Psoriasis-Project-M-clip-vit-large-patch14

This model is a fine-tuned version of openai/clip-vit-large-patch14 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4710
• Accuracy: 0.8958

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.92	6	1.8042	0.7917
0.1258	2.0	13	1.4387	0.8333
0.1258	2.92	19	2.5280	0.7292
0.0815	4.0	26	0.9424	0.8542
0.0493	4.62	30	0.8434	0.8542
No log	0.92	6	8.7831	0.2917
6.4844	2.0	13	3.2443	0.5417
6.4844	2.92	19	1.4924	0.7708
1.5554	4.0	26	0.6663	0.875
0.2061	4.62	30	0.7655	0.8125
No log	0.92	6	1.1418	0.8333
0.0506	2.0	13	2.5893	0.7292
0.0506	2.92	19	1.5925	0.7917
0.1137	4.0	26	1.3275	0.8958
0.0132	4.62	30	1.4710	0.8958

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2