{
  "best_metric": 0.4752452075481415,
  "best_model_checkpoint": "hBERTv1_new_pretrain_sst2/checkpoint-1581",
  "epoch": 8.0,
  "global_step": 4216,
  "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": 0.4258,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8061926605504587,
      "eval_loss": 0.49944204092025757,
      "eval_runtime": 1.5738,
      "eval_samples_per_second": 554.064,
      "eval_steps_per_second": 4.448,
      "step": 527
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.2652,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8004587155963303,
      "eval_loss": 0.5633484125137329,
      "eval_runtime": 1.5754,
      "eval_samples_per_second": 553.509,
      "eval_steps_per_second": 4.443,
      "step": 1054
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.76e-05,
      "loss": 0.2214,
      "step": 1581
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7878440366972477,
      "eval_loss": 0.4752452075481415,
      "eval_runtime": 1.5737,
      "eval_samples_per_second": 554.116,
      "eval_steps_per_second": 4.448,
      "step": 1581
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.680000000000001e-05,
      "loss": 0.2014,
      "step": 2108
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7889908256880734,
      "eval_loss": 0.532899796962738,
      "eval_runtime": 1.5757,
      "eval_samples_per_second": 553.39,
      "eval_steps_per_second": 4.442,
      "step": 2108
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.6e-05,
      "loss": 0.1813,
      "step": 2635
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7924311926605505,
      "eval_loss": 0.541002631187439,
      "eval_runtime": 1.5754,
      "eval_samples_per_second": 553.495,
      "eval_steps_per_second": 4.443,
      "step": 2635
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.52e-05,
      "loss": 0.1679,
      "step": 3162
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8084862385321101,
      "eval_loss": 0.5856852531433105,
      "eval_runtime": 1.575,
      "eval_samples_per_second": 553.657,
      "eval_steps_per_second": 4.444,
      "step": 3162
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.44e-05,
      "loss": 0.1526,
      "step": 3689
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8038990825688074,
      "eval_loss": 0.7653970718383789,
      "eval_runtime": 1.5719,
      "eval_samples_per_second": 554.734,
      "eval_steps_per_second": 4.453,
      "step": 3689
    },
    {
      "epoch": 8.0,
      "learning_rate": 3.3600000000000004e-05,
      "loss": 0.1405,
      "step": 4216
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7878440366972477,
      "eval_loss": 0.671506941318512,
      "eval_runtime": 1.5757,
      "eval_samples_per_second": 553.416,
      "eval_steps_per_second": 4.443,
      "step": 4216
    },
    {
      "epoch": 8.0,
      "step": 4216,
      "total_flos": 7.979335412403405e+16,
      "train_loss": 0.21951200025583806,
      "train_runtime": 2980.0427,
      "train_samples_per_second": 1130.001,
      "train_steps_per_second": 8.842
    }
  ],
  "max_steps": 26350,
  "num_train_epochs": 50,
  "total_flos": 7.979335412403405e+16,
  "trial_name": null,
  "trial_params": null
}