run-0/checkpoint-216/trainer_state.json

{
  "best_metric": 0.8350533952135925,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/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": 1.1317814588546753,
      "eval_pearson": 0.7925397117075783,
      "eval_runtime": 0.9029,
      "eval_samples_per_second": 1661.35,
      "eval_spearmanr": 0.7981526098929177,
      "eval_steps_per_second": 104.111,
      "step": 72
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8140504360198975,
      "eval_pearson": 0.8184498144194529,
      "eval_runtime": 1.1042,
      "eval_samples_per_second": 1358.431,
      "eval_spearmanr": 0.8199506621029472,
      "eval_steps_per_second": 85.128,
      "step": 144
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7895862460136414,
      "eval_pearson": 0.8350533952135925,
      "eval_runtime": 1.2556,
      "eval_samples_per_second": 1194.637,
      "eval_spearmanr": 0.8311768906317339,
      "eval_steps_per_second": 74.864,
      "step": 216
    }
  ],
  "logging_steps": 500,
  "max_steps": 360,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 7.503545930910804e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 8,
    "seed": 19
  }
}