t5-base-end2end-questions-generation_squad_eli_exp_imp
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2204
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: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3587 | 0.24 | 100 | 2.2995 |
| 2.1713 | 0.48 | 200 | 2.2715 |
| 2.1506 | 0.72 | 300 | 2.2446 |
| 2.1138 | 0.96 | 400 | 2.2391 |
| 2.0454 | 1.21 | 500 | 2.2350 |
| 2.0286 | 1.45 | 600 | 2.2319 |
| 2.0171 | 1.69 | 700 | 2.2214 |
| 2.0041 | 1.93 | 800 | 2.2205 |
| 1.9694 | 2.17 | 900 | 2.2208 |
| 1.964 | 2.41 | 1000 | 2.2232 |
| 1.9667 | 2.65 | 1100 | 2.2191 |
| 1.9659 | 2.89 | 1200 | 2.2204 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.1
- Tokenizers 0.13.3