---
base_model: facebook/mbart-large-50-many-to-many-mmt
tags:
- generated_from_trainer
model-index:
- name: hanzi_huayu_translation
  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. -->

# hanzi_huayu_translation

This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1273

## 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-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.2874        | 0.56  | 500  | 0.2242          |
| 0.1208        | 1.12  | 1000 | 0.1447          |
| 0.1207        | 1.69  | 1500 | 0.1350          |
| 0.0928        | 2.25  | 2000 | 0.1312          |
| 0.1008        | 2.81  | 2500 | 0.1278          |
| 0.0769        | 3.37  | 3000 | 0.1272          |
| 0.0799        | 3.93  | 3500 | 0.1259          |
| 0.0689        | 4.49  | 4000 | 0.1266          |
| 0.0593        | 5.06  | 4500 | 0.1263          |
| 0.0534        | 5.62  | 5000 | 0.1270          |
| 0.0497        | 6.18  | 5500 | 0.1268          |
| 0.0483        | 6.74  | 6000 | 0.1268          |
| 0.0453        | 7.3   | 6500 | 0.1274          |
| 0.0486        | 7.87  | 7000 | 0.1273          |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2