run-1/checkpoint-135/trainer_state.json

{
  "best_metric": 0.3367711412058402,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-135",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 135,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.6137323379516602,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.4985,
      "eval_samples_per_second": 2092.402,
      "eval_steps_per_second": 132.405,
      "step": 27
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5712264180183411,
      "eval_matthews_correlation": 0.20590544441185202,
      "eval_runtime": 0.5232,
      "eval_samples_per_second": 1993.581,
      "eval_steps_per_second": 126.152,
      "step": 54
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5899873375892639,
      "eval_matthews_correlation": 0.2957275464729565,
      "eval_runtime": 0.6455,
      "eval_samples_per_second": 1615.69,
      "eval_steps_per_second": 102.239,
      "step": 81
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6281552314758301,
      "eval_matthews_correlation": 0.3259325330443582,
      "eval_runtime": 0.7017,
      "eval_samples_per_second": 1486.423,
      "eval_steps_per_second": 94.059,
      "step": 108
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6593989133834839,
      "eval_matthews_correlation": 0.3367711412058402,
      "eval_runtime": 0.6019,
      "eval_samples_per_second": 1732.92,
      "eval_steps_per_second": 109.657,
      "step": 135
    }
  ],
  "logging_steps": 500,
  "max_steps": 135,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 3.5363396216788776e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 32,
    "seed": 2
  }
}