|
--- |
|
library_name: transformers |
|
base_model: allenai/biomed_roberta_base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: BioMedRoBERTa-finetuned-valid-testing-0.0001-32 |
|
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. --> |
|
|
|
# BioMedRoBERTa-finetuned-valid-testing-0.0001-32 |
|
|
|
This model is a fine-tuned version of [allenai/biomed_roberta_base](https://huggingface.co/allenai/biomed_roberta_base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0835 |
|
- Precision: 0.8178 |
|
- Recall: 0.8281 |
|
- F1: 0.8229 |
|
- Accuracy: 0.9769 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 209 | 0.0882 | 0.7639 | 0.7805 | 0.7721 | 0.9718 | |
|
| No log | 2.0 | 418 | 0.0735 | 0.8259 | 0.8222 | 0.8240 | 0.9775 | |
|
| 0.2568 | 3.0 | 627 | 0.0779 | 0.8060 | 0.8110 | 0.8085 | 0.9746 | |
|
| 0.2568 | 4.0 | 836 | 0.0815 | 0.8062 | 0.8245 | 0.8152 | 0.9768 | |
|
| 0.0375 | 5.0 | 1045 | 0.0835 | 0.8178 | 0.8281 | 0.8229 | 0.9769 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
