clip-vit-base-patch16-finetuned-openai-clip-vit-base-patch16-mnist

This model is a fine-tuned version of openai/clip-vit-base-patch16 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0153
• Accuracy: 0.9958

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• 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
0.5063	1.0	422	0.0742	0.981
0.5043	2.0	844	0.0705	0.9762
0.3477	3.0	1266	0.0400	0.9883
0.3968	4.0	1688	0.0319	0.9895
0.4089	5.0	2110	0.0361	0.9893
0.3039	6.0	2532	0.0329	0.9882
0.293	7.0	2954	0.0244	0.9918
0.2723	8.0	3376	0.0241	0.9912
0.2441	9.0	3798	0.0164	0.9958
0.2394	10.0	4220	0.0153	0.9958

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1