| { | |
| "best_metric": 0.4806080758571625, | |
| "best_model_checkpoint": "./vit-base-HAM-10000-sharpened-patch-32/checkpoint-1500", | |
| "epoch": 4.0, | |
| "global_step": 2004, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019900199600798404, | |
| "loss": 1.3003, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019800399201596808, | |
| "loss": 1.0452, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001970059880239521, | |
| "loss": 1.0441, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019600798403193614, | |
| "loss": 1.1619, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019500998003992018, | |
| "loss": 1.072, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019401197604790419, | |
| "loss": 0.8558, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019301397205588822, | |
| "loss": 1.0121, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019211576846307385, | |
| "loss": 0.7572, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0001911177644710579, | |
| "loss": 0.8409, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019011976047904192, | |
| "loss": 0.8099, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.7246882793017456, | |
| "eval_f1": 0.7246882793017455, | |
| "eval_loss": 0.8059983253479004, | |
| "eval_precision": 0.7246882793017456, | |
| "eval_recall": 0.7246882793017456, | |
| "eval_runtime": 32.144, | |
| "eval_samples_per_second": 62.376, | |
| "eval_steps_per_second": 7.809, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00018912175648702596, | |
| "loss": 0.8289, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00018812375249501, | |
| "loss": 0.7222, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00018712574850299402, | |
| "loss": 0.7763, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00018612774451097806, | |
| "loss": 0.8652, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001851297405189621, | |
| "loss": 0.8849, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001841317365269461, | |
| "loss": 0.793, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00018313373253493016, | |
| "loss": 0.9436, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001821357285429142, | |
| "loss": 0.7433, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00018113772455089823, | |
| "loss": 0.8123, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00018013972055888223, | |
| "loss": 0.7437, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.7541147132169576, | |
| "eval_f1": 0.7541147132169576, | |
| "eval_loss": 0.7020390033721924, | |
| "eval_precision": 0.7541147132169576, | |
| "eval_recall": 0.7541147132169576, | |
| "eval_runtime": 31.8897, | |
| "eval_samples_per_second": 62.873, | |
| "eval_steps_per_second": 7.871, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00017914171656686627, | |
| "loss": 0.7392, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00017814371257485033, | |
| "loss": 0.9703, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00017714570858283433, | |
| "loss": 0.7205, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00017614770459081837, | |
| "loss": 0.5989, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001751497005988024, | |
| "loss": 0.9393, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00017415169660678644, | |
| "loss": 0.8561, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00017315369261477047, | |
| "loss": 0.6189, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0001721556886227545, | |
| "loss": 0.6329, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00017115768463073854, | |
| "loss": 0.6716, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00017015968063872257, | |
| "loss": 0.7982, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.7411471321695761, | |
| "eval_f1": 0.7411471321695761, | |
| "eval_loss": 0.7351944446563721, | |
| "eval_precision": 0.7411471321695761, | |
| "eval_recall": 0.7411471321695761, | |
| "eval_runtime": 32.0466, | |
| "eval_samples_per_second": 62.565, | |
| "eval_steps_per_second": 7.832, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0001691616766467066, | |
| "loss": 0.5802, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001681636726546906, | |
| "loss": 0.7923, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00016716566866267467, | |
| "loss": 0.7872, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0001661676646706587, | |
| "loss": 0.7089, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0001651696606786427, | |
| "loss": 0.684, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00016417165668662675, | |
| "loss": 0.663, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00016317365269461078, | |
| "loss": 0.6289, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00016217564870259484, | |
| "loss": 0.5073, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00016117764471057885, | |
| "loss": 0.707, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00016017964071856288, | |
| "loss": 0.7646, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.7625935162094764, | |
| "eval_f1": 0.7625935162094764, | |
| "eval_loss": 0.6603409647941589, | |
| "eval_precision": 0.7625935162094764, | |
| "eval_recall": 0.7625935162094764, | |
| "eval_runtime": 32.0437, | |
| "eval_samples_per_second": 62.571, | |
