{
  "best_metric": 0.4105323553085327,
  "best_model_checkpoint": "hBERTv2_new_pretrain_w_init__sst2/checkpoint-527",
  "epoch": 6.0,
  "global_step": 3162,
  "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": 0.3399,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8360091743119266,
      "eval_loss": 0.4105323553085327,
      "eval_runtime": 1.5047,
      "eval_samples_per_second": 579.5,
      "eval_steps_per_second": 4.652,
      "step": 527
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.2098,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8222477064220184,
      "eval_loss": 0.4836847484111786,
      "eval_runtime": 1.5026,
      "eval_samples_per_second": 580.318,
      "eval_steps_per_second": 4.659,
      "step": 1054
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.76e-05,
      "loss": 0.1578,
      "step": 1581
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8119266055045872,
      "eval_loss": 0.5173419713973999,
      "eval_runtime": 1.5032,
      "eval_samples_per_second": 580.114,
      "eval_steps_per_second": 4.657,
      "step": 1581
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.680000000000001e-05,
      "loss": 0.1219,
      "step": 2108
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8337155963302753,
      "eval_loss": 0.5737453103065491,
      "eval_runtime": 1.5074,
      "eval_samples_per_second": 578.464,
      "eval_steps_per_second": 4.644,
      "step": 2108
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.6e-05,
      "loss": 0.0978,
      "step": 2635
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8165137614678899,
      "eval_loss": 0.5373868346214294,
      "eval_runtime": 1.5058,
      "eval_samples_per_second": 579.095,
      "eval_steps_per_second": 4.649,
      "step": 2635
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.52e-05,
      "loss": 0.0803,
      "step": 3162
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8245412844036697,
      "eval_loss": 0.6070067882537842,
      "eval_runtime": 1.5046,
      "eval_samples_per_second": 579.547,
      "eval_steps_per_second": 4.652,
      "step": 3162
    },
    {
      "epoch": 6.0,
      "step": 3162,
      "total_flos": 5.913478047360614e+16,
      "train_loss": 0.1679188283767073,
      "train_runtime": 2130.856,
      "train_samples_per_second": 1580.327,
      "train_steps_per_second": 12.366
    }
  ],
  "max_steps": 26350,
  "num_train_epochs": 50,
  "total_flos": 5.913478047360614e+16,
  "trial_name": null,
  "trial_params": null
}