|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: Variome_5e-05_250 |
|
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. --> |
|
|
|
# Variome_5e-05_250 |
|
|
|
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: 0.0679 |
|
- Precision: 0.6097 |
|
- Recall: 0.5389 |
|
- F1: 0.5721 |
|
- Accuracy: 0.9860 |
|
|
|
## 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: 500 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.5834 | 0.35 | 25 | 0.1849 | 0.0 | 0.0 | 0.0 | 0.9760 | |
|
| 0.1856 | 0.69 | 50 | 0.1791 | 0.0 | 0.0 | 0.0 | 0.9760 | |
|
| 0.1611 | 1.04 | 75 | 0.1698 | 0.0 | 0.0 | 0.0 | 0.9760 | |
|
| 0.1471 | 1.39 | 100 | 0.1219 | 0.1478 | 0.0290 | 0.0485 | 0.9764 | |
|
| 0.1117 | 1.74 | 125 | 0.1133 | 0.1784 | 0.1426 | 0.1585 | 0.9767 | |
|
| 0.1071 | 2.08 | 150 | 0.1030 | 0.2899 | 0.2220 | 0.2515 | 0.9789 | |
|
| 0.0844 | 2.43 | 175 | 0.0977 | 0.3838 | 0.2750 | 0.3204 | 0.9805 | |
|
| 0.087 | 2.78 | 200 | 0.0884 | 0.4084 | 0.3903 | 0.3991 | 0.9815 | |
|
| 0.0785 | 3.12 | 225 | 0.0803 | 0.4895 | 0.4176 | 0.4507 | 0.9833 | |
|
| 0.0647 | 3.47 | 250 | 0.0784 | 0.5545 | 0.4518 | 0.4979 | 0.9842 | |
|
| 0.0592 | 3.82 | 275 | 0.0740 | 0.5655 | 0.5013 | 0.5315 | 0.9847 | |
|
| 0.0525 | 4.17 | 300 | 0.0725 | 0.5916 | 0.5158 | 0.5511 | 0.9854 | |
|
| 0.0515 | 4.51 | 325 | 0.0698 | 0.5861 | 0.5115 | 0.5463 | 0.9853 | |
|
| 0.0483 | 4.86 | 350 | 0.0691 | 0.5994 | 0.5201 | 0.5569 | 0.9855 | |
|
| 0.047 | 5.21 | 375 | 0.0702 | 0.5905 | 0.5209 | 0.5535 | 0.9855 | |
|
| 0.0429 | 5.56 | 400 | 0.0693 | 0.5986 | 0.5286 | 0.5615 | 0.9858 | |
|
| 0.0435 | 5.9 | 425 | 0.0673 | 0.5951 | 0.5397 | 0.5661 | 0.9858 | |
|
| 0.0418 | 6.25 | 450 | 0.0676 | 0.5949 | 0.5329 | 0.5622 | 0.9858 | |
|
| 0.038 | 6.6 | 475 | 0.0679 | 0.6013 | 0.5397 | 0.5689 | 0.9860 | |
|
| 0.0355 | 6.94 | 500 | 0.0679 | 0.6097 | 0.5389 | 0.5721 | 0.9860 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.2 |
|
|
