beit-base-patch16-224-pt22k-ft22k-finetuned-conspiracy_imagery_2

This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1099
• Accuracy: 0.5880

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: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.8533	0.9630	13	1.4568	0.4259
1.4844	2.0	27	1.2233	0.5417
1.1179	2.9630	40	1.1893	0.5509
1.0325	4.0	54	1.1467	0.5833
0.9755	4.9630	67	1.1300	0.5926
0.8969	5.7778	78	1.1099	0.5880

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1