t5-end2end-questions-generation
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: 1.5674
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 |
---|---|---|---|
2.5884 | 0.34 | 100 | 1.9159 |
1.9705 | 0.68 | 200 | 1.7310 |
1.8439 | 1.02 | 300 | 1.6672 |
1.7426 | 1.35 | 400 | 1.6382 |
1.7147 | 1.69 | 500 | 1.6199 |
1.6908 | 2.03 | 600 | 1.6053 |
1.6315 | 2.37 | 700 | 1.5967 |
1.627 | 2.71 | 800 | 1.5939 |
1.6122 | 3.05 | 900 | 1.5877 |
1.5706 | 3.39 | 1000 | 1.5861 |
1.5708 | 3.73 | 1100 | 1.5742 |
1.5534 | 4.06 | 1200 | 1.5798 |
1.5351 | 4.4 | 1300 | 1.5738 |
1.5226 | 4.74 | 1400 | 1.5757 |
1.5187 | 5.08 | 1500 | 1.5727 |
1.4963 | 5.42 | 1600 | 1.5710 |
1.4841 | 5.76 | 1700 | 1.5668 |
1.5025 | 6.1 | 1800 | 1.5688 |
1.4778 | 6.44 | 1900 | 1.5717 |
1.4769 | 6.77 | 2000 | 1.5674 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Downloads last month
- 18
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.