<!-- 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-base-extraction-cnndm_1000-all-loss-ep50
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8701
- Hint Hit Num: 2.2908
- Hint Precision: 0.4224
- Num: 5.4042
- Gen Len: 18.9791
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: 60
- eval_batch_size: 400
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Hint Hit Num | Hint Precision | Num | Gen Len |
|---|---|---|---|---|---|---|---|
| 2.4002 | 5.88 | 100 | 1.9290 | 2.16 | 0.4094 | 5.2408 | 18.9734 |
| 2.0248 | 11.76 | 200 | 1.8906 | 2.2181 | 0.4168 | 5.2966 | 18.9708 |
| 1.9015 | 17.65 | 300 | 1.8701 | 2.2908 | 0.4224 | 5.4042 | 18.9791 |
| 1.8255 | 23.53 | 400 | 1.8709 | 2.3019 | 0.4236 | 5.4179 | 18.9865 |
| 1.7675 | 29.41 | 500 | 1.8756 | 2.3209 | 0.4249 | 5.4454 | 18.9889 |
| 1.7203 | 35.29 | 600 | 1.8798 | 2.3049 | 0.4239 | 5.4188 | 18.9861 |
| 1.6937 | 41.18 | 700 | 1.8791 | 2.311 | 0.4232 | 5.4415 | 18.9895 |
| 1.6725 | 47.06 | 800 | 1.8822 | 2.3248 | 0.4247 | 5.451 | 18.989 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1
