<!-- 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. -->
text-to-sparql-t5-base-2023-04-28_09-33
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1030
- Gen Len: 19.0
- Bertscorer-p: 0.5930
- Bertscorer-r: 0.1065
- Bertscorer-f1: 0.3388
- Sacrebleu-score: 6.6831
- Sacrebleu-precisions: [93.30425644697809, 87.38127821238179, 83.23877470131929, 80.25593452955827]
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Gen Len | Bertscorer-p | Bertscorer-r | Bertscorer-f1 | Sacrebleu-score | Sacrebleu-precisions |
|---|---|---|---|---|---|---|---|---|---|
| 0.1687 | 1.0 | 4807 | 0.1246 | 19.0 | 0.5869 | 0.1028 | 0.3340 | 6.5777 | [92.7309397451507, 86.01551337007552, 81.37766360745528, 78.09762043832694] |
| 0.1114 | 2.0 | 9614 | 0.1030 | 19.0 | 0.5930 | 0.1065 | 0.3388 | 6.6831 | [93.30425644697809, 87.38127821238179, 83.23877470131929, 80.25593452955827] |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Tokenizers 0.13.3
