|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: bert-base-cased-PubmedQAmodel |
|
|
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-base-cased-PubmedQAmodel |
|
|
|
|
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.9589 |
|
|
|
|
|
## 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: 20 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| No log | 1.0 | 21 | 3.4082 | |
|
|
| No log | 2.0 | 42 | 3.2677 | |
|
|
| No log | 3.0 | 63 | 3.1695 | |
|
|
| No log | 4.0 | 84 | 3.1515 | |
|
|
| No log | 5.0 | 105 | 3.0953 | |
|
|
| No log | 6.0 | 126 | 3.0906 | |
|
|
| No log | 7.0 | 147 | 2.9182 | |
|
|
| No log | 8.0 | 168 | 3.1660 | |
|
|
| No log | 9.0 | 189 | 3.1540 | |
|
|
| No log | 10.0 | 210 | 3.4559 | |
|
|
| No log | 11.0 | 231 | 3.5064 | |
|
|
| No log | 12.0 | 252 | 3.7371 | |
|
|
| No log | 13.0 | 273 | 3.7140 | |
|
|
| No log | 14.0 | 294 | 3.7878 | |
|
|
| No log | 15.0 | 315 | 3.8032 | |
|
|
| No log | 16.0 | 336 | 3.7973 | |
|
|
| No log | 17.0 | 357 | 3.8729 | |
|
|
| No log | 18.0 | 378 | 3.9404 | |
|
|
| No log | 19.0 | 399 | 3.9781 | |
|
|
| No log | 20.0 | 420 | 3.9589 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.28.1 |
|
|
- Pytorch 2.0.0+cu118 |
|
|
- Datasets 2.11.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
