Conversion_at_month_2_Class_Weighted_Loss-swin-base-patch4-window7-224_class_weight

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4821
• Accuracy: 1.0
• Precision Macro: 1.0
• Recall Macro: 1.0
• F1 Macro: 1.0

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: 4
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision Macro	Recall Macro	F1 Macro
No log	1.0	2	0.7139	0.875	0.4375	0.5	0.4667
No log	2.0	4	1.1869	0.875	0.4375	0.5	0.4667
No log	3.0	6	1.9141	0.875	0.4375	0.5	0.4667
No log	4.0	8	3.7772	0.875	0.4375	0.5	0.4667
1.4632	5.0	10	3.9050	0.875	0.4375	0.5	0.4667
1.4632	6.0	12	6.2791	0.875	0.4375	0.5	0.4667

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2