<!-- 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_4000-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: 1.7725
- Hint Hit Num: 2.3971
- Hint Precision: 0.4325
- Num: 5.5242
- Gen Len: 18.9994
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 |
|---|---|---|---|---|---|---|---|
| 2.4364 | 1.49 | 100 | 1.9011 | 2.2142 | 0.4104 | 5.4023 | 18.9832 |
| 2.1323 | 2.99 | 200 | 1.8601 | 2.2703 | 0.4207 | 5.4015 | 18.9909 |
| 2.053 | 4.48 | 300 | 1.8248 | 2.3204 | 0.4264 | 5.4393 | 18.996 |
| 1.9901 | 5.97 | 400 | 1.8057 | 2.3274 | 0.4276 | 5.434 | 18.9989 |
| 1.9581 | 7.46 | 500 | 1.7883 | 2.3746 | 0.4323 | 5.4853 | 18.9992 |
| 1.924 | 8.96 | 600 | 1.7860 | 2.3598 | 0.4305 | 5.4683 | 18.9996 |
| 1.8916 | 10.45 | 700 | 1.7822 | 2.3769 | 0.4316 | 5.4918 | 18.9998 |
| 1.8678 | 11.94 | 800 | 1.7885 | 2.3537 | 0.43 | 5.457 | 18.999 |
| 1.8388 | 13.43 | 900 | 1.7785 | 2.3959 | 0.4335 | 5.5158 | 18.9987 |
| 1.8219 | 14.93 | 1000 | 1.7790 | 2.3789 | 0.4309 | 5.5044 | 18.9987 |
| 1.8016 | 16.42 | 1100 | 1.7789 | 2.3677 | 0.4306 | 5.485 | 18.9991 |
| 1.7739 | 17.91 | 1200 | 1.7725 | 2.3971 | 0.4325 | 5.5242 | 18.9994 |
| 1.7626 | 19.4 | 1300 | 1.7852 | 2.3603 | 0.4289 | 5.483 | 18.9991 |
| 1.7512 | 20.9 | 1400 | 1.7821 | 2.3861 | 0.4314 | 5.5117 | 18.9993 |
| 1.7319 | 22.39 | 1500 | 1.7821 | 2.3966 | 0.4323 | 5.5287 | 18.9994 |
| 1.7135 | 23.88 | 1600 | 1.7893 | 2.403 | 0.433 | 5.5313 | 18.9993 |
| 1.7004 | 25.37 | 1700 | 1.7853 | 2.4254 | 0.4345 | 5.5673 | 18.9996 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1
