{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.731946144430845,
  "global_step": 5500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.61,
      "learning_rate": 9.288129560420003e-05,
      "loss": 0.6366,
      "step": 500
    },
    {
      "epoch": 0.61,
      "eval_accuracy": 0.89628166395538,
      "eval_f1": 0.3185402661735773,
      "eval_loss": 0.3915744125843048,
      "eval_runtime": 10.4747,
      "eval_samples_per_second": 314.091,
      "eval_steps_per_second": 39.333,
      "step": 500
    },
    {
      "epoch": 1.22,
      "learning_rate": 8.398291510945009e-05,
      "loss": 0.3572,
      "step": 1000
    },
    {
      "epoch": 1.22,
      "eval_accuracy": 0.908552172902626,
      "eval_f1": 0.4301535570388646,
      "eval_loss": 0.3250293731689453,
      "eval_runtime": 10.4843,
      "eval_samples_per_second": 313.802,
      "eval_steps_per_second": 39.297,
      "step": 1000
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.508453461470013e-05,
      "loss": 0.2839,
      "step": 1500
    },
    {
      "epoch": 1.84,
      "eval_accuracy": 0.9177550546130606,
      "eval_f1": 0.4733065481810558,
      "eval_loss": 0.29356610774993896,
      "eval_runtime": 10.3662,
      "eval_samples_per_second": 317.379,
      "eval_steps_per_second": 39.745,
      "step": 1500
    },
    {
      "epoch": 2.45,
      "learning_rate": 6.618615411995017e-05,
      "loss": 0.2231,
      "step": 2000
    },
    {
      "epoch": 2.45,
      "eval_accuracy": 0.9202416918429003,
      "eval_f1": 0.5303373844974727,
      "eval_loss": 0.29578134417533875,
      "eval_runtime": 10.3862,
      "eval_samples_per_second": 316.768,
      "eval_steps_per_second": 39.668,
      "step": 2000
    },
    {
      "epoch": 3.06,
      "learning_rate": 5.728777362520021e-05,
      "loss": 0.1893,
      "step": 2500
    },
    {
      "epoch": 3.06,
      "eval_accuracy": 0.9223100162677202,
      "eval_f1": 0.5747956508031589,
      "eval_loss": 0.32106420397758484,
      "eval_runtime": 10.402,
      "eval_samples_per_second": 316.284,
      "eval_steps_per_second": 39.608,
      "step": 2500
    },
    {
      "epoch": 3.67,
      "learning_rate": 4.838939313045026e-05,
      "loss": 0.1372,
      "step": 3000
    },
    {
      "epoch": 3.67,
      "eval_accuracy": 0.9265628631187544,
      "eval_f1": 0.5956050840740277,
      "eval_loss": 0.2856525480747223,
      "eval_runtime": 10.4359,
      "eval_samples_per_second": 315.259,
      "eval_steps_per_second": 39.479,
      "step": 3000
    },
    {
      "epoch": 4.28,
      "learning_rate": 3.9491012635700305e-05,
      "loss": 0.1148,
      "step": 3500
    },
    {
      "epoch": 4.28,
      "eval_accuracy": 0.9301417615617011,
      "eval_f1": 0.6182402434709684,
      "eval_loss": 0.2969909608364105,
      "eval_runtime": 10.3712,
      "eval_samples_per_second": 317.225,
      "eval_steps_per_second": 39.725,
      "step": 3500
    },
    {
      "epoch": 4.9,
      "learning_rate": 3.059263214095035e-05,
      "loss": 0.092,
      "step": 4000
    },
    {
      "epoch": 4.9,
      "eval_accuracy": 0.932396002788752,
      "eval_f1": 0.6418559187952009,
      "eval_loss": 0.28680795431137085,
      "eval_runtime": 10.3835,
      "eval_samples_per_second": 316.85,
      "eval_steps_per_second": 39.678,
      "step": 4000
    },
    {
      "epoch": 5.51,
      "learning_rate": 2.169425164620039e-05,
      "loss": 0.0585,
      "step": 4500
    },
    {
      "epoch": 5.51,
      "eval_accuracy": 0.932419242389031,
      "eval_f1": 0.6322022976473333,
      "eval_loss": 0.30797600746154785,
      "eval_runtime": 10.3681,
      "eval_samples_per_second": 317.319,
      "eval_steps_per_second": 39.737,
      "step": 4500
    },
    {
      "epoch": 6.12,
      "learning_rate": 1.2795871151450436e-05,
      "loss": 0.0492,
      "step": 5000
    },
    {
      "epoch": 6.12,
      "eval_accuracy": 0.9329769927957239,
      "eval_f1": 0.6370967443537814,
      "eval_loss": 0.31786486506462097,
      "eval_runtime": 10.4041,
      "eval_samples_per_second": 316.22,
      "eval_steps_per_second": 39.6,
      "step": 5000
    },
    {
      "epoch": 6.73,
      "learning_rate": 3.897490656700481e-06,
      "loss": 0.0295,
      "step": 5500
    },
    {
      "epoch": 6.73,
      "eval_accuracy": 0.934278410411341,
      "eval_f1": 0.6499060895478286,
      "eval_loss": 0.3314834535121918,
      "eval_runtime": 10.3769,
      "eval_samples_per_second": 317.051,
      "eval_steps_per_second": 39.704,
      "step": 5500
    }
  ],
  "max_steps": 5719,
  "num_train_epochs": 7,
  "total_flos": 1.1503917613056e+16,
  "trial_name": null,
  "trial_params": null
}