|
--- |
|
language: |
|
- eng |
|
license: apache-2.0 |
|
base_model: facebook/dinov2-large |
|
tags: |
|
- multilabel-image-classification |
|
- multilabel |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: dino-large-2023_12_19-kornia_img-size518_batch-size16_epochs20 |
|
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. --> |
|
|
|
# dino-large-2023_12_19-kornia_img-size518_batch-size16_epochs20 |
|
|
|
This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on the multilabel_complete_dataset dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1199 |
|
- F1 Micro: 0.8367 |
|
- F1 Macro: 0.8026 |
|
- Roc Auc: 0.9072 |
|
- Accuracy: 0.5354 |
|
- Learning Rate: 0.001 |
|
|
|
## 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: 0.01 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Roc Auc | Accuracy | Rate | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-------:|:--------:|:-----:| |
|
| 0.2545 | 1.0 | 536 | 0.1936 | 0.7016 | 0.5553 | 0.7908 | 0.4134 | 0.01 | |
|
| 0.2163 | 2.0 | 1072 | 0.1644 | 0.7672 | 0.6940 | 0.8669 | 0.4241 | 0.01 | |
|
| 0.2142 | 3.0 | 1608 | 0.1720 | 0.7264 | 0.6226 | 0.8210 | 0.4259 | 0.01 | |
|
| 0.2107 | 4.0 | 2144 | 0.1779 | 0.7311 | 0.6056 | 0.8442 | 0.4019 | 0.01 | |
|
| 0.2117 | 5.0 | 2680 | 0.1835 | 0.7542 | 0.6745 | 0.8724 | 0.3834 | 0.01 | |
|
| 0.2171 | 6.0 | 3216 | 0.1732 | 0.7347 | 0.5959 | 0.8236 | 0.4209 | 0.01 | |
|
| 0.2178 | 7.0 | 3752 | 0.2698 | 0.7253 | 0.5932 | 0.8165 | 0.3905 | 0.01 | |
|
| 0.2177 | 8.0 | 4288 | 0.1940 | 0.7360 | 0.6280 | 0.8286 | 0.4119 | 0.01 | |
|
| 0.212 | 9.0 | 4824 | 0.1455 | 0.7993 | 0.7491 | 0.8757 | 0.4898 | 0.001 | |
|
| 0.1761 | 10.0 | 5360 | 0.1357 | 0.8116 | 0.7661 | 0.8733 | 0.5123 | 0.001 | |
|
| 0.1681 | 11.0 | 5896 | 0.1386 | 0.8152 | 0.7753 | 0.8791 | 0.5166 | 0.001 | |
|
| 0.1579 | 12.0 | 6432 | 0.1820 | 0.8220 | 0.7827 | 0.8919 | 0.5163 | 0.001 | |
|
| 0.1553 | 13.0 | 6968 | 0.1228 | 0.8297 | 0.7908 | 0.8898 | 0.5327 | 0.001 | |
|
| 0.1512 | 14.0 | 7504 | 0.1233 | 0.8258 | 0.7815 | 0.8845 | 0.5302 | 0.001 | |
|
| 0.1508 | 15.0 | 8040 | 0.1248 | 0.8179 | 0.7682 | 0.8740 | 0.5305 | 0.001 | |
|
| 0.1499 | 16.0 | 8576 | 0.1193 | 0.8277 | 0.7903 | 0.8806 | 0.5395 | 0.001 | |
|
| 0.1435 | 17.0 | 9112 | 0.1159 | 0.8381 | 0.7996 | 0.9037 | 0.5380 | 0.001 | |
|
| 0.1463 | 18.0 | 9648 | 0.1166 | 0.8393 | 0.8033 | 0.8957 | 0.5481 | 0.001 | |
|
| 0.1423 | 19.0 | 10184 | 0.1216 | 0.8327 | 0.8009 | 0.8865 | 0.5459 | 0.001 | |
|
| 0.1444 | 20.0 | 10720 | 0.1171 | 0.8383 | 0.8020 | 0.8908 | 0.5509 | 0.001 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
