| { | |
| "best_metric": 0.5296002626419067, | |
| "best_model_checkpoint": "./vit-base-16-thesis-demo-HAM10000/checkpoint-1300", | |
| "epoch": 4.0, | |
| "eval_steps": 50, | |
| "global_step": 1736, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019884792626728113, | |
| "loss": 1.8769, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019769585253456222, | |
| "loss": 1.6987, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019654377880184333, | |
| "loss": 1.5002, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019539170506912442, | |
| "loss": 1.4262, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019423963133640554, | |
| "loss": 1.4855, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.5093457943925234, | |
| "eval_f1": 0.5093457943925234, | |
| "eval_loss": 1.351930856704712, | |
| "eval_precision": 0.5093457943925234, | |
| "eval_recall": 0.5093457943925234, | |
| "eval_runtime": 22.9282, | |
| "eval_samples_per_second": 65.335, | |
| "eval_steps_per_second": 8.2, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019308755760368663, | |
| "loss": 1.2274, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019193548387096775, | |
| "loss": 1.1676, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019078341013824886, | |
| "loss": 1.0299, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00018963133640552998, | |
| "loss": 1.192, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00018847926267281107, | |
| "loss": 1.044, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.6268357810413885, | |
| "eval_f1": 0.6268357810413885, | |
| "eval_loss": 1.0514885187149048, | |
| "eval_precision": 0.6268357810413885, | |
| "eval_recall": 0.6268357810413885, | |
| "eval_runtime": 23.586, | |
| "eval_samples_per_second": 63.512, | |
| "eval_steps_per_second": 7.971, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00018732718894009219, | |
| "loss": 1.1791, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00018617511520737328, | |
| "loss": 0.9907, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001850230414746544, | |
| "loss": 0.9862, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00018387096774193548, | |
| "loss": 0.9692, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001827188940092166, | |
| "loss": 1.0774, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_accuracy": 0.568090787716956, | |
| "eval_f1": 0.568090787716956, | |
| "eval_loss": 1.2103569507598877, | |
| "eval_precision": 0.568090787716956, | |
| "eval_recall": 0.568090787716956, | |
| "eval_runtime": 23.5075, | |
| "eval_samples_per_second": 63.724, | |
| "eval_steps_per_second": 7.997, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0001815668202764977, | |
| "loss": 1.0483, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0001804147465437788, | |
| "loss": 0.8997, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001792626728110599, | |
| "loss": 0.9513, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.000178110599078341, | |
| "loss": 0.9172, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00017695852534562213, | |
| "loss": 0.9508, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.6061415220293725, | |
| "eval_f1": 0.6061415220293725, | |
| "eval_loss": 1.0623714923858643, | |
| "eval_precision": 0.6061415220293725, | |
| "eval_recall": 0.6061415220293725, | |
| "eval_runtime": 23.18, | |
| "eval_samples_per_second": 64.625, | |
| "eval_steps_per_second": 8.11, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00017580645161290325, | |
| "loss": 0.7999, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00017465437788018436, | |
| "loss": 0.8259, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00017350230414746545, | |
| "loss": 0.6937, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00017235023041474657, | |
| "loss": 0.7381, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00017119815668202766, | |
| "loss": 0.9522, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.6448598130841121, | |
| "eval_f1": 0.6448598130841121, | |
| "eval_loss": 0.9337974786758423, | |
| "eval_precision": 0.6448598130841121, | |
| "eval_recall": 0.6448598130841121, | |
| "eval_runtime": 23.4699, | |
| "eval_samples_per_second": 63.826, | |
| "eval_steps_per_second": 8.01, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00017004608294930878, | |
| "loss": 0.964, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00016889400921658987, | |
| "loss": 0.9078, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00016774193548387098, | |
| "loss": 0.8004, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00016658986175115207, | |
| "loss": 0.8192, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0001654377880184332, | |
| "loss": 0.774, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.6675567423230975, | |
| "eval_f1": 0.6675567423230975, | |
