metadata
license: apache-2.0
base_model: google/flan-t5-large
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: flan-t5-large_question_answering_finetuining
results: []
flan-t5-large_question_answering_finetuining
This model is a fine-tuned version of google/flan-t5-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6768
- Rouge1: 16.22
- Rouge2: 9.65
- Rougel: 15.62
- Rougelsum: 15.75
- R: 13.82
- Gen Len: 30.3456
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | R | Gen Len |
|---|---|---|---|---|---|---|---|---|---|
| 10.4307 | 1.0 | 79 | 0.5836 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 0.4454 | 2.0 | 158 | 0.4834 | 4.07 | 0.61 | 4.18 | 4.15 | 2.95 | 13.7574 |
| 0.3152 | 3.0 | 237 | 0.4520 | 7.89 | 2.42 | 7.49 | 7.53 | 5.93 | 27.9044 |
| 0.2321 | 4.0 | 316 | 0.4634 | 7.5 | 3.24 | 7.41 | 7.39 | 6.05 | 20.0588 |
| 0.1775 | 5.0 | 395 | 0.4656 | 12.1 | 5.52 | 11.98 | 11.81 | 9.86 | 21.1176 |
| 0.1299 | 6.0 | 474 | 0.4958 | 15.28 | 8.79 | 14.71 | 14.68 | 12.92 | 22.9044 |
| 0.096 | 7.0 | 553 | 0.5332 | 15.42 | 9.23 | 14.84 | 14.94 | 13.15 | 28.3382 |
| 0.0685 | 8.0 | 632 | 0.6132 | 15.45 | 9.76 | 15.07 | 14.99 | 13.42 | 26.4559 |
| 0.0542 | 9.0 | 711 | 0.6218 | 17.08 | 11.34 | 16.54 | 16.67 | 14.98 | 28.2353 |
| 0.0442 | 10.0 | 790 | 0.6768 | 16.22 | 9.65 | 15.62 | 15.75 | 13.82 | 30.3456 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.2