convnext-base-8e-5-15ep

This model is a fine-tuned version of facebook/convnextv2-base-22k-384 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.3097
• Accuracy: 0.9369

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: 8e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5403	1.0	1099	0.4231	0.8744
0.4376	2.0	2198	0.3817	0.8899
0.3601	3.0	3297	0.3818	0.9018
0.3202	4.0	4396	0.3153	0.9201
0.2463	5.0	5495	0.3216	0.9229
0.2051	6.0	6594	0.3338	0.9213
0.2108	7.0	7693	0.3224	0.9272
0.1568	8.0	8792	0.3127	0.9356
0.1491	9.0	9891	0.3258	0.9352
0.0998	10.0	10990	0.3257	0.9348
0.0728	11.0	12089	0.3289	0.9368
0.0872	12.0	13188	0.3288	0.9408
0.0731	13.0	14287	0.3320	0.9408
0.0693	14.0	15386	0.3270	0.9423
0.0586	15.0	16485	0.3251	0.9427

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2