{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.02139037433155,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5695608258247375,
      "eval_loss": 0.6931408643722534,
      "eval_runtime": 14.7678,
      "eval_samples_per_second": 201.994,
      "eval_steps_per_second": 12.663,
      "step": 187
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5115655660629272,
      "eval_loss": 0.6931466460227966,
      "eval_runtime": 14.1666,
      "eval_samples_per_second": 210.566,
      "eval_steps_per_second": 13.2,
      "step": 374
    },
    {
      "epoch": 2.6737967914438503,
      "grad_norm": 0.5249342918395996,
      "learning_rate": 6.592302596343259e-05,
      "loss": 0.6952,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5340261459350586,
      "eval_loss": 0.6931462287902832,
      "eval_runtime": 18.3671,
      "eval_samples_per_second": 162.41,
      "eval_steps_per_second": 10.181,
      "step": 561
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.451894074678421,
      "eval_loss": 0.6931475400924683,
      "eval_runtime": 17.1911,
      "eval_samples_per_second": 173.52,
      "eval_steps_per_second": 10.878,
      "step": 748
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5494468808174133,
      "eval_loss": 0.6931442022323608,
      "eval_runtime": 16.5408,
      "eval_samples_per_second": 180.341,
      "eval_steps_per_second": 11.305,
      "step": 935
    },
    {
      "epoch": 5.347593582887701,
      "grad_norm": 0.5341861844062805,
      "learning_rate": 4.1863527436632376e-05,
      "loss": 0.6948,
      "step": 1000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.45390546321868896,
      "eval_loss": 0.6931485533714294,
      "eval_runtime": 17.1349,
      "eval_samples_per_second": 174.09,
      "eval_steps_per_second": 10.913,
      "step": 1122
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5544753670692444,
      "eval_loss": 0.6931463479995728,
      "eval_runtime": 16.6506,
      "eval_samples_per_second": 179.152,
      "eval_steps_per_second": 11.231,
      "step": 1309
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5517935156822205,
      "eval_loss": 0.6931464076042175,
      "eval_runtime": 13.4695,
      "eval_samples_per_second": 221.463,
      "eval_steps_per_second": 13.883,
      "step": 1496
    },
    {
      "epoch": 8.02139037433155,
      "grad_norm": 0.34662115573883057,
      "learning_rate": 1.780402890983216e-05,
      "loss": 0.6945,
      "step": 1500
    }
  ],
  "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": 4644506675442972.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 8.99825244902328e-05,
    "per_device_train_batch_size": 64
  }
}