---
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-mnli-100
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: tmnam20/VieGLUE/MNLI
      type: tmnam20/VieGLUE
      config: mnli
      split: validation_matched
      args: mnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8412327095199349
---

<!-- 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-mnli-100

This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the tmnam20/VieGLUE/MNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4764
- Accuracy: 0.8412

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.5194        | 0.41  | 5000  | 0.4901          | 0.8127   |
| 0.4861        | 0.81  | 10000 | 0.4713          | 0.8114   |
| 0.3993        | 1.22  | 15000 | 0.4508          | 0.8285   |
| 0.3867        | 1.63  | 20000 | 0.4546          | 0.8302   |
| 0.3496        | 2.04  | 25000 | 0.4765          | 0.8295   |
| 0.3376        | 2.44  | 30000 | 0.4828          | 0.8315   |
| 0.3104        | 2.85  | 35000 | 0.4852          | 0.8314   |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.2.0.dev20231203+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0