| { | |
| "best_metric": 0.9872068230277186, | |
| "best_model_checkpoint": "teacher-status-van-tiny-256-0/checkpoint-1140", | |
| "epoch": 29.68421052631579, | |
| "eval_steps": 500, | |
| "global_step": 1410, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.5460992907801423e-06, | |
| "loss": 0.693, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.092198581560285e-06, | |
| "loss": 0.692, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.0638297872340426e-05, | |
| "loss": 0.6887, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.418439716312057e-05, | |
| "loss": 0.6788, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.6933333333333334, | |
| "eval_f1_score": 0.8188976377952756, | |
| "eval_loss": 0.6436793804168701, | |
| "eval_precision": 0.6933333333333334, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 3.9449, | |
| "eval_samples_per_second": 171.109, | |
| "eval_steps_per_second": 5.577, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.773049645390071e-05, | |
| "loss": 0.6568, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.1276595744680852e-05, | |
| "loss": 0.6118, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.4822695035460995e-05, | |
| "loss": 0.5534, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.836879432624114e-05, | |
| "loss": 0.4849, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.191489361702128e-05, | |
| "loss": 0.463, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8755555555555555, | |
| "eval_f1_score": 0.9161676646706586, | |
| "eval_loss": 0.3405998945236206, | |
| "eval_precision": 0.8595505617977528, | |
| "eval_recall": 0.9807692307692307, | |
| "eval_runtime": 4.4067, | |
| "eval_samples_per_second": 153.174, | |
| "eval_steps_per_second": 4.992, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.546099290780142e-05, | |
| "loss": 0.4401, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 3.900709219858156e-05, | |
| "loss": 0.4196, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.2553191489361704e-05, | |
| "loss": 0.3933, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.609929078014185e-05, | |
| "loss": 0.3977, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 4.964539007092199e-05, | |
| "loss": 0.3596, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.9303703703703704, | |
| "eval_f1_score": 0.9503695881731784, | |
| "eval_loss": 0.2071676254272461, | |
| "eval_precision": 0.9394572025052192, | |
| "eval_recall": 0.9615384615384616, | |
| "eval_runtime": 3.9276, | |
| "eval_samples_per_second": 171.861, | |
| "eval_steps_per_second": 5.601, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 4.964539007092199e-05, | |
| "loss": 0.3506, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 4.9251379038613084e-05, | |
| "loss": 0.354, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 4.885736800630418e-05, | |
| "loss": 0.3132, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 4.846335697399527e-05, | |
| "loss": 0.3324, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.806934594168637e-05, | |
| "loss": 0.3505, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9525925925925925, | |
| "eval_f1_score": 0.9661016949152542, | |
| "eval_loss": 0.15637531876564026, | |
| "eval_precision": 0.957983193277311, | |
| "eval_recall": 0.9743589743589743, | |
| "eval_runtime": 4.0891, | |
| "eval_samples_per_second": 165.073, | |
| "eval_steps_per_second": 5.38, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 4.7675334909377466e-05, | |
| "loss": 0.3181, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 4.728132387706856e-05, | |
| "loss": 0.3174, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 4.6887312844759653e-05, | |
| "loss": 0.3161, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 4.6493301812450754e-05, | |
| "loss": 0.2962, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.9555555555555556, | |
| "eval_f1_score": 0.9680851063829786, | |
| "eval_loss": 0.12618891894817352, | |
| "eval_precision": 0.9639830508474576, | |
| "eval_recall": 0.9722222222222222, | |
| "eval_runtime": 4.4801, | |
| "eval_samples_per_second": 150.665, | |
| "eval_steps_per_second": 4.911, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 4.609929078014185e-05, | |
| "loss": 0.3017, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 4.570527974783294e-05, | |
| "loss": 0.2852, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 4.5311268715524035e-05, | |
