| --- |
| license: apache-2.0 |
| base_model: Intel/dynamic_tinybert |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: dynamic_tinybert-finetuned-squad |
| results: [] |
| --- |
| |
| <!-- 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. --> |
|
|
| # dynamic_tinybert-finetuned-squad |
| |
| This model is a fine-tuned version of [Intel/dynamic_tinybert](https://huggingface.co/Intel/dynamic_tinybert) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 1.4682 |
| |
| ## 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: 2e-05 |
| - train_batch_size: 16 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 3 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:-----:|:---------------:| |
| | 0.5086 | 1.0 | 5533 | 1.1495 | |
| | 0.3869 | 2.0 | 11066 | 1.2774 | |
| | 0.2659 | 3.0 | 16599 | 1.4682 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.36.2 |
| - Pytorch 2.1.2+cu121 |
| - Datasets 2.16.1 |
| - Tokenizers 0.15.0 |
| |
