jojajovai-t5-small-es-grn
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0253
- Bleu: 0.6389
- Chrf: 9.3741
- Combined: 5.0065
- Gen Len: 19.003
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- 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
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf | Combined | Gen Len |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 316 | 3.3359 | 0.6171 | 8.7546 | 4.6859 | 18.9648 |
| 3.4784 | 2.0 | 632 | 3.0960 | 0.6049 | 9.1369 | 4.8709 | 19.0299 |
| 3.4784 | 3.0 | 948 | 3.0342 | 0.5773 | 9.1212 | 4.8492 | 19.0412 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.7.1+cu118
- Datasets 4.4.1
- Tokenizers 0.22.1