nllb-lora-Paiwan
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: 7.3958
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 |
|---|---|---|---|
| 7.4934 | 1.0 | 201 | 7.4371 |
| 7.4808 | 2.0 | 402 | 7.4273 |
| 7.4608 | 3.0 | 603 | 7.4223 |
| 7.4547 | 4.0 | 804 | 7.4194 |
| 7.4386 | 5.0 | 1005 | 7.4172 |
| 7.4414 | 6.0 | 1206 | 7.4116 |
| 7.4349 | 7.0 | 1407 | 7.4079 |
| 7.4189 | 8.0 | 1608 | 7.4040 |
| 7.4228 | 9.0 | 1809 | 7.4029 |
| 7.4111 | 10.0 | 2010 | 7.4001 |
| 7.4093 | 11.0 | 2211 | 7.3995 |
| 7.4088 | 12.0 | 2412 | 7.3982 |
| 7.4067 | 13.0 | 2613 | 7.3981 |
| 7.402 | 14.0 | 2814 | 7.3971 |
| 7.3989 | 15.0 | 3015 | 7.3963 |
| 7.3954 | 16.0 | 3216 | 7.3960 |
| 7.3914 | 17.0 | 3417 | 7.3960 |
| 7.3803 | 18.0 | 3618 | 7.3959 |
| 7.3742 | 19.0 | 3819 | 7.3963 |
| 7.3832 | 20.0 | 4020 | 7.3958 |
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
- 13
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for aslinguist/nllb-lora-Paiwan
Base model
facebook/nllb-200-distilled-600M