| "loss": 0.3222, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 4.491725768321513e-05, | |
| "loss": 0.2662, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 4.452324665090622e-05, | |
| "loss": 0.2762, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9644444444444444, | |
| "eval_f1_score": 0.9745222929936307, | |
| "eval_loss": 0.10375303775072098, | |
| "eval_precision": 0.9683544303797469, | |
| "eval_recall": 0.9807692307692307, | |
| "eval_runtime": 3.8894, | |
| "eval_samples_per_second": 173.548, | |
| "eval_steps_per_second": 5.656, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 4.412923561859732e-05, | |
| "loss": 0.2803, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 4.373522458628842e-05, | |
| "loss": 0.2672, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 4.334121355397952e-05, | |
| "loss": 0.2768, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 4.294720252167061e-05, | |
| "loss": 0.2709, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 4.2553191489361704e-05, | |
| "loss": 0.2604, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.9718518518518519, | |
| "eval_f1_score": 0.979765708200213, | |
| "eval_loss": 0.09324438869953156, | |
| "eval_precision": 0.9766454352441614, | |
| "eval_recall": 0.9829059829059829, | |
| "eval_runtime": 3.9359, | |
| "eval_samples_per_second": 171.498, | |
| "eval_steps_per_second": 5.59, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 4.21591804570528e-05, | |
| "loss": 0.2647, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 4.176516942474389e-05, | |
| "loss": 0.2632, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 4.1371158392434986e-05, | |
| "loss": 0.2688, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 4.0977147360126086e-05, | |
| "loss": 0.2699, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.058313632781718e-05, | |
| "loss": 0.2427, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9718518518518519, | |
| "eval_f1_score": 0.9796791443850267, | |
| "eval_loss": 0.09280087053775787, | |
| "eval_precision": 0.9807280513918629, | |
| "eval_recall": 0.9786324786324786, | |
| "eval_runtime": 4.2848, | |
| "eval_samples_per_second": 157.534, | |
| "eval_steps_per_second": 5.134, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 4.018912529550828e-05, | |
| "loss": 0.241, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 3.9795114263199374e-05, | |
| "loss": 0.2311, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 3.940110323089047e-05, | |
| "loss": 0.2447, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 3.900709219858156e-05, | |
| "loss": 0.2465, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.9718518518518519, | |
| "eval_f1_score": 0.9796791443850267, | |
| "eval_loss": 0.08982550352811813, | |
| "eval_precision": 0.9807280513918629, | |
| "eval_recall": 0.9786324786324786, | |
| "eval_runtime": 3.8511, | |
| "eval_samples_per_second": 175.276, | |
| "eval_steps_per_second": 5.713, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 3.8613081166272655e-05, | |
| "loss": 0.2579, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 3.8219070133963755e-05, | |
| "loss": 0.2393, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 3.782505910165485e-05, | |
| "loss": 0.2532, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 3.743104806934594e-05, | |
| "loss": 0.2501, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2519, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9688888888888889, | |
| "eval_f1_score": 0.9775401069518715, | |
| "eval_loss": 0.09134020656347275, | |
| "eval_precision": 0.9785867237687366, | |
| "eval_recall": 0.9764957264957265, | |
| "eval_runtime": 4.1234, | |
| "eval_samples_per_second": 163.699, | |
| "eval_steps_per_second": 5.335, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 3.664302600472813e-05, | |
| "loss": 0.2177, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 3.624901497241923e-05, | |
| "loss": 0.2248, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "learning_rate": 3.5855003940110324e-05, | |
| "loss": 0.2583, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 10.74, | |
| "learning_rate": 3.546099290780142e-05, | |
| "loss": 0.2344, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 3.506698187549252e-05, | |
| "loss": 0.2258, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_f1_score": 0.980891719745223, | |
| "eval_loss": 0.08469923585653305, | |
| "eval_precision": 0.9746835443037974, | |
