trainer_output
This model is a fine-tuned version of facebook/nllb-200-distilled-600M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9640
- Bleu: 18.5861
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 2.392 | 1.0 | 2525 | 2.2508 | 13.6779 |
| 2.1302 | 2.0 | 5050 | 2.0765 | 17.1351 |
| 1.9159 | 3.0 | 7575 | 1.9920 | 17.7167 |
| 1.7718 | 4.0 | 10100 | 1.9664 | 18.6164 |
| 1.6949 | 5.0 | 12625 | 1.9633 | 18.6201 |
| 1.6918 | 6.0 | 15150 | 1.9640 | 18.5861 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.4.2
- Tokenizers 0.22.1
- Downloads last month
- 48
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Gaoussin/trainer_output
Base model
facebook/nllb-200-distilled-600M