|
|
--- |
|
|
library_name: transformers |
|
|
base_model: huawei-noah/TinyBERT_General_4L_312D |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- precision |
|
|
- recall |
|
|
model-index: |
|
|
- name: NF4-KD-NID |
|
|
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. --> |
|
|
|
|
|
# NF4-KD-NID |
|
|
|
|
|
This model is a fine-tuned version of [huawei-noah/TinyBERT_General_4L_312D](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0419 |
|
|
- Accuracy: 0.9919 |
|
|
- Precision: 0.9744 |
|
|
- Recall: 0.9469 |
|
|
- F1 score: 0.9546 |
|
|
|
|
|
## 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: 5e-05 |
|
|
- train_batch_size: 650 |
|
|
- eval_batch_size: 650 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 15 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 score | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:--------:| |
|
|
| 0.2112 | 1.0 | 1828 | 0.1824 | 0.9775 | 0.7759 | 0.7784 | 0.7742 | |
|
|
| 0.1196 | 2.0 | 3656 | 0.1061 | 0.9850 | 0.9060 | 0.8522 | 0.8502 | |
|
|
| 0.0956 | 3.0 | 5484 | 0.0855 | 0.9874 | 0.9140 | 0.8833 | 0.8858 | |
|
|
| 0.0823 | 4.0 | 7312 | 0.0708 | 0.9891 | 0.9204 | 0.8982 | 0.9029 | |
|
|
| 0.0653 | 5.0 | 9140 | 0.0628 | 0.9897 | 0.9313 | 0.8985 | 0.9070 | |
|
|
| 0.066 | 6.0 | 10968 | 0.0572 | 0.9901 | 0.9206 | 0.9132 | 0.9106 | |
|
|
| 0.0546 | 7.0 | 12796 | 0.0534 | 0.9907 | 0.9284 | 0.9156 | 0.9187 | |
|
|
| 0.0486 | 8.0 | 14624 | 0.0511 | 0.9909 | 0.9287 | 0.9184 | 0.9199 | |
|
|
| 0.0473 | 9.0 | 16452 | 0.0490 | 0.9911 | 0.9732 | 0.9284 | 0.9346 | |
|
|
| 0.0483 | 10.0 | 18280 | 0.0469 | 0.9914 | 0.9788 | 0.9237 | 0.9344 | |
|
|
| 0.0435 | 11.0 | 20108 | 0.0451 | 0.9915 | 0.9722 | 0.9323 | 0.9360 | |
|
|
| 0.0388 | 12.0 | 21936 | 0.0429 | 0.9917 | 0.9757 | 0.9395 | 0.9477 | |
|
|
| 0.039 | 13.0 | 23764 | 0.0426 | 0.9917 | 0.9758 | 0.9514 | 0.9597 | |
|
|
| 0.0362 | 14.0 | 25592 | 0.0423 | 0.9918 | 0.9743 | 0.9467 | 0.9542 | |
|
|
| 0.0357 | 15.0 | 27420 | 0.0419 | 0.9919 | 0.9744 | 0.9469 | 0.9546 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.4.1 |
|
|
- Tokenizers 0.21.1 |
|
|
|
