|
--- |
|
license: mit |
|
base_model: microsoft/deberta-v3-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: subcate-cs |
|
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. --> |
|
|
|
# subcate-cs |
|
|
|
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: 0.0762 |
|
- Accuracy: 0.6868 |
|
- F1: 0.7105 |
|
- Precision: 0.7235 |
|
- Recall: 0.6980 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 256 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| No log | 1.0 | 98 | 0.0743 | 0.6887 | 0.7074 | 0.7103 | 0.7044 | |
|
| No log | 2.0 | 196 | 0.0753 | 0.6926 | 0.7141 | 0.7262 | 0.7025 | |
|
| No log | 3.0 | 294 | 0.0751 | 0.6829 | 0.7078 | 0.7219 | 0.6942 | |
|
| No log | 4.0 | 392 | 0.0774 | 0.6797 | 0.7009 | 0.7117 | 0.6903 | |
|
| No log | 5.0 | 490 | 0.0762 | 0.6868 | 0.7105 | 0.7235 | 0.6980 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
