metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit_epochs5_batch64_lr0.001_size224_tiles1_seed1_vit_old_transform_old_hp
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: Dogs_vs_Cats
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7538666666666667
vit_epochs5_batch64_lr0.001_size224_tiles1_seed1_vit_old_transform_old_hp
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the Dogs_vs_Cats dataset. It achieves the following results on the evaluation set:
- Loss: 0.5220
- Accuracy: 0.7539
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: 0.001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6668 | 1.0 | 235 | 0.6653 | 0.5725 |
0.6527 | 2.0 | 470 | 0.6233 | 0.6528 |
0.5628 | 3.0 | 705 | 0.5658 | 0.7048 |
0.4683 | 4.0 | 940 | 0.5314 | 0.7291 |
0.3694 | 5.0 | 1175 | 0.5220 | 0.7539 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1