<!-- 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-hint_precision-ep10
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0572
- Hint Hit: 1.154
- Hint Hit Num: 2.106
- Hint Precision: 0.3563
- Hint Bleu: 3.8159
- Num: 5.914
- Gen Len: 18.98
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 |
---|---|---|---|---|---|---|---|---|---|
1.0982 | 0.8 | 400 | 1.9452 | 1.093 | 2.064 | 0.3494 | 3.6663 | 5.948 | 18.986 |
1.0291 | 1.6 | 800 | 2.0448 | 1.0975 | 2.086 | 0.3489 | 3.8148 | 6.04 | 18.988 |
0.9856 | 2.4 | 1200 | 2.0572 | 1.154 | 2.106 | 0.3563 | 3.8159 | 5.914 | 18.98 |
1.1174 | 3.2 | 1600 | 2.0025 | 1.0885 | 2.066 | 0.3489 | 3.7311 | 5.976 | 18.992 |
1.0846 | 4.0 | 2000 | 1.9925 | 1.1005 | 2.068 | 0.3523 | 3.7582 | 5.938 | 18.994 |
1.0633 | 4.8 | 2400 | 2.0297 | 1.042 | 2.008 | 0.3436 | 3.6891 | 5.872 | 18.99 |
1.0466 | 5.6 | 2800 | 2.0564 | 1.102 | 2.068 | 0.3512 | 3.7983 | 5.932 | 18.992 |
1.0527 | 6.4 | 3200 | 2.0553 | 1.11 | 2.084 | 0.3511 | 3.7702 | 5.98 | 18.998 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1