{
  "best_metric": 0.8472222222222222,
  "best_model_checkpoint": "lungcancer_model_deit/checkpoint-84",
  "epoch": 12.987012987012987,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 9.56179428100586,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.3622,
      "step": 7
    },
    {
      "epoch": 0.9090909090909091,
      "eval_accuracy": 0.4583333333333333,
      "eval_loss": 1.1259331703186035,
      "eval_runtime": 1.0658,
      "eval_samples_per_second": 67.556,
      "eval_steps_per_second": 8.444,
      "step": 7
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 4.5356645584106445,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.735,
      "step": 14
    },
    {
      "epoch": 1.948051948051948,
      "eval_accuracy": 0.5,
      "eval_loss": 0.9460827708244324,
      "eval_runtime": 1.2329,
      "eval_samples_per_second": 58.401,
      "eval_steps_per_second": 7.3,
      "step": 15
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 11.363588333129883,
      "learning_rate": 4e-05,
      "loss": 0.5287,
      "step": 21
    },
    {
      "epoch": 2.987012987012987,
      "eval_accuracy": 0.5972222222222222,
      "eval_loss": 0.9006068706512451,
      "eval_runtime": 1.1547,
      "eval_samples_per_second": 62.353,
      "eval_steps_per_second": 7.794,
      "step": 23
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 9.22575855255127,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.2822,
      "step": 28
    },
    {
      "epoch": 3.896103896103896,
      "eval_accuracy": 0.6666666666666666,
      "eval_loss": 0.7236449718475342,
      "eval_runtime": 1.0624,
      "eval_samples_per_second": 67.772,
      "eval_steps_per_second": 8.471,
      "step": 30
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 10.75616455078125,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.1459,
      "step": 35
    },
    {
      "epoch": 4.935064935064935,
      "eval_accuracy": 0.7777777777777778,
      "eval_loss": 0.5326564908027649,
      "eval_runtime": 1.0763,
      "eval_samples_per_second": 66.898,
      "eval_steps_per_second": 8.362,
      "step": 38
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 2.9255380630493164,
      "learning_rate": 3e-05,
      "loss": 0.0687,
      "step": 42
    },
    {
      "epoch": 5.974025974025974,
      "eval_accuracy": 0.8333333333333334,
      "eval_loss": 0.42256489396095276,
      "eval_runtime": 1.9017,
      "eval_samples_per_second": 37.86,
      "eval_steps_per_second": 4.733,
      "step": 46
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 2.1261632442474365,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.0269,
      "step": 49
    },
    {
      "epoch": 6.883116883116883,
      "eval_accuracy": 0.8333333333333334,
      "eval_loss": 0.4134489595890045,
      "eval_runtime": 1.0782,
      "eval_samples_per_second": 66.781,
      "eval_steps_per_second": 8.348,
      "step": 53
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 0.20565827190876007,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.0139,
      "step": 56
    },
    {
      "epoch": 7.922077922077922,
      "eval_accuracy": 0.8333333333333334,
      "eval_loss": 0.3836323916912079,
      "eval_runtime": 1.0936,
      "eval_samples_per_second": 65.839,
      "eval_steps_per_second": 8.23,
      "step": 61
    },
    {
      "epoch": 8.181818181818182,
      "grad_norm": 0.11971937119960785,
      "learning_rate": 2e-05,
      "loss": 0.0077,
      "step": 63
    },
    {
      "epoch": 8.96103896103896,
      "eval_accuracy": 0.8194444444444444,
      "eval_loss": 0.5306501984596252,
      "eval_runtime": 1.071,
      "eval_samples_per_second": 67.228,
      "eval_steps_per_second": 8.404,
      "step": 69
    },
    {
      "epoch": 9.090909090909092,
      "grad_norm": 0.09062337130308151,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0054,
      "step": 70
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.041697677224874496,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.0042,
      "step": 77
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8333333333333334,
      "eval_loss": 0.4780552089214325,
      "eval_runtime": 1.1093,
      "eval_samples_per_second": 64.905,
      "eval_steps_per_second": 8.113,
      "step": 77
    },
    {
      "epoch": 10.909090909090908,
      "grad_norm": 0.0230174008756876,
      "learning_rate": 1e-05,
      "loss": 0.0038,
      "step": 84
    },
    {
      "epoch": 10.909090909090908,
      "eval_accuracy": 0.8472222222222222,
      "eval_loss": 0.41819339990615845,
      "eval_runtime": 1.0796,
      "eval_samples_per_second": 66.694,
      "eval_steps_per_second": 8.337,
      "step": 84
    },
    {
      "epoch": 11.818181818181818,
      "grad_norm": 0.024311551824212074,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.0039,
      "step": 91
    },
    {
      "epoch": 11.948051948051948,
      "eval_accuracy": 0.8472222222222222,
      "eval_loss": 0.39705508947372437,
      "eval_runtime": 1.0729,
      "eval_samples_per_second": 67.106,
      "eval_steps_per_second": 8.388,
      "step": 92
    },
    {
      "epoch": 12.727272727272727,
      "grad_norm": 0.022643834352493286,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0018,
      "step": 98
    },
    {
      "epoch": 12.987012987012987,
      "eval_accuracy": 0.8472222222222222,
      "eval_loss": 0.39274024963378906,
      "eval_runtime": 1.0807,
      "eval_samples_per_second": 66.626,
      "eval_steps_per_second": 8.328,
      "step": 100
    }
  ],
  "logging_steps": 7,
  "max_steps": 105,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "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": 6.175723941563904e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}