| --- |
| library_name: peft |
| license: mit |
| base_model: facebook/mbart-large-50 |
| tags: |
| - base_model:adapter:facebook/mbart-large-50 |
| - lora |
| - transformers |
| model-index: |
| - name: mbart-large-50-GEC-spanish-LORA-cowsl2h |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # mbart-large-50-GEC-spanish-LORA-cowsl2h |
|
|
| This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 8.1098 |
| - Gleu: 0.5515 |
|
|
| ## 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: 0.00044406688888615583 |
| - train_batch_size: 16 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - 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: 0.08309212265191754 |
| - num_epochs: 3 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Gleu | |
| |:-------------:|:-----:|:----:|:---------------:|:------:| |
| | 9.2875 | 1.0 | 388 | 8.1391 | 0.4431 | |
| | 8.1733 | 2.0 | 776 | 8.1141 | 0.5315 | |
| | 8.1488 | 3.0 | 1164 | 8.1098 | 0.5515 | |
| |
| |
| ### Framework versions |
| |
| - PEFT 0.18.1 |
| - Transformers 5.0.0 |
| - Pytorch 2.7.0+cu126 |
| - Datasets 4.8.5 |
| - Tokenizers 0.22.2 |
