<!-- 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-base-samsum_nl_split
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3366
- Rouge1: 31.6745
- Rouge2: 10.8679
- Rougel: 27.0526
- Rougelsum: 28.5667
- Gen Len: 18.7411
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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.7945 | 1.0 | 1842 | 1.5467 | 30.5738 | 9.4687 | 25.7625 | 27.2563 | 18.7570 |
| 1.5826 | 2.0 | 3684 | 1.4362 | 30.5686 | 9.7518 | 26.1974 | 27.5434 | 18.7802 |
| 1.4657 | 3.0 | 5526 | 1.3886 | 31.1872 | 10.3565 | 26.7847 | 28.2698 | 18.7937 |
| 1.4115 | 4.0 | 7368 | 1.3553 | 31.5017 | 10.7823 | 26.9506 | 28.5006 | 18.7827 |
| 1.3838 | 5.0 | 9210 | 1.3408 | 31.569 | 10.8184 | 26.9738 | 28.4678 | 18.7619 |
| 1.3536 | 6.0 | 11052 | 1.3366 | 31.6745 | 10.8679 | 27.0526 | 28.5667 | 18.7411 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
