t5-end2end-questions-generation
This model is a fine-tuned version of t5-base on the squad v1.1 dataset. It achieves the following results on the evaluation set:
- Loss: 1.5789
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5879 | 0.34 | 100 | 1.9133 |
| 1.9688 | 0.68 | 200 | 1.7313 |
| 1.8513 | 1.02 | 300 | 1.6691 |
| 1.7459 | 1.36 | 400 | 1.6413 |
| 1.7206 | 1.69 | 500 | 1.6200 |
| 1.7026 | 2.03 | 600 | 1.6101 |
| 1.6447 | 2.37 | 700 | 1.5983 |
| 1.6402 | 2.71 | 800 | 1.5979 |
| 1.6332 | 3.05 | 900 | 1.5924 |
| 1.5953 | 3.39 | 1000 | 1.5877 |
| 1.5922 | 3.73 | 1100 | 1.5854 |
| 1.5832 | 4.07 | 1200 | 1.5830 |
| 1.5726 | 4.41 | 1300 | 1.5799 |
| 1.5587 | 4.75 | 1400 | 1.5789 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 7
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.