<!-- 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: 1.8006
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: 0.001
- 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 |
---|---|---|---|
2.1137 | 0.34 | 100 | 1.7232 |
1.7934 | 0.68 | 200 | 1.6669 |
1.7274 | 1.02 | 300 | 1.6386 |
1.4922 | 1.35 | 400 | 1.6310 |
1.5064 | 1.69 | 500 | 1.6207 |
1.4764 | 2.03 | 600 | 1.6457 |
1.2802 | 2.37 | 700 | 1.6392 |
1.3035 | 2.71 | 800 | 1.6235 |
1.2837 | 3.05 | 900 | 1.6841 |
1.1289 | 3.39 | 1000 | 1.6862 |
1.1485 | 3.73 | 1100 | 1.6586 |
1.1213 | 4.06 | 1200 | 1.7228 |
1.0096 | 4.4 | 1300 | 1.7205 |
1.0124 | 4.74 | 1400 | 1.6989 |
0.9942 | 5.08 | 1500 | 1.7720 |
0.9044 | 5.42 | 1600 | 1.7633 |
0.9058 | 5.76 | 1700 | 1.7673 |
0.8977 | 6.1 | 1800 | 1.8048 |
0.8347 | 6.44 | 1900 | 1.8019 |
0.8379 | 6.77 | 2000 | 1.8006 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3