run-6/checkpoint-690/trainer_state.json

{
  "best_metric": 0.8979591836734694,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-6\\checkpoint-552",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 690,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7836734693877551,
      "eval_loss": 0.9130998849868774,
      "eval_runtime": 1.126,
      "eval_samples_per_second": 217.584,
      "eval_steps_per_second": 14.21,
      "step": 138
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8612244897959184,
      "eval_loss": 0.5591093897819519,
      "eval_runtime": 1.146,
      "eval_samples_per_second": 213.787,
      "eval_steps_per_second": 13.962,
      "step": 276
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8938775510204081,
      "eval_loss": 0.4424550533294678,
      "eval_runtime": 1.167,
      "eval_samples_per_second": 209.939,
      "eval_steps_per_second": 13.71,
      "step": 414
    },
    {
      "epoch": 3.62,
      "learning_rate": 1.8440945343636115e-05,
      "loss": 0.8394,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8979591836734694,
      "eval_loss": 0.3997510075569153,
      "eval_runtime": 1.169,
      "eval_samples_per_second": 209.581,
      "eval_steps_per_second": 13.687,
      "step": 552
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8979591836734694,
      "eval_loss": 0.38741201162338257,
      "eval_runtime": 1.159,
      "eval_samples_per_second": 211.389,
      "eval_steps_per_second": 13.805,
      "step": 690
    }
  ],
  "logging_steps": 500,
  "max_steps": 690,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 6399527187900.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 6.696974887952063e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 16,
    "seed": 16
  }
}