run-8/checkpoint-125/trainer_state.json

{
  "best_metric": 0.0,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-25",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.6461844444274902,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 3.4192,
      "eval_samples_per_second": 29.247,
      "eval_steps_per_second": 2.047,
      "step": 25
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6415550708770752,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 5.8192,
      "eval_samples_per_second": 17.184,
      "eval_steps_per_second": 1.203,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6404489278793335,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 6.5835,
      "eval_samples_per_second": 15.19,
      "eval_steps_per_second": 1.063,
      "step": 75
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6379709839820862,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 5.6789,
      "eval_samples_per_second": 17.609,
      "eval_steps_per_second": 1.233,
      "step": 100
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6394399404525757,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 3.3862,
      "eval_samples_per_second": 29.532,
      "eval_steps_per_second": 2.067,
      "step": 125
    }
  ],
  "logging_steps": 500,
  "max_steps": 125,
  "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": 7.381702785298678e-06,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 8,
    "seed": 37
  }
}