{
  "best_metric": 0.6844189763069153,
  "best_model_checkpoint": "hBERTv1_new_pretrain_w_init__wnli/checkpoint-10",
  "epoch": 7.0,
  "global_step": 35,
  "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": 0.9261,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5352112676056338,
      "eval_loss": 0.6915163993835449,
      "eval_runtime": 0.1353,
      "eval_samples_per_second": 524.626,
      "eval_steps_per_second": 7.389,
      "step": 5
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.7312,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5633802816901409,
      "eval_loss": 0.6844189763069153,
      "eval_runtime": 0.1352,
      "eval_samples_per_second": 525.264,
      "eval_steps_per_second": 7.398,
      "step": 10
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.76e-05,
      "loss": 0.7289,
      "step": 15
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5633802816901409,
      "eval_loss": 0.733659565448761,
      "eval_runtime": 0.1387,
      "eval_samples_per_second": 511.967,
      "eval_steps_per_second": 7.211,
      "step": 15
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.680000000000001e-05,
      "loss": 0.7656,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.43661971830985913,
      "eval_loss": 0.758527934551239,
      "eval_runtime": 0.1346,
      "eval_samples_per_second": 527.673,
      "eval_steps_per_second": 7.432,
      "step": 20
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.6e-05,
      "loss": 0.7189,
      "step": 25
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5633802816901409,
      "eval_loss": 0.6906359791755676,
      "eval_runtime": 0.1389,
      "eval_samples_per_second": 511.121,
      "eval_steps_per_second": 7.199,
      "step": 25
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.52e-05,
      "loss": 0.7167,
      "step": 30
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5633802816901409,
      "eval_loss": 0.6910760402679443,
      "eval_runtime": 0.1418,
      "eval_samples_per_second": 500.863,
      "eval_steps_per_second": 7.054,
      "step": 30
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.44e-05,
      "loss": 0.7089,
      "step": 35
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.43661971830985913,
      "eval_loss": 0.7181998491287231,
      "eval_runtime": 0.1365,
      "eval_samples_per_second": 520.086,
      "eval_steps_per_second": 7.325,
      "step": 35
    },
    {
      "epoch": 7.0,
      "step": 35,
      "total_flos": 658290182717440.0,
      "train_loss": 0.7566231863839286,
      "train_runtime": 61.1061,
      "train_samples_per_second": 519.588,
      "train_steps_per_second": 4.091
    }
  ],
  "max_steps": 250,
  "num_train_epochs": 50,
  "total_flos": 658290182717440.0,
  "trial_name": null,
  "trial_params": null
}