| "eval_steps_per_second": 7.833, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00015918163672654691, | |
| "loss": 0.7719, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00015818363273453095, | |
| "loss": 0.6473, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00015718562874251495, | |
| "loss": 0.7036, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00015618762475049902, | |
| "loss": 0.7248, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00015518962075848305, | |
| "loss": 0.7479, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00015419161676646708, | |
| "loss": 0.7072, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0001531936127744511, | |
| "loss": 0.7838, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00015219560878243512, | |
| "loss": 0.6009, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00015119760479041918, | |
| "loss": 0.6748, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00015019960079840322, | |
| "loss": 0.6141, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7770573566084789, | |
| "eval_f1": 0.7770573566084789, | |
| "eval_loss": 0.6373246312141418, | |
| "eval_precision": 0.7770573566084789, | |
| "eval_recall": 0.7770573566084789, | |
| "eval_runtime": 31.7078, | |
| "eval_samples_per_second": 63.234, | |
| "eval_steps_per_second": 7.916, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00014920159680638722, | |
| "loss": 0.6177, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00014820359281437126, | |
| "loss": 0.5687, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0001472055888223553, | |
| "loss": 0.6073, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00014620758483033933, | |
| "loss": 0.4702, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00014520958083832336, | |
| "loss": 0.6447, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0001442115768463074, | |
| "loss": 0.5832, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00014321357285429143, | |
| "loss": 0.5503, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00014221556886227546, | |
| "loss": 0.5396, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00014121756487025947, | |
| "loss": 0.4324, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00014021956087824353, | |
| "loss": 0.5934, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.7820448877805486, | |
| "eval_f1": 0.7820448877805487, | |
| "eval_loss": 0.6141160726547241, | |
| "eval_precision": 0.7820448877805486, | |
| "eval_recall": 0.7820448877805486, | |
| "eval_runtime": 32.1568, | |
| "eval_samples_per_second": 62.351, | |
| "eval_steps_per_second": 7.805, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00013922155688622756, | |
| "loss": 0.5206, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0001382235528942116, | |
| "loss": 0.5714, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0001372255489021956, | |
| "loss": 0.4591, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00013622754491017964, | |
| "loss": 0.6433, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0001352295409181637, | |
| "loss": 0.5583, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0001342315369261477, | |
| "loss": 0.6621, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00013323353293413174, | |
| "loss": 0.5437, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00013223552894211577, | |
| "loss": 0.4628, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0001312375249500998, | |
| "loss": 0.5553, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00013023952095808384, | |
| "loss": 0.5524, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_accuracy": 0.8029925187032418, | |
| "eval_f1": 0.8029925187032418, | |
| "eval_loss": 0.5620763301849365, | |
| "eval_precision": 0.8029925187032418, | |
| "eval_recall": 0.8029925187032418, | |
| "eval_runtime": 32.0501, | |
| "eval_samples_per_second": 62.558, | |
| "eval_steps_per_second": 7.831, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00012924151696606787, | |
| "loss": 0.5667, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0001282435129740519, | |
| "loss": 0.5561, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00012724550898203594, | |
| "loss": 0.5223, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00012624750499001995, | |
| "loss": 0.547, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00012524950099800398, | |
| "loss": 0.5797, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00012425149700598804, | |
| "loss": 0.5009, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00012325349301397208, | |
| "loss": 0.3869, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00012225548902195608, | |
| "loss": 0.6393, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00012125748502994012, | |
| "loss": 0.5089, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00012025948103792415, | |
| "loss": 0.5057, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_accuracy": 0.7855361596009975, | |
| "eval_f1": 0.7855361596009975, | |
| "eval_loss": 0.6073994636535645, | |
| "eval_precision": 0.7855361596009975, | |
| "eval_recall": 0.7855361596009975, | |
| "eval_runtime": 31.8224, | |
| "eval_samples_per_second": 63.006, | |
| "eval_steps_per_second": 7.888, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0001192614770459082, | |
| "loss": 0.4625, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00011826347305389223, | |
