run-10/checkpoint-552/trainer_state.json

{
  "best_metric": 0.9224489795918367,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-10\\checkpoint-414",
  "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": 0.8571428571428571,
      "eval_loss": 0.7101830244064331,
      "eval_runtime": 1.1461,
      "eval_samples_per_second": 213.774,
      "eval_steps_per_second": 13.961,
      "step": 138
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.889795918367347,
      "eval_loss": 0.43645206093788147,
      "eval_runtime": 1.148,
      "eval_samples_per_second": 213.415,
      "eval_steps_per_second": 13.937,
      "step": 276
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9224489795918367,
      "eval_loss": 0.35530897974967957,
      "eval_runtime": 1.169,
      "eval_samples_per_second": 209.582,
      "eval_steps_per_second": 13.687,
      "step": 414
    },
    {
      "epoch": 3.62,
      "learning_rate": 2.4223640179474175e-05,
      "loss": 0.6984,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9183673469387755,
      "eval_loss": 0.3266046643257141,
      "eval_runtime": 1.145,
      "eval_samples_per_second": 213.974,
      "eval_steps_per_second": 13.974,
      "step": 552
    }
  ],
  "logging_steps": 500,
  "max_steps": 690,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 6141098220600.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 8.797006170440622e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 16,
    "seed": 40
  }
}