<!-- 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_4000-all-new
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: 1.7217
- Rouge1: 35.7039
- Rouge2: 15.7172
- Rougel: 30.4548
- Rougelsum: 30.4927
- 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 48
- 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 |
---|---|---|---|---|---|---|---|---|
2.1171 | 0.8 | 200 | 1.7879 | 33.136 | 13.8435 | 28.2659 | 28.2963 | 19.0 |
1.8929 | 1.6 | 400 | 1.7502 | 34.0512 | 14.7178 | 29.4891 | 29.4818 | 18.99 |
1.8254 | 2.4 | 600 | 1.7331 | 35.166 | 15.5654 | 30.1143 | 30.1629 | 18.99 |
1.7543 | 3.2 | 800 | 1.7371 | 35.4455 | 15.7511 | 30.7242 | 30.6975 | 19.0 |
1.7053 | 4.0 | 1000 | 1.7217 | 35.7039 | 15.7172 | 30.4548 | 30.4927 | 19.0 |
1.6508 | 4.8 | 1200 | 1.7275 | 35.0989 | 15.6698 | 30.0472 | 30.0981 | 19.0 |
1.6029 | 5.6 | 1400 | 1.7308 | 35.3936 | 16.1155 | 30.5695 | 30.633 | 19.0 |
1.5741 | 6.4 | 1600 | 1.7547 | 35.4065 | 15.9775 | 30.4598 | 30.5162 | 19.0 |
1.5497 | 7.2 | 1800 | 1.7508 | 35.5377 | 16.0075 | 30.5775 | 30.5533 | 19.0 |
1.5029 | 8.0 | 2000 | 1.7498 | 34.9215 | 15.4151 | 29.8118 | 29.802 | 19.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1