|
--- |
|
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-02 |
|
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-02 |
|
|
|
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: 0.0393 |
|
- Accuracy: 0.9874 |
|
- F1: 0.6311 |
|
- Precision: 0.6927 |
|
- Recall: 0.5796 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.0932 | 0.4931 | 1000 | 0.0863 | 0.9815 | 0.0 | 0.0 | 0.0 | |
|
| 0.0742 | 0.9862 | 2000 | 0.0662 | 0.9815 | 0.0 | 0.0 | 0.0 | |
|
| 0.0596 | 1.4793 | 3000 | 0.0549 | 0.9826 | 0.1370 | 0.8442 | 0.0746 | |
|
| 0.053 | 1.9724 | 4000 | 0.0491 | 0.9849 | 0.3899 | 0.7714 | 0.2608 | |
|
| 0.0467 | 2.4655 | 5000 | 0.0452 | 0.9857 | 0.4527 | 0.7816 | 0.3186 | |
|
| 0.044 | 2.9586 | 6000 | 0.0427 | 0.9864 | 0.5022 | 0.7753 | 0.3714 | |
|
| 0.039 | 3.4517 | 7000 | 0.0409 | 0.9867 | 0.5505 | 0.7410 | 0.4379 | |
|
| 0.037 | 3.9448 | 8000 | 0.0390 | 0.9870 | 0.5589 | 0.7507 | 0.4452 | |
|
| 0.0337 | 4.4379 | 9000 | 0.0383 | 0.9875 | 0.5772 | 0.7737 | 0.4603 | |
|
| 0.0337 | 4.9310 | 10000 | 0.0375 | 0.9875 | 0.5917 | 0.7530 | 0.4873 | |
|
| 0.0293 | 5.4241 | 11000 | 0.0375 | 0.9877 | 0.6105 | 0.7380 | 0.5205 | |
|
| 0.0297 | 5.9172 | 12000 | 0.0375 | 0.9876 | 0.6050 | 0.7390 | 0.5122 | |
|
| 0.0263 | 6.4103 | 13000 | 0.0372 | 0.9879 | 0.6160 | 0.7472 | 0.5240 | |
|
| 0.0265 | 6.9034 | 14000 | 0.0377 | 0.9876 | 0.6178 | 0.7208 | 0.5406 | |
|
| 0.0235 | 7.3964 | 15000 | 0.0378 | 0.9878 | 0.6238 | 0.7303 | 0.5444 | |
|
| 0.0237 | 7.8895 | 16000 | 0.0379 | 0.9878 | 0.6255 | 0.7242 | 0.5505 | |
|
| 0.0205 | 8.3826 | 17000 | 0.0383 | 0.9878 | 0.6324 | 0.7159 | 0.5664 | |
|
| 0.0208 | 8.8757 | 18000 | 0.0393 | 0.9874 | 0.6311 | 0.6927 | 0.5796 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
