kwk-nllb-model
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: 7.0536
- Bleu: 0.5439
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: 3e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 11.8536 | 1.0 | 192 | 8.7583 | 0.0 |
| 8.1736 | 2.0 | 384 | 7.4605 | 0.2068 |
| 7.6073 | 3.0 | 576 | 7.3311 | 1.0085 |
| 7.4295 | 4.0 | 768 | 7.2383 | 1.2905 |
| 7.3204 | 5.0 | 960 | 7.1652 | 0.8375 |
| 7.2429 | 6.0 | 1152 | 7.1109 | 0.7959 |
| 7.1897 | 7.0 | 1344 | 7.0742 | 0.8037 |
| 7.1567 | 8.0 | 1536 | 7.0541 | 0.8031 |
| 7.1409 | 9.0 | 1728 | 7.0462 | 0.8000 |
| 7.1363 | 10.0 | 1920 | 7.0451 | 0.8051 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.1.0+cu118
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for farhanShaikh/kwk-nllb-model
Base model
facebook/nllb-200-distilled-600M