|
--- |
|
license: mit |
|
base_model: microsoft/deberta-v3-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: DeBERTaV3_model_V4 |
|
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. --> |
|
|
|
# DeBERTaV3_model_V4 |
|
|
|
This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1557 |
|
- Accuracy: 0.9485 |
|
- F1: 0.7248 |
|
- Precision: 0.7778 |
|
- Recall: 0.6786 |
|
|
|
## 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: 5 |
|
- eval_batch_size: 5 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 12 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| No log | 1.0 | 159 | 0.2879 | 0.9 | 0.0 | 0.0 | 0.0 | |
|
| No log | 2.0 | 318 | 0.2226 | 0.9189 | 0.3457 | 0.8936 | 0.2143 | |
|
| No log | 3.0 | 477 | 0.1883 | 0.9347 | 0.5975 | 0.7787 | 0.4847 | |
|
| 0.2618 | 4.0 | 636 | 0.1557 | 0.9485 | 0.7248 | 0.7778 | 0.6786 | |
|
| 0.2618 | 5.0 | 795 | 0.1593 | 0.9480 | 0.7273 | 0.7640 | 0.6939 | |
|
| 0.2618 | 6.0 | 954 | 0.1564 | 0.9505 | 0.7413 | 0.7765 | 0.7092 | |
|
| 0.0829 | 7.0 | 1113 | 0.1636 | 0.9520 | 0.7552 | 0.7713 | 0.7398 | |
|
| 0.0829 | 8.0 | 1272 | 0.1761 | 0.9485 | 0.7363 | 0.7540 | 0.7194 | |
|
| 0.0829 | 9.0 | 1431 | 0.1686 | 0.9536 | 0.7599 | 0.7869 | 0.7347 | |
|
| 0.0297 | 10.0 | 1590 | 0.1807 | 0.9526 | 0.7584 | 0.7725 | 0.7449 | |
|
| 0.0297 | 11.0 | 1749 | 0.1765 | 0.9531 | 0.7629 | 0.7708 | 0.7551 | |
|
| 0.0297 | 12.0 | 1908 | 0.1790 | 0.9536 | 0.7649 | 0.7749 | 0.7551 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
