vit-base-patch16-224

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3122
• F1 Macro: 0.5397
• F1 Micro: 0.6212
• F1 Weighted: 0.6077
• Precision Macro: 0.5343
• Precision Micro: 0.6212
• Precision Weighted: 0.6084
• Recall Macro: 0.5571
• Recall Micro: 0.6212
• Recall Weighted: 0.6212
• Accuracy: 0.6212

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.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	F1 Macro	F1 Micro	F1 Weighted	Precision Macro	Precision Micro	Precision Weighted	Recall Macro	Recall Micro	Recall Weighted	Accuracy
1.9037	1.0	29	1.8618	0.1250	0.2197	0.1592	0.1401	0.2197	0.1692	0.1674	0.2197	0.2197	0.2197
1.6981	2.0	58	1.8760	0.1537	0.2424	0.1896	0.2152	0.2424	0.2787	0.2068	0.2424	0.2424	0.2424
1.7426	3.0	87	1.6971	0.2272	0.3333	0.2622	0.1959	0.3333	0.2233	0.2846	0.3333	0.3333	0.3333
1.1847	4.0	116	1.5082	0.3360	0.4242	0.3911	0.3925	0.4242	0.4281	0.3553	0.4242	0.4242	0.4242
1.3906	5.0	145	1.4063	0.3152	0.4621	0.3815	0.2727	0.4621	0.3279	0.3785	0.4621	0.4621	0.4621
1.5575	6.0	174	1.3833	0.4414	0.4621	0.4526	0.4850	0.4621	0.4941	0.4402	0.4621	0.4621	0.4621
1.1063	7.0	203	1.2431	0.4750	0.5833	0.5453	0.5898	0.5833	0.6329	0.4890	0.5833	0.5833	0.5833
1.1503	8.0	232	1.3635	0.4036	0.4924	0.4586	0.4145	0.4924	0.4762	0.4436	0.4924	0.4924	0.4924
0.5124	9.0	261	1.1603	0.5463	0.6288	0.6136	0.5488	0.6288	0.6113	0.5551	0.6288	0.6288	0.6288
0.6648	10.0	290	1.4136	0.4184	0.5	0.4713	0.4713	0.5	0.5275	0.4413	0.5	0.5	0.5
0.2917	11.0	319	1.2004	0.5155	0.6061	0.5892	0.5180	0.6061	0.5882	0.5268	0.6061	0.6061	0.6061
0.4962	12.0	348	1.3730	0.4970	0.5682	0.5671	0.5094	0.5682	0.5909	0.5109	0.5682	0.5682	0.5682
0.5723	13.0	377	1.3377	0.5705	0.6136	0.6077	0.7050	0.6136	0.6879	0.5756	0.6136	0.6136	0.6136
0.4589	14.0	406	1.3717	0.5648	0.6136	0.6094	0.6239	0.6136	0.6458	0.5609	0.6136	0.6136	0.6136
0.2544	15.0	435	1.4129	0.5086	0.5985	0.5793	0.5140	0.5985	0.5772	0.5187	0.5985	0.5985	0.5985
0.3179	16.0	464	1.3589	0.5882	0.6439	0.6347	0.6912	0.6439	0.6603	0.5777	0.6439	0.6439	0.6439
0.1304	17.0	493	1.5604	0.5010	0.5758	0.5606	0.5123	0.5758	0.5669	0.5076	0.5758	0.5758	0.5758
0.0887	18.0	522	1.6231	0.5091	0.6061	0.5800	0.5344	0.6061	0.5917	0.5190	0.6061	0.6061	0.6061
0.0254	19.0	551	1.6095	0.5625	0.6136	0.6070	0.6642	0.6136	0.6353	0.5520	0.6136	0.6136	0.6136
0.0908	20.0	580	1.6941	0.5270	0.6136	0.5962	0.5331	0.6136	0.6004	0.5381	0.6136	0.6136	0.6136
0.0913	21.0	609	1.6917	0.5537	0.6136	0.6018	0.5909	0.6136	0.6169	0.5579	0.6136	0.6136	0.6136
0.015	22.0	638	1.8274	0.4866	0.5682	0.5512	0.4855	0.5682	0.5477	0.5003	0.5682	0.5682	0.5682
0.0156	23.0	667	1.7322	0.5772	0.6439	0.6233	0.6870	0.6439	0.6598	0.5802	0.6439	0.6439	0.6439
0.0275	24.0	696	1.6262	0.5293	0.6212	0.6006	0.5274	0.6212	0.5913	0.5422	0.6212	0.6212	0.6212
0.0034	25.0	725	1.7278	0.5680	0.6591	0.6409	0.5674	0.6591	0.6333	0.5786	0.6591	0.6591	0.6591
0.0021	26.0	754	1.7111	0.5542	0.6439	0.6250	0.5506	0.6439	0.6148	0.5657	0.6439	0.6439	0.6439
0.0021	27.0	783	1.7412	0.5556	0.6439	0.6257	0.5507	0.6439	0.6163	0.5684	0.6439	0.6439	0.6439
0.0079	28.0	812	1.8651	0.5506	0.6364	0.6176	0.5427	0.6364	0.6078	0.5670	0.6364	0.6364	0.6364
0.0018	29.0	841	1.8016	0.5508	0.6364	0.6184	0.5425	0.6364	0.6074	0.5654	0.6364	0.6364	0.6364
0.0068	30.0	870	1.7936	0.5510	0.6364	0.6182	0.5436	0.6364	0.6073	0.5650	0.6364	0.6364	0.6364

Framework versions

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