output_dir
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: 3.0336
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.7119 | 0.64 | 10000 | 4.8451 |
| 4.7287 | 1.28 | 20000 | 4.2161 |
| 4.1533 | 1.92 | 30000 | 3.8090 |
| 3.7565 | 2.55 | 40000 | 3.5356 |
| 3.4905 | 3.19 | 50000 | 3.3501 |
| 3.2839 | 3.83 | 60000 | 3.2065 |
| 3.1323 | 4.47 | 70000 | 3.1168 |
| 3.0369 | 5.11 | 80000 | 3.0617 |
| 2.9753 | 5.75 | 90000 | 3.0336 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.8.0+cu126
- Datasets 2.16.1
- Tokenizers 0.15.2
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for salmabahdad1/output_dir
Base model
facebook/nllb-200-distilled-600M