|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: rmsprop_VitB-p16-224-2e-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: 0.9597701149425287 |
|
--- |
|
|
|
<!-- 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-p16-224-2e-4-batch_16_epoch_4_classes_24 |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2491 |
|
- Accuracy: 0.9598 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 3.235 | 0.07 | 100 | 3.3086 | 0.0445 | |
|
| 2.3747 | 0.14 | 200 | 2.8722 | 0.1825 | |
|
| 0.4827 | 0.21 | 300 | 0.5081 | 0.8491 | |
|
| 0.2845 | 0.28 | 400 | 0.6097 | 0.8218 | |
|
| 0.1748 | 0.35 | 500 | 0.3931 | 0.8980 | |
|
| 0.0725 | 0.42 | 600 | 0.4109 | 0.9009 | |
|
| 0.1573 | 0.49 | 700 | 0.3453 | 0.9138 | |
|
| 0.1495 | 0.56 | 800 | 0.3197 | 0.9152 | |
|
| 0.1026 | 0.63 | 900 | 0.3218 | 0.9181 | |
|
| 0.1645 | 0.7 | 1000 | 0.2377 | 0.9296 | |
|
| 0.1471 | 0.77 | 1100 | 0.2831 | 0.9138 | |
|
| 0.0889 | 0.84 | 1200 | 0.1498 | 0.9598 | |
|
| 0.1578 | 0.91 | 1300 | 0.2784 | 0.9325 | |
|
| 0.0856 | 0.97 | 1400 | 0.2652 | 0.9454 | |
|
| 0.0248 | 1.04 | 1500 | 0.2398 | 0.9440 | |
|
| 0.0027 | 1.11 | 1600 | 0.2065 | 0.9583 | |
|
| 0.0109 | 1.18 | 1700 | 0.3166 | 0.9325 | |
|
| 0.0072 | 1.25 | 1800 | 0.3091 | 0.9368 | |
|
| 0.0708 | 1.32 | 1900 | 0.3574 | 0.9267 | |
|
| 0.1434 | 1.39 | 2000 | 0.3906 | 0.9282 | |
|
| 0.0038 | 1.46 | 2100 | 0.3159 | 0.9325 | |
|
| 0.0588 | 1.53 | 2200 | 0.2547 | 0.9511 | |
|
| 0.0009 | 1.6 | 2300 | 0.2685 | 0.9411 | |
|
| 0.0488 | 1.67 | 2400 | 0.6258 | 0.8966 | |
|
| 0.0079 | 1.74 | 2500 | 0.3972 | 0.9282 | |
|
| 0.1493 | 1.81 | 2600 | 0.2655 | 0.9598 | |
|
| 0.042 | 1.88 | 2700 | 0.2861 | 0.9468 | |
|
| 0.0275 | 1.95 | 2800 | 0.3714 | 0.9382 | |
|
| 0.0404 | 2.02 | 2900 | 0.3931 | 0.9325 | |
|
| 0.0002 | 2.09 | 3000 | 0.3090 | 0.9454 | |
|
| 0.0141 | 2.16 | 3100 | 0.4250 | 0.9195 | |
|
| 0.0067 | 2.23 | 3200 | 0.2866 | 0.9497 | |
|
| 0.0003 | 2.3 | 3300 | 0.2893 | 0.9526 | |
|
| 0.0254 | 2.37 | 3400 | 0.3169 | 0.9483 | |
|
| 0.0003 | 2.44 | 3500 | 0.2359 | 0.9526 | |
|
| 0.0001 | 2.51 | 3600 | 0.2565 | 0.9540 | |
|
| 0.001 | 2.58 | 3700 | 0.3259 | 0.9468 | |
|
| 0.0005 | 2.65 | 3800 | 0.2131 | 0.9598 | |
|
| 0.0013 | 2.72 | 3900 | 0.2858 | 0.9526 | |
|
| 0.0014 | 2.79 | 4000 | 0.2378 | 0.9598 | |
|
| 0.0076 | 2.86 | 4100 | 0.2497 | 0.9598 | |
|
| 0.0244 | 2.92 | 4200 | 0.2342 | 0.9583 | |
|
| 0.0002 | 2.99 | 4300 | 0.2881 | 0.9598 | |
|
| 0.0 | 3.06 | 4400 | 0.2758 | 0.9555 | |
|
| 0.0011 | 3.13 | 4500 | 0.2810 | 0.9555 | |
|
| 0.0007 | 3.2 | 4600 | 0.2978 | 0.9598 | |
|
| 0.0 | 3.27 | 4700 | 0.2581 | 0.9626 | |
|
| 0.0 | 3.34 | 4800 | 0.2640 | 0.9641 | |
|
| 0.0 | 3.41 | 4900 | 0.2531 | 0.9598 | |
|
| 0.013 | 3.48 | 5000 | 0.2582 | 0.9626 | |
|
| 0.0004 | 3.55 | 5100 | 0.2815 | 0.9598 | |
|
| 0.0 | 3.62 | 5200 | 0.2768 | 0.9598 | |
|
| 0.0 | 3.69 | 5300 | 0.2803 | 0.9612 | |
|
| 0.0 | 3.76 | 5400 | 0.2619 | 0.9612 | |
|
| 0.0 | 3.83 | 5500 | 0.2594 | 0.9612 | |
|
| 0.0204 | 3.9 | 5600 | 0.2473 | 0.9612 | |
|
| 0.0 | 3.97 | 5700 | 0.2491 | 0.9598 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|