test_model_8

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.8797
• F1 Macro: 0.0598
• F1 Micro: 0.2121
• F1 Weighted: 0.0845
• Precision Macro: 0.1723
• Precision Micro: 0.2121
• Precision Weighted: 0.2316
• Recall Macro: 0.1486
• Recall Micro: 0.2121
• Recall Weighted: 0.2121
• Accuracy: 0.2121

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Macro	F1 Micro	F1 Weighted	Precision Macro	Precision Micro	Precision Weighted	Recall Macro	Recall Micro	Recall Weighted	Accuracy
1.9439	0.8	3	1.9065	0.0541	0.1894	0.0764	0.0625	0.1894	0.0857	0.1327	0.1894	0.1894	0.1894
1.9049	1.8	6	1.8820	0.0578	0.2045	0.0818	0.0501	0.2045	0.0696	0.1433	0.2045	0.2045	0.2045
2.3436	2.8	9	1.8773	0.0738	0.1894	0.1022	0.0567	0.1894	0.0780	0.1348	0.1894	0.1894	0.1894

Framework versions

• Transformers 4.48.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0