clip-vit-base-patch32-finetuned-cars

This model is a fine-tuned version of openai/clip-vit-base-patch32 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.4621
• Accuracy: 1.0

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: 3
• eval_batch_size: 3
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 12
• optimizer: Use adamw_torch_fused 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	2	0.4621	1.0
No log	2.0	4	0.3222	1.0
No log	3.0	6	0.2562	0.8889
No log	4.0	8	0.2668	0.8889
0.3954	5.0	10	0.2213	0.8889

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0
• Datasets 4.0.0
• Tokenizers 0.22.0