clip-deepfashion-multimodal-10ep

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

• Loss: 0.5629

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-06
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• 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
0.8267	0.8787	500	0.8286
0.5601	1.7575	1000	0.6419
0.385	2.6362	1500	0.5994
0.2596	3.5149	2000	0.5553
0.2132	4.3937	2500	0.5643
0.1657	5.2724	3000	0.5802
0.1419	6.1511	3500	0.5547
0.1213	7.0299	4000	0.5635
0.1059	7.9086	4500	0.5448
0.0935	8.7873	5000	0.5702
0.0804	9.6661	5500	0.5629

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.1+cu124
• Datasets 4.4.1
• Tokenizers 0.19.1