run-4/checkpoint-165/trainer_state.json

{
  "best_metric": 0.6924242424242424,
  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-4\\checkpoint-165",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 165,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 2.7562580137457846e-05,
      "loss": 0.2619,
      "step": 55
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6757575757575758,
      "eval_loss": 0.2587513327598572,
      "eval_runtime": 3.3651,
      "eval_samples_per_second": 588.396,
      "eval_steps_per_second": 4.755,
      "step": 55
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.3781290068728923e-05,
      "loss": 0.2565,
      "step": 110
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6883838383838384,
      "eval_loss": 0.25351962447166443,
      "eval_runtime": 3.3732,
      "eval_samples_per_second": 586.986,
      "eval_steps_per_second": 4.743,
      "step": 110
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.2525,
      "step": 165
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6924242424242424,
      "eval_loss": 0.2523554265499115,
      "eval_runtime": 3.3099,
      "eval_samples_per_second": 598.21,
      "eval_steps_per_second": 4.834,
      "step": 165
    }
  ],
  "logging_steps": 500,
  "max_steps": 165,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2524547079600.0,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.37297394921136384,
    "learning_rate": 4.134387020618677e-05,
    "num_train_epochs": 3,
    "temperature": 9
  }
}