| | --- |
| | library_name: transformers |
| | language: |
| | - en |
| | base_model: Hartunka/tiny_bert_km_5_v1 |
| | tags: |
| | - generated_from_trainer |
| | datasets: |
| | - glue |
| | metrics: |
| | - accuracy |
| | - f1 |
| | model-index: |
| | - name: tiny_bert_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: 0.8229037843185754 |
| | - name: F1 |
| | type: f1 |
| | value: 0.7561474014031742 |
| | --- |
| | |
| | <!-- 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. --> |
| |
|
| | # tiny_bert_km_5_v1_qqp |
| | |
| | This model is a fine-tuned version of [Hartunka/tiny_bert_km_5_v1](https://huggingface.co/Hartunka/tiny_bert_km_5_v1) on the GLUE QQP dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.3982 |
| | - Accuracy: 0.8229 |
| | - F1: 0.7561 |
| | - Combined Score: 0.7895 |
| | |
| | ## 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 | |
| | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:| |
| | | 0.4854 | 1.0 | 1422 | 0.4320 | 0.7934 | 0.7100 | 0.7517 | |
| | | 0.3893 | 2.0 | 2844 | 0.4019 | 0.8130 | 0.7421 | 0.7775 | |
| | | 0.3257 | 3.0 | 4266 | 0.3982 | 0.8229 | 0.7561 | 0.7895 | |
| | | 0.2734 | 4.0 | 5688 | 0.4342 | 0.8248 | 0.7447 | 0.7847 | |
| | | 0.2309 | 5.0 | 7110 | 0.4551 | 0.8302 | 0.7638 | 0.7970 | |
| | | 0.1964 | 6.0 | 8532 | 0.4515 | 0.8269 | 0.7721 | 0.7995 | |
| | | 0.1681 | 7.0 | 9954 | 0.4995 | 0.8293 | 0.7751 | 0.8022 | |
| | | 0.146 | 8.0 | 11376 | 0.5505 | 0.8304 | 0.7759 | 0.8031 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.50.2 |
| | - Pytorch 2.2.1+cu121 |
| | - Datasets 2.18.0 |
| | - Tokenizers 0.21.1 |
| | |
