metadata

language:
  - en
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
  - generated_from_trainer
datasets:
  - tmnam20/VieGLUE
metrics:
  - accuracy
  - f1
model-index:
  - name: bert-base-multilingual-cased-qqp-100
    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: 0.8905515706158793
          - name: F1
            type: f1
            value: 0.8513354611120443

bert-base-multilingual-cased-qqp-100

This model is a fine-tuned version of bert-base-multilingual-cased on the tmnam20/VieGLUE/QQP dataset. It achieves the following results on the evaluation set:

Loss: 0.2983
Accuracy: 0.8906
F1: 0.8513
Combined Score: 0.8709

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	F1	Combined Score
0.3417	0.44	5000	0.3198	0.8578	0.8057	0.8317
0.2998	0.88	10000	0.2908	0.8724	0.8252	0.8488
0.2629	1.32	15000	0.2970	0.8763	0.8300	0.8532
0.2269	1.76	20000	0.2874	0.8845	0.8405	0.8625
0.1933	2.2	25000	0.2962	0.8867	0.8470	0.8669
0.1752	2.64	30000	0.3174	0.8895	0.8497	0.8696

Framework versions

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