|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- image-classification |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: vit-base-clothing-leafs-example-full-simple |
|
|
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 |
|
|
|
|
|
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: 0.9954 |
|
|
- Accuracy: 0.7155 |
|
|
|
|
|
## 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: 3e-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 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
|
| 1.9495 | 0.14 | 1000 | 1.4553 | 0.6307 | |
|
|
| 1.3079 | 0.28 | 2000 | 1.2347 | 0.6677 | |
|
|
| 1.178 | 0.41 | 3000 | 1.1607 | 0.6758 | |
|
|
| 1.1324 | 0.55 | 4000 | 1.1307 | 0.6824 | |
|
|
| 1.0928 | 0.69 | 5000 | 1.0956 | 0.6909 | |
|
|
| 1.0679 | 0.83 | 6000 | 1.0790 | 0.6912 | |
|
|
| 1.0488 | 0.97 | 7000 | 1.0486 | 0.7014 | |
|
|
| 0.9548 | 1.11 | 8000 | 1.0449 | 0.7016 | |
|
|
| 0.9352 | 1.24 | 9000 | 1.0348 | 0.7042 | |
|
|
| 0.9164 | 1.38 | 10000 | 1.0340 | 0.7034 | |
|
|
| 0.9267 | 1.52 | 11000 | 1.0178 | 0.7089 | |
|
|
| 0.9058 | 1.66 | 12000 | 1.0160 | 0.7063 | |
|
|
| 0.9028 | 1.8 | 13000 | 1.0084 | 0.7111 | |
|
|
| 0.9093 | 1.94 | 14000 | 1.0009 | 0.7136 | |
|
|
| 0.8346 | 2.07 | 15000 | 1.0152 | 0.7117 | |
|
|
| 0.7897 | 2.21 | 16000 | 1.0072 | 0.7141 | |
|
|
| 0.7869 | 2.35 | 17000 | 1.0088 | 0.7083 | |
|
|
| 0.7853 | 2.49 | 18000 | 0.9981 | 0.7162 | |
|
|
| 0.7732 | 2.63 | 19000 | 1.0030 | 0.7149 | |
|
|
| 0.779 | 2.77 | 20000 | 0.9954 | 0.7155 | |
|
|
| 0.7655 | 2.9 | 21000 | 0.9972 | 0.7179 | |
|
|
| 0.74 | 3.04 | 22000 | 1.0114 | 0.7138 | |
|
|
| 0.6824 | 3.18 | 23000 | 1.0171 | 0.7130 | |
|
|
| 0.68 | 3.32 | 24000 | 1.0111 | 0.7178 | |
|
|
| 0.6787 | 3.46 | 25000 | 1.0124 | 0.7151 | |
|
|
| 0.6808 | 3.6 | 26000 | 1.0181 | 0.7150 | |
|
|
| 0.6561 | 3.73 | 27000 | 1.0144 | 0.7168 | |
|
|
| 0.6611 | 3.87 | 28000 | 1.0154 | 0.7155 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.29.2 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