| "eval_recall": 0.9871794871794872, | |
| "eval_runtime": 4.0414, | |
| "eval_samples_per_second": 167.022, | |
| "eval_steps_per_second": 5.444, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 3.467297084318361e-05, | |
| "loss": 0.2357, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "learning_rate": 3.4278959810874706e-05, | |
| "loss": 0.2057, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 3.38849487785658e-05, | |
| "loss": 0.2107, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "learning_rate": 3.349093774625689e-05, | |
| "loss": 0.228, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.309692671394799e-05, | |
| "loss": 0.2184, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9792592592592593, | |
| "eval_f1_score": 0.9851063829787234, | |
| "eval_loss": 0.08121450245380402, | |
| "eval_precision": 0.9809322033898306, | |
| "eval_recall": 0.9893162393162394, | |
| "eval_runtime": 3.8823, | |
| "eval_samples_per_second": 173.868, | |
| "eval_steps_per_second": 5.667, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 3.270291568163909e-05, | |
| "loss": 0.1992, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 3.230890464933019e-05, | |
| "loss": 0.2289, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 3.191489361702128e-05, | |
| "loss": 0.2029, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 3.1520882584712375e-05, | |
| "loss": 0.2208, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.9807407407407407, | |
| "eval_f1_score": 0.9861259338313767, | |
| "eval_loss": 0.06925630569458008, | |
| "eval_precision": 0.9850746268656716, | |
| "eval_recall": 0.9871794871794872, | |
| "eval_runtime": 4.4316, | |
| "eval_samples_per_second": 152.316, | |
| "eval_steps_per_second": 4.964, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 3.112687155240347e-05, | |
| "loss": 0.2284, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 13.26, | |
| "learning_rate": 3.073286052009456e-05, | |
| "loss": 0.2129, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 3.033884948778566e-05, | |
| "loss": 0.2219, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 13.68, | |
| "learning_rate": 2.9944838455476754e-05, | |
| "loss": 0.219, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 2.9550827423167847e-05, | |
| "loss": 0.2201, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9762962962962963, | |
| "eval_f1_score": 0.9829424307036249, | |
| "eval_loss": 0.06279809772968292, | |
| "eval_precision": 0.9808510638297873, | |
| "eval_recall": 0.9850427350427351, | |
| "eval_runtime": 3.8891, | |
| "eval_samples_per_second": 173.56, | |
| "eval_steps_per_second": 5.657, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "learning_rate": 2.9156816390858944e-05, | |
| "loss": 0.223, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 14.32, | |
| "learning_rate": 2.8762805358550045e-05, | |
| "loss": 0.2151, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 14.53, | |
| "learning_rate": 2.836879432624114e-05, | |
| "loss": 0.2096, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 2.7974783293932232e-05, | |
| "loss": 0.2081, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 2.758077226162333e-05, | |
| "loss": 0.2251, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_f1_score": 0.9809725158562368, | |
| "eval_loss": 0.08107414096593857, | |
| "eval_precision": 0.9707112970711297, | |
| "eval_recall": 0.9914529914529915, | |
| "eval_runtime": 3.8972, | |
| "eval_samples_per_second": 173.203, | |
| "eval_steps_per_second": 5.645, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 2.7186761229314423e-05, | |
| "loss": 0.2067, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 15.37, | |
| "learning_rate": 2.6792750197005517e-05, | |
| "loss": 0.1864, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 15.58, | |
| "learning_rate": 2.639873916469661e-05, | |
| "loss": 0.208, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "learning_rate": 2.6004728132387708e-05, | |
| "loss": 0.1931, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.56107171000788e-05, | |
| "loss": 0.2135, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9762962962962963, | |
| "eval_f1_score": 0.9829424307036249, | |
| "eval_loss": 0.0718333050608635, | |
| "eval_precision": 0.9808510638297873, | |
| "eval_recall": 0.9850427350427351, | |
| "eval_runtime": 4.4867, | |
| "eval_samples_per_second": 150.444, | |
| "eval_steps_per_second": 4.903, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 16.21, | |
