---
library_name: transformers
language:
- nan
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-ZH
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- bleu
model-index:
- name: helsinki_new_ver3
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# helsinki_new_ver3

This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ZH](https://huggingface.co/Helsinki-NLP/opus-mt-en-ZH) on the mozilla-foundation/common_voice_17_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7044
- Bleu: 2.2015

## 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: 1e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- training_steps: 23000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Bleu   |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 0.9675        | 0.32  | 1000  | 1.0573          | 0.7690 |
| 0.9217        | 0.64  | 2000  | 0.9924          | 1.3531 |
| 0.8782        | 0.96  | 3000  | 0.9463          | 1.8407 |
| 0.8377        | 1.28  | 4000  | 0.9078          | 3.0190 |
| 0.8304        | 1.6   | 5000  | 0.8765          | 2.1759 |
| 0.8114        | 1.92  | 6000  | 0.8479          | 3.2072 |
| 0.7735        | 2.24  | 7000  | 0.8247          | 4.0669 |
| 0.7667        | 2.56  | 8000  | 0.8051          | 5.6676 |
| 0.7547        | 2.88  | 9000  | 0.7882          | 4.2755 |
| 0.7151        | 3.2   | 10000 | 0.7712          | 5.7800 |
| 0.7103        | 3.52  | 11000 | 0.7591          | 6.0659 |
| 0.7095        | 3.84  | 12000 | 0.7458          | 7.0038 |
| 0.7044        | 4.16  | 13000 | 0.7351          | 1.7120 |
| 0.6717        | 4.48  | 14000 | 0.7250          | 8.0104 |
| 0.6856        | 4.8   | 15000 | 0.7169          | 2.1741 |
| 0.6755        | 5.12  | 16000 | 0.7097          | 2.1614 |
| 0.6635        | 5.44  | 17000 | 0.7044          | 2.2015 |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1