convnextv2-large-1k-224-finetuned-BreastCancer-Classification-BreakHis-AH-60-20-20-Shuffled

This model is a fine-tuned version of facebook/convnextv2-large-1k-224 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0398
• Accuracy: 0.9882

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.9
• num_epochs: 14

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
0.5059	1.0	199	0.9001	0.4826
0.2533	2.0	398	0.9515	0.2124
0.2358	3.0	597	0.9538	0.1543
0.2584	4.0	796	0.9642	0.1136
0.1085	5.0	995	0.9746	0.0891
0.1007	6.0	1194	0.9769	0.0725
0.1463	7.0	1393	0.9840	0.0541
0.3564	8.0	1592	0.9802	0.0880
0.0957	9.0	1791	0.9656	0.1375
0.1481	10.0	1990	0.0511	0.9873
0.1536	11.0	2189	0.0827	0.9713
0.0458	12.0	2388	0.0398	0.9882
0.4956	13.0	2587	0.3474	0.8643
0.0801	14.0	2786	0.0850	0.9797

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3