<!-- 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. -->
t5-base-SQuAD-qg-ep10
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4837
- Rouge1: 39.225
- Rouge2: 17.5912
- Rougel: 35.5634
- Rougelsum: 35.5514
- Gen Len: 13.5941
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: 72
- eval_batch_size: 144
- 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.0366 | 0.76 | 200 | 1.6135 | 38.2514 | 16.449 | 34.7626 | 34.7415 | 13.4074 |
| 1.7544 | 1.52 | 400 | 1.5574 | 38.4555 | 16.7217 | 34.8476 | 34.799 | 13.6033 |
| 1.6827 | 2.28 | 600 | 1.5303 | 38.6393 | 16.8394 | 35.0986 | 35.0749 | 13.5573 |
| 1.6544 | 3.04 | 800 | 1.5159 | 38.0175 | 16.4916 | 34.5157 | 34.492 | 13.6831 |
| 1.6202 | 3.8 | 1000 | 1.5046 | 39.029 | 17.2625 | 35.4493 | 35.439 | 13.5815 |
| 1.5817 | 4.56 | 1200 | 1.4998 | 38.5684 | 16.8763 | 34.9933 | 34.9728 | 13.6425 |
| 1.583 | 5.32 | 1400 | 1.4951 | 38.8284 | 17.2627 | 35.2844 | 35.261 | 13.5651 |
| 1.5553 | 6.08 | 1600 | 1.4922 | 38.7763 | 17.1948 | 35.1699 | 35.1494 | 13.6507 |
| 1.5405 | 6.84 | 1800 | 1.4877 | 39.1529 | 17.5602 | 35.5378 | 35.5285 | 13.5893 |
| 1.5391 | 7.6 | 2000 | 1.4854 | 39.2661 | 17.5374 | 35.6662 | 35.649 | 13.6067 |
| 1.5298 | 8.37 | 2200 | 1.4843 | 39.281 | 17.611 | 35.6203 | 35.6159 | 13.6222 |
| 1.5224 | 9.13 | 2400 | 1.4837 | 39.225 | 17.5912 | 35.5634 | 35.5514 | 13.5941 |
| 1.5143 | 9.89 | 2600 | 1.4837 | 39.2284 | 17.5523 | 35.5238 | 35.5112 | 13.5583 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1
