finetune-clip-vit-large-patch14

This model is a fine-tuned version of openai/clip-vit-large-patch14 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6545
• F1: 0.6242

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.7084	0.3690	100	0.7173	0.5405
0.6818	0.7380	200	0.7269	0.5683
0.7169	1.1070	300	0.6949	0.5683
0.6957	1.4760	400	0.6799	0.5650
0.6218	1.8450	500	0.7344	0.5766
0.6406	2.2140	600	0.6600	0.6118
0.6645	2.5830	700	0.6581	0.6113
0.6546	2.9520	800	0.6549	0.6192
0.6068	3.3210	900	0.6542	0.6224
0.6351	3.6900	1000	0.6545	0.6242

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0