{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9985228951255539,
  "eval_steps": 500,
  "global_step": 169,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.29542097488921715,
      "grad_norm": 3.6940183639526367,
      "learning_rate": 2.5e-05,
      "loss": 3.3429,
      "step": 50
    },
    {
      "epoch": 0.5908419497784343,
      "grad_norm": 0.5006749033927917,
      "learning_rate": 5e-05,
      "loss": 0.7796,
      "step": 100
    },
    {
      "epoch": 0.8862629246676514,
      "grad_norm": 0.5715117454528809,
      "learning_rate": 4.726477024070022e-05,
      "loss": 0.22,
      "step": 150
    }
  ],
  "logging_steps": 50,
  "max_steps": 1014,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 2.673267488980992e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}