square_run_second_vote

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

• Loss: 1.1557
• F1 Macro: 0.5777
• F1 Micro: 0.6667
• F1 Weighted: 0.6629
• Precision Macro: 0.5756
• Precision Micro: 0.6667
• Precision Weighted: 0.6734
• Recall Macro: 0.5912
• Recall Micro: 0.6667
• Recall Weighted: 0.6667
• Accuracy: 0.6667

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_BNB 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	F1 Macro	F1 Micro	F1 Weighted	Precision Macro	Precision Micro	Precision Weighted	Recall Macro	Recall Micro	Recall Weighted	Accuracy
1.8754	1.0	58	1.7961	0.1385	0.2803	0.1722	0.1426	0.2803	0.1603	0.2098	0.2803	0.2803	0.2803
2.0246	2.0	116	2.0138	0.2236	0.3106	0.2484	0.2558	0.3106	0.2692	0.2842	0.3106	0.3106	0.3106
1.6189	3.0	174	1.5039	0.2444	0.3864	0.3195	0.2633	0.3864	0.3301	0.2847	0.3864	0.3864	0.3864
1.3445	4.0	232	1.3982	0.3287	0.4394	0.3866	0.3186	0.4394	0.3730	0.3696	0.4394	0.4394	0.4394
1.3387	5.0	290	1.1920	0.4401	0.5758	0.5265	0.4315	0.5758	0.5031	0.4683	0.5758	0.5758	0.5758
1.1664	6.0	348	1.1778	0.4179	0.5076	0.4988	0.5068	0.5076	0.5862	0.4395	0.5076	0.5076	0.5076
1.1622	7.0	406	1.1723	0.4518	0.5379	0.5251	0.4514	0.5379	0.5526	0.4867	0.5379	0.5379	0.5379
0.9827	8.0	464	1.0619	0.5084	0.6212	0.6074	0.5037	0.6212	0.6140	0.5345	0.6212	0.6212	0.6212
1.3416	9.0	522	1.3995	0.3997	0.5	0.4690	0.4218	0.5	0.5024	0.4509	0.5	0.5	0.5
0.758	10.0	580	1.1693	0.5066	0.5985	0.5836	0.5262	0.5985	0.6031	0.5279	0.5985	0.5985	0.5985
0.7758	11.0	638	1.0800	0.5491	0.6515	0.6320	0.5729	0.6515	0.6501	0.5710	0.6515	0.6515	0.6515
0.2319	12.0	696	1.1553	0.5467	0.6742	0.6410	0.5816	0.6742	0.6699	0.5711	0.6742	0.6742	0.6742
0.3528	13.0	754	1.1685	0.5794	0.6894	0.6711	0.5887	0.6894	0.6752	0.5955	0.6894	0.6894	0.6894
0.6238	14.0	812	1.1781	0.5579	0.6439	0.6285	0.5451	0.6439	0.6278	0.5856	0.6439	0.6439	0.6439
0.1869	15.0	870	1.2305	0.5146	0.6061	0.5983	0.5032	0.6061	0.6013	0.5369	0.6061	0.6061	0.6061
0.1015	16.0	928	1.3576	0.5019	0.5909	0.5932	0.5440	0.5909	0.6312	0.4959	0.5909	0.5909	0.5909
0.3809	17.0	986	1.2998	0.5667	0.6591	0.6527	0.5828	0.6591	0.6885	0.5838	0.6591	0.6591	0.6591
0.0887	18.0	1044	1.4154	0.5572	0.6667	0.6489	0.5682	0.6667	0.6518	0.5683	0.6667	0.6667	0.6667
0.1422	19.0	1102	1.3989	0.5609	0.6667	0.6472	0.5672	0.6667	0.6420	0.5695	0.6667	0.6667	0.6667
0.0037	20.0	1160	1.5134	0.5242	0.6212	0.6078	0.5263	0.6212	0.6093	0.5374	0.6212	0.6212	0.6212
0.0602	21.0	1218	1.5349	0.5660	0.6667	0.6544	0.5710	0.6667	0.6503	0.5671	0.6667	0.6667	0.6667
0.0353	22.0	1276	1.4489	0.6137	0.7045	0.6919	0.6146	0.7045	0.6909	0.6242	0.7045	0.7045	0.7045
0.001	23.0	1334	1.4781	0.5715	0.6667	0.6541	0.5657	0.6667	0.6449	0.5805	0.6667	0.6667	0.6667
0.0007	24.0	1392	1.6326	0.5713	0.6591	0.6511	0.5871	0.6591	0.6648	0.5786	0.6591	0.6591	0.6591
0.0084	25.0	1450	1.5856	0.5684	0.6591	0.6569	0.5662	0.6591	0.6672	0.5802	0.6591	0.6591	0.6591
0.0008	26.0	1508	1.5799	0.5826	0.6818	0.6675	0.5849	0.6818	0.6632	0.5884	0.6818	0.6818	0.6818
0.0053	27.0	1566	1.5308	0.5719	0.6667	0.6556	0.5667	0.6667	0.6524	0.5843	0.6667	0.6667	0.6667
0.0004	28.0	1624	1.5639	0.5732	0.6667	0.6617	0.5684	0.6667	0.6673	0.5867	0.6667	0.6667	0.6667
0.0007	29.0	1682	1.5346	0.5835	0.6742	0.6678	0.5786	0.6742	0.6703	0.5965	0.6742	0.6742	0.6742
0.0004	30.0	1740	1.5232	0.5791	0.6742	0.6661	0.5707	0.6742	0.6628	0.5918	0.6742	0.6742	0.6742

Framework versions

• Transformers 4.48.2
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0