NEO_MUL_EXP2_4

This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0441
• Accuracy: 0.9833

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: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1651	0.9886	65	0.2185	0.9233
0.1203	1.9924	131	0.1108	0.9583
0.0871	2.9962	197	0.0879	0.9692
0.0738	4.0	263	0.0665	0.9742
0.0614	4.9430	325	0.0441	0.9833

Framework versions

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