{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.37383177570093457,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 62.896324157714844,
      "learning_rate": 1e-05,
      "loss": 124.4913,
      "step": 1
    },
    {
      "epoch": 0.07476635514018691,
      "eval_loss": 7.666586399078369,
      "eval_runtime": 16.6694,
      "eval_samples_per_second": 1.38,
      "eval_steps_per_second": 0.72,
      "step": 1
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 71.1831283569336,
      "learning_rate": 2e-05,
      "loss": 124.7486,
      "step": 2
    },
    {
      "epoch": 0.14953271028037382,
      "eval_loss": NaN,
      "eval_runtime": 0.7458,
      "eval_samples_per_second": 30.841,
      "eval_steps_per_second": 16.091,
      "step": 2
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 65.19701385498047,
      "learning_rate": 3e-05,
      "loss": 126.2791,
      "step": 3
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 68.43965148925781,
      "learning_rate": 4e-05,
      "loss": 123.7978,
      "step": 4
    },
    {
      "epoch": 0.29906542056074764,
      "eval_loss": NaN,
      "eval_runtime": 0.7661,
      "eval_samples_per_second": 30.021,
      "eval_steps_per_second": 15.663,
      "step": 4
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 72.72246551513672,
      "learning_rate": 5e-05,
      "loss": 124.7262,
      "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": 3257466271825920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}