| "eval_loss": 0.8939006328582764, | |
| "eval_precision": 0.6675567423230975, | |
| "eval_recall": 0.6675567423230975, | |
| "eval_runtime": 22.8187, | |
| "eval_samples_per_second": 65.648, | |
| "eval_steps_per_second": 8.239, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00016428571428571428, | |
| "loss": 0.6929, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0001631336405529954, | |
| "loss": 0.8671, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00016198156682027649, | |
| "loss": 0.843, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0001608294930875576, | |
| "loss": 0.7337, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00015967741935483872, | |
| "loss": 0.7675, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.7182910547396528, | |
| "eval_f1": 0.7182910547396528, | |
| "eval_loss": 0.774177074432373, | |
| "eval_precision": 0.7182910547396528, | |
| "eval_recall": 0.7182910547396528, | |
| "eval_runtime": 23.9091, | |
| "eval_samples_per_second": 62.654, | |
| "eval_steps_per_second": 7.863, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00015852534562211984, | |
| "loss": 0.7298, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00015737327188940093, | |
| "loss": 0.716, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00015622119815668204, | |
| "loss": 0.6206, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00015506912442396313, | |
| "loss": 0.8554, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00015391705069124425, | |
| "loss": 0.7167, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.7216288384512684, | |
| "eval_f1": 0.7216288384512684, | |
| "eval_loss": 0.7695363163948059, | |
| "eval_precision": 0.7216288384512684, | |
| "eval_recall": 0.7216288384512684, | |
| "eval_runtime": 23.7595, | |
| "eval_samples_per_second": 63.049, | |
| "eval_steps_per_second": 7.913, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00015276497695852537, | |
| "loss": 0.8005, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00015161290322580646, | |
| "loss": 0.6622, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015046082949308757, | |
| "loss": 0.7918, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00014930875576036866, | |
| "loss": 0.5941, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00014815668202764978, | |
| "loss": 0.5204, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_accuracy": 0.7303070761014686, | |
| "eval_f1": 0.7303070761014686, | |
| "eval_loss": 0.8005053400993347, | |
| "eval_precision": 0.7303070761014686, | |
| "eval_recall": 0.7303070761014686, | |
| "eval_runtime": 23.4092, | |
| "eval_samples_per_second": 63.992, | |
| "eval_steps_per_second": 8.031, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00014700460829493087, | |
| "loss": 0.6149, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00014585253456221199, | |
| "loss": 0.459, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0001447004608294931, | |
| "loss": 0.5677, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00014354838709677422, | |
| "loss": 0.5199, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001423963133640553, | |
| "loss": 0.456, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_accuracy": 0.6902536715620827, | |
| "eval_f1": 0.6902536715620827, | |
| "eval_loss": 0.8523401618003845, | |
| "eval_precision": 0.6902536715620827, | |
| "eval_recall": 0.6902536715620827, | |
| "eval_runtime": 24.2665, | |
| "eval_samples_per_second": 61.731, | |
| "eval_steps_per_second": 7.747, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00014124423963133643, | |
| "loss": 0.5875, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00014009216589861752, | |
| "loss": 0.4803, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00013894009216589863, | |
| "loss": 0.6385, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00013778801843317972, | |
| "loss": 0.5299, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00013663594470046084, | |
| "loss": 0.5421, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_accuracy": 0.7543391188251002, | |
| "eval_f1": 0.7543391188251003, | |
| "eval_loss": 0.6753360629081726, | |
| "eval_precision": 0.7543391188251002, | |
| "eval_recall": 0.7543391188251002, | |
| "eval_runtime": 24.4291, | |
| "eval_samples_per_second": 61.32, | |
| "eval_steps_per_second": 7.696, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00013548387096774193, | |
| "loss": 0.4458, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00013433179723502305, | |
| "loss": 0.5533, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00013317972350230414, | |
| "loss": 0.4426, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00013202764976958525, | |
| "loss": 0.4254, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00013087557603686637, | |
