<!-- 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-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: 6.2845
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: 0.5
- 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 |
---|---|---|---|
13.9791 | 0.34 | 100 | 7.0257 |
6.7646 | 0.68 | 200 | 6.7606 |
6.7318 | 1.02 | 300 | 7.0232 |
6.458 | 1.35 | 400 | 6.4509 |
6.4751 | 1.69 | 500 | 6.4592 |
6.3794 | 2.03 | 600 | 6.3833 |
6.31 | 2.37 | 700 | 6.3374 |
6.26 | 2.71 | 800 | 6.3314 |
6.3181 | 3.05 | 900 | 6.3919 |
6.2577 | 3.39 | 1000 | 6.3266 |
6.226 | 3.73 | 1100 | 6.2640 |
6.2227 | 4.06 | 1200 | 6.3328 |
6.2423 | 4.4 | 1300 | 6.3034 |
6.224 | 4.74 | 1400 | 6.2845 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3