<!-- 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-end2end-questions-generation1
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: 1.5657
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: 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: 7
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.4892 | 0.34 | 100 | 1.9104 |
1.9634 | 0.68 | 200 | 1.7233 |
1.8409 | 1.02 | 300 | 1.6656 |
1.743 | 1.35 | 400 | 1.6368 |
1.7147 | 1.69 | 500 | 1.6170 |
1.6906 | 2.03 | 600 | 1.6086 |
1.6333 | 2.37 | 700 | 1.5969 |
1.6292 | 2.71 | 800 | 1.5868 |
1.6124 | 3.05 | 900 | 1.5908 |
1.5729 | 3.39 | 1000 | 1.5820 |
1.5683 | 3.73 | 1100 | 1.5712 |
1.552 | 4.06 | 1200 | 1.5815 |
1.5371 | 4.4 | 1300 | 1.5799 |
1.5268 | 4.74 | 1400 | 1.5677 |
1.5202 | 5.08 | 1500 | 1.5744 |
1.4993 | 5.42 | 1600 | 1.5711 |
1.486 | 5.76 | 1700 | 1.5685 |
1.5027 | 6.1 | 1800 | 1.5678 |
1.4779 | 6.44 | 1900 | 1.5660 |
1.4811 | 6.77 | 2000 | 1.5657 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3