run-1/checkpoint-216/trainer_state.json

{
  "best_metric": 0.40073101077295625,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-216",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 216,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 4.080541133880615,
      "eval_pearson": 0.19568172531555392,
      "eval_runtime": 0.8653,
      "eval_samples_per_second": 1733.563,
      "eval_spearmanr": 0.19374973140130425,
      "eval_steps_per_second": 108.637,
      "step": 72
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.333472728729248,
      "eval_pearson": 0.3042437087139711,
      "eval_runtime": 0.8835,
      "eval_samples_per_second": 1697.883,
      "eval_spearmanr": 0.3379135804732249,
      "eval_steps_per_second": 106.401,
      "step": 144
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.1389713287353516,
      "eval_pearson": 0.40073101077295625,
      "eval_runtime": 0.8693,
      "eval_samples_per_second": 1725.481,
      "eval_spearmanr": 0.4525934449018444,
      "eval_steps_per_second": 108.13,
      "step": 216
    }
  ],
  "logging_steps": 500,
  "max_steps": 288,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.9518876446612178e-06,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 8,
    "seed": 1
  }
}