<!-- 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. -->
flan-t5-small-preferencebot
This model is a fine-tuned version of google/flan-t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5985
- Rouge1: 10.3563
- Rouge2: 2.219
- Rougel: 8.7303
- Rougelsum: 9.7906
- Gen Len: 19.0
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.2219 | 1.0 | 11 | 2.6762 | 9.0589 | 3.3625 | 7.6488 | 8.1718 | 14.8 |
| 3.1589 | 2.0 | 22 | 2.6530 | 9.2897 | 2.7733 | 7.1237 | 8.5217 | 16.5 |
| 3.0522 | 3.0 | 33 | 2.6349 | 9.4754 | 2.5007 | 7.4186 | 8.5739 | 18.2 |
| 3.086 | 4.0 | 44 | 2.6199 | 8.1732 | 2.1256 | 6.8356 | 7.4716 | 18.3 |
| 3.0436 | 5.0 | 55 | 2.6100 | 8.8588 | 1.9525 | 7.1538 | 8.0757 | 19.0 |
| 2.9848 | 6.0 | 66 | 2.6038 | 10.3103 | 2.141 | 8.7298 | 9.7082 | 19.0 |
| 2.977 | 7.0 | 77 | 2.6008 | 10.3963 | 2.219 | 8.8111 | 9.782 | 19.0 |
| 2.9861 | 8.0 | 88 | 2.5995 | 10.3563 | 2.219 | 8.7303 | 9.7906 | 19.0 |
| 2.9991 | 9.0 | 99 | 2.5986 | 10.3563 | 2.219 | 8.7303 | 9.7906 | 19.0 |
| 2.9378 | 10.0 | 110 | 2.5985 | 10.3563 | 2.219 | 8.7303 | 9.7906 | 19.0 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
