{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00013981614177356776,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.660538059118925e-05,
      "grad_norm": 0.013180263340473175,
      "learning_rate": 2e-05,
      "loss": 10.3787,
      "step": 1
    },
    {
      "epoch": 4.660538059118925e-05,
      "eval_loss": 10.381084442138672,
      "eval_runtime": 24.2148,
      "eval_samples_per_second": 373.119,
      "eval_steps_per_second": 186.58,
      "step": 1
    },
    {
      "epoch": 9.32107611823785e-05,
      "grad_norm": 0.014053184539079666,
      "learning_rate": 4e-05,
      "loss": 10.383,
      "step": 2
    },
    {
      "epoch": 0.00013981614177356776,
      "grad_norm": 0.017326638102531433,
      "learning_rate": 6e-05,
      "loss": 10.3827,
      "step": 3
    },
    {
      "epoch": 0.00013981614177356776,
      "eval_loss": 10.381073951721191,
      "eval_runtime": 24.3154,
      "eval_samples_per_second": 371.575,
      "eval_steps_per_second": 185.808,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 51723632640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}