{
  "best_metric": 0.012786287814378738,
  "best_model_checkpoint": "convnext-tiny-224-finetuned-barkley\\checkpoint-1102",
  "epoch": 30.0,
  "eval_steps": 500,
  "global_step": 1140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "train_accuracy": 0.2138157894736842
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.7230629920959473,
      "learning_rate": 8.365843306988109e-07,
      "loss": 1.6288,
      "step": 38
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2371292106586224,
      "eval_error_rate": 0.7628707893413775,
      "eval_f1": 0.20430842832369756,
      "eval_loss": 1.6004831790924072,
      "eval_precision": 0.2132792246940375,
      "eval_recall": 0.26973684210526316,
      "eval_runtime": 41.666,
      "eval_samples_per_second": 3.648,
      "eval_steps_per_second": 0.456,
      "eval_top1_accuracy": 0.26973684210526316,
      "step": 38
    },
    {
      "epoch": 2.0,
      "train_accuracy": 0.25
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.8333628177642822,
      "learning_rate": 9.460584867009364e-07,
      "loss": 1.6059,
      "step": 76
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.24728506787330323,
      "eval_error_rate": 0.7527149321266968,
      "eval_f1": 0.2243479907737179,
      "eval_loss": 1.5801552534103394,
      "eval_precision": 0.2383676582761251,
      "eval_recall": 0.27631578947368424,
      "eval_runtime": 40.3741,
      "eval_samples_per_second": 3.765,
      "eval_steps_per_second": 0.471,
      "eval_top1_accuracy": 0.27631578947368424,
      "step": 76
    },
    {
      "epoch": 3.0,
      "train_accuracy": 0.2894736842105263
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.8583333492279053,
      "learning_rate": 1.1275880849384341e-06,
      "loss": 1.5808,
      "step": 114
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2744343891402715,
      "eval_error_rate": 0.7255656108597285,
      "eval_f1": 0.25945030547058157,
      "eval_loss": 1.5570068359375,
      "eval_precision": 0.2778035204289794,
      "eval_recall": 0.3026315789473684,
      "eval_runtime": 25.2172,
      "eval_samples_per_second": 6.028,
      "eval_steps_per_second": 0.753,
      "eval_top1_accuracy": 0.3026315789473684,
      "step": 114
    },
    {
      "epoch": 4.0,
      "train_accuracy": 0.32383040935672514
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.166118860244751,
      "learning_rate": 1.3797895548168056e-06,
      "loss": 1.5555,
      "step": 152
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3510859728506787,
      "eval_error_rate": 0.6489140271493212,
      "eval_f1": 0.3490548373858623,
      "eval_loss": 1.5290976762771606,
      "eval_precision": 0.3831372574793627,
      "eval_recall": 0.375,
      "eval_runtime": 28.1947,
      "eval_samples_per_second": 5.391,
      "eval_steps_per_second": 0.674,
      "eval_top1_accuracy": 0.375,
      "step": 152
    },
    {
      "epoch": 5.0,
      "train_accuracy": 0.38742690058479534
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.677858591079712,
      "learning_rate": 1.7007406834242322e-06,
      "loss": 1.5232,
      "step": 190
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.41472599296128704,
      "eval_error_rate": 0.585274007038713,
      "eval_f1": 0.41544045031957555,
      "eval_loss": 1.4932990074157715,
      "eval_precision": 0.4251577933805101,
      "eval_recall": 0.4407894736842105,
      "eval_runtime": 25.5314,
      "eval_samples_per_second": 5.953,
      "eval_steps_per_second": 0.744,
      "eval_top1_accuracy": 0.4407894736842105,
      "step": 190
    },
    {
      "epoch": 6.0,
      "train_accuracy": 0.47076023391812866
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.4222543239593506,
      "learning_rate": 2.087995266130065e-06,
      "loss": 1.4784,
      "step": 228
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.49721468074409253,
      "eval_error_rate": 0.5027853192559075,
      "eval_f1": 0.4925881060058483,
      "eval_loss": 1.4484349489212036,
      "eval_precision": 0.5076020884114232,
      "eval_recall": 0.5197368421052632,
      "eval_runtime": 56.6448,
      "eval_samples_per_second": 2.683,
      "eval_steps_per_second": 0.335,
