<!-- 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-azz
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8508
- Bleu: 0.0946
- 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 | 199 | 2.7138 | 0.0093 | 19.0 |
No log | 2.0 | 398 | 2.3010 | 0.0071 | 19.0 |
3.0507 | 3.0 | 597 | 2.1325 | 0.1019 | 19.0 |
3.0507 | 4.0 | 796 | 2.0305 | 0.1309 | 19.0 |
3.0507 | 5.0 | 995 | 1.9620 | 0.0927 | 19.0 |
2.3223 | 6.0 | 1194 | 1.9178 | 0.0773 | 19.0 |
2.3223 | 7.0 | 1393 | 1.8883 | 0.1025 | 19.0 |
2.1572 | 8.0 | 1592 | 1.8655 | 0.0928 | 19.0 |
2.1572 | 9.0 | 1791 | 1.8544 | 0.0958 | 19.0 |
2.1572 | 10.0 | 1990 | 1.8508 | 0.0946 | 19.0 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3