{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006696428571428571,
  "eval_steps": 9,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000744047619047619,
      "eval_loss": 8.732146263122559,
      "eval_runtime": 160.2118,
      "eval_samples_per_second": 14.131,
      "eval_steps_per_second": 1.766,
      "step": 1
    },
    {
      "epoch": 0.002232142857142857,
      "grad_norm": 3.8788089752197266,
      "learning_rate": 1.5e-05,
      "loss": 8.6329,
      "step": 3
    },
    {
      "epoch": 0.004464285714285714,
      "grad_norm": 3.3676693439483643,
      "learning_rate": 3e-05,
      "loss": 8.6812,
      "step": 6
    },
    {
      "epoch": 0.006696428571428571,
      "grad_norm": 4.344758033752441,
      "learning_rate": 4.5e-05,
      "loss": 8.5473,
      "step": 9
    },
    {
      "epoch": 0.006696428571428571,
      "eval_loss": 8.29433536529541,
      "eval_runtime": 161.9566,
      "eval_samples_per_second": 13.979,
      "eval_steps_per_second": 1.747,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3353971104088064e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}