{
  "best_metric": 1.0985355377197266,
  "best_model_checkpoint": "hBERTv2_new_pretrain_w_init_48_ver2_mnli/checkpoint-24544",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 55224,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 3.733333333333334e-05,
      "loss": 1.1017,
      "step": 6136
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.099240779876709,
      "eval_runtime": 20.6002,
      "eval_samples_per_second": 476.452,
      "eval_steps_per_second": 7.476,
      "step": 6136
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.466666666666667e-05,
      "loss": 1.0988,
      "step": 12272
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.0993497371673584,
      "eval_runtime": 20.656,
      "eval_samples_per_second": 475.165,
      "eval_steps_per_second": 7.455,
      "step": 12272
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.0987,
      "step": 18408
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.0986136198043823,
      "eval_runtime": 20.721,
      "eval_samples_per_second": 473.674,
      "eval_steps_per_second": 7.432,
      "step": 18408
    },
    {
      "epoch": 4.0,
      "learning_rate": 2.9333333333333333e-05,
      "loss": 1.0987,
      "step": 24544
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3544574630667346,
      "eval_loss": 1.0985355377197266,
      "eval_runtime": 20.7461,
      "eval_samples_per_second": 473.1,
      "eval_steps_per_second": 7.423,
      "step": 24544
    },
    {
      "epoch": 5.0,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.0987,
      "step": 30680
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.098646640777588,
      "eval_runtime": 20.7299,
      "eval_samples_per_second": 473.47,
      "eval_steps_per_second": 7.429,
      "step": 30680
    },
    {
      "epoch": 6.0,
      "learning_rate": 2.4e-05,
      "loss": 1.0986,
      "step": 36816
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3273560876209883,
      "eval_loss": 1.098628282546997,
      "eval_runtime": 20.7789,
      "eval_samples_per_second": 472.354,
      "eval_steps_per_second": 7.411,
      "step": 36816
    },
    {
      "epoch": 7.0,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 1.0986,
      "step": 42952
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3544574630667346,
      "eval_loss": 1.098601222038269,
      "eval_runtime": 20.7327,
      "eval_samples_per_second": 473.407,
      "eval_steps_per_second": 7.428,
      "step": 42952
    },
    {
      "epoch": 8.0,
      "learning_rate": 1.866666666666667e-05,
      "loss": 1.0986,
      "step": 49088
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.3544574630667346,
      "eval_loss": 1.0986049175262451,
      "eval_runtime": 20.6966,
      "eval_samples_per_second": 474.232,
      "eval_steps_per_second": 7.441,
      "step": 49088
    },
    {
      "epoch": 9.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.0986,
      "step": 55224
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.098617434501648,
      "eval_runtime": 20.702,
      "eval_samples_per_second": 474.11,
      "eval_steps_per_second": 7.439,
      "step": 55224
    },
    {
      "epoch": 9.0,
      "step": 55224,
      "total_flos": 5.1721333631247974e+17,
      "train_loss": 1.0990169016188613,
      "train_runtime": 23433.9477,
      "train_samples_per_second": 251.367,
      "train_steps_per_second": 3.928
    }
  ],
  "logging_steps": 1,
  "max_steps": 92040,
  "num_train_epochs": 15,
  "save_steps": 500,
  "total_flos": 5.1721333631247974e+17,
  "trial_name": null,
  "trial_params": null
}