{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6737967914438503,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6640965342521667,
      "eval_loss": 0.5810248851776123,
      "eval_runtime": 14.2872,
      "eval_samples_per_second": 208.788,
      "eval_steps_per_second": 13.089,
      "step": 187
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6832048296928406,
      "eval_loss": 0.5652729272842407,
      "eval_runtime": 13.8796,
      "eval_samples_per_second": 214.919,
      "eval_steps_per_second": 13.473,
      "step": 374
    },
    {
      "epoch": 2.6737967914438503,
      "grad_norm": 6.708367824554443,
      "learning_rate": 2.9957568655605055e-05,
      "loss": 0.5459,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1870,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4056945908795220.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.089098787297916e-05,
    "per_device_train_batch_size": 64
  }
}