|
--- |
|
license: cc-by-4.0 |
|
base_model: deepset/bert-base-cased-squad2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bert-30 |
|
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-30 |
|
|
|
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: 11.5113 |
|
|
|
## 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: 3e-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: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 11.3133 | 0.09 | 5 | 12.3059 | |
|
| 11.4119 | 0.18 | 10 | 12.2326 | |
|
| 10.9781 | 0.27 | 15 | 12.1623 | |
|
| 11.087 | 0.36 | 20 | 12.0961 | |
|
| 11.0516 | 0.45 | 25 | 12.0332 | |
|
| 11.0596 | 0.55 | 30 | 11.9737 | |
|
| 10.3306 | 0.64 | 35 | 11.9182 | |
|
| 10.9488 | 0.73 | 40 | 11.8666 | |
|
| 10.4959 | 0.82 | 45 | 11.8184 | |
|
| 10.3818 | 0.91 | 50 | 11.7738 | |
|
| 10.143 | 1.0 | 55 | 11.7325 | |
|
| 10.3456 | 1.09 | 60 | 11.6951 | |
|
| 10.4584 | 1.18 | 65 | 11.6612 | |
|
| 10.6774 | 1.27 | 70 | 11.6308 | |
|
| 10.2145 | 1.36 | 75 | 11.6035 | |
|
| 10.6536 | 1.45 | 80 | 11.5801 | |
|
| 10.3892 | 1.55 | 85 | 11.5599 | |
|
| 10.3469 | 1.64 | 90 | 11.5429 | |
|
| 10.1863 | 1.73 | 95 | 11.5295 | |
|
| 10.4296 | 1.82 | 100 | 11.5200 | |
|
| 9.989 | 1.91 | 105 | 11.5140 | |
|
| 10.3568 | 2.0 | 110 | 11.5113 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
