square_run_square_run_second_vote_full_pic_stratified_vgg2

This model is a fine-tuned version of timm/vgg19_bn.tv_in1k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0143
• F1 Macro: 0.5140
• F1 Micro: 0.6212
• F1 Weighted: 0.6038
• Precision Macro: 0.5210
• Precision Micro: 0.6212
• Precision Weighted: 0.6124
• Recall Macro: 0.5342
• 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
• 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
1.7749	1.0	58	1.7397	0.1686	0.2727	0.2196	0.1887	0.2727	0.2269	0.1998	0.2727	0.2727	0.2727
1.5924	2.0	116	1.4291	0.3580	0.4621	0.4393	0.3810	0.4621	0.4825	0.3943	0.4621	0.4621	0.4621
1.4563	3.0	174	1.4826	0.3331	0.4697	0.4290	0.4364	0.4697	0.5308	0.3673	0.4697	0.4697	0.4697
1.2888	4.0	232	1.3110	0.4048	0.5530	0.4917	0.4449	0.5530	0.5385	0.4632	0.5530	0.5530	0.5530
1.2381	5.0	290	1.5292	0.3700	0.4318	0.4001	0.4623	0.4318	0.5131	0.4062	0.4318	0.4318	0.4318
0.8614	6.0	348	1.2528	0.4719	0.5833	0.5605	0.5388	0.5833	0.6189	0.4791	0.5833	0.5833	0.5833
0.6534	7.0	406	0.9814	0.5645	0.6515	0.6509	0.5754	0.6515	0.6658	0.5679	0.6515	0.6515	0.6515
0.8215	8.0	464	1.7659	0.4721	0.5833	0.5505	0.5161	0.5833	0.5741	0.4795	0.5833	0.5833	0.5833
1.0124	9.0	522	1.2417	0.5315	0.6364	0.6192	0.5533	0.6364	0.6354	0.5431	0.6364	0.6364	0.6364
0.4758	10.0	580	1.1776	0.5466	0.6364	0.6432	0.5769	0.6364	0.6841	0.5503	0.6364	0.6364	0.6364
0.5769	11.0	638	1.4177	0.5237	0.6288	0.6036	0.5515	0.6288	0.6187	0.5322	0.6288	0.6288	0.6288
0.4681	12.0	696	1.7591	0.4900	0.5909	0.5736	0.5555	0.5909	0.6291	0.4891	0.5909	0.5909	0.5909
0.9084	13.0	754	1.1417	0.6398	0.7045	0.7026	0.6509	0.7045	0.7058	0.6353	0.7045	0.7045	0.7045
0.0526	14.0	812	1.4903	0.5463	0.6667	0.6413	0.5855	0.6667	0.6794	0.5720	0.6667	0.6667	0.6667
0.6759	15.0	870	2.0678	0.5527	0.6061	0.5935	0.6105	0.6061	0.6249	0.5409	0.6061	0.6061	0.6061
0.2646	16.0	928	1.9471	0.6265	0.6818	0.6949	0.6584	0.6818	0.7281	0.6358	0.6818	0.6818	0.6818
0.0445	17.0	986	1.8514	0.6629	0.7045	0.7012	0.6802	0.7045	0.7136	0.6574	0.7045	0.7045	0.7045
0.1438	18.0	1044	2.6504	0.5446	0.6439	0.6340	0.5799	0.6439	0.6624	0.5482	0.6439	0.6439	0.6439
0.0011	19.0	1102	2.0833	0.6141	0.6667	0.6667	0.6241	0.6667	0.6826	0.6302	0.6667	0.6667	0.6667
0.0195	20.0	1160	2.5074	0.5801	0.6515	0.6551	0.6232	0.6515	0.7020	0.5867	0.6515	0.6515	0.6515
0.0089	21.0	1218	2.5588	0.6032	0.6742	0.6598	0.6426	0.6742	0.6746	0.6036	0.6742	0.6742	0.6742
0.0	22.0	1276	2.3691	0.6211	0.6818	0.6851	0.6357	0.6818	0.7047	0.6380	0.6818	0.6818	0.6818
0.0014	23.0	1334	2.7237	0.5942	0.6667	0.6600	0.6263	0.6667	0.6828	0.5952	0.6667	0.6667	0.6667
0.0004	24.0	1392	2.5083	0.6426	0.6970	0.6982	0.6515	0.6970	0.7163	0.6548	0.6970	0.6970	0.6970
0.0132	25.0	1450	2.7855	0.6647	0.7121	0.7015	0.6819	0.7121	0.7083	0.6632	0.7121	0.7121	0.7121
0.0022	26.0	1508	2.7880	0.6500	0.6970	0.6925	0.6636	0.6970	0.7010	0.6494	0.6970	0.6970	0.6970
0.0	27.0	1566	2.8432	0.6574	0.7121	0.7012	0.6749	0.7121	0.7126	0.6623	0.7121	0.7121	0.7121
0.0	28.0	1624	2.7713	0.6243	0.6970	0.6935	0.6376	0.6970	0.7017	0.6230	0.6970	0.6970	0.6970
0.0	29.0	1682	2.7503	0.6245	0.6970	0.6945	0.6395	0.6970	0.7043	0.6225	0.6970	0.6970	0.6970
0.0001	30.0	1740	2.8260	0.6361	0.7045	0.7012	0.6569	0.7045	0.7122	0.6318	0.7045	0.7045	0.7045

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0