{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00013909647105298114,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.954823552649057e-05,
      "grad_norm": 10.644390106201172,
      "learning_rate": 1.999999978457693e-05,
      "loss": 2.1327,
      "step": 100
    },
    {
      "epoch": 0.00013909647105298114,
      "grad_norm": 8.314470291137695,
      "learning_rate": 1.9999999092358764e-05,
      "loss": 1.9946,
      "step": 200
    }
  ],
  "logging_steps": 100,
  "max_steps": 1437851,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1109343074088960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}