 0.8213176727294922, "learning_rate": 8.540213818896151e-06, "loss": 0.0817, "step": 38656 }, { "epoch": 1.469986022439651, "grad_norm": 0.9972093105316162, "learning_rate": 8.530542858222206e-06, "loss": 0.0814, "step": 38912 }, { "epoch": 1.479656983113596, "grad_norm": 0.4948064982891083, "learning_rate": 8.52087189754826e-06, "loss": 0.0812, "step": 39168 }, { "epoch": 1.489327943787541, "grad_norm": 0.4733751714229584, "learning_rate": 8.511200936874316e-06, "loss": 0.0818, "step": 39424 }, { "epoch": 1.4989989044614862, "grad_norm": 0.822875440120697, "learning_rate": 8.501567753390504e-06, "loss": 0.0824, "step": 39680 }, { "epoch": 1.508669865135431, "grad_norm": 1.3491216897964478, "learning_rate": 8.491896792716558e-06, "loss": 0.0814, "step": 39936 }, { "epoch": 1.5183408258093762, "grad_norm": 0.8379246592521667, "learning_rate": 8.482225832042614e-06, "loss": 0.0806, "step": 40192 }, { "epoch": 1.5280117864833214, "grad_norm": 1.1273539066314697, "learning_rate": 8.472554871368668e-06, "loss": 0.081, "step": 40448 }, { "epoch": 1.5376827471572665, "grad_norm": 2.4888546466827393, "learning_rate": 8.462883910694724e-06, "loss": 0.0809, "step": 40704 }, { "epoch": 1.5473537078312116, "grad_norm": 1.3608648777008057, "learning_rate": 8.453212950020778e-06, "loss": 0.0814, "step": 40960 }, { "epoch": 1.5570246685051568, "grad_norm": 1.0673141479492188, "learning_rate": 8.443541989346832e-06, "loss": 0.0808, "step": 41216 }, { "epoch": 1.5666956291791017, "grad_norm": 1.0284321308135986, "learning_rate": 8.433871028672888e-06, "loss": 0.079, "step": 41472 }, { "epoch": 1.5763665898530468, "grad_norm": 0.8516680002212524, "learning_rate": 8.424237845189076e-06, "loss": 0.0794, "step": 41728 }, { "epoch": 1.5860375505269917, "grad_norm": 0.6379256248474121, "learning_rate": 8.41456688451513e-06, "loss": 0.0786, "step": 41984 }, { "epoch": 1.5957085112009368, "grad_norm": 0.7259079813957214, "learning_rate": 8.404895923841185e-06, "loss": 0.0786, "step": 42240 }, { "epoch": 1.605379471874882, "grad_norm": 0.75168776512146, "learning_rate": 8.39522496316724e-06, "loss": 0.0774, "step": 42496 }, { "epoch": 1.615050432548827, "grad_norm": 1.1931142807006836, "learning_rate": 8.385554002493296e-06, "loss": 0.0783, "step": 42752 }, { "epoch": 1.6247213932227722, "grad_norm": 0.8186140656471252, "learning_rate": 8.37588304181935e-06, "loss": 0.0794, "step": 43008 }, { "epoch": 1.634392353896717, "grad_norm": 1.4272133111953735, "learning_rate": 8.366212081145405e-06, "loss": 0.0773, "step": 43264 }, { "epoch": 1.6440633145706622, "grad_norm": 0.9854140281677246, "learning_rate": 8.356541120471459e-06, "loss": 0.0777, "step": 43520 }, { "epoch": 1.6537342752446071, "grad_norm": 0.8142780065536499, "learning_rate": 8.346907936987647e-06, "loss": 0.078, "step": 43776 }, { "epoch": 1.6634052359185523, "grad_norm": 0.9533801078796387, "learning_rate": 8.337236976313703e-06, "loss": 0.0777, "step": 44032 }, { "epoch": 1.6730761965924974, "grad_norm": 0.8595249652862549, "learning_rate": 8.327566015639757e-06, "loss": 0.0759, "step": 44288 }, { "epoch": 1.6827471572664425, "grad_norm": 1.223415732383728, "learning_rate": 8.317895054965813e-06, "loss": 0.077, "step": 44544 }, { "epoch": 1.6924181179403877, "grad_norm": 0.7294178009033203, "learning_rate": 8.308224094291867e-06, "loss": 0.0775, "step": 44800 }, { "epoch": 1.7020890786143328, "grad_norm": 1.3167471885681152, "learning_rate": 8.298553133617923e-06, "loss": 0.0769, "step": 45056 }, { "epoch": 1.7117600392882777, "grad_norm": 1.0041106939315796, "learning_rate": 8.288882172943977e-06, "loss": 0.075, "step": 45312 }, { "epoch": 1.7214309999622228, "grad_norm": 0.756957471370697, "learning_rate": 8.279211212270031e-06, "loss": 0.0756, "step": 45568 }, { "epoch": 1.7311019606361677, "grad_norm": 0.8045690059661865, "learning_rate": 8.26957802878622e-06, "loss": 0.0765, "step": 45824 }, { "epoch": 1.7407729213101129, "grad_norm": 0.8670371770858765, "learning_rate": 8.259907068112273e-06, "loss": 0.0739, "step": 46080 }, { "epoch": 1.750443881984058, "grad_norm": 0.6296207308769226, "learning_rate": 8.25023610743833e-06, "loss": 0.0755, "step": 46336 }, { "epoch": 1.760114842658003, "grad_norm": 0.9736904501914978, "learning_rate": 8.240565146764384e-06, "loss": 0.0753, "step": 46592 }, { "epoch": 1.7697858033319482, "grad_norm": 1.0412877798080444, "learning_rate": 8.23089418609044e-06, "loss": 0.0757, "step": 46848 }, { "epoch": 1.7794567640058934, "grad_norm": 0.544987142086029, "learning_rate": 8.221223225416494e-06, "loss": 0.0755, "step": 47104 }, { "epoch": 1.7891277246798383, "grad_norm": 1.1452064514160156, "learning_rate": 8.21155226474255e-06, "loss": 0.0742, "step": 47360 }, { "epoch": 1.7987986853537834, "grad_norm": 1.3037222623825073, "learning_rate": 8.201881304068604e-06, "loss": 0.0737, "step": 47616 }, { "epoch": 1.8084696460277283, "grad_norm": 1.3497453927993774, "learning_rate": 8.192210343394658e-06, "loss": 0.0737, "step": 47872 }, { "epoch": 1.8181406067016734, "grad_norm": 1.2125358581542969, "learning_rate": 8.182577159910846e-06, "loss": 0.0754, "step": 48128 }, { "epoch": 1.8278115673756186, "grad_norm": 0.8075161576271057, "learning_rate": 8.172906199236902e-06, "loss": 0.0731, "step": 48384 }, { "epoch": 1.8374825280495637, "grad_norm": 0.7323962450027466, "learning_rate": 8.163235238562956e-06, "loss": 0.0738, "step": 48640 }, { "epoch": 1.8471534887235088, "grad_norm": 0.9873864054679871, "learning_rate": 8.153564277889012e-06, "loss": 0.0722, "step": 48896 }, { "epoch": 1.856824449397454, "grad_norm": 0.8080263733863831, "learning_rate": 8.143893317215066e-06, "loss": 0.0727, "step": 49152 }, { "epoch": 1.8664954100713989, "grad_norm": 0.8908374309539795, "learning_rate": 8.134222356541122e-06, "loss": 0.073, "step": 49408 }, { "epoch": 1.876166370745344, "grad_norm": 1.0740896463394165, "learning_rate": 8.124551395867176e-06, "loss": 0.0732, "step": 49664 }, { "epoch": 1.8858373314192889, "grad_norm": 0.7212347984313965, "learning_rate": 8.11488043519323e-06, "loss": 0.0716, "step": 49920 }, { "epoch": 1.895508292093234, "grad_norm": 1.2111915349960327, "learning_rate": 8.105209474519285e-06, "loss": 0.0715, "step": 50176 }, { "epoch": 1.9051792527671791, "grad_norm": 0.6595506072044373, "learning_rate": 8.095576291035473e-06, "loss": 0.0733, "step": 50432 }, { "epoch": 1.9148502134411243, "grad_norm": 0.8859845995903015, "learning_rate": 8.085905330361529e-06, "loss": 0.0711, "step": 50688 }, { "epoch": 1.9245211741150694, "grad_norm": 0.7194809913635254, "learning_rate": 8.076234369687583e-06, "loss": 0.0717, "step": 50944 }, { "epoch": 1.9341921347890145, "grad_norm": 1.29291832447052, "learning_rate": 8.066563409013639e-06, "loss": 0.0717, "step": 51200 }, { "epoch": 1.9438630954629594, "grad_norm": 1.0920240879058838, "learning_rate": 8.056892448339693e-06, "loss": 0.0729, "step": 51456 }, { "epoch": 1.9535340561369046, "grad_norm": 0.8484604358673096, "learning_rate": 8.047221487665749e-06, "loss": 0.0715, "step": 51712 }, { "epoch": 1.9632050168108495, "grad_norm": 0.8444635272026062, "learning_rate": 8.037550526991803e-06, "loss": 0.071, "step": 51968 }, { "epoch": 1.9728759774847946, "grad_norm": 1.0049161911010742, "learning_rate": 8.027879566317857e-06, "loss": 0.0715, "step": 52224 }, { "epoch": 1.9825469381587397, "grad_norm": 1.4205676317214966, "learning_rate": 8.018208605643913e-06, "loss": 0.0689, "step": 52480 }, { "epoch": 1.9922178988326849, "grad_norm": 1.0721908807754517, "learning_rate": 8.008575422160101e-06, "loss": 0.0704, "step": 52736 }, { "epoch": 2.0, "eval_f1_B-DISEASE": 0.830906786338255, "eval_f1_B-MEDICATION": 0.9476126328393953, "eval_f1_B-PROCEDURE": 0.8511328671328672, "eval_f1_B-SYMPTOM": 0.8151037698473166, "eval_f1_I-DISEASE": 0.8746663007409995, "eval_f1_I-MEDICATION": 0.9575982064528706, "eval_f1_I-PROCEDURE": 0.8711981449824823, "eval_f1_I-SYMPTOM": 0.8184269255604771, "eval_f1_O": 0.9330515587419709, "eval_f1_macro": 0.8777441325151817, "eval_f1_micro": 0.9003430701205902, "eval_loss": 0.052078790962696075, "eval_precision_B-DISEASE": 0.8268280211351627, "eval_precision_B-MEDICATION": 0.958951832777946, "eval_precision_B-PROCEDURE": 0.8631567003290593, "eval_precision_B-SYMPTOM": 0.8249336870026526, "eval_precision_I-DISEASE": 0.8533283028971661, "eval_precision_I-MEDICATION": 0.9581585877304204, "eval_precision_I-PROCEDURE": 0.8886145878290893, "eval_precision_I-SYMPTOM": 0.8155582021482556, "eval_precision_O": 0.9427005517853116, "eval_precision_macro": 0.881358941515007, "eval_precision_micro": 0.9047441319793716, "eval_rauc_macro": 0.9286648516644438, "eval_rauc_micro": 0.9419777175113015, "eval_recall_B-DISEASE": 0.8350259923572142, "eval_recall_B-MEDICATION": 0.9365384615384615, "eval_recall_B-PROCEDURE": 0.839439417347164, "eval_recall_B-SYMPTOM": 0.8055053607999036, "eval_recall_I-DISEASE": 0.8970988068963311, "eval_recall_I-MEDICATION": 0.9570384802727716, "eval_recall_I-PROCEDURE": 0.8544512873292276, "eval_recall_I-SYMPTOM": 0.8213159016626403, "eval_recall_O": 0.9235980885867461, "eval_recall_macro": 0.87444575519894, "eval_recall_micro": 0.895984618277494, "eval_roc_auc_B-DISEASE": 0.9156172530920984, "eval_roc_auc_B-MEDICATION": 0.9681697542871597, "eval_roc_auc_B-PROCEDURE": 0.9183714242146286, "eval_roc_auc_B-SYMPTOM": 0.9006279311136295, "eval_roc_auc_I-DISEASE": 0.9386106449703465, "eval_roc_auc_I-MEDICATION": 0.9782010760838806, "eval_roc_auc_I-PROCEDURE": 0.9220574656075828, "eval_roc_auc_I-SYMPTOM": 0.8969622545583333, "eval_roc_auc_O": 0.9193658610523336, "eval_runtime": 38.368, "eval_samples_per_second": 283.387, "eval_steps_per_second": 35.446, "step": 52942 }, { "epoch": 2.00188885950663, "grad_norm": 0.9378567337989807, "learning_rate": 7.998904461486155e-06, "loss": 0.069, "step": 52992 }, { "epoch": 2.011559820180575, "grad_norm": 2.0163495540618896, "learning_rate": 7.98923350081221e-06, "loss": 0.0653, "step": 53248 }, { "epoch": 2.0212307808545202, "grad_norm": 1.2898911237716675, "learning_rate": 7.979562540138265e-06, "loss": 0.0664, "step": 53504 }, { "epoch": 2.030901741528465, "grad_norm": 1.9762269258499146, "learning_rate": 7.969891579464321e-06, "loss": 0.0654, "step": 53760 }, { "epoch": 2.04057270220241, "grad_norm": 0.5827069282531738, "learning_rate": 7.960220618790375e-06, "loss": 0.0662, "step": 54016 }, { "epoch": 2.050243662876355, "grad_norm": 1.0920411348342896, "learning_rate": 7.95054965811643e-06, "loss": 0.0651, "step": 54272 }, { "epoch": 2.0599146235503003, "grad_norm": 1.0318385362625122, "learning_rate": 7.940878697442484e-06, "loss": 0.0652, "step": 54528 }, { "epoch": 2.0695855842242454, "grad_norm": 1.0778378248214722, "learning_rate": 7.931245513958672e-06, "loss": 0.0658, "step": 54784 }, { "epoch": 2.0792565448981906, "grad_norm": 4.142551422119141, "learning_rate": 7.921574553284728e-06, "loss": 0.0644, "step": 55040 }, { "epoch": 2.0889275055721357, "grad_norm": 2.7905218601226807, "learning_rate": 7.911903592610782e-06, "loss": 0.0651, "step": 55296 }, { "epoch": 2.098598466246081, "grad_norm": 1.1025984287261963, "learning_rate": 7.902232631936838e-06, "loss": 0.0649, "step": 55552 }, { "epoch": 2.1082694269200255, "grad_norm": 0.8471400141716003, "learning_rate": 7.892561671262892e-06, "loss": 0.0638, "step": 55808 }, { "epoch": 2.1179403875939706, "grad_norm": 1.2384495735168457, "learning_rate": 7.882890710588948e-06, "loss": 0.0654, "step": 56064 }, { "epoch": 2.1276113482679158, "grad_norm": 0.7104564905166626, "learning_rate": 7.873219749915002e-06, "loss": 0.0641, "step": 56320 }, { "epoch": 2.137282308941861, "grad_norm": 0.9126619100570679, "learning_rate": 7.863548789241056e-06, "loss": 0.0637, "step": 56576 }, { "epoch": 2.146953269615806, "grad_norm": 2.24965500831604, "learning_rate": 7.85387782856711e-06, "loss": 0.063, "step": 56832 }, { "epoch": 2.156624230289751, "grad_norm": 1.4002108573913574, "learning_rate": 7.844206867893166e-06, "loss": 0.0632, "step": 57088 }, { "epoch": 2.1662951909636963, "grad_norm": 0.8987147808074951, "learning_rate": 7.834535907219222e-06, "loss": 0.0645, "step": 57344 }, { "epoch": 2.1759661516376414, "grad_norm": 0.9125319719314575, "learning_rate": 7.824902723735408e-06, "loss": 0.0644, "step": 57600 }, { "epoch": 2.185637112311586, "grad_norm": 1.348766803741455, "learning_rate": 7.815231763061464e-06, "loss": 0.0635, "step": 57856 }, { "epoch": 2.195308072985531, "grad_norm": 1.1573940515518188, "learning_rate": 7.80556080238752e-06, "loss": 0.0642, "step": 58112 }, { "epoch": 2.2049790336594763, "grad_norm": 1.7240798473358154, "learning_rate": 7.795889841713575e-06, "loss": 0.0627, "step": 58368 }, { "epoch": 2.2146499943334215, "grad_norm": 1.6762793064117432, "learning_rate": 7.786218881039629e-06, "loss": 0.0616, "step": 58624 }, { "epoch": 2.2243209550073666, "grad_norm": 1.6505228281021118, "learning_rate": 7.776547920365683e-06, "loss": 0.0633, "step": 58880 }, { "epoch": 2.2339919156813117, "grad_norm": 0.5941863656044006, "learning_rate": 7.766876959691739e-06, "loss": 0.064, "step": 59136 }, { "epoch": 2.243662876355257, "grad_norm": 0.9291194081306458, "learning_rate": 7.757205999017793e-06, "loss": 0.0631, "step": 59392 }, { "epoch": 2.253333837029202, "grad_norm": 0.976757287979126, "learning_rate": 7.747535038343849e-06, "loss": 0.0627, "step": 59648 }, { "epoch": 2.2630047977031467, "grad_norm": 0.9753232598304749, "learning_rate": 7.737864077669903e-06, "loss": 0.0611, "step": 59904 }, { "epoch": 2.272675758377092, "grad_norm": 1.528145670890808, "learning_rate": 7.728193116995959e-06, "loss": 0.061, "step": 60160 }, { "epoch": 2.282346719051037, "grad_norm": 1.1430556774139404, "learning_rate": 7.718522156322013e-06, "loss": 0.0617, "step": 60416 }, { "epoch": 2.292017679724982, "grad_norm": 0.6305384039878845, "learning_rate": 7.708851195648068e-06, "loss": 0.0623, "step": 60672 }, { "epoch": 2.301688640398927, "grad_norm": 1.172042727470398, "learning_rate": 7.699180234974123e-06, "loss": 0.0603, "step": 60928 }, { "epoch": 2.3113596010728723, "grad_norm": 1.3437776565551758, "learning_rate": 7.68950927430018e-06, "loss": 0.0614, "step": 61184 }, { "epoch": 2.3210305617468174, "grad_norm": 1.300218939781189, "learning_rate": 7.679838313626234e-06, "loss": 0.06, "step": 61440 }, { "epoch": 2.330701522420762, "grad_norm": 1.323150873184204, "learning_rate": 7.670205130142421e-06, "loss": 0.0606, "step": 61696 }, { "epoch": 2.3403724830947072, "grad_norm": 0.9929313659667969, "learning_rate": 7.660534169468476e-06, "loss": 0.0628, "step": 61952 }, { "epoch": 2.3500434437686524, "grad_norm": 1.01109778881073, "learning_rate": 7.65086320879453e-06, "loss": 0.0611, "step": 62208 }, { "epoch": 2.3597144044425975, "grad_norm": 0.8141628503799438, "learning_rate": 7.641192248120586e-06, "loss": 0.0616, "step": 62464 }, { "epoch": 2.3693853651165426, "grad_norm": 1.4890193939208984, "learning_rate": 7.63152128744664e-06, "loss": 0.0598, "step": 62720 }, { "epoch": 2.3790563257904878, "grad_norm": 0.9983785152435303, "learning_rate": 7.621850326772695e-06, "loss": 0.0614, "step": 62976 }, { "epoch": 2.388727286464433, "grad_norm": 0.9996428489685059, "learning_rate": 7.61217936609875e-06, "loss": 0.0598, "step": 63232 }, { "epoch": 2.398398247138378, "grad_norm": 0.9679495692253113, "learning_rate": 7.602508405424805e-06, "loss": 0.0606, "step": 63488 }, { "epoch": 2.408069207812323, "grad_norm": 0.7718194723129272, "learning_rate": 7.59283744475086e-06, "loss": 0.0604, "step": 63744 }, { "epoch": 2.417740168486268, "grad_norm": 0.8671106696128845, "learning_rate": 7.5831664840769145e-06, "loss": 0.0598, "step": 64000 }, { "epoch": 2.427411129160213, "grad_norm": 1.336706280708313, "learning_rate": 7.5734955234029695e-06, "loss": 0.0592, "step": 64256 }, { "epoch": 2.437082089834158, "grad_norm": 0.8477568030357361, "learning_rate": 7.563862339919158e-06, "loss": 0.0617, "step": 64512 }, { "epoch": 2.446753050508103, "grad_norm": 0.7895193696022034, "learning_rate": 7.5541913792452124e-06, "loss": 0.0598, "step": 64768 }, { "epoch": 2.4564240111820483, "grad_norm": 0.7384200692176819, "learning_rate": 7.5445204185712675e-06, "loss": 0.0586, "step": 65024 }, { "epoch": 2.4660949718559935, "grad_norm": 0.8035416007041931, "learning_rate": 7.534849457897322e-06, "loss": 0.0593, "step": 65280 }, { "epoch": 2.4757659325299386, "grad_norm": 1.2153276205062866, "learning_rate": 7.525178497223378e-06, "loss": 0.0599, "step": 65536 }, { "epoch": 2.4854368932038833, "grad_norm": 0.6699234247207642, "learning_rate": 7.515507536549433e-06, "loss": 0.0592, "step": 65792 }, { "epoch": 2.4951078538778284, "grad_norm": 1.1999285221099854, "learning_rate": 7.505836575875487e-06, "loss": 0.0591, "step": 66048 }, { "epoch": 2.5047788145517735, "grad_norm": 0.9291724562644958, "learning_rate": 7.496165615201542e-06, "loss": 0.0589, "step": 66304 }, { "epoch": 2.5144497752257187, "grad_norm": 1.065503478050232, "learning_rate": 7.486494654527597e-06, "loss": 0.0578, "step": 66560 }, { "epoch": 2.524120735899664, "grad_norm": 2.0710666179656982, "learning_rate": 7.476823693853652e-06, "loss": 0.058, "step": 66816 }, { "epoch": 2.533791696573609, "grad_norm": 0.7372413277626038, "learning_rate": 7.467190510369839e-06, "loss": 0.0589, "step": 67072 }, { "epoch": 2.543462657247554, "grad_norm": 1.651160478591919, "learning_rate": 7.457519549695894e-06, "loss": 0.0579, "step": 67328 }, { "epoch": 2.5531336179214987, "grad_norm": 