metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: flan-t5-end2end-question-generation
results: []
pipeline_tag: text2text-generation
inference:
parameters:
max_length: 256
num_beams: 4
length_penalty: 1.5
no_repeat_ngram_size: 3
early_stopping: true
flan-t5-end2end-question-generation
This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5506
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- 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 |
|---|---|---|---|
| 2.6246 | 0.34 | 100 | 1.8376 |
| 1.9742 | 0.68 | 200 | 1.7341 |
| 1.8778 | 1.02 | 300 | 1.6817 |
| 1.8245 | 1.35 | 400 | 1.6455 |
| 1.7808 | 1.69 | 500 | 1.6298 |
| 1.754 | 2.03 | 600 | 1.6213 |
| 1.7226 | 2.37 | 700 | 1.6102 |
| 1.7078 | 2.71 | 800 | 1.5914 |
| 1.6953 | 3.05 | 900 | 1.5871 |
| 1.682 | 3.39 | 1000 | 1.5857 |
| 1.6593 | 3.73 | 1100 | 1.5742 |
| 1.6538 | 4.06 | 1200 | 1.5675 |
| 1.6417 | 4.4 | 1300 | 1.5682 |
| 1.6274 | 4.74 | 1400 | 1.5571 |
| 1.6375 | 5.08 | 1500 | 1.5566 |
| 1.6217 | 5.42 | 1600 | 1.5564 |
| 1.625 | 5.76 | 1700 | 1.5543 |
| 1.6055 | 6.1 | 1800 | 1.5517 |
| 1.6129 | 6.44 | 1900 | 1.5516 |
| 1.609 | 6.77 | 2000 | 1.5506 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2