| "learning_rate": 2.5216706067769895e-05, | |
| "loss": 0.2, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 16.42, | |
| "learning_rate": 2.4822695035460995e-05, | |
| "loss": 0.2025, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 16.63, | |
| "learning_rate": 2.442868400315209e-05, | |
| "loss": 0.2017, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 16.84, | |
| "learning_rate": 2.4034672970843186e-05, | |
| "loss": 0.1851, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.9762962962962963, | |
| "eval_f1_score": 0.9829787234042553, | |
| "eval_loss": 0.07912527769804001, | |
| "eval_precision": 0.9788135593220338, | |
| "eval_recall": 0.9871794871794872, | |
| "eval_runtime": 3.9283, | |
| "eval_samples_per_second": 171.83, | |
| "eval_steps_per_second": 5.6, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "learning_rate": 2.364066193853428e-05, | |
| "loss": 0.1901, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 17.26, | |
| "learning_rate": 2.3246650906225377e-05, | |
| "loss": 0.2272, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 17.47, | |
| "learning_rate": 2.285263987391647e-05, | |
| "loss": 0.1965, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 17.68, | |
| "learning_rate": 2.2458628841607564e-05, | |
| "loss": 0.1854, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 17.89, | |
| "learning_rate": 2.206461780929866e-05, | |
| "loss": 0.2152, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9748148148148148, | |
| "eval_f1_score": 0.9818181818181818, | |
| "eval_loss": 0.0737040787935257, | |
| "eval_precision": 0.9828693790149893, | |
| "eval_recall": 0.9807692307692307, | |
| "eval_runtime": 3.9311, | |
| "eval_samples_per_second": 171.706, | |
| "eval_steps_per_second": 5.596, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 18.11, | |
| "learning_rate": 2.167060677698976e-05, | |
| "loss": 0.1991, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 18.32, | |
| "learning_rate": 2.1276595744680852e-05, | |
| "loss": 0.1637, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "learning_rate": 2.0882584712371946e-05, | |
| "loss": 0.1906, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 18.74, | |
| "learning_rate": 2.0488573680063043e-05, | |
| "loss": 0.1899, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 18.95, | |
| "learning_rate": 2.009456264775414e-05, | |
| "loss": 0.1871, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.9762962962962963, | |
| "eval_f1_score": 0.9829787234042553, | |
| "eval_loss": 0.08143588900566101, | |
| "eval_precision": 0.9788135593220338, | |
| "eval_recall": 0.9871794871794872, | |
| "eval_runtime": 4.2729, | |
| "eval_samples_per_second": 157.973, | |
| "eval_steps_per_second": 5.149, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 19.16, | |
| "learning_rate": 1.9700551615445234e-05, | |
| "loss": 0.1708, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 19.37, | |
| "learning_rate": 1.9306540583136327e-05, | |
| "loss": 0.1864, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 19.58, | |
| "learning_rate": 1.8912529550827425e-05, | |
| "loss": 0.1991, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2152, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.8124507486209615e-05, | |
| "loss": 0.1714, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9762962962962963, | |
| "eval_f1_score": 0.9830148619957537, | |
| "eval_loss": 0.06924613565206528, | |
| "eval_precision": 0.9767932489451476, | |
| "eval_recall": 0.9893162393162394, | |
| "eval_runtime": 3.9174, | |
| "eval_samples_per_second": 172.306, | |
| "eval_steps_per_second": 5.616, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "learning_rate": 1.773049645390071e-05, | |
| "loss": 0.1878, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 20.42, | |
| "learning_rate": 1.7336485421591806e-05, | |
| "loss": 0.1782, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 20.63, | |
| "learning_rate": 1.69424743892829e-05, | |
| "loss": 0.187, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 20.84, | |
| "learning_rate": 1.6548463356973994e-05, | |
| "loss": 0.188, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.9777777777777777, | |
| "eval_f1_score": 0.983991462113127, | |
| "eval_loss": 0.06410012394189835, | |
| "eval_precision": 0.9829424307036247, | |
| "eval_recall": 0.9850427350427351, | |
| "eval_runtime": 4.4961, | |
| "eval_samples_per_second": 150.132, | |
