mt5-large-GEC-spanish-LORA-cowsl2h
This model is a fine-tuned version of google/mt5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0646
- Gleu: 0.5390
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: 0.0004542233703472283
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.07566828197066039
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Gleu |
|---|---|---|---|---|
| 2.8971 | 1.0 | 388 | 0.1123 | 0.3934 |
| 0.3864 | 2.0 | 776 | 0.0699 | 0.4984 |
| 0.3465 | 3.0 | 1164 | 0.0673 | 0.5164 |
| 0.3290 | 4.0 | 1552 | 0.0646 | 0.5390 |
Framework versions
- PEFT 0.18.1
- Transformers 5.0.0
- Pytorch 2.7.0+cu126
- Datasets 4.8.5
- Tokenizers 0.22.2