| "loss": 0.3309, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00011726546906187625, | |
| "loss": 0.5541, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00011626746506986028, | |
| "loss": 0.6548, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0001152694610778443, | |
| "loss": 0.4578, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00011427145708582837, | |
| "loss": 0.4702, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00011327345309381239, | |
| "loss": 0.622, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00011227544910179642, | |
| "loss": 0.5547, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00011127744510978044, | |
| "loss": 0.6202, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00011027944111776447, | |
| "loss": 0.5519, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_accuracy": 0.7990024937655861, | |
| "eval_f1": 0.7990024937655861, | |
| "eval_loss": 0.5486381649971008, | |
| "eval_precision": 0.7990024937655861, | |
| "eval_recall": 0.7990024937655861, | |
| "eval_runtime": 31.819, | |
| "eval_samples_per_second": 63.013, | |
| "eval_steps_per_second": 7.888, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0001092814371257485, | |
| "loss": 0.4968, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00010828343313373255, | |
| "loss": 0.5381, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00010728542914171657, | |
| "loss": 0.4597, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00010628742514970061, | |
| "loss": 0.5073, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00010528942115768463, | |
| "loss": 0.4388, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010429141716566866, | |
| "loss": 0.4437, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00010329341317365271, | |
| "loss": 0.5385, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010229540918163673, | |
| "loss": 0.4844, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010129740518962076, | |
| "loss": 0.462, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001002994011976048, | |
| "loss": 0.4784, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8059850374064838, | |
| "eval_f1": 0.8059850374064838, | |
| "eval_loss": 0.5382136702537537, | |
| "eval_precision": 0.8059850374064838, | |
| "eval_recall": 0.8059850374064838, | |
| "eval_runtime": 31.7884, | |
| "eval_samples_per_second": 63.073, | |
| "eval_steps_per_second": 7.896, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.930139720558883e-05, | |
| "loss": 0.4136, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.830339321357286e-05, | |
| "loss": 0.2614, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.730538922155689e-05, | |
| "loss": 0.3999, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.630738522954092e-05, | |
| "loss": 0.3702, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.530938123752495e-05, | |
| "loss": 0.2452, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 9.431137724550899e-05, | |
| "loss": 0.3152, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.331337325349302e-05, | |
| "loss": 0.3001, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 9.231536926147705e-05, | |
| "loss": 0.2705, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 9.131736526946109e-05, | |
| "loss": 0.2754, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 9.031936127744511e-05, | |
| "loss": 0.2592, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_accuracy": 0.8164588528678304, | |
| "eval_f1": 0.8164588528678304, | |
| "eval_loss": 0.5237112045288086, | |
| "eval_precision": 0.8164588528678304, | |
| "eval_recall": 0.8164588528678304, | |
| "eval_runtime": 31.7879, | |
| "eval_samples_per_second": 63.074, | |
| "eval_steps_per_second": 7.896, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 8.932135728542914e-05, | |
| "loss": 0.3575, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 8.832335329341318e-05, | |
| "loss": 0.3859, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 8.732534930139721e-05, | |
| "loss": 0.271, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 8.632734530938124e-05, | |
| "loss": 0.31, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 8.532934131736528e-05, | |
| "loss": 0.4024, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 8.43313373253493e-05, | |
| "loss": 0.4161, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.3029, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 8.233532934131736e-05, | |
| "loss": 0.3475, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 8.13373253493014e-05, | |
| "loss": 0.3746, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.033932135728543e-05, | |
| "loss": 0.3872, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.8119700748129676, | |
| "eval_f1": 0.8119700748129677, | |
| "eval_loss": 0.5345078706741333, | |
| "eval_precision": 0.8119700748129676, | |
| "eval_recall": 0.8119700748129676, | |
| "eval_runtime": 31.5896, | |
| "eval_samples_per_second": 63.47, | |
| "eval_steps_per_second": 7.946, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 7.934131736526947e-05, | |
| "loss": 0.3798, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.83433133732535e-05, | |
| "loss": 0.2521, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.734530938123753e-05, | |
