Edit model card

bert-base-multilingual-cased-qnli-1

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

  • Loss: 0.3278
  • Accuracy: 0.8852

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: 1
  • 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
0.3938 0.15 500 0.3494 0.8495
0.3712 0.31 1000 0.3266 0.8570
0.3837 0.46 1500 0.3174 0.8655
0.3466 0.61 2000 0.2957 0.8785
0.3084 0.76 2500 0.3093 0.8715
0.322 0.92 3000 0.2950 0.8731
0.273 1.07 3500 0.2872 0.8834
0.2628 1.22 4000 0.3110 0.8794
0.2732 1.37 4500 0.2910 0.8797
0.2592 1.53 5000 0.2855 0.8849
0.241 1.68 5500 0.2974 0.8861
0.2256 1.83 6000 0.2914 0.8850
0.2402 1.99 6500 0.2759 0.8883
0.1958 2.14 7000 0.3080 0.8880
0.1684 2.29 7500 0.3190 0.8847
0.1472 2.44 8000 0.3305 0.8871
0.1601 2.6 8500 0.3298 0.8836
0.1857 2.75 9000 0.3274 0.8847
0.1667 2.9 9500 0.3256 0.8841

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.2.0.dev20231203+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
8
Safetensors
Model size
178M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for tmnam20/bert-base-multilingual-cased-qnli-1

Finetuned
(500)
this model

Dataset used to train tmnam20/bert-base-multilingual-cased-qnli-1

Collection including tmnam20/bert-base-multilingual-cased-qnli-1

Evaluation results