cmmy

This model is a fine-tuned version of therealcyberlord/stanford-car-vit-patch16 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Accuracy: 0.5412
• Loss: 1.4404

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: 256
• eval_batch_size: 256
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 1024
• 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	Accuracy	Validation Loss
16.0903	0.9967	226	0.1969	3.4455
11.5438	1.9967	452	0.2992	2.4033
9.5963	2.9967	678	0.3492	2.0761
8.3873	3.9967	904	0.3934	1.8921
7.3127	4.9967	1130	0.4288	1.7535
6.2178	5.9967	1356	0.4609	1.6533
5.4619	6.9967	1582	0.4856	1.5859
4.618	7.9967	1808	0.5129	1.5253
3.9349	8.9967	2034	0.5315	1.4693
3.4667	9.9967	2260	0.5412	1.4404

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0