<!-- 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-small-qg-2.0
This model is a fine-tuned version of t5-small on the the_squad_qg dataset. It achieves the following results on the evaluation set:
- Loss: 1.9589
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2981 | 0.68 | 100 | 2.3598 |
| 2.4962 | 1.36 | 200 | 2.2479 |
| 2.374 | 2.03 | 300 | 2.1625 |
| 2.2951 | 2.71 | 400 | 2.0871 |
| 2.2279 | 3.39 | 500 | 2.0532 |
| 2.1926 | 4.07 | 600 | 2.0325 |
| 2.1605 | 4.75 | 700 | 2.0154 |
| 2.1438 | 5.42 | 800 | 1.9920 |
| 2.1154 | 6.1 | 900 | 1.9829 |
| 2.1014 | 6.78 | 1000 | 1.9782 |
| 2.0976 | 7.46 | 1100 | 1.9649 |
| 2.0817 | 8.14 | 1200 | 1.9647 |
| 2.0767 | 8.81 | 1300 | 1.9631 |
| 2.0749 | 9.49 | 1400 | 1.9589 |
Framework versions
- Transformers 4.27.3
- Pytorch 2.0.0
- Datasets 2.10.1
- Tokenizers 0.11.0