| "eval_steps_per_second": 4.893, | |
| "step": 997 | |
| }, | |
| { | |
| "epoch": 21.05, | |
| "learning_rate": 1.6154452324665094e-05, | |
| "loss": 0.1543, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 21.26, | |
| "learning_rate": 1.5760441292356188e-05, | |
| "loss": 0.1752, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 21.47, | |
| "learning_rate": 1.536643026004728e-05, | |
| "loss": 0.1606, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 21.68, | |
| "learning_rate": 1.4972419227738377e-05, | |
| "loss": 0.184, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 21.89, | |
| "learning_rate": 1.4578408195429472e-05, | |
| "loss": 0.191, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9792592592592593, | |
| "eval_f1_score": 0.9850746268656716, | |
| "eval_loss": 0.06437370181083679, | |
| "eval_precision": 0.9829787234042553, | |
| "eval_recall": 0.9871794871794872, | |
| "eval_runtime": 3.9414, | |
| "eval_samples_per_second": 171.258, | |
| "eval_steps_per_second": 5.582, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 22.11, | |
| "learning_rate": 1.418439716312057e-05, | |
| "loss": 0.177, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 22.32, | |
| "learning_rate": 1.3790386130811665e-05, | |
| "loss": 0.1727, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 22.53, | |
| "learning_rate": 1.3396375098502758e-05, | |
| "loss": 0.1872, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 22.74, | |
| "learning_rate": 1.3002364066193854e-05, | |
| "loss": 0.1558, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 22.95, | |
| "learning_rate": 1.2608353033884947e-05, | |
| "loss": 0.2025, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_accuracy": 0.9792592592592593, | |
| "eval_f1_score": 0.9850107066381155, | |
| "eval_loss": 0.06750550121068954, | |
| "eval_precision": 0.9871244635193133, | |
| "eval_recall": 0.9829059829059829, | |
| "eval_runtime": 3.9141, | |
| "eval_samples_per_second": 172.455, | |
| "eval_steps_per_second": 5.621, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 23.16, | |
| "learning_rate": 1.2214342001576045e-05, | |
| "loss": 0.1766, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 23.37, | |
| "learning_rate": 1.182033096926714e-05, | |
| "loss": 0.167, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 23.58, | |
| "learning_rate": 1.1426319936958235e-05, | |
| "loss": 0.1995, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 23.79, | |
| "learning_rate": 1.103230890464933e-05, | |
| "loss": 0.1775, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.0638297872340426e-05, | |
| "loss": 0.1753, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9822222222222222, | |
| "eval_f1_score": 0.9872068230277186, | |
| "eval_loss": 0.06550905108451843, | |
| "eval_precision": 0.9851063829787234, | |
| "eval_recall": 0.9893162393162394, | |
| "eval_runtime": 4.3235, | |
| "eval_samples_per_second": 156.125, | |
| "eval_steps_per_second": 5.089, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 24.21, | |
| "learning_rate": 1.0244286840031522e-05, | |
| "loss": 0.1825, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 24.42, | |
| "learning_rate": 9.850275807722617e-06, | |
| "loss": 0.1587, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 24.63, | |
| "learning_rate": 9.456264775413712e-06, | |
| "loss": 0.1846, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 24.84, | |
| "learning_rate": 9.062253743104808e-06, | |
| "loss": 0.1857, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.9792592592592593, | |
| "eval_f1_score": 0.9851380042462845, | |
| "eval_loss": 0.07306463271379471, | |
| "eval_precision": 0.9789029535864979, | |
| "eval_recall": 0.9914529914529915, | |
| "eval_runtime": 3.9407, | |
| "eval_samples_per_second": 171.288, | |
| "eval_steps_per_second": 5.583, | |
| "step": 1187 | |
| }, | |
| { | |
| "epoch": 25.05, | |
| "learning_rate": 8.668242710795903e-06, | |
| "loss": 0.1747, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 25.26, | |
| "learning_rate": 8.274231678486997e-06, | |
| "loss": 0.165, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 25.47, | |
| "learning_rate": 7.880220646178094e-06, | |
| "loss": 0.1774, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 25.68, | |
| "learning_rate": 7.486209613869188e-06, | |
| "loss": 0.1762, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 25.89, | |
| "learning_rate": 7.092198581560285e-06, | |
