|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: microsoft/deberta-v3-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: doc-topic-model_eval-00_train-03 |
|
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. --> |
|
|
|
# doc-topic-model_eval-00_train-03 |
|
|
|
This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0381 |
|
- Accuracy: 0.9878 |
|
- F1: 0.6228 |
|
- Precision: 0.7288 |
|
- Recall: 0.5437 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 256 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 100 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.0935 | 0.4931 | 1000 | 0.0895 | 0.9815 | 0.0 | 0.0 | 0.0 | |
|
| 0.0764 | 0.9862 | 2000 | 0.0700 | 0.9815 | 0.0 | 0.0 | 0.0 | |
|
| 0.0621 | 1.4793 | 3000 | 0.0567 | 0.9821 | 0.0730 | 0.8925 | 0.0381 | |
|
| 0.0542 | 1.9724 | 4000 | 0.0497 | 0.9841 | 0.2891 | 0.8391 | 0.1747 | |
|
| 0.0468 | 2.4655 | 5000 | 0.0465 | 0.9853 | 0.4216 | 0.7739 | 0.2897 | |
|
| 0.0441 | 2.9586 | 6000 | 0.0435 | 0.9861 | 0.4879 | 0.7667 | 0.3578 | |
|
| 0.0395 | 3.4517 | 7000 | 0.0417 | 0.9862 | 0.5322 | 0.7197 | 0.4222 | |
|
| 0.0384 | 3.9448 | 8000 | 0.0401 | 0.9866 | 0.5600 | 0.7182 | 0.4589 | |
|
| 0.0343 | 4.4379 | 9000 | 0.0393 | 0.9870 | 0.5789 | 0.7217 | 0.4833 | |
|
| 0.0337 | 4.9310 | 10000 | 0.0378 | 0.9873 | 0.5907 | 0.7358 | 0.4934 | |
|
| 0.0305 | 5.4241 | 11000 | 0.0375 | 0.9875 | 0.5960 | 0.7457 | 0.4963 | |
|
| 0.0295 | 5.9172 | 12000 | 0.0378 | 0.9874 | 0.6050 | 0.7213 | 0.5210 | |
|
| 0.0271 | 6.4103 | 13000 | 0.0376 | 0.9877 | 0.6048 | 0.7457 | 0.5087 | |
|
| 0.0257 | 6.9034 | 14000 | 0.0379 | 0.9875 | 0.6068 | 0.7269 | 0.5208 | |
|
| 0.0234 | 7.3964 | 15000 | 0.0377 | 0.9876 | 0.6246 | 0.7108 | 0.5571 | |
|
| 0.0241 | 7.8895 | 16000 | 0.0381 | 0.9878 | 0.6228 | 0.7288 | 0.5437 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|