{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04319654427645788,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008639308855291577,
      "grad_norm": 0.8302701711654663,
      "learning_rate": 1e-05,
      "loss": 0.2592,
      "step": 1
    },
    {
      "epoch": 0.008639308855291577,
      "eval_loss": 0.30351966619491577,
      "eval_runtime": 151.8338,
      "eval_samples_per_second": 1.284,
      "eval_steps_per_second": 0.645,
      "step": 1
    },
    {
      "epoch": 0.017278617710583154,
      "grad_norm": 0.48937609791755676,
      "learning_rate": 2e-05,
      "loss": 0.2145,
      "step": 2
    },
    {
      "epoch": 0.017278617710583154,
      "eval_loss": 0.2815435826778412,
      "eval_runtime": 16.0488,
      "eval_samples_per_second": 12.15,
      "eval_steps_per_second": 6.106,
      "step": 2
    },
    {
      "epoch": 0.02591792656587473,
      "grad_norm": 0.7053600549697876,
      "learning_rate": 3e-05,
      "loss": 0.295,
      "step": 3
    },
    {
      "epoch": 0.03455723542116631,
      "grad_norm": 0.6742414832115173,
      "learning_rate": 4e-05,
      "loss": 0.2353,
      "step": 4
    },
    {
      "epoch": 0.03455723542116631,
      "eval_loss": 0.2548750340938568,
      "eval_runtime": 16.1075,
      "eval_samples_per_second": 12.106,
      "eval_steps_per_second": 6.084,
      "step": 4
    },
    {
      "epoch": 0.04319654427645788,
      "grad_norm": 1.1908938884735107,
      "learning_rate": 5e-05,
      "loss": 0.3374,
      "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": 6380996656103424.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}