| { | |
| "best_metric": 0.9778142974527526, | |
| "best_model_checkpoint": "teacher-status-van-tiny-256-1-2/checkpoint-703", | |
| "epoch": 29.55223880597015, | |
| "eval_steps": 500, | |
| "global_step": 990, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.6865, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.683, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.6722, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.640083945435467, | |
| "eval_f1_score": 0.780550223928343, | |
| "eval_loss": 0.6498541831970215, | |
| "eval_precision": 0.640083945435467, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 6.6964, | |
| "eval_samples_per_second": 142.315, | |
| "eval_steps_per_second": 1.195, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.646, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5252525252525256e-05, | |
| "loss": 0.6078, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.5431, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7817418677859391, | |
| "eval_f1_score": 0.8531073446327684, | |
| "eval_loss": 0.4163793921470642, | |
| "eval_precision": 0.749379652605459, | |
| "eval_recall": 0.9901639344262295, | |
| "eval_runtime": 6.7638, | |
| "eval_samples_per_second": 140.898, | |
| "eval_steps_per_second": 1.183, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.497, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.4483, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.4193, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 4.994388327721661e-05, | |
| "loss": 0.393, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.887722980062959, | |
| "eval_f1_score": 0.9078380706287683, | |
| "eval_loss": 0.2832907438278198, | |
| "eval_precision": 0.956442831215971, | |
| "eval_recall": 0.8639344262295082, | |
| "eval_runtime": 6.6321, | |
| "eval_samples_per_second": 143.695, | |
| "eval_steps_per_second": 1.206, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 0.3729, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 4.882154882154882e-05, | |
| "loss": 0.3616, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 4.8260381593714935e-05, | |
| "loss": 0.354, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9275970619097587, | |
| "eval_f1_score": 0.9435813573180704, | |
| "eval_loss": 0.19304586946964264, | |
| "eval_precision": 0.9412724306688418, | |
| "eval_recall": 0.9459016393442623, | |
| "eval_runtime": 6.5785, | |
| "eval_samples_per_second": 144.865, | |
| "eval_steps_per_second": 1.216, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 4.7699214365881036e-05, | |
| "loss": 0.3214, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.713804713804714e-05, | |
| "loss": 0.3272, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 4.6576879910213244e-05, | |
| "loss": 0.3007, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.9370409233997902, | |
| "eval_f1_score": 0.9510603588907015, | |
| "eval_loss": 0.15851934254169464, | |
| "eval_precision": 0.9464285714285714, | |
| "eval_recall": 0.9557377049180328, | |
| "eval_runtime": 6.4566, | |
| "eval_samples_per_second": 147.6, | |
| "eval_steps_per_second": 1.239, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 4.601571268237935e-05, | |
| "loss": 0.3006, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.2935, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 4.4893378226711566e-05, | |
| "loss": 0.3092, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 4.433221099887767e-05, | |
| "loss": 0.2898, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9464847848898216, | |
| "eval_f1_score": 0.9580936729663106, | |
| "eval_loss": 0.144499272108078, | |
| "eval_precision": 0.9604612850082372, | |
| "eval_recall": 0.9557377049180328, | |
| "eval_runtime": 6.0258, | |
| "eval_samples_per_second": 158.154, | |
| "eval_steps_per_second": 1.328, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 4.3771043771043774e-05, | |
| "loss": 0.2696, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.3025, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 4.264870931537598e-05, | |
| "loss": 0.2824, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.9464847848898216, | |
| "eval_f1_score": 0.9579554822753504, | |
| "eval_loss": 0.13527622818946838, | |
| "eval_precision": 0.9635157545605307, | |
| "eval_recall": 0.9524590163934427, | |
| "eval_runtime": 6.0159, | |
| "eval_samples_per_second": 158.414, | |
| "eval_steps_per_second": 1.33, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 4.208754208754209e-05, | |
| "loss": 0.2782, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 4.15263748597082e-05, | |
| "loss": 0.2629, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 4.0965207631874305e-05, | |
| "loss": 0.2763, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9485834207764953, | |
| "eval_f1_score": 0.960323886639676, | |
| "eval_loss": 0.13593612611293793, | |
| "eval_precision": 0.9488, | |
| "eval_recall": 0.9721311475409836, | |
| "eval_runtime": 6.3017, | |
| "eval_samples_per_second": 151.228, | |
| "eval_steps_per_second": 1.269, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.2698, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 3.984287317620651e-05, | |
| "loss": 0.2621, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 3.9281705948372613e-05, | |
