|
|
--- |
|
|
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-04_train-01 |
|
|
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-04_train-01 |
|
|
|
|
|
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: 0.0396 |
|
|
- Accuracy: 0.9879 |
|
|
- F1: 0.6415 |
|
|
- Precision: 0.7120 |
|
|
- Recall: 0.5837 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-------:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
|
| 0.0941 | 0.4931 | 1000 | 0.0902 | 0.9815 | 0.0 | 0.0 | 0.0 | |
|
|
| 0.0787 | 0.9862 | 2000 | 0.0703 | 0.9815 | 0.0 | 0.0 | 0.0 | |
|
|
| 0.0628 | 1.4793 | 3000 | 0.0572 | 0.9823 | 0.1235 | 0.7562 | 0.0672 | |
|
|
| 0.0537 | 1.9724 | 4000 | 0.0500 | 0.9843 | 0.3220 | 0.7927 | 0.2021 | |
|
|
| 0.0478 | 2.4655 | 5000 | 0.0466 | 0.9853 | 0.4339 | 0.7566 | 0.3042 | |
|
|
| 0.0453 | 2.9586 | 6000 | 0.0441 | 0.9859 | 0.5020 | 0.7244 | 0.3841 | |
|
|
| 0.0389 | 3.4517 | 7000 | 0.0414 | 0.9865 | 0.5425 | 0.7258 | 0.4332 | |
|
|
| 0.0393 | 3.9448 | 8000 | 0.0406 | 0.9863 | 0.5470 | 0.7070 | 0.4461 | |
|
|
| 0.0349 | 4.4379 | 9000 | 0.0392 | 0.9870 | 0.5759 | 0.7229 | 0.4786 | |
|
|
| 0.0344 | 4.9310 | 10000 | 0.0386 | 0.9872 | 0.5807 | 0.7357 | 0.4796 | |
|
|
| 0.0302 | 5.4241 | 11000 | 0.0381 | 0.9873 | 0.5950 | 0.7282 | 0.5030 | |
|
|
| 0.0305 | 5.9172 | 12000 | 0.0381 | 0.9872 | 0.5975 | 0.7153 | 0.5129 | |
|
|
| 0.027 | 6.4103 | 13000 | 0.0378 | 0.9875 | 0.6030 | 0.7290 | 0.5141 | |
|
|
| 0.0282 | 6.9034 | 14000 | 0.0374 | 0.9876 | 0.6094 | 0.7303 | 0.5229 | |
|
|
| 0.0235 | 7.3964 | 15000 | 0.0378 | 0.9876 | 0.6213 | 0.7128 | 0.5507 | |
|
|
| 0.0255 | 7.8895 | 16000 | 0.0372 | 0.9878 | 0.6303 | 0.7188 | 0.5613 | |
|
|
| 0.0214 | 8.3826 | 17000 | 0.0378 | 0.9878 | 0.6356 | 0.7125 | 0.5737 | |
|
|
| 0.0222 | 8.8757 | 18000 | 0.0381 | 0.9878 | 0.6313 | 0.7141 | 0.5658 | |
|
|
| 0.0192 | 9.3688 | 19000 | 0.0390 | 0.9875 | 0.6285 | 0.6951 | 0.5736 | |
|
|
| 0.0189 | 9.8619 | 20000 | 0.0391 | 0.9878 | 0.6365 | 0.7085 | 0.5778 | |
|
|
| 0.0159 | 10.3550 | 21000 | 0.0396 | 0.9879 | 0.6415 | 0.7120 | 0.5837 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.44.2 |
|
|
- Pytorch 2.4.1+cu121 |
|
|
- Datasets 2.21.0 |
|
|
- Tokenizers 0.19.1 |
|
|
|
