|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: biolinkbert-base-medqa-usmle-MPNet-context |
|
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. --> |
|
|
|
# biolinkbert-base-medqa-usmle-MPNet-context |
|
|
|
This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-base](https://huggingface.co/michiyasunaga/BioLinkBERT-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4506 |
|
- Accuracy: 0.3936 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 318 | 1.3518 | 0.3354 | |
|
| 1.3648 | 2.0 | 636 | 1.3308 | 0.3684 | |
|
| 1.3648 | 3.0 | 954 | 1.3267 | 0.3943 | |
|
| 1.2711 | 4.0 | 1272 | 1.3455 | 0.3865 | |
|
| 1.1769 | 5.0 | 1590 | 1.3739 | 0.3943 | |
|
| 1.1769 | 6.0 | 1908 | 1.3960 | 0.4069 | |
|
| 1.0815 | 7.0 | 2226 | 1.4320 | 0.3959 | |
|
| 1.0092 | 8.0 | 2544 | 1.4506 | 0.3936 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.2 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
