{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2553191489361702,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0851063829787234,
      "eval_loss": 3.537301540374756,
      "eval_runtime": 0.8155,
      "eval_samples_per_second": 24.526,
      "eval_steps_per_second": 3.679,
      "step": 1
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 4.053133964538574,
      "learning_rate": 3e-05,
      "loss": 3.9013,
      "step": 3
    },
    {
      "epoch": 0.2553191489361702,
      "eval_loss": 3.498924732208252,
      "eval_runtime": 0.4147,
      "eval_samples_per_second": 48.228,
      "eval_steps_per_second": 7.234,
      "step": 3
    }
  ],
  "logging_steps": 3,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 600579369861120.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}