{
  "best_metric": 1.0961673259735107,
  "best_model_checkpoint": "hBERTv1_new_pretrain_mnli/checkpoint-24544",
  "epoch": 13.0,
  "global_step": 39884,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 3.9200000000000004e-05,
      "loss": 1.1036,
      "step": 3068
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.0992199182510376,
      "eval_runtime": 17.6477,
      "eval_samples_per_second": 556.162,
      "eval_steps_per_second": 4.363,
      "step": 3068
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 1.0989,
      "step": 6136
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.0991482734680176,
      "eval_runtime": 17.6383,
      "eval_samples_per_second": 556.461,
      "eval_steps_per_second": 4.366,
      "step": 6136
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.76e-05,
      "loss": 1.099,
      "step": 9204
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.33958227203260316,
      "eval_loss": 1.0985369682312012,
      "eval_runtime": 17.6432,
      "eval_samples_per_second": 556.306,
      "eval_steps_per_second": 4.364,
      "step": 9204
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.680000000000001e-05,
      "loss": 1.099,
      "step": 12272
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.0975842475891113,
      "eval_runtime": 17.6309,
      "eval_samples_per_second": 556.694,
      "eval_steps_per_second": 4.367,
      "step": 12272
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.6e-05,
      "loss": 1.0991,
      "step": 15340
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.0994316339492798,
      "eval_runtime": 17.6333,
      "eval_samples_per_second": 556.617,
      "eval_steps_per_second": 4.367,
      "step": 15340
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.52e-05,
      "loss": 1.0992,
      "step": 18408
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3544574630667346,
      "eval_loss": 1.098584771156311,
      "eval_runtime": 17.6283,
      "eval_samples_per_second": 556.774,
      "eval_steps_per_second": 4.368,
      "step": 18408
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.44e-05,
      "loss": 1.0992,
      "step": 21476
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3273560876209883,
      "eval_loss": 1.096727728843689,
      "eval_runtime": 17.6361,
      "eval_samples_per_second": 556.528,
      "eval_steps_per_second": 4.366,
      "step": 21476
    },
    {
      "epoch": 8.0,
      "learning_rate": 3.3600000000000004e-05,
      "loss": 1.0992,
      "step": 24544
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.3544574630667346,
      "eval_loss": 1.0961673259735107,
      "eval_runtime": 17.6187,
      "eval_samples_per_second": 557.077,
      "eval_steps_per_second": 4.37,
      "step": 24544
    },
    {
      "epoch": 9.0,
      "learning_rate": 3.28e-05,
      "loss": 1.0991,
      "step": 27612
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.1021356582641602,
      "eval_runtime": 17.638,
      "eval_samples_per_second": 556.469,
      "eval_steps_per_second": 4.366,
      "step": 27612
    },
    {
      "epoch": 10.0,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.099,
      "step": 30680
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.0981477499008179,
      "eval_runtime": 17.631,
      "eval_samples_per_second": 556.691,
      "eval_steps_per_second": 4.367,
      "step": 30680
    },
    {
      "epoch": 11.0,
      "learning_rate": 3.1200000000000006e-05,
      "loss": 1.0992,
      "step": 33748
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.3544574630667346,
      "eval_loss": 1.0980195999145508,
      "eval_runtime": 17.6356,
      "eval_samples_per_second": 556.544,
      "eval_steps_per_second": 4.366,
      "step": 33748
    },
    {
      "epoch": 12.0,
      "learning_rate": 3.0400000000000004e-05,
      "loss": 1.2036,
      "step": 36816
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.3544574630667346,
      "eval_loss": 1.1015625,
      "eval_runtime": 17.6259,
      "eval_samples_per_second": 556.851,
      "eval_steps_per_second": 4.369,
      "step": 36816
    },
    {
      "epoch": 13.0,
      "learning_rate": 2.96e-05,
      "loss": 2.2296,
      "step": 39884
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.3544574630667346,
      "eval_loss": 1.1015625,
      "eval_runtime": 17.7344,
      "eval_samples_per_second": 553.444,
      "eval_steps_per_second": 4.342,
      "step": 39884
    },
    {
      "epoch": 13.0,
      "step": 39884,
      "total_flos": 7.560587139109356e+17,
      "train_loss": 1.194441406935582,
      "train_runtime": 27037.304,
      "train_samples_per_second": 726.223,
      "train_steps_per_second": 5.674
    }
  ],
  "max_steps": 153400,
  "num_train_epochs": 50,
  "total_flos": 7.560587139109356e+17,
  "trial_name": null,
  "trial_params": null
}