t5-end2end-questions-generation
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1822
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 |
---|---|---|---|
1.704 | 0.43 | 100 | 1.2946 |
1.3902 | 0.86 | 200 | 1.2393 |
1.2897 | 1.3 | 300 | 1.2200 |
1.2572 | 1.73 | 400 | 1.1981 |
1.2286 | 2.16 | 500 | 1.1941 |
1.1591 | 2.59 | 600 | 1.1852 |
1.1686 | 3.02 | 700 | 1.1789 |
1.1071 | 3.45 | 800 | 1.1810 |
1.1117 | 3.89 | 900 | 1.1766 |
1.0728 | 4.32 | 1000 | 1.1829 |
1.063 | 4.75 | 1100 | 1.1783 |
1.0657 | 5.18 | 1200 | 1.1810 |
1.031 | 5.61 | 1300 | 1.1809 |
1.0304 | 6.05 | 1400 | 1.1809 |
1.0111 | 6.48 | 1500 | 1.1818 |
1.0161 | 6.91 | 1600 | 1.1822 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0
- Datasets 2.12.0
- Tokenizers 0.11.0
- Downloads last month
- 15
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.