{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14953271028037382,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 2.3950917720794678,
      "learning_rate": 1e-05,
      "loss": 8.9,
      "step": 1
    },
    {
      "epoch": 0.037383177570093455,
      "eval_loss": 9.027441024780273,
      "eval_runtime": 100.7998,
      "eval_samples_per_second": 0.446,
      "eval_steps_per_second": 0.228,
      "step": 1
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 2.868694305419922,
      "learning_rate": 2e-05,
      "loss": 8.9898,
      "step": 2
    },
    {
      "epoch": 0.07476635514018691,
      "eval_loss": 8.986785888671875,
      "eval_runtime": 1.1244,
      "eval_samples_per_second": 40.021,
      "eval_steps_per_second": 20.455,
      "step": 2
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 2.3952722549438477,
      "learning_rate": 3e-05,
      "loss": 8.6792,
      "step": 3
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 2.4765498638153076,
      "learning_rate": 4e-05,
      "loss": 9.2336,
      "step": 4
    },
    {
      "epoch": 0.14953271028037382,
      "eval_loss": 8.928328514099121,
      "eval_runtime": 1.1519,
      "eval_samples_per_second": 39.067,
      "eval_steps_per_second": 19.968,
      "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": 2959302797033472.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}