tebak-gambar-mobilevit

This model is a fine-tuned version of apple/mobilevit-x-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0799
• Accuracy: 0.7289

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: 0.0008
• train_batch_size: 256
• eval_batch_size: 256
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.5084	0.2844	5000	1.4700	0.6364
1.3684	0.5689	10000	1.3353	0.6674
1.3568	0.8533	15000	1.2764	0.6804
1.226	1.1377	20000	1.2323	0.6924
1.2125	1.4222	25000	1.1850	0.7031
1.1912	1.7066	30000	1.1567	0.7092
1.1902	1.9910	35000	1.1297	0.7165
1.131	2.2754	40000	1.1106	0.7213
1.124	2.5599	45000	1.0916	0.7258
1.1245	2.8443	50000	1.0782	0.7300

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1