{
  "best_metric": 1.0956659317016602,
  "best_model_checkpoint": "hBERTv2_new_pretrain_w_init__mnli/checkpoint-6136",
  "epoch": 7.0,
  "global_step": 21476,
  "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": 1.1017,
      "step": 3068
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3273560876209883,
      "eval_loss": 1.098468542098999,
      "eval_runtime": 16.8183,
      "eval_samples_per_second": 583.592,
      "eval_steps_per_second": 4.578,
      "step": 3068
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 1.0989,
      "step": 6136
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3273560876209883,
      "eval_loss": 1.0956659317016602,
      "eval_runtime": 16.7915,
      "eval_samples_per_second": 584.522,
      "eval_steps_per_second": 4.586,
      "step": 6136
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.76e-05,
      "loss": 1.0987,
      "step": 9204
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3273560876209883,
      "eval_loss": 1.0989995002746582,
      "eval_runtime": 16.7925,
      "eval_samples_per_second": 584.486,
      "eval_steps_per_second": 4.585,
      "step": 9204
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.680000000000001e-05,
      "loss": 1.0986,
      "step": 12272
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3273560876209883,
      "eval_loss": 1.0989333391189575,
      "eval_runtime": 16.8176,
      "eval_samples_per_second": 583.614,
      "eval_steps_per_second": 4.579,
      "step": 12272
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.6e-05,
      "loss": 1.0988,
      "step": 15340
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3273560876209883,
      "eval_loss": 1.110775113105774,
      "eval_runtime": 16.8012,
      "eval_samples_per_second": 584.185,
      "eval_steps_per_second": 4.583,
      "step": 15340
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.52e-05,
      "loss": 1.099,
      "step": 18408
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3544574630667346,
      "eval_loss": 1.096816897392273,
      "eval_runtime": 16.8121,
      "eval_samples_per_second": 583.805,
      "eval_steps_per_second": 4.58,
      "step": 18408
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.44e-05,
      "loss": 1.0988,
      "step": 21476
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3273560876209883,
      "eval_loss": 1.0975699424743652,
      "eval_runtime": 16.8047,
      "eval_samples_per_second": 584.062,
      "eval_steps_per_second": 4.582,
      "step": 21476
    },
    {
      "epoch": 7.0,
      "step": 21476,
      "total_flos": 4.022770393541509e+17,
      "train_loss": 1.0992188363973157,
      "train_runtime": 13829.8552,
      "train_samples_per_second": 1419.762,
      "train_steps_per_second": 11.092
    }
  ],
  "max_steps": 153400,
  "num_train_epochs": 50,
  "total_flos": 4.022770393541509e+17,
  "trial_name": null,
  "trial_params": null
}