{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009751340809361287,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019502681618722574,
      "grad_norm": 6.870009899139404,
      "learning_rate": 1e-05,
      "loss": 9.9895,
      "step": 1
    },
    {
      "epoch": 0.0019502681618722574,
      "eval_loss": 10.612870216369629,
      "eval_runtime": 32.9954,
      "eval_samples_per_second": 26.185,
      "eval_steps_per_second": 13.093,
      "step": 1
    },
    {
      "epoch": 0.0039005363237445147,
      "grad_norm": 7.725345134735107,
      "learning_rate": 2e-05,
      "loss": 10.4699,
      "step": 2
    },
    {
      "epoch": 0.0039005363237445147,
      "eval_loss": 10.524613380432129,
      "eval_runtime": 6.0119,
      "eval_samples_per_second": 143.715,
      "eval_steps_per_second": 71.857,
      "step": 2
    },
    {
      "epoch": 0.005850804485616773,
      "grad_norm": 7.5263991355896,
      "learning_rate": 3e-05,
      "loss": 10.0585,
      "step": 3
    },
    {
      "epoch": 0.0078010726474890294,
      "grad_norm": 7.526846408843994,
      "learning_rate": 4e-05,
      "loss": 10.4262,
      "step": 4
    },
    {
      "epoch": 0.0078010726474890294,
      "eval_loss": 10.386100769042969,
      "eval_runtime": 6.066,
      "eval_samples_per_second": 142.432,
      "eval_steps_per_second": 71.216,
      "step": 4
    },
    {
      "epoch": 0.009751340809361287,
      "grad_norm": 7.800673961639404,
      "learning_rate": 5e-05,
      "loss": 10.0465,
      "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": 481091030876160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}