| | --- |
| | library_name: transformers |
| | language: |
| | - en |
| | base_model: Hartunka/bert_base_km_5_v1 |
| | tags: |
| | - generated_from_trainer |
| | datasets: |
| | - glue |
| | metrics: |
| | - accuracy |
| | - f1 |
| | model-index: |
| | - name: bert_base_km_5_v1_qqp |
| | results: |
| | - task: |
| | name: Text Classification |
| | type: text-classification |
| | dataset: |
| | name: GLUE QQP |
| | type: glue |
| | args: qqp |
| | metrics: |
| | - name: Accuracy |
| | type: accuracy |
| | value: 0.8282958199356913 |
| | - name: F1 |
| | type: f1 |
| | value: 0.766545601291364 |
| | --- |
| | |
| | <!-- 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. --> |
| |
|
| | # bert_base_km_5_v1_qqp |
| | |
| | This model is a fine-tuned version of [Hartunka/bert_base_km_5_v1](https://huggingface.co/Hartunka/bert_base_km_5_v1) on the GLUE QQP dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.3769 |
| | - Accuracy: 0.8283 |
| | - F1: 0.7665 |
| | - Combined Score: 0.7974 |
| | |
| | ## 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: 5e-05 |
| | - train_batch_size: 256 |
| | - eval_batch_size: 256 |
| | - seed: 10 |
| | - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| | - lr_scheduler_type: linear |
| | - num_epochs: 50 |
| | |
| | ### Training results |
| | |
| | | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score | |
| | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:| |
| | | 0.4663 | 1.0 | 1422 | 0.4186 | 0.8002 | 0.7067 | 0.7534 | |
| | | 0.3533 | 2.0 | 2844 | 0.3769 | 0.8283 | 0.7665 | 0.7974 | |
| | | 0.2678 | 3.0 | 4266 | 0.3989 | 0.8297 | 0.7791 | 0.8044 | |
| | | 0.2011 | 4.0 | 5688 | 0.4220 | 0.8425 | 0.7772 | 0.8099 | |
| | | 0.1514 | 5.0 | 7110 | 0.4985 | 0.8437 | 0.7811 | 0.8124 | |
| | | 0.1188 | 6.0 | 8532 | 0.5644 | 0.8442 | 0.7816 | 0.8129 | |
| | | 0.0964 | 7.0 | 9954 | 0.6046 | 0.8413 | 0.7848 | 0.8131 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.50.2 |
| | - Pytorch 2.2.1+cu121 |
| | - Datasets 2.18.0 |
| | - Tokenizers 0.21.1 |
| | |
