This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the generator dataset. It achieves the following results on the evaluation set:

Loss: 0.3588
Accuracy: 0.9571

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: 256
eval_batch_size: 256
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6955	1.0	2	0.6818	0.6
0.6482	2.0	4	0.6114	0.8429
0.5613	3.0	6	0.5547	0.8714
0.5062	4.0	8	0.4905	0.8714
0.5174	5.0	10	0.4499	0.8857
0.4428	6.0	12	0.4480	0.9286
0.4778	7.0	14	0.4045	0.9143
0.4379	8.0	16	0.4020	0.9429
0.3983	9.0	18	0.3847	0.9571
0.3377	10.0	20	0.3588	0.9571

Framework versions

Transformers 4.52.3
Pytorch 2.7.0+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Jedrzej-Smok/2025-06-01_13-58-11

2025-06-01_13-58-11

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Jedrzej-Smok/
2025-06-01_13-58-11