{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017460386747566458,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034920773495132916,
      "grad_norm": 1.2742584943771362,
      "learning_rate": 1e-05,
      "loss": 8.5311,
      "step": 1
    },
    {
      "epoch": 0.00034920773495132916,
      "eval_loss": 8.479562759399414,
      "eval_runtime": 84.6503,
      "eval_samples_per_second": 56.976,
      "eval_steps_per_second": 28.494,
      "step": 1
    },
    {
      "epoch": 0.0006984154699026583,
      "grad_norm": 1.2720140218734741,
      "learning_rate": 2e-05,
      "loss": 8.5747,
      "step": 2
    },
    {
      "epoch": 0.0006984154699026583,
      "eval_loss": 8.47692584991455,
      "eval_runtime": 12.8665,
      "eval_samples_per_second": 374.849,
      "eval_steps_per_second": 187.463,
      "step": 2
    },
    {
      "epoch": 0.0010476232048539874,
      "grad_norm": 1.2419705390930176,
      "learning_rate": 3e-05,
      "loss": 8.5907,
      "step": 3
    },
    {
      "epoch": 0.0013968309398053166,
      "grad_norm": 1.1904064416885376,
      "learning_rate": 4e-05,
      "loss": 8.6315,
      "step": 4
    },
    {
      "epoch": 0.0013968309398053166,
      "eval_loss": 8.471273422241211,
      "eval_runtime": 12.8675,
      "eval_samples_per_second": 374.82,
      "eval_steps_per_second": 187.449,
      "step": 4
    },
    {
      "epoch": 0.0017460386747566458,
      "grad_norm": 1.3321144580841064,
      "learning_rate": 5e-05,
      "loss": 8.4537,
      "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": 1311170887680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}