YagiASAFAS's picture
update model card README.md
f980948
|
raw
history blame
2.06 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: malaysia-news-classification-bert-malay
    results: []

malaysia-news-classification-bert-malay

This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0311
  • Accuracy: 0.7601

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: 3e-05
  • train_batch_size: 16
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 225 1.0295 0.7104
No log 2.0 450 0.9205 0.7409
1.1064 3.0 675 0.8432 0.7590
1.1064 4.0 900 0.8552 0.7695
0.5596 5.0 1125 0.8836 0.7612
0.5596 6.0 1350 0.9057 0.7665
0.3499 7.0 1575 0.9766 0.7590
0.3499 8.0 1800 0.9974 0.7640
0.2144 9.0 2025 1.0211 0.7612
0.2144 10.0 2250 1.0311 0.7601

Framework versions

  • Transformers 4.18.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.12.1