{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 804,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "learning_rate": 1.8756218905472638e-05,
      "loss": 0.6236,
      "step": 50
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.7512437810945274e-05,
      "loss": 0.6036,
      "step": 100
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.626865671641791e-05,
      "loss": 0.6254,
      "step": 150
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.5024875621890549e-05,
      "loss": 0.6065,
      "step": 200
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.3781094527363185e-05,
      "loss": 0.6068,
      "step": 250
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.2537313432835823e-05,
      "loss": 0.6043,
      "step": 300
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.129353233830846e-05,
      "loss": 0.6125,
      "step": 350
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.0049751243781096e-05,
      "loss": 0.6024,
      "step": 400
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.805970149253732e-06,
      "loss": 0.6011,
      "step": 450
    },
    {
      "epoch": 1.87,
      "learning_rate": 7.5621890547263685e-06,
      "loss": 0.6099,
      "step": 500
    },
    {
      "epoch": 1.87,
      "eval_loss": 0.6054543852806091,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.6224,
      "eval_samples_per_second": 1675.875,
      "eval_steps_per_second": 106.048,
      "step": 500
    },
    {
      "epoch": 2.05,
      "learning_rate": 6.318407960199006e-06,
      "loss": 0.5897,
      "step": 550
    },
    {
      "epoch": 2.24,
      "learning_rate": 5.074626865671642e-06,
      "loss": 0.5986,
      "step": 600
    },
    {
      "epoch": 2.43,
      "learning_rate": 3.8308457711442784e-06,
      "loss": 0.5629,
      "step": 650
    },
    {
      "epoch": 2.61,
      "learning_rate": 2.5870646766169156e-06,
      "loss": 0.5535,
      "step": 700
    },
    {
      "epoch": 2.8,
      "learning_rate": 1.3432835820895524e-06,
      "loss": 0.5783,
      "step": 750
    },
    {
      "epoch": 2.99,
      "learning_rate": 9.950248756218906e-08,
      "loss": 0.5564,
      "step": 800
    },
    {
      "epoch": 3.0,
      "step": 804,
      "total_flos": 387639667862280.0,
      "train_loss": 0.5957831627693936,
      "train_runtime": 68.8413,
      "train_samples_per_second": 372.64,
      "train_steps_per_second": 11.679
    }
  ],
  "logging_steps": 50,
  "max_steps": 804,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 387639667862280.0,
  "trial_name": null,
  "trial_params": null
}