{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 157,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32,
      "grad_norm": 0.6840799866686034,
      "learning_rate": 8.071063563448341e-06,
      "loss": 0.40745651245117187,
      "step": 50
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.7269712087746059,
      "learning_rate": 3.1824601471808504e-06,
      "loss": 0.3509598922729492,
      "step": 100
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.6680954327618741,
      "learning_rate": 6.819348298638839e-08,
      "loss": 0.3304820251464844,
      "step": 150
    },
    {
      "epoch": 1.0,
      "step": 157,
      "total_flos": 2963008389120.0,
      "train_loss": 0.36064160249795124,
      "train_runtime": 4884.8111,
      "train_samples_per_second": 2.047,
      "train_steps_per_second": 0.032
    }
  ],
  "logging_steps": 50,
  "max_steps": 157,
  "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": 2963008389120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}