<!-- 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_recommendation_sports_equipment_english
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0846
- Rouge1: 8.5433
- Rouge2: 3.6562
- Rougel: 8.4576
- Rougelsum: 8.5177
- Gen Len: 5.795
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: 0.0001
- train_batch_size: 15
- eval_batch_size: 15
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 60
- 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 0.99 | 53 | 0.1981 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| No log | 1.99 | 106 | 0.1297 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| No log | 2.99 | 159 | 0.0940 | 7.9888 | 1.5625 | 7.9690 | 7.9744 | 6.495 |
| No log | 3.99 | 212 | 0.0918 | 8.4655 | 1.9420 | 8.3894 | 8.4181 | 6.3525 |
| No log | 4.99 | 265 | 0.0896 | 8.6135 | 2.0312 | 8.4973 | 8.5159 | 6.1212 |
| No log | 5.99 | 318 | 0.0884 | 8.9882 | 2.5625 | 8.8042 | 8.8302 | 6.1513 |
| No log | 6.99 | 371 | 0.0871 | 8.9843 | 2.7812 | 8.9216 | 8.9330 | 6.1188 |
| No log | 7.99 | 424 | 0.0867 | 9.1104 | 3.4601 | 8.9543 | 8.9860 | 5.91 |
| No log | 8.99 | 477 | 0.0857 | 8.7896 | 3.6069 | 8.6949 | 8.7387 | 5.79 |
| 0.4188 | 9.99 | 530 | 0.0846 | 8.5433 | 3.6562 | 8.4576 | 8.5177 | 5.795 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.3
