t5-base-sheldon-chat
This model is a fine-tuned version of google-t5/t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5988
- Rouge1: 9.7407
- Rouge2: 1.9252
- Rougel: 9.2148
- Rougelsum: 9.3917
- Gen Len: 12.3466
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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
3.0866 | 1.0 | 2902 | 2.8205 | 8.7518 | 1.7718 | 8.3985 | 8.4501 | 9.5291 |
2.8627 | 2.0 | 5804 | 2.6565 | 9.9048 | 2.0274 | 9.341 | 9.5101 | 12.2791 |
2.7773 | 3.0 | 8706 | 2.5988 | 9.7407 | 1.9252 | 9.2148 | 9.3917 | 12.3466 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.15.2
- Downloads last month
- 2