metadata
license: apache-2.0
base_model: google/flan-t5-small
tags:
- generated_from_trainer
model-index:
- name: flan-t5-mc-question-generation
results: []
inference:
parameters:
max_length: 512
num_beams: 4
length_penalty: 1.5
no_repeat_ngram_size: 3
early_stopping: true
flan-t5-mc-question-generation
This model is a fine-tuned version of google/flan-t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2509
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: 5e-05
- 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 |
|---|---|---|---|
| 1.9047 | 0.25 | 100 | 1.4246 |
| 1.5894 | 0.51 | 200 | 1.3711 |
| 1.5355 | 0.76 | 300 | 1.3450 |
| 1.5041 | 1.02 | 400 | 1.3255 |
| 1.4858 | 1.27 | 500 | 1.3134 |
| 1.4711 | 1.53 | 600 | 1.3038 |
| 1.4576 | 1.78 | 700 | 1.2951 |
| 1.4466 | 2.04 | 800 | 1.2888 |
| 1.4405 | 2.29 | 900 | 1.2836 |
| 1.4284 | 2.55 | 1000 | 1.2794 |
| 1.4228 | 2.8 | 1100 | 1.2758 |
| 1.4234 | 3.06 | 1200 | 1.2719 |
| 1.4104 | 3.31 | 1300 | 1.2690 |
| 1.4147 | 3.56 | 1400 | 1.2666 |
| 1.41 | 3.82 | 1500 | 1.2637 |
| 1.3996 | 4.07 | 1600 | 1.2622 |
| 1.4015 | 4.33 | 1700 | 1.2600 |
| 1.3958 | 4.58 | 1800 | 1.2583 |
| 1.395 | 4.84 | 1900 | 1.2566 |
| 1.3899 | 5.09 | 2000 | 1.2553 |
| 1.3929 | 5.35 | 2100 | 1.2542 |
| 1.3884 | 5.6 | 2200 | 1.2529 |
| 1.3884 | 5.86 | 2300 | 1.2523 |
| 1.3821 | 6.11 | 2400 | 1.2520 |
| 1.3886 | 6.37 | 2500 | 1.2513 |
| 1.3865 | 6.62 | 2600 | 1.2510 |
| 1.3841 | 6.87 | 2700 | 1.2509 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3