mobilevit-trained-task3

This model is a fine-tuned version of apple/mobilevitv2-1.0-imagenet1k-256 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1371
• Accuracy: 0.9670

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: 0.001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6753	0.99	126	0.8382	0.7376
0.6882	2.0	253	0.6129	0.7874
0.4068	3.0	380	0.3532	0.8876
0.3587	4.0	507	0.4896	0.8622
0.3013	4.99	633	0.2656	0.9078
0.2777	6.0	760	0.1679	0.9472
0.2093	7.0	887	0.2264	0.9302
0.1866	8.0	1014	0.2245	0.9263
0.1896	8.99	1140	0.2252	0.9333
0.1059	10.0	1267	0.1544	0.9528
0.1072	11.0	1394	0.2232	0.9391
0.1121	12.0	1521	0.1723	0.9467
0.103	12.99	1647	0.1750	0.9530
0.071	14.0	1774	0.1713	0.9541
0.0276	15.0	1901	0.1384	0.9631
0.0279	16.0	2028	0.1575	0.9607
0.0396	16.99	2154	0.1579	0.9604
0.0129	18.0	2281	0.1389	0.9674
0.0031	19.0	2408	0.1315	0.9689
0.0074	19.88	2520	0.1371	0.9670

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2