|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
model-index: |
|
- name: donut-base-sroie |
|
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. --> |
|
|
|
# donut-base-sroie |
|
|
|
This model was trained from scratch on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 5.7016 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 25 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 9.5672 | 1.0 | 3 | 8.6900 | |
|
| 9.2165 | 2.0 | 6 | 8.1679 | |
|
| 8.6254 | 3.0 | 9 | 8.8826 | |
|
| 8.5961 | 4.0 | 12 | 7.9094 | |
|
| 8.0975 | 5.0 | 15 | 7.6390 | |
|
| 8.0688 | 6.0 | 18 | 7.3710 | |
|
| 7.8179 | 7.0 | 21 | 7.1756 | |
|
| 7.4056 | 8.0 | 24 | 7.1199 | |
|
| 7.2254 | 9.0 | 27 | 6.8964 | |
|
| 7.1395 | 10.0 | 30 | 6.8406 | |
|
| 7.2451 | 11.0 | 33 | 6.5694 | |
|
| 6.8052 | 12.0 | 36 | 6.7802 | |
|
| 6.8587 | 13.0 | 39 | 6.3983 | |
|
| 6.6803 | 14.0 | 42 | 6.3614 | |
|
| 6.5832 | 15.0 | 45 | 6.2045 | |
|
| 6.3016 | 16.0 | 48 | 6.3187 | |
|
| 6.3266 | 17.0 | 51 | 6.1394 | |
|
| 6.2154 | 18.0 | 54 | 5.9751 | |
|
| 6.0545 | 19.0 | 57 | 5.9170 | |
|
| 6.0753 | 20.0 | 60 | 5.9828 | |
|
| 6.0034 | 21.0 | 63 | 5.9600 | |
|
| 6.0545 | 22.0 | 66 | 5.8052 | |
|
| 5.8055 | 23.0 | 69 | 5.7358 | |
|
| 5.7705 | 24.0 | 72 | 5.6998 | |
|
| 5.8007 | 25.0 | 75 | 5.7016 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|