| "loss": 0.2631, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 3.872053872053872e-05, | |
| "loss": 0.2473, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.9569779643231899, | |
| "eval_f1_score": 0.9664209664209664, | |
| "eval_loss": 0.12131528556346893, | |
| "eval_precision": 0.9656301145662848, | |
| "eval_recall": 0.9672131147540983, | |
| "eval_runtime": 6.691, | |
| "eval_samples_per_second": 142.431, | |
| "eval_steps_per_second": 1.196, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 3.815937149270483e-05, | |
| "loss": 0.2339, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 3.7598204264870936e-05, | |
| "loss": 0.249, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2598, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9569779643231899, | |
| "eval_f1_score": 0.966530612244898, | |
| "eval_loss": 0.10907502472400665, | |
| "eval_precision": 0.9626016260162602, | |
| "eval_recall": 0.9704918032786886, | |
| "eval_runtime": 6.9942, | |
| "eval_samples_per_second": 136.256, | |
| "eval_steps_per_second": 1.144, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 3.6475869809203144e-05, | |
| "loss": 0.2497, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 3.5914702581369245e-05, | |
| "loss": 0.253, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.2476, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.9632738719832109, | |
| "eval_f1_score": 0.9714285714285714, | |
| "eval_loss": 0.1040654331445694, | |
| "eval_precision": 0.967479674796748, | |
| "eval_recall": 0.9754098360655737, | |
| "eval_runtime": 6.6817, | |
| "eval_samples_per_second": 142.629, | |
| "eval_steps_per_second": 1.197, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 3.4792368125701466e-05, | |
| "loss": 0.2314, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 3.423120089786757e-05, | |
| "loss": 0.2422, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 3.3670033670033675e-05, | |
| "loss": 0.2406, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 3.3108866442199775e-05, | |
| "loss": 0.2376, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9601259181532005, | |
| "eval_f1_score": 0.9686468646864688, | |
| "eval_loss": 0.09974055737257004, | |
| "eval_precision": 0.9750830564784053, | |
| "eval_recall": 0.9622950819672131, | |
| "eval_runtime": 6.6227, | |
| "eval_samples_per_second": 143.899, | |
| "eval_steps_per_second": 1.208, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 3.254769921436588e-05, | |
| "loss": 0.2282, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 12.54, | |
| "learning_rate": 3.198653198653199e-05, | |
| "loss": 0.2264, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 3.14253647586981e-05, | |
| "loss": 0.2402, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.9622245540398741, | |
| "eval_f1_score": 0.9703947368421052, | |
| "eval_loss": 0.09718549996614456, | |
| "eval_precision": 0.9735973597359736, | |
| "eval_recall": 0.9672131147540983, | |
| "eval_runtime": 6.1102, | |
| "eval_samples_per_second": 155.969, | |
| "eval_steps_per_second": 1.309, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.2216, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 13.43, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.2361, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 2.9741863075196406e-05, | |
| "loss": 0.2324, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9664218258132214, | |
| "eval_f1_score": 0.973941368078176, | |
| "eval_loss": 0.09498707950115204, | |
| "eval_precision": 0.9676375404530745, | |
| "eval_recall": 0.980327868852459, | |
| "eval_runtime": 6.0066, | |
| "eval_samples_per_second": 158.659, | |
| "eval_steps_per_second": 1.332, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 2.9180695847362517e-05, | |
| "loss": 0.2223, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 2.8619528619528618e-05, | |
| "loss": 0.213, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 14.63, | |
| "learning_rate": 2.8058361391694725e-05, | |
| "loss": 0.2206, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 2.7497194163860833e-05, | |
| "loss": 0.2256, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.9706190975865687, | |
| "eval_f1_score": 0.9770114942528735, | |
| "eval_loss": 0.09094734489917755, | |
| "eval_precision": 0.9786184210526315, | |
| "eval_recall": 0.9754098360655737, | |
| "eval_runtime": 5.9668, | |
| "eval_samples_per_second": 159.718, | |
| "eval_steps_per_second": 1.341, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 2.6936026936026937e-05, | |
| "loss": 0.209, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 2.6374859708193044e-05, | |
| "loss": 0.2254, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "learning_rate": 2.581369248035915e-05, | |
| "loss": 0.21, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9622245540398741, | |
| "eval_f1_score": 0.970345963756178, | |
| "eval_loss": 0.09220422059297562, | |
| "eval_precision": 0.9751655629139073, | |
| "eval_recall": 0.9655737704918033, | |
| "eval_runtime": 6.5986, | |
| "eval_samples_per_second": 144.424, | |
| "eval_steps_per_second": 1.212, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 16.12, | |
| "learning_rate": 2.5252525252525256e-05, | |
| "loss": 0.2114, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 16.42, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.1963, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 2.4130190796857467e-05, | |
