{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 0.11728378385305405,
      "learning_rate": 0.00016,
      "loss": 0.2403,
      "step": 10
    },
    {
      "epoch": 1.3389830508474576,
      "grad_norm": 0.06212500482797623,
      "learning_rate": 0.00011555555555555555,
      "loss": 0.0296,
      "step": 20
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.06956837326288223,
      "learning_rate": 7.111111111111112e-05,
      "loss": 0.0146,
      "step": 30
    },
    {
      "epoch": 2.6779661016949152,
      "grad_norm": 0.0719493106007576,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.0083,
      "step": 40
    }
  ],
  "logging_steps": 10,
  "max_steps": 45,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 221023218696192.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}