1.757703423500061, "learning_rate": 7.447848589021948e-06, "loss": 0.0569, "step": 67584 }, { "epoch": 2.5628045785954443, "grad_norm": 0.6503134369850159, "learning_rate": 7.438177628348004e-06, "loss": 0.0594, "step": 67840 }, { "epoch": 2.572475539269389, "grad_norm": 1.0340873003005981, "learning_rate": 7.428506667674059e-06, "loss": 0.058, "step": 68096 }, { "epoch": 2.582146499943334, "grad_norm": 1.0522361993789673, "learning_rate": 7.4188357070001136e-06, "loss": 0.0564, "step": 68352 }, { "epoch": 2.5918174606172792, "grad_norm": 1.6682968139648438, "learning_rate": 7.409164746326169e-06, "loss": 0.0561, "step": 68608 }, { "epoch": 2.6014884212912244, "grad_norm": 1.004595398902893, "learning_rate": 7.3994937856522245e-06, "loss": 0.056, "step": 68864 }, { "epoch": 2.6111593819651695, "grad_norm": 0.8527024388313293, "learning_rate": 7.3898606021684115e-06, "loss": 0.0583, "step": 69120 }, { "epoch": 2.6208303426391146, "grad_norm": 1.530884027481079, "learning_rate": 7.380189641494467e-06, "loss": 0.056, "step": 69376 }, { "epoch": 2.6305013033130598, "grad_norm": 1.601316213607788, "learning_rate": 7.370518680820521e-06, "loss": 0.0583, "step": 69632 }, { "epoch": 2.6401722639870044, "grad_norm": 0.8617104291915894, "learning_rate": 7.360847720146576e-06, "loss": 0.055, "step": 69888 }, { "epoch": 2.6498432246609496, "grad_norm": 0.647162675857544, "learning_rate": 7.351176759472631e-06, "loss": 0.0553, "step": 70144 }, { "epoch": 2.6595141853348947, "grad_norm": 0.9281507134437561, "learning_rate": 7.341505798798686e-06, "loss": 0.0559, "step": 70400 }, { "epoch": 2.66918514600884, "grad_norm": 1.2437316179275513, "learning_rate": 7.33183483812474e-06, "loss": 0.0541, "step": 70656 }, { "epoch": 2.678856106682785, "grad_norm": 0.7374536991119385, "learning_rate": 7.322163877450795e-06, "loss": 0.0566, "step": 70912 }, { "epoch": 2.68852706735673, "grad_norm": 1.3053284883499146, "learning_rate": 7.312492916776851e-06, "loss": 0.0559, "step": 71168 }, { "epoch": 2.698198028030675, "grad_norm": 1.3258627653121948, "learning_rate": 7.302859733293038e-06, "loss": 0.0549, "step": 71424 }, { "epoch": 2.70786898870462, "grad_norm": 1.1512227058410645, "learning_rate": 7.293188772619093e-06, "loss": 0.0561, "step": 71680 }, { "epoch": 2.7175399493785655, "grad_norm": 1.007872462272644, "learning_rate": 7.2835178119451475e-06, "loss": 0.0554, "step": 71936 }, { "epoch": 2.72721091005251, "grad_norm": 1.4102001190185547, "learning_rate": 7.273846851271203e-06, "loss": 0.0558, "step": 72192 }, { "epoch": 2.7368818707264553, "grad_norm": 1.9055171012878418, "learning_rate": 7.2641758905972584e-06, "loss": 0.0541, "step": 72448 }, { "epoch": 2.7465528314004004, "grad_norm": 1.195149302482605, "learning_rate": 7.254504929923313e-06, "loss": 0.0547, "step": 72704 }, { "epoch": 2.7562237920743455, "grad_norm": 0.9224119782447815, "learning_rate": 7.244833969249368e-06, "loss": 0.055, "step": 72960 }, { "epoch": 2.7658947527482907, "grad_norm": 2.209676504135132, "learning_rate": 7.235163008575423e-06, "loss": 0.0544, "step": 73216 }, { "epoch": 2.775565713422236, "grad_norm": 0.9217004776000977, "learning_rate": 7.225529825091611e-06, "loss": 0.0543, "step": 73472 }, { "epoch": 2.785236674096181, "grad_norm": 1.2464416027069092, "learning_rate": 7.215858864417665e-06, "loss": 0.0549, "step": 73728 }, { "epoch": 2.7949076347701256, "grad_norm": 1.122103214263916, "learning_rate": 7.20618790374372e-06, "loss": 0.0532, "step": 73984 }, { "epoch": 2.8045785954440707, "grad_norm": 1.0579702854156494, "learning_rate": 7.196516943069775e-06, "loss": 0.0528, "step": 74240 }, { "epoch": 2.814249556118016, "grad_norm": 1.006489634513855, "learning_rate": 7.18684598239583e-06, "loss": 0.0525, "step": 74496 }, { "epoch": 2.823920516791961, "grad_norm": 1.3829524517059326, "learning_rate": 7.177175021721885e-06, "loss": 0.0539, "step": 74752 }, { "epoch": 2.833591477465906, "grad_norm": 1.1811540126800537, "learning_rate": 7.167504061047939e-06, "loss": 0.0526, "step": 75008 }, { "epoch": 2.8432624381398512, "grad_norm": 1.1461611986160278, "learning_rate": 7.157833100373994e-06, "loss": 0.0533, "step": 75264 }, { "epoch": 2.8529333988137964, "grad_norm": 0.7401432394981384, "learning_rate": 7.14816213970005e-06, "loss": 0.0537, "step": 75520 }, { "epoch": 2.862604359487741, "grad_norm": 1.054335117340088, "learning_rate": 7.1384911790261045e-06, "loss": 0.0519, "step": 75776 }, { "epoch": 2.8722753201616866, "grad_norm": 0.7766178846359253, "learning_rate": 7.1288202183521596e-06, "loss": 0.0526, "step": 76032 }, { "epoch": 2.8819462808356313, "grad_norm": 1.2377870082855225, "learning_rate": 7.119149257678214e-06, "loss": 0.0526, "step": 76288 }, { "epoch": 2.8916172415095764, "grad_norm": 0.8688779473304749, "learning_rate": 7.10947829700427e-06, "loss": 0.0516, "step": 76544 }, { "epoch": 2.9012882021835216, "grad_norm": 0.6655518412590027, "learning_rate": 7.0998451135204575e-06, "loss": 0.0528, "step": 76800 }, { "epoch": 2.9109591628574667, "grad_norm": 0.8370956778526306, "learning_rate": 7.090174152846512e-06, "loss": 0.0526, "step": 77056 }, { "epoch": 2.920630123531412, "grad_norm": 1.9562077522277832, "learning_rate": 7.080503192172567e-06, "loss": 0.0512, "step": 77312 }, { "epoch": 2.930301084205357, "grad_norm": 0.581018328666687, "learning_rate": 7.070832231498622e-06, "loss": 0.0521, "step": 77568 }, { "epoch": 2.939972044879302, "grad_norm": 1.0120258331298828, "learning_rate": 7.061161270824677e-06, "loss": 0.0528, "step": 77824 }, { "epoch": 2.9496430055532468, "grad_norm": 1.627193570137024, "learning_rate": 7.051490310150731e-06, "loss": 0.053, "step": 78080 }, { "epoch": 2.959313966227192, "grad_norm": 1.1197772026062012, "learning_rate": 7.041819349476786e-06, "loss": 0.0507, "step": 78336 }, { "epoch": 2.968984926901137, "grad_norm": 1.3899377584457397, "learning_rate": 7.032148388802842e-06, "loss": 0.0506, "step": 78592 }, { "epoch": 2.978655887575082, "grad_norm": 1.966417670249939, "learning_rate": 7.022515205319029e-06, "loss": 0.0516, "step": 78848 }, { "epoch": 2.9883268482490273, "grad_norm": 1.2017033100128174, "learning_rate": 7.012844244645084e-06, "loss": 0.0519, "step": 79104 }, { "epoch": 2.9979978089229724, "grad_norm": 1.040667176246643, "learning_rate": 7.003173283971138e-06, "loss": 0.0516, "step": 79360 }, { "epoch": 3.0, "eval_f1_B-DISEASE": 0.8394542433989608, "eval_f1_B-MEDICATION": 0.9547319074128333, "eval_f1_B-PROCEDURE": 0.8609510484360905, "eval_f1_B-SYMPTOM": 0.8250361988923886, "eval_f1_I-DISEASE": 0.8785681818914467, "eval_f1_I-MEDICATION": 0.9599060560308673, "eval_f1_I-PROCEDURE": 0.8836826064109301, "eval_f1_I-SYMPTOM": 0.8308232442147206, "eval_f1_O": 0.9370527300642346, "eval_f1_macro": 0.8855784685280524, "eval_f1_micro": 0.9064777986745736, "eval_loss": 0.05300184339284897, "eval_precision_B-DISEASE": 0.8625022698383875, "eval_precision_B-MEDICATION": 0.945589088798607, "eval_precision_B-PROCEDURE": 0.8617919139055762, "eval_precision_B-SYMPTOM": 0.8179181341936248, "eval_precision_I-DISEASE": 0.8854846255815767, "eval_precision_I-MEDICATION": 0.9448035099306505, "eval_precision_I-PROCEDURE": 0.895308919611902, "eval_precision_I-SYMPTOM": 0.8148502404897245, "eval_precision_O": 0.9430145499735109, "eval_precision_macro": 0.8856959169248401, "eval_precision_micro": 0.9094283877399175, "eval_rauc_macro": 0.9346142180621246, "eval_rauc_micro": 0.9460357666904499, "eval_recall_B-DISEASE": 0.8176059489792405, "eval_recall_B-MEDICATION": 0.9640532544378698, "eval_recall_B-PROCEDURE": 0.8601118222614581, "eval_recall_B-SYMPTOM": 0.8322792434646428, "eval_recall_I-DISEASE": 0.8717589482775165, "eval_recall_I-MEDICATION": 0.9754992693619094, "eval_recall_I-PROCEDURE": 0.872354376587374, "eval_recall_I-SYMPTOM": 0.847434986499929, "eval_recall_O": 0.9311658188624008, "eval_recall_macro": 0.8858070743035935, "eval_recall_micro": 0.9035462937311873, "eval_roc_auc_B-DISEASE": 0.9073901234412892, "eval_roc_auc_B-MEDICATION": 0.9818889752603492, "eval_roc_auc_B-PROCEDURE": 0.928658435530653, "eval_roc_auc_B-SYMPTOM": 0.913836686987879, "eval_roc_auc_I-DISEASE": 0.9286127131274897, "eval_roc_auc_I-MEDICATION": 0.9873157746093567, "eval_roc_auc_I-PROCEDURE": 0.93125492323472, "eval_roc_auc_I-SYMPTOM": 0.9095196871096386, "eval_roc_auc_O": 0.9230506432577466, "eval_runtime": 38.5615, "eval_samples_per_second": 281.965, "eval_steps_per_second": 35.268, "step": 79413 }, { "epoch": 3.0076687695969175, "grad_norm": 0.8741080164909363, "learning_rate": 6.9935023232971935e-06, "loss": 0.0477, "step": 79616 }, { "epoch": 3.0173397302708627, "grad_norm": 0.4949030578136444, "learning_rate": 6.983831362623249e-06, "loss": 0.0484, "step": 79872 }, { "epoch": 3.0270106909448073, "grad_norm": 0.6741498112678528, "learning_rate": 6.974160401949304e-06, "loss": 0.047, "step": 80128 }, { "epoch": 3.0366816516187525, "grad_norm": 0.8091663122177124, "learning_rate": 6.964489441275359e-06, "loss": 0.0472, "step": 80384 }, { "epoch": 3.0463526122926976, "grad_norm": 1.3941477537155151, "learning_rate": 6.954818480601413e-06, "loss": 0.0464, "step": 80640 }, { "epoch": 3.0560235729666427, "grad_norm": 1.378766417503357, "learning_rate": 6.9451852971176016e-06, "loss": 0.0468, "step": 80896 }, { "epoch": 3.065694533640588, "grad_norm": 1.1112360954284668, "learning_rate": 6.935514336443656e-06, "loss": 0.0459, "step": 81152 }, { "epoch": 3.075365494314533, "grad_norm": 0.5344024300575256, "learning_rate": 6.925843375769711e-06, "loss": 0.0469, "step": 81408 }, { "epoch": 3.085036454988478, "grad_norm": 1.5045959949493408, "learning_rate": 6.916172415095765e-06, "loss": 0.0457, "step": 81664 }, { "epoch": 3.0947074156624232, "grad_norm": 0.7609874606132507, "learning_rate": 6.906501454421821e-06, "loss": 0.0465, "step": 81920 }, { "epoch": 3.104378376336368, "grad_norm": 1.5546683073043823, "learning_rate": 6.896830493747876e-06, "loss": 0.0457, "step": 82176 }, { "epoch": 3.114049337010313, "grad_norm": 1.6246542930603027, "learning_rate": 6.88715953307393e-06, "loss": 0.0454, "step": 82432 }, { "epoch": 3.123720297684258, "grad_norm": 0.606778085231781, "learning_rate": 6.877488572399985e-06, "loss": 0.0456, "step": 82688 }, { "epoch": 3.1333912583582033, "grad_norm": 1.9695652723312378, "learning_rate": 6.867817611726041e-06, "loss": 0.046, "step": 82944 }, { "epoch": 3.1430622190321484, "grad_norm": 1.566140055656433, "learning_rate": 6.8581466510520955e-06, "loss": 0.0461, "step": 83200 }, { "epoch": 3.1527331797060936, "grad_norm": 1.2838099002838135, "learning_rate": 6.8484756903781505e-06, "loss": 0.0456, "step": 83456 }, { "epoch": 3.1624041403800387, "grad_norm": 2.1926662921905518, "learning_rate": 6.838804729704205e-06, "loss": 0.0455, "step": 83712 }, { "epoch": 3.1720751010539834, "grad_norm": 0.7610294222831726, "learning_rate": 6.8291715462203926e-06, "loss": 0.0456, "step": 83968 }, { "epoch": 3.1817460617279285, "grad_norm": 0.9290745258331299, "learning_rate": 6.819500585546448e-06, "loss": 0.0467, "step": 84224 }, { "epoch": 3.1914170224018736, "grad_norm": 0.6943319439888, "learning_rate": 6.809829624872503e-06, "loss": 0.0453, "step": 84480 }, { "epoch": 3.2010879830758188, "grad_norm": 1.6822216510772705, "learning_rate": 6.800158664198557e-06, "loss": 0.0453, "step": 84736 }, { "epoch": 3.210758943749764, "grad_norm": 1.1268625259399414, "learning_rate": 6.790487703524612e-06, "loss": 0.0455, "step": 84992 }, { "epoch": 3.220429904423709, "grad_norm": 1.3868532180786133, "learning_rate": 6.780816742850668e-06, "loss": 0.0453, "step": 85248 }, { "epoch": 3.230100865097654, "grad_norm": 0.8341856598854065, "learning_rate": 6.771145782176722e-06, "loss": 0.0457, "step": 85504 }, { "epoch": 3.2397718257715993, "grad_norm": 1.7002472877502441, "learning_rate": 6.761474821502777e-06, "loss": 0.0459, "step": 85760 }, { "epoch": 3.2494427864455444, "grad_norm": 0.786827802658081, "learning_rate": 6.751803860828831e-06, "loss": 0.0447, "step": 86016 }, { "epoch": 3.259113747119489, "grad_norm": 1.3061785697937012, "learning_rate": 6.742132900154887e-06, "loss": 0.0444, "step": 86272 }, { "epoch": 3.268784707793434, "grad_norm": 0.8705328106880188, "learning_rate": 6.732461939480942e-06, "loss": 0.045, "step": 86528 }, { "epoch": 3.2784556684673793, "grad_norm": 0.728818953037262, "learning_rate": 6.722790978806997e-06, "loss": 0.0454, "step": 86784 }, { "epoch": 3.2881266291413245, "grad_norm": 0.7723854184150696, "learning_rate": 6.713120018133052e-06, "loss": 0.0445, "step": 87040 }, { "epoch": 3.2977975898152696, "grad_norm": 1.028493881225586, "learning_rate": 6.703449057459107e-06, "loss": 0.0438, "step": 87296 }, { "epoch": 3.3074685504892147, "grad_norm": 1.6149994134902954, "learning_rate": 6.693778096785162e-06, "loss": 0.0435, "step": 87552 }, { "epoch": 3.31713951116316, "grad_norm": 1.7051756381988525, "learning_rate": 6.684107136111217e-06, "loss": 0.0432, "step": 87808 }, { "epoch": 3.3268104718371045, "grad_norm": 1.2699980735778809, "learning_rate": 6.674473952627404e-06, "loss": 0.0437, "step": 88064 }, { "epoch": 3.3364814325110497, "grad_norm": 1.4506620168685913, "learning_rate": 6.66480299195346e-06, "loss": 0.0434, "step": 88320 }, { "epoch": 3.346152393184995, "grad_norm": 1.033900260925293, "learning_rate": 6.655169808469647e-06, "loss": 0.0445, "step": 88576 }, { "epoch": 3.35582335385894, "grad_norm": 1.0005041360855103, "learning_rate": 6.645498847795702e-06, "loss": 0.0458, "step": 88832 }, { "epoch": 3.365494314532885, "grad_norm": 1.1036962270736694, "learning_rate": 6.635827887121756e-06, "loss": 0.0417, "step": 89088 }, { "epoch": 3.37516527520683, "grad_norm": 0.5079169273376465, "learning_rate": 6.626156926447811e-06, "loss": 0.0439, "step": 89344 }, { "epoch": 3.3848362358807753, "grad_norm": 1.0200902223587036, "learning_rate": 6.616485965773867e-06, "loss": 0.044, "step": 89600 }, { "epoch": 3.3945071965547204, "grad_norm": 1.1664658784866333, "learning_rate": 6.606815005099921e-06, "loss": 0.0429, "step": 89856 }, { "epoch": 3.4041781572286656, "grad_norm": 1.3110089302062988, "learning_rate": 6.597144044425976e-06, "loss": 0.0423, "step": 90112 }, { "epoch": 3.4138491179026103, "grad_norm": 1.1745210886001587, "learning_rate": 6.5874730837520305e-06, "loss": 0.043, "step": 90368 }, { "epoch": 3.4235200785765554, "grad_norm": 1.5075658559799194, "learning_rate": 6.577802123078086e-06, "loss": 0.043, "step": 90624 }, { "epoch": 3.4331910392505005, "grad_norm": 1.0469071865081787, "learning_rate": 6.5681311624041415e-06, "loss": 0.0424, "step": 90880 }, { "epoch": 3.4428619999244456, "grad_norm": 0.7738886475563049, "learning_rate": 6.558460201730196e-06, "loss": 0.0422, "step": 91136 }, { "epoch": 3.4525329605983908, "grad_norm": 1.0838168859481812, "learning_rate": 6.5488270182463835e-06, "loss": 0.042, "step": 91392 }, { "epoch": 3.462203921272336, "grad_norm": 0.970690906047821, "learning_rate": 6.539156057572438e-06, "loss": 0.042, "step": 91648 }, { "epoch": 3.471874881946281, "grad_norm": 1.2972304821014404, "learning_rate": 6.529485096898494e-06, "loss": 0.0435, "step": 91904 }, { "epoch": 3.4815458426202257, "grad_norm": 0.7299090027809143, "learning_rate": 6.519814136224548e-06, "loss": 0.0421, "step": 92160 }, { "epoch": 3.491216803294171, "grad_norm": 0.9907008409500122, "learning_rate": 6.510143175550603e-06, "loss": 0.0423, "step": 92416 }, { "epoch": 3.500887763968116, "grad_norm": 1.160920262336731, "learning_rate": 6.500472214876657e-06, "loss": 0.0421, "step": 92672 }, { "epoch": 3.510558724642061, "grad_norm": 1.733642816543579, "learning_rate": 6.490801254202713e-06, "loss": 0.0412, "step": 92928 }, { "epoch": 3.520229685316006, "grad_norm": 1.9292608499526978, "learning_rate": 6.481130293528768e-06, "loss": 0.0409, "step": 93184 }, { "epoch": 3.5299006459899513, "grad_norm": 1.060757040977478, "learning_rate": 6.471459332854822e-06, "loss": 0.0414, "step": 93440 }, { "epoch": 3.5395716066638965, "grad_norm": 2.676583766937256, "learning_rate": 6.461788372180877e-06, "loss": 0.0428, "step": 93696 }, { "epoch": 3.549242567337841, "grad_norm": 1.2607671022415161, "learning_rate": 6.452117411506933e-06, "loss": 0.0429, "step": 93952 }, { "epoch": 3.5589135280117867, "grad_norm": 1.5024772882461548, "learning_rate": 6.4424464508329875e-06, "loss": 0.041, "step": 94208 }, { "epoch": 3.5685844886857314, "grad_norm": 2.0261263847351074, "learning_rate": 6.432775490159043e-06, "loss": 0.0416, "step": 94464 }, { "epoch": 3.5782554493596765, "grad_norm": 0.6179674863815308, "learning_rate": 6.423104529485097e-06, "loss": 0.0405, "step": 94720 }, { "epoch": 3.5879264100336217, "grad_norm": 0.8594775199890137, "learning_rate": 6.413433568811153e-06, "loss": 0.0407, "step": 94976 }, { "epoch": 3.597597370707567, "grad_norm": 1.236023187637329, "learning_rate": 6.40380038532734e-06, "loss": 0.0419, "step": 95232 }, { "epoch": 3.607268331381512, "grad_norm": 1.166448712348938, "learning_rate": 6.394129424653395e-06, "loss": 0.0404, "step": 95488 }, { "epoch": 3.616939292055457, "grad_norm": 0.7166916131973267, "learning_rate": 6.384458463979449e-06, "loss": 0.0412, "step": 95744 }, { "epoch": 3.626610252729402, "grad_norm": 0.9981210231781006, "learning_rate": 6.374787503305505e-06, "loss": 0.0417, "step": 96000 }, { "epoch": 3.636281213403347, "grad_norm": 0.8939995765686035, "learning_rate": 6.36511654263156e-06, "loss": 0.0414, "step": 96256 }, { "epoch": 3.645952174077292, "grad_norm": 0.7995880246162415, "learning_rate": 