{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 46,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 1.9281949996948242,
      "learning_rate": 1.8961655569610557e-05,
      "loss": 3.9294,
      "step": 12
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 1.67686128616333,
      "learning_rate": 1.1903911091646684e-05,
      "loss": 3.1055,
      "step": 24
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 1.3326585292816162,
      "learning_rate": 3.3467429983443477e-06,
      "loss": 2.5722,
      "step": 36
    }
  ],
  "logging_steps": 12,
  "max_steps": 46,
  "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": 7119843342852672.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}