metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- vision
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-mgas
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: ./mgr/dataset/HF_DS
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7322834645669292
vit-base-mgas
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the ./mgr/dataset/HF_DS dataset. It achieves the following results on the evaluation set:
- Loss: 0.8530
- Accuracy: 0.7323
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 1.4331 | 1.0 | 143 | 0.4803 | 1.3804 |
| 1.1653 | 2.0 | 286 | 0.6850 | 1.0843 |
| 1.0919 | 3.0 | 429 | 0.7165 | 0.9539 |
| 0.9689 | 4.0 | 572 | 0.7323 | 0.8724 |
| 0.9175 | 5.0 | 715 | 0.8530 | 0.7323 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.15.0
- Tokenizers 0.15.0