convnextv2-tiny-1k-224-finetuned-topwear-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: 0.5060
• Accuracy: 0.8177
• Precision: 0.8427

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	77	1.4963	0.6615	0.7047
No log	2.0	154	1.0708	0.6354	0.7218
No log	3.0	231	0.8045	0.7708	0.8080
No log	4.0	308	0.6572	0.7969	0.8195
No log	5.0	385	0.5992	0.7969	0.8338
No log	6.0	462	0.5877	0.8021	0.8398
0.8831	7.0	539	0.5497	0.8073	0.8614
0.8831	8.0	616	0.5412	0.8073	0.8275
0.8831	9.0	693	0.5060	0.8177	0.8427
0.8831	10.0	770	0.5167	0.8281	0.8372
0.8831	11.0	847	0.6315	0.7969	0.8148
0.8831	12.0	924	0.5166	0.8125	0.8318

Framework versions

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