6.355445581957614e-06, "loss": 0.0414, "step": 96512 }, { "epoch": 3.655623134751237, "grad_norm": 1.1740238666534424, "learning_rate": 6.345774621283669e-06, "loss": 0.0414, "step": 96768 }, { "epoch": 3.6652940954251823, "grad_norm": 0.9633038640022278, "learning_rate": 6.336103660609725e-06, "loss": 0.0399, "step": 97024 }, { "epoch": 3.6749650560991274, "grad_norm": 1.135442852973938, "learning_rate": 6.326432699935779e-06, "loss": 0.0405, "step": 97280 }, { "epoch": 3.6846360167730725, "grad_norm": 2.1878178119659424, "learning_rate": 6.3167617392618344e-06, "loss": 0.0401, "step": 97536 }, { "epoch": 3.6943069774470176, "grad_norm": 0.8652902841567993, "learning_rate": 6.3071285557780214e-06, "loss": 0.0404, "step": 97792 }, { "epoch": 3.7039779381209623, "grad_norm": 1.220574140548706, "learning_rate": 6.2974575951040765e-06, "loss": 0.0381, "step": 98048 }, { "epoch": 3.713648898794908, "grad_norm": 0.9763311743736267, "learning_rate": 6.2877866344301316e-06, "loss": 0.0396, "step": 98304 }, { "epoch": 3.7233198594688526, "grad_norm": 1.2430843114852905, "learning_rate": 6.278115673756187e-06, "loss": 0.0394, "step": 98560 }, { "epoch": 3.7329908201427977, "grad_norm": 0.8721135854721069, "learning_rate": 6.268444713082241e-06, "loss": 0.0403, "step": 98816 }, { "epoch": 3.742661780816743, "grad_norm": 0.7808983325958252, "learning_rate": 6.258773752408296e-06, "loss": 0.0401, "step": 99072 }, { "epoch": 3.752332741490688, "grad_norm": 0.8956592082977295, "learning_rate": 6.249102791734352e-06, "loss": 0.0407, "step": 99328 }, { "epoch": 3.762003702164633, "grad_norm": 0.9244728684425354, "learning_rate": 6.239431831060406e-06, "loss": 0.0387, "step": 99584 }, { "epoch": 3.771674662838578, "grad_norm": 0.8228873610496521, "learning_rate": 6.229760870386461e-06, "loss": 0.04, "step": 99840 }, { "epoch": 3.7813456235125233, "grad_norm": 0.8980506658554077, "learning_rate": 6.220089909712515e-06, "loss": 0.0391, "step": 100096 }, { "epoch": 3.791016584186468, "grad_norm": 0.8709131479263306, "learning_rate": 6.210418949038571e-06, "loss": 0.0382, "step": 100352 }, { "epoch": 3.800687544860413, "grad_norm": 1.481712818145752, "learning_rate": 6.200747988364626e-06, "loss": 0.0401, "step": 100608 }, { "epoch": 3.8103585055343583, "grad_norm": 0.715301513671875, "learning_rate": 6.1910770276906805e-06, "loss": 0.0388, "step": 100864 }, { "epoch": 3.8200294662083034, "grad_norm": 0.699769914150238, "learning_rate": 6.1814060670167356e-06, "loss": 0.0401, "step": 101120 }, { "epoch": 3.8297004268822485, "grad_norm": 1.719165563583374, "learning_rate": 6.171735106342791e-06, "loss": 0.039, "step": 101376 }, { "epoch": 3.8393713875561937, "grad_norm": 0.7806033492088318, "learning_rate": 6.162064145668846e-06, "loss": 0.0392, "step": 101632 }, { "epoch": 3.849042348230139, "grad_norm": 1.0042738914489746, "learning_rate": 6.152430962185033e-06, "loss": 0.0379, "step": 101888 }, { "epoch": 3.8587133089040835, "grad_norm": 0.6985491514205933, "learning_rate": 6.142760001511088e-06, "loss": 0.0395, "step": 102144 }, { "epoch": 3.868384269578029, "grad_norm": 1.0750198364257812, "learning_rate": 6.133089040837144e-06, "loss": 0.0383, "step": 102400 }, { "epoch": 3.8780552302519737, "grad_norm": 0.8359323143959045, "learning_rate": 6.123418080163198e-06, "loss": 0.0387, "step": 102656 }, { "epoch": 3.887726190925919, "grad_norm": 1.1092971563339233, "learning_rate": 6.113747119489253e-06, "loss": 0.038, "step": 102912 }, { "epoch": 3.897397151599864, "grad_norm": 0.8704983592033386, "learning_rate": 6.104076158815307e-06, "loss": 0.0384, "step": 103168 }, { "epoch": 3.907068112273809, "grad_norm": 1.6833209991455078, "learning_rate": 6.094405198141363e-06, "loss": 0.0375, "step": 103424 }, { "epoch": 3.9167390729477543, "grad_norm": 6.685204982757568, "learning_rate": 6.084734237467418e-06, "loss": 0.0382, "step": 103680 }, { "epoch": 3.9264100336216994, "grad_norm": 1.6752196550369263, "learning_rate": 6.075101053983605e-06, "loss": 0.0373, "step": 103936 }, { "epoch": 3.9360809942956445, "grad_norm": 0.7766474485397339, "learning_rate": 6.06543009330966e-06, "loss": 0.0371, "step": 104192 }, { "epoch": 3.945751954969589, "grad_norm": 1.3872442245483398, "learning_rate": 6.055759132635714e-06, "loss": 0.0377, "step": 104448 }, { "epoch": 3.9554229156435343, "grad_norm": 0.8299127221107483, "learning_rate": 6.04608817196177e-06, "loss": 0.0372, "step": 104704 }, { "epoch": 3.9650938763174794, "grad_norm": 0.8447323441505432, "learning_rate": 6.036417211287825e-06, "loss": 0.0377, "step": 104960 }, { "epoch": 3.9747648369914246, "grad_norm": 0.9614108204841614, "learning_rate": 6.026784027804012e-06, "loss": 0.0373, "step": 105216 }, { "epoch": 3.9844357976653697, "grad_norm": 0.8760530352592468, "learning_rate": 6.0171130671300674e-06, "loss": 0.0365, "step": 105472 }, { "epoch": 3.994106758339315, "grad_norm": 0.7628864049911499, "learning_rate": 6.0074421064561225e-06, "loss": 0.0369, "step": 105728 }, { "epoch": 4.0, "eval_f1_B-DISEASE": 0.8509981441975822, "eval_f1_B-MEDICATION": 0.9488472622478387, "eval_f1_B-PROCEDURE": 0.8670437433430052, "eval_f1_B-SYMPTOM": 0.8422448210922787, "eval_f1_I-DISEASE": 0.8882337424550406, "eval_f1_I-MEDICATION": 0.9527070101291526, "eval_f1_I-PROCEDURE": 0.8883074621130048, "eval_f1_I-SYMPTOM": 0.8433666963812189, "eval_f1_O": 0.9401220332143431, "eval_f1_macro": 0.8913189905748293, "eval_f1_micro": 0.9118464807112274, "eval_loss": 0.05749918147921562, "eval_precision_B-DISEASE": 0.8574973785389723, "eval_precision_B-MEDICATION": 0.9248595505617978, "eval_precision_B-PROCEDURE": 0.8657400616106792, "eval_precision_B-SYMPTOM": 0.8426637725724277, "eval_precision_I-DISEASE": 0.8625241080038573, "eval_precision_I-MEDICATION": 0.9244833432616963, "eval_precision_I-PROCEDURE": 0.8752648497103773, "eval_precision_I-SYMPTOM": 0.8371462653800704, "eval_precision_O": 0.9531163858156736, "eval_precision_macro": 0.8825884128283946, "eval_precision_micro": 0.9134930650393855, "eval_rauc_macro": 0.9427871451969972, "eval_rauc_micro": 0.9496071869373252, "eval_recall_B-DISEASE": 0.8445966881261404, "eval_recall_B-MEDICATION": 0.974112426035503, "eval_recall_B-PROCEDURE": 0.8683513573162657, "eval_recall_B-SYMPTOM": 0.8418262859896398, "eval_recall_I-DISEASE": 0.9155231423727729, "eval_recall_I-MEDICATION": 0.9827082318558208, "eval_recall_I-PROCEDURE": 0.9017446589532047, "eval_recall_I-SYMPTOM": 0.8496802614750604, "eval_recall_O": 0.9274772330873062, "eval_recall_macro": 0.9006689205790792, "eval_recall_micro": 0.9102058216862766, "eval_roc_auc_B-DISEASE": 0.9207768982828152, "eval_roc_auc_B-MEDICATION": 0.9868598295568363, "eval_roc_auc_B-PROCEDURE": 0.9328113698122986, "eval_roc_auc_B-SYMPTOM": 0.9189594667218607, "eval_roc_auc_I-DISEASE": 0.9483559751660133, "eval_roc_auc_I-MEDICATION": 0.990743003621933, "eval_roc_auc_I-PROCEDURE": 0.944671236725749, "eval_roc_auc_I-SYMPTOM": 0.9126524405602745, "eval_roc_auc_O": 0.9292540863251936, "eval_runtime": 38.4752, "eval_samples_per_second": 282.598, "eval_steps_per_second": 35.347, "step": 105884 }, { "epoch": 4.00377771901326, "grad_norm": 0.6653640270233154, "learning_rate": 5.9977711457821776e-06, "loss": 0.0361, "step": 105984 }, { "epoch": 4.013448679687205, "grad_norm": 1.1266523599624634, "learning_rate": 5.988100185108232e-06, "loss": 0.0345, "step": 106240 }, { "epoch": 4.02311964036115, "grad_norm": 1.2451099157333374, "learning_rate": 5.978429224434287e-06, "loss": 0.0335, "step": 106496 }, { "epoch": 4.032790601035095, "grad_norm": 2.1595659255981445, "learning_rate": 5.968758263760343e-06, "loss": 0.0323, "step": 106752 }, { "epoch": 4.0424615617090405, "grad_norm": 1.075042963027954, "learning_rate": 5.959087303086397e-06, "loss": 0.0337, "step": 107008 }, { "epoch": 4.052132522382985, "grad_norm": 0.7220308184623718, "learning_rate": 5.949416342412452e-06, "loss": 0.0339, "step": 107264 }, { "epoch": 4.06180348305693, "grad_norm": 0.8600826859474182, "learning_rate": 5.939745381738506e-06, "loss": 0.0334, "step": 107520 }, { "epoch": 4.071474443730875, "grad_norm": 0.6774386763572693, "learning_rate": 5.930112198254694e-06, "loss": 0.0342, "step": 107776 }, { "epoch": 4.08114540440482, "grad_norm": 0.7089745402336121, "learning_rate": 5.92044123758075e-06, "loss": 0.0327, "step": 108032 }, { "epoch": 4.090816365078766, "grad_norm": 0.6529690623283386, "learning_rate": 5.910770276906804e-06, "loss": 0.0333, "step": 108288 }, { "epoch": 4.10048732575271, "grad_norm": 1.2246057987213135, "learning_rate": 5.901099316232859e-06, "loss": 0.0335, "step": 108544 }, { "epoch": 4.110158286426656, "grad_norm": 0.7716206908226013, "learning_rate": 5.8914283555589135e-06, "loss": 0.0332, "step": 108800 }, { "epoch": 4.119829247100601, "grad_norm": 0.5499569773674011, "learning_rate": 5.881757394884969e-06, "loss": 0.0325, "step": 109056 }, { "epoch": 4.129500207774546, "grad_norm": 1.4891330003738403, "learning_rate": 5.872086434211024e-06, "loss": 0.0335, "step": 109312 }, { "epoch": 4.139171168448491, "grad_norm": 1.3562936782836914, "learning_rate": 5.862415473537079e-06, "loss": 0.0317, "step": 109568 }, { "epoch": 4.1488421291224356, "grad_norm": 1.5345656871795654, "learning_rate": 5.852744512863133e-06, "loss": 0.0323, "step": 109824 }, { "epoch": 4.158513089796381, "grad_norm": 1.0285918712615967, "learning_rate": 5.843073552189189e-06, "loss": 0.0316, "step": 110080 }, { "epoch": 4.168184050470326, "grad_norm": 1.1976503133773804, "learning_rate": 5.833402591515244e-06, "loss": 0.0327, "step": 110336 }, { "epoch": 4.177855011144271, "grad_norm": 1.0610854625701904, "learning_rate": 5.823769408031431e-06, "loss": 0.0332, "step": 110592 }, { "epoch": 4.187525971818216, "grad_norm": 1.108175277709961, "learning_rate": 5.814098447357486e-06, "loss": 0.0329, "step": 110848 }, { "epoch": 4.197196932492162, "grad_norm": 1.01539146900177, "learning_rate": 5.804427486683542e-06, "loss": 0.0326, "step": 111104 }, { "epoch": 4.206867893166106, "grad_norm": 1.9922451972961426, "learning_rate": 5.794756526009596e-06, "loss": 0.0331, "step": 111360 }, { "epoch": 4.216538853840051, "grad_norm": 0.9041112065315247, "learning_rate": 5.785085565335651e-06, "loss": 0.0327, "step": 111616 }, { "epoch": 4.226209814513997, "grad_norm": 2.7803843021392822, "learning_rate": 5.775414604661705e-06, "loss": 0.0324, "step": 111872 }, { "epoch": 4.235880775187941, "grad_norm": 0.9206538796424866, "learning_rate": 5.765743643987761e-06, "loss": 0.0311, "step": 112128 }, { "epoch": 4.245551735861887, "grad_norm": 1.1627826690673828, "learning_rate": 5.7560726833138155e-06, "loss": 0.0319, "step": 112384 }, { "epoch": 4.2552226965358315, "grad_norm": 0.9371087551116943, "learning_rate": 5.7464017226398706e-06, "loss": 0.0316, "step": 112640 }, { "epoch": 4.264893657209777, "grad_norm": 1.1846144199371338, "learning_rate": 5.736730761965925e-06, "loss": 0.0339, "step": 112896 }, { "epoch": 4.274564617883722, "grad_norm": 0.9367378354072571, "learning_rate": 5.727059801291981e-06, "loss": 0.0311, "step": 113152 }, { "epoch": 4.2842355785576665, "grad_norm": 1.100913643836975, "learning_rate": 5.717388840618036e-06, "loss": 0.0315, "step": 113408 }, { "epoch": 4.293906539231612, "grad_norm": 1.187778353691101, "learning_rate": 5.70771787994409e-06, "loss": 0.0316, "step": 113664 }, { "epoch": 4.303577499905557, "grad_norm": 0.725979745388031, "learning_rate": 5.698046919270145e-06, "loss": 0.0315, "step": 113920 }, { "epoch": 4.313248460579502, "grad_norm": 1.1214196681976318, "learning_rate": 5.688375958596201e-06, "loss": 0.0323, "step": 114176 }, { "epoch": 4.322919421253447, "grad_norm": 1.4811276197433472, "learning_rate": 5.678742775112388e-06, "loss": 0.0316, "step": 114432 }, { "epoch": 4.3325903819273925, "grad_norm": 1.1874852180480957, "learning_rate": 5.669071814438443e-06, "loss": 0.0318, "step": 114688 }, { "epoch": 4.342261342601337, "grad_norm": 1.5446730852127075, "learning_rate": 5.659400853764497e-06, "loss": 0.0319, "step": 114944 }, { "epoch": 4.351932303275283, "grad_norm": 1.3255748748779297, "learning_rate": 5.649729893090552e-06, "loss": 0.0311, "step": 115200 }, { "epoch": 4.3616032639492275, "grad_norm": 2.808878183364868, "learning_rate": 5.640058932416607e-06, "loss": 0.0303, "step": 115456 }, { "epoch": 4.371274224623172, "grad_norm": 1.8177087306976318, "learning_rate": 5.630387971742662e-06, "loss": 0.0321, "step": 115712 }, { "epoch": 4.380945185297118, "grad_norm": 1.0746417045593262, "learning_rate": 5.620717011068717e-06, "loss": 0.0321, "step": 115968 }, { "epoch": 4.390616145971062, "grad_norm": 1.4166860580444336, "learning_rate": 5.611046050394772e-06, "loss": 0.031, "step": 116224 }, { "epoch": 4.400287106645008, "grad_norm": 0.6993358135223389, "learning_rate": 5.601412866910959e-06, "loss": 0.031, "step": 116480 }, { "epoch": 4.409958067318953, "grad_norm": 1.108292579650879, "learning_rate": 5.591741906237015e-06, "loss": 0.032, "step": 116736 }, { "epoch": 4.419629027992898, "grad_norm": 0.8879403471946716, "learning_rate": 5.58207094556307e-06, "loss": 0.0309, "step": 116992 }, { "epoch": 4.429299988666843, "grad_norm": 0.9429001212120056, "learning_rate": 5.572399984889124e-06, "loss": 0.0309, "step": 117248 }, { "epoch": 4.438970949340788, "grad_norm": 0.9483521580696106, "learning_rate": 5.562729024215179e-06, "loss": 0.0307, "step": 117504 }, { "epoch": 4.448641910014733, "grad_norm": 0.6683099865913391, "learning_rate": 5.553058063541235e-06, "loss": 0.03, "step": 117760 }, { "epoch": 4.458312870688678, "grad_norm": 1.0182121992111206, "learning_rate": 5.543387102867289e-06, "loss": 0.0305, "step": 118016 }, { "epoch": 4.4679838313626234, "grad_norm": 1.771382451057434, "learning_rate": 5.533716142193344e-06, "loss": 0.0306, "step": 118272 }, { "epoch": 4.477654792036568, "grad_norm": 1.163429856300354, "learning_rate": 5.524082958709531e-06, "loss": 0.0307, "step": 118528 }, { "epoch": 4.487325752710514, "grad_norm": 2.089336633682251, "learning_rate": 5.514411998035587e-06, "loss": 0.0308, "step": 118784 }, { "epoch": 4.496996713384458, "grad_norm": 1.2090080976486206, "learning_rate": 5.504741037361642e-06, "loss": 0.0316, "step": 119040 }, { "epoch": 4.506667674058404, "grad_norm": 1.0133914947509766, "learning_rate": 5.495070076687696e-06, "loss": 0.0301, "step": 119296 }, { "epoch": 4.516338634732349, "grad_norm": 1.0716972351074219, "learning_rate": 5.485399116013751e-06, "loss": 0.0298, "step": 119552 }, { "epoch": 4.526009595406293, "grad_norm": 0.6935496926307678, "learning_rate": 5.4757281553398064e-06, "loss": 0.0305, "step": 119808 }, { "epoch": 4.535680556080239, "grad_norm": 0.8148974776268005, "learning_rate": 5.4660571946658615e-06, "loss": 0.0302, "step": 120064 }, { "epoch": 4.545351516754184, "grad_norm": 1.1045907735824585, "learning_rate": 5.456386233991916e-06, "loss": 0.0289, "step": 120320 }, { "epoch": 4.555022477428129, "grad_norm": 1.0339943170547485, "learning_rate": 5.446715273317971e-06, "loss": 0.0307, "step": 120576 }, { "epoch": 4.564693438102074, "grad_norm": 0.9054391980171204, "learning_rate": 5.437044312644027e-06, "loss": 0.0296, "step": 120832 }, { "epoch": 4.574364398776019, "grad_norm": 1.1923002004623413, "learning_rate": 5.427373351970081e-06, "loss": 0.0298, "step": 121088 }, { "epoch": 4.584035359449964, "grad_norm": 1.5210239887237549, "learning_rate": 5.417702391296136e-06, "loss": 0.0304, "step": 121344 }, { "epoch": 4.593706320123909, "grad_norm": 0.7538612484931946, "learning_rate": 5.40803143062219e-06, "loss": 0.0291, "step": 121600 }, { "epoch": 4.603377280797854, "grad_norm": 1.1296252012252808, "learning_rate": 5.398360469948246e-06, "loss": 0.0294, "step": 121856 }, { "epoch": 4.613048241471799, "grad_norm": 0.7613297700881958, "learning_rate": 5.388689509274301e-06, "loss": 0.0296, "step": 122112 }, { "epoch": 4.622719202145745, "grad_norm": 0.6040092706680298, "learning_rate": 5.379018548600355e-06, "loss": 0.0287, "step": 122368 }, { "epoch": 4.632390162819689, "grad_norm": 0.9116784334182739, "learning_rate": 5.369385365116543e-06, "loss": 0.0296, "step": 122624 }, { "epoch": 4.642061123493635, "grad_norm": 0.7086608409881592, "learning_rate": 5.3597144044425974e-06, "loss": 0.0299, "step": 122880 }, { "epoch": 4.6517320841675796, "grad_norm": 0.7918397188186646, "learning_rate": 5.350043443768653e-06, "loss": 0.0292, "step": 123136 }, { "epoch": 4.661403044841524, "grad_norm": 1.2006558179855347, "learning_rate": 5.3403724830947076e-06, "loss": 0.0294, "step": 123392 }, { "epoch": 4.67107400551547, "grad_norm": 0.8358765840530396, "learning_rate": 5.330701522420763e-06, "loss": 0.0295, "step": 123648 }, { "epoch": 4.6807449661894145, "grad_norm": 0.6896599531173706, "learning_rate": 5.321030561746817e-06, "loss": 0.0292, "step": 123904 }, { "epoch": 4.69041592686336, "grad_norm": 1.1973057985305786, "learning_rate": 5.311359601072873e-06, "loss": 0.0294, "step": 124160 }, { "epoch": 4.700086887537305, "grad_norm": 1.2296339273452759, "learning_rate": 5.301688640398928e-06, "loss": 0.0287, "step": 124416 }, { "epoch": 4.70975784821125, "grad_norm": 1.0709811449050903, "learning_rate": 5.292055456915115e-06, "loss": 0.0289, "step": 124672 }, { "epoch": 4.719428808885195, "grad_norm": 1.000148057937622, "learning_rate": 5.28238449624117e-06, "loss": 0.029, "step": 124928 }, { "epoch": 4.729099769559141, "grad_norm": 0.9339204430580139, "learning_rate": 5.272751312757357e-06, "loss": 0.0283, "step": 125184 }, { "epoch": 