{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14285714285714285,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023809523809523808,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.023809523809523808,
      "eval_loss": NaN,
      "eval_runtime": 1.1589,
      "eval_samples_per_second": 31.064,
      "eval_steps_per_second": 7.766,
      "step": 1
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.07142857142857142,
      "eval_loss": NaN,
      "eval_runtime": 1.1881,
      "eval_samples_per_second": 30.3,
      "eval_steps_per_second": 7.575,
      "step": 3
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.14285714285714285,
      "eval_loss": NaN,
      "eval_runtime": 1.1268,
      "eval_samples_per_second": 31.948,
      "eval_steps_per_second": 7.987,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "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": 8877908391100416.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}