{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9999173348764157,
  "eval_steps": 500,
  "global_step": 6048,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001653302471687195,
      "grad_norm": 0.169921875,
      "learning_rate": 0.0002,
      "loss": 1.51,
      "step": 1
    },
    {
      "epoch": 0.16533024716871952,
      "grad_norm": 0.181640625,
      "learning_rate": 0.0002,
      "loss": 0.7844,
      "step": 1000
    },
    {
      "epoch": 0.33066049433743905,
      "grad_norm": 0.216796875,
      "learning_rate": 0.0002,
      "loss": 0.5644,
      "step": 2000
    },
    {
      "epoch": 0.4959907415061586,
      "grad_norm": 0.2119140625,
      "learning_rate": 0.0002,
      "loss": 0.4884,
      "step": 3000
    },
    {
      "epoch": 0.6613209886748781,
      "grad_norm": 0.1904296875,
      "learning_rate": 0.0002,
      "loss": 0.45,
      "step": 4000
    },
    {
      "epoch": 0.8266512358435976,
      "grad_norm": 0.251953125,
      "learning_rate": 0.0002,
      "loss": 0.4151,
      "step": 5000
    },
    {
      "epoch": 0.9919814830123171,
      "grad_norm": 0.2314453125,
      "learning_rate": 0.0002,
      "loss": 0.3945,
      "step": 6000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 6048,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.221833426685133e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}