mt5-small-GEC-spanish-cowsl2h-exp
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0082
- 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Gleu |
|---|---|---|---|---|
| 3205.9113 | 1.0 | 194 | 7.1162 | 0.0000 |
| 53.1602 | 2.0 | 388 | 1.5675 | 0.0 |
| 6.9103 | 3.0 | 582 | 1.1224 | 0.0 |
| 5.3435 | 4.0 | 776 | 1.0082 | 0.0 |
Framework versions
- Transformers 5.5.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2