| { | |
| "best_metric": 0.11314285546541214, | |
| "best_model_checkpoint": "/content/drive/MyDrive/Emotionen/multilingual-e5-large/multilingual_e5_large_2024-05-28/checkpoint-10126", | |
| "epoch": 10.0, | |
| "eval_steps": 1, | |
| "global_step": 50630, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09875567845151097, | |
| "grad_norm": 0.31362369656562805, | |
| "learning_rate": 1.980248864309698e-05, | |
| "loss": 0.1658, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.19751135690302193, | |
| "grad_norm": 0.3713989555835724, | |
| "learning_rate": 1.9604977286193957e-05, | |
| "loss": 0.1306, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.29626703535453286, | |
| "grad_norm": 0.33911290764808655, | |
| "learning_rate": 1.9407465929290937e-05, | |
| "loss": 0.1229, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.39502271380604387, | |
| "grad_norm": 0.41552165150642395, | |
| "learning_rate": 1.9209954572387913e-05, | |
| "loss": 0.1199, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.4937783922575548, | |
| "grad_norm": 0.5132314562797546, | |
| "learning_rate": 1.9012443215484893e-05, | |
| "loss": 0.1189, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.5925340707090657, | |
| "grad_norm": 0.460574209690094, | |
| "learning_rate": 1.8814931858581872e-05, | |
| "loss": 0.118, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6912897491605767, | |
| "grad_norm": 0.4870443642139435, | |
| "learning_rate": 1.8617420501678848e-05, | |
| "loss": 0.117, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.7900454276120877, | |
| "grad_norm": 0.39810240268707275, | |
| "learning_rate": 1.8419909144775828e-05, | |
| "loss": 0.1164, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.8888011060635986, | |
| "grad_norm": 0.3674732744693756, | |
| "learning_rate": 1.8222397787872804e-05, | |
| "loss": 0.1153, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.9875567845151096, | |
| "grad_norm": 0.419662743806839, | |
| "learning_rate": 1.802488643096978e-05, | |
| "loss": 0.1158, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.18166666666666667, | |
| "eval_f1_micro": 0.30011781927237674, | |
| "eval_loss": 0.11470416933298111, | |
| "eval_roc_auc": 0.5961780161730722, | |
| "eval_runtime": 39.4359, | |
| "eval_samples_per_second": 456.437, | |
| "eval_steps_per_second": 14.276, | |
| "step": 5063 | |
| }, | |
| { | |
| "epoch": 1.0863124629666205, | |
| "grad_norm": 0.41265037655830383, | |
| "learning_rate": 1.782737507406676e-05, | |
| "loss": 0.1126, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.1850681414181317, | |
| "grad_norm": 0.38658422231674194, | |
| "learning_rate": 1.762986371716374e-05, | |
| "loss": 0.1106, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.2838238198696426, | |
| "grad_norm": 0.45577454566955566, | |
| "learning_rate": 1.7432352360260715e-05, | |
| "loss": 0.1114, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.3825794983211535, | |
| "grad_norm": 0.5785081386566162, | |
| "learning_rate": 1.7234841003357695e-05, | |
| "loss": 0.1117, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.4813351767726644, | |
| "grad_norm": 0.42792847752571106, | |
| "learning_rate": 1.703732964645467e-05, | |
| "loss": 0.1113, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.5800908552241753, | |
| "grad_norm": 0.5515544414520264, | |
| "learning_rate": 1.683981828955165e-05, | |
| "loss": 0.1107, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.6788465336756864, | |
| "grad_norm": 0.4049302637577057, | |
| "learning_rate": 1.664230693264863e-05, | |
| "loss": 0.1113, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.7776022121271973, | |
| "grad_norm": 0.4182845652103424, | |
| "learning_rate": 1.6444795575745606e-05, | |
| "loss": 0.1112, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.8763578905787082, | |
| "grad_norm": 0.4281316101551056, | |
| "learning_rate": 1.6247284218842586e-05, | |
| "loss": 0.1109, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.9751135690302193, | |
| "grad_norm": 0.4670790433883667, | |
| "learning_rate": 1.6049772861939562e-05, | |
| "loss": 0.1102, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.21488888888888888, | |
| "eval_f1_micro": 0.3304371622083875, | |
| "eval_loss": 0.11314285546541214, | |
| "eval_roc_auc": 0.6102983856871789, | |
