run-6/checkpoint-108/trainer_state.json

{
  "best_metric": 0.8216396482083662,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-6/checkpoint-108",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 108,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.9094555377960205,
      "eval_pearson": 0.5682043731058958,
      "eval_runtime": 0.8058,
      "eval_samples_per_second": 1861.603,
      "eval_spearmanr": 0.5712894898305707,
      "eval_steps_per_second": 116.66,
      "step": 36
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.9170708060264587,
      "eval_pearson": 0.8095416463018199,
      "eval_runtime": 0.7946,
      "eval_samples_per_second": 1887.657,
      "eval_spearmanr": 0.8070877388190617,
      "eval_steps_per_second": 118.293,
      "step": 72
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7417043447494507,
      "eval_pearson": 0.8216396482083662,
      "eval_runtime": 0.8035,
      "eval_samples_per_second": 1866.838,
      "eval_spearmanr": 0.821914669684342,
      "eval_steps_per_second": 116.989,
      "step": 108
    }
  ],
  "logging_steps": 500,
  "max_steps": 108,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 5.712636964604973e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 16,
    "seed": 36
  }
}