{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.037405026300409115,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009351256575102279,
      "grad_norm": 31.33281135559082,
      "learning_rate": 1e-05,
      "loss": 114.6236,
      "step": 1
    },
    {
      "epoch": 0.009351256575102279,
      "eval_loss": 7.341782093048096,
      "eval_runtime": 66.8936,
      "eval_samples_per_second": 2.706,
      "eval_steps_per_second": 1.36,
      "step": 1
    },
    {
      "epoch": 0.018702513150204558,
      "grad_norm": 34.3769416809082,
      "learning_rate": 2e-05,
      "loss": 118.623,
      "step": 2
    },
    {
      "epoch": 0.018702513150204558,
      "eval_loss": 7.1771321296691895,
      "eval_runtime": 43.3339,
      "eval_samples_per_second": 4.177,
      "eval_steps_per_second": 2.1,
      "step": 2
    },
    {
      "epoch": 0.028053769725306838,
      "grad_norm": 32.84296417236328,
      "learning_rate": 3e-05,
      "loss": 110.9102,
      "step": 3
    },
    {
      "epoch": 0.037405026300409115,
      "grad_norm": 35.27595520019531,
      "learning_rate": 4e-05,
      "loss": 115.7492,
      "step": 4
    },
    {
      "epoch": 0.037405026300409115,
      "eval_loss": 7.080971717834473,
      "eval_runtime": 48.7623,
      "eval_samples_per_second": 3.712,
      "eval_steps_per_second": 1.866,
      "step": 4
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5065958888570880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}