t5-small-finetunesmallT5
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 22.8504
- Rouge1: 80.2116
- Rouge2: 70.3704
- Rougel: 80.2116
- Rougelsum: 80.2116
- Gen Len: 4.0
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 4 | 27.3213 | 80.2116 | 70.3704 | 80.2116 | 80.2116 | 4.0 |
| No log | 2.0 | 8 | 25.8240 | 80.2116 | 70.3704 | 80.2116 | 80.2116 | 4.0 |
| No log | 3.0 | 12 | 24.2754 | 80.2116 | 70.3704 | 80.2116 | 80.2116 | 4.0 |
| No log | 4.0 | 16 | 23.4084 | 80.2116 | 70.3704 | 80.2116 | 80.2116 | 4.0 |
| No log | 5.0 | 20 | 22.8504 | 80.2116 | 70.3704 | 80.2116 | 80.2116 | 4.0 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3