| --- |
| library_name: transformers |
| language: |
| - en |
| license: apache-2.0 |
| base_model: google/bert_uncased_L-2_H-128_A-2 |
| tags: |
| - generated_from_trainer |
| datasets: |
| - glue |
| metrics: |
| - accuracy |
| - f1 |
| model-index: |
| - name: bert_uncased_L-2_H-128_A-2_qqp |
| results: |
| - task: |
| name: Text Classification |
| type: text-classification |
| dataset: |
| name: GLUE QQP |
| type: glue |
| args: qqp |
| metrics: |
| - name: Accuracy |
| type: accuracy |
| value: 0.8481573089290131 |
| - name: F1 |
| type: f1 |
| value: 0.8112876948141773 |
| --- |
| |
| <!-- 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_uncased_L-2_H-128_A-2_qqp |
| |
| This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the GLUE QQP dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.3371 |
| - Accuracy: 0.8482 |
| - F1: 0.8113 |
| - Combined Score: 0.8297 |
| |
| ## 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 | |
| |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:| |
| | 0.4684 | 1.0 | 1422 | 0.4047 | 0.8017 | 0.7601 | 0.7809 | |
| | 0.3983 | 2.0 | 2844 | 0.3846 | 0.8136 | 0.7782 | 0.7959 | |
| | 0.371 | 3.0 | 4266 | 0.3736 | 0.8217 | 0.7890 | 0.8054 | |
| | 0.3511 | 4.0 | 5688 | 0.3561 | 0.8330 | 0.7976 | 0.8153 | |
| | 0.3338 | 5.0 | 7110 | 0.3568 | 0.8332 | 0.7990 | 0.8161 | |
| | 0.3199 | 6.0 | 8532 | 0.3526 | 0.8369 | 0.8028 | 0.8198 | |
| | 0.3067 | 7.0 | 9954 | 0.3513 | 0.8392 | 0.8046 | 0.8219 | |
| | 0.296 | 8.0 | 11376 | 0.3567 | 0.8361 | 0.8044 | 0.8203 | |
| | 0.2857 | 9.0 | 12798 | 0.3518 | 0.8407 | 0.8071 | 0.8239 | |
| | 0.2776 | 10.0 | 14220 | 0.3371 | 0.8482 | 0.8113 | 0.8297 | |
| | 0.2679 | 11.0 | 15642 | 0.3506 | 0.8446 | 0.8105 | 0.8276 | |
| | 0.2609 | 12.0 | 17064 | 0.3419 | 0.8511 | 0.8145 | 0.8328 | |
| | 0.2539 | 13.0 | 18486 | 0.3397 | 0.8524 | 0.8164 | 0.8344 | |
| | 0.2461 | 14.0 | 19908 | 0.3523 | 0.8525 | 0.8164 | 0.8344 | |
| | 0.2401 | 15.0 | 21330 | 0.3407 | 0.8546 | 0.8181 | 0.8363 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.46.3 |
| - Pytorch 2.2.1+cu118 |
| - Datasets 2.17.0 |
| - Tokenizers 0.20.3 |
| |
