<!-- 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-end-to-end-questions-generation_8ep_lr0.01
This model is a fine-tuned version of t5-base on the squad_modified_for_t5_qg dataset. It achieves the following results on the evaluation set:
- Loss: 2.5802
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: 0.01
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2717 | 0.34 | 100 | 2.4864 |
| 2.5087 | 0.68 | 200 | 2.3288 |
| 2.3408 | 1.02 | 300 | 2.2495 |
| 2.0581 | 1.35 | 400 | 2.1871 |
| 2.0438 | 1.69 | 500 | 2.1204 |
| 1.9822 | 2.03 | 600 | 2.1118 |
| 1.722 | 2.37 | 700 | 2.0911 |
| 1.7595 | 2.71 | 800 | 2.0643 |
| 1.7159 | 3.05 | 900 | 2.0890 |
| 1.4757 | 3.39 | 1000 | 2.0822 |
| 1.5139 | 3.73 | 1100 | 2.0632 |
| 1.46 | 4.06 | 1200 | 2.1460 |
| 1.2551 | 4.4 | 1300 | 2.1216 |
| 1.2766 | 4.74 | 1400 | 2.1117 |
| 1.2149 | 5.08 | 1500 | 2.2481 |
| 1.0209 | 5.42 | 1600 | 2.2210 |
| 1.0359 | 5.76 | 1700 | 2.2369 |
| 0.9834 | 6.1 | 1800 | 2.3935 |
| 0.8123 | 6.44 | 1900 | 2.3865 |
| 0.8144 | 6.77 | 2000 | 2.3698 |
| 0.7583 | 7.11 | 2100 | 2.5418 |
| 0.6369 | 7.45 | 2200 | 2.5720 |
| 0.6271 | 7.79 | 2300 | 2.5802 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
