m2m100_418M-GEC-spanish-merged
This model is a fine-tuned version of facebook/m2m100_418M on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0410
- Gleu: 0.8377
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: 4.3060297566589666e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.060453811040672545
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Gleu |
|---|---|---|---|---|
| 0.1250 | 1.0 | 1402 | 0.0441 | 0.8262 |
| 0.0870 | 2.0 | 2804 | 0.0410 | 0.8377 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2