4.738770730233085, "grad_norm": 0.944106936454773, "learning_rate": 5.263080352083413e-06, "loss": 0.0283, "step": 125440 }, { "epoch": 4.748441690907031, "grad_norm": 2.134193181991577, "learning_rate": 5.253409391409468e-06, "loss": 0.0293, "step": 125696 }, { "epoch": 4.7581126515809755, "grad_norm": 1.1633158922195435, "learning_rate": 5.243738430735522e-06, "loss": 0.0289, "step": 125952 }, { "epoch": 4.76778361225492, "grad_norm": 1.4737567901611328, "learning_rate": 5.234067470061577e-06, "loss": 0.0286, "step": 126208 }, { "epoch": 4.777454572928866, "grad_norm": 0.6703898906707764, "learning_rate": 5.224396509387632e-06, "loss": 0.0275, "step": 126464 }, { "epoch": 4.7871255336028105, "grad_norm": 0.9056229591369629, "learning_rate": 5.214725548713687e-06, "loss": 0.0288, "step": 126720 }, { "epoch": 4.796796494276756, "grad_norm": 1.5667541027069092, "learning_rate": 5.2050545880397415e-06, "loss": 0.0295, "step": 126976 }, { "epoch": 4.806467454950701, "grad_norm": 1.0100566148757935, "learning_rate": 5.1953836273657965e-06, "loss": 0.0286, "step": 127232 }, { "epoch": 4.816138415624646, "grad_norm": 0.48219913244247437, "learning_rate": 5.185750443881985e-06, "loss": 0.0287, "step": 127488 }, { "epoch": 4.825809376298591, "grad_norm": 0.6783737540245056, "learning_rate": 5.1760794832080394e-06, "loss": 0.0276, "step": 127744 }, { "epoch": 4.835480336972536, "grad_norm": 1.4024484157562256, "learning_rate": 5.1664085225340945e-06, "loss": 0.0279, "step": 128000 }, { "epoch": 4.845151297646481, "grad_norm": 0.753887951374054, "learning_rate": 5.156737561860149e-06, "loss": 0.0276, "step": 128256 }, { "epoch": 4.854822258320426, "grad_norm": 0.9314492344856262, "learning_rate": 5.147066601186205e-06, "loss": 0.0279, "step": 128512 }, { "epoch": 4.8644932189943715, "grad_norm": 0.5442036986351013, "learning_rate": 5.13739564051226e-06, "loss": 0.0274, "step": 128768 }, { "epoch": 4.874164179668316, "grad_norm": 0.9161281585693359, "learning_rate": 5.127724679838314e-06, "loss": 0.028, "step": 129024 }, { "epoch": 4.883835140342262, "grad_norm": 0.7710080146789551, "learning_rate": 5.118053719164369e-06, "loss": 0.0278, "step": 129280 }, { "epoch": 4.893506101016206, "grad_norm": 1.237382411956787, "learning_rate": 5.108382758490424e-06, "loss": 0.0277, "step": 129536 }, { "epoch": 4.903177061690151, "grad_norm": 0.7518734335899353, "learning_rate": 5.098711797816479e-06, "loss": 0.028, "step": 129792 }, { "epoch": 4.912848022364097, "grad_norm": 1.2846450805664062, "learning_rate": 5.089078614332666e-06, "loss": 0.0273, "step": 130048 }, { "epoch": 4.922518983038041, "grad_norm": 0.7847537398338318, "learning_rate": 5.079407653658721e-06, "loss": 0.0274, "step": 130304 }, { "epoch": 4.932189943711987, "grad_norm": 1.0385159254074097, "learning_rate": 5.069736692984775e-06, "loss": 0.0274, "step": 130560 }, { "epoch": 4.941860904385932, "grad_norm": 2.1298296451568604, "learning_rate": 5.060065732310831e-06, "loss": 0.0278, "step": 130816 }, { "epoch": 4.951531865059877, "grad_norm": 0.9606920480728149, "learning_rate": 5.050394771636886e-06, "loss": 0.0277, "step": 131072 }, { "epoch": 4.961202825733822, "grad_norm": 0.7911926507949829, "learning_rate": 5.0407238109629406e-06, "loss": 0.0272, "step": 131328 }, { "epoch": 4.970873786407767, "grad_norm": 0.8920175433158875, "learning_rate": 5.031052850288996e-06, "loss": 0.0263, "step": 131584 }, { "epoch": 4.980544747081712, "grad_norm": 1.2151284217834473, "learning_rate": 5.0213818896150515e-06, "loss": 0.0274, "step": 131840 }, { "epoch": 4.990215707755657, "grad_norm": 0.9935512542724609, "learning_rate": 5.011710928941106e-06, "loss": 0.0268, "step": 132096 }, { "epoch": 4.999886668429602, "grad_norm": 0.887349545955658, "learning_rate": 5.002077745457294e-06, "loss": 0.0272, "step": 132352 }, { "epoch": 5.0, "eval_f1_B-DISEASE": 0.859286083807553, "eval_f1_B-MEDICATION": 0.9611983924004385, "eval_f1_B-PROCEDURE": 0.8722304283604135, "eval_f1_B-SYMPTOM": 0.8498140814413979, "eval_f1_I-DISEASE": 0.89268359711691, "eval_f1_I-MEDICATION": 0.9650105303465442, "eval_f1_I-PROCEDURE": 0.8940237055520899, "eval_f1_I-SYMPTOM": 0.8535565794541228, "eval_f1_O": 0.9429699196951137, "eval_f1_macro": 0.8989748131305093, "eval_f1_micro": 0.9165948150326803, "eval_loss": 0.0577140636742115, "eval_precision_B-DISEASE": 0.8608299070587015, "eval_precision_B-MEDICATION": 0.9497472924187725, "eval_precision_B-PROCEDURE": 0.8756580410765923, "eval_precision_B-SYMPTOM": 0.8530375675183589, "eval_precision_I-DISEASE": 0.8720354857013857, "eval_precision_I-MEDICATION": 0.9485743859979298, "eval_precision_I-PROCEDURE": 0.8959389170445452, "eval_precision_I-SYMPTOM": 0.8443680615809028, "eval_precision_O": 0.9527554665170026, "eval_precision_macro": 0.8947716805460212, "eval_precision_micro": 0.9184077264722751, "eval_rauc_macro": 0.9444449386237811, "eval_rauc_micro": 0.9522128016210953, "eval_recall_B-DISEASE": 0.8577477880676145, "eval_recall_B-MEDICATION": 0.9729289940828403, "eval_recall_B-PROCEDURE": 0.8688295446185537, "eval_recall_B-SYMPTOM": 0.8466148656788339, "eval_recall_I-DISEASE": 0.9143332373732527, "eval_recall_I-MEDICATION": 0.9820263029712616, "eval_recall_I-PROCEDURE": 0.8921166647300012, "eval_recall_I-SYMPTOM": 0.8629472786698877, "eval_recall_O": 0.933383339826895, "eval_recall_macro": 0.9034364462243489, "eval_recall_micro": 0.9147890467666947, "eval_roc_auc_B-DISEASE": 0.9273707339644259, "eval_roc_auc_B-MEDICATION": 0.9863367560238527, "eval_roc_auc_B-PROCEDURE": 0.9331648701325689, "eval_roc_auc_B-SYMPTOM": 0.9214945081048047, "eval_roc_auc_I-DISEASE": 0.9485185009603971, "eval_roc_auc_I-MEDICATION": 0.9906078445982319, "eval_roc_auc_I-PROCEDURE": 0.9410583684108798, "eval_roc_auc_I-SYMPTOM": 0.919745727558749, "eval_roc_auc_O": 0.9317071378601189, "eval_runtime": 38.4642, "eval_samples_per_second": 282.679, "eval_steps_per_second": 35.358, "step": 132355 }, { "epoch": 5.009557629103547, "grad_norm": 0.7259097099304199, "learning_rate": 4.992444561973481e-06, "loss": 0.0252, "step": 132608 }, { "epoch": 5.019228589777493, "grad_norm": 1.2974145412445068, "learning_rate": 4.982773601299536e-06, "loss": 0.0241, "step": 132864 }, { "epoch": 5.028899550451437, "grad_norm": 1.4934676885604858, "learning_rate": 4.973102640625591e-06, "loss": 0.0234, "step": 133120 }, { "epoch": 5.038570511125383, "grad_norm": 0.5889936089515686, "learning_rate": 4.963431679951646e-06, "loss": 0.0235, "step": 133376 }, { "epoch": 5.048241471799328, "grad_norm": 1.063180923461914, "learning_rate": 4.9537607192777e-06, "loss": 0.0237, "step": 133632 }, { "epoch": 5.057912432473272, "grad_norm": 0.9742263555526733, "learning_rate": 4.944089758603756e-06, "loss": 0.0246, "step": 133888 }, { "epoch": 5.067583393147218, "grad_norm": 0.6171449422836304, "learning_rate": 4.93441879792981e-06, "loss": 0.0238, "step": 134144 }, { "epoch": 5.0772543538211625, "grad_norm": 0.5888407230377197, "learning_rate": 4.924747837255865e-06, "loss": 0.0236, "step": 134400 }, { "epoch": 5.086925314495108, "grad_norm": 0.7588221430778503, "learning_rate": 4.91507687658192e-06, "loss": 0.0225, "step": 134656 }, { "epoch": 5.096596275169053, "grad_norm": 1.1143656969070435, "learning_rate": 4.905405915907975e-06, "loss": 0.0245, "step": 134912 }, { "epoch": 5.106267235842998, "grad_norm": 0.6728629469871521, "learning_rate": 4.89573495523403e-06, "loss": 0.0237, "step": 135168 }, { "epoch": 5.115938196516943, "grad_norm": 1.6702111959457397, "learning_rate": 4.8860639945600854e-06, "loss": 0.0235, "step": 135424 }, { "epoch": 5.125609157190888, "grad_norm": 0.5475626587867737, "learning_rate": 4.87639303388614e-06, "loss": 0.0232, "step": 135680 }, { "epoch": 5.135280117864833, "grad_norm": 1.3953115940093994, "learning_rate": 4.866722073212195e-06, "loss": 0.0237, "step": 135936 }, { "epoch": 5.144951078538778, "grad_norm": 0.8066737055778503, "learning_rate": 4.85705111253825e-06, "loss": 0.024, "step": 136192 }, { "epoch": 5.1546220392127235, "grad_norm": 0.8877065181732178, "learning_rate": 4.847380151864305e-06, "loss": 0.0239, "step": 136448 }, { "epoch": 5.164292999886668, "grad_norm": 1.0573451519012451, "learning_rate": 4.83770919119036e-06, "loss": 0.0232, "step": 136704 }, { "epoch": 5.173963960560614, "grad_norm": 1.0898510217666626, "learning_rate": 4.828038230516415e-06, "loss": 0.0236, "step": 136960 }, { "epoch": 5.1836349212345585, "grad_norm": 1.2083805799484253, "learning_rate": 4.818367269842469e-06, "loss": 0.0235, "step": 137216 }, { "epoch": 5.193305881908504, "grad_norm": 0.7825539112091064, "learning_rate": 4.808696309168524e-06, "loss": 0.0237, "step": 137472 }, { "epoch": 5.202976842582449, "grad_norm": 2.970543622970581, "learning_rate": 4.799025348494579e-06, "loss": 0.024, "step": 137728 }, { "epoch": 5.212647803256393, "grad_norm": 1.5980459451675415, "learning_rate": 4.789392165010766e-06, "loss": 0.0236, "step": 137984 }, { "epoch": 5.222318763930339, "grad_norm": 1.7351824045181274, "learning_rate": 4.779721204336822e-06, "loss": 0.0234, "step": 138240 }, { "epoch": 5.231989724604284, "grad_norm": 0.9596850872039795, "learning_rate": 4.7700502436628764e-06, "loss": 0.023, "step": 138496 }, { "epoch": 5.241660685278229, "grad_norm": 0.8805390000343323, "learning_rate": 4.7603792829889315e-06, "loss": 0.0239, "step": 138752 }, { "epoch": 5.251331645952174, "grad_norm": 1.6254891157150269, "learning_rate": 4.7507083223149866e-06, "loss": 0.023, "step": 139008 }, { "epoch": 5.2610026066261195, "grad_norm": 1.079866647720337, "learning_rate": 4.741037361641042e-06, "loss": 0.0232, "step": 139264 }, { "epoch": 5.270673567300064, "grad_norm": 0.6499260067939758, "learning_rate": 4.731366400967096e-06, "loss": 0.0228, "step": 139520 }, { "epoch": 5.280344527974009, "grad_norm": 2.5609185695648193, "learning_rate": 4.721695440293152e-06, "loss": 0.0236, "step": 139776 }, { "epoch": 5.2900154886479545, "grad_norm": 0.6212811470031738, "learning_rate": 4.712024479619206e-06, "loss": 0.023, "step": 140032 }, { "epoch": 5.299686449321899, "grad_norm": 0.8417946100234985, "learning_rate": 4.702353518945261e-06, "loss": 0.023, "step": 140288 }, { "epoch": 5.309357409995845, "grad_norm": 1.4460341930389404, "learning_rate": 4.692682558271316e-06, "loss": 0.0219, "step": 140544 }, { "epoch": 5.319028370669789, "grad_norm": 0.40644606947898865, "learning_rate": 4.683011597597371e-06, "loss": 0.0227, "step": 140800 }, { "epoch": 5.328699331343735, "grad_norm": 1.5526468753814697, "learning_rate": 4.673340636923425e-06, "loss": 0.0224, "step": 141056 }, { "epoch": 5.33837029201768, "grad_norm": 1.1209834814071655, "learning_rate": 4.663669676249481e-06, "loss": 0.0225, "step": 141312 }, { "epoch": 5.348041252691624, "grad_norm": 0.9618773460388184, "learning_rate": 4.6539987155755355e-06, "loss": 0.0233, "step": 141568 }, { "epoch": 5.35771221336557, "grad_norm": 1.260158896446228, "learning_rate": 4.644327754901591e-06, "loss": 0.0231, "step": 141824 }, { "epoch": 5.367383174039515, "grad_norm": 0.5958794355392456, "learning_rate": 4.6346945714177784e-06, "loss": 0.0229, "step": 142080 }, { "epoch": 5.37705413471346, "grad_norm": 0.6704425811767578, "learning_rate": 4.6250236107438335e-06, "loss": 0.022, "step": 142336 }, { "epoch": 5.386725095387405, "grad_norm": 2.0310544967651367, "learning_rate": 4.615352650069888e-06, "loss": 0.0234, "step": 142592 }, { "epoch": 5.39639605606135, "grad_norm": 0.5750619769096375, "learning_rate": 4.605681689395944e-06, "loss": 0.0231, "step": 142848 }, { "epoch": 5.406067016735295, "grad_norm": 1.2628861665725708, "learning_rate": 4.596010728721998e-06, "loss": 0.0227, "step": 143104 }, { "epoch": 5.415737977409241, "grad_norm": 0.6070398688316345, "learning_rate": 4.586339768048053e-06, "loss": 0.0229, "step": 143360 }, { "epoch": 5.425408938083185, "grad_norm": 0.769862711429596, "learning_rate": 4.576668807374108e-06, "loss": 0.0221, "step": 143616 }, { "epoch": 5.43507989875713, "grad_norm": 0.44296690821647644, "learning_rate": 4.566997846700163e-06, "loss": 0.0227, "step": 143872 }, { "epoch": 5.444750859431076, "grad_norm": 2.5941524505615234, "learning_rate": 4.55736466321635e-06, "loss": 0.0229, "step": 144128 }, { "epoch": 5.45442182010502, "grad_norm": 0.6940840482711792, "learning_rate": 4.547693702542405e-06, "loss": 0.0228, "step": 144384 }, { "epoch": 5.464092780778966, "grad_norm": 0.8339863419532776, "learning_rate": 4.53802274186846e-06, "loss": 0.0221, "step": 144640 }, { "epoch": 5.473763741452911, "grad_norm": 0.7753921747207642, "learning_rate": 4.528351781194515e-06, "loss": 0.0219, "step": 144896 }, { "epoch": 5.483434702126856, "grad_norm": 0.7037907242774963, "learning_rate": 4.51868082052057e-06, "loss": 0.0226, "step": 145152 }, { "epoch": 5.493105662800801, "grad_norm": 0.8467398285865784, "learning_rate": 4.5090098598466245e-06, "loss": 0.022, "step": 145408 }, { "epoch": 5.502776623474746, "grad_norm": 0.4071617126464844, "learning_rate": 4.4993388991726796e-06, "loss": 0.0225, "step": 145664 }, { "epoch": 5.512447584148691, "grad_norm": 0.9832024574279785, "learning_rate": 4.489667938498735e-06, "loss": 0.0223, "step": 145920 }, { "epoch": 5.522118544822636, "grad_norm": 1.3408091068267822, "learning_rate": 4.47999697782479e-06, "loss": 0.0215, "step": 146176 }, { "epoch": 5.531789505496581, "grad_norm": 1.1191693544387817, "learning_rate": 4.470326017150845e-06, "loss": 0.0222, "step": 146432 }, { "epoch": 5.541460466170526, "grad_norm": 0.7799406051635742, "learning_rate": 4.4606550564769e-06, "loss": 0.022, "step": 146688 }, { "epoch": 5.551131426844472, "grad_norm": 0.7386727333068848, "learning_rate": 4.450984095802954e-06, "loss": 0.0222, "step": 146944 }, { "epoch": 5.560802387518416, "grad_norm": 0.6070919632911682, "learning_rate": 4.44131313512901e-06, "loss": 0.0227, "step": 147200 }, { "epoch": 5.570473348192362, "grad_norm": 0.9108920693397522, "learning_rate": 4.431642174455064e-06, "loss": 0.0218, "step": 147456 }, { "epoch": 5.5801443088663065, "grad_norm": 1.1719551086425781, "learning_rate": 4.421971213781119e-06, "loss": 0.0212, "step": 147712 }, { "epoch": 5.589815269540251, "grad_norm": 0.965921938419342, "learning_rate": 4.412300253107174e-06, "loss": 0.0218, "step": 147968 }, { "epoch": 5.599486230214197, "grad_norm": 0.8204768896102905, "learning_rate": 4.402667069623362e-06, "loss": 0.0221, "step": 148224 }, { "epoch": 5.6091571908881415, "grad_norm": 1.483976125717163, "learning_rate": 4.393033886139549e-06, "loss": 0.0213, "step": 148480 }, { "epoch": 5.618828151562087, "grad_norm": 1.0646507740020752, "learning_rate": 4.383362925465604e-06, "loss": 0.0222, "step": 148736 }, { "epoch": 5.628499112236032, "grad_norm": 1.0907351970672607, "learning_rate": 4.373691964791659e-06, "loss": 0.0207, "step": 148992 }, { "epoch": 5.638170072909977, "grad_norm": 3.157839775085449, "learning_rate": 4.364021004117714e-06, "loss": 0.0217, "step": 149248 }, { "epoch": 5.647841033583922, "grad_norm": 0.9379634857177734, "learning_rate": 4.354350043443769e-06, "loss": 0.0215, "step": 149504 }, { "epoch": 5.657511994257867, "grad_norm": 1.2948676347732544, "learning_rate": 4.344679082769824e-06, "loss": 0.0213, "step": 149760 }, { "epoch": 5.667182954931812, "grad_norm": 1.2549010515213013, "learning_rate": 4.335008122095879e-06, "loss": 0.0209, "step": 150016 }, { "epoch": 5.676853915605757, "grad_norm": 1.946027398109436, "learning_rate": 4.325337161421934e-06, "loss": 0.0216, "step": 150272 }, { "epoch": 5.6865248762797025, "grad_norm": 1.1487503051757812, "learning_rate": 4.315666200747989e-06, "loss": 0.021, "step": 150528 }, { "epoch": 5.696195836953647, "grad_norm": 1.934919834136963, "learning_rate": 4.306033017264177e-06, "loss": 0.0213, "step": 150784 }, { "epoch": 5.705866797627593, "grad_norm": 1.0932055711746216, "learning_rate": 4.296362056590232e-06, "loss": 0.0219, "step": 151040 }, { "epoch": 5.715537758301537, "grad_norm": 1.896328091621399, "learning_rate": 4.286691095916286e-06, "loss": 0.0214, "step": 151296 }, { "epoch": 5.725208718975482, "grad_norm": 0.4600565433502197, "learning_rate": 4.277020135242341e-06, "loss": 0.0211, "step": 151552 }, { "epoch": 5.734879679649428, "grad_norm": 1.0107779502868652, "learning_rate": 4.267349174568396e-06, "loss": 0.0211, "step": 151808 }, { "epoch": 5.744550640323372, "grad_norm": 1.8353612422943115, "learning_rate": 4.257678213894451e-06, "loss": 0.0211, "step": 152064 }, { "epoch": 5.754221600997318, "grad_norm": 0.6806939244270325, "learning_rate": 4.248007253220506e-06, "loss": 0.0212, "step": 152320 }, { "epoch": 5.763892561671263, "grad_norm": 0.6145659685134888, "learning_rate": 4.238336292546561e-06, "loss": 0.021, "step": 152576 }, { "epoch": 5.773563522345208, "grad_norm": 1.3267852067947388, "learning_rate": 4.2286653318726154e-06, "loss": 0.0217, "step": 152832 }, { "epoch": 5.783234483019153, "grad_norm": 0.6466089487075806, "learning_rate": 4.2189943711986705e-06, "loss": 0.0214, "step": 153088 }, { "epoch": 5.7929054436930985, "grad_norm": 1.5534400939941406, "learning_rate": 4.2093234105247256e-06, "loss": 0.0202, "step": 153344 }, { "epoch": 5.802576404367043, "grad_norm": 1.3532108068466187, "learning_rate": 4.199652449850781e-06, "loss": 0.0205, "step": 153600 }, { "epoch": 5.812247365040989, "grad_norm": 0.8023514151573181, "learning_rate": 4.189981489176836e-06, "loss": 0.0207, "step": 153856 }, { "epoch": 5.821918325714933, "grad_norm": 0.5584861636161804, "learning_rate": 4.180348305693023e-06, "loss": 