| "loss": 0.2007, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9792592592592593, | |
| "eval_f1_score": 0.9851380042462845, | |
| "eval_loss": 0.06768698245286942, | |
| "eval_precision": 0.9789029535864979, | |
| "eval_recall": 0.9914529914529915, | |
| "eval_runtime": 4.3978, | |
| "eval_samples_per_second": 153.486, | |
| "eval_steps_per_second": 5.002, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 26.11, | |
| "learning_rate": 6.698187549251379e-06, | |
| "loss": 0.1588, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "learning_rate": 6.304176516942474e-06, | |
| "loss": 0.166, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 26.53, | |
| "learning_rate": 5.91016548463357e-06, | |
| "loss": 0.191, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 26.74, | |
| "learning_rate": 5.516154452324665e-06, | |
| "loss": 0.1603, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 26.95, | |
| "learning_rate": 5.122143420015761e-06, | |
| "loss": 0.2086, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.9792592592592593, | |
| "eval_f1_score": 0.9851063829787234, | |
| "eval_loss": 0.0640312060713768, | |
| "eval_precision": 0.9809322033898306, | |
| "eval_recall": 0.9893162393162394, | |
| "eval_runtime": 3.8919, | |
| "eval_samples_per_second": 173.437, | |
| "eval_steps_per_second": 5.653, | |
| "step": 1282 | |
| }, | |
| { | |
| "epoch": 27.16, | |
| "learning_rate": 4.728132387706856e-06, | |
| "loss": 0.1807, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 27.37, | |
| "learning_rate": 4.3341213553979515e-06, | |
| "loss": 0.1697, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 27.58, | |
| "learning_rate": 3.940110323089047e-06, | |
| "loss": 0.1799, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 27.79, | |
| "learning_rate": 3.5460992907801423e-06, | |
| "loss": 0.1551, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 3.152088258471237e-06, | |
| "loss": 0.1666, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9777777777777777, | |
| "eval_f1_score": 0.9840595111583422, | |
| "eval_loss": 0.07120572775602341, | |
| "eval_precision": 0.9788583509513742, | |
| "eval_recall": 0.9893162393162394, | |
| "eval_runtime": 3.8788, | |
| "eval_samples_per_second": 174.025, | |
| "eval_steps_per_second": 5.672, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 28.21, | |
| "learning_rate": 2.7580772261623327e-06, | |
| "loss": 0.1736, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 28.42, | |
| "learning_rate": 2.364066193853428e-06, | |
| "loss": 0.2003, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 28.63, | |
| "learning_rate": 1.9700551615445235e-06, | |
| "loss": 0.1777, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 28.84, | |
| "learning_rate": 1.5760441292356184e-06, | |
| "loss": 0.157, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.9807407407407407, | |
| "eval_f1_score": 0.9861554845580405, | |
| "eval_loss": 0.06606751680374146, | |
| "eval_precision": 0.9830148619957537, | |
| "eval_recall": 0.9893162393162394, | |
| "eval_runtime": 4.4114, | |
| "eval_samples_per_second": 153.014, | |
| "eval_steps_per_second": 4.987, | |
| "step": 1377 | |
| }, | |
| { | |
| "epoch": 29.05, | |
| "learning_rate": 1.182033096926714e-06, | |
| "loss": 0.169, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 29.26, | |
| "learning_rate": 7.880220646178092e-07, | |
| "loss": 0.1736, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 29.47, | |
| "learning_rate": 3.940110323089046e-07, | |
| "loss": 0.1748, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 29.68, | |
| "learning_rate": 0.0, | |
| "loss": 0.1758, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 29.68, | |
| "eval_accuracy": 0.9777777777777777, | |
| "eval_f1_score": 0.9840595111583422, | |
| "eval_loss": 0.06716117262840271, | |
| "eval_precision": 0.9788583509513742, | |
| "eval_recall": 0.9893162393162394, | |
| "eval_runtime": 4.087, | |
| "eval_samples_per_second": 165.159, | |
| "eval_steps_per_second": 5.383, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 29.68, | |
| "step": 1410, | |
| "total_flos": 8.181902891907809e+17, | |
| "train_loss": 0.24775470698133428, | |
| "train_runtime": 3242.8553, | |
| "train_samples_per_second": 56.145, | |
| "train_steps_per_second": 0.435 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1410, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 8.181902891907809e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |