<!-- 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-all-cnn_8000-ep10-nonstop
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: 1.6878
- Hint Hit Num: 1.924
- Hint Precision: 0.3322
- Num: 5.757
- 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: 24
- eval_batch_size: 192
- 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 Num | Hint Precision | Num | Gen Len |
---|---|---|---|---|---|---|---|
2.0939 | 0.6 | 200 | 1.7621 | 1.858 | 0.3246 | 5.703 | 18.995 |
1.8887 | 1.2 | 400 | 1.7165 | 1.888 | 0.3321 | 5.687 | 18.995 |
1.8152 | 1.8 | 600 | 1.6944 | 1.912 | 0.3324 | 5.754 | 19.0 |
1.7724 | 2.4 | 800 | 1.6947 | 1.891 | 0.3291 | 5.705 | 19.0 |
1.7501 | 2.99 | 1000 | 1.6792 | 1.887 | 0.3288 | 5.722 | 18.994 |
1.7014 | 3.59 | 1200 | 1.6855 | 1.911 | 0.3333 | 5.703 | 19.0 |
1.6752 | 4.19 | 1400 | 1.6934 | 1.937 | 0.337 | 5.73 | 19.0 |
1.6556 | 4.79 | 1600 | 1.6708 | 1.956 | 0.3404 | 5.711 | 19.0 |
1.6359 | 5.39 | 1800 | 1.6862 | 1.95 | 0.337 | 5.772 | 18.994 |
1.6224 | 5.99 | 2000 | 1.6794 | 1.925 | 0.3348 | 5.724 | 19.0 |
1.6088 | 6.59 | 2200 | 1.6879 | 1.973 | 0.342 | 5.765 | 18.994 |
1.5895 | 7.19 | 2400 | 1.6858 | 1.938 | 0.3348 | 5.777 | 18.994 |
1.5866 | 7.78 | 2600 | 1.6826 | 1.936 | 0.3341 | 5.77 | 19.0 |
1.5717 | 8.38 | 2800 | 1.6912 | 1.942 | 0.3357 | 5.758 | 19.0 |
1.5594 | 8.98 | 3000 | 1.6879 | 1.932 | 0.3324 | 5.777 | 19.0 |
1.5637 | 9.58 | 3200 | 1.6896 | 1.934 | 0.3347 | 5.749 | 19.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1