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

tmnam20/mdeberta-v3-base-qqp-10

mdeberta-v3-base-qqp-10

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

tmnam20/
mdeberta-v3-base-qqp-10