LC_Classification_mymodel

This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.4954
• Accuracy: 0.8127

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 128
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.5039	1.0	20	1.4275	0.2540
1.1888	2.0	40	1.1616	0.4730
1.0682	3.0	60	1.0345	0.5302
0.8865	4.0	80	0.9234	0.5683
0.7938	5.0	100	0.8973	0.5492
0.7519	6.0	120	0.8358	0.6127
0.6776	7.0	140	0.8197	0.6222
0.5899	8.0	160	0.7399	0.6635
0.5905	9.0	180	0.7407	0.6381
0.5343	10.0	200	0.7049	0.7143
0.4882	11.0	220	0.6190	0.7333
0.4188	12.0	240	0.6137	0.7524
0.4429	13.0	260	0.5947	0.7556
0.4362	14.0	280	0.6187	0.7175
0.3318	15.0	300	0.5669	0.7683
0.3945	16.0	320	0.5443	0.7937
0.3985	17.0	340	0.5436	0.8095
0.2732	18.0	360	0.5000	0.8222
0.3049	19.0	380	0.5211	0.8
0.2911	20.0	400	0.5371	0.7714
0.2853	21.0	420	0.4954	0.8127

Framework versions

• Transformers 4.51.3
• Pytorch 2.5.1+cu121
• Datasets 3.6.0
• Tokenizers 0.21.1