|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: SETH_5e-05_0404_ES6_strict |
|
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. --> |
|
|
|
# SETH_5e-05_0404_ES6_strict |
|
|
|
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0633 |
|
- Precision: 0.7953 |
|
- Recall: 0.8692 |
|
- F1: 0.8306 |
|
- Accuracy: 0.9864 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.3171 | 0.96 | 25 | 0.0921 | 0.6399 | 0.7676 | 0.6980 | 0.9759 | |
|
| 0.0656 | 1.92 | 50 | 0.0588 | 0.7528 | 0.8227 | 0.7862 | 0.9796 | |
|
| 0.04 | 2.88 | 75 | 0.0456 | 0.7641 | 0.8640 | 0.8110 | 0.9837 | |
|
| 0.031 | 3.85 | 100 | 0.0481 | 0.7647 | 0.8726 | 0.8151 | 0.9840 | |
|
| 0.0241 | 4.81 | 125 | 0.0443 | 0.7915 | 0.8623 | 0.8254 | 0.9857 | |
|
| 0.0162 | 5.77 | 150 | 0.0469 | 0.8443 | 0.8399 | 0.8421 | 0.9868 | |
|
| 0.0132 | 6.73 | 175 | 0.0487 | 0.8310 | 0.8296 | 0.8303 | 0.9865 | |
|
| 0.013 | 7.69 | 200 | 0.0545 | 0.7692 | 0.8778 | 0.8199 | 0.9854 | |
|
| 0.0091 | 8.65 | 225 | 0.0539 | 0.8093 | 0.8399 | 0.8243 | 0.9865 | |
|
| 0.0071 | 9.62 | 250 | 0.0691 | 0.7820 | 0.8520 | 0.8155 | 0.9855 | |
|
| 0.0049 | 10.58 | 275 | 0.0633 | 0.7953 | 0.8692 | 0.8306 | 0.9864 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
