|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
base_model: bert-base-multilingual-cased |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- tmnam20/VieGLUE |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: bert-base-multilingual-cased-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: 0.891085484166209 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# bert-base-multilingual-cased-qnli-10 |
|
|
|
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the tmnam20/VieGLUE/QNLI dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3198 |
|
- Accuracy: 0.8911 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.4249 | 0.15 | 500 | 0.3656 | 0.8464 | |
|
| 0.3989 | 0.31 | 1000 | 0.3319 | 0.8581 | |
|
| 0.3557 | 0.46 | 1500 | 0.3096 | 0.8688 | |
|
| 0.3257 | 0.61 | 2000 | 0.3055 | 0.8700 | |
|
| 0.3403 | 0.76 | 2500 | 0.2893 | 0.8786 | |
|
| 0.311 | 0.92 | 3000 | 0.2919 | 0.8841 | |
|
| 0.2424 | 1.07 | 3500 | 0.2974 | 0.8838 | |
|
| 0.2663 | 1.22 | 4000 | 0.2966 | 0.8845 | |
|
| 0.2486 | 1.37 | 4500 | 0.2904 | 0.8828 | |
|
| 0.2442 | 1.53 | 5000 | 0.2919 | 0.8810 | |
|
| 0.252 | 1.68 | 5500 | 0.2781 | 0.8880 | |
|
| 0.2514 | 1.83 | 6000 | 0.2754 | 0.8867 | |
|
| 0.254 | 1.99 | 6500 | 0.2692 | 0.8882 | |
|
| 0.1632 | 2.14 | 7000 | 0.3349 | 0.8867 | |
|
| 0.1835 | 2.29 | 7500 | 0.3126 | 0.8902 | |
|
| 0.1725 | 2.44 | 8000 | 0.3145 | 0.8902 | |
|
| 0.1624 | 2.6 | 8500 | 0.3272 | 0.8876 | |
|
| 0.1751 | 2.75 | 9000 | 0.3240 | 0.8882 | |
|
| 0.1653 | 2.9 | 9500 | 0.3235 | 0.8900 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.2.0.dev20231203+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
