mt5-small-GEC-spanish-LORA-merged-exp-r-128
This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4064
- Gleu: 0.0
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: 0.001635475313478006
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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: 0.0993688388184371
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Gleu |
|---|---|---|---|---|
| 33.2491 | 1.0 | 2216 | 3.1838 | 0.0 |
| 16.4357 | 2.0 | 4432 | 2.4064 | 0.0 |
Framework versions
- PEFT 0.18.1
- Transformers 5.0.0
- Pytorch 2.7.0+cu126
- Datasets 4.8.5
- Tokenizers 0.22.2