|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: peft-finetune-flan-t5-mc-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 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# peft-finetune-flan-t5-mc-question-generation |
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1306 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.2907 | 0.13 | 100 | 1.7315 | |
|
| 1.8012 | 0.25 | 200 | 1.3366 | |
|
| 1.5077 | 0.38 | 300 | 1.2346 | |
|
| 1.419 | 0.51 | 400 | 1.2027 | |
|
| 1.3772 | 0.64 | 500 | 1.1884 | |
|
| 1.3566 | 0.76 | 600 | 1.1770 | |
|
| 1.3348 | 0.89 | 700 | 1.1696 | |
|
| 1.3307 | 1.02 | 800 | 1.1624 | |
|
| 1.3247 | 1.15 | 900 | 1.1586 | |
|
| 1.3139 | 1.27 | 1000 | 1.1537 | |
|
| 1.3048 | 1.4 | 1100 | 1.1507 | |
|
| 1.3045 | 1.53 | 1200 | 1.1476 | |
|
| 1.2999 | 1.65 | 1300 | 1.1451 | |
|
| 1.2978 | 1.78 | 1400 | 1.1425 | |
|
| 1.2903 | 1.91 | 1500 | 1.1407 | |
|
| 1.2897 | 2.04 | 1600 | 1.1409 | |
|
| 1.2881 | 2.16 | 1700 | 1.1386 | |
|
| 1.2845 | 2.29 | 1800 | 1.1374 | |
|
| 1.2749 | 2.42 | 1900 | 1.1360 | |
|
| 1.2846 | 2.55 | 2000 | 1.1349 | |
|
| 1.281 | 2.67 | 2100 | 1.1339 | |
|
| 1.282 | 2.8 | 2200 | 1.1331 | |
|
| 1.2786 | 2.93 | 2300 | 1.1326 | |
|
| 1.2799 | 3.06 | 2400 | 1.1322 | |
|
| 1.2777 | 3.18 | 2500 | 1.1320 | |
|
| 1.2767 | 3.31 | 2600 | 1.1316 | |
|
| 1.2716 | 3.44 | 2700 | 1.1313 | |
|
| 1.2762 | 3.56 | 2800 | 1.1309 | |
|
| 1.2723 | 3.69 | 2900 | 1.1305 | |
|
| 1.2741 | 3.82 | 3000 | 1.1304 | |
|
| 1.2762 | 3.95 | 3100 | 1.1306 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.3 |
|
|
