<!-- 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-cnndm_4000-ep5-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: 1.7363
- Hint Hit Num: 1.936
- Hint Precision: 0.3338
- Num: 5.818
- Gen Len: 18.99
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: 40
- eval_batch_size: 80
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Hint Hit Num | Hint Precision | Num | Gen Len |
---|---|---|---|---|---|---|---|
2.1988 | 1.0 | 100 | 1.8020 | 1.852 | 0.3214 | 5.78 | 19.0 |
1.9385 | 2.0 | 200 | 1.7482 | 1.974 | 0.3426 | 5.796 | 18.986 |
1.8744 | 3.0 | 300 | 1.7407 | 1.976 | 0.3399 | 5.86 | 18.99 |
1.8422 | 4.0 | 400 | 1.7398 | 1.958 | 0.3382 | 5.816 | 18.99 |
1.8238 | 5.0 | 500 | 1.7363 | 1.936 | 0.3338 | 5.818 | 18.99 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1