metadata
license: apache-2.0
base_model: google/vit-large-patch16-224-in21k
tags:
- image-classification
- vision
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: fashion-images-pack-types-vit-large-patch16-224-in21k-v3
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: touchtech/fashion-images-pack-types
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9908103592314118
fashion-images-pack-types-vit-large-patch16-224-in21k-v3
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on the touchtech/fashion-images-pack-types dataset. It achieves the following results on the evaluation set:
- Loss: 0.0485
- Accuracy: 0.9908
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 |
|---|---|---|---|---|
| 0.1662 | 1.0 | 1696 | 0.9737 | 0.1074 |
| 0.116 | 2.0 | 3392 | 0.9816 | 0.0545 |
| 0.091 | 3.0 | 5088 | 0.9850 | 0.0647 |
| 0.0601 | 4.0 | 6784 | 0.0502 | 0.9887 |
| 0.0438 | 5.0 | 8480 | 0.0485 | 0.9908 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3