|
--- |
|
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-02_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-02_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: 0.9877 |
|
- F1: 0.6218 |
|
- Precision: 0.7302 |
|
- Recall: 0.5414 |
|
|
|
## 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 | 0.0899 | 0.9814 | 0.0 | 0.0 | 0.0 | |
|
| 0.0764 | 0.9862 | 2000 | 0.0701 | 0.9814 | 0.0 | 0.0 | 0.0 | |
|
| 0.0621 | 1.4793 | 3000 | 0.0569 | 0.9820 | 0.0746 | 0.9191 | 0.0389 | |
|
| 0.0542 | 1.9724 | 4000 | 0.0500 | 0.9840 | 0.2899 | 0.8341 | 0.1755 | |
|
| 0.0468 | 2.4655 | 5000 | 0.0468 | 0.9852 | 0.4234 | 0.7741 | 0.2914 | |
|
| 0.0441 | 2.9586 | 6000 | 0.0437 | 0.9861 | 0.4909 | 0.7705 | 0.3601 | |
|
| 0.0395 | 3.4517 | 7000 | 0.0420 | 0.9860 | 0.5308 | 0.7110 | 0.4235 | |
|
| 0.0384 | 3.9448 | 8000 | 0.0399 | 0.9867 | 0.5640 | 0.7255 | 0.4613 | |
|
| 0.0343 | 4.4379 | 9000 | 0.0392 | 0.9868 | 0.5773 | 0.7176 | 0.4829 | |
|
| 0.0337 | 4.9310 | 10000 | 0.0380 | 0.9873 | 0.5936 | 0.7367 | 0.4970 | |
|
| 0.0305 | 5.4241 | 11000 | 0.0374 | 0.9875 | 0.5965 | 0.7448 | 0.4974 | |
|
| 0.0295 | 5.9172 | 12000 | 0.0379 | 0.9874 | 0.6077 | 0.7252 | 0.5230 | |
|
| 0.0271 | 6.4103 | 13000 | 0.0375 | 0.9876 | 0.6052 | 0.7476 | 0.5083 | |
|
| 0.0257 | 6.9034 | 14000 | 0.0376 | 0.9877 | 0.6152 | 0.7354 | 0.5288 | |
|
| 0.0234 | 7.3964 | 15000 | 0.0374 | 0.9877 | 0.6281 | 0.7177 | 0.5583 | |
|
| 0.0241 | 7.8895 | 16000 | 0.0381 | 0.9877 | 0.6218 | 0.7302 | 0.5414 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
