<!-- 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. -->
t5-base-finetuned-es-to-maz
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4284
- Bleu: 0.0935
- Gen Len: 19.0
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
No log | 1.0 | 197 | 2.0266 | 0.0049 | 19.0 |
No log | 2.0 | 394 | 1.7260 | 0.0161 | 19.0 |
2.3521 | 3.0 | 591 | 1.6107 | 0.0222 | 19.0 |
2.3521 | 4.0 | 788 | 1.5442 | 0.0692 | 19.0 |
2.3521 | 5.0 | 985 | 1.5024 | 0.0907 | 19.0 |
1.7566 | 6.0 | 1182 | 1.4730 | 0.0909 | 19.0 |
1.7566 | 7.0 | 1379 | 1.4523 | 0.0907 | 19.0 |
1.6434 | 8.0 | 1576 | 1.4394 | 0.0899 | 19.0 |
1.6434 | 9.0 | 1773 | 1.4315 | 0.0916 | 19.0 |
1.6434 | 10.0 | 1970 | 1.4284 | 0.0935 | 19.0 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3