Main_Fashion-convnext

This model is a fine-tuned version of facebook/convnext-tiny-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1758
• Accuracy: 0.6381

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0951	0.9630	13	2.0201	0.2251
1.9821	2.0	27	1.8213	0.4037
1.7245	2.9630	40	1.6774	0.4640
1.6117	4.0	54	1.5480	0.5452
1.5	4.9630	67	1.4506	0.5615
1.3393	6.0	81	1.3610	0.5963
1.2579	6.9630	94	1.2995	0.6172
1.2405	8.0	108	1.2480	0.6288
1.1479	8.9630	121	1.2127	0.6357
1.1005	10.0	135	1.1898	0.6381
1.0989	10.9630	148	1.1778	0.6381
1.0816	11.5556	156	1.1758	0.6381

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1