      "eval_top1_accuracy": 0.5197368421052632,
      "step": 228
    },
    {
      "epoch": 7.0,
      "train_accuracy": 0.5701754385964912
    },
    {
      "epoch": 7.0,
      "grad_norm": 3.0168983936309814,
      "learning_rate": 2.5386017509096417e-06,
      "loss": 1.4242,
      "step": 266
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6248768225238813,
      "eval_error_rate": 0.3751231774761187,
      "eval_f1": 0.6307132735050356,
      "eval_loss": 1.390175223350525,
      "eval_precision": 0.6856800923548139,
      "eval_recall": 0.6381578947368421,
      "eval_runtime": 59.0359,
      "eval_samples_per_second": 2.575,
      "eval_steps_per_second": 0.322,
      "eval_top1_accuracy": 0.6381578947368421,
      "step": 266
    },
    {
      "epoch": 8.0,
      "train_accuracy": 0.6498538011695907
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.808101177215576,
      "learning_rate": 3.049125734293339e-06,
      "loss": 1.3586,
      "step": 304
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7134087481146305,
      "eval_error_rate": 0.2865912518853695,
      "eval_f1": 0.7165677244674166,
      "eval_loss": 1.318568229675293,
      "eval_precision": 0.7728468899521532,
      "eval_recall": 0.7171052631578947,
      "eval_runtime": 55.4154,
      "eval_samples_per_second": 2.743,
      "eval_steps_per_second": 0.343,
      "eval_top1_accuracy": 0.7171052631578947,
      "step": 304
    },
    {
      "epoch": 9.0,
      "train_accuracy": 0.7149122807017544
    },
    {
      "epoch": 9.0,
      "grad_norm": 2.8706772327423096,
      "learning_rate": 3.6156761374816205e-06,
      "loss": 1.276,
      "step": 342
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.805972850678733,
      "eval_error_rate": 0.19402714932126697,
      "eval_f1": 0.8108964691671459,
      "eval_loss": 1.223597526550293,
      "eval_precision": 0.8547017577806745,
      "eval_recall": 0.8026315789473685,
      "eval_runtime": 55.5305,
      "eval_samples_per_second": 2.737,
      "eval_steps_per_second": 0.342,
      "eval_top1_accuracy": 0.8026315789473685,
      "step": 342
    },
    {
      "epoch": 10.0,
      "train_accuracy": 0.8033625730994152
    },
    {
      "epoch": 10.0,
      "grad_norm": 3.2001399993896484,
      "learning_rate": 4.233934863118696e-06,
      "loss": 1.1778,
      "step": 380
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8600754147812971,
      "eval_error_rate": 0.13992458521870288,
      "eval_f1": 0.8609113468479812,
      "eval_loss": 1.1122019290924072,
      "eval_precision": 0.8898553355968974,
      "eval_recall": 0.8552631578947368,
      "eval_runtime": 53.869,
      "eval_samples_per_second": 2.822,
      "eval_steps_per_second": 0.353,
      "eval_top1_accuracy": 0.8552631578947368,
      "step": 380
    },
    {
      "epoch": 11.0,
      "train_accuracy": 0.868421052631579
    },
    {
      "epoch": 11.0,
      "grad_norm": 3.1884777545928955,
      "learning_rate": 4.899189706688707e-06,
      "loss": 1.0543,
      "step": 418
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.9004725992961287,
      "eval_error_rate": 0.09952740070387134,
      "eval_f1": 0.8958336111023342,
      "eval_loss": 0.9839252829551697,
      "eval_precision": 0.9063624095203042,
      "eval_recall": 0.8947368421052632,
      "eval_runtime": 54.1079,
      "eval_samples_per_second": 2.809,
      "eval_steps_per_second": 0.351,
      "eval_top1_accuracy": 0.8947368421052632,
      "step": 418
    },
    {
      "epoch": 12.0,
      "train_accuracy": 0.902046783625731
    },
    {
      "epoch": 12.0,
      "grad_norm": 3.692692279815674,
      "learning_rate": 5.6063702716924525e-06,
      "loss": 0.921,
      "step": 456
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9575364504776269,
      "eval_error_rate": 0.04246354952237308,
      "eval_f1": 0.9537314326645565,
      "eval_loss": 0.8418065309524536,
      "eval_precision": 0.9540851522650184,
      "eval_recall": 0.9539473684210527,
      "eval_runtime": 54.166,
      "eval_samples_per_second": 2.806,
      "eval_steps_per_second": 0.351,
      "eval_top1_accuracy": 0.9539473684210527,
      "step": 456
    },
    {
      "epoch": 13.0,
      "train_accuracy": 0.9371345029239766
