metadata
language:
- en
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
datasets:
- tmnam20/VieGLUE
metrics:
- accuracy
- f1
model-index:
- name: mdeberta-v3-base-qqp-10
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: tmnam20/VieGLUE/QQP
type: tmnam20/VieGLUE
config: qqp
split: validation
args: qqp
metrics:
- name: Accuracy
type: accuracy
value: 0.8998268612416522
- name: F1
type: f1
value: 0.8668551515550004
mdeberta-v3-base-qqp-10
This model is a fine-tuned version of microsoft/mdeberta-v3-base on the tmnam20/VieGLUE/QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.2766
- Accuracy: 0.8998
- F1: 0.8669
- Combined Score: 0.8833
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 | F1 | Combined Score |
---|---|---|---|---|---|---|
0.2833 | 0.44 | 5000 | 0.3087 | 0.8708 | 0.8217 | 0.8462 |
0.2702 | 0.88 | 10000 | 0.2763 | 0.8818 | 0.8421 | 0.8619 |
0.2269 | 1.32 | 15000 | 0.2819 | 0.8883 | 0.8469 | 0.8676 |
0.2182 | 1.76 | 20000 | 0.2728 | 0.8929 | 0.8599 | 0.8764 |
0.1682 | 2.2 | 25000 | 0.2922 | 0.8971 | 0.8613 | 0.8792 |
0.175 | 2.64 | 30000 | 0.2755 | 0.8981 | 0.8635 | 0.8808 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.2.0.dev20231203+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0