seekwell_skincancer

This model is a fine-tuned version of Anwarkh1/Skin_Cancer-Image_Classification on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4759
• Accuracy: 0.5370
• Balanced Accuracy: 0.5487
• F1: 0.5636
• Precision: 0.6202
• Recall: 0.5370

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-06
• train_batch_size: 64
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Balanced Accuracy	F1	Precision	Recall
No log	1.0	29	1.7928	0.1717	0.1621	0.1560	0.2095	0.1717
No log	2.0	58	1.7462	0.2891	0.2562	0.2608	0.3386	0.2891
No log	3.0	87	1.7055	0.3717	0.3505	0.3412	0.4271	0.3717
No log	4.0	116	1.6709	0.4478	0.4589	0.4324	0.5368	0.4478
No log	5.0	145	1.6375	0.4891	0.5031	0.4946	0.6003	0.4891
No log	6.0	174	1.6067	0.4891	0.4941	0.5050	0.6001	0.4891
No log	7.0	203	1.5787	0.5065	0.5266	0.5260	0.6004	0.5065
No log	8.0	232	1.5530	0.5130	0.5307	0.5370	0.6014	0.5130
No log	9.0	261	1.5301	0.5130	0.5313	0.5395	0.6015	0.5130
No log	10.0	290	1.5117	0.5217	0.5359	0.5489	0.6089	0.5217
No log	11.0	319	1.4960	0.5239	0.5429	0.5505	0.6099	0.5239
No log	12.0	348	1.4840	0.5304	0.5430	0.5569	0.6135	0.5304
No log	13.0	377	1.4759	0.5370	0.5487	0.5636	0.6202	0.5370
No log	14.0	406	1.4704	0.5326	0.5467	0.5598	0.6179	0.5326
No log	15.0	435	1.4688	0.5348	0.5478	0.5622	0.6205	0.5348

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1