<!-- 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-large-extraction-cnndm_1000-all
This model is a fine-tuned version of google/flan-t5-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8091
- Rouge1: 34.4985
- Rouge2: 14.964
- Rougel: 29.6673
- Rougelsum: 29.6632
- Gen Len: 18.978
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: 8
- eval_batch_size: 24
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
2.1257 | 1.6 | 200 | 1.8318 | 35.0827 | 14.7034 | 29.3871 | 29.3654 | 18.994 |
1.8202 | 3.2 | 400 | 1.8333 | 34.8523 | 15.0986 | 29.9144 | 29.9472 | 18.986 |
1.6711 | 4.8 | 600 | 1.8091 | 34.4985 | 14.964 | 29.6673 | 29.6632 | 18.978 |
1.5597 | 6.4 | 800 | 1.8217 | 34.6517 | 15.2819 | 29.7011 | 29.7576 | 18.988 |
1.4743 | 8.0 | 1000 | 1.8223 | 34.0466 | 14.7149 | 29.259 | 29.3157 | 18.976 |
1.3895 | 9.6 | 1200 | 1.8799 | 34.224 | 14.8791 | 29.0879 | 29.0948 | 18.986 |
1.3446 | 11.2 | 1400 | 1.8773 | 34.4388 | 14.5656 | 29.0993 | 29.0684 | 18.994 |
1.272 | 12.8 | 1600 | 1.9016 | 34.4097 | 14.6647 | 29.1727 | 29.1556 | 18.984 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1