0.0205, "step": 154112 }, { "epoch": 5.831589286388878, "grad_norm": 0.5633936524391174, "learning_rate": 4.170677345019078e-06, "loss": 0.021, "step": 154368 }, { "epoch": 5.841260247062824, "grad_norm": 0.7239835262298584, "learning_rate": 4.161006384345133e-06, "loss": 0.0208, "step": 154624 }, { "epoch": 5.850931207736768, "grad_norm": 2.3800885677337646, "learning_rate": 4.151335423671188e-06, "loss": 0.0205, "step": 154880 }, { "epoch": 5.860602168410714, "grad_norm": 2.1673309803009033, "learning_rate": 4.141664462997242e-06, "loss": 0.0213, "step": 155136 }, { "epoch": 5.870273129084659, "grad_norm": 1.1194077730178833, "learning_rate": 4.131993502323298e-06, "loss": 0.0204, "step": 155392 }, { "epoch": 5.879944089758604, "grad_norm": 1.4655418395996094, "learning_rate": 4.122322541649352e-06, "loss": 0.0209, "step": 155648 }, { "epoch": 5.889615050432549, "grad_norm": 1.1395246982574463, "learning_rate": 4.112651580975407e-06, "loss": 0.0205, "step": 155904 }, { "epoch": 5.8992860111064935, "grad_norm": 1.106829047203064, "learning_rate": 4.102980620301462e-06, "loss": 0.0207, "step": 156160 }, { "epoch": 5.908956971780439, "grad_norm": 0.6761823892593384, "learning_rate": 4.093347436817649e-06, "loss": 0.0216, "step": 156416 }, { "epoch": 5.918627932454384, "grad_norm": 0.8383803963661194, "learning_rate": 4.083676476143704e-06, "loss": 0.0205, "step": 156672 }, { "epoch": 5.928298893128329, "grad_norm": 0.9389529824256897, "learning_rate": 4.0740055154697595e-06, "loss": 0.0202, "step": 156928 }, { "epoch": 5.937969853802274, "grad_norm": 0.532670795917511, "learning_rate": 4.0643345547958145e-06, "loss": 0.0202, "step": 157184 }, { "epoch": 5.94764081447622, "grad_norm": 1.710627794265747, "learning_rate": 4.05466359412187e-06, "loss": 0.0206, "step": 157440 }, { "epoch": 5.957311775150164, "grad_norm": 0.8534083962440491, "learning_rate": 4.044992633447925e-06, "loss": 0.0205, "step": 157696 }, { "epoch": 5.966982735824109, "grad_norm": 0.8284239768981934, "learning_rate": 4.035321672773979e-06, "loss": 0.0196, "step": 157952 }, { "epoch": 5.976653696498055, "grad_norm": 1.6392523050308228, "learning_rate": 4.025650712100034e-06, "loss": 0.0195, "step": 158208 }, { "epoch": 5.986324657171999, "grad_norm": 1.2992466688156128, "learning_rate": 4.015979751426089e-06, "loss": 0.0201, "step": 158464 }, { "epoch": 5.995995617845945, "grad_norm": 2.7163853645324707, "learning_rate": 4.006308790752144e-06, "loss": 0.0201, "step": 158720 }, { "epoch": 6.0, "eval_f1_B-DISEASE": 0.8635271504084575, "eval_f1_B-MEDICATION": 0.9668309185849819, "eval_f1_B-PROCEDURE": 0.8783394909306945, "eval_f1_B-SYMPTOM": 0.854456093367215, "eval_f1_I-DISEASE": 0.8961992432371378, "eval_f1_I-MEDICATION": 0.9716007714561234, "eval_f1_I-PROCEDURE": 0.8945448474477232, "eval_f1_I-SYMPTOM": 0.8595216795570101, "eval_f1_O": 0.9448674877090889, "eval_f1_macro": 0.9033208536331592, "eval_f1_micro": 0.9195041254593926, "eval_loss": 0.0639418289065361, "eval_precision_B-DISEASE": 0.8609561616645564, "eval_precision_B-MEDICATION": 0.961386573058359, "eval_precision_B-PROCEDURE": 0.8867188964276342, "eval_precision_B-SYMPTOM": 0.8635091496232508, "eval_precision_I-DISEASE": 0.879380091249977, "eval_precision_I-MEDICATION": 0.9618615751789976, "eval_precision_I-PROCEDURE": 0.8997044698928703, "eval_precision_I-SYMPTOM": 0.8561623362340746, "eval_precision_O": 0.9505469803686498, "eval_precision_macro": 0.9022473592998188, "eval_precision_micro": 0.9208961541562525, "eval_rauc_macro": 0.9450339030702332, "eval_rauc_micro": 0.9540298137028659, "eval_recall_B-DISEASE": 0.8661135401246256, "eval_recall_B-MEDICATION": 0.9723372781065088, "eval_recall_B-PROCEDURE": 0.8701169719708673, "eval_recall_B-SYMPTOM": 0.8455908926635345, "eval_recall_I-DISEASE": 0.9136743114864216, "eval_recall_I-MEDICATION": 0.9815392109108622, "eval_recall_I-PROCEDURE": 0.8894440663335602, "eval_recall_I-SYMPTOM": 0.8629074889867842, "eval_recall_O": 0.9392554615708594, "eval_recall_macro": 0.9045532469060027, "eval_recall_micro": 0.9181162987981415, "eval_roc_auc_B-DISEASE": 0.9315405487708789, "eval_roc_auc_B-MEDICATION": 0.9860717320744103, "eval_roc_auc_B-PROCEDURE": 0.9339323069818524, "eval_roc_auc_B-SYMPTOM": 0.9211341289722362, "eval_roc_auc_I-DISEASE": 0.948759311550352, "eval_roc_auc_I-MEDICATION": 0.9904733198167928, "eval_roc_auc_I-PROCEDURE": 0.9399375434682918, "eval_roc_auc_I-SYMPTOM": 0.9207644205730121, "eval_roc_auc_O": 0.9326918154242724, "eval_runtime": 38.6067, "eval_samples_per_second": 281.635, "eval_steps_per_second": 35.227, "step": 158826 }, { "epoch": 6.0056665785198895, "grad_norm": 0.9516779184341431, "learning_rate": 3.996637830078199e-06, "loss": 0.0184, "step": 158976 }, { "epoch": 6.015337539193835, "grad_norm": 1.6006931066513062, "learning_rate": 3.986966869404254e-06, "loss": 0.0173, "step": 159232 }, { "epoch": 6.02500849986778, "grad_norm": 1.685799241065979, "learning_rate": 3.977295908730309e-06, "loss": 0.0173, "step": 159488 }, { "epoch": 6.034679460541725, "grad_norm": 0.874465823173523, "learning_rate": 3.967662725246496e-06, "loss": 0.0183, "step": 159744 }, { "epoch": 6.04435042121567, "grad_norm": 0.6346389055252075, "learning_rate": 3.957991764572551e-06, "loss": 0.0184, "step": 160000 }, { "epoch": 6.054021381889615, "grad_norm": 1.1518771648406982, "learning_rate": 3.948320803898606e-06, "loss": 0.0176, "step": 160256 }, { "epoch": 6.06369234256356, "grad_norm": 0.521160364151001, "learning_rate": 3.9386498432246614e-06, "loss": 0.0177, "step": 160512 }, { "epoch": 6.073363303237505, "grad_norm": 0.6918174028396606, "learning_rate": 3.9289788825507165e-06, "loss": 0.0179, "step": 160768 }, { "epoch": 6.0830342639114505, "grad_norm": 0.6411401629447937, "learning_rate": 3.919307921876771e-06, "loss": 0.0176, "step": 161024 }, { "epoch": 6.092705224585395, "grad_norm": 0.49361225962638855, "learning_rate": 3.909636961202826e-06, "loss": 0.0176, "step": 161280 }, { "epoch": 6.102376185259341, "grad_norm": 0.7907077670097351, "learning_rate": 3.899966000528881e-06, "loss": 0.0179, "step": 161536 }, { "epoch": 6.1120471459332855, "grad_norm": 0.9638190865516663, "learning_rate": 3.890295039854936e-06, "loss": 0.0179, "step": 161792 }, { "epoch": 6.12171810660723, "grad_norm": 0.6037548780441284, "learning_rate": 3.880624079180991e-06, "loss": 0.0176, "step": 162048 }, { "epoch": 6.131389067281176, "grad_norm": 0.7704125046730042, "learning_rate": 3.870953118507046e-06, "loss": 0.0173, "step": 162304 }, { "epoch": 6.14106002795512, "grad_norm": 0.8190270662307739, "learning_rate": 3.8612821578331e-06, "loss": 0.0175, "step": 162560 }, { "epoch": 6.150730988629066, "grad_norm": 1.1010074615478516, "learning_rate": 3.851611197159156e-06, "loss": 0.0172, "step": 162816 }, { "epoch": 6.160401949303011, "grad_norm": 1.1795998811721802, "learning_rate": 3.841978013675343e-06, "loss": 0.0178, "step": 163072 }, { "epoch": 6.170072909976956, "grad_norm": 1.3430454730987549, "learning_rate": 3.832307053001398e-06, "loss": 0.0167, "step": 163328 }, { "epoch": 6.179743870650901, "grad_norm": 1.2660478353500366, "learning_rate": 3.822636092327453e-06, "loss": 0.0174, "step": 163584 }, { "epoch": 6.1894148313248465, "grad_norm": 0.4003163278102875, "learning_rate": 3.8129651316535075e-06, "loss": 0.0173, "step": 163840 }, { "epoch": 6.199085791998791, "grad_norm": 0.43318817019462585, "learning_rate": 3.803294170979563e-06, "loss": 0.0178, "step": 164096 }, { "epoch": 6.208756752672736, "grad_norm": 1.2851486206054688, "learning_rate": 3.7936232103056176e-06, "loss": 0.0169, "step": 164352 }, { "epoch": 6.218427713346681, "grad_norm": 0.5519583821296692, "learning_rate": 3.7839522496316727e-06, "loss": 0.0176, "step": 164608 }, { "epoch": 6.228098674020626, "grad_norm": 1.4025540351867676, "learning_rate": 3.7742812889577273e-06, "loss": 0.0169, "step": 164864 }, { "epoch": 6.237769634694572, "grad_norm": 1.2124977111816406, "learning_rate": 3.764648105473915e-06, "loss": 0.0172, "step": 165120 }, { "epoch": 6.247440595368516, "grad_norm": 0.7466005682945251, "learning_rate": 3.75497714479997e-06, "loss": 0.0168, "step": 165376 }, { "epoch": 6.257111556042462, "grad_norm": 0.387214720249176, "learning_rate": 3.7453061841260253e-06, "loss": 0.0171, "step": 165632 }, { "epoch": 6.266782516716407, "grad_norm": 1.151214599609375, "learning_rate": 3.73563522345208e-06, "loss": 0.0168, "step": 165888 }, { "epoch": 6.276453477390351, "grad_norm": 0.6176560521125793, "learning_rate": 3.725964262778135e-06, "loss": 0.0167, "step": 166144 }, { "epoch": 6.286124438064297, "grad_norm": 1.3864374160766602, "learning_rate": 3.7162933021041897e-06, "loss": 0.0167, "step": 166400 }, { "epoch": 6.295795398738242, "grad_norm": 0.7332329750061035, "learning_rate": 3.7066223414302447e-06, "loss": 0.0165, "step": 166656 }, { "epoch": 6.305466359412187, "grad_norm": 0.6729167103767395, "learning_rate": 3.6969513807562994e-06, "loss": 0.0178, "step": 166912 }, { "epoch": 6.315137320086132, "grad_norm": 0.9473170638084412, "learning_rate": 3.687280420082355e-06, "loss": 0.0164, "step": 167168 }, { "epoch": 6.324808280760077, "grad_norm": 1.1327837705612183, "learning_rate": 3.6776094594084095e-06, "loss": 0.0172, "step": 167424 }, { "epoch": 6.334479241434022, "grad_norm": 3.3836171627044678, "learning_rate": 3.6679384987344646e-06, "loss": 0.0167, "step": 167680 }, { "epoch": 6.344150202107967, "grad_norm": 0.9129564166069031, "learning_rate": 3.658267538060519e-06, "loss": 0.0171, "step": 167936 }, { "epoch": 6.353821162781912, "grad_norm": 0.7095524668693542, "learning_rate": 3.6485965773865743e-06, "loss": 0.0173, "step": 168192 }, { "epoch": 6.363492123455857, "grad_norm": 0.6879532933235168, "learning_rate": 3.6389633939027617e-06, "loss": 0.0171, "step": 168448 }, { "epoch": 6.373163084129803, "grad_norm": 1.009499192237854, "learning_rate": 3.6292924332288163e-06, "loss": 0.0174, "step": 168704 }, { "epoch": 6.382834044803747, "grad_norm": 2.211432695388794, "learning_rate": 3.619621472554872e-06, "loss": 0.0166, "step": 168960 }, { "epoch": 6.392505005477693, "grad_norm": 0.8503689765930176, "learning_rate": 3.6099505118809264e-06, "loss": 0.0174, "step": 169216 }, { "epoch": 6.4021759661516375, "grad_norm": 1.5202765464782715, "learning_rate": 3.6002795512069815e-06, "loss": 0.0171, "step": 169472 }, { "epoch": 6.411846926825583, "grad_norm": 1.088889479637146, "learning_rate": 3.590608590533036e-06, "loss": 0.0166, "step": 169728 }, { "epoch": 6.421517887499528, "grad_norm": 0.6144846081733704, "learning_rate": 3.5809376298590916e-06, "loss": 0.0164, "step": 169984 }, { "epoch": 6.4311888481734725, "grad_norm": 1.1575945615768433, "learning_rate": 3.5712666691851463e-06, "loss": 0.0171, "step": 170240 }, { "epoch": 6.440859808847418, "grad_norm": 0.7061285376548767, "learning_rate": 3.5615957085112013e-06, "loss": 0.0163, "step": 170496 }, { "epoch": 6.450530769521363, "grad_norm": 0.8547090291976929, "learning_rate": 3.551924747837256e-06, "loss": 0.0167, "step": 170752 }, { "epoch": 6.460201730195308, "grad_norm": 1.7807695865631104, "learning_rate": 3.542253787163311e-06, "loss": 0.0166, "step": 171008 }, { "epoch": 6.469872690869253, "grad_norm": 0.8691855669021606, "learning_rate": 3.5325828264893657e-06, "loss": 0.0163, "step": 171264 }, { "epoch": 6.479543651543199, "grad_norm": 0.6221545934677124, "learning_rate": 3.522911865815421e-06, "loss": 0.0169, "step": 171520 }, { "epoch": 6.489214612217143, "grad_norm": 0.9039457440376282, "learning_rate": 3.513240905141476e-06, "loss": 0.0165, "step": 171776 }, { "epoch": 6.498885572891089, "grad_norm": 0.4935069978237152, "learning_rate": 3.503569944467531e-06, "loss": 0.0166, "step": 172032 }, { "epoch": 6.5085565335650335, "grad_norm": 1.0860068798065186, "learning_rate": 3.4938989837935855e-06, "loss": 0.0167, "step": 172288 }, { "epoch": 6.518227494238978, "grad_norm": 0.5234951972961426, "learning_rate": 3.4842280231196406e-06, "loss": 0.0162, "step": 172544 }, { "epoch": 6.527898454912924, "grad_norm": 0.9759318232536316, "learning_rate": 3.474594839635828e-06, "loss": 0.0164, "step": 172800 }, { "epoch": 6.537569415586868, "grad_norm": 1.109062671661377, "learning_rate": 3.4649238789618835e-06, "loss": 0.0166, "step": 173056 }, { "epoch": 6.547240376260814, "grad_norm": 0.7958534359931946, "learning_rate": 3.455252918287938e-06, "loss": 0.0161, "step": 173312 }, { "epoch": 6.556911336934759, "grad_norm": 0.6285087466239929, "learning_rate": 3.445581957613993e-06, "loss": 0.0167, "step": 173568 }, { "epoch": 6.566582297608704, "grad_norm": 1.0555269718170166, "learning_rate": 3.4359487741301806e-06, "loss": 0.0159, "step": 173824 }, { "epoch": 6.576253258282649, "grad_norm": 0.706255316734314, "learning_rate": 3.4262778134562352e-06, "loss": 0.0159, "step": 174080 }, { "epoch": 6.585924218956594, "grad_norm": 0.4856029152870178, "learning_rate": 3.4166068527822903e-06, "loss": 0.0161, "step": 174336 }, { "epoch": 6.595595179630539, "grad_norm": 0.7811611890792847, "learning_rate": 3.406935892108345e-06, "loss": 0.016, "step": 174592 }, { "epoch": 6.605266140304484, "grad_norm": 0.6881721615791321, "learning_rate": 3.3972649314344004e-06, "loss": 0.0162, "step": 174848 }, { "epoch": 6.6149371009784295, "grad_norm": 0.8269228935241699, "learning_rate": 3.387593970760455e-06, "loss": 0.0166, "step": 175104 }, { "epoch": 6.624608061652374, "grad_norm": 0.8271245360374451, "learning_rate": 3.37792301008651e-06, "loss": 0.0165, "step": 175360 }, { "epoch": 6.63427902232632, "grad_norm": 0.6497036218643188, "learning_rate": 3.3682520494125648e-06, "loss": 0.0163, "step": 175616 }, { "epoch": 6.643949983000264, "grad_norm": 2.562542676925659, "learning_rate": 3.35858108873862e-06, "loss": 0.0159, "step": 175872 }, { "epoch": 6.653620943674209, "grad_norm": 0.9905675649642944, "learning_rate": 3.3489101280646745e-06, "loss": 0.0156, "step": 176128 }, { "epoch": 6.663291904348155, "grad_norm": 0.8474075794219971, "learning_rate": 3.33923916739073e-06, "loss": 0.0164, "step": 176384 }, { "epoch": 6.672962865022099, "grad_norm": 1.0555962324142456, "learning_rate": 3.3295682067167846e-06, "loss": 0.0161, "step": 176640 }, { "epoch": 6.682633825696045, "grad_norm": 1.2208625078201294, "learning_rate": 3.3198972460428397e-06, "loss": 0.0151, "step": 176896 }, { "epoch": 6.69230478636999, "grad_norm": 0.8965372443199158, "learning_rate": 3.3102262853688943e-06, "loss": 0.0151, "step": 177152 }, { "epoch": 6.701975747043935, "grad_norm": 0.9162973165512085, "learning_rate": 3.3005553246949494e-06, "loss": 0.0162, "step": 177408 }, { "epoch": 6.71164670771788, "grad_norm": 0.629772961139679, "learning_rate": 3.290884364021004e-06, "loss": 0.0165, "step": 177664 }, { "epoch": 6.7213176683918245, "grad_norm": 0.9662770628929138, "learning_rate": 3.2812511805371923e-06, "loss": 0.0159, "step": 177920 }, { "epoch": 6.73098862906577, "grad_norm": 0.4742802679538727, "learning_rate": 3.271580219863247e-06, "loss": 0.0157, "step": 178176 }, { "epoch": 6.740659589739715, "grad_norm": 0.8070750832557678, "learning_rate": 3.261909259189302e-06, "loss": 0.0159, "step": 178432 }, { "epoch": 6.75033055041366, "grad_norm": 0.49841606616973877, "learning_rate": 3.2522382985153566e-06, "loss": 0.0158, "step": 178688 }, { "epoch": 6.760001511087605, "grad_norm": 0.8847957849502563, "learning_rate": 3.2425673378414117e-06, "loss": 0.0153, "step": 178944 }, { "epoch": 6.769672471761551, "grad_norm": 0.7336966395378113, "learning_rate": 3.2328963771674663e-06, "loss": 0.0149, "step": 179200 }, { "epoch": 6.779343432435495, "grad_norm": 1.584037184715271, "learning_rate": 3.223225416493522e-06, "loss": 0.0153, "step": 179456 }, { "epoch": 6.789014393109441, "grad_norm": 0.7785377502441406, "learning_rate": 3.2135544558195765e-06, "loss": 0.0158, "step": 179712 }, { "epoch": 6.798685353783386, "grad_norm": 0.7900734543800354, "learning_rate": 3.2038834951456315e-06, "loss": 0.015, "step": 179968 }, { "epoch": 6.808356314457331, "grad_norm": 1.014478087425232, "learning_rate": 3.194250311661819e-06, "loss": 0.0164, "step": 180224 }, { "epoch": 6.818027275131276, "grad_norm": 0.719078004360199, "learning_rate": 3.1845793509878736e-06, "loss": 0.0152, "step": 180480 }, { "epoch": 6.8276982358052205, "grad_norm": 0.8632174134254456, "learning_rate": 3.1749083903139286e-06, "loss": 0.0154, "step": 180736 }, { "epoch": 6.837369196479166, "grad_norm": 1.7675926685333252, "learning_rate": 3.1652374296399833e-06, "loss": 0.0153, "step": 180992 }, { "epoch": 6.847040157153111, "grad_norm": 0.7516529560089111, "learning_rate": 3.1555664689660388e-06, "loss": 0.0154, "step": 181248 }, { "epoch": 6.856711117827056, "grad_norm": 0.567512035369873, "learning_rate": 3.1458955082920934e-06, "loss": 0.0156, "step": 181504 }, { "epoch": 6.866382078501001, "grad_norm": 0.990955650806427, "learning_rate": 3.1362245476181485e-06, "loss": 0.0153, "step": 181760 }, { "epoch": 6.876053039174947, "grad_norm": 0.30770573019981384, "learning_rate": 3.126553586944203e-06, "loss": 0.0146, "step": 182016 }, { "epoch": 6.885723999848891, "grad_norm": 1.2275207042694092, "learning_rate": 3.116882626270258e-06, "loss": 0.015, "step": 182272 }, { "epoch": 6.895394960522836, "grad_norm": 1.2327375411987305, "learning_rate": 3.1072494427864456e-06, "loss": 0.0147, "step": 182528 }, { "epoch": 6.9050659211967815, "grad_norm": 0.5120306611061096, "learning_rate": 3.0975784821125002e-06, "loss": 0.0151, "step": 182784 }, { "epoch": 6.914736881870726, "grad_norm": 0.8106947541236877, "learning_rate": 3.0879075214385557e-06, "loss": 0.0153, "step": 183040 }, { "epoch": 6.924407842544672, "grad_norm": 1.0325617790222168, "learning_rate": 3.0782365607646104e-06, "loss": 0.0158, "step": 183296 }, { "epoch": 6.9340788032186165, "grad_norm": 1.0854499340057373, "learning_rate": 3.0685656000906654e-06, "loss": 0.0153, "step": 183552 }, { "epoch": 6.943749763892562, "grad_norm": 0.5279197692871094, "learning_rate": 3.05889463941672e-06, "loss": 0.0151, "step": 183808 }, { "epoch": 6.953420724566507, "grad_norm": 0.7425877451896667, "learning_rate": 3.0492236787427756e-06, "loss": 0.0146, "step": 184064 }, { "epoch": 6.963091685240451, "grad_norm": 1.2882142066955566, "learning_rate": 3.0395527180688306e-06, "loss": 0.0146, "step": 184320 }, { "epoch": 6.972762645914397, "grad_norm": 1.135740041732788, "learning_rate": 3.029919534585018e-06, "loss": 0.0152, "step": 184576 }, { "epoch": 6.982433606588342, "grad_norm": 1.425507664680481, "learning_rate": 3.0202485739110727e-06, "loss": 0.0151, "step": 184832 }, { "epoch": 6.992104567262287, "grad_norm": 1.9582375288009644, "learning_rate": 3.0105776132371277e-06, "loss": 0.0145, "step": 185088 }, { "epoch": 7.0, "eval_f1_B-DISEASE": 0.8683835766861692, "eval_f1_B-MEDICATION": 0.9647612741852424, "eval_f1_B-PROCEDURE": 0.8810707316175117, "eval_f1_B-SYMPTOM": 0.8611881039778261, "eval_f1_I-DISEASE": 0.9006904513324859, "eval_f1_I-MEDICATION": 0.9684884651772069, "eval_f1_I-PROCEDURE": 0.8967690833917367, "eval_f1_I-SYMPTOM": 0.8655111983162697, "eval_f1_O": 0.9463754094618816, "eval_f1_macro": 0.9059153660162589, "eval_f1_micro": 0.9219545202806908, "eval_loss": 0.0723479613661766, "eval_precision_B-DISEASE": 0.8655766862771925, "eval_precision_B-MEDICATION": 0.9596077857456461, "eval_precision_B-PROCEDURE": 0.8819475158484447, "eval_precision_B-SYMPTOM": 0.8568617512894666, "eval_precision_I-DISEASE": 0.8883365272143551, "eval_precision_I-MEDICATION": 0.964674044362828, "eval_precision_I-PROCEDURE": 0.8961187498446008, "eval_precision_I-SYMPTOM": 0.8514066383652641, "eval_precision_O": 0.9543346366122647, "eval_precision_macro": 0.9020960372844513, "eval_precision_micro": 0.9227532330840041, "eval_rauc_macro": 0.9479819415861408, "eval_rauc_micro": 0.9556619578922063, "eval_recall_B-DISEASE": 0.8712087306778669, "eval_recall_B-MEDICATION": 0.9699704142011835, "eval_recall_B-PROCEDURE": 0.8801956889575517, "eval_recall_B-SYMPTOM": 0.865558366461872, "eval_recall_I-DISEASE": 0.9133928285833094, "eval_recall_I-MEDICATION": 0.9723331709693132, "eval_recall_I-PROCEDURE": 0.897420361547783, "eval_recall_I-SYMPTOM": 0.880090947847094, "eval_recall_O": 0.9385478454119649, "eval_recall_macro": 0.9098575949619931, "eval_recall_micro": 0.9211571889744227, "eval_roc_auc_B-DISEASE": 0.9341377766912998, "eval_roc_auc_B-MEDICATION": 0.9848838952590729, "eval_roc_auc_B-PROCEDURE": 0.9389042139862309, "eval_roc_auc_B-SYMPTOM": 0.9309819807426285, "eval_roc_auc_I-DISEASE": 0.9492960534070586, "eval_roc_auc_I-MEDICATION": 0.9858955156450513, "eval_roc_auc_I-PROCEDURE": 0.9436901913313291, "eval_roc_auc_I-SYMPTOM": 0.928719920638709, "eval_roc_auc_O": 0.9353279265738865, "eval_runtime": 38.2553, "eval_samples_per_second": 284.222, "eval_steps_per_second": 35.551, "step": 185297 }, { "epoch": 7.001775527936232, "grad_norm": 0.4037480056285858, "learning_rate": 3.0009066525631824e-06, "loss": 0.0142, "step": 185344 }, { "epoch": 7.0114464886101775, "grad_norm": 0.5653617978096008, "learning_rate": 2.991235691889238e-06, "loss": 0.0131, "step": 185600 }, { "epoch": 7.021117449284122, "grad_norm": 1.6284412145614624, "learning_rate": 2.9815647312152925e-06, "loss": 0.0134, "step": 185856 }, { "epoch": 7.030788409958068, "grad_norm": 1.3709075450897217, "learning_rate": 2.9718937705413476e-06, "loss": 0.0133, "step": 186112 }, { "epoch": 7.040459370632012, "grad_norm": 0.4692825973033905, "learning_rate": 2.962260587057535e-06, "loss": 0.0135, "step": 186368 }, { "epoch": 7.050130331305957, "grad_norm": 0.7211587429046631, "learning_rate": 2.9525896263835896e-06, "loss": 0.0127, "step": 186624 }, { "epoch": 7.059801291979903, "grad_norm": 0.8826980590820312, "learning_rate": 2.9429186657096447e-06, "loss": 0.013, "step": 186880 }, { "epoch": 7.069472252653847, "grad_norm": 1.0008989572525024, "learning_rate": 2.9332477050356993e-06, "loss": 0.0128, "step": 187136 }, { "epoch": 7.079143213327793, "grad_norm": 0.883436381816864, "learning_rate": 2.923576744361755e-06, "loss": 0.0132, "step": 187392 }, { "epoch": 7.088814174001738, "grad_norm": 0.7375462055206299, "learning_rate": 2.9139057836878095e-06, "loss": 0.0134, "step": 187648 }, { "epoch": 7.098485134675683, "grad_norm": 0.7351277470588684, "learning_rate": 2.9042348230138645e-06, "loss": 0.0129, "step": 187904 }, { "epoch": 7.108156095349628, "grad_norm": 0.92567378282547, "learning_rate": 2.894563862339919e-06, "loss": 0.013, "step": 188160 }, { "epoch": 7.117827056023573, "grad_norm": 0.7460564374923706, "learning_rate": 2.8848929016659742e-06, "loss": 0.013, "step": 188416 }, { "epoch": 7.127498016697518, "grad_norm": 0.4165281355381012, "learning_rate": 2.875221940992029e-06, "loss": 0.0127, "step": 188672 }, { "epoch": 7.137168977371463, "grad_norm": 0.5380236506462097, "learning_rate": 2.8655509803180844e-06, "loss": 0.0129, "step": 188928 }, { "epoch": 7.146839938045408, "grad_norm": 0.8997848629951477, "learning_rate": 2.855880019644139e-06, "loss": 0.013, "step": 189184 }, { "epoch": 7.156510898719353, "grad_norm": 0.7361161112785339, "learning_rate": 2.846209058970194e-06, "loss": 0.013, "step": 189440 }, { "epoch": 7.166181859393299, "grad_norm": 0.9856345057487488, "learning_rate": 2.8365380982962487e-06, "loss": 0.0124, "step": 189696 }, { "epoch": 7.175852820067243, "grad_norm": 0.4223635196685791, "learning_rate": 2.8268671376223038e-06, "loss": 0.0125, "step": 189952 }, { "epoch": 7.185523780741189, "grad_norm": 0.8026881814002991, "learning_rate": 2.8171961769483584e-06, "loss": 0.0129, "step": 190208 }, { "epoch": 7.195194741415134, "grad_norm": 0.5311381220817566, "learning_rate": 2.8075629934645467e-06, "loss": 0.0134, "step": 190464 }, { "epoch": 7.204865702089078, "grad_norm": 1.399657964706421, "learning_rate": 2.7978920327906013e-06, "loss": 0.0135, "step": 190720 }, { "epoch": 7.214536662763024, "grad_norm": 1.193272590637207, "learning_rate": 2.7882210721166564e-06, "loss": 0.0131, "step": 190976 }, { "epoch": 7.2242076234369685, "grad_norm": 0.6488497257232666, "learning_rate": 2.778550111442711e-06, "loss": 0.013, "step": 191232 }, { "epoch": 7.233878584110914, "grad_norm": 0.34056881070137024, "learning_rate": 2.768879150768766e-06, "loss": 0.0133, "step": 191488 }, { "epoch": 7.243549544784859, "grad_norm": 0.5745522975921631, "learning_rate": 2.7592081900948207e-06, "loss": 0.013, "step": 191744 }, { "epoch": 7.253220505458804, "grad_norm": 0.6764463782310486, "learning_rate": 2.7495372294208762e-06, "loss": 0.013, "step": 192000 }, { "epoch": 7.262891466132749, "grad_norm": 0.5475955009460449, "learning_rate": 2.739866268746931e-06, "loss": 0.0129, "step": 192256 }, { "epoch": 7.272562426806694, "grad_norm": 1.4028669595718384, "learning_rate": 2.730195308072986e-06, "loss": 0.0129, "step": 192512 }, { "epoch": 7.282233387480639, "grad_norm": 0.6126695275306702, "learning_rate": 2.7205243473990406e-06, "loss": 0.0125, "step": 192768 }, { "epoch": 7.291904348154584, "grad_norm": 0.874689519405365, "learning_rate": 2.7108533867250956e-06, "loss": 0.0127, "step": 193024 }, { "epoch": 7.30157530882853, "grad_norm": 0.4735936224460602, "learning_rate": 2.701220203241283e-06, "loss": 0.0128, "step": 193280 }, { "epoch": 7.311246269502474, "grad_norm": 1.5664587020874023, "learning_rate": 2.6915492425673377e-06, "loss": 0.0125, "step": 193536 }, { "epoch": 7.32091723017642, "grad_norm": 0.77314293384552, "learning_rate": 2.681878281893393e-06, "loss": 0.0125, "step": 193792 }, { "epoch": 7.3305881908503645, "grad_norm": 1.1619236469268799, "learning_rate": 2.672207321219448e-06, "loss": 0.0123, "step": 194048 }, { "epoch": 7.340259151524309, "grad_norm": 0.8979329466819763, "learning_rate": 2.662536360545503e-06, "loss": 0.0132, "step": 194304 }, { "epoch": 7.349930112198255, "grad_norm": 0.7251694202423096, "learning_rate": 2.6528653998715575e-06, "loss": 0.0127, "step": 194560 }, { "epoch": 7.3596010728721994, "grad_norm": 1.4056588411331177, "learning_rate": 2.6432322163877453e-06, "loss": 0.0132, "step": 194816 }, { "epoch": 7.369272033546145, "grad_norm": 0.574004054069519, "learning_rate": 2.6335612557138e-06, "loss": 0.0122, "step": 195072 }, { "epoch": 7.37894299422009, "grad_norm": 1.6402719020843506, "learning_rate": 2.6238902950398555e-06, "loss": 0.0122, "step": 195328 }, { "epoch": 7.388613954894035, "grad_norm": 1.1506208181381226, "learning_rate": 2.61421933436591e-06, "loss": 0.0123, "step": 195584 }, { "epoch": 7.39828491556798, "grad_norm": 1.1200196743011475, "learning_rate": 2.604548373691965e-06, "loss": 0.0123, "step": 195840 }, { "epoch": 7.4079558762419255, "grad_norm": 0.4092794358730316, "learning_rate": 2.59487741301802e-06, "loss": 0.0127, "step": 196096 }, { "epoch": 7.41762683691587, "grad_norm": 0.643757700920105, "learning_rate": 2.585206452344075e-06, "loss": 0.0126, "step": 196352 }, { "epoch": 7.427297797589815, "grad_norm": 1.182263970375061, "learning_rate": 2.5755354916701295e-06, "loss": 0.0122, "step": 196608 }, { "epoch": 7.4369687582637605, "grad_norm": 1.5153677463531494, "learning_rate": 2.565864530996185e-06, "loss": 0.0124, "step": 196864 }, { "epoch": 7.446639718937705, "grad_norm": 0.3546278476715088, "learning_rate": 2.5561935703222397e-06, "loss": 0.0129, "step": 197120 }, { "epoch": 7.456310679611651, "grad_norm": 0.4651656746864319, "learning_rate": 2.546560386838427e-06, "loss": 0.0125, "step": 197376 }, { "epoch": 7.465981640285595, "grad_norm": 0.9394788146018982, "learning_rate": 2.536889426164482e-06, "loss": 0.0121, "step": 197632 }, { "epoch": 7.475652600959541, "grad_norm": 0.6536080241203308, "learning_rate": 2.5272184654905368e-06, "loss": 0.012, "step": 197888 }, { "epoch": 7.485323561633486, "grad_norm": 0.46054571866989136, "learning_rate": 2.517547504816592e-06, "loss": 0.0123, "step": 198144 }, { "epoch": 7.494994522307431, "grad_norm": 0.8182215690612793, "learning_rate": 2.507876544142647e-06, "loss": 0.0125, "step": 198400 }, { "epoch": 7.504665482981376, "grad_norm": 0.5930477380752563, "learning_rate": 2.498205583468702e-06, "loss": 0.0119, "step": 198656 }, { "epoch": 7.514336443655321, "grad_norm": 0.44399377703666687, "learning_rate": 2.488534622794757e-06, "loss": 0.0123, "step": 198912 }, { "epoch": 7.524007404329266, "grad_norm": 0.5599132776260376, "learning_rate": 2.4788636621208117e-06, "loss": 0.0121, "step": 199168 }, { "epoch": 7.533678365003211, "grad_norm": 0.3389645516872406, "learning_rate": 2.4691927014468667e-06, "loss": 0.0126, "step": 199424 }, { "epoch": 7.543349325677156, "grad_norm": 0.7381057739257812, "learning_rate": 2.459521740772922e-06, "loss": 0.012, "step": 199680 }, { "epoch": 7.553020286351101, "grad_norm": 4.257303714752197, "learning_rate": 2.4498507800989764e-06, "loss": 0.0117, "step": 199936 }, { "epoch": 7.562691247025047, "grad_norm": 0.7396208047866821, "learning_rate": 2.4401798194250315e-06, "loss": 0.0125, "step": 200192 }, { "epoch": 7.572362207698991, "grad_norm": 0.76679927110672, "learning_rate": 2.4305088587510866e-06, "loss": 0.0119, "step": 200448 }, { "epoch": 7.582033168372936, "grad_norm": 2.741219997406006, "learning_rate": 2.4208378980771412e-06, "loss": 0.0123, "step": 200704 }, { "epoch": 7.591704129046882, "grad_norm": 0.7193456292152405, "learning_rate": 2.4111669374031963e-06, "loss": 0.0122, "step": 200960 }, { "epoch": 7.601375089720826, "grad_norm": 0.44765761494636536, "learning_rate": 2.4015337539193837e-06, "loss": 0.0123, "step": 201216 }, { "epoch": 7.611046050394772, "grad_norm": 1.0574860572814941, "learning_rate": 2.3918627932454388e-06, "loss": 0.0124, "step": 201472 }, { "epoch": 7.620717011068717, "grad_norm": 1.1437393426895142, "learning_rate": 2.3821918325714934e-06, "loss": 0.0122, "step": 201728 }, { "epoch": 7.630387971742662, "grad_norm": 1.0393418073654175, "learning_rate": 2.3725208718975485e-06, "loss": 0.012, "step": 201984 }, { "epoch": 7.640058932416607, "grad_norm": 0.5275835394859314, "learning_rate": 2.3628499112236035e-06, "loss": 0.0117, "step": 202240 }, { "epoch": 7.6497298930905515, "grad_norm": 0.32876691222190857, "learning_rate": 2.353216727739791e-06, "loss": 0.0128, "step": 202496 }, { "epoch": 7.659400853764497, "grad_norm": 0.5710610151290894, "learning_rate": 2.343545767065846e-06, "loss": 0.0123, "step": 202752 }, { "epoch": 7.669071814438442, "grad_norm": 0.903110146522522, "learning_rate": 2.333874806391901e-06, "loss": 0.0117, "step": 203008 }, { "epoch": 7.678742775112387, "grad_norm": 0.5795237421989441, "learning_rate": 2.3242038457179557e-06, "loss": 0.0116, "step": 203264 }, { "epoch": 7.688413735786332, "grad_norm": 0.5828751921653748, "learning_rate": 2.3145328850440108e-06, "loss": 0.0114, "step": 203520 }, { "epoch": 7.698084696460278, "grad_norm": 0.8606652617454529, "learning_rate": 2.304861924370066e-06, "loss": 0.0121, "step": 203776 }, { "epoch": 7.707755657134222, "grad_norm": 0.4666405916213989, "learning_rate": 2.2951909636961205e-06, "loss": 0.0119, "step": 204032 }, { "epoch": 7.717426617808167, "grad_norm": 1.9802192449569702, "learning_rate": 2.2855200030221755e-06, "loss": 0.0116, "step": 204288 }, { "epoch": 7.7270975784821125, "grad_norm": 0.9215091466903687, "learning_rate": 2.2758490423482306e-06, "loss": 0.012, "step": 204544 }, { "epoch": 7.736768539156057, "grad_norm": 0.9200983643531799, "learning_rate": 2.2661780816742852e-06, "loss": 0.0123, "step": 204800 }, { "epoch": 7.746439499830003, "grad_norm": 0.4531884491443634, "learning_rate": 2.2565071210003403e-06, "loss": 0.0115, "step": 205056 }, { "epoch": 7.7561104605039475, "grad_norm": 1.0625410079956055, "learning_rate": 2.2468361603263954e-06, "loss": 0.0119, "step": 205312 }, { "epoch": 7.765781421177893, "grad_norm": 0.7316881418228149, "learning_rate": 2.23716519965245e-06, "loss": 0.0117, "step": 205568 }, { "epoch": 7.775452381851838, "grad_norm": 0.4531678259372711, "learning_rate": 2.227494238978505e-06, "loss": 0.0117, "step": 205824 }, { "epoch": 7.785123342525783, "grad_norm": 0.7635496854782104, "learning_rate": 2.21782327830456e-06, "loss": 0.0121, "step": 206080 }, { "epoch": 7.794794303199728, "grad_norm": 2.019440174102783, "learning_rate": 2.2081523176306148e-06, "loss": 0.0117, "step": 206336 }, { "epoch": 7.804465263873674, "grad_norm": 0.7002264857292175, "learning_rate": 2.19848135695667e-06, "loss": 0.0114, "step": 206592 }, { "epoch": 7.814136224547618, "grad_norm": 0.8247295022010803, "learning_rate": 2.188810396282725e-06, "loss": 0.0114, "step": 206848 }, { "epoch": 7.823807185221563, "grad_norm": 0.5641749501228333, "learning_rate": 2.1791772127989123e-06, "loss": 0.0117, "step": 207104 }, { "epoch": 7.8334781458955085, "grad_norm": 0.798319399356842, "learning_rate": 2.169506252124967e-06, "loss": 0.0118, "step": 207360 }, { "epoch": 7.843149106569453, "grad_norm": 1.0480519533157349, "learning_rate": 2.159835291451022e-06, "loss": 0.0113, "step": 207616 }, { "epoch": 7.852820067243399, "grad_norm": 0.4718455672264099, "learning_rate": 2.150164330777077e-06, "loss": 0.0114, "step": 207872 }, { "epoch": 7.8624910279173434, "grad_norm": 1.4916471242904663, "learning_rate": 2.1404933701031317e-06, "loss": 0.0118, "step": 208128 }, { "epoch": 7.872161988591289, "grad_norm": 0.4426773190498352, "learning_rate": 2.130822409429187e-06, "loss": 0.0118, "step": 208384 }, { "epoch": 7.881832949265234, "grad_norm": 0.7467395067214966, "learning_rate": 2.121151448755242e-06, "loss": 0.012, "step": 208640 }, { "epoch": 7.891503909939178, "grad_norm": 0.3759344816207886, "learning_rate": 2.1114804880812965e-06, "loss": 0.0114, "step": 208896 }, { "epoch": 7.901174870613124, "grad_norm": 0.6115685701370239, "learning_rate": 2.101847304597484e-06, "loss": 0.0113, "step": 209152 }, { "epoch": 7.910845831287069, "grad_norm": 0.4685599207878113, "learning_rate": 2.092176343923539e-06, "loss": 0.0119, "step": 209408 }, { "epoch": 7.920516791961014, "grad_norm": 0.9348412156105042, "learning_rate": 2.082505383249594e-06, "loss": 0.0113, "step": 209664 }, { "epoch": 7.930187752634959, "grad_norm": 0.7617163062095642, "learning_rate": 2.0728344225756487e-06, "loss": 0.0119, "step": 209920 }, { "epoch": 7.9398587133089045, "grad_norm": 1.7726918458938599, "learning_rate": 2.0631634619017038e-06, "loss": 0.0115, "step": 210176 }, { "epoch": 7.949529673982849, "grad_norm": 0.44086819887161255, "learning_rate": 2.053492501227759e-06, "loss": 0.0118, "step": 210432 }, { "epoch": 7.959200634656794, "grad_norm": 0.510193407535553, "learning_rate": 2.0438215405538135e-06, "loss": 0.0113, "step": 210688 }, { "epoch": 7.968871595330739, "grad_norm": 0.9059385657310486, "learning_rate": 2.0341505798798685e-06, "loss": 0.0118, "step": 210944 }, { "epoch": 7.978542556004684, "grad_norm": 0.5377389788627625, "learning_rate": 2.0245173963960564e-06, "loss": 0.0118, "step": 211200 }, { "epoch": 7.98821351667863, "grad_norm": 0.6641307473182678, "learning_rate": 2.0148842129122438e-06, "loss": 0.0123, "step": 211456 }, { "epoch": 