| | --- |
| | license: cc-by-4.0 |
| | base_model: deepset/bert-base-cased-squad2 |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: bert-26 |
| | 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. --> |
| |
|
| | # bert-26 |
| |
|
| | This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 6.8756 |
| |
|
| | ## 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: 32 |
| | - eval_batch_size: 32 |
| | - 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 | |
| | |:-------------:|:-----:|:----:|:---------------:| |
| | | 7.1774 | 0.18 | 5 | 7.2847 | |
| | | 6.9676 | 0.36 | 10 | 7.1874 | |
| | | 6.9639 | 0.54 | 15 | 7.1658 | |
| | | 6.821 | 0.71 | 20 | 7.1371 | |
| | | 6.7658 | 0.89 | 25 | 7.1082 | |
| | | 6.7752 | 1.07 | 30 | 7.0762 | |
| | | 6.7502 | 1.25 | 35 | 7.0440 | |
| | | 6.7292 | 1.43 | 40 | 7.0080 | |
| | | 6.6645 | 1.61 | 45 | 6.9767 | |
| | | 6.6253 | 1.79 | 50 | 6.9528 | |
| | | 6.6661 | 1.96 | 55 | 6.9324 | |
| | | 6.6808 | 2.14 | 60 | 6.9133 | |
| | | 6.692 | 2.32 | 65 | 6.8985 | |
| | | 6.5486 | 2.5 | 70 | 6.8864 | |
| | | 6.5355 | 2.68 | 75 | 6.8789 | |
| | | 6.5888 | 2.86 | 80 | 6.8756 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.34.1 |
| | - Pytorch 2.0.1+cu118 |
| | - Datasets 2.14.5 |
| | - Tokenizers 0.14.1 |
| |
|
