my-text-to-sparql-id-combined-dataset-t5-base-2023-05-07_15-33
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3333
- Gen Len: 19.0
- Bertscorer-p: 0.5060
- Bertscorer-r: 0.1130
- Bertscorer-f1: 0.3017
- Sacrebleu-score: 6.1737
- Sacrebleu-precisions: [78.41306042322238, 65.32969938575438, 54.170628484068835, 48.69315639562166]
- Bleu-bp: 0.1018
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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Gen Len | Bertscorer-p | Bertscorer-r | Bertscorer-f1 | Sacrebleu-score | Sacrebleu-precisions | Bleu-bp |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.3541 | 1.0 | 7822 | 0.3333 | 19.0 | 0.5060 | 0.1130 | 0.3017 | 6.1737 | [78.41306042322238, 65.32969938575438, 54.170628484068835, 48.69315639562166] | 0.1018 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3