metadata
license: cc-by-nc-4.0
library_name: peft
tags:
- generated_from_trainer
datasets:
- mt_eng_vietnamese
metrics:
- bleu
base_model: facebook/nllb-200-1.3B
model-index:
- name: my_fine_tuning_nllb_1B3_peft_en_vi_model_nmt
results: []
my_fine_tuning_nllb_1B3_peft_en_vi_model_nmt
This model is a fine-tuned version of facebook/nllb-200-1.3B on the mt_eng_vietnamese dataset. It achieves the following results on the evaluation set:
- Loss: 7.2576
- Bleu: 35.9386
- Gen Len: 30.7029
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 7.8689 | 1.0 | 133318 | 7.2597 | 35.8608 | 30.6438 |
| 7.8599 | 2.0 | 266636 | 7.2576 | 35.9386 | 30.7029 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.15.2