run-1/checkpoint-804/trainer_state.json

{
  "best_metric": 0.5308567193176762,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.4548027515411377,
      "eval_matthews_correlation": 0.47933610275431493,
      "eval_runtime": 0.987,
      "eval_samples_per_second": 1056.73,
      "eval_steps_per_second": 132.724,
      "step": 268
    },
    {
      "epoch": 1.8656716417910446,
      "grad_norm": 7.233431816101074,
      "learning_rate": 1.9349684143738284e-05,
      "loss": 0.4133,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.46222877502441406,
      "eval_matthews_correlation": 0.5274949902750498,
      "eval_runtime": 1.8381,
      "eval_samples_per_second": 567.436,
      "eval_steps_per_second": 71.269,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6320855021476746,
      "eval_matthews_correlation": 0.5308567193176762,
      "eval_runtime": 1.085,
      "eval_samples_per_second": 961.258,
      "eval_steps_per_second": 120.733,
      "step": 804
    }
  ],
  "logging_steps": 500,
  "max_steps": 804,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 95031128639340.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 5.117482253804467e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 32,
    "seed": 16
  }
}