run-1/checkpoint-428/trainer_state.json

{
  "best_metric": 0.6352032367163551,
  "best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-1/checkpoint-107",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 428,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.3989429175853729,
      "eval_matthews_correlation": 0.6352032367163551,
      "eval_runtime": 8.55,
      "eval_samples_per_second": 121.988,
      "eval_steps_per_second": 7.719,
      "step": 107
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.7654077410697937,
      "eval_matthews_correlation": 0.6243387594128297,
      "eval_runtime": 8.6801,
      "eval_samples_per_second": 120.16,
      "eval_steps_per_second": 7.604,
      "step": 214
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.0246310234069824,
      "eval_matthews_correlation": 0.6044964516136625,
      "eval_runtime": 8.7151,
      "eval_samples_per_second": 119.678,
      "eval_steps_per_second": 7.573,
      "step": 321
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.1292502880096436,
      "eval_matthews_correlation": 0.6070286836001448,
      "eval_runtime": 8.7702,
      "eval_samples_per_second": 118.926,
      "eval_steps_per_second": 7.526,
      "step": 428
    }
  ],
  "logging_steps": 500,
  "max_steps": 535,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.359139262812914e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 8,
    "seed": 19
  }
}