    },
    {
      "epoch": 13.0,
      "grad_norm": 3.067211389541626,
      "learning_rate": 6.350086614868708e-06,
      "loss": 0.773,
      "step": 494
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9652287581699346,
      "eval_error_rate": 0.034771241830065414,
      "eval_f1": 0.9604621710987601,
      "eval_loss": 0.6935167908668518,
      "eval_precision": 0.9623944201691405,
      "eval_recall": 0.9605263157894737,
      "eval_runtime": 67.8683,
      "eval_samples_per_second": 2.24,
      "eval_steps_per_second": 0.28,
      "eval_top1_accuracy": 0.9605263157894737,
      "step": 494
    },
    {
      "epoch": 14.0,
      "train_accuracy": 0.9576023391812866
    },
    {
      "epoch": 14.0,
      "grad_norm": 2.8400356769561768,
      "learning_rate": 7.124670326916465e-06,
      "loss": 0.6204,
      "step": 532
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.9707843137254901,
      "eval_error_rate": 0.029215686274509878,
      "eval_f1": 0.96721850419808,
      "eval_loss": 0.5515281558036804,
      "eval_precision": 0.9687600085406214,
      "eval_recall": 0.9671052631578947,
      "eval_runtime": 75.408,
      "eval_samples_per_second": 2.016,
      "eval_steps_per_second": 0.252,
      "eval_top1_accuracy": 0.9671052631578947,
      "step": 532
    },
    {
      "epoch": 15.0,
      "train_accuracy": 0.9707602339181286
    },
    {
      "epoch": 15.0,
      "grad_norm": 2.3800432682037354,
      "learning_rate": 7.924217735611663e-06,
      "loss": 0.4835,
      "step": 570
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.9696732026143791,
      "eval_error_rate": 0.03032679738562094,
      "eval_f1": 0.9676301640599072,
      "eval_loss": 0.4145788848400116,
      "eval_precision": 0.9704260651629072,
      "eval_recall": 0.9671052631578947,
      "eval_runtime": 43.8505,
      "eval_samples_per_second": 3.466,
      "eval_steps_per_second": 0.433,
      "eval_top1_accuracy": 0.9671052631578947,
      "step": 570
    },
    {
      "epoch": 16.0,
      "train_accuracy": 0.9736842105263158
    },
    {
      "epoch": 16.0,
      "grad_norm": 3.108427047729492,
      "learning_rate": 8.742634902035743e-06,
      "loss": 0.3641,
      "step": 608
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.9830065359477125,
      "eval_error_rate": 0.01699346405228752,
      "eval_f1": 0.980191060766086,
      "eval_loss": 0.3042638599872589,
      "eval_precision": 0.9805310767959324,
      "eval_recall": 0.9802631578947368,
      "eval_runtime": 32.0995,
      "eval_samples_per_second": 4.735,
      "eval_steps_per_second": 0.592,
      "eval_top1_accuracy": 0.9802631578947368,
      "step": 608
    },
    {
      "epoch": 17.0,
      "train_accuracy": 0.9788011695906432
    },
    {
      "epoch": 17.0,
      "grad_norm": 2.5407485961914062,
      "learning_rate": 9.573684066966612e-06,
      "loss": 0.2706,
      "step": 646
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.9830065359477125,
      "eval_error_rate": 0.01699346405228752,
      "eval_f1": 0.980191060766086,
      "eval_loss": 0.22474148869514465,
      "eval_precision": 0.9805310767959324,
      "eval_recall": 0.9802631578947368,
      "eval_runtime": 44.9328,
      "eval_samples_per_second": 3.383,
      "eval_steps_per_second": 0.423,
      "eval_top1_accuracy": 0.9802631578947368,
      "step": 646
    },
    {
      "epoch": 18.0,
      "train_accuracy": 0.9817251461988304
    },
    {
      "epoch": 18.0,
      "grad_norm": 3.097386598587036,
      "learning_rate": 1.0411031193429937e-05,
      "loss": 0.1998,
      "step": 684
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.9888888888888889,
      "eval_error_rate": 0.011111111111111072,
      "eval_f1": 0.9867701266776593,
      "eval_loss": 0.17049287259578705,
      "eval_precision": 0.9872979940891655,
      "eval_recall": 0.9868421052631579,
      "eval_runtime": 39.0056,
      "eval_samples_per_second": 3.897,
      "eval_steps_per_second": 0.487,
      "eval_top1_accuracy": 0.9868421052631579,
      "step": 684
    },
    {
      "epoch": 19.0,
      "train_accuracy": 0.9890350877192983
    },
    {
      "epoch": 19.0,
      "grad_norm": 2.5862479209899902,
