opus_zh_en_finetuned
This model is a fine-tuned version of Helsinki-NLP/opus-mt-zh-en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2696
- Bleu: 54.7403
- Chrf: 59.4450
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf |
|---|---|---|---|---|---|
| 2.2207 | 1.0 | 22 | 1.3842 | 45.7321 | 55.5944 |
| 1.4839 | 2.0 | 44 | 1.3005 | 48.2970 | 57.3784 |
| 1.2985 | 3.0 | 66 | 1.2696 | 54.7403 | 59.4450 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cpu
- Datasets 5.0.0
- Tokenizers 0.22.2
- Downloads last month
- 33
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for RinKana/opus_zh_en_finetuned
Base model
Helsinki-NLP/opus-mt-zh-en