|
--- |
|
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-100 |
|
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: 0.8885227896760022 |
|
--- |
|
|
|
<!-- 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-100 |
|
|
|
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: 0.3284 |
|
- Accuracy: 0.8885 |
|
|
|
## 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: 100 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.4041 | 0.15 | 500 | 0.3611 | 0.8488 | |
|
| 0.3784 | 0.31 | 1000 | 0.3232 | 0.8603 | |
|
| 0.364 | 0.46 | 1500 | 0.3128 | 0.8642 | |
|
| 0.364 | 0.61 | 2000 | 0.3020 | 0.8702 | |
|
| 0.3236 | 0.76 | 2500 | 0.2960 | 0.8768 | |
|
| 0.3475 | 0.92 | 3000 | 0.2895 | 0.8816 | |
|
| 0.252 | 1.07 | 3500 | 0.3019 | 0.8812 | |
|
| 0.261 | 1.22 | 4000 | 0.2783 | 0.8893 | |
|
| 0.2718 | 1.37 | 4500 | 0.2880 | 0.8832 | |
|
| 0.2407 | 1.53 | 5000 | 0.3017 | 0.8812 | |
|
| 0.254 | 1.68 | 5500 | 0.2775 | 0.8827 | |
|
| 0.2611 | 1.83 | 6000 | 0.2837 | 0.8812 | |
|
| 0.257 | 1.99 | 6500 | 0.2816 | 0.8852 | |
|
| 0.1645 | 2.14 | 7000 | 0.3323 | 0.8845 | |
|
| 0.1679 | 2.29 | 7500 | 0.3568 | 0.8825 | |
|
| 0.1643 | 2.44 | 8000 | 0.3203 | 0.8889 | |
|
| 0.1662 | 2.6 | 8500 | 0.3240 | 0.8878 | |
|
| 0.1558 | 2.75 | 9000 | 0.3302 | 0.8856 | |
|
| 0.1614 | 2.9 | 9500 | 0.3299 | 0.8872 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.2.0.dev20231203+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
