{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0056789948179172284,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011357989635834458,
      "grad_norm": 2.944114923477173,
      "learning_rate": 1e-05,
      "loss": 177.0,
      "step": 1
    },
    {
      "epoch": 0.0011357989635834458,
      "eval_loss": 11.064775466918945,
      "eval_runtime": 18.9888,
      "eval_samples_per_second": 78.099,
      "eval_steps_per_second": 39.076,
      "step": 1
    },
    {
      "epoch": 0.0022715979271668916,
      "grad_norm": 2.6945459842681885,
      "learning_rate": 2e-05,
      "loss": 177.0,
      "step": 2
    },
    {
      "epoch": 0.0022715979271668916,
      "eval_loss": 11.064775466918945,
      "eval_runtime": 3.0046,
      "eval_samples_per_second": 493.576,
      "eval_steps_per_second": 246.954,
      "step": 2
    },
    {
      "epoch": 0.0034073968907503372,
      "grad_norm": 2.947964906692505,
      "learning_rate": 3e-05,
      "loss": 177.0625,
      "step": 3
    },
    {
      "epoch": 0.004543195854333783,
      "grad_norm": 2.750715970993042,
      "learning_rate": 4e-05,
      "loss": 177.125,
      "step": 4
    },
    {
      "epoch": 0.004543195854333783,
      "eval_loss": 11.064691543579102,
      "eval_runtime": 3.1122,
      "eval_samples_per_second": 476.512,
      "eval_steps_per_second": 238.417,
      "step": 4
    },
    {
      "epoch": 0.0056789948179172284,
      "grad_norm": 2.8877432346343994,
      "learning_rate": 5e-05,
      "loss": 176.9375,
      "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": 29324083200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}