|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch32-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: rmsProp_ViTB-32-224-in21k-2e-4-batch_16_epoch_4_classes_24 |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: train |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9367816091954023 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# rmsProp_ViTB-32-224-in21k-2e-4-batch_16_epoch_4_classes_24 |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch32-224-in21k](https://huggingface.co/google/vit-base-patch32-224-in21k) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3224 |
|
- Accuracy: 0.9368 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 2.7852 | 0.07 | 100 | 2.7614 | 0.1494 | |
|
| 1.9058 | 0.14 | 200 | 1.8155 | 0.4813 | |
|
| 1.1158 | 0.21 | 300 | 1.0835 | 0.7328 | |
|
| 0.8073 | 0.28 | 400 | 0.7663 | 0.7931 | |
|
| 0.4979 | 0.35 | 500 | 0.5854 | 0.8376 | |
|
| 0.3927 | 0.42 | 600 | 0.3968 | 0.8865 | |
|
| 0.3211 | 0.49 | 700 | 0.4845 | 0.8621 | |
|
| 0.2881 | 0.56 | 800 | 0.3788 | 0.8865 | |
|
| 0.233 | 0.63 | 900 | 0.4301 | 0.8649 | |
|
| 0.2446 | 0.7 | 1000 | 0.3978 | 0.8836 | |
|
| 0.351 | 0.77 | 1100 | 0.4557 | 0.8649 | |
|
| 0.1268 | 0.84 | 1200 | 0.3445 | 0.8908 | |
|
| 0.1973 | 0.91 | 1300 | 0.5640 | 0.8477 | |
|
| 0.1321 | 0.97 | 1400 | 0.4515 | 0.8793 | |
|
| 0.0914 | 1.04 | 1500 | 0.3113 | 0.9109 | |
|
| 0.1177 | 1.11 | 1600 | 0.4890 | 0.8664 | |
|
| 0.0532 | 1.18 | 1700 | 0.4442 | 0.8836 | |
|
| 0.1037 | 1.25 | 1800 | 0.3393 | 0.9210 | |
|
| 0.0857 | 1.32 | 1900 | 0.4536 | 0.8865 | |
|
| 0.1201 | 1.39 | 2000 | 0.4316 | 0.8937 | |
|
| 0.162 | 1.46 | 2100 | 0.3895 | 0.9023 | |
|
| 0.0761 | 1.53 | 2200 | 0.3556 | 0.9239 | |
|
| 0.054 | 1.6 | 2300 | 0.3811 | 0.9052 | |
|
| 0.1666 | 1.67 | 2400 | 0.3660 | 0.9195 | |
|
| 0.1038 | 1.74 | 2500 | 0.4206 | 0.9066 | |
|
| 0.068 | 1.81 | 2600 | 0.4614 | 0.8980 | |
|
| 0.0452 | 1.88 | 2700 | 0.4233 | 0.9037 | |
|
| 0.0395 | 1.95 | 2800 | 0.4487 | 0.8994 | |
|
| 0.0064 | 2.02 | 2900 | 0.4042 | 0.9124 | |
|
| 0.006 | 2.09 | 3000 | 0.3274 | 0.9095 | |
|
| 0.0153 | 2.16 | 3100 | 0.4322 | 0.8951 | |
|
| 0.0674 | 2.23 | 3200 | 0.3815 | 0.9052 | |
|
| 0.052 | 2.3 | 3300 | 0.5513 | 0.8966 | |
|
| 0.0058 | 2.37 | 3400 | 0.4124 | 0.9181 | |
|
| 0.0331 | 2.44 | 3500 | 0.2915 | 0.9339 | |
|
| 0.0014 | 2.51 | 3600 | 0.3652 | 0.9224 | |
|
| 0.0485 | 2.58 | 3700 | 0.3655 | 0.9181 | |
|
| 0.0463 | 2.65 | 3800 | 0.4681 | 0.9066 | |
|
| 0.0008 | 2.72 | 3900 | 0.3798 | 0.9224 | |
|
| 0.0007 | 2.79 | 4000 | 0.3576 | 0.9239 | |
|
| 0.0008 | 2.86 | 4100 | 0.3683 | 0.9239 | |
|
| 0.0062 | 2.92 | 4200 | 0.3980 | 0.9210 | |
|
| 0.0009 | 2.99 | 4300 | 0.3483 | 0.9253 | |
|
| 0.0006 | 3.06 | 4400 | 0.3098 | 0.9382 | |
|
| 0.0003 | 3.13 | 4500 | 0.3137 | 0.9339 | |
|
| 0.0003 | 3.2 | 4600 | 0.3562 | 0.9325 | |
|
| 0.0692 | 3.27 | 4700 | 0.3462 | 0.9296 | |
|
| 0.0215 | 3.34 | 4800 | 0.3913 | 0.9239 | |
|
| 0.0549 | 3.41 | 4900 | 0.3144 | 0.9397 | |
|
| 0.0004 | 3.48 | 5000 | 0.3545 | 0.9368 | |
|
| 0.0008 | 3.55 | 5100 | 0.3295 | 0.9397 | |
|
| 0.0002 | 3.62 | 5200 | 0.3135 | 0.9382 | |
|
| 0.0004 | 3.69 | 5300 | 0.3249 | 0.9368 | |
|
| 0.0003 | 3.76 | 5400 | 0.3157 | 0.9353 | |
|
| 0.0002 | 3.83 | 5500 | 0.3242 | 0.9368 | |
|
| 0.0002 | 3.9 | 5600 | 0.3222 | 0.9353 | |
|
| 0.0002 | 3.97 | 5700 | 0.3224 | 0.9368 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
