ViGLUE
Collection
A collection to store all the artifacts of the paper: ViGLUE: A Vietnamese General Language Understanding Benchmark and Analysis of Vietnamese LMs. • 145 items • Updated
mdeberta-v3-base-vsmec-1
This model is a fine-tuned version of microsoft/mdeberta-v3-base on the tmnam20/VieGLUE/VSMEC dataset. It achieves the following results on the evaluation set:
- Loss: 1.2431
- Accuracy: 0.5335
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: 1
- 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 |
|---|---|---|---|---|
| 1.0725 | 2.87 | 500 | 1.2408 | 0.5408 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 15
Model tree for tmnam20/mdeberta-v3-base-vsmec-1
Base model
microsoft/mdeberta-v3-baseDataset used to train tmnam20/mdeberta-v3-base-vsmec-1
Collection including tmnam20/mdeberta-v3-base-vsmec-1
Evaluation results
- Accuracy on tmnam20/VieGLUE/VSMECvalidation set self-reported0.534