0.5-1.0-1.0_0.001_alllora

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: 2.0976

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: 0.001
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.2591	0.5043	58	1.8737
0.2307	1.0087	116	1.8561
0.168	1.5130	174	1.9298
0.1804	2.0174	232	1.8496
0.1204	2.5217	290	1.8696
0.0984	3.0261	348	1.9012
0.0967	3.5304	406	1.9590
0.0872	4.0348	464	2.0099
0.0642	4.5391	522	2.0354
0.063	5.0435	580	1.9165
0.0445	5.5478	638	2.0544
0.0528	6.0522	696	1.9761
0.0545	6.5565	754	2.0307
0.0332	7.0609	812	2.0031
0.0417	7.5652	870	2.0609
0.0398	8.0696	928	2.0922
0.0363	8.5739	986	2.0674
0.0393	9.0783	1044	2.0836
0.0342	9.5826	1102	2.0976

Framework versions

• PEFT 0.10.0
• Transformers 4.40.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.19.1