vit-base-patch16-224-ethos-data

This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.7705
• Accuracy: 0.7733

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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
1.6788	0.9905	26	1.4249	0.4667
1.0638	1.9810	52	1.0795	0.64
0.9182	2.9714	78	0.9361	0.7133
0.7136	4.0	105	0.8225	0.78
0.5723	4.9905	131	0.7854	0.76
0.514	5.9429	156	0.7705	0.7733

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1