| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: deepvk/RuModernBERT-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: RuHalluBERT-base-v5 |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # RuHalluBERT-base-v5 |
|
|
| This model is a fine-tuned version of [deepvk/RuModernBERT-base](https://huggingface.co/deepvk/RuModernBERT-base) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.6279 |
| - F1 Macro: 0.6522 |
| - F1 Class1: 0.6352 |
| - F1 Class0: 0.6693 |
| - Accuracy: 0.6531 |
| - Precision Macro: 0.6526 |
| - Recall Macro: 0.6522 |
|
|
| ## Model description |
|
|
| More information needed |
|
|
| ## Intended uses & limitations |
|
|
| More information needed |
|
|
| ## Training and evaluation data |
|
|
| More information needed |
|
|
| ## Training procedure |
|
|
| ### Training hyperparameters |
|
|
| The following hyperparameters were used during training: |
| - learning_rate: 2e-05 |
| - train_batch_size: 2 |
| - eval_batch_size: 2 |
| - seed: 42 |
| - distributed_type: multi-GPU |
| - gradient_accumulation_steps: 16 |
| - total_train_batch_size: 32 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 0.06 |
| - num_epochs: 10 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Class1 | F1 Class0 | Accuracy | Precision Macro | Recall Macro | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:---------:|:--------:|:---------------:|:------------:| |
| | 11.0041 | 1.0 | 123 | 0.6441 | 0.6245 | 0.5951 | 0.6539 | 0.6268 | 0.6269 | 0.6250 | |
| | 10.3103 | 2.0 | 246 | 0.6137 | 0.6680 | 0.6653 | 0.6708 | 0.6680 | 0.6683 | 0.6684 | |
| | 9.7315 | 3.0 | 369 | 0.6577 | 0.6269 | 0.7 | 0.5538 | 0.6412 | 0.6799 | 0.6479 | |
| | 8.9430 | 4.0 | 492 | 0.6604 | 0.6395 | 0.7205 | 0.5585 | 0.6577 | 0.7147 | 0.6653 | |
| | 7.8493 | 5.0 | 615 | 0.6796 | 0.6279 | 0.5474 | 0.7085 | 0.6454 | 0.6660 | 0.6393 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 5.8.1 |
| - Pytorch 2.11.0+cu130 |
| - Datasets 4.8.5 |
| - Tokenizers 0.22.2 |
|
|