| "eval_runtime": 39.4597, | |
| "eval_samples_per_second": 456.162, | |
| "eval_steps_per_second": 14.268, | |
| "step": 10126 | |
| }, | |
| { | |
| "epoch": 2.0738692474817304, | |
| "grad_norm": 0.46797189116477966, | |
| "learning_rate": 1.585226150503654e-05, | |
| "loss": 0.1071, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.172624925933241, | |
| "grad_norm": 0.5314794778823853, | |
| "learning_rate": 1.565475014813352e-05, | |
| "loss": 0.1066, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.271380604384752, | |
| "grad_norm": 0.6094779372215271, | |
| "learning_rate": 1.5457238791230497e-05, | |
| "loss": 0.1048, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.3701362828362633, | |
| "grad_norm": 0.46292218565940857, | |
| "learning_rate": 1.5259727434327476e-05, | |
| "loss": 0.1063, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.468891961287774, | |
| "grad_norm": 0.4565483033657074, | |
| "learning_rate": 1.5062216077424454e-05, | |
| "loss": 0.1052, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.567647639739285, | |
| "grad_norm": 0.5294711589813232, | |
| "learning_rate": 1.486470472052143e-05, | |
| "loss": 0.107, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.6664033181907962, | |
| "grad_norm": 0.5409520864486694, | |
| "learning_rate": 1.4667193363618408e-05, | |
| "loss": 0.1061, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.765158996642307, | |
| "grad_norm": 0.572907567024231, | |
| "learning_rate": 1.4469682006715386e-05, | |
| "loss": 0.1062, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.863914675093818, | |
| "grad_norm": 0.4891163110733032, | |
| "learning_rate": 1.4272170649812364e-05, | |
| "loss": 0.1065, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.9626703535453287, | |
| "grad_norm": 0.49211814999580383, | |
| "learning_rate": 1.4074659292909343e-05, | |
| "loss": 0.1059, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.2378888888888889, | |
| "eval_f1_micro": 0.35730189914865756, | |
| "eval_loss": 0.11334217339754105, | |
| "eval_roc_auc": 0.6243103133779553, | |
| "eval_runtime": 39.4216, | |
| "eval_samples_per_second": 456.603, | |
| "eval_steps_per_second": 14.282, | |
| "step": 15189 | |
| }, | |
| { | |
| "epoch": 3.06142603199684, | |
| "grad_norm": 0.7181198596954346, | |
| "learning_rate": 1.3877147936006321e-05, | |
| "loss": 0.1024, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 3.160181710448351, | |
| "grad_norm": 0.57438725233078, | |
| "learning_rate": 1.3679636579103299e-05, | |
| "loss": 0.0994, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 3.2589373888998616, | |
| "grad_norm": 0.7449280619621277, | |
| "learning_rate": 1.3482125222200277e-05, | |
| "loss": 0.1003, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 3.3576930673513727, | |
| "grad_norm": 0.6857854723930359, | |
| "learning_rate": 1.3284613865297255e-05, | |
| "loss": 0.1019, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 3.456448745802884, | |
| "grad_norm": 0.6422079801559448, | |
| "learning_rate": 1.3087102508394234e-05, | |
| "loss": 0.1011, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 3.5552044242543945, | |
| "grad_norm": 0.6514602899551392, | |
| "learning_rate": 1.2889591151491212e-05, | |
| "loss": 0.1012, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 3.6539601027059057, | |
| "grad_norm": 0.5365302562713623, | |
| "learning_rate": 1.269207979458819e-05, | |
| "loss": 0.1017, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 3.7527157811574163, | |
| "grad_norm": 0.6385504603385925, | |
| "learning_rate": 1.2494568437685168e-05, | |
| "loss": 0.1009, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 3.8514714596089275, | |
| "grad_norm": 0.6212201714515686, | |
| "learning_rate": 1.2297057080782147e-05, | |
| "loss": 0.1014, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 3.9502271380604386, | |
| "grad_norm": 0.7167210578918457, | |
| "learning_rate": 1.2099545723879125e-05, | |
| "loss": 0.102, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.24166666666666667, | |
| "eval_f1_micro": 0.3643195453110199, | |
| "eval_loss": 0.11566581577062607, | |
| "eval_roc_auc": 0.63082221324154, | |
| "eval_runtime": 39.4388, | |
| "eval_samples_per_second": 456.403, | |
| "eval_steps_per_second": 14.275, | |
