{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007217610970768676,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001443522194153735,
      "grad_norm": 7.214014530181885,
      "learning_rate": 1e-05,
      "loss": 23.2511,
      "step": 1
    },
    {
      "epoch": 0.001443522194153735,
      "eval_loss": NaN,
      "eval_runtime": 350.5022,
      "eval_samples_per_second": 3.33,
      "eval_steps_per_second": 1.666,
      "step": 1
    },
    {
      "epoch": 0.00288704438830747,
      "grad_norm": 7.739083766937256,
      "learning_rate": 2e-05,
      "loss": 24.3232,
      "step": 2
    },
    {
      "epoch": 0.00288704438830747,
      "eval_loss": NaN,
      "eval_runtime": 242.5825,
      "eval_samples_per_second": 4.811,
      "eval_steps_per_second": 2.407,
      "step": 2
    },
    {
      "epoch": 0.004330566582461205,
      "grad_norm": 6.875201225280762,
      "learning_rate": 3e-05,
      "loss": 22.7572,
      "step": 3
    },
    {
      "epoch": 0.00577408877661494,
      "grad_norm": 6.780890464782715,
      "learning_rate": 4e-05,
      "loss": 22.3612,
      "step": 4
    },
    {
      "epoch": 0.00577408877661494,
      "eval_loss": NaN,
      "eval_runtime": 241.9135,
      "eval_samples_per_second": 4.824,
      "eval_steps_per_second": 2.414,
      "step": 4
    },
    {
      "epoch": 0.007217610970768676,
      "grad_norm": 8.078629493713379,
      "learning_rate": 5e-05,
      "loss": 23.6548,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.26648972214272e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}