{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05983545250560957,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011967090501121914,
      "grad_norm": 66.83621978759766,
      "learning_rate": 1e-05,
      "loss": 113.7389,
      "step": 1
    },
    {
      "epoch": 0.011967090501121914,
      "eval_loss": NaN,
      "eval_runtime": 124.515,
      "eval_samples_per_second": 1.132,
      "eval_steps_per_second": 0.57,
      "step": 1
    },
    {
      "epoch": 0.02393418100224383,
      "grad_norm": 68.59111785888672,
      "learning_rate": 2e-05,
      "loss": 113.4407,
      "step": 2
    },
    {
      "epoch": 0.02393418100224383,
      "eval_loss": NaN,
      "eval_runtime": 5.2486,
      "eval_samples_per_second": 26.864,
      "eval_steps_per_second": 13.527,
      "step": 2
    },
    {
      "epoch": 0.03590127150336574,
      "grad_norm": 66.30567169189453,
      "learning_rate": 3e-05,
      "loss": 107.7654,
      "step": 3
    },
    {
      "epoch": 0.04786836200448766,
      "grad_norm": 65.51502227783203,
      "learning_rate": 4e-05,
      "loss": 106.2607,
      "step": 4
    },
    {
      "epoch": 0.04786836200448766,
      "eval_loss": NaN,
      "eval_runtime": 5.3223,
      "eval_samples_per_second": 26.492,
      "eval_steps_per_second": 13.34,
      "step": 4
    },
    {
      "epoch": 0.05983545250560957,
      "grad_norm": 68.32709503173828,
      "learning_rate": 5e-05,
      "loss": 103.4362,
      "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": 6332448610713600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}