nllb-lora-Amis
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: 7.3832
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 |
|---|---|---|---|
| 7.4953 | 1.0 | 204 | 7.4400 |
| 7.4708 | 2.0 | 408 | 7.4237 |
| 7.4492 | 3.0 | 612 | 7.4126 |
| 7.44 | 4.0 | 816 | 7.4059 |
| 7.2377 | 5.0 | 1020 | 7.4002 |
| 7.4189 | 6.0 | 1224 | 7.3966 |
| 7.4058 | 7.0 | 1428 | 7.3948 |
| 7.4031 | 8.0 | 1632 | 7.3912 |
| 7.4069 | 9.0 | 1836 | 7.3889 |
| 7.209 | 10.0 | 2040 | 7.3873 |
| 7.4002 | 11.0 | 2244 | 7.3866 |
| 7.3932 | 12.0 | 2448 | 7.3868 |
| 7.3901 | 13.0 | 2652 | 7.3861 |
| 7.3901 | 14.0 | 2856 | 7.3842 |
| 7.2014 | 15.0 | 3060 | 7.3839 |
| 7.3808 | 16.0 | 3264 | 7.3839 |
| 7.3823 | 17.0 | 3468 | 7.3838 |
| 7.3772 | 18.0 | 3672 | 7.3832 |
| 7.3797 | 19.0 | 3876 | 7.3833 |
| 7.3799 | 19.9031 | 4060 | 7.3832 |
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
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for aslinguist/nllb-lora-Amis
Base model
facebook/nllb-200-distilled-600M