{
  "best_metric": 0.691364049911499,
  "best_model_checkpoint": "hBERTv1_new_pretrain_w_init__qnli/checkpoint-2457",
  "epoch": 8.0,
  "global_step": 6552,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.00049,
      "loss": 0.8188,
      "step": 819
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5053999633900788,
      "eval_loss": 0.6932117342948914,
      "eval_runtime": 9.863,
      "eval_samples_per_second": 553.888,
      "eval_steps_per_second": 4.36,
      "step": 819
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00048,
      "loss": 0.6937,
      "step": 1638
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4946000366099213,
      "eval_loss": 0.6934226751327515,
      "eval_runtime": 9.8555,
      "eval_samples_per_second": 554.308,
      "eval_steps_per_second": 4.363,
      "step": 1638
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00047,
      "loss": 0.6932,
      "step": 2457
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5053999633900788,
      "eval_loss": 0.691364049911499,
      "eval_runtime": 9.8848,
      "eval_samples_per_second": 552.667,
      "eval_steps_per_second": 4.35,
      "step": 2457
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00046,
      "loss": 0.6932,
      "step": 3276
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4946000366099213,
      "eval_loss": 0.6934226751327515,
      "eval_runtime": 9.8572,
      "eval_samples_per_second": 554.216,
      "eval_steps_per_second": 4.362,
      "step": 3276
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00045000000000000004,
      "loss": 0.6932,
      "step": 4095
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5053999633900788,
      "eval_loss": 0.6933382749557495,
      "eval_runtime": 9.8568,
      "eval_samples_per_second": 554.238,
      "eval_steps_per_second": 4.362,
      "step": 4095
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00044,
      "loss": 0.6932,
      "step": 4914
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5053999633900788,
      "eval_loss": 0.6933382749557495,
      "eval_runtime": 9.8513,
      "eval_samples_per_second": 554.547,
      "eval_steps_per_second": 4.365,
      "step": 4914
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.00043,
      "loss": 0.6932,
      "step": 5733
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5053999633900788,
      "eval_loss": 0.6933382749557495,
      "eval_runtime": 9.9161,
      "eval_samples_per_second": 550.923,
      "eval_steps_per_second": 4.336,
      "step": 5733
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.00042,
      "loss": 0.6931,
      "step": 6552
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5053999633900788,
      "eval_loss": 0.6933382749557495,
      "eval_runtime": 9.9544,
      "eval_samples_per_second": 548.802,
      "eval_steps_per_second": 4.32,
      "step": 6552
    },
    {
      "epoch": 8.0,
      "step": 6552,
      "total_flos": 1.2409680077573325e+17,
      "train_loss": 0.7089429955488306,
      "train_runtime": 4466.842,
      "train_samples_per_second": 1172.45,
      "train_steps_per_second": 9.168
    }
  ],
  "max_steps": 40950,
  "num_train_epochs": 50,
  "total_flos": 1.2409680077573325e+17,
  "trial_name": null,
  "trial_params": null
}