7.997884477352574, "grad_norm": 0.9336340427398682, "learning_rate": 2.0052132522382984e-06, "loss": 0.0114, "step": 211712 }, { "epoch": 8.0, "eval_f1_B-DISEASE": 0.8696338492158814, "eval_f1_B-MEDICATION": 0.9661538461538461, "eval_f1_B-PROCEDURE": 0.8836079856155116, "eval_f1_B-SYMPTOM": 0.865606588914272, "eval_f1_I-DISEASE": 0.9021935434725339, "eval_f1_I-MEDICATION": 0.968433734939759, "eval_f1_I-PROCEDURE": 0.8988507771195217, "eval_f1_I-SYMPTOM": 0.8687601005566529, "eval_f1_O": 0.9475574883287501, "eval_f1_macro": 0.907866434924081, "eval_f1_micro": 0.9237513981841913, "eval_loss": 0.07444994896650314, "eval_precision_B-DISEASE": 0.8668376945442107, "eval_precision_B-MEDICATION": 0.9570391872278665, "eval_precision_B-PROCEDURE": 0.8906244161279474, "eval_precision_B-SYMPTOM": 0.8639445577823113, "eval_precision_I-DISEASE": 0.8952855505020599, "eval_precision_I-MEDICATION": 0.958273724368145, "eval_precision_I-PROCEDURE": 0.9081989714217933, "eval_precision_I-SYMPTOM": 0.8577713016161471, "eval_precision_O": 0.950992833407909, "eval_precision_macro": 0.9054409152220434, "eval_precision_micro": 0.9240592237653457, "eval_rauc_macro": 0.9481641654297108, "eval_rauc_micro": 0.9568832265170913, "eval_recall_B-DISEASE": 0.8724481013529797, "eval_recall_B-MEDICATION": 0.9754437869822485, "eval_recall_B-PROCEDURE": 0.876701243286986, "eval_recall_B-SYMPTOM": 0.867275027105168, "eval_recall_I-DISEASE": 0.9092089690688674, "eval_recall_I-MEDICATION": 0.9788114953726255, "eval_recall_I-PROCEDURE": 0.8896930661841603, "eval_recall_I-SYMPTOM": 0.8800341054426603, "eval_recall_O": 0.94414687344109, "eval_recall_macro": 0.9104180742485316, "eval_recall_micro": 0.9234437776224358, "eval_roc_auc_B-DISEASE": 0.9347712696064548, "eval_roc_auc_B-MEDICATION": 0.9876132402118141, "eval_roc_auc_B-PROCEDURE": 0.9372598453551135, "eval_roc_auc_B-SYMPTOM": 0.9319398852908731, "eval_roc_auc_I-DISEASE": 0.947750068811213, "eval_roc_auc_I-MEDICATION": 0.9890812796840492, "eval_roc_auc_I-PROCEDURE": 0.9405070097467662, "eval_roc_auc_I-SYMPTOM": 0.9292577351883912, "eval_roc_auc_O": 0.9352971549727221, "eval_runtime": 38.3929, "eval_samples_per_second": 283.203, "eval_steps_per_second": 35.423, "step": 211768 }, { "epoch": 8.00755543802652, "grad_norm": 0.6295717358589172, "learning_rate": 1.9955800687544862e-06, "loss": 0.0113, "step": 211968 }, { "epoch": 8.017226398700465, "grad_norm": 0.46094998717308044, "learning_rate": 1.9859091080805413e-06, "loss": 0.01, "step": 212224 }, { "epoch": 8.02689735937441, "grad_norm": 0.387386292219162, "learning_rate": 1.976238147406596e-06, "loss": 0.01, "step": 212480 }, { "epoch": 8.036568320048355, "grad_norm": 0.5144914388656616, "learning_rate": 1.966567186732651e-06, "loss": 0.0101, "step": 212736 }, { "epoch": 8.0462392807223, "grad_norm": 0.2996685206890106, "learning_rate": 1.956896226058706e-06, "loss": 0.0095, "step": 212992 }, { "epoch": 8.055910241396244, "grad_norm": 0.5830399394035339, "learning_rate": 1.9472252653847607e-06, "loss": 0.01, "step": 213248 }, { "epoch": 8.06558120207019, "grad_norm": 0.9357680678367615, "learning_rate": 1.9375543047108158e-06, "loss": 0.0098, "step": 213504 }, { "epoch": 8.075252162744135, "grad_norm": 0.9837816953659058, "learning_rate": 1.927883344036871e-06, "loss": 0.0099, "step": 213760 }, { "epoch": 8.084923123418081, "grad_norm": 0.8791128993034363, "learning_rate": 1.9182123833629255e-06, "loss": 0.0099, "step": 214016 }, { "epoch": 8.094594084092025, "grad_norm": 0.755608081817627, "learning_rate": 1.9085414226889806e-06, "loss": 0.0097, "step": 214272 }, { "epoch": 8.10426504476597, "grad_norm": 0.5776179432868958, "learning_rate": 1.8988704620150356e-06, "loss": 0.0097, "step": 214528 }, { "epoch": 8.113936005439916, "grad_norm": 1.3392775058746338, "learning_rate": 1.8891995013410905e-06, "loss": 0.0098, "step": 214784 }, { "epoch": 8.12360696611386, "grad_norm": 0.3040987551212311, "learning_rate": 1.8795663178572779e-06, "loss": 0.0113, "step": 215040 }, { "epoch": 8.133277926787805, "grad_norm": 0.3788696825504303, "learning_rate": 1.8698953571833327e-06, "loss": 0.0104, "step": 215296 }, { "epoch": 8.14294888746175, "grad_norm": 0.7203466892242432, "learning_rate": 1.8602243965093878e-06, "loss": 0.0103, "step": 215552 }, { "epoch": 8.152619848135696, "grad_norm": 3.8453776836395264, "learning_rate": 1.8505534358354427e-06, "loss": 0.01, "step": 215808 }, { "epoch": 8.16229080880964, "grad_norm": 0.6163116693496704, "learning_rate": 1.8408824751614975e-06, "loss": 0.0095, "step": 216064 }, { "epoch": 8.171961769483586, "grad_norm": 0.42412546277046204, "learning_rate": 1.8312115144875526e-06, "loss": 0.0098, "step": 216320 }, { "epoch": 8.181632730157531, "grad_norm": 0.6262984871864319, "learning_rate": 1.8215405538136074e-06, "loss": 0.0102, "step": 216576 }, { "epoch": 8.191303690831475, "grad_norm": 0.6823177337646484, "learning_rate": 1.8118695931396623e-06, "loss": 0.0096, "step": 216832 }, { "epoch": 8.20097465150542, "grad_norm": 0.5827828645706177, "learning_rate": 1.8021986324657173e-06, "loss": 0.0101, "step": 217088 }, { "epoch": 8.210645612179366, "grad_norm": 1.0810794830322266, "learning_rate": 1.7925276717917722e-06, "loss": 0.0101, "step": 217344 }, { "epoch": 8.220316572853312, "grad_norm": 3.537891149520874, "learning_rate": 1.7828567111178273e-06, "loss": 0.0094, "step": 217600 }, { "epoch": 8.229987533527256, "grad_norm": 0.8385944962501526, "learning_rate": 1.7731857504438821e-06, "loss": 0.0102, "step": 217856 }, { "epoch": 8.239658494201201, "grad_norm": 0.8690928220748901, "learning_rate": 1.763514789769937e-06, "loss": 0.0097, "step": 218112 }, { "epoch": 8.249329454875147, "grad_norm": 0.4036335349082947, "learning_rate": 1.753843829095992e-06, "loss": 0.0102, "step": 218368 }, { "epoch": 8.259000415549092, "grad_norm": 0.9242327809333801, "learning_rate": 1.7441728684220469e-06, "loss": 0.0099, "step": 218624 }, { "epoch": 8.268671376223036, "grad_norm": 0.3493492603302002, "learning_rate": 1.7345019077481017e-06, "loss": 0.0097, "step": 218880 }, { "epoch": 8.278342336896982, "grad_norm": 0.6041299104690552, "learning_rate": 1.7248309470741568e-06, "loss": 0.0096, "step": 219136 }, { "epoch": 8.288013297570927, "grad_norm": 1.3182116746902466, "learning_rate": 1.7151599864002116e-06, "loss": 0.0095, "step": 219392 }, { "epoch": 8.297684258244871, "grad_norm": 0.9263989925384521, "learning_rate": 1.7054890257262665e-06, "loss": 0.0095, "step": 219648 }, { "epoch": 8.307355218918817, "grad_norm": 0.49908000230789185, "learning_rate": 1.6958180650523216e-06, "loss": 0.0097, "step": 219904 }, { "epoch": 8.317026179592762, "grad_norm": 1.492987036705017, "learning_rate": 1.6861471043783764e-06, "loss": 0.0094, "step": 220160 }, { "epoch": 8.326697140266708, "grad_norm": 0.7962930202484131, "learning_rate": 1.6764761437044313e-06, "loss": 0.0098, "step": 220416 }, { "epoch": 8.336368100940652, "grad_norm": 0.46002140641212463, "learning_rate": 1.6668051830304863e-06, "loss": 0.0099, "step": 220672 }, { "epoch": 8.346039061614597, "grad_norm": 0.5267321467399597, "learning_rate": 1.6571342223565412e-06, "loss": 0.0101, "step": 220928 }, { "epoch": 8.355710022288543, "grad_norm": 0.7515775561332703, "learning_rate": 1.6475010388727288e-06, "loss": 0.0095, "step": 221184 }, { "epoch": 8.365380982962487, "grad_norm": 0.49031391739845276, "learning_rate": 1.6378300781987839e-06, "loss": 0.0097, "step": 221440 }, { "epoch": 8.375051943636432, "grad_norm": 0.6219070553779602, "learning_rate": 1.6281591175248387e-06, "loss": 0.0097, "step": 221696 }, { "epoch": 8.384722904310378, "grad_norm": 1.6510612964630127, "learning_rate": 1.6184881568508936e-06, "loss": 0.0097, "step": 221952 }, { "epoch": 8.394393864984323, "grad_norm": 0.6530472636222839, "learning_rate": 1.6088171961769486e-06, "loss": 0.0097, "step": 222208 }, { "epoch": 8.404064825658267, "grad_norm": 0.48233506083488464, "learning_rate": 1.5991462355030035e-06, "loss": 0.0095, "step": 222464 }, { "epoch": 8.413735786332213, "grad_norm": 0.42932048439979553, "learning_rate": 1.5894752748290584e-06, "loss": 0.0097, "step": 222720 }, { "epoch": 8.423406747006158, "grad_norm": 1.1517680883407593, "learning_rate": 1.5798043141551134e-06, "loss": 0.0098, "step": 222976 }, { "epoch": 8.433077707680102, "grad_norm": 0.9816575646400452, "learning_rate": 1.5701333534811683e-06, "loss": 0.0096, "step": 223232 }, { "epoch": 8.442748668354048, "grad_norm": 0.7513278722763062, "learning_rate": 1.5605001699973557e-06, "loss": 0.0096, "step": 223488 }, { "epoch": 8.452419629027993, "grad_norm": 0.4248201549053192, "learning_rate": 1.5508292093234105e-06, "loss": 0.0095, "step": 223744 }, { "epoch": 8.462090589701939, "grad_norm": 0.3757069408893585, "learning_rate": 1.5411582486494656e-06, "loss": 0.0097, "step": 224000 }, { "epoch": 8.471761550375883, "grad_norm": 0.6515098214149475, "learning_rate": 1.5314872879755205e-06, "loss": 0.0095, "step": 224256 }, { "epoch": 8.481432511049828, "grad_norm": 0.6790785193443298, "learning_rate": 1.5218163273015755e-06, "loss": 0.0092, "step": 224512 }, { "epoch": 8.491103471723774, "grad_norm": 3.6280386447906494, "learning_rate": 1.512183143817763e-06, "loss": 0.0098, "step": 224768 }, { "epoch": 8.500774432397717, "grad_norm": 0.4772231876850128, "learning_rate": 1.5025121831438178e-06, "loss": 0.0094, "step": 225024 }, { "epoch": 8.510445393071663, "grad_norm": 0.9561179876327515, "learning_rate": 1.4928412224698726e-06, "loss": 0.0097, "step": 225280 }, { "epoch": 8.520116353745609, "grad_norm": 0.9146032333374023, "learning_rate": 1.4831702617959277e-06, "loss": 0.0094, "step": 225536 }, { "epoch": 8.529787314419554, "grad_norm": 0.4631132483482361, "learning_rate": 1.4734993011219828e-06, "loss": 0.0089, "step": 225792 }, { "epoch": 8.539458275093498, "grad_norm": 0.40875178575515747, "learning_rate": 1.4638283404480378e-06, "loss": 0.0097, "step": 226048 }, { "epoch": 8.549129235767444, "grad_norm": 0.7949475646018982, "learning_rate": 1.4541573797740927e-06, "loss": 0.0093, "step": 226304 }, { "epoch": 8.55880019644139, "grad_norm": 0.520740807056427, "learning_rate": 1.4444864191001475e-06, "loss": 0.0091, "step": 226560 }, { "epoch": 8.568471157115333, "grad_norm": 0.8199343085289001, "learning_rate": 1.4348154584262026e-06, "loss": 0.0094, "step": 226816 }, { "epoch": 8.578142117789278, "grad_norm": 0.740252673625946, "learning_rate": 1.4251444977522574e-06, "loss": 0.0094, "step": 227072 }, { "epoch": 8.587813078463224, "grad_norm": 1.9775928258895874, "learning_rate": 1.4154735370783123e-06, "loss": 0.0095, "step": 227328 }, { "epoch": 8.59748403913717, "grad_norm": 2.733029842376709, "learning_rate": 1.4058025764043674e-06, "loss": 0.0095, "step": 227584 }, { "epoch": 8.607154999811113, "grad_norm": 0.6637881994247437, "learning_rate": 1.3961316157304222e-06, "loss": 0.0094, "step": 227840 }, { "epoch": 8.616825960485059, "grad_norm": 0.9983887672424316, "learning_rate": 1.386460655056477e-06, "loss": 0.0093, "step": 228096 }, { "epoch": 8.626496921159005, "grad_norm": 0.5538541078567505, "learning_rate": 1.3767896943825321e-06, "loss": 0.0092, "step": 228352 }, { "epoch": 8.63616788183295, "grad_norm": 0.43385013937950134, "learning_rate": 1.367118733708587e-06, "loss": 0.0092, "step": 228608 }, { "epoch": 8.645838842506894, "grad_norm": 0.73806232213974, "learning_rate": 1.3574477730346418e-06, "loss": 0.0093, "step": 228864 }, { "epoch": 8.65550980318084, "grad_norm": 0.9631660580635071, "learning_rate": 1.3478145895508293e-06, "loss": 0.0098, "step": 229120 }, { "epoch": 8.665180763854785, "grad_norm": 0.7335557341575623, "learning_rate": 1.3381436288768843e-06, "loss": 0.0092, "step": 229376 }, { "epoch": 8.674851724528729, "grad_norm": 0.5021054744720459, "learning_rate": 1.3284726682029392e-06, "loss": 0.0091, "step": 229632 }, { "epoch": 8.684522685202674, "grad_norm": 0.6557485461235046, "learning_rate": 1.318801707528994e-06, "loss": 0.0092, "step": 229888 }, { "epoch": 8.69419364587662, "grad_norm": 0.45181798934936523, "learning_rate": 1.309130746855049e-06, "loss": 0.0092, "step": 230144 }, { "epoch": 8.703864606550566, "grad_norm": 1.323675274848938, "learning_rate": 1.299459786181104e-06, "loss": 0.0091, "step": 230400 }, { "epoch": 8.71353556722451, "grad_norm": 2.563812494277954, "learning_rate": 1.2897888255071588e-06, "loss": 0.0092, "step": 230656 }, { "epoch": 8.723206527898455, "grad_norm": 0.24427855014801025, "learning_rate": 1.2801178648332139e-06, "loss": 0.0092, "step": 230912 }, { "epoch": 8.7328774885724, "grad_norm": 0.634715735912323, "learning_rate": 1.2704469041592687e-06, "loss": 0.009, "step": 231168 }, { "epoch": 8.742548449246344, "grad_norm": 0.38282138109207153, "learning_rate": 1.2608137206754561e-06, "loss": 0.0096, "step": 231424 }, { "epoch": 8.75221940992029, "grad_norm": 0.5743502378463745, "learning_rate": 1.2511427600015112e-06, "loss": 0.0092, "step": 231680 }, { "epoch": 8.761890370594235, "grad_norm": 0.3509744703769684, "learning_rate": 1.2414717993275662e-06, "loss": 0.0087, "step": 231936 }, { "epoch": 8.771561331268181, "grad_norm": 0.9023687839508057, "learning_rate": 1.231800838653621e-06, "loss": 0.0089, "step": 232192 }, { "epoch": 8.781232291942125, "grad_norm": 0.5190021991729736, "learning_rate": 1.222129877979676e-06, "loss": 0.009, "step": 232448 }, { "epoch": 8.79090325261607, "grad_norm": 1.3661150932312012, "learning_rate": 1.212458917305731e-06, "loss": 0.0087, "step": 232704 }, { "epoch": 8.800574213290016, "grad_norm": 1.2023141384124756, "learning_rate": 1.2027879566317859e-06, "loss": 0.0086, "step": 232960 }, { "epoch": 8.81024517396396, "grad_norm": 1.965481162071228, "learning_rate": 1.1931169959578407e-06, "loss": 0.0086, "step": 233216 }, { "epoch": 8.819916134637905, "grad_norm": 0.38584277033805847, "learning_rate": 1.1834460352838958e-06, "loss": 0.0087, "step": 233472 }, { "epoch": 8.829587095311851, "grad_norm": 0.5356454253196716, "learning_rate": 1.1738128518000832e-06, "loss": 0.0092, "step": 233728 }, { "epoch": 8.839258055985797, "grad_norm": 0.5331792235374451, "learning_rate": 1.1641418911261383e-06, "loss": 0.0087, "step": 233984 }, { "epoch": 8.84892901665974, "grad_norm": 0.7078236937522888, "learning_rate": 1.1544709304521931e-06, "loss": 0.009, "step": 234240 }, { "epoch": 8.858599977333686, "grad_norm": 0.6543323397636414, "learning_rate": 1.144799969778248e-06, "loss": 0.0088, "step": 234496 }, { "epoch": 8.868270938007631, "grad_norm": 0.48029881715774536, "learning_rate": 1.135129009104303e-06, "loss": 0.0087, "step": 234752 }, { "epoch": 8.877941898681575, "grad_norm": 0.48811179399490356, "learning_rate": 1.1254580484303579e-06, "loss": 0.0089, "step": 235008 }, { "epoch": 8.88761285935552, "grad_norm": 0.3187180161476135, "learning_rate": 1.1157870877564127e-06, "loss": 0.0087, "step": 235264 }, { "epoch": 8.897283820029466, "grad_norm": 0.9484221935272217, "learning_rate": 1.1061161270824678e-06, "loss": 0.0089, "step": 235520 }, { "epoch": 8.906954780703412, "grad_norm": 0.704910397529602, "learning_rate": 1.0964451664085227e-06, "loss": 0.0086, "step": 235776 }, { "epoch": 8.916625741377356, "grad_norm": 0.6486955285072327, "learning_rate": 1.0867742057345775e-06, "loss": 0.0089, "step": 236032 }, { "epoch": 8.926296702051301, "grad_norm": 0.8381194472312927, "learning_rate": 1.0771032450606326e-06, "loss": 0.0091, "step": 236288 }, { "epoch": 8.935967662725247, "grad_norm": 0.7842695713043213, "learning_rate": 1.0674322843866874e-06, "loss": 0.0087, "step": 236544 }, { "epoch": 8.94563862339919, "grad_norm": 0.8942869305610657, "learning_rate": 1.0577613237127423e-06, "loss": 0.0086, "step": 236800 }, { "epoch": 8.955309584073136, "grad_norm": 0.9882628917694092, "learning_rate": 1.04812814022893e-06, "loss": 0.0086, "step": 237056 }, { "epoch": 8.964980544747082, "grad_norm": 0.9440307021141052, "learning_rate": 1.0384571795549848e-06, "loss": 0.0088, "step": 237312 }, { "epoch": 8.974651505421027, "grad_norm": 0.6903641819953918, "learning_rate": 1.0287862188810398e-06, "loss": 0.0085, "step": 237568 }, { "epoch": 8.984322466094971, "grad_norm": 0.5977570414543152, "learning_rate": 1.0191152582070947e-06, "loss": 0.0092, "step": 237824 }, { "epoch": 8.993993426768917, "grad_norm": 0.7220622301101685, "learning_rate": 1.0094442975331495e-06, "loss": 0.0089, "step": 238080 }, { "epoch": 9.0, "eval_f1_B-DISEASE": 0.8734459019762304, "eval_f1_B-MEDICATION": 0.96692037470726, "eval_f1_B-PROCEDURE": 0.8840022798727684, "eval_f1_B-SYMPTOM": 0.8650744927753238, "eval_f1_I-DISEASE": 0.9046373559886052, "eval_f1_I-MEDICATION": 0.9700122841245755, "eval_f1_I-PROCEDURE": 0.9004011279902363, "eval_f1_I-SYMPTOM": 0.8700653199670881, "eval_f1_O": 0.9480001100099926, "eval_f1_macro": 0.9091732497124533, "eval_f1_micro": 0.9245820875323214, "eval_loss": 0.08157005161046982, "eval_precision_B-DISEASE": 0.8689814972569598, "eval_precision_B-MEDICATION": 0.9568366164542295, "eval_precision_B-PROCEDURE": 0.8837260596257765, "eval_precision_B-SYMPTOM": 0.8602185759804651, "eval_precision_I-DISEASE": 0.8914178895920408, "eval_precision_I-MEDICATION": 0.9594510887692381, "eval_precision_I-PROCEDURE": 0.9037552993118211, "eval_precision_I-SYMPTOM": 0.8569514810384083, "eval_precision_O": 0.9547519333466286, "eval_precision_macro": 0.9040100490417298, "eval_precision_micro": 0.924911785766356, "eval_rauc_macro": 0.9504489598860165, "eval_rauc_micro": 0.9573421952418221, "eval_recall_B-DISEASE": 