{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.48839299086416e-05,
  "eval_steps": 100,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.4961309969547202e-05,
      "grad_norm": 41.783329010009766,
      "learning_rate": 0.0003,
      "loss": 3.3915,
      "step": 1
    },
    {
      "epoch": 4.9922619939094404e-05,
      "grad_norm": 45.086753845214844,
      "learning_rate": 0.00015,
      "loss": 2.6814,
      "step": 2
    },
    {
      "epoch": 7.48839299086416e-05,
      "grad_norm": 71.21851348876953,
      "learning_rate": 0.0,
      "loss": 4.6356,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 3,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 131600695296.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}