0.50-800Train-100Test-beit-base

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: 0.7501
• Accuracy: 0.8192

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: 16
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7627	0.9536	18	0.6991	0.7860
0.3414	1.9603	37	0.5881	0.8070
0.1402	2.9669	56	0.5879	0.8114
0.0663	3.9735	75	0.6249	0.8175
0.0377	4.9801	94	0.6539	0.8210
0.0314	5.9868	113	0.7074	0.8175
0.0189	6.9934	132	0.7596	0.8210
0.0147	8.0	151	0.7211	0.8253
0.0157	8.9536	169	0.7412	0.8166
0.0095	9.5364	180	0.7501	0.8192

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1