{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02238388360380526,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004476776720761052,
      "grad_norm": 0.017779290676116943,
      "learning_rate": 1e-05,
      "loss": 11.7629,
      "step": 1
    },
    {
      "epoch": 0.004476776720761052,
      "eval_loss": 11.762974739074707,
      "eval_runtime": 26.2254,
      "eval_samples_per_second": 14.375,
      "eval_steps_per_second": 7.207,
      "step": 1
    },
    {
      "epoch": 0.008953553441522105,
      "grad_norm": 0.015599766746163368,
      "learning_rate": 2e-05,
      "loss": 11.7649,
      "step": 2
    },
    {
      "epoch": 0.008953553441522105,
      "eval_loss": 11.762969970703125,
      "eval_runtime": 0.5711,
      "eval_samples_per_second": 660.14,
      "eval_steps_per_second": 330.945,
      "step": 2
    },
    {
      "epoch": 0.013430330162283156,
      "grad_norm": 0.01903875544667244,
      "learning_rate": 3e-05,
      "loss": 11.7634,
      "step": 3
    },
    {
      "epoch": 0.01790710688304421,
      "grad_norm": 0.01464943028986454,
      "learning_rate": 4e-05,
      "loss": 11.7638,
      "step": 4
    },
    {
      "epoch": 0.01790710688304421,
      "eval_loss": 11.762955665588379,
      "eval_runtime": 0.5641,
      "eval_samples_per_second": 668.267,
      "eval_steps_per_second": 335.02,
      "step": 4
    },
    {
      "epoch": 0.02238388360380526,
      "grad_norm": 0.014391904696822166,
      "learning_rate": 5e-05,
      "loss": 11.7622,
      "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": 1040996302848.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}