0.8779564154645919, "eval_recall_B-MEDICATION": 0.9772189349112426, "eval_recall_B-PROCEDURE": 0.884278672846318, "eval_recall_B-SYMPTOM": 0.8699855439103722, "eval_recall_I-DISEASE": 0.9182548060007037, "eval_recall_I-MEDICATION": 0.980808572820263, "eval_recall_I-PROCEDURE": 0.8970717617569429, "eval_recall_I-SYMPTOM": 0.883586755719767, "eval_recall_O": 0.9413431113020744, "eval_recall_macro": 0.9145005083035862, "eval_recall_micro": 0.9242526242659734, "eval_roc_auc_B-DISEASE": 0.9375433391953618, "eval_roc_auc_B-MEDICATION": 0.9885000800325321, "eval_roc_auc_B-PROCEDURE": 0.9409606123370149, "eval_roc_auc_B-SYMPTOM": 0.9332356237610356, "eval_roc_auc_I-DISEASE": 0.9519179579841219, "eval_roc_auc_I-MEDICATION": 0.9900887181016443, "eval_roc_auc_I-PROCEDURE": 0.9439260134391947, "eval_roc_auc_I-SYMPTOM": 0.9309179631372511, "eval_roc_auc_O": 0.9369503309859926, "eval_runtime": 38.4746, "eval_samples_per_second": 282.602, "eval_steps_per_second": 35.348, "step": 238239 }, { "epoch": 9.003664387442862, "grad_norm": 0.6710495352745056, "learning_rate": 9.997733368592046e-07, "loss": 0.009, "step": 238336 }, { "epoch": 9.013335348116808, "grad_norm": 0.7028139233589172, "learning_rate": 9.901023761852594e-07, "loss": 0.0076, "step": 238592 }, { "epoch": 9.023006308790752, "grad_norm": 0.08780034631490707, "learning_rate": 9.804314155113145e-07, "loss": 0.0082, "step": 238848 }, { "epoch": 9.032677269464697, "grad_norm": 0.9086233377456665, "learning_rate": 9.707604548373694e-07, "loss": 0.007, "step": 239104 }, { "epoch": 9.042348230138643, "grad_norm": 0.7967291474342346, "learning_rate": 9.611272713535568e-07, "loss": 0.0079, "step": 239360 }, { "epoch": 9.052019190812587, "grad_norm": 1.2340435981750488, "learning_rate": 9.514563106796116e-07, "loss": 0.0078, "step": 239616 }, { "epoch": 9.061690151486532, "grad_norm": 0.23547600209712982, "learning_rate": 9.417853500056666e-07, "loss": 0.0077, "step": 239872 }, { "epoch": 9.071361112160478, "grad_norm": 0.5875318646430969, "learning_rate": 9.321143893317215e-07, "loss": 0.0077, "step": 240128 }, { "epoch": 9.081032072834423, "grad_norm": 0.6370847821235657, "learning_rate": 9.224434286577765e-07, "loss": 0.0079, "step": 240384 }, { "epoch": 9.090703033508367, "grad_norm": 0.5130833983421326, "learning_rate": 9.127724679838314e-07, "loss": 0.0076, "step": 240640 }, { "epoch": 9.100373994182313, "grad_norm": 0.6742642521858215, "learning_rate": 9.031015073098863e-07, "loss": 0.0079, "step": 240896 }, { "epoch": 9.110044954856258, "grad_norm": 0.7362642884254456, "learning_rate": 8.934305466359413e-07, "loss": 0.0079, "step": 241152 }, { "epoch": 9.119715915530202, "grad_norm": 1.2293381690979004, "learning_rate": 8.837595859619961e-07, "loss": 0.0075, "step": 241408 }, { "epoch": 9.129386876204148, "grad_norm": 0.6655508875846863, "learning_rate": 8.740886252880511e-07, "loss": 0.0079, "step": 241664 }, { "epoch": 9.139057836878093, "grad_norm": 0.2488839328289032, "learning_rate": 8.644554418042386e-07, "loss": 0.0078, "step": 241920 }, { "epoch": 9.148728797552039, "grad_norm": 0.24622561037540436, "learning_rate": 8.547844811302936e-07, "loss": 0.008, "step": 242176 }, { "epoch": 9.158399758225983, "grad_norm": 0.6279994249343872, "learning_rate": 8.451135204563485e-07, "loss": 0.0073, "step": 242432 }, { "epoch": 9.168070718899928, "grad_norm": 0.6180801391601562, "learning_rate": 8.354425597824034e-07, "loss": 0.0078, "step": 242688 }, { "epoch": 9.177741679573874, "grad_norm": 0.5243353843688965, "learning_rate": 8.257715991084583e-07, "loss": 0.0079, "step": 242944 }, { "epoch": 9.187412640247818, "grad_norm": 0.6651556491851807, "learning_rate": 8.161006384345133e-07, "loss": 0.0079, "step": 243200 }, { "epoch": 9.197083600921763, "grad_norm": 0.5583295822143555, "learning_rate": 8.064296777605681e-07, "loss": 0.0081, "step": 243456 }, { "epoch": 9.206754561595709, "grad_norm": 0.5324780344963074, "learning_rate": 7.967587170866231e-07, "loss": 0.0079, "step": 243712 }, { "epoch": 9.216425522269654, "grad_norm": 0.5136213302612305, "learning_rate": 7.870877564126781e-07, "loss": 0.0084, "step": 243968 }, { "epoch": 9.226096482943598, "grad_norm": 0.7337320446968079, "learning_rate": 7.774545729288656e-07, "loss": 0.008, "step": 244224 }, { "epoch": 9.235767443617544, "grad_norm": 0.8372251987457275, "learning_rate": 7.677836122549205e-07, "loss": 0.0077, "step": 244480 }, { "epoch": 9.24543840429149, "grad_norm": 0.5399196147918701, "learning_rate": 7.581126515809755e-07, "loss": 0.0081, "step": 244736 }, { "epoch": 9.255109364965433, "grad_norm": 0.6882326602935791, "learning_rate": 7.484416909070303e-07, "loss": 0.0074, "step": 244992 }, { "epoch": 9.264780325639379, "grad_norm": 0.4875848889350891, "learning_rate": 7.387707302330853e-07, "loss": 0.0078, "step": 245248 }, { "epoch": 9.274451286313324, "grad_norm": 0.6352758407592773, "learning_rate": 7.290997695591403e-07, "loss": 0.0076, "step": 245504 }, { "epoch": 9.28412224698727, "grad_norm": 0.5875768065452576, "learning_rate": 7.194288088851951e-07, "loss": 0.0076, "step": 245760 }, { "epoch": 9.293793207661214, "grad_norm": 1.1072258949279785, "learning_rate": 7.097578482112501e-07, "loss": 0.0077, "step": 246016 }, { "epoch": 9.303464168335159, "grad_norm": 0.26419010758399963, "learning_rate": 7.00086887537305e-07, "loss": 0.008, "step": 246272 }, { "epoch": 9.313135129009105, "grad_norm": 0.6776321530342102, "learning_rate": 6.904159268633599e-07, "loss": 0.0078, "step": 246528 }, { "epoch": 9.322806089683048, "grad_norm": 0.787264347076416, "learning_rate": 6.807449661894148e-07, "loss": 0.0078, "step": 246784 }, { "epoch": 9.332477050356994, "grad_norm": 1.5133908987045288, "learning_rate": 6.710740055154698e-07, "loss": 0.0079, "step": 247040 }, { "epoch": 9.34214801103094, "grad_norm": 1.9702894687652588, "learning_rate": 6.614030448415248e-07, "loss": 0.0078, "step": 247296 }, { "epoch": 9.351818971704885, "grad_norm": 0.9628565907478333, "learning_rate": 6.517320841675796e-07, "loss": 0.0077, "step": 247552 }, { "epoch": 9.361489932378829, "grad_norm": 0.8602891564369202, "learning_rate": 6.420611234936346e-07, "loss": 0.0073, "step": 247808 }, { "epoch": 9.371160893052775, "grad_norm": 1.872865080833435, "learning_rate": 6.323901628196895e-07, "loss": 0.0078, "step": 248064 }, { "epoch": 9.38083185372672, "grad_norm": 0.39893224835395813, "learning_rate": 6.227947565260096e-07, "loss": 0.0076, "step": 248320 }, { "epoch": 9.390502814400666, "grad_norm": 1.3531806468963623, "learning_rate": 6.131237958520646e-07, "loss": 0.0076, "step": 248576 }, { "epoch": 9.40017377507461, "grad_norm": 0.8268289566040039, "learning_rate": 6.034528351781195e-07, "loss": 0.0074, "step": 248832 }, { "epoch": 9.409844735748555, "grad_norm": 0.7647328972816467, "learning_rate": 5.937818745041745e-07, "loss": 0.0078, "step": 249088 }, { "epoch": 9.4195156964225, "grad_norm": 1.1182609796524048, "learning_rate": 5.841109138302293e-07, "loss": 0.0075, "step": 249344 }, { "epoch": 9.429186657096444, "grad_norm": 1.0218778848648071, "learning_rate": 5.74477730346417e-07, "loss": 0.0085, "step": 249600 }, { "epoch": 9.43885761777039, "grad_norm": 1.2883316278457642, "learning_rate": 5.648067696724718e-07, "loss": 0.0072, "step": 249856 }, { "epoch": 9.448528578444336, "grad_norm": 1.2774299383163452, "learning_rate": 5.551358089985268e-07, "loss": 0.0074, "step": 250112 }, { "epoch": 9.458199539118281, "grad_norm": 0.2154589146375656, "learning_rate": 5.454648483245817e-07, "loss": 0.0073, "step": 250368 }, { "epoch": 9.467870499792225, "grad_norm": 0.4761625826358795, "learning_rate": 5.357938876506366e-07, "loss": 0.0074, "step": 250624 }, { "epoch": 9.47754146046617, "grad_norm": 0.6142901182174683, "learning_rate": 5.261229269766915e-07, "loss": 0.0072, "step": 250880 }, { "epoch": 9.487212421140116, "grad_norm": 0.5031432509422302, "learning_rate": 5.164519663027465e-07, "loss": 0.0076, "step": 251136 }, { "epoch": 9.49688338181406, "grad_norm": 0.4784689247608185, "learning_rate": 5.067810056288013e-07, "loss": 0.0074, "step": 251392 }, { "epoch": 9.506554342488005, "grad_norm": 1.2748435735702515, "learning_rate": 4.971100449548563e-07, "loss": 0.0081, "step": 251648 }, { "epoch": 9.516225303161951, "grad_norm": 0.4508354365825653, "learning_rate": 4.874390842809113e-07, "loss": 0.0075, "step": 251904 }, { "epoch": 9.525896263835897, "grad_norm": 0.5680904388427734, "learning_rate": 4.777681236069662e-07, "loss": 0.0077, "step": 252160 }, { "epoch": 9.53556722450984, "grad_norm": 0.3383603096008301, "learning_rate": 4.680971629330211e-07, "loss": 0.0073, "step": 252416 }, { "epoch": 9.545238185183786, "grad_norm": 0.46678826212882996, "learning_rate": 4.5842620225907603e-07, "loss": 0.0077, "step": 252672 }, { "epoch": 9.554909145857732, "grad_norm": 0.7010180354118347, "learning_rate": 4.4875524158513094e-07, "loss": 0.0075, "step": 252928 }, { "epoch": 9.564580106531675, "grad_norm": 0.3917682468891144, "learning_rate": 4.390842809111859e-07, "loss": 0.0073, "step": 253184 }, { "epoch": 9.574251067205621, "grad_norm": 0.9071930646896362, "learning_rate": 4.294133202372408e-07, "loss": 0.0072, "step": 253440 }, { "epoch": 9.583922027879566, "grad_norm": 0.3399870693683624, "learning_rate": 4.197423595632957e-07, "loss": 0.0072, "step": 253696 }, { "epoch": 9.593592988553512, "grad_norm": 0.35928821563720703, "learning_rate": 4.1007139888935067e-07, "loss": 0.0075, "step": 253952 }, { "epoch": 9.603263949227456, "grad_norm": 0.6536191701889038, "learning_rate": 4.0043821540553813e-07, "loss": 0.007, "step": 254208 }, { "epoch": 9.612934909901401, "grad_norm": 0.9190776944160461, "learning_rate": 3.9076725473159304e-07, "loss": 0.0077, "step": 254464 }, { "epoch": 9.622605870575347, "grad_norm": 0.38866549730300903, "learning_rate": 3.81096294057648e-07, "loss": 0.0076, "step": 254720 }, { "epoch": 9.632276831249293, "grad_norm": 0.859380841255188, "learning_rate": 3.714631105738355e-07, "loss": 0.0076, "step": 254976 }, { "epoch": 9.641947791923236, "grad_norm": 0.6037071943283081, "learning_rate": 3.617921498998905e-07, "loss": 0.0075, "step": 255232 }, { "epoch": 9.651618752597182, "grad_norm": 0.6212716698646545, "learning_rate": 3.521211892259454e-07, "loss": 0.0074, "step": 255488 }, { "epoch": 9.661289713271128, "grad_norm": 0.7153804898262024, "learning_rate": 3.4245022855200034e-07, "loss": 0.0074, "step": 255744 }, { "epoch": 9.670960673945071, "grad_norm": 0.40921831130981445, "learning_rate": 3.3277926787805525e-07, "loss": 0.0071, "step": 256000 }, { "epoch": 9.680631634619017, "grad_norm": 0.4033842384815216, "learning_rate": 3.2310830720411015e-07, "loss": 0.0074, "step": 256256 }, { "epoch": 9.690302595292962, "grad_norm": 0.7276524305343628, "learning_rate": 3.134373465301651e-07, "loss": 0.0069, "step": 256512 }, { "epoch": 9.699973555966906, "grad_norm": 0.33199068903923035, "learning_rate": 3.0376638585622e-07, "loss": 0.0073, "step": 256768 }, { "epoch": 9.709644516640852, "grad_norm": 1.7634646892547607, "learning_rate": 2.9409542518227497e-07, "loss": 0.0074, "step": 257024 }, { "epoch": 9.719315477314797, "grad_norm": 0.8427956104278564, "learning_rate": 2.8442446450832993e-07, "loss": 0.0074, "step": 257280 }, { "epoch": 9.728986437988743, "grad_norm": 1.259232521057129, "learning_rate": 2.7475350383438484e-07, "loss": 0.0073, "step": 257536 }, { "epoch": 9.738657398662687, "grad_norm": 0.6267582178115845, "learning_rate": 2.6512032035057236e-07, "loss": 0.0083, "step": 257792 }, { "epoch": 9.748328359336632, "grad_norm": 0.8313575387001038, "learning_rate": 2.5544935967662726e-07, "loss": 0.0074, "step": 258048 }, { "epoch": 9.757999320010578, "grad_norm": 0.4028800129890442, "learning_rate": 2.457783990026822e-07, "loss": 0.007, "step": 258304 }, { "epoch": 9.767670280684523, "grad_norm": 0.8609083294868469, "learning_rate": 2.3610743832873712e-07, "loss": 0.007, "step": 258560 }, { "epoch": 9.777341241358467, "grad_norm": 0.8979120850563049, "learning_rate": 2.2643647765479206e-07, "loss": 0.0073, "step": 258816 }, { "epoch": 9.787012202032413, "grad_norm": 0.4054584801197052, "learning_rate": 2.16765516980847e-07, "loss": 0.0073, "step": 259072 }, { "epoch": 9.796683162706358, "grad_norm": 0.624259352684021, "learning_rate": 2.0709455630690192e-07, "loss": 0.0073, "step": 259328 }, { "epoch": 9.806354123380302, "grad_norm": 2.5179178714752197, "learning_rate": 1.9742359563295683e-07, "loss": 0.007, "step": 259584 }, { "epoch": 9.816025084054248, "grad_norm": 0.4426276981830597, "learning_rate": 1.8775263495901176e-07, "loss": 0.0074, "step": 259840 }, { "epoch": 9.825696044728193, "grad_norm": 0.5008834600448608, "learning_rate": 1.780816742850667e-07, "loss": 0.0071, "step": 260096 }, { "epoch": 9.835367005402139, "grad_norm": 0.5199950337409973, "learning_rate": 1.6841071361112162e-07, "loss": 0.0073, "step": 260352 }, { "epoch": 9.845037966076083, "grad_norm": 0.4818352162837982, "learning_rate": 1.5873975293717655e-07, "loss": 0.0073, "step": 260608 }, { "epoch": 9.854708926750028, "grad_norm": 0.5122827887535095, "learning_rate": 1.4906879226323146e-07, "loss": 0.0072, "step": 260864 }, { "epoch": 9.864379887423974, "grad_norm": 0.47744113206863403, "learning_rate": 1.393978315892864e-07, "loss": 0.0071, "step": 261120 }, { "epoch": 9.874050848097918, "grad_norm": 0.9473596215248108, "learning_rate": 1.2972687091534132e-07, "loss": 0.0074, "step": 261376 }, { "epoch": 9.883721808771863, "grad_norm": 0.4428626596927643, "learning_rate": 1.2005591024139625e-07, "loss": 0.0065, "step": 261632 }, { "epoch": 9.893392769445809, "grad_norm": 0.5689484477043152, "learning_rate": 1.1038494956745117e-07, "loss": 0.0073, "step": 261888 }, { "epoch": 9.903063730119754, "grad_norm": 1.360382080078125, "learning_rate": 1.007139888935061e-07, "loss": 0.0074, "step": 262144 }, { "epoch": 9.912734690793698, "grad_norm": 0.3847149908542633, "learning_rate": 9.104302821956105e-08, "loss": 0.0073, "step": 262400 }, { "epoch": 9.922405651467644, "grad_norm": 0.9170914888381958, "learning_rate": 8.137206754561597e-08, "loss": 0.0069, "step": 262656 }, { "epoch": 9.93207661214159, "grad_norm": 1.0417931079864502, "learning_rate": 7.170110687167089e-08, "loss": 0.0072, "step": 262912 }, { "epoch": 9.941747572815533, "grad_norm": 0.2915762960910797, "learning_rate": 6.203014619772582e-08, "loss": 0.0074, "step": 263168 }, { "epoch": 9.951418533489479, "grad_norm": 0.5322707891464233, "learning_rate": 5.2359185523780745e-08, "loss": 0.0069, "step": 263424 }, { "epoch": 9.961089494163424, "grad_norm": 0.43616533279418945, "learning_rate": 4.272600203996827e-08, "loss": 0.0071, "step": 263680 }, { "epoch": 9.97076045483737, "grad_norm": 0.18823404610157013, "learning_rate": 3.3055041366023196e-08, "loss": 0.0068, "step": 263936 }, { "epoch": 9.980431415511314, "grad_norm": 0.354751318693161, "learning_rate": 2.3384080692078125e-08, "loss": 0.007, "step": 264192 }, { "epoch": 9.99010237618526, "grad_norm": 0.5725421905517578, "learning_rate": 1.3713120018133052e-08, "loss": 0.0069, "step": 264448 }, { "epoch": 9.999773336859205, "grad_norm": 0.6068072319030762, "learning_rate": 4.0421593441879794e-09, "loss": 0.0069, "step": 264704 }, { "epoch": 10.0, "eval_f1_B-DISEASE": 0.8741828663589726, "eval_f1_B-MEDICATION": 0.9680640187945084, "eval_f1_B-PROCEDURE": 0.886726381363117, "eval_f1_B-SYMPTOM": 0.8677488624930548, "eval_f1_I-DISEASE": 0.9058862087873993, "eval_f1_I-MEDICATION": 0.9721148269862749, "eval_f1_I-PROCEDURE": 0.9025097931470866, "eval_f1_I-SYMPTOM": 0.871689065166, "eval_f1_O": 0.9488277945102961, "eval_f1_macro": 0.91086109084519, "eval_f1_micro": 0.9258209025413705, "eval_loss": 0.084662064909935, "eval_precision_B-DISEASE": 0.8713572308113285, "eval_precision_B-MEDICATION": 0.9609386386824078, "eval_precision_B-PROCEDURE": 0.8885933806146572, "eval_precision_B-SYMPTOM": 0.8653448740603192, "eval_precision_I-DISEASE": 0.8926976515965541, "eval_precision_I-MEDICATION": 0.9645631533518749, "eval_precision_I-PROCEDURE": 0.9053174874934231, "eval_precision_I-SYMPTOM": 0.8622294637097672, "eval_precision_O": 0.9544161188553127, "eval_precision_macro": 0.9072731110195161, "eval_precision_micro": 0.9261736675283222, "eval_rauc_macro": 0.9505346838766735, "eval_rauc_micro": 0.958030714553245, "eval_recall_B-DISEASE": 0.8770268874582573, "eval_recall_B-MEDICATION": 0.9752958579881656, "eval_recall_B-PROCEDURE": 0.8848672110645185, "eval_recall_B-SYMPTOM": 0.8701662450307192, "eval_recall_I-DISEASE": 0.9194703003550523, "eval_recall_I-MEDICATION": 0.9797856794934242, "eval_recall_I-PROCEDURE": 0.8997194601683239, "eval_recall_I-SYMPTOM": 0.8813585334659656, "eval_recall_O": 0.9433045310495416, "eval_recall_macro": 0.9145549673415521, "eval_recall_micro": 0.9254684061773778, "eval_roc_auc_B-DISEASE": 0.937109922125121, "eval_roc_auc_B-MEDICATION": 0.9875495537276804, "eval_roc_auc_B-PROCEDURE": 0.9413096624896381, "eval_roc_auc_B-SYMPTOM": 0.9334000934823601, "eval_roc_auc_I-DISEASE": 0.9526114729812102, "eval_roc_auc_I-MEDICATION": 0.9896188033425148, "eval_roc_auc_I-PROCEDURE": 0.9453191508348936, "eval_roc_auc_I-SYMPTOM": 0.930295483791977, "eval_roc_auc_O": 0.9375980121146665, "eval_runtime": 38.3837, "eval_samples_per_second": 283.271, "eval_steps_per_second": 35.432, "step": 264710 } ], "logging_steps": 256, "max_steps": 264710, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 9.931800327681485e+17, "train_batch_size": 8, "trial_name": null, "trial_params": null }