{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 19641,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.4597,
      "step": 6547
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8411129416071755,
      "eval_loss": 0.37129390239715576,
      "eval_runtime": 39.7582,
      "eval_samples_per_second": 137.406,
      "eval_steps_per_second": 17.179,
      "step": 6547
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.3252,
      "step": 13094
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8420281896393923,
      "eval_loss": 0.378091961145401,
      "eval_runtime": 39.5864,
      "eval_samples_per_second": 138.002,
      "eval_steps_per_second": 17.253,
      "step": 13094
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.2243,
      "step": 19641
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8438586857038257,
      "eval_loss": 0.4746157228946686,
      "eval_runtime": 39.7955,
      "eval_samples_per_second": 137.277,
      "eval_steps_per_second": 17.163,
      "step": 19641
    },
    {
      "epoch": 3.0,
      "step": 19641,
      "total_flos": 5.588217742563533e+16,
      "train_loss": 0.33642483034333476,
      "train_runtime": 6501.9071,
      "train_samples_per_second": 48.329,
      "train_steps_per_second": 3.021
    }
  ],
  "max_steps": 19641,
  "num_train_epochs": 3,
  "total_flos": 5.588217742563533e+16,
  "trial_name": null,
  "trial_params": null
}