| "loss": 0.4446, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_accuracy": 0.7810413885180241, | |
| "eval_f1": 0.7810413885180241, | |
| "eval_loss": 0.6042020320892334, | |
| "eval_precision": 0.7810413885180241, | |
| "eval_recall": 0.7810413885180241, | |
| "eval_runtime": 24.5813, | |
| "eval_samples_per_second": 60.941, | |
| "eval_steps_per_second": 7.648, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00012972350230414746, | |
| "loss": 0.5428, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00012857142857142858, | |
| "loss": 0.5215, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0001274193548387097, | |
| "loss": 0.4636, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0001262672811059908, | |
| "loss": 0.5301, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0001251152073732719, | |
| "loss": 0.455, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 0.7409879839786382, | |
| "eval_f1": 0.7409879839786382, | |
| "eval_loss": 0.6912689208984375, | |
| "eval_precision": 0.7409879839786382, | |
| "eval_recall": 0.7409879839786382, | |
| "eval_runtime": 24.0409, | |
| "eval_samples_per_second": 62.31, | |
| "eval_steps_per_second": 7.82, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00012396313364055302, | |
| "loss": 0.6054, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0001228110599078341, | |
| "loss": 0.4855, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00012165898617511522, | |
| "loss": 0.4318, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00012050691244239631, | |
| "loss": 0.5567, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00011935483870967743, | |
| "loss": 0.4175, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_accuracy": 0.7810413885180241, | |
| "eval_f1": 0.7810413885180241, | |
| "eval_loss": 0.6142333745956421, | |
| "eval_precision": 0.7810413885180241, | |
| "eval_recall": 0.7810413885180241, | |
| "eval_runtime": 24.8763, | |
| "eval_samples_per_second": 60.218, | |
| "eval_steps_per_second": 7.557, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00011820276497695852, | |
| "loss": 0.6193, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00011705069124423964, | |
| "loss": 0.4553, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00011589861751152074, | |
| "loss": 0.4813, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00011474654377880186, | |
| "loss": 0.4984, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00011359447004608295, | |
| "loss": 0.3626, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_accuracy": 0.8004005340453939, | |
| "eval_f1": 0.8004005340453939, | |
| "eval_loss": 0.5830577611923218, | |
| "eval_precision": 0.8004005340453939, | |
| "eval_recall": 0.8004005340453939, | |
| "eval_runtime": 24.5527, | |
| "eval_samples_per_second": 61.012, | |
| "eval_steps_per_second": 7.657, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00011244239631336406, | |
| "loss": 0.3285, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00011140552995391706, | |
| "loss": 0.5726, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00011025345622119817, | |
| "loss": 0.4853, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00010910138248847928, | |
| "loss": 0.5274, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00010794930875576037, | |
| "loss": 0.4816, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_accuracy": 0.7890520694259012, | |
| "eval_f1": 0.7890520694259012, | |
| "eval_loss": 0.5586402416229248, | |
| "eval_precision": 0.7890520694259012, | |
| "eval_recall": 0.7890520694259012, | |
| "eval_runtime": 25.1015, | |
| "eval_samples_per_second": 59.678, | |
| "eval_steps_per_second": 7.49, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00010679723502304149, | |
| "loss": 0.4794, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00010564516129032258, | |
| "loss": 0.418, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0001044930875576037, | |
| "loss": 0.3756, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00010334101382488478, | |
| "loss": 0.5326, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0001021889400921659, | |
| "loss": 0.3257, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_accuracy": 0.7990654205607477, | |
| "eval_f1": 0.7990654205607477, | |
| "eval_loss": 0.5758947134017944, | |
| "eval_precision": 0.7990654205607477, | |
| "eval_recall": 0.7990654205607477, | |
| "eval_runtime": 23.5154, | |
| "eval_samples_per_second": 63.703, | |
| "eval_steps_per_second": 7.995, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.000101036866359447, | |
| "loss": 0.3173, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.988479262672812e-05, | |
| "loss": 0.3198, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.873271889400923e-05, | |
| "loss": 0.2706, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.758064516129033e-05, | |
