---
library_name: peft
license: cc-by-nc-4.0
base_model: facebook/nllb-200-distilled-600M
tags:
- generated_from_trainer
model-index:
- name: nllb-lora-zh2Paiwan
  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. -->

# nllb-lora-zh2Paiwan

This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 7.3264

## 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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 7.4959        | 1.0   | 201  | 7.4363          |
| 7.4622        | 2.0   | 402  | 7.4087          |
| 7.4338        | 3.0   | 603  | 7.3922          |
| 7.4289        | 4.0   | 804  | 7.3816          |
| 7.3944        | 5.0   | 1005 | 7.3703          |
| 7.3907        | 6.0   | 1206 | 7.3608          |
| 7.3872        | 7.0   | 1407 | 7.3555          |
| 7.3554        | 8.0   | 1608 | 7.3516          |
| 7.3666        | 9.0   | 1809 | 7.3456          |
| 7.3666        | 10.0  | 2010 | 7.3418          |
| 7.3431        | 11.0  | 2211 | 7.3382          |
| 7.353         | 12.0  | 2412 | 7.3357          |
| 7.3402        | 13.0  | 2613 | 7.3332          |
| 7.3323        | 14.0  | 2814 | 7.3315          |
| 7.3432        | 15.0  | 3015 | 7.3294          |
| 7.3315        | 16.0  | 3216 | 7.3274          |
| 7.3263        | 17.0  | 3417 | 7.3277          |
| 7.3086        | 18.0  | 3618 | 7.3268          |
| 7.3039        | 19.0  | 3819 | 7.3268          |
| 7.2977        | 20.0  | 4020 | 7.3264          |


### Framework versions

- PEFT 0.15.0
- Transformers 4.51.2
- Pytorch 2.2.2+cu118
- Datasets 3.5.0
- Tokenizers 0.21.1