{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02164111812443643,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036068530207394047,
      "grad_norm": 1.000554084777832,
      "learning_rate": 2e-05,
      "loss": 9.9891,
      "step": 1
    },
    {
      "epoch": 0.0036068530207394047,
      "eval_loss": 2.2239835262298584,
      "eval_runtime": 6.4848,
      "eval_samples_per_second": 18.042,
      "eval_steps_per_second": 9.098,
      "step": 1
    },
    {
      "epoch": 0.007213706041478809,
      "grad_norm": 0.8824946284294128,
      "learning_rate": 4e-05,
      "loss": 9.2809,
      "step": 2
    },
    {
      "epoch": 0.010820559062218215,
      "grad_norm": 0.9153320789337158,
      "learning_rate": 6e-05,
      "loss": 8.3497,
      "step": 3
    },
    {
      "epoch": 0.010820559062218215,
      "eval_loss": 2.2219033241271973,
      "eval_runtime": 6.4392,
      "eval_samples_per_second": 18.17,
      "eval_steps_per_second": 9.163,
      "step": 3
    },
    {
      "epoch": 0.014427412082957619,
      "grad_norm": 1.1444321870803833,
      "learning_rate": 8e-05,
      "loss": 8.8211,
      "step": 4
    },
    {
      "epoch": 0.018034265103697024,
      "grad_norm": 1.063988447189331,
      "learning_rate": 0.0001,
      "loss": 9.426,
      "step": 5
    },
    {
      "epoch": 0.02164111812443643,
      "grad_norm": 1.241377830505371,
      "learning_rate": 0.00012,
      "loss": 8.5312,
      "step": 6
    },
    {
      "epoch": 0.02164111812443643,
      "eval_loss": 2.1837971210479736,
      "eval_runtime": 6.5191,
      "eval_samples_per_second": 17.947,
      "eval_steps_per_second": 9.05,
      "step": 6
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1899734583214080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}