| "step": 20252 | |
| }, | |
| { | |
| "epoch": 4.048982816511949, | |
| "grad_norm": 0.7785666584968567, | |
| "learning_rate": 1.1902034366976103e-05, | |
| "loss": 0.099, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 4.147738494963461, | |
| "grad_norm": 0.6057512760162354, | |
| "learning_rate": 1.1704523010073081e-05, | |
| "loss": 0.0951, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 4.2464941734149715, | |
| "grad_norm": 0.7943652868270874, | |
| "learning_rate": 1.1507011653170059e-05, | |
| "loss": 0.0956, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 4.345249851866482, | |
| "grad_norm": 0.8373062014579773, | |
| "learning_rate": 1.1309500296267035e-05, | |
| "loss": 0.0949, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 4.444005530317993, | |
| "grad_norm": 0.6966761946678162, | |
| "learning_rate": 1.1111988939364013e-05, | |
| "loss": 0.0962, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 4.542761208769504, | |
| "grad_norm": 0.7649087309837341, | |
| "learning_rate": 1.0914477582460992e-05, | |
| "loss": 0.0964, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 4.641516887221015, | |
| "grad_norm": 0.695787787437439, | |
| "learning_rate": 1.071696622555797e-05, | |
| "loss": 0.0967, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 4.740272565672527, | |
| "grad_norm": 0.6631536483764648, | |
| "learning_rate": 1.0519454868654948e-05, | |
| "loss": 0.0968, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 4.839028244124037, | |
| "grad_norm": 0.6649767160415649, | |
| "learning_rate": 1.0321943511751926e-05, | |
| "loss": 0.0966, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 4.937783922575548, | |
| "grad_norm": 0.6164096593856812, | |
| "learning_rate": 1.0124432154848904e-05, | |
| "loss": 0.0969, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.25194444444444447, | |
| "eval_f1_micro": 0.37071333765472114, | |
| "eval_loss": 0.11759943515062332, | |
| "eval_roc_auc": 0.6358616290591664, | |
| "eval_runtime": 39.4749, | |
| "eval_samples_per_second": 455.985, | |
| "eval_steps_per_second": 14.262, | |
| "step": 25315 | |
| }, | |
| { | |
| "epoch": 5.036539601027059, | |
| "grad_norm": 0.8620449304580688, | |
| "learning_rate": 9.926920797945883e-06, | |
| "loss": 0.0955, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 5.13529527947857, | |
| "grad_norm": 0.7160885334014893, | |
| "learning_rate": 9.729409441042861e-06, | |
| "loss": 0.0897, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 5.234050957930081, | |
| "grad_norm": 0.8834371566772461, | |
| "learning_rate": 9.531898084139839e-06, | |
| "loss": 0.0897, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 5.332806636381592, | |
| "grad_norm": 0.7659549117088318, | |
| "learning_rate": 9.334386727236817e-06, | |
| "loss": 0.0915, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 5.431562314833103, | |
| "grad_norm": 0.9961947202682495, | |
| "learning_rate": 9.136875370333796e-06, | |
| "loss": 0.0917, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 5.530317993284614, | |
| "grad_norm": 0.8744510412216187, | |
| "learning_rate": 8.939364013430774e-06, | |
| "loss": 0.0911, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 5.6290736717361245, | |
| "grad_norm": 0.8435235023498535, | |
| "learning_rate": 8.74185265652775e-06, | |
| "loss": 0.0935, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 5.727829350187636, | |
| "grad_norm": 0.848759114742279, | |
| "learning_rate": 8.544341299624728e-06, | |
| "loss": 0.0924, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 5.826585028639147, | |
| "grad_norm": 0.7850985527038574, | |
| "learning_rate": 8.346829942721707e-06, | |
| "loss": 0.0935, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 5.925340707090657, | |
| "grad_norm": 0.8016532063484192, | |
| "learning_rate": 8.149318585818685e-06, | |
| "loss": 0.0917, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.25655555555555554, | |
| "eval_f1_micro": 0.3737782371179684, | |
| "eval_loss": 0.12158573418855667, | |
| "eval_roc_auc": 0.6422934232904187, | |
| "eval_runtime": 39.5217, | |
| "eval_samples_per_second": 455.446, | |
| "eval_steps_per_second": 14.245, | |
| "step": 30378 | |
| }, | |
| { | |
| "epoch": 6.024096385542169, | |
| "grad_norm": 0.782853364944458, | |
