t5_small_A_SapBERT
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8647
- Rouge1: 0.1085
- Rouge2: 0.0448
- Rougel: 0.1043
- Rougelsum: 0.1046
- Gen Len: 3.8938
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.034 | 1.0 | 527 | 1.1249 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.0575 | 2.0 | 1054 | 1.0118 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.9878 | 3.0 | 1581 | 0.9322 | 0.0104 | 0.0058 | 0.0101 | 0.0101 | 0.5221 |
| 0.8865 | 4.0 | 2108 | 0.9022 | 0.0363 | 0.0149 | 0.0349 | 0.0341 | 3.1681 |
| 0.8832 | 5.0 | 2635 | 0.8891 | 0.0758 | 0.0303 | 0.0713 | 0.0715 | 3.9558 |
| 0.8657 | 6.0 | 3162 | 0.8815 | 0.0955 | 0.041 | 0.0912 | 0.0924 | 4.292 |
| 0.8153 | 7.0 | 3689 | 0.8753 | 0.1007 | 0.0439 | 0.0948 | 0.0957 | 3.9292 |
| 0.8237 | 8.0 | 4216 | 0.8710 | 0.1063 | 0.0457 | 0.1006 | 0.1009 | 3.8319 |
| 0.8491 | 9.0 | 4743 | 0.8681 | 0.103 | 0.0418 | 0.0982 | 0.0989 | 3.708 |
| 0.8227 | 10.0 | 5270 | 0.8660 | 0.1085 | 0.0448 | 0.1043 | 0.1046 | 3.9027 |
| 0.8355 | 11.0 | 5797 | 0.8649 | 0.1085 | 0.0448 | 0.1043 | 0.1046 | 3.8938 |
| 0.7787 | 12.0 | 6324 | 0.8647 | 0.1085 | 0.0448 | 0.1043 | 0.1046 | 3.8938 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2