bart-base-translate-en-vi
This model is a fine-tuned version of GuysTrans/bart-base-translate-en-vi on the mt_eng_vietnamese dataset. It achieves the following results on the evaluation set:
- Loss: 0.6744
- Rouge1: 56.0521
- Rouge2: 34.1329
- Rougel: 47.1473
- Rougelsum: 47.8238
- Bleu: 12.7027
- Gen Len: 19.9921
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Gen Len |
|---|---|---|---|---|---|---|---|---|---|
| 0.661 | 1.0 | 16665 | 0.6744 | 56.0521 | 34.1329 | 47.1473 | 47.8238 | 12.7027 | 19.9921 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.1.0+cu118
- Datasets 2.10.1
- Tokenizers 0.13.3
- Downloads last month
- 39
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Dataset used to train GuysTrans/bart-base-translate-en-vi
Evaluation results
- Rouge1 on mt_eng_vietnamesevalidation set self-reported56.052
- Bleu on mt_eng_vietnamesevalidation set self-reported12.703
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("GuysTrans/bart-base-translate-en-vi") model = AutoModelForSeq2SeqLM.from_pretrained("GuysTrans/bart-base-translate-en-vi")