test1

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

• Loss: 1.1366
• Accuracy: 0.7952
• F1: 0.7855
• Recall: 0.7952

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Recall
No log	0.4554	500	0.6376	0.7896	0.7429	0.7896
0.657	0.9107	1000	0.5839	0.8109	0.7679	0.8109
0.657	1.3661	1500	0.7632	0.7322	0.7195	0.7322
0.5653	1.8215	2000	0.5927	0.8144	0.7689	0.8144
0.5653	2.2769	2500	0.5855	0.8174	0.7765	0.8174
0.5128	2.7322	3000	0.5567	0.8210	0.7931	0.8210
0.5128	3.1876	3500	0.5578	0.8214	0.7894	0.8214
0.4648	3.6430	4000	0.5699	0.8236	0.7928	0.8236
0.4648	4.0984	4500	0.6039	0.8053	0.7850	0.8053
0.411	4.5537	5000	0.5662	0.8203	0.7989	0.8203
0.411	5.0091	5500	0.6043	0.8252	0.7962	0.8252
0.3532	5.4645	6000	0.6559	0.8060	0.7915	0.8060
0.3532	5.9199	6500	0.6310	0.8175	0.7919	0.8175
0.2847	6.3752	7000	0.7075	0.8029	0.7890	0.8029
0.2847	6.8306	7500	0.8056	0.7743	0.7745	0.7743
0.2265	7.2860	8000	0.8991	0.7957	0.7875	0.7957
0.2265	7.7413	8500	0.8929	0.7904	0.7866	0.7904
0.1626	8.1967	9000	0.9503	0.8022	0.7883	0.8022
0.1626	8.6521	9500	1.0467	0.7904	0.7838	0.7904
0.1099	9.1075	10000	1.0435	0.8009	0.7877	0.8009
0.1099	9.5628	10500	1.1366	0.7952	0.7855	0.7952

Framework versions

• Transformers 4.41.2
• Pytorch 2.2.1
• Datasets 2.19.1
• Tokenizers 0.19.1