{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 122,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4098360655737705,
      "grad_norm": 3.3998632431030273,
      "learning_rate": 6.697247706422019e-06,
      "loss": 0.564799690246582,
      "step": 50
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 3.1558451652526855,
      "learning_rate": 2.110091743119266e-06,
      "loss": 0.5171302795410156,
      "step": 100
    }
  ],
  "logging_steps": 50,
  "max_steps": 122,
  "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": 0.0,
  "train_batch_size": 1024,
  "trial_name": null,
  "trial_params": null
}