| --- |
| library_name: transformers |
| language: |
| - en |
| base_model: Hartunka/tiny_bert_rand_5_v2 |
| tags: |
| - generated_from_trainer |
| datasets: |
| - glue |
| metrics: |
| - accuracy |
| model-index: |
| - name: tiny_bert_rand_5_v2_qnli |
| results: |
| - task: |
| name: Text Classification |
| type: text-classification |
| dataset: |
| name: GLUE QNLI |
| type: glue |
| args: qnli |
| metrics: |
| - name: Accuracy |
| type: accuracy |
| value: 0.6267618524620172 |
| --- |
| |
| <!-- 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_rand_5_v2_qnli |
| |
| This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v2](https://huggingface.co/Hartunka/tiny_bert_rand_5_v2) on the GLUE QNLI dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.6468 |
| - Accuracy: 0.6268 |
| |
| ## 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 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | 0.6655 | 1.0 | 410 | 0.6482 | 0.6207 | |
| | 0.636 | 2.0 | 820 | 0.6468 | 0.6268 | |
| | 0.5935 | 3.0 | 1230 | 0.6598 | 0.6231 | |
| | 0.5345 | 4.0 | 1640 | 0.6996 | 0.6246 | |
| | 0.4697 | 5.0 | 2050 | 0.7827 | 0.6143 | |
| | 0.4077 | 6.0 | 2460 | 0.8890 | 0.6041 | |
| | 0.3487 | 7.0 | 2870 | 1.0397 | 0.6042 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.50.2 |
| - Pytorch 2.2.1+cu121 |
| - Datasets 2.18.0 |
| - Tokenizers 0.21.1 |
| |
