|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: jordyvl/vit-base_rvl-cdip |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: vit-base_rvl_cdip_ce |
|
|
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. --> |
|
|
|
|
|
# vit-base_rvl_cdip_ce |
|
|
|
|
|
This model is a fine-tuned version of [jordyvl/vit-base_rvl-cdip](https://huggingface.co/jordyvl/vit-base_rvl-cdip) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.5626 |
|
|
- Accuracy: 0.8932 |
|
|
- Brier Loss: 0.1854 |
|
|
- Nll: 0.8898 |
|
|
- F1 Micro: 0.8932 |
|
|
- F1 Macro: 0.8934 |
|
|
- Ece: 0.0831 |
|
|
- Aurc: 0.0199 |
|
|
|
|
|
## 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: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 32 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| |
|
|
| 0.1771 | 1.0 | 500 | 0.4123 | 0.887 | 0.1720 | 1.2003 | 0.887 | 0.8872 | 0.0534 | 0.0204 | |
|
|
| 0.1349 | 2.0 | 1000 | 0.4344 | 0.8895 | 0.1754 | 1.1219 | 0.8895 | 0.8900 | 0.0614 | 0.0207 | |
|
|
| 0.0656 | 3.0 | 1500 | 0.4602 | 0.8852 | 0.1836 | 1.0477 | 0.8852 | 0.8856 | 0.0734 | 0.0197 | |
|
|
| 0.0314 | 4.0 | 2000 | 0.5044 | 0.889 | 0.1851 | 1.0124 | 0.889 | 0.8888 | 0.0729 | 0.0230 | |
|
|
| 0.0134 | 5.0 | 2500 | 0.5193 | 0.8895 | 0.1861 | 0.9779 | 0.8895 | 0.8905 | 0.0803 | 0.0207 | |
|
|
| 0.0075 | 6.0 | 3000 | 0.5300 | 0.8915 | 0.1848 | 0.9515 | 0.8915 | 0.8922 | 0.0793 | 0.0203 | |
|
|
| 0.0057 | 7.0 | 3500 | 0.5552 | 0.89 | 0.1893 | 0.9200 | 0.89 | 0.8897 | 0.0852 | 0.0205 | |
|
|
| 0.0047 | 8.0 | 4000 | 0.5589 | 0.892 | 0.1871 | 0.9245 | 0.892 | 0.8923 | 0.0826 | 0.0198 | |
|
|
| 0.0046 | 9.0 | 4500 | 0.5620 | 0.8935 | 0.1854 | 0.8987 | 0.8935 | 0.8937 | 0.0828 | 0.0199 | |
|
|
| 0.0042 | 10.0 | 5000 | 0.5626 | 0.8932 | 0.1854 | 0.8898 | 0.8932 | 0.8934 | 0.0831 | 0.0199 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.2.0.dev20231002 |
|
|
- Datasets 2.7.1 |
|
|
- Tokenizers 0.13.3 |
|
|
|
