| --- |
| library_name: peft |
| license: mit |
| base_model: facebook/m2m100_418M |
| tags: |
| - base_model:adapter:facebook/m2m100_418M |
| - lora |
| - transformers |
| model-index: |
| - name: m2m100_418M-GEC-spanish-LORA-synthetic |
| 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. --> |
|
|
| # m2m100_418M-GEC-spanish-LORA-synthetic |
| |
| This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 3.9074 |
| - Gleu: 0.9276 |
| |
| ## 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: 0.00044107500561578277 |
| - train_batch_size: 16 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.ADAFACTOR and the args are: |
| No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 0.08950396527674138 |
| - num_epochs: 2 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Gleu | |
| |:-------------:|:-----:|:-----:|:---------------:|:------:| |
| | 3.9485 | 1.0 | 6896 | 3.9114 | 0.9166 | |
| | 3.9632 | 2.0 | 13792 | 3.9074 | 0.9276 | |
|
|
|
|
| ### Framework versions |
|
|
| - PEFT 0.18.1 |
| - Transformers 5.0.0 |
| - Pytorch 2.7.0+cu126 |
| - Datasets 4.8.5 |
| - Tokenizers 0.22.2 |