| "loss": 0.217, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.9611752360965372, | |
| "eval_f1_score": 0.9695473251028807, | |
| "eval_loss": 0.09329694509506226, | |
| "eval_precision": 0.9735537190082645, | |
| "eval_recall": 0.9655737704918033, | |
| "eval_runtime": 6.5505, | |
| "eval_samples_per_second": 145.485, | |
| "eval_steps_per_second": 1.221, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 2.356902356902357e-05, | |
| "loss": 0.219, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 2.3007856341189676e-05, | |
| "loss": 0.2154, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 17.61, | |
| "learning_rate": 2.2446689113355783e-05, | |
| "loss": 0.2157, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 2.1885521885521887e-05, | |
| "loss": 0.2092, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9664218258132214, | |
| "eval_f1_score": 0.9738134206219312, | |
| "eval_loss": 0.08909059315919876, | |
| "eval_precision": 0.9722222222222222, | |
| "eval_recall": 0.9754098360655737, | |
| "eval_runtime": 5.9927, | |
| "eval_samples_per_second": 159.027, | |
| "eval_steps_per_second": 1.335, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 18.21, | |
| "learning_rate": 2.132435465768799e-05, | |
| "loss": 0.1979, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 18.51, | |
| "learning_rate": 2.07631874298541e-05, | |
| "loss": 0.1975, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 18.81, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.2063, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.9653725078698846, | |
| "eval_f1_score": 0.972972972972973, | |
| "eval_loss": 0.09130384773015976, | |
| "eval_precision": 0.972176759410802, | |
| "eval_recall": 0.9737704918032787, | |
| "eval_runtime": 5.9748, | |
| "eval_samples_per_second": 159.504, | |
| "eval_steps_per_second": 1.339, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 19.1, | |
| "learning_rate": 1.9640852974186307e-05, | |
| "loss": 0.215, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 19.4, | |
| "learning_rate": 1.9079685746352414e-05, | |
| "loss": 0.214, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 19.7, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2072, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.7957351290684622e-05, | |
| "loss": 0.2217, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9643231899265478, | |
| "eval_f1_score": 0.971993410214168, | |
| "eval_loss": 0.09169190376996994, | |
| "eval_precision": 0.9768211920529801, | |
| "eval_recall": 0.9672131147540983, | |
| "eval_runtime": 6.2954, | |
| "eval_samples_per_second": 151.381, | |
| "eval_steps_per_second": 1.271, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 20.3, | |
| "learning_rate": 1.7396184062850733e-05, | |
| "loss": 0.1996, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 20.6, | |
| "learning_rate": 1.6835016835016837e-05, | |
| "loss": 0.1968, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 20.9, | |
| "learning_rate": 1.627384960718294e-05, | |
| "loss": 0.1952, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.9716684155299056, | |
| "eval_f1_score": 0.9778142974527526, | |
| "eval_loss": 0.0859055444598198, | |
| "eval_precision": 0.9802306425041186, | |
| "eval_recall": 0.9754098360655737, | |
| "eval_runtime": 6.6363, | |
| "eval_samples_per_second": 143.604, | |
| "eval_steps_per_second": 1.205, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 21.19, | |
| "learning_rate": 1.571268237934905e-05, | |
| "loss": 0.2051, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 21.49, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.1927, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 21.79, | |
| "learning_rate": 1.4590347923681259e-05, | |
| "loss": 0.2068, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.968520461699895, | |
| "eval_f1_score": 0.9754500818330606, | |
| "eval_loss": 0.09068847447633743, | |
| "eval_precision": 0.9738562091503268, | |
| "eval_recall": 0.9770491803278688, | |
| "eval_runtime": 6.1893, | |
| "eval_samples_per_second": 153.975, | |
| "eval_steps_per_second": 1.293, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 22.09, | |
| "learning_rate": 1.4029180695847363e-05, | |
| "loss": 0.1957, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 22.39, | |
| "learning_rate": 1.3468013468013468e-05, | |
| "loss": 0.2021, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 22.69, | |
| "learning_rate": 1.2906846240179574e-05, | |
| "loss": 0.202, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.1914, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_accuracy": 0.9695697796432319, | |
| "eval_f1_score": 0.9762878168438266, | |
| "eval_loss": 0.08471482992172241, | |
| "eval_precision": 0.9738988580750407, | |
| "eval_recall": 0.978688524590164, | |
| "eval_runtime": 5.9499, | |
| "eval_samples_per_second": 160.172, | |
| "eval_steps_per_second": 1.345, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 23.28, | |
| "learning_rate": 1.1784511784511786e-05, | |
| "loss": 0.1937, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 23.58, | |
| "learning_rate": 1.1223344556677892e-05, | |
| "loss": 0.1876, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 23.88, | |