| "loss": 0.2695, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.642857142857143e-05, | |
| "loss": 0.3111, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_accuracy": 0.7930574098798397, | |
| "eval_f1": 0.7930574098798397, | |
| "eval_loss": 0.6100362539291382, | |
| "eval_precision": 0.7930574098798397, | |
| "eval_recall": 0.7930574098798397, | |
| "eval_runtime": 22.7882, | |
| "eval_samples_per_second": 65.736, | |
| "eval_steps_per_second": 8.25, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.527649769585254e-05, | |
| "loss": 0.2007, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 9.412442396313365e-05, | |
| "loss": 0.2584, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.297235023041476e-05, | |
| "loss": 0.257, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 9.182027649769586e-05, | |
| "loss": 0.3709, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 9.066820276497696e-05, | |
| "loss": 0.2052, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_accuracy": 0.8110814419225634, | |
| "eval_f1": 0.8110814419225634, | |
| "eval_loss": 0.5674178600311279, | |
| "eval_precision": 0.8110814419225634, | |
| "eval_recall": 0.8110814419225634, | |
| "eval_runtime": 23.6606, | |
| "eval_samples_per_second": 63.312, | |
| "eval_steps_per_second": 7.946, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 8.951612903225806e-05, | |
| "loss": 0.1869, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 8.836405529953917e-05, | |
| "loss": 0.3195, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 8.721198156682027e-05, | |
| "loss": 0.3406, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 8.605990783410139e-05, | |
| "loss": 0.26, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 8.490783410138249e-05, | |
| "loss": 0.2273, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_accuracy": 0.80173564753004, | |
| "eval_f1": 0.8017356475300401, | |
| "eval_loss": 0.5974730253219604, | |
| "eval_precision": 0.80173564753004, | |
| "eval_recall": 0.80173564753004, | |
| "eval_runtime": 22.7233, | |
| "eval_samples_per_second": 65.923, | |
| "eval_steps_per_second": 8.273, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 8.37557603686636e-05, | |
| "loss": 0.2222, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 8.26036866359447e-05, | |
| "loss": 0.2741, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 8.145161290322582e-05, | |
| "loss": 0.2503, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.029953917050692e-05, | |
| "loss": 0.2778, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 7.914746543778802e-05, | |
| "loss": 0.3007, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_accuracy": 0.8204272363150867, | |
| "eval_f1": 0.8204272363150867, | |
| "eval_loss": 0.5713711977005005, | |
| "eval_precision": 0.8204272363150867, | |
| "eval_recall": 0.8204272363150867, | |
| "eval_runtime": 23.4991, | |
| "eval_samples_per_second": 63.747, | |
| "eval_steps_per_second": 8.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.799539170506914e-05, | |
| "loss": 0.2108, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.684331797235024e-05, | |
| "loss": 0.2268, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.569124423963135e-05, | |
| "loss": 0.1861, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 7.453917050691245e-05, | |
| "loss": 0.2302, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.338709677419355e-05, | |
| "loss": 0.2812, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_accuracy": 0.8004005340453939, | |
| "eval_f1": 0.8004005340453939, | |
| "eval_loss": 0.6080873608589172, | |
| "eval_precision": 0.8004005340453939, | |
| "eval_recall": 0.8004005340453939, | |
| "eval_runtime": 23.4447, | |
| "eval_samples_per_second": 63.895, | |
| "eval_steps_per_second": 8.019, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.223502304147465e-05, | |
| "loss": 0.2486, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.108294930875576e-05, | |
| "loss": 0.1691, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 6.993087557603687e-05, | |
| "loss": 0.2579, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.877880184331798e-05, | |
| "loss": 0.2635, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.762672811059908e-05, | |
| "loss": 0.2661, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_accuracy": 0.822429906542056, | |
| "eval_f1": 0.822429906542056, | |
| "eval_loss": 0.5652973651885986, | |
| "eval_precision": 0.822429906542056, | |
| "eval_recall": 0.822429906542056, | |
| "eval_runtime": 23.861, | |
| "eval_samples_per_second": 62.78, | |
| "eval_steps_per_second": 7.879, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.647465437788018e-05, | |
| "loss": 0.3103, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 6.532258064516129e-05, | |
| "loss": 0.2789, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 6.417050691244239e-05, | |
