Paper_compared-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: 0.5363
• Accuracy: 0.8409

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.6803	0.9492	14	0.9171	0.7156
0.8219	1.9661	29	0.5230	0.8330
0.2323	2.9831	44	0.5110	0.8047
0.1112	4.0	59	0.4968	0.8138
0.0387	4.9492	73	0.5502	0.8093
0.0232	5.9661	88	0.5506	0.8296
0.0096	6.9831	103	0.5341	0.8431
0.0068	8.0	118	0.6003	0.8149
0.0046	8.9492	132	0.5298	0.8409
0.0051	9.4915	140	0.5363	0.8409

Framework versions

• Transformers 4.41.1
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1