| "learning_rate": 1.0662177328843996e-05, | |
| "loss": 0.1961, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.968520461699895, | |
| "eval_f1_score": 0.9754500818330606, | |
| "eval_loss": 0.08703567832708359, | |
| "eval_precision": 0.9738562091503268, | |
| "eval_recall": 0.9770491803278688, | |
| "eval_runtime": 6.0627, | |
| "eval_samples_per_second": 157.191, | |
| "eval_steps_per_second": 1.32, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 24.18, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.1817, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 24.48, | |
| "learning_rate": 9.539842873176207e-06, | |
| "loss": 0.1869, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 24.78, | |
| "learning_rate": 8.978675645342311e-06, | |
| "loss": 0.1911, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.9664218258132214, | |
| "eval_f1_score": 0.9738562091503268, | |
| "eval_loss": 0.08837948739528656, | |
| "eval_precision": 0.9706840390879479, | |
| "eval_recall": 0.9770491803278688, | |
| "eval_runtime": 6.585, | |
| "eval_samples_per_second": 144.722, | |
| "eval_steps_per_second": 1.215, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 25.07, | |
| "learning_rate": 8.417508417508419e-06, | |
| "loss": 0.1904, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 25.37, | |
| "learning_rate": 7.856341189674524e-06, | |
| "loss": 0.1831, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 25.67, | |
| "learning_rate": 7.295173961840629e-06, | |
| "loss": 0.184, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 25.97, | |
| "learning_rate": 6.734006734006734e-06, | |
| "loss": 0.1961, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.968520461699895, | |
| "eval_f1_score": 0.9753694581280787, | |
| "eval_loss": 0.08696460723876953, | |
| "eval_precision": 0.9769736842105263, | |
| "eval_recall": 0.9737704918032787, | |
| "eval_runtime": 6.5592, | |
| "eval_samples_per_second": 145.293, | |
| "eval_steps_per_second": 1.22, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 26.27, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.1988, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 26.57, | |
| "learning_rate": 5.611672278338946e-06, | |
| "loss": 0.1796, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 26.87, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.1978, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.968520461699895, | |
| "eval_f1_score": 0.9754098360655737, | |
| "eval_loss": 0.08714743703603745, | |
| "eval_precision": 0.9754098360655737, | |
| "eval_recall": 0.9754098360655737, | |
| "eval_runtime": 5.8888, | |
| "eval_samples_per_second": 161.832, | |
| "eval_steps_per_second": 1.359, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 27.16, | |
| "learning_rate": 4.489337822671156e-06, | |
| "loss": 0.2099, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 27.46, | |
| "learning_rate": 3.928170594837262e-06, | |
| "loss": 0.1867, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 27.76, | |
| "learning_rate": 3.367003367003367e-06, | |
| "loss": 0.1854, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.968520461699895, | |
| "eval_f1_score": 0.9754500818330606, | |
| "eval_loss": 0.08582841604948044, | |
| "eval_precision": 0.9738562091503268, | |
| "eval_recall": 0.9770491803278688, | |
| "eval_runtime": 5.9622, | |
| "eval_samples_per_second": 159.839, | |
| "eval_steps_per_second": 1.342, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "learning_rate": 2.805836139169473e-06, | |
| "loss": 0.1931, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 28.36, | |
| "learning_rate": 2.244668911335578e-06, | |
| "loss": 0.1957, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 28.66, | |
| "learning_rate": 1.6835016835016836e-06, | |
| "loss": 0.1849, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 1.122334455667789e-06, | |
| "loss": 0.1733, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.968520461699895, | |
| "eval_f1_score": 0.9753694581280787, | |
| "eval_loss": 0.08600697666406631, | |
| "eval_precision": 0.9769736842105263, | |
| "eval_recall": 0.9737704918032787, | |
| "eval_runtime": 6.5847, | |
| "eval_samples_per_second": 144.729, | |
| "eval_steps_per_second": 1.215, | |
| "step": 971 | |
| }, | |
| { | |
| "epoch": 29.25, | |
| "learning_rate": 5.611672278338944e-07, | |
| "loss": 0.202, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 29.55, | |
| "learning_rate": 0.0, | |
| "loss": 0.1762, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 29.55, | |
| "eval_accuracy": 0.9664218258132214, | |
| "eval_f1_score": 0.9737704918032787, | |
| "eval_loss": 0.0858435109257698, | |
| "eval_precision": 0.9737704918032787, | |
| "eval_recall": 0.9737704918032787, | |
| "eval_runtime": 6.517, | |
| "eval_samples_per_second": 146.233, | |
| "eval_steps_per_second": 1.228, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 29.55, | |
| "step": 990, | |
| "total_flos": 1.1503239286004122e+18, | |
| "train_loss": 0.2626483961789295, | |
| "train_runtime": 6214.0737, | |
| "train_samples_per_second": 41.379, | |
| "train_steps_per_second": 0.159 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 990, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 1.1503239286004122e+18, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |