| | --- |
| | library_name: transformers |
| | language: |
| | - en |
| | license: apache-2.0 |
| | base_model: gokulsrinivasagan/tinybert_base_train_kd |
| | tags: |
| | - generated_from_trainer |
| | datasets: |
| | - glue |
| | metrics: |
| | - accuracy |
| | - f1 |
| | model-index: |
| | - name: tinybert_base_train_kd_qqp |
| | results: |
| | - task: |
| | name: Text Classification |
| | type: text-classification |
| | dataset: |
| | name: GLUE QQP |
| | type: glue |
| | args: qqp |
| | metrics: |
| | - name: Accuracy |
| | type: accuracy |
| | value: 0.8704922087558743 |
| | - name: F1 |
| | type: f1 |
| | value: 0.8217592592592593 |
| | --- |
| | |
| | <!-- 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. --> |
| |
|
| | # tinybert_base_train_kd_qqp |
| |
|
| | This model is a fine-tuned version of [gokulsrinivasagan/tinybert_base_train_kd](https://huggingface.co/gokulsrinivasagan/tinybert_base_train_kd) on the GLUE QQP dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.3005 |
| | - Accuracy: 0.8705 |
| | - F1: 0.8218 |
| | - Combined Score: 0.8461 |
| |
|
| | ## 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 | |
| | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:| |
| | | 0.4061 | 1.0 | 1422 | 0.3443 | 0.8430 | 0.7827 | 0.8129 | |
| | | 0.3179 | 2.0 | 2844 | 0.3138 | 0.8611 | 0.8150 | 0.8381 | |
| | | 0.269 | 3.0 | 4266 | 0.3077 | 0.8663 | 0.8258 | 0.8461 | |
| | | 0.2275 | 4.0 | 5688 | 0.3005 | 0.8705 | 0.8218 | 0.8461 | |
| | | 0.1923 | 5.0 | 7110 | 0.3269 | 0.8750 | 0.8254 | 0.8502 | |
| | | 0.1614 | 6.0 | 8532 | 0.3224 | 0.8750 | 0.8291 | 0.8521 | |
| | | 0.1349 | 7.0 | 9954 | 0.3559 | 0.8761 | 0.8387 | 0.8574 | |
| | | 0.1132 | 8.0 | 11376 | 0.4348 | 0.8775 | 0.8324 | 0.8550 | |
| | | 0.0966 | 9.0 | 12798 | 0.4351 | 0.8796 | 0.8394 | 0.8595 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.51.2 |
| | - Pytorch 2.6.0+cu126 |
| | - Datasets 3.5.0 |
| | - Tokenizers 0.21.1 |
| |
|
