|
--- |
|
license: mit |
|
base_model: microsoft/deberta-v3-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: DeBERTaV3_model_V3_multilabel |
|
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_V3_multilabel |
|
|
|
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: 0.0117 |
|
- Accuracy: 0.9978 |
|
- F1: 0.9985 |
|
- Precision: 0.9970 |
|
- Recall: 1.0 |
|
|
|
## 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: 13 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| No log | 1.0 | 90 | 0.0239 | 0.9978 | 0.9985 | 0.9970 | 1.0 | |
|
| No log | 2.0 | 180 | 0.0147 | 0.9978 | 0.9985 | 0.9970 | 1.0 | |
|
| No log | 3.0 | 270 | 0.0131 | 0.9978 | 0.9985 | 0.9970 | 1.0 | |
|
| No log | 4.0 | 360 | 0.0124 | 0.9978 | 0.9985 | 0.9970 | 1.0 | |
|
| No log | 5.0 | 450 | 0.0121 | 0.9978 | 0.9985 | 0.9970 | 1.0 | |
|
| 0.0608 | 6.0 | 540 | 0.0119 | 0.9978 | 0.9985 | 0.9970 | 1.0 | |
|
| 0.0608 | 7.0 | 630 | 0.0117 | 0.9978 | 0.9985 | 0.9970 | 1.0 | |
|
| 0.0608 | 8.0 | 720 | 0.0120 | 0.9978 | 0.9985 | 0.9970 | 1.0 | |
|
| 0.0608 | 9.0 | 810 | 0.0127 | 0.9978 | 0.9985 | 0.9970 | 1.0 | |
|
| 0.0608 | 10.0 | 900 | 0.0132 | 0.9978 | 0.9985 | 0.9970 | 1.0 | |
|
| 0.0608 | 11.0 | 990 | 0.0139 | 0.9970 | 0.998 | 0.9970 | 0.9990 | |
|
| 0.0121 | 12.0 | 1080 | 0.0143 | 0.9970 | 0.998 | 0.9970 | 0.9990 | |
|
| 0.0121 | 13.0 | 1170 | 0.0143 | 0.9970 | 0.998 | 0.9970 | 0.9990 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
