|
--- |
|
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-01_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-01_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: 0.0386 |
|
- Accuracy: 0.9878 |
|
- F1: 0.6354 |
|
- Precision: 0.7155 |
|
- Recall: 0.5714 |
|
|
|
## 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 | 0.0911 | 0.9814 | 0.0 | 0.0 | 0.0 | |
|
| 0.0785 | 0.9862 | 2000 | 0.0707 | 0.9814 | 0.0 | 0.0 | 0.0 | |
|
| 0.0622 | 1.4793 | 3000 | 0.0574 | 0.9823 | 0.1057 | 0.8595 | 0.0563 | |
|
| 0.0542 | 1.9724 | 4000 | 0.0498 | 0.9843 | 0.3396 | 0.7800 | 0.2171 | |
|
| 0.048 | 2.4655 | 5000 | 0.0461 | 0.9852 | 0.4251 | 0.7708 | 0.2935 | |
|
| 0.0436 | 2.9586 | 6000 | 0.0433 | 0.9860 | 0.5031 | 0.7426 | 0.3804 | |
|
| 0.0384 | 3.4517 | 7000 | 0.0413 | 0.9865 | 0.5389 | 0.7357 | 0.4252 | |
|
| 0.0385 | 3.9448 | 8000 | 0.0399 | 0.9867 | 0.5362 | 0.7647 | 0.4128 | |
|
| 0.0343 | 4.4379 | 9000 | 0.0396 | 0.9869 | 0.5599 | 0.7452 | 0.4484 | |
|
| 0.0343 | 4.9310 | 10000 | 0.0387 | 0.9870 | 0.5692 | 0.7471 | 0.4598 | |
|
| 0.0304 | 5.4241 | 11000 | 0.0385 | 0.9873 | 0.5861 | 0.7432 | 0.4837 | |
|
| 0.0299 | 5.9172 | 12000 | 0.0373 | 0.9875 | 0.6055 | 0.7342 | 0.5152 | |
|
| 0.0265 | 6.4103 | 13000 | 0.0376 | 0.9873 | 0.6069 | 0.7159 | 0.5268 | |
|
| 0.0261 | 6.9034 | 14000 | 0.0372 | 0.9877 | 0.6138 | 0.7384 | 0.5252 | |
|
| 0.0236 | 7.3964 | 15000 | 0.0378 | 0.9876 | 0.6187 | 0.7225 | 0.5409 | |
|
| 0.0236 | 7.8895 | 16000 | 0.0379 | 0.9878 | 0.6205 | 0.7374 | 0.5357 | |
|
| 0.0215 | 8.3826 | 17000 | 0.0383 | 0.9876 | 0.6241 | 0.7126 | 0.5551 | |
|
| 0.0216 | 8.8757 | 18000 | 0.0386 | 0.9877 | 0.6297 | 0.7143 | 0.5630 | |
|
| 0.0177 | 9.3688 | 19000 | 0.0386 | 0.9878 | 0.6354 | 0.7155 | 0.5714 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