| "learning_rate": 7.951807228915663e-06, | |
| "loss": 0.0914, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 6.12285206399368, | |
| "grad_norm": 0.8463727235794067, | |
| "learning_rate": 7.754295872012641e-06, | |
| "loss": 0.0862, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 6.22160774244519, | |
| "grad_norm": 0.9679527282714844, | |
| "learning_rate": 7.55678451510962e-06, | |
| "loss": 0.0868, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 6.320363420896702, | |
| "grad_norm": 0.8114763498306274, | |
| "learning_rate": 7.3592731582065975e-06, | |
| "loss": 0.0865, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 6.419119099348213, | |
| "grad_norm": 0.8869866132736206, | |
| "learning_rate": 7.161761801303575e-06, | |
| "loss": 0.0881, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 6.517874777799723, | |
| "grad_norm": 0.9731593132019043, | |
| "learning_rate": 6.964250444400553e-06, | |
| "loss": 0.0866, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 6.616630456251235, | |
| "grad_norm": 0.8720415830612183, | |
| "learning_rate": 6.766739087497531e-06, | |
| "loss": 0.0881, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 6.7153861347027455, | |
| "grad_norm": 0.8622246980667114, | |
| "learning_rate": 6.56922773059451e-06, | |
| "loss": 0.0883, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 6.814141813154256, | |
| "grad_norm": 0.8367873430252075, | |
| "learning_rate": 6.3717163736914875e-06, | |
| "loss": 0.089, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 6.912897491605768, | |
| "grad_norm": 0.8973580598831177, | |
| "learning_rate": 6.174205016788466e-06, | |
| "loss": 0.088, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.2574444444444444, | |
| "eval_f1_micro": 0.37320491873763867, | |
| "eval_loss": 0.12590783834457397, | |
| "eval_roc_auc": 0.6456773567793932, | |
| "eval_runtime": 39.5146, | |
| "eval_samples_per_second": 455.528, | |
| "eval_steps_per_second": 14.248, | |
| "step": 35441 | |
| }, | |
| { | |
| "epoch": 7.011653170057278, | |
| "grad_norm": 0.9826680421829224, | |
| "learning_rate": 5.976693659885444e-06, | |
| "loss": 0.0876, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 7.110408848508789, | |
| "grad_norm": 1.1457393169403076, | |
| "learning_rate": 5.779182302982423e-06, | |
| "loss": 0.0813, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 7.209164526960301, | |
| "grad_norm": 0.9791042804718018, | |
| "learning_rate": 5.5816709460794006e-06, | |
| "loss": 0.0834, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 7.307920205411811, | |
| "grad_norm": 0.996573805809021, | |
| "learning_rate": 5.3841595891763776e-06, | |
| "loss": 0.0834, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 7.406675883863322, | |
| "grad_norm": 1.0137947797775269, | |
| "learning_rate": 5.186648232273355e-06, | |
| "loss": 0.0836, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 7.505431562314833, | |
| "grad_norm": 0.9656222462654114, | |
| "learning_rate": 4.989136875370334e-06, | |
| "loss": 0.0838, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 7.604187240766344, | |
| "grad_norm": 0.9735883474349976, | |
| "learning_rate": 4.791625518467312e-06, | |
| "loss": 0.0832, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 7.702942919217855, | |
| "grad_norm": 0.9456019997596741, | |
| "learning_rate": 4.594114161564291e-06, | |
| "loss": 0.0845, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 7.8016985976693665, | |
| "grad_norm": 0.98697429895401, | |
| "learning_rate": 4.3966028046612684e-06, | |
| "loss": 0.0842, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 7.900454276120877, | |
| "grad_norm": 0.9538049697875977, | |
| "learning_rate": 4.199091447758246e-06, | |
| "loss": 0.0843, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 7.999209954572388, | |
| "grad_norm": 0.9173344373703003, | |
| "learning_rate": 4.001580090855224e-06, | |
| "loss": 0.0848, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.25755555555555554, | |
| "eval_f1_micro": 0.370994086172909, | |
| "eval_loss": 0.12952594459056854, | |
| "eval_roc_auc": 0.6469219706450647, | |
| "eval_runtime": 39.7032, | |
| "eval_samples_per_second": 453.364, | |
| "eval_steps_per_second": 14.18, | |
| "step": 40504 | |
| }, | |
| { | |
| "epoch": 8.097965633023898, | |
