{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005020206330480182,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010040412660960366,
      "grad_norm": 0.5369173288345337,
      "learning_rate": 1e-05,
      "loss": 1.551,
      "step": 1
    },
    {
      "epoch": 0.00010040412660960366,
      "eval_loss": 3.6199207305908203,
      "eval_runtime": 1267.7139,
      "eval_samples_per_second": 13.232,
      "eval_steps_per_second": 6.617,
      "step": 1
    },
    {
      "epoch": 0.0002008082532192073,
      "grad_norm": 0.4612913131713867,
      "learning_rate": 2e-05,
      "loss": 1.3669,
      "step": 2
    },
    {
      "epoch": 0.0002008082532192073,
      "eval_loss": 3.5390496253967285,
      "eval_runtime": 1202.0092,
      "eval_samples_per_second": 13.956,
      "eval_steps_per_second": 6.978,
      "step": 2
    },
    {
      "epoch": 0.00030121237982881096,
      "grad_norm": 0.37833720445632935,
      "learning_rate": 3e-05,
      "loss": 1.5779,
      "step": 3
    },
    {
      "epoch": 0.0004016165064384146,
      "grad_norm": 0.3701484203338623,
      "learning_rate": 4e-05,
      "loss": 1.5406,
      "step": 4
    },
    {
      "epoch": 0.0004016165064384146,
      "eval_loss": 3.453155279159546,
      "eval_runtime": 974.1859,
      "eval_samples_per_second": 17.22,
      "eval_steps_per_second": 8.61,
      "step": 4
    },
    {
      "epoch": 0.0005020206330480182,
      "grad_norm": 0.41933751106262207,
      "learning_rate": 5e-05,
      "loss": 1.54,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4531432407957504.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}