<!-- 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_2000-all-hint_precision-ep10
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8074
- Hint Hit: 1.1835
- Hint Hit Num: 2.124
- Hint Precision: 0.3635
- Hint Bleu: 3.8356
- Num: 5.886
- 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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Hint Hit | Hint Hit Num | Hint Precision | Hint Bleu | Num | Gen Len |
---|---|---|---|---|---|---|---|---|---|
1.4841 | 1.6 | 400 | 1.8074 | 1.1835 | 2.124 | 0.3635 | 3.8356 | 5.886 | 19.0 |
1.3607 | 3.2 | 800 | 1.8859 | 0.987 | 1.956 | 0.3355 | 3.5039 | 5.832 | 18.99 |
1.362 | 4.8 | 1200 | 1.8439 | 1.0915 | 2.04 | 0.351 | 3.6963 | 5.834 | 19.0 |
1.3634 | 6.4 | 1600 | 1.8609 | 1.0995 | 2.062 | 0.351 | 3.7585 | 5.912 | 18.978 |
1.3221 | 8.0 | 2000 | 1.8717 | 1.1175 | 2.058 | 0.3535 | 3.71 | 5.82 | 18.99 |
1.2845 | 9.6 | 2400 | 1.8741 | 1.151 | 2.09 | 0.3582 | 3.7956 | 5.846 | 18.978 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1