|
--- |
|
license: apache-2.0 |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
base_model: google/vit-base-patch16-224-in21k |
|
model-index: |
|
- name: vit-base-clothing-leafs-example-full-simple_highres |
|
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-clothing-leafs-example-full-simple_highres |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9880 |
|
- Accuracy: 0.7166 |
|
|
|
## 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: 2.5e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 2.0202 | 0.14 | 1000 | 1.4969 | 0.6338 | |
|
| 1.3694 | 0.28 | 2000 | 1.2786 | 0.6647 | |
|
| 1.2063 | 0.42 | 3000 | 1.1788 | 0.6794 | |
|
| 1.1544 | 0.56 | 4000 | 1.1320 | 0.6856 | |
|
| 1.1089 | 0.7 | 5000 | 1.1021 | 0.6867 | |
|
| 1.0681 | 0.84 | 6000 | 1.0775 | 0.6935 | |
|
| 1.0483 | 0.98 | 7000 | 1.0461 | 0.7006 | |
|
| 0.9591 | 1.12 | 8000 | 1.0398 | 0.7022 | |
|
| 0.9541 | 1.26 | 9000 | 1.0423 | 0.6981 | |
|
| 0.9382 | 1.4 | 10000 | 1.0322 | 0.7014 | |
|
| 0.9363 | 1.54 | 11000 | 1.0301 | 0.7020 | |
|
| 0.9199 | 1.68 | 12000 | 1.0079 | 0.7106 | |
|
| 0.919 | 1.82 | 13000 | 0.9972 | 0.7120 | |
|
| 0.9203 | 1.96 | 14000 | 1.0011 | 0.7096 | |
|
| 0.8377 | 2.1 | 15000 | 0.9912 | 0.7146 | |
|
| 0.8148 | 2.24 | 16000 | 0.9991 | 0.7121 | |
|
| 0.8153 | 2.38 | 17000 | 1.0070 | 0.7102 | |
|
| 0.8004 | 2.52 | 18000 | 0.9979 | 0.7154 | |
|
| 0.7937 | 2.66 | 19000 | 1.0022 | 0.7136 | |
|
| 0.7989 | 2.8 | 20000 | 0.9880 | 0.7166 | |
|
| 0.7953 | 2.94 | 21000 | 0.9907 | 0.7175 | |
|
| 0.7576 | 3.08 | 22000 | 1.0013 | 0.7136 | |
|
| 0.7018 | 3.22 | 23000 | 1.0022 | 0.7156 | |
|
| 0.7127 | 3.36 | 24000 | 1.0080 | 0.7151 | |
|
| 0.6989 | 3.5 | 25000 | 1.0025 | 0.7159 | |
|
| 0.702 | 3.64 | 26000 | 1.0087 | 0.7167 | |
|
| 0.7122 | 3.78 | 27000 | 1.0042 | 0.7159 | |
|
| 0.6986 | 3.92 | 28000 | 1.0017 | 0.7164 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
