|
--- |
|
base_model: allenai/biomed_roberta_base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: biomed_roberta_all_deep |
|
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. --> |
|
|
|
# biomed_roberta_all_deep |
|
|
|
This model is a fine-tuned version of [allenai/biomed_roberta_base](https://huggingface.co/allenai/biomed_roberta_base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7519 |
|
- Precision: 0.6732 |
|
- Recall: 0.7142 |
|
- F1: 0.6931 |
|
- Accuracy: 0.8255 |
|
|
|
## 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 | 0.5600 | 0.6059 | 0.6773 | 0.6396 | 0.8131 | |
|
| 0.7102 | 2.0 | 726 | 0.5290 | 0.6310 | 0.7172 | 0.6713 | 0.8248 | |
|
| 0.4147 | 3.0 | 1089 | 0.5253 | 0.6620 | 0.7075 | 0.6840 | 0.8289 | |
|
| 0.4147 | 4.0 | 1452 | 0.5572 | 0.6664 | 0.7062 | 0.6857 | 0.8263 | |
|
| 0.3081 | 5.0 | 1815 | 0.5942 | 0.6615 | 0.7127 | 0.6862 | 0.8244 | |
|
| 0.231 | 6.0 | 2178 | 0.6393 | 0.6745 | 0.7064 | 0.6901 | 0.8268 | |
|
| 0.1864 | 7.0 | 2541 | 0.6771 | 0.6769 | 0.7050 | 0.6907 | 0.8250 | |
|
| 0.1864 | 8.0 | 2904 | 0.7091 | 0.6708 | 0.7120 | 0.6908 | 0.8263 | |
|
| 0.1523 | 9.0 | 3267 | 0.7463 | 0.6702 | 0.7159 | 0.6923 | 0.8255 | |
|
| 0.1336 | 10.0 | 3630 | 0.7519 | 0.6732 | 0.7142 | 0.6931 | 0.8255 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
