{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07946598855689765,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01589319771137953,
      "grad_norm": 0.9081700444221497,
      "learning_rate": 0.0002,
      "loss": 2.3142,
      "step": 100
    },
    {
      "epoch": 0.03178639542275906,
      "grad_norm": 0.8463758826255798,
      "learning_rate": 0.0002,
      "loss": 2.0015,
      "step": 200
    },
    {
      "epoch": 0.04767959313413859,
      "grad_norm": 1.0305041074752808,
      "learning_rate": 0.0002,
      "loss": 1.9429,
      "step": 300
    },
    {
      "epoch": 0.06357279084551812,
      "grad_norm": 0.48407527804374695,
      "learning_rate": 0.0002,
      "loss": 1.9406,
      "step": 400
    },
    {
      "epoch": 0.07946598855689765,
      "grad_norm": 0.9855284690856934,
      "learning_rate": 0.0002,
      "loss": 1.79,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 6292,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2550104850432000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}