{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0028110862212851937,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007027715553212984,
      "grad_norm": 0.6136889457702637,
      "learning_rate": 1e-05,
      "loss": 15.5317,
      "step": 1
    },
    {
      "epoch": 0.0007027715553212984,
      "eval_loss": 1.1447471380233765,
      "eval_runtime": 351.9627,
      "eval_samples_per_second": 6.81,
      "eval_steps_per_second": 3.407,
      "step": 1
    },
    {
      "epoch": 0.0014055431106425968,
      "grad_norm": 1.8403490781784058,
      "learning_rate": 2e-05,
      "loss": 19.2217,
      "step": 2
    },
    {
      "epoch": 0.0014055431106425968,
      "eval_loss": NaN,
      "eval_runtime": 186.4831,
      "eval_samples_per_second": 12.854,
      "eval_steps_per_second": 6.43,
      "step": 2
    },
    {
      "epoch": 0.002108314665963895,
      "grad_norm": 1.2213809490203857,
      "learning_rate": 3e-05,
      "loss": 19.3735,
      "step": 3
    },
    {
      "epoch": 0.0028110862212851937,
      "grad_norm": 0.8632063865661621,
      "learning_rate": 4e-05,
      "loss": 17.4995,
      "step": 4
    },
    {
      "epoch": 0.0028110862212851937,
      "eval_loss": 1.1437196731567383,
      "eval_runtime": 197.8087,
      "eval_samples_per_second": 12.118,
      "eval_steps_per_second": 6.061,
      "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": 9656984131338240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}