You can deploy this model and start earning money today!

nathanaelvw/
image_classification

Name: image_classification
Rating: 2.5 (5 reviews)

tensorboard

safetensors

vit

generated_from_trainer

imagefolder

nathanaelvw/image_classification

finetune

apache-2.0

model-index

Views

No views yet

image_classification

This model is a fine-tuned version of nathanaelvw/image_classification on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 1.4983
Accuracy: 0.5062

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: 1e-05
train_batch_size: 8
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.2
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.6309	1.0	20	1.7392	0.4375
1.6329	2.0	40	1.7210	0.4437
1.6151	3.0	60	1.7045	0.4625
1.5724	4.0	80	1.6784	0.4
1.514	5.0	100	1.6341	0.4188
1.5115	6.0	120	1.6069	0.5
1.4803	7.0	140	1.5779	0.4938
1.4209	8.0	160	1.5963	0.4313
1.4094	9.0	180	1.5536	0.475
1.3915	10.0	200	1.5183	0.5
1.3404	11.0	220	1.5237	0.4813
1.3488	12.0	240	1.5148	0.4625
1.3061	13.0	260	1.4860	0.5312
1.2829	14.0	280	1.4801	0.4875
1.2322	15.0	300	1.4922	0.4813
1.2572	16.0	320	1.5054	0.4938
1.2308	17.0	340	1.4647	0.5
1.2364	18.0	360	1.4809	0.4625
1.2389	19.0	380	1.4798	0.4813
1.2551	20.0	400	1.4617	0.5125

Framework versions

Transformers 4.42.4
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1