Configuration Parsing
Warning:
In adapter_config.json: "peft.base_model_name_or_path" must be a string
opus-mt-zh-en-finetuned-en-to-zh
This model is a fine-tuned version of Helsinki-NLP/opus-mt-zh-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0839
- Bleu: 7.8213
- Gen Len: 53.7486
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 13.7325 | 1.0 | 540 | 3.1163 | 7.7165 | 54.2061 |
| 13.2107 | 1.9977 | 1078 | 3.0839 | 7.8213 | 53.7486 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 4
Model tree for Rawsand/opus-mt-zh-en-finetuned-en-to-zh
Base model
Helsinki-NLP/opus-mt-zh-en