|
--- |
|
language: |
|
- en |
|
license: mit |
|
base_model: microsoft/mdeberta-v3-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- tmnam20/VieGLUE |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: mdeberta-v3-base-qnli-10 |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: tmnam20/VieGLUE/QNLI |
|
type: tmnam20/VieGLUE |
|
config: qnli |
|
split: validation |
|
args: qnli |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8984074684239429 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# mdeberta-v3-base-qnli-10 |
|
|
|
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the tmnam20/VieGLUE/QNLI dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2859 |
|
- Accuracy: 0.8984 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 16 |
|
- seed: 10 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.3968 | 0.15 | 500 | 0.3264 | 0.8623 | |
|
| 0.3826 | 0.31 | 1000 | 0.2996 | 0.8774 | |
|
| 0.3478 | 0.46 | 1500 | 0.2894 | 0.8845 | |
|
| 0.2959 | 0.61 | 2000 | 0.2745 | 0.8883 | |
|
| 0.3228 | 0.76 | 2500 | 0.2640 | 0.8905 | |
|
| 0.2899 | 0.92 | 3000 | 0.2723 | 0.8925 | |
|
| 0.2269 | 1.07 | 3500 | 0.2850 | 0.8935 | |
|
| 0.2614 | 1.22 | 4000 | 0.2607 | 0.8984 | |
|
| 0.2508 | 1.37 | 4500 | 0.2831 | 0.8878 | |
|
| 0.2563 | 1.53 | 5000 | 0.2556 | 0.8960 | |
|
| 0.2485 | 1.68 | 5500 | 0.2618 | 0.9019 | |
|
| 0.2373 | 1.83 | 6000 | 0.2600 | 0.8953 | |
|
| 0.2361 | 1.99 | 6500 | 0.2545 | 0.9023 | |
|
| 0.162 | 2.14 | 7000 | 0.3093 | 0.8997 | |
|
| 0.2115 | 2.29 | 7500 | 0.2685 | 0.9010 | |
|
| 0.176 | 2.44 | 8000 | 0.2966 | 0.8982 | |
|
| 0.2047 | 2.6 | 8500 | 0.2767 | 0.8982 | |
|
| 0.1831 | 2.75 | 9000 | 0.2918 | 0.8968 | |
|
| 0.1818 | 2.9 | 9500 | 0.2818 | 0.8979 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.2.0.dev20231203+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
