| --- |
| 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 |
| model-index: |
| - name: bert_uncased_L-2_H-128_A-2_qnli |
| results: |
| - task: |
| name: Text Classification |
| type: text-classification |
| dataset: |
| name: GLUE QNLI |
| type: glue |
| args: qnli |
| metrics: |
| - name: Accuracy |
| type: accuracy |
| value: 0.8004759289767527 |
| --- |
| |
| <!-- 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_qnli |
| |
| 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 QNLI dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.4352 |
| - Accuracy: 0.8005 |
| |
| ## 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 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | 0.5442 | 1.0 | 410 | 0.4932 | 0.7679 | |
| | 0.4861 | 2.0 | 820 | 0.4810 | 0.7692 | |
| | 0.4609 | 3.0 | 1230 | 0.4527 | 0.7882 | |
| | 0.4422 | 4.0 | 1640 | 0.4639 | 0.7803 | |
| | 0.4256 | 5.0 | 2050 | 0.4744 | 0.7770 | |
| | 0.409 | 6.0 | 2460 | 0.4702 | 0.7809 | |
| | 0.392 | 7.0 | 2870 | 0.4352 | 0.8005 | |
| | 0.3772 | 8.0 | 3280 | 0.4429 | 0.7970 | |
| | 0.3608 | 9.0 | 3690 | 0.4630 | 0.7875 | |
| | 0.3459 | 10.0 | 4100 | 0.5137 | 0.7688 | |
| | 0.3354 | 11.0 | 4510 | 0.4836 | 0.7880 | |
| | 0.3213 | 12.0 | 4920 | 0.4981 | 0.7842 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.46.3 |
| - Pytorch 2.2.1+cu118 |
| - Datasets 2.17.0 |
| - Tokenizers 0.20.3 |
| |