| "loss": 0.1855, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 6.301843317972351e-05, | |
| "loss": 0.1857, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 6.186635944700461e-05, | |
| "loss": 0.1796, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_accuracy": 0.8337783711615487, | |
| "eval_f1": 0.8337783711615487, | |
| "eval_loss": 0.544723629951477, | |
| "eval_precision": 0.8337783711615487, | |
| "eval_recall": 0.8337783711615487, | |
| "eval_runtime": 23.9024, | |
| "eval_samples_per_second": 62.672, | |
| "eval_steps_per_second": 7.865, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 6.0714285714285715e-05, | |
| "loss": 0.1997, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 5.956221198156682e-05, | |
| "loss": 0.2206, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 5.8410138248847935e-05, | |
| "loss": 0.1756, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.725806451612904e-05, | |
| "loss": 0.232, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 5.610599078341015e-05, | |
| "loss": 0.1882, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_accuracy": 0.828437917222964, | |
| "eval_f1": 0.828437917222964, | |
| "eval_loss": 0.5357471704483032, | |
| "eval_precision": 0.828437917222964, | |
| "eval_recall": 0.828437917222964, | |
| "eval_runtime": 23.7377, | |
| "eval_samples_per_second": 63.106, | |
| "eval_steps_per_second": 7.92, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 5.495391705069125e-05, | |
| "loss": 0.1958, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 5.3801843317972355e-05, | |
| "loss": 0.1584, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.264976958525346e-05, | |
| "loss": 0.1785, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 5.149769585253457e-05, | |
| "loss": 0.144, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 5.034562211981567e-05, | |
| "loss": 0.1596, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8344459279038718, | |
| "eval_f1": 0.834445927903872, | |
| "eval_loss": 0.5296002626419067, | |
| "eval_precision": 0.8344459279038718, | |
| "eval_recall": 0.8344459279038718, | |
| "eval_runtime": 23.9184, | |
| "eval_samples_per_second": 62.629, | |
| "eval_steps_per_second": 7.86, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.9193548387096775e-05, | |
| "loss": 0.0465, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.8041474654377885e-05, | |
| "loss": 0.1005, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 4.688940092165899e-05, | |
| "loss": 0.133, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 4.573732718894009e-05, | |
| "loss": 0.1057, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 4.45852534562212e-05, | |
| "loss": 0.075, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_accuracy": 0.8197596795727636, | |
| "eval_f1": 0.8197596795727636, | |
| "eval_loss": 0.5875993967056274, | |
| "eval_precision": 0.8197596795727636, | |
| "eval_recall": 0.8197596795727636, | |
| "eval_runtime": 24.1647, | |
| "eval_samples_per_second": 61.991, | |
| "eval_steps_per_second": 7.78, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 4.3433179723502305e-05, | |
| "loss": 0.0836, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 4.228110599078341e-05, | |
| "loss": 0.0834, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 4.112903225806452e-05, | |
| "loss": 0.1301, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.997695852534563e-05, | |
| "loss": 0.0711, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 3.882488479262673e-05, | |
| "loss": 0.1128, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_accuracy": 0.8337783711615487, | |
| "eval_f1": 0.8337783711615487, | |
| "eval_loss": 0.56122225522995, | |
| "eval_precision": 0.8337783711615487, | |
| "eval_recall": 0.8337783711615487, | |
| "eval_runtime": 24.1153, | |
| "eval_samples_per_second": 62.118, | |
| "eval_steps_per_second": 7.796, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.7672811059907835e-05, | |
| "loss": 0.0848, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3.6520737327188945e-05, | |
| "loss": 0.0885, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 3.536866359447005e-05, | |
| "loss": 0.0432, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 3.421658986175115e-05, | |
| "loss": 0.0557, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 3.306451612903226e-05, | |
| "loss": 0.0677, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "eval_accuracy": 0.8331108144192256, | |
| "eval_f1": 0.8331108144192256, | |
| "eval_loss": 0.5910764932632446, | |
| "eval_precision": 0.8331108144192256, | |
| "eval_recall": 0.8331108144192256, | |
| "eval_runtime": 22.9405, | |
| "eval_samples_per_second": 65.299, | |
| "eval_steps_per_second": 8.195, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 3.1912442396313365e-05, | |
