nllb-lora-Atayal
This model is a fine-tuned version of facebook/nllb-200-distilled-600M on the None dataset. It achieves the following results on the evaluation set:
- Loss: 7.3188
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 |
|---|---|---|---|
| 7.0804 | 1.0 | 240 | 7.4038 |
| 7.0618 | 2.0 | 480 | 7.3912 |
| 7.0414 | 3.0 | 720 | 7.3707 |
| 7.0314 | 4.0 | 960 | 7.3647 |
| 7.0192 | 5.0 | 1200 | 7.3581 |
| 7.0171 | 6.0 | 1440 | 7.3495 |
| 7.0124 | 7.0 | 1680 | 7.3436 |
| 6.9902 | 8.0 | 1920 | 7.3389 |
| 7.0014 | 9.0 | 2160 | 7.3344 |
| 6.9798 | 10.0 | 2400 | 7.3334 |
| 6.9712 | 11.0 | 2640 | 7.3276 |
| 6.9703 | 12.0 | 2880 | 7.3256 |
| 6.9845 | 13.0 | 3120 | 7.3237 |
| 6.9707 | 14.0 | 3360 | 7.3218 |
| 6.9703 | 15.0 | 3600 | 7.3208 |
| 6.9671 | 16.0 | 3840 | 7.3198 |
| 6.9612 | 17.0 | 4080 | 7.3194 |
| 6.9508 | 18.0 | 4320 | 7.3188 |
| 6.9577 | 19.0 | 4560 | 7.3189 |
| 7.3136 | 19.9186 | 4780 | 7.3188 |
Framework versions
- PEFT 0.15.0
- Transformers 4.51.2
- Pytorch 2.2.2+cu118
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- 6
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for aslinguist/nllb-lora-Atayal2zh
Base model
facebook/nllb-200-distilled-600M