run-3/checkpoint-70/trainer_state.json

{
  "best_metric": 0.0,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-14",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 70,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.6366313099861145,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.7373,
      "eval_samples_per_second": 1414.699,
      "eval_steps_per_second": 89.521,
      "step": 14
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6198997497558594,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.0022,
      "eval_samples_per_second": 1040.684,
      "eval_steps_per_second": 65.853,
      "step": 28
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6155935525894165,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.8197,
      "eval_samples_per_second": 1272.398,
      "eval_steps_per_second": 80.516,
      "step": 42
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6139842867851257,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.3039,
      "eval_samples_per_second": 799.914,
      "eval_steps_per_second": 50.618,
      "step": 56
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6134741902351379,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.7992,
      "eval_samples_per_second": 1305.091,
      "eval_steps_per_second": 82.585,
      "step": 70
    }
  ],
  "logging_steps": 500,
  "max_steps": 70,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 5.334111722797918e-06,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 64,
    "seed": 26
  }
}