| "loss": 0.0931, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 3.076036866359447e-05, | |
| "loss": 0.0276, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 2.960829493087558e-05, | |
| "loss": 0.0311, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 2.8456221198156685e-05, | |
| "loss": 0.0513, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 2.730414746543779e-05, | |
| "loss": 0.0794, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "eval_accuracy": 0.8304405874499332, | |
| "eval_f1": 0.8304405874499331, | |
| "eval_loss": 0.5970631837844849, | |
| "eval_precision": 0.8304405874499332, | |
| "eval_recall": 0.8304405874499332, | |
| "eval_runtime": 24.072, | |
| "eval_samples_per_second": 62.23, | |
| "eval_steps_per_second": 7.81, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 2.6152073732718895e-05, | |
| "loss": 0.0655, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0626, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 2.3847926267281108e-05, | |
| "loss": 0.0936, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 2.269585253456221e-05, | |
| "loss": 0.0507, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 2.154377880184332e-05, | |
| "loss": 0.0367, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_accuracy": 0.8377837116154874, | |
| "eval_f1": 0.8377837116154874, | |
| "eval_loss": 0.5634308457374573, | |
| "eval_precision": 0.8377837116154874, | |
| "eval_recall": 0.8377837116154874, | |
| "eval_runtime": 24.4701, | |
| "eval_samples_per_second": 61.218, | |
| "eval_steps_per_second": 7.683, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 2.0391705069124424e-05, | |
| "loss": 0.1449, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.923963133640553e-05, | |
| "loss": 0.0286, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.8087557603686638e-05, | |
| "loss": 0.0877, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.693548387096774e-05, | |
| "loss": 0.0332, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.578341013824885e-05, | |
| "loss": 0.0279, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_accuracy": 0.8391188251001335, | |
| "eval_f1": 0.8391188251001335, | |
| "eval_loss": 0.5674164891242981, | |
| "eval_precision": 0.8391188251001335, | |
| "eval_recall": 0.8391188251001335, | |
| "eval_runtime": 23.0964, | |
| "eval_samples_per_second": 64.859, | |
| "eval_steps_per_second": 8.14, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1.4631336405529954e-05, | |
| "loss": 0.0474, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.3479262672811061e-05, | |
| "loss": 0.0546, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 1.2327188940092166e-05, | |
| "loss": 0.1128, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 1.1175115207373273e-05, | |
| "loss": 0.0242, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.0023041474654378e-05, | |
| "loss": 0.0216, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_accuracy": 0.835781041388518, | |
| "eval_f1": 0.835781041388518, | |
| "eval_loss": 0.5776631236076355, | |
| "eval_precision": 0.835781041388518, | |
| "eval_recall": 0.835781041388518, | |
| "eval_runtime": 23.9672, | |
| "eval_samples_per_second": 62.502, | |
| "eval_steps_per_second": 7.844, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 8.870967741935484e-06, | |
| "loss": 0.0495, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 7.71889400921659e-06, | |
| "loss": 0.0738, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 6.566820276497695e-06, | |
| "loss": 0.0212, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 5.414746543778802e-06, | |
| "loss": 0.0874, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 4.2626728110599085e-06, | |
| "loss": 0.0161, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_accuracy": 0.8437917222963952, | |
| "eval_f1": 0.8437917222963952, | |
| "eval_loss": 0.5607731342315674, | |
| "eval_precision": 0.8437917222963952, | |
| "eval_recall": 0.8437917222963952, | |
| "eval_runtime": 22.8075, | |
| "eval_samples_per_second": 65.68, | |
| "eval_steps_per_second": 8.243, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 3.110599078341014e-06, | |
| "loss": 0.018, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 1.9585253456221198e-06, | |
| "loss": 0.0698, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 8.064516129032258e-07, | |
| "loss": 0.0687, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1736, | |
| "total_flos": 2.1525139607212524e+18, | |
| "train_loss": 0.438499038875927, | |
| "train_runtime": 1854.8343, | |
| "train_samples_per_second": 14.975, | |
| "train_steps_per_second": 0.936 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1736, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "total_flos": 2.1525139607212524e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |