|
--- |
|
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-00 |
|
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-00 |
|
|
|
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: 0.0382 |
|
- Accuracy: 0.9879 |
|
- F1: 0.6370 |
|
- Precision: 0.7208 |
|
- Recall: 0.5707 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.0929 | 0.4931 | 1000 | 0.0912 | 0.9814 | 0.0 | 0.0 | 0.0 | |
|
| 0.0785 | 0.9862 | 2000 | 0.0708 | 0.9814 | 0.0 | 0.0 | 0.0 | |
|
| 0.0622 | 1.4793 | 3000 | 0.0576 | 0.9823 | 0.1109 | 0.8665 | 0.0592 | |
|
| 0.0542 | 1.9724 | 4000 | 0.0501 | 0.9842 | 0.3406 | 0.7715 | 0.2185 | |
|
| 0.048 | 2.4655 | 5000 | 0.0461 | 0.9853 | 0.4277 | 0.7762 | 0.2952 | |
|
| 0.0436 | 2.9586 | 6000 | 0.0434 | 0.9861 | 0.5112 | 0.7463 | 0.3887 | |
|
| 0.0384 | 3.4517 | 7000 | 0.0414 | 0.9867 | 0.5496 | 0.7437 | 0.4358 | |
|
| 0.0385 | 3.9448 | 8000 | 0.0402 | 0.9867 | 0.5363 | 0.7625 | 0.4136 | |
|
| 0.0343 | 4.4379 | 9000 | 0.0396 | 0.9870 | 0.5633 | 0.7528 | 0.4500 | |
|
| 0.0343 | 4.9310 | 10000 | 0.0388 | 0.9872 | 0.5772 | 0.7528 | 0.4681 | |
|
| 0.0304 | 5.4241 | 11000 | 0.0388 | 0.9871 | 0.5816 | 0.7349 | 0.4812 | |
|
| 0.0299 | 5.9172 | 12000 | 0.0374 | 0.9875 | 0.6071 | 0.7340 | 0.5176 | |
|
| 0.0265 | 6.4103 | 13000 | 0.0377 | 0.9875 | 0.6135 | 0.7213 | 0.5337 | |
|
| 0.0261 | 6.9034 | 14000 | 0.0372 | 0.9876 | 0.6117 | 0.7383 | 0.5221 | |
|
| 0.0236 | 7.3964 | 15000 | 0.0377 | 0.9877 | 0.6207 | 0.7257 | 0.5423 | |
|
| 0.0236 | 7.8895 | 16000 | 0.0377 | 0.9878 | 0.6228 | 0.7376 | 0.5389 | |
|
| 0.0215 | 8.3826 | 17000 | 0.0379 | 0.9879 | 0.6336 | 0.7236 | 0.5634 | |
|
| 0.0216 | 8.8757 | 18000 | 0.0382 | 0.9878 | 0.6330 | 0.7212 | 0.5640 | |
|
| 0.0177 | 9.3688 | 19000 | 0.0382 | 0.9879 | 0.6370 | 0.7208 | 0.5707 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
