convnextv2-tiny-1k-224-finetuned-bottomwear-v2

This model is a fine-tuned version of facebook/convnextv2-tiny-1k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.3267
• Accuracy: 0.8981
• Precision: 0.9001

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: 2e-05
• train_batch_size: 10
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision
No log	1.0	87	1.3349	0.6852	0.7395
No log	2.0	174	0.7869	0.8426	0.8543
No log	3.0	261	0.6571	0.8472	0.8712
No log	4.0	348	0.4293	0.9028	0.9122
No log	5.0	435	0.4030	0.8935	0.8953
0.916	6.0	522	0.4251	0.8657	0.8787
0.916	7.0	609	0.3536	0.8889	0.8936
0.916	8.0	696	0.3611	0.8796	0.8833
0.916	9.0	783	0.3267	0.8981	0.9001
0.916	10.0	870	0.3526	0.8796	0.8972
0.916	11.0	957	0.3694	0.8981	0.9100
0.3192	12.0	1044	0.3694	0.8935	0.9007

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1