|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: t5-end2end-questions-generation_2 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# t5-end2end-questions-generation_2 |
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6223 |
|
|
|
## 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: 0.0001 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.7103 | 0.13 | 10 | 1.7584 | |
|
| 1.8298 | 0.26 | 20 | 1.3377 | |
|
| 1.4424 | 0.39 | 30 | 1.1610 | |
|
| 1.4063 | 0.52 | 40 | 1.0564 | |
|
| 1.2738 | 0.65 | 50 | 1.0332 | |
|
| 1.2477 | 0.78 | 60 | 0.9531 | |
|
| 1.146 | 0.91 | 70 | 0.9050 | |
|
| 1.0134 | 1.04 | 80 | 0.9388 | |
|
| 0.8782 | 1.17 | 90 | 0.9215 | |
|
| 0.8869 | 1.3 | 100 | 0.8930 | |
|
| 0.8963 | 1.43 | 110 | 0.8996 | |
|
| 0.9138 | 1.56 | 120 | 0.8616 | |
|
| 0.7963 | 1.69 | 130 | 0.8060 | |
|
| 0.8611 | 1.82 | 140 | 0.7611 | |
|
| 1.0504 | 1.95 | 150 | 0.7606 | |
|
| 0.6802 | 2.08 | 160 | 0.7791 | |
|
| 0.7488 | 2.21 | 170 | 0.7470 | |
|
| 0.6659 | 2.34 | 180 | 0.7367 | |
|
| 0.7061 | 2.47 | 190 | 0.7194 | |
|
| 0.6771 | 2.6 | 200 | 0.7006 | |
|
| 0.7267 | 2.73 | 210 | 0.6858 | |
|
| 0.7251 | 2.86 | 220 | 0.6797 | |
|
| 0.7426 | 2.99 | 230 | 0.6877 | |
|
| 0.5425 | 3.12 | 240 | 0.6994 | |
|
| 0.5298 | 3.25 | 250 | 0.7096 | |
|
| 0.697 | 3.38 | 260 | 0.6941 | |
|
| 0.5643 | 3.51 | 270 | 0.6534 | |
|
| 0.6983 | 3.64 | 280 | 0.6407 | |
|
| 0.587 | 3.77 | 290 | 0.6404 | |
|
| 0.6487 | 3.9 | 300 | 0.6489 | |
|
| 0.5862 | 4.03 | 310 | 0.6567 | |
|
| 0.5524 | 4.16 | 320 | 0.6610 | |
|
| 0.5432 | 4.29 | 330 | 0.6609 | |
|
| 0.5165 | 4.42 | 340 | 0.6558 | |
|
| 0.5248 | 4.55 | 350 | 0.6387 | |
|
| 0.5322 | 4.68 | 360 | 0.6319 | |
|
| 0.5272 | 4.81 | 370 | 0.6214 | |
|
| 0.5555 | 4.94 | 380 | 0.6252 | |
|
| 0.597 | 5.06 | 390 | 0.6281 | |
|
| 0.5745 | 5.19 | 400 | 0.6283 | |
|
| 0.5156 | 5.32 | 410 | 0.6265 | |
|
| 0.4898 | 5.45 | 420 | 0.6307 | |
|
| 0.543 | 5.58 | 430 | 0.6280 | |
|
| 0.5094 | 5.71 | 440 | 0.6295 | |
|
| 0.5023 | 5.84 | 450 | 0.6279 | |
|
| 0.4483 | 5.97 | 460 | 0.6228 | |
|
| 0.5134 | 6.1 | 470 | 0.6239 | |
|
| 0.5054 | 6.23 | 480 | 0.6230 | |
|
| 0.4632 | 6.36 | 490 | 0.6205 | |
|
| 0.5016 | 6.49 | 500 | 0.6212 | |
|
| 0.4838 | 6.62 | 510 | 0.6219 | |
|
| 0.4613 | 6.75 | 520 | 0.6225 | |
|
| 0.5062 | 6.88 | 530 | 0.6223 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|