{
  "best_metric": 0.6864272356033325,
  "best_model_checkpoint": "hBERTv2_new_pretrain_w_init_48_wnli/checkpoint-5",
  "epoch": 6.0,
  "global_step": 30,
  "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": 0.9651,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5633802816901409,
      "eval_loss": 0.6864272356033325,
      "eval_runtime": 0.1331,
      "eval_samples_per_second": 533.502,
      "eval_steps_per_second": 7.514,
      "step": 5
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.7199,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5633802816901409,
      "eval_loss": 0.69921875,
      "eval_runtime": 0.1329,
      "eval_samples_per_second": 534.219,
      "eval_steps_per_second": 7.524,
      "step": 10
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.76e-05,
      "loss": 0.7059,
      "step": 15
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3380281690140845,
      "eval_loss": 0.7100022435188293,
      "eval_runtime": 0.132,
      "eval_samples_per_second": 537.743,
      "eval_steps_per_second": 7.574,
      "step": 15
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.680000000000001e-05,
      "loss": 0.7029,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4647887323943662,
      "eval_loss": 0.701364278793335,
      "eval_runtime": 0.1324,
      "eval_samples_per_second": 536.16,
      "eval_steps_per_second": 7.552,
      "step": 20
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.6e-05,
      "loss": 0.7045,
      "step": 25
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.43661971830985913,
      "eval_loss": 0.7245818376541138,
      "eval_runtime": 0.1327,
      "eval_samples_per_second": 534.995,
      "eval_steps_per_second": 7.535,
      "step": 25
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.52e-05,
      "loss": 0.7259,
      "step": 30
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5633802816901409,
      "eval_loss": 0.7127530574798584,
      "eval_runtime": 0.1346,
      "eval_samples_per_second": 527.457,
      "eval_steps_per_second": 7.429,
      "step": 30
    },
    {
      "epoch": 6.0,
      "step": 30,
      "total_flos": 557552253272064.0,
      "train_loss": 0.7540303071339926,
      "train_runtime": 47.1307,
      "train_samples_per_second": 673.658,
      "train_steps_per_second": 5.304
    }
  ],
  "max_steps": 250,
  "num_train_epochs": 50,
  "total_flos": 557552253272064.0,
  "trial_name": null,
  "trial_params": null
}