run-0/checkpoint-804/trainer_state.json

{
  "best_metric": 0.5325167447166456,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-804",
  "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": 0.4662749767303467,
      "eval_matthews_correlation": 0.42386559425174,
      "eval_runtime": 30.5523,
      "eval_samples_per_second": 34.138,
      "eval_steps_per_second": 2.16,
      "step": 268
    },
    {
      "epoch": 1.87,
      "learning_rate": 3.9114607492078965e-05,
      "loss": 0.425,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5247857570648193,
      "eval_matthews_correlation": 0.48074996963903815,
      "eval_runtime": 31.3458,
      "eval_samples_per_second": 33.274,
      "eval_steps_per_second": 2.106,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5911181569099426,
      "eval_matthews_correlation": 0.5325167447166456,
      "eval_runtime": 30.5442,
      "eval_samples_per_second": 34.147,
      "eval_steps_per_second": 2.161,
      "step": 804
    }
  ],
  "logging_steps": 500,
  "max_steps": 1072,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 95542370006028.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 7.330569795718295e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 32,
    "seed": 19
  }
}