convnextv2-tiny-1k-224-finetuned-fullwear-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: 0.5128
• Accuracy: 0.8229
• Precision: 0.8356

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	116	1.8085	0.5625	0.6486
No log	2.0	232	1.2627	0.6771	0.7218
No log	3.0	348	1.0071	0.6806	0.7166
No log	4.0	464	0.8603	0.7188	0.7466
1.3688	5.0	580	0.7240	0.7708	0.8074
1.3688	6.0	696	0.7496	0.7535	0.7994
1.3688	7.0	812	0.5832	0.8056	0.8176
1.3688	8.0	928	0.5809	0.7986	0.8156
0.4904	9.0	1044	0.5456	0.7986	0.8052
0.4904	10.0	1160	0.5833	0.7951	0.8198
0.4904	11.0	1276	0.5782	0.7986	0.8069
0.4904	12.0	1392	0.5128	0.8229	0.8356
0.2966	13.0	1508	0.5421	0.8160	0.8319
0.2966	14.0	1624	0.6090	0.7847	0.8171
0.2966	15.0	1740	0.6090	0.8021	0.8135

Framework versions

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