EN_t5-small_10_spider
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5052
- Rouge2 Precision: 0.4842
- Rouge2 Recall: 0.3056
- Rouge2 Fmeasure: 0.3504
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|---|---|---|---|---|---|---|
| No log | 1.0 | 438 | 0.5472 | 0.3074 | 0.216 | 0.2252 |
| 1.0392 | 2.0 | 876 | 0.4983 | 0.3811 | 0.2468 | 0.2738 |
| 0.3686 | 3.0 | 1314 | 0.5082 | 0.4151 | 0.2587 | 0.2955 |
| 0.3023 | 4.0 | 1752 | 0.4882 | 0.4484 | 0.2716 | 0.3148 |
| 0.2571 | 5.0 | 2190 | 0.4744 | 0.458 | 0.2785 | 0.3233 |
| 0.2369 | 6.0 | 2628 | 0.4777 | 0.4734 | 0.2959 | 0.3402 |
| 0.2208 | 7.0 | 3066 | 0.5062 | 0.4811 | 0.2987 | 0.3445 |
| 0.2095 | 8.0 | 3504 | 0.4881 | 0.4923 | 0.3113 | 0.3572 |
| 0.2095 | 9.0 | 3942 | 0.5006 | 0.4843 | 0.3047 | 0.3498 |
| 0.2013 | 10.0 | 4380 | 0.5052 | 0.4842 | 0.3056 | 0.3504 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.7.dev0
- Tokenizers 0.13.3