run-21/checkpoint-1650/trainer_state.json

{
  "best_metric": 0.926530612244898,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-21\\checkpoint-1650",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1650,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.91,
      "learning_rate": 4.073808226669123e-05,
      "loss": 1.2386,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8530612244897959,
      "eval_loss": 0.5178775787353516,
      "eval_runtime": 1.124,
      "eval_samples_per_second": 217.971,
      "eval_steps_per_second": 14.235,
      "step": 550
    },
    {
      "epoch": 1.82,
      "learning_rate": 2.875629336472322e-05,
      "loss": 0.463,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9224489795918367,
      "eval_loss": 0.3506206274032593,
      "eval_runtime": 1.407,
      "eval_samples_per_second": 174.129,
      "eval_steps_per_second": 11.372,
      "step": 1100
    },
    {
      "epoch": 2.73,
      "learning_rate": 1.677450446275521e-05,
      "loss": 0.3174,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.926530612244898,
      "eval_loss": 0.31416016817092896,
      "eval_runtime": 1.329,
      "eval_samples_per_second": 184.349,
      "eval_steps_per_second": 12.039,
      "step": 1650
    }
  ],
  "logging_steps": 500,
  "max_steps": 2200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 2875119593850.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 5.271987116865924e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 4,
    "seed": 33
  }
}