|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: biolinkbert-base-medqa-usmle-nocontext |
|
results: [] |
|
datasets: |
|
- GBaker/MedQA-USMLE-4-options-hf |
|
--- |
|
|
|
<!-- 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-nocontext |
|
|
|
This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-base](https://huggingface.co/michiyasunaga/BioLinkBERT-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5149 |
|
- Accuracy: 0.3943 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 64 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 0.98 | 39 | 1.3339 | 0.3590 | |
|
| No log | 1.98 | 78 | 1.3685 | 0.3794 | |
|
| No log | 2.98 | 117 | 1.4162 | 0.3912 | |
|
| No log | 3.98 | 156 | 1.4484 | 0.3888 | |
|
| No log | 4.98 | 195 | 1.4869 | 0.3983 | |
|
| No log | 5.98 | 234 | 1.5149 | 0.3943 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
