|
--- |
|
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: 10.2691 |
|
|
|
## 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 11.3132 | 0.09 | 5 | 12.3055 | |
|
| 11.4109 | 0.18 | 10 | 12.2292 | |
|
| 10.9744 | 0.27 | 15 | 12.1547 | |
|
| 11.0771 | 0.36 | 20 | 12.0814 | |
|
| 11.0342 | 0.45 | 25 | 12.0101 | |
|
| 11.0327 | 0.55 | 30 | 11.9396 | |
|
| 10.2954 | 0.64 | 35 | 11.8706 | |
|
| 10.8979 | 0.73 | 40 | 11.8043 | |
|
| 10.432 | 0.82 | 45 | 11.7386 | |
|
| 10.3023 | 0.91 | 50 | 11.6747 | |
|
| 10.0494 | 1.0 | 55 | 11.6128 | |
|
| 10.2273 | 1.09 | 60 | 11.5521 | |
|
| 10.3139 | 1.18 | 65 | 11.4931 | |
|
| 10.5075 | 1.27 | 70 | 11.4349 | |
|
| 10.0234 | 1.36 | 75 | 11.3790 | |
|
| 10.4276 | 1.45 | 80 | 11.3238 | |
|
| 10.1397 | 1.55 | 85 | 11.2699 | |
|
| 10.0675 | 1.64 | 90 | 11.2174 | |
|
| 9.8835 | 1.73 | 95 | 11.1665 | |
|
| 10.0738 | 1.82 | 100 | 11.1169 | |
|
| 9.6112 | 1.91 | 105 | 11.0687 | |
|
| 9.9186 | 2.0 | 110 | 11.0227 | |
|
| 9.8411 | 2.09 | 115 | 10.9779 | |
|
| 9.6506 | 2.18 | 120 | 10.9342 | |
|
| 9.7831 | 2.27 | 125 | 10.8916 | |
|
| 9.8835 | 2.36 | 130 | 10.8509 | |
|
| 9.4752 | 2.45 | 135 | 10.8111 | |
|
| 9.8176 | 2.55 | 140 | 10.7731 | |
|
| 9.3628 | 2.64 | 145 | 10.7369 | |
|
| 9.819 | 2.73 | 150 | 10.7017 | |
|
| 9.572 | 2.82 | 155 | 10.6681 | |
|
| 9.522 | 2.91 | 160 | 10.6356 | |
|
| 9.6874 | 3.0 | 165 | 10.6046 | |
|
| 9.6037 | 3.09 | 170 | 10.5750 | |
|
| 9.5624 | 3.18 | 175 | 10.5468 | |
|
| 9.2702 | 3.27 | 180 | 10.5202 | |
|
| 9.1347 | 3.36 | 185 | 10.4947 | |
|
| 9.8154 | 3.45 | 190 | 10.4706 | |
|
| 9.4045 | 3.55 | 195 | 10.4475 | |
|
| 9.2453 | 3.64 | 200 | 10.4262 | |
|
| 9.1087 | 3.73 | 205 | 10.4062 | |
|
| 8.985 | 3.82 | 210 | 10.3875 | |
|
| 9.0054 | 3.91 | 215 | 10.3705 | |
|
| 9.4764 | 4.0 | 220 | 10.3545 | |
|
| 9.13 | 4.09 | 225 | 10.3401 | |
|
| 9.4397 | 4.18 | 230 | 10.3272 | |
|
| 9.0841 | 4.27 | 235 | 10.3153 | |
|
| 9.5885 | 4.36 | 240 | 10.3048 | |
|
| 9.4137 | 4.45 | 245 | 10.2958 | |
|
| 9.1068 | 4.55 | 250 | 10.2878 | |
|
| 9.1388 | 4.64 | 255 | 10.2816 | |
|
| 8.8014 | 4.73 | 260 | 10.2763 | |
|
| 8.9782 | 4.82 | 265 | 10.2727 | |
|
| 9.222 | 4.91 | 270 | 10.2701 | |
|
| 9.292 | 5.0 | 275 | 10.2691 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|