      "learning_rate": 1.1248294243054004e-05,
      "loss": 0.1446,
      "step": 722
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.9944444444444445,
      "eval_error_rate": 0.005555555555555536,
      "eval_f1": 0.99343678755752,
      "eval_loss": 0.12706294655799866,
      "eval_precision": 0.9936647173489279,
      "eval_recall": 0.993421052631579,
      "eval_runtime": 35.4207,
      "eval_samples_per_second": 4.291,
      "eval_steps_per_second": 0.536,
      "eval_top1_accuracy": 0.993421052631579,
      "step": 722
    },
    {
      "epoch": 20.0,
      "train_accuracy": 0.9897660818713451
    },
    {
      "epoch": 20.0,
      "grad_norm": 4.520482540130615,
      "learning_rate": 1.2079091818278531e-05,
      "loss": 0.1106,
      "step": 760
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.9888888888888889,
      "eval_error_rate": 0.011111111111111072,
      "eval_f1": 0.9867701266776593,
      "eval_loss": 0.1046518012881279,
      "eval_precision": 0.9872979940891655,
      "eval_recall": 0.9868421052631579,
      "eval_runtime": 41.2892,
      "eval_samples_per_second": 3.681,
      "eval_steps_per_second": 0.46,
      "eval_top1_accuracy": 0.9868421052631579,
      "step": 760
    },
    {
      "epoch": 21.0,
      "train_accuracy": 0.9883040935672515
    },
    {
      "epoch": 21.0,
      "grad_norm": 9.188246726989746,
      "learning_rate": 1.2897091799679402e-05,
      "loss": 0.0872,
      "step": 798
    },
    {
      "epoch": 21.0,
      "eval_accuracy": 0.9944444444444445,
      "eval_error_rate": 0.005555555555555536,
      "eval_f1": 0.99343678755752,
      "eval_loss": 0.0779847577214241,
      "eval_precision": 0.9936647173489279,
      "eval_recall": 0.993421052631579,
      "eval_runtime": 68.0671,
      "eval_samples_per_second": 2.233,
      "eval_steps_per_second": 0.279,
      "eval_top1_accuracy": 0.993421052631579,
      "step": 798
    },
    {
      "epoch": 22.0,
      "train_accuracy": 0.993421052631579
    },
    {
      "epoch": 22.0,
      "grad_norm": 1.4848785400390625,
      "learning_rate": 1.3696059607708444e-05,
      "loss": 0.0614,
      "step": 836
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.9888888888888889,
      "eval_error_rate": 0.011111111111111072,
      "eval_f1": 0.9867701266776593,
      "eval_loss": 0.07387673109769821,
      "eval_precision": 0.9872979940891655,
      "eval_recall": 0.9868421052631579,
      "eval_runtime": 57.9913,
      "eval_samples_per_second": 2.621,
      "eval_steps_per_second": 0.328,
      "eval_top1_accuracy": 0.9868421052631579,
      "step": 836
    },
    {
      "epoch": 23.0,
      "train_accuracy": 0.9948830409356725
    },
    {
      "epoch": 23.0,
      "grad_norm": 0.7044534683227539,
      "learning_rate": 1.4469905721010107e-05,
      "loss": 0.0491,
      "step": 874
    },
    {
      "epoch": 23.0,
      "eval_accuracy": 0.9944444444444445,
      "eval_error_rate": 0.005555555555555536,
      "eval_f1": 0.99343678755752,
      "eval_loss": 0.05167735368013382,
      "eval_precision": 0.9936647173489279,
      "eval_recall": 0.993421052631579,
      "eval_runtime": 43.1178,
      "eval_samples_per_second": 3.525,
      "eval_steps_per_second": 0.441,
      "eval_top1_accuracy": 0.993421052631579,
      "step": 874
    },
    {
      "epoch": 24.0,
      "train_accuracy": 0.9956140350877193
    },
    {
      "epoch": 24.0,
      "grad_norm": 4.517460346221924,
      "learning_rate": 1.5212732089142938e-05,
      "loss": 0.0365,
      "step": 912
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.9877777777777779,
      "eval_error_rate": 0.012222222222222134,
      "eval_f1": 0.9868484170131115,
      "eval_loss": 0.04010358452796936,
      "eval_precision": 0.9870857699805068,
      "eval_recall": 0.9868421052631579,
      "eval_runtime": 37.7666,
      "eval_samples_per_second": 4.025,
      "eval_steps_per_second": 0.503,
      "eval_top1_accuracy": 0.9868421052631579,
      "step": 912
    },
    {
      "epoch": 25.0,
      "train_accuracy": 0.9956140350877193
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.25067076086997986,
      "learning_rate": 1.590081029331129e-05,
      "loss": 0.0255,
      "step": 950
    },
    {
      "epoch": 25.0,
      "eval_accuracy": 0.9944444444444445,
      "eval_error_rate": 0.005555555555555536,
      "eval_f1": 0.99343678755752,
      "eval_loss": 0.033598948270082474,
      "eval_precision": 0.9936647173489279,
      "eval_recall": 0.993421052631579,
      "eval_runtime": 41.2598,
      "eval_samples_per_second": 3.684,
      "eval_steps_per_second": 0.46,
      "eval_top1_accuracy": 0.993421052631579,
      "step": 950
    },
    {
      "epoch": 26.0,
      "train_accuracy": 0.9963450292397661
    },
    {
      "epoch": 26.0,
      "grad_norm": 3.2572007179260254,
      "learning_rate": 1.65660651368813e-05,
      "loss": 0.0212,
      "step": 988
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.9888888888888889,
      "eval_error_rate": 0.011111111111111072,
      "eval_f1": 0.9867701266776593,
      "eval_loss": 0.037725575268268585,
      "eval_precision": 0.9872979940891655,
      "eval_recall": 0.9868421052631579,
      "eval_runtime": 39.6757,
      "eval_samples_per_second": 3.831,
      "eval_steps_per_second": 0.479,
      "eval_top1_accuracy": 0.9868421052631579,
      "step": 988
    },
    {
      "epoch": 27.0,
      "train_accuracy": 0.9956140350877193
    },
    {
      "epoch": 27.0,
      "grad_norm": 0.9294455051422119,
      "learning_rate": 1.7184323862518377e-05,
      "loss": 0.0175,
      "step": 1026
    },
    {
      "epoch": 27.0,
      "eval_accuracy": 0.9944444444444445,
      "eval_error_rate": 0.005555555555555536,
      "eval_f1": 0.99343678755752,
      "eval_loss": 0.019463175907731056,
      "eval_precision": 0.9936647173489279,
      "eval_recall": 0.993421052631579,
      "eval_runtime": 41.079,
      "eval_samples_per_second": 3.7,
      "eval_steps_per_second": 0.463,
      "eval_top1_accuracy": 0.993421052631579,
      "step": 1026
    },
    {
      "epoch": 28.0,
      "train_accuracy": 0.9978070175438597
    },
    {
      "epoch": 28.0,
      "grad_norm": 3.1146209239959717,
      "learning_rate": 1.775087426570666e-05,
      "loss": 0.0125,
      "step": 1064
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.9933333333333334,
      "eval_error_rate": 0.006666666666666599,
      "eval_f1": 0.9934103601236665,
      "eval_loss": 0.02142958901822567,
      "eval_precision": 0.9935988620199147,
      "eval_recall": 0.993421052631579,
      "eval_runtime": 71.7993,
      "eval_samples_per_second": 2.117,
      "eval_steps_per_second": 0.265,
      "eval_top1_accuracy": 0.993421052631579,
      "step": 1064
    },
    {
      "epoch": 29.0,
      "train_accuracy": 0.9948830409356725
    },
    {
      "epoch": 29.0,
      "grad_norm": 0.6761703491210938,
      "learning_rate": 1.826139824909036e-05,
      "loss": 0.0155,
      "step": 1102
    },
    {
      "epoch": 29.0,
      "eval_accuracy": 1.0,
      "eval_error_rate": 0.0,
      "eval_f1": 1.0,
      "eval_loss": 0.012786287814378738,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 70.5861,
      "eval_samples_per_second": 2.153,
      "eval_steps_per_second": 0.269,
      "eval_top1_accuracy": 1.0,
      "step": 1102
    },
    {
      "epoch": 30.0,
      "train_accuracy": 0.9985380116959064
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.24630075693130493,
      "learning_rate": 1.8712004733869936e-05,
      "loss": 0.0104,
      "step": 1140
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.9944444444444445,
      "eval_error_rate": 0.005555555555555536,
      "eval_f1": 0.99343678755752,
      "eval_loss": 0.0159451961517334,
      "eval_precision": 0.9936647173489279,
      "eval_recall": 0.993421052631579,
      "eval_runtime": 68.8635,
      "eval_samples_per_second": 2.207,
      "eval_steps_per_second": 0.276,
      "eval_top1_accuracy": 0.993421052631579,
      "step": 1140
    },
    {
      "epoch": 30.0,
      "step": 1140,
      "total_flos": 9.167322602550067e+17,
      "train_loss": 0.6629255272840199,
      "train_runtime": 13519.4546,
      "train_samples_per_second": 2.698,
      "train_steps_per_second": 0.084
    }
  ],
  "logging_steps": 10,
  "max_steps": 1140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.167322602550067e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}