| "loss": 0.2907, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.634730538922155e-05, | |
| "loss": 0.3063, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.53493013972056e-05, | |
| "loss": 0.2479, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 7.435129740518962e-05, | |
| "loss": 0.2735, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.335329341317365e-05, | |
| "loss": 0.3781, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.235528942115769e-05, | |
| "loss": 0.2744, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.135728542914172e-05, | |
| "loss": 0.2315, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.035928143712576e-05, | |
| "loss": 0.2506, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_accuracy": 0.8214463840399002, | |
| "eval_f1": 0.8214463840399002, | |
| "eval_loss": 0.5061450004577637, | |
| "eval_precision": 0.8214463840399002, | |
| "eval_recall": 0.8214463840399002, | |
| "eval_runtime": 31.7167, | |
| "eval_samples_per_second": 63.216, | |
| "eval_steps_per_second": 7.914, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.936127744510979e-05, | |
| "loss": 0.2581, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.836327345309381e-05, | |
| "loss": 0.1982, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.736526946107786e-05, | |
| "loss": 0.2994, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.636726546906188e-05, | |
| "loss": 0.256, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 6.536926147704591e-05, | |
| "loss": 0.3021, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 6.437125748502994e-05, | |
| "loss": 0.2466, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 6.337325349301398e-05, | |
| "loss": 0.3637, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 6.237524950099801e-05, | |
| "loss": 0.2795, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 6.137724550898205e-05, | |
| "loss": 0.3259, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 6.0379241516966066e-05, | |
| "loss": 0.2907, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_accuracy": 0.8354114713216958, | |
| "eval_f1": 0.8354114713216958, | |
| "eval_loss": 0.494029700756073, | |
| "eval_precision": 0.8354114713216958, | |
| "eval_recall": 0.8354114713216958, | |
| "eval_runtime": 32.0608, | |
| "eval_samples_per_second": 62.537, | |
| "eval_steps_per_second": 7.829, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 5.938123752495011e-05, | |
| "loss": 0.2325, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 5.8383233532934134e-05, | |
| "loss": 0.2369, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 5.738522954091816e-05, | |
| "loss": 0.4407, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 5.63872255489022e-05, | |
| "loss": 0.2911, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 5.538922155688623e-05, | |
| "loss": 0.2887, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 5.439121756487027e-05, | |
| "loss": 0.2648, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 5.3393213572854296e-05, | |
| "loss": 0.2497, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.239520958083832e-05, | |
| "loss": 0.27, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 5.139720558882236e-05, | |
| "loss": 0.2391, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 5.039920159680639e-05, | |
| "loss": 0.2436, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.8369077306733167, | |
| "eval_f1": 0.8369077306733167, | |
| "eval_loss": 0.4806080758571625, | |
| "eval_precision": 0.8369077306733167, | |
| "eval_recall": 0.8369077306733167, | |
| "eval_runtime": 31.9742, | |
| "eval_samples_per_second": 62.707, | |
| "eval_steps_per_second": 7.85, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 4.9401197604790424e-05, | |
| "loss": 0.2191, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.840319361277446e-05, | |
| "loss": 0.1681, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 4.7405189620758485e-05, | |
| "loss": 0.1873, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 4.640718562874252e-05, | |
| "loss": 0.0975, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 4.540918163672655e-05, | |
| "loss": 0.1881, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 4.4411177644710586e-05, | |
| "loss": 0.0768, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 4.341317365269461e-05, | |
| "loss": 0.1629, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 4.241516966067865e-05, | |
| "loss": 0.2801, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.141716566866268e-05, | |
| "loss": 0.1328, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 4.041916167664671e-05, | |
| "loss": 0.1472, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_accuracy": 0.8219451371571073, | |
| "eval_f1": 0.8219451371571073, | |
| "eval_loss": 0.5230672359466553, | |
| "eval_precision": 0.8219451371571073, | |
| "eval_recall": 0.8219451371571073, | |
| "eval_runtime": 31.9062, | |
| "eval_samples_per_second": 62.841, | |
| "eval_steps_per_second": 7.867, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3.942115768463074e-05, | |
| "loss": 0.1176, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 3.8423153692614775e-05, | |
| "loss": 0.0994, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.74251497005988e-05, | |
| "loss": 0.1491, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3.6427145708582836e-05, | |
