metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad_modified_for_t5_qg
model-index:
- name: t5-end2end-questions-generation
results: []
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: 1.5665
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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5889 | 0.34 | 100 | 1.9101 |
| 1.9627 | 0.68 | 200 | 1.7224 |
| 1.8415 | 1.02 | 300 | 1.6637 |
| 1.7416 | 1.35 | 400 | 1.6346 |
| 1.712 | 1.69 | 500 | 1.6162 |
| 1.6879 | 2.03 | 600 | 1.6081 |
| 1.6291 | 2.37 | 700 | 1.5917 |
| 1.6246 | 2.71 | 800 | 1.5865 |
| 1.6081 | 3.05 | 900 | 1.5860 |
| 1.5659 | 3.39 | 1000 | 1.5815 |
| 1.5612 | 3.73 | 1100 | 1.5665 |
| 1.5452 | 4.06 | 1200 | 1.5770 |
| 1.5264 | 4.4 | 1300 | 1.5809 |
| 1.5154 | 4.74 | 1400 | 1.5650 |
| 1.5079 | 5.08 | 1500 | 1.5733 |
| 1.484 | 5.42 | 1600 | 1.5690 |
| 1.4708 | 5.76 | 1700 | 1.5707 |
| 1.4857 | 6.1 | 1800 | 1.5645 |
| 1.4568 | 6.44 | 1900 | 1.5677 |
| 1.4597 | 6.77 | 2000 | 1.5643 |
| 1.4666 | 7.11 | 2100 | 1.5670 |
| 1.4495 | 7.45 | 2200 | 1.5620 |
| 1.4387 | 7.79 | 2300 | 1.5665 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3