|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: peft-flan-t5-mc-question-generation-eduqg |
|
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-flan-t5-mc-question-generation-eduqg |
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9867 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 4 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.548 | 0.15 | 100 | 1.9606 | |
|
| 2.0409 | 0.29 | 200 | 1.5282 | |
|
| 1.6969 | 0.44 | 300 | 1.2851 | |
|
| 1.4654 | 0.59 | 400 | 1.1794 | |
|
| 1.3643 | 0.73 | 500 | 1.1358 | |
|
| 1.3305 | 0.88 | 600 | 1.1068 | |
|
| 1.2952 | 1.03 | 700 | 1.0873 | |
|
| 1.211 | 1.17 | 800 | 1.0703 | |
|
| 1.2123 | 1.32 | 900 | 1.0590 | |
|
| 1.229 | 1.47 | 1000 | 1.0505 | |
|
| 1.2136 | 1.61 | 1100 | 1.0464 | |
|
| 1.1835 | 1.76 | 1200 | 1.0402 | |
|
| 1.217 | 1.91 | 1300 | 1.0319 | |
|
| 1.1986 | 2.05 | 1400 | 1.0300 | |
|
| 1.1586 | 2.2 | 1500 | 1.0257 | |
|
| 1.1634 | 2.35 | 1600 | 1.0214 | |
|
| 1.1661 | 2.49 | 1700 | 1.0170 | |
|
| 1.166 | 2.64 | 1800 | 1.0157 | |
|
| 1.1663 | 2.79 | 1900 | 1.0126 | |
|
| 1.1367 | 2.93 | 2000 | 1.0107 | |
|
| 1.1576 | 3.08 | 2100 | 1.0100 | |
|
| 1.1314 | 3.23 | 2200 | 1.0070 | |
|
| 1.1198 | 3.37 | 2300 | 1.0049 | |
|
| 1.1712 | 3.52 | 2400 | 1.0019 | |
|
| 1.1369 | 3.67 | 2500 | 1.0028 | |
|
| 1.1604 | 3.82 | 2600 | 1.0005 | |
|
| 1.1101 | 3.96 | 2700 | 0.9977 | |
|
| 1.1227 | 4.11 | 2800 | 0.9968 | |
|
| 1.1247 | 4.26 | 2900 | 0.9963 | |
|
| 1.1211 | 4.4 | 3000 | 0.9952 | |
|
| 1.1398 | 4.55 | 3100 | 0.9939 | |
|
| 1.1333 | 4.7 | 3200 | 0.9928 | |
|
| 1.1367 | 4.84 | 3300 | 0.9918 | |
|
| 1.1124 | 4.99 | 3400 | 0.9919 | |
|
| 1.1298 | 5.14 | 3500 | 0.9905 | |
|
| 1.117 | 5.28 | 3600 | 0.9904 | |
|
| 1.1237 | 5.43 | 3700 | 0.9886 | |
|
| 1.1016 | 5.58 | 3800 | 0.9889 | |
|
| 1.1492 | 5.72 | 3900 | 0.9887 | |
|
| 1.1032 | 5.87 | 4000 | 0.9882 | |
|
| 1.0838 | 6.02 | 4100 | 0.9879 | |
|
| 1.0807 | 6.16 | 4200 | 0.9880 | |
|
| 1.1062 | 6.31 | 4300 | 0.9879 | |
|
| 1.131 | 6.46 | 4400 | 0.9873 | |
|
| 1.1159 | 6.6 | 4500 | 0.9872 | |
|
| 1.1361 | 6.75 | 4600 | 0.9868 | |
|
| 1.1051 | 6.9 | 4700 | 0.9867 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.3 |
|
|
