metadata

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-sst2-100
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: tmnam20/VieGLUE/SST2
          type: tmnam20/VieGLUE
          config: sst2
          split: validation
          args: sst2
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8944954128440367

mdeberta-v3-base-sst2-100

This model is a fine-tuned version of microsoft/mdeberta-v3-base on the tmnam20/VieGLUE/SST2 dataset. It achieves the following results on the evaluation set:

Loss: 0.3880
Accuracy: 0.8945

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
0.3414	0.24	500	0.3477	0.8681
0.2858	0.48	1000	0.3121	0.8911
0.2358	0.71	1500	0.3466	0.8807
0.2413	0.95	2000	0.3225	0.8819
0.1722	1.19	2500	0.3268	0.8933
0.1926	1.43	3000	0.3712	0.8899
0.1766	1.66	3500	0.3130	0.9014
0.1706	1.9	4000	0.3517	0.8899
0.1308	2.14	4500	0.3970	0.9014
0.1315	2.38	5000	0.3525	0.8991
0.1504	2.61	5500	0.3728	0.8968
0.1178	2.85	6000	0.3987	0.8922

Framework versions

Transformers 4.36.0
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.15.0