{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9979035639412998,
  "eval_steps": 500,
  "global_step": 119,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16771488469601678,
      "grad_norm": 0.023019764572381973,
      "learning_rate": 0.000233974358974359,
      "loss": 11.9301,
      "step": 20
    },
    {
      "epoch": 0.33542976939203356,
      "grad_norm": 0.05555475503206253,
      "learning_rate": 0.0002126068376068376,
      "loss": 11.9266,
      "step": 40
    },
    {
      "epoch": 0.5031446540880503,
      "grad_norm": 0.04104316607117653,
      "learning_rate": 0.00019123931623931623,
      "loss": 11.9229,
      "step": 60
    },
    {
      "epoch": 0.6708595387840671,
      "grad_norm": 0.0416753776371479,
      "learning_rate": 0.0001698717948717949,
      "loss": 11.9211,
      "step": 80
    },
    {
      "epoch": 0.8385744234800838,
      "grad_norm": 0.04827936738729477,
      "learning_rate": 0.0001485042735042735,
      "loss": 11.9211,
      "step": 100
    },
    {
      "epoch": 0.9979035639412998,
      "eval_loss": 11.919425964355469,
      "eval_runtime": 0.4166,
      "eval_samples_per_second": 242.468,
      "eval_steps_per_second": 62.417,
      "step": 119
    }
  ],
  "logging_steps": 20,
  "max_steps": 239,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 134180413440.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}