{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006473431956345831,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6598543477809823e-05,
      "eval_loss": 3.306856870651245,
      "eval_runtime": 2034.959,
      "eval_samples_per_second": 12.466,
      "eval_steps_per_second": 6.233,
      "step": 1
    },
    {
      "epoch": 8.29927173890491e-05,
      "grad_norm": 6.088284015655518,
      "learning_rate": 5e-05,
      "loss": 2.6346,
      "step": 5
    },
    {
      "epoch": 0.0001659854347780982,
      "grad_norm": 6.237154006958008,
      "learning_rate": 0.0001,
      "loss": 2.4719,
      "step": 10
    },
    {
      "epoch": 0.0001659854347780982,
      "eval_loss": 1.8655370473861694,
      "eval_runtime": 2039.7166,
      "eval_samples_per_second": 12.437,
      "eval_steps_per_second": 6.219,
      "step": 10
    },
    {
      "epoch": 0.00024897815216714733,
      "grad_norm": 4.459682941436768,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.542,
      "step": 15
    },
    {
      "epoch": 0.0003319708695561964,
      "grad_norm": 4.069087982177734,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.2403,
      "step": 20
    },
    {
      "epoch": 0.0003319708695561964,
      "eval_loss": 1.2442752122879028,
      "eval_runtime": 2042.5262,
      "eval_samples_per_second": 12.419,
      "eval_steps_per_second": 6.21,
      "step": 20
    },
    {
      "epoch": 0.00041496358694524557,
      "grad_norm": 3.6503212451934814,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.1624,
      "step": 25
    },
    {
      "epoch": 0.0004979563043342947,
      "grad_norm": 4.6950483322143555,
      "learning_rate": 5e-05,
      "loss": 1.2399,
      "step": 30
    },
    {
      "epoch": 0.0004979563043342947,
      "eval_loss": 1.0979321002960205,
      "eval_runtime": 2038.1003,
      "eval_samples_per_second": 12.446,
      "eval_steps_per_second": 6.223,
      "step": 30
    },
    {
      "epoch": 0.0005809490217233438,
      "grad_norm": 3.921696901321411,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.1501,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7453256523448320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}