| "grad_norm": 0.9694753885269165, | |
| "learning_rate": 3.8040687339522024e-06, | |
| "loss": 0.0784, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 8.19672131147541, | |
| "grad_norm": 1.1527094841003418, | |
| "learning_rate": 3.6065573770491806e-06, | |
| "loss": 0.0798, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 8.295476989926922, | |
| "grad_norm": 1.3963054418563843, | |
| "learning_rate": 3.409046020146159e-06, | |
| "loss": 0.0791, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 8.394232668378432, | |
| "grad_norm": 1.226542353630066, | |
| "learning_rate": 3.2115346632431367e-06, | |
| "loss": 0.0808, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 8.492988346829943, | |
| "grad_norm": 1.0286864042282104, | |
| "learning_rate": 3.0140233063401146e-06, | |
| "loss": 0.0803, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 8.591744025281454, | |
| "grad_norm": 1.1959236860275269, | |
| "learning_rate": 2.816511949437093e-06, | |
| "loss": 0.0808, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 8.690499703732964, | |
| "grad_norm": 0.9853003025054932, | |
| "learning_rate": 2.619000592534071e-06, | |
| "loss": 0.0809, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 8.789255382184475, | |
| "grad_norm": 0.8722342252731323, | |
| "learning_rate": 2.421489235631049e-06, | |
| "loss": 0.0812, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 8.888011060635986, | |
| "grad_norm": 0.9437873959541321, | |
| "learning_rate": 2.2239778787280267e-06, | |
| "loss": 0.0806, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 8.986766739087498, | |
| "grad_norm": 1.0116231441497803, | |
| "learning_rate": 2.026466521825005e-06, | |
| "loss": 0.0805, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.2628333333333333, | |
| "eval_f1_micro": 0.3753562815172111, | |
| "eval_loss": 0.13347476720809937, | |
| "eval_roc_auc": 0.6523150114535268, | |
| "eval_runtime": 39.603, | |
| "eval_samples_per_second": 454.511, | |
| "eval_steps_per_second": 14.216, | |
| "step": 45567 | |
| }, | |
| { | |
| "epoch": 9.085522417539009, | |
| "grad_norm": 0.9861115217208862, | |
| "learning_rate": 1.828955164921983e-06, | |
| "loss": 0.0768, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 9.18427809599052, | |
| "grad_norm": 0.7694704532623291, | |
| "learning_rate": 1.6314438080189613e-06, | |
| "loss": 0.0771, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 9.28303377444203, | |
| "grad_norm": 1.1088521480560303, | |
| "learning_rate": 1.4339324511159391e-06, | |
| "loss": 0.0775, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 9.38178945289354, | |
| "grad_norm": 1.0436288118362427, | |
| "learning_rate": 1.2364210942129174e-06, | |
| "loss": 0.0769, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 9.480545131345052, | |
| "grad_norm": 1.055021047592163, | |
| "learning_rate": 1.0389097373098954e-06, | |
| "loss": 0.0781, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 9.579300809796564, | |
| "grad_norm": 1.1790095567703247, | |
| "learning_rate": 8.413983804068734e-07, | |
| "loss": 0.077, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 9.678056488248075, | |
| "grad_norm": 0.8629137873649597, | |
| "learning_rate": 6.438870235038514e-07, | |
| "loss": 0.0783, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 9.776812166699585, | |
| "grad_norm": 1.006084680557251, | |
| "learning_rate": 4.463756666008296e-07, | |
| "loss": 0.0766, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 9.875567845151096, | |
| "grad_norm": 1.0732314586639404, | |
| "learning_rate": 2.4886430969780764e-07, | |
| "loss": 0.0774, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 9.974323523602607, | |
| "grad_norm": 1.122566819190979, | |
| "learning_rate": 5.1352952794785706e-08, | |
| "loss": 0.0778, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.2629444444444444, | |
| "eval_f1_micro": 0.3750875491622218, | |
| "eval_loss": 0.13676531612873077, | |
| "eval_roc_auc": 0.6544563659537705, | |
| "eval_runtime": 39.7687, | |
| "eval_samples_per_second": 452.617, | |
| "eval_steps_per_second": 14.157, | |
| "step": 50630 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 50630, | |
| "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": 1.3843807083022118e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |