{
  "best_metric": 0.5393258426966292,
  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-masakhaner-luo/checkpoint-3000",
  "epoch": 190.47619047619048,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.52,
      "eval_accuracy_score": 0.8869188337273444,
      "eval_f1": 0.3120204603580563,
      "eval_loss": 0.47248074412345886,
      "eval_precision": 0.31443298969072164,
      "eval_recall": 0.3096446700507614,
      "eval_runtime": 0.7192,
      "eval_samples_per_second": 127.926,
      "eval_steps_per_second": 16.686,
      "step": 200
    },
    {
      "epoch": 19.05,
      "eval_accuracy_score": 0.9109535066981875,
      "eval_f1": 0.44504021447721176,
      "eval_loss": 0.478135347366333,
      "eval_precision": 0.4715909090909091,
      "eval_recall": 0.4213197969543147,
      "eval_runtime": 0.7178,
      "eval_samples_per_second": 128.163,
      "eval_steps_per_second": 16.717,
      "step": 400
    },
    {
      "epoch": 23.81,
      "learning_rate": 4.865771812080537e-05,
      "loss": 0.2981,
      "step": 500
    },
    {
      "epoch": 28.57,
      "eval_accuracy_score": 0.9070133963750985,
      "eval_f1": 0.4329896907216495,
      "eval_loss": 0.5391231179237366,
      "eval_precision": 0.4397905759162304,
      "eval_recall": 0.4263959390862944,
      "eval_runtime": 0.7173,
      "eval_samples_per_second": 128.251,
      "eval_steps_per_second": 16.728,
      "step": 600
    },
    {
      "epoch": 38.1,
      "eval_accuracy_score": 0.9093774625689519,
      "eval_f1": 0.46808510638297873,
      "eval_loss": 0.5991037487983704,
      "eval_precision": 0.49162011173184356,
      "eval_recall": 0.4467005076142132,
      "eval_runtime": 0.7178,
      "eval_samples_per_second": 128.167,
      "eval_steps_per_second": 16.717,
      "step": 800
    },
    {
      "epoch": 47.62,
      "learning_rate": 4.697986577181208e-05,
      "loss": 0.014,
      "step": 1000
    },
    {
      "epoch": 47.62,
      "eval_accuracy_score": 0.9180457052797478,
      "eval_f1": 0.5203252032520326,
      "eval_loss": 0.5821110606193542,
      "eval_precision": 0.5581395348837209,
      "eval_recall": 0.4873096446700508,
      "eval_runtime": 0.7157,
      "eval_samples_per_second": 128.547,
      "eval_steps_per_second": 16.767,
      "step": 1000
    },
    {
      "epoch": 57.14,
      "eval_accuracy_score": 0.9137115839243499,
      "eval_f1": 0.48066298342541436,
      "eval_loss": 0.6444269418716431,
      "eval_precision": 0.5272727272727272,
      "eval_recall": 0.4416243654822335,
      "eval_runtime": 0.7171,
      "eval_samples_per_second": 128.297,
      "eval_steps_per_second": 16.734,
      "step": 1200
    },
    {
      "epoch": 66.67,
      "eval_accuracy_score": 0.9188337273443656,
      "eval_f1": 0.5168539325842697,
      "eval_loss": 0.6572203636169434,
      "eval_precision": 0.5786163522012578,
      "eval_recall": 0.467005076142132,
      "eval_runtime": 0.717,
      "eval_samples_per_second": 128.321,
      "eval_steps_per_second": 16.737,
      "step": 1400
    },
    {
      "epoch": 71.43,
      "learning_rate": 4.530201342281879e-05,
      "loss": 0.0052,
      "step": 1500
    },
    {
      "epoch": 76.19,
      "eval_accuracy_score": 0.91725768321513,
      "eval_f1": 0.49572649572649574,
      "eval_loss": 0.6961527466773987,
      "eval_precision": 0.564935064935065,
      "eval_recall": 0.4416243654822335,
      "eval_runtime": 0.717,
      "eval_samples_per_second": 128.32,
      "eval_steps_per_second": 16.737,
      "step": 1600
    },
    {
      "epoch": 85.71,
      "eval_accuracy_score": 0.9184397163120568,
      "eval_f1": 0.5449438202247191,
      "eval_loss": 0.6793113946914673,
      "eval_precision": 0.610062893081761,
      "eval_recall": 0.49238578680203043,
      "eval_runtime": 0.7177,
      "eval_samples_per_second": 128.191,
      "eval_steps_per_second": 16.721,
      "step": 1800
    },
    {
      "epoch": 95.24,
      "learning_rate": 4.36241610738255e-05,
      "loss": 0.0032,
      "step": 2000
    },
    {
      "epoch": 95.24,
      "eval_accuracy_score": 0.9117415287628053,
      "eval_f1": 0.5128205128205129,
      "eval_loss": 0.6560418605804443,
      "eval_precision": 0.5181347150259067,
      "eval_recall": 0.5076142131979695,
      "eval_runtime": 0.7165,
      "eval_samples_per_second": 128.402,
      "eval_steps_per_second": 16.748,
      "step": 2000
    },
    {
      "epoch": 104.76,
      "eval_accuracy_score": 0.9160756501182034,
      "eval_f1": 0.5078534031413612,
      "eval_loss": 0.6600853204727173,
      "eval_precision": 0.5243243243243243,
      "eval_recall": 0.49238578680203043,
      "eval_runtime": 0.7195,
      "eval_samples_per_second": 127.871,
      "eval_steps_per_second": 16.679,
      "step": 2200
    },
    {
      "epoch": 114.29,
      "eval_accuracy_score": 0.9204097714736013,
      "eval_f1": 0.5561797752808989,
      "eval_loss": 0.6852244734764099,
      "eval_precision": 0.6226415094339622,
      "eval_recall": 0.5025380710659898,
      "eval_runtime": 0.7198,
      "eval_samples_per_second": 127.819,
      "eval_steps_per_second": 16.672,
      "step": 2400
    },
    {
      "epoch": 119.05,
      "learning_rate": 4.194630872483222e-05,
      "loss": 0.0033,
      "step": 2500
    },
    {
      "epoch": 123.81,
      "eval_accuracy_score": 0.9188337273443656,
      "eval_f1": 0.4918032786885246,
      "eval_loss": 0.6922882199287415,
      "eval_precision": 0.5325443786982249,
      "eval_recall": 0.45685279187817257,
      "eval_runtime": 0.7172,
      "eval_samples_per_second": 128.274,
      "eval_steps_per_second": 16.731,
      "step": 2600
    },
    {
      "epoch": 133.33,
      "eval_accuracy_score": 0.9196217494089834,
      "eval_f1": 0.5494505494505494,
      "eval_loss": 0.692544162273407,
      "eval_precision": 0.5988023952095808,
      "eval_recall": 0.5076142131979695,
      "eval_runtime": 0.7167,
      "eval_samples_per_second": 128.357,
      "eval_steps_per_second": 16.742,
      "step": 2800
    },
    {
      "epoch": 142.86,
      "learning_rate": 4.026845637583892e-05,
      "loss": 0.0016,
      "step": 3000
    },
    {
      "epoch": 142.86,
      "eval_accuracy_score": 0.9196217494089834,
      "eval_f1": 0.5393258426966292,
      "eval_loss": 0.7244275808334351,
      "eval_precision": 0.6037735849056604,
      "eval_recall": 0.4873096446700508,
      "eval_runtime": 0.7173,
      "eval_samples_per_second": 128.256,
      "eval_steps_per_second": 16.729,
      "step": 3000
    },
    {
      "epoch": 152.38,
      "eval_accuracy_score": 0.9180457052797478,
      "eval_f1": 0.5354330708661418,
      "eval_loss": 0.7083867192268372,
      "eval_precision": 0.5543478260869565,
      "eval_recall": 0.5177664974619289,
      "eval_runtime": 0.7181,
      "eval_samples_per_second": 128.118,
      "eval_steps_per_second": 16.711,
      "step": 3200
    },
    {
      "epoch": 161.9,
      "eval_accuracy_score": 0.917651694247439,
      "eval_f1": 0.5136612021857923,
      "eval_loss": 0.7186570167541504,
      "eval_precision": 0.5562130177514792,
      "eval_recall": 0.47715736040609136,
      "eval_runtime": 0.7195,
      "eval_samples_per_second": 127.874,
      "eval_steps_per_second": 16.679,
      "step": 3400
    },
    {
      "epoch": 166.67,
      "learning_rate": 3.859060402684564e-05,
      "loss": 0.0023,
      "step": 3500
    },
    {
      "epoch": 171.43,
      "eval_accuracy_score": 0.91725768321513,
      "eval_f1": 0.4947916666666667,
      "eval_loss": 0.6916423439979553,
      "eval_precision": 0.5080213903743316,
      "eval_recall": 0.48223350253807107,
      "eval_runtime": 0.7175,
      "eval_samples_per_second": 128.22,
      "eval_steps_per_second": 16.724,
      "step": 3600
    },
    {
      "epoch": 180.95,
      "eval_accuracy_score": 0.91725768321513,
      "eval_f1": 0.5376344086021505,
      "eval_loss": 0.7268627882003784,
      "eval_precision": 0.5714285714285714,
      "eval_recall": 0.5076142131979695,
      "eval_runtime": 0.7169,
      "eval_samples_per_second": 128.321,
      "eval_steps_per_second": 16.738,
      "step": 3800
    },
    {
      "epoch": 190.48,
      "learning_rate": 3.6912751677852356e-05,
      "loss": 0.0023,
      "step": 4000
    },
    {
      "epoch": 190.48,
      "eval_accuracy_score": 0.9156816390858944,
      "eval_f1": 0.528,
      "eval_loss": 0.7125107049942017,
      "eval_precision": 0.5561797752808989,
      "eval_recall": 0.5025380710659898,
      "eval_runtime": 0.7164,
      "eval_samples_per_second": 128.423,
      "eval_steps_per_second": 16.751,
      "step": 4000
    },
    {
      "epoch": 190.48,
      "step": 4000,
      "total_flos": 2.014607440594944e+16,
      "train_loss": 0.04124551719427109,
      "train_runtime": 1894.3661,
      "train_samples_per_second": 253.383,
      "train_steps_per_second": 7.918
    }
  ],
  "max_steps": 15000,
  "num_train_epochs": 715,
  "total_flos": 2.014607440594944e+16,
  "trial_name": null,
  "trial_params": null
}