|
--- |
|
base_model: dmis-lab/biobert-v1.1 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: biobert-all |
|
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. --> |
|
|
|
# biobert-all |
|
|
|
This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7750 |
|
- Precision: 0.5990 |
|
- Recall: 0.6572 |
|
- F1: 0.6268 |
|
- Accuracy: 0.8385 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 363 | 0.4337 | 0.5819 | 0.6535 | 0.6156 | 0.8427 | |
|
| 0.4325 | 2.0 | 726 | 0.4422 | 0.5912 | 0.6675 | 0.6270 | 0.8438 | |
|
| 0.2832 | 3.0 | 1089 | 0.4720 | 0.6010 | 0.6422 | 0.6209 | 0.8443 | |
|
| 0.2832 | 4.0 | 1452 | 0.5342 | 0.6076 | 0.6522 | 0.6291 | 0.8454 | |
|
| 0.1948 | 5.0 | 1815 | 0.5969 | 0.6059 | 0.6594 | 0.6315 | 0.8415 | |
|
| 0.1315 | 6.0 | 2178 | 0.6428 | 0.6051 | 0.6551 | 0.6291 | 0.8408 | |
|
| 0.0987 | 7.0 | 2541 | 0.6933 | 0.5933 | 0.6649 | 0.6270 | 0.8384 | |
|
| 0.0987 | 8.0 | 2904 | 0.7353 | 0.5949 | 0.6633 | 0.6273 | 0.8390 | |
|
| 0.0762 | 9.0 | 3267 | 0.7640 | 0.5920 | 0.6623 | 0.6252 | 0.8389 | |
|
| 0.0628 | 10.0 | 3630 | 0.7750 | 0.5990 | 0.6572 | 0.6268 | 0.8385 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
