trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 189,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 8.61410903930664,
      "eval_runtime": 13.2143,
      "eval_samples_per_second": 3.784,
      "eval_steps_per_second": 0.53,
      "step": 63
    },
    {
      "epoch": 2.0,
      "eval_loss": 8.225358963012695,
      "eval_runtime": 11.7566,
      "eval_samples_per_second": 4.253,
      "eval_steps_per_second": 0.595,
      "step": 126
    },
    {
      "epoch": 3.0,
      "eval_loss": 8.128830909729004,
      "eval_runtime": 11.8544,
      "eval_samples_per_second": 4.218,
      "eval_steps_per_second": 0.59,
      "step": 189
    },
    {
      "epoch": 3.0,
      "step": 189,
      "total_flos": 97984512000000.0,
      "train_loss": 8.390519076554233,
      "train_runtime": 1102.7597,
      "train_samples_per_second": 1.36,
      "train_steps_per_second": 0.171
    },
    {
      "epoch": 3.0,
      "eval_loss": 8.128830909729004,
      "eval_runtime": 11.6588,
      "eval_samples_per_second": 4.289,
      "eval_steps_per_second": 0.6,
      "step": 189
    }
  ],
  "max_steps": 189,
  "num_train_epochs": 3,
  "total_flos": 97984512000000.0,
  "trial_name": null,
  "trial_params": null
}