run-5/checkpoint-804/trainer_state.json

{
  "best_metric": 0.0,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-268",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 804,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.5973381996154785,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.8179,
      "eval_samples_per_second": 1275.195,
      "eval_steps_per_second": 80.693,
      "step": 268
    },
    {
      "epoch": 1.87,
      "learning_rate": 8.966586782094777e-07,
      "loss": 0.5938,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5737119913101196,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.3554,
      "eval_samples_per_second": 769.5,
      "eval_steps_per_second": 48.693,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5607194304466248,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.3243,
      "eval_samples_per_second": 787.602,
      "eval_steps_per_second": 49.839,
      "step": 804
    }
  ],
  "logging_steps": 500,
  "max_steps": 804,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 95454920824884.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.3714262410540132e-06,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 32,
    "seed": 36
  }
}