<!-- 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_2000-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: 1.7514
- Hint Hit Num: 1.973
- Hint Precision: 0.3391
- Num: 5.818
- Gen Len: 18.995
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: 16
- eval_batch_size: 128
- 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 |
|---|---|---|---|---|---|---|---|
| 2.2357 | 0.8 | 100 | 1.8147 | 1.81 | 0.3173 | 5.756 | 18.997 |
| 1.9511 | 1.6 | 200 | 1.7767 | 1.961 | 0.3392 | 5.803 | 18.993 |
| 1.8506 | 2.4 | 300 | 1.7798 | 1.834 | 0.3218 | 5.712 | 18.993 |
| 1.7954 | 3.2 | 400 | 1.7513 | 1.899 | 0.3322 | 5.722 | 18.995 |
| 1.7482 | 4.0 | 500 | 1.7512 | 1.948 | 0.3373 | 5.794 | 18.995 |
| 1.7069 | 4.8 | 600 | 1.7475 | 1.936 | 0.3334 | 5.799 | 18.995 |
| 1.6723 | 5.6 | 700 | 1.7407 | 1.922 | 0.3355 | 5.752 | 18.995 |
| 1.6374 | 6.4 | 800 | 1.7492 | 1.941 | 0.3356 | 5.79 | 18.995 |
| 1.6437 | 7.2 | 900 | 1.7478 | 1.936 | 0.3364 | 5.758 | 18.995 |
| 1.6001 | 8.0 | 1000 | 1.7504 | 1.949 | 0.3363 | 5.784 | 18.995 |
| 1.5906 | 8.8 | 1100 | 1.7513 | 1.93 | 0.3335 | 5.784 | 18.995 |
| 1.5832 | 9.6 | 1200 | 1.7523 | 1.977 | 0.3396 | 5.823 | 18.995 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1
