{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0010319118747258984,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010319118747258984,
      "grad_norm": 2.742561101913452,
      "learning_rate": 2e-05,
      "loss": 2.1835,
      "step": 1
    },
    {
      "epoch": 0.00010319118747258984,
      "eval_loss": NaN,
      "eval_runtime": 317.799,
      "eval_samples_per_second": 12.841,
      "eval_steps_per_second": 6.422,
      "step": 1
    },
    {
      "epoch": 0.00020638237494517968,
      "grad_norm": 2.325059175491333,
      "learning_rate": 4e-05,
      "loss": 1.576,
      "step": 2
    },
    {
      "epoch": 0.00030957356241776953,
      "grad_norm": 3.646341562271118,
      "learning_rate": 6e-05,
      "loss": 2.6003,
      "step": 3
    },
    {
      "epoch": 0.00030957356241776953,
      "eval_loss": NaN,
      "eval_runtime": 315.6548,
      "eval_samples_per_second": 12.929,
      "eval_steps_per_second": 6.466,
      "step": 3
    },
    {
      "epoch": 0.00041276474989035937,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 3.5042,
      "step": 4
    },
    {
      "epoch": 0.0005159559373629492,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 3.7389,
      "step": 5
    },
    {
      "epoch": 0.0006191471248355391,
      "grad_norm": 3.0812764167785645,
      "learning_rate": 0.00012,
      "loss": 1.8717,
      "step": 6
    },
    {
      "epoch": 0.0006191471248355391,
      "eval_loss": NaN,
      "eval_runtime": 315.7214,
      "eval_samples_per_second": 12.926,
      "eval_steps_per_second": 6.465,
      "step": 6
    },
    {
      "epoch": 0.0007223383123081289,
      "grad_norm": 4.424726486206055,
      "learning_rate": 0.00014,
      "loss": 2.0521,
      "step": 7
    },
    {
      "epoch": 0.0008255294997807187,
      "grad_norm": 2.7366762161254883,
      "learning_rate": 0.00016,
      "loss": 1.3545,
      "step": 8
    },
    {
      "epoch": 0.0009287206872533086,
      "grad_norm": 2.943781852722168,
      "learning_rate": 0.00018,
      "loss": 1.9685,
      "step": 9
    },
    {
      "epoch": 0.0009287206872533086,
      "eval_loss": NaN,
      "eval_runtime": 316.0129,
      "eval_samples_per_second": 12.914,
      "eval_steps_per_second": 6.459,
      "step": 9
    },
    {
      "epoch": 0.0010319118747258984,
      "grad_norm": 3.552509307861328,
      "learning_rate": 0.0002,
      "loss": 2.0653,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5225796096491520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}