{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9936305732484076,
  "eval_steps": 500,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3821656050955414,
      "grad_norm": 0.5991920828819275,
      "learning_rate": 0.00017777777777777779,
      "loss": 3.1374,
      "step": 30
    },
    {
      "epoch": 0.7643312101910829,
      "grad_norm": 0.5930201411247253,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.8232,
      "step": 60
    }
  ],
  "logging_steps": 30,
  "max_steps": 78,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7224355813588992.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}