This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.7504
Accuracy: 0.8537

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: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0726	1.0	110	0.3341	0.9024
0.0333	2.0	220	0.9022	0.7561
0.0011	3.0	330	0.5944	0.8293
0.0026	4.0	440	0.6847	0.8293
0.0012	5.0	550	1.1544	0.8049
0.0005	6.0	660	0.4633	0.8537
0.0031	7.0	770	0.5821	0.8780
0.0	8.0	880	0.7434	0.8780
0.0	9.0	990	0.7497	0.8537
0.0	10.0	1100	0.7504	0.8537

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

hkivancoral/hushem_40x_deit_tiny_f5

hushem_40x_deit_tiny_f5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_40x_deit_tiny_f5