run-5/checkpoint-552/trainer_state.json

{
  "best_metric": 0.9142857142857143,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-5\\checkpoint-552",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 552,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8612244897959184,
      "eval_loss": 0.6846103668212891,
      "eval_runtime": 1.159,
      "eval_samples_per_second": 211.389,
      "eval_steps_per_second": 13.805,
      "step": 138
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8979591836734694,
      "eval_loss": 0.4278050363063812,
      "eval_runtime": 1.189,
      "eval_samples_per_second": 206.056,
      "eval_steps_per_second": 13.457,
      "step": 276
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9102040816326531,
      "eval_loss": 0.36468449234962463,
      "eval_runtime": 1.2525,
      "eval_samples_per_second": 195.604,
      "eval_steps_per_second": 12.774,
      "step": 414
    },
    {
      "epoch": 3.62,
      "learning_rate": 9.112610205064478e-06,
      "loss": 0.6676,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9142857142857143,
      "eval_loss": 0.3511519432067871,
      "eval_runtime": 1.279,
      "eval_samples_per_second": 191.556,
      "eval_steps_per_second": 12.51,
      "step": 552
    }
  ],
  "logging_steps": 500,
  "max_steps": 552,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 6218171249850.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 9.67338621768383e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 16,
    "seed": 1
  }
}