| "loss": 0.1405, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 3.542914171656686e-05, | |
| "loss": 0.112, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 3.4431137724550896e-05, | |
| "loss": 0.1789, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.343313373253493e-05, | |
| "loss": 0.1099, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 3.2435129740518964e-05, | |
| "loss": 0.0776, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 3.143712574850299e-05, | |
| "loss": 0.0741, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 3.0439121756487028e-05, | |
| "loss": 0.1441, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "eval_accuracy": 0.8329177057356608, | |
| "eval_f1": 0.8329177057356608, | |
| "eval_loss": 0.5452331304550171, | |
| "eval_precision": 0.8329177057356608, | |
| "eval_recall": 0.8329177057356608, | |
| "eval_runtime": 31.887, | |
| "eval_samples_per_second": 62.878, | |
| "eval_steps_per_second": 7.872, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 2.944111776447106e-05, | |
| "loss": 0.1816, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 2.8443113772455092e-05, | |
| "loss": 0.0989, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 2.7445109780439123e-05, | |
| "loss": 0.0777, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 2.6447105788423153e-05, | |
| "loss": 0.1193, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 2.5449101796407187e-05, | |
| "loss": 0.1304, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 2.4451097804391217e-05, | |
| "loss": 0.1311, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 2.345309381237525e-05, | |
| "loss": 0.0976, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 2.245508982035928e-05, | |
| "loss": 0.0705, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 2.1457085828343315e-05, | |
| "loss": 0.1045, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 2.0459081836327345e-05, | |
| "loss": 0.1327, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "eval_accuracy": 0.8354114713216958, | |
| "eval_f1": 0.8354114713216958, | |
| "eval_loss": 0.5410035252571106, | |
| "eval_precision": 0.8354114713216958, | |
| "eval_recall": 0.8354114713216958, | |
| "eval_runtime": 32.2465, | |
| "eval_samples_per_second": 62.177, | |
| "eval_steps_per_second": 7.784, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.946107784431138e-05, | |
| "loss": 0.1133, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.846307385229541e-05, | |
| "loss": 0.0655, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 1.7465069860279443e-05, | |
| "loss": 0.0539, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.6467065868263474e-05, | |
| "loss": 0.0903, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.5469061876247507e-05, | |
| "loss": 0.0591, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1.4471057884231538e-05, | |
| "loss": 0.0482, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.347305389221557e-05, | |
| "loss": 0.1512, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.24750499001996e-05, | |
| "loss": 0.0841, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.1477045908183632e-05, | |
| "loss": 0.0768, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.0479041916167664e-05, | |
| "loss": 0.0615, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_accuracy": 0.8423940149625935, | |
| "eval_f1": 0.8423940149625935, | |
| "eval_loss": 0.547346293926239, | |
| "eval_precision": 0.8423940149625935, | |
| "eval_recall": 0.8423940149625935, | |
| "eval_runtime": 32.1079, | |
| "eval_samples_per_second": 62.446, | |
| "eval_steps_per_second": 7.817, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 9.481037924151696e-06, | |
| "loss": 0.1723, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 8.483033932135728e-06, | |
| "loss": 0.1122, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 7.48502994011976e-06, | |
| "loss": 0.0739, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 6.4870259481037925e-06, | |
| "loss": 0.1172, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 5.4890219560878245e-06, | |
| "loss": 0.0465, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 4.4910179640718566e-06, | |
| "loss": 0.086, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 3.493013972055888e-06, | |
| "loss": 0.1032, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 2.4950099800399203e-06, | |
| "loss": 0.1119, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 1.4970059880239521e-06, | |
| "loss": 0.1039, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 4.990019960079841e-07, | |
| "loss": 0.0943, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.8408977556109726, | |
| "eval_f1": 0.8408977556109726, | |
| "eval_loss": 0.5490320920944214, | |
| "eval_precision": 0.8408977556109726, | |
| "eval_recall": 0.8408977556109726, | |
| "eval_runtime": 31.9752, | |
| "eval_samples_per_second": 62.705, | |
| "eval_steps_per_second": 7.85, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 2004, | |
| "total_flos": 2.530891784455373e+18, | |
| "train_loss": 0.43380199842705225, | |
| "train_runtime": 1592.9033, | |
| "train_samples_per_second": 20.114, | |
| "train_steps_per_second": 1.258 | |
| } | |
| ], | |
| "max_steps": 2004, | |
| "num_train_epochs": 4, | |
| "total_flos": 2.530891784455373e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |