square_run_second_vote_full_pic_50_age_gender

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: 1.6845
• F1 Macro: 0.2886
• F1 Micro: 0.3182
• F1 Weighted: 0.3108
• Precision Macro: 0.3139
• Precision Micro: 0.3182
• Precision Weighted: 0.3485
• Recall Macro: 0.3032
• Recall Micro: 0.3182
• Recall Weighted: 0.3182
• Accuracy: 0.3182

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
1.8934	1.0	58	1.8939	0.0919	0.1970	0.1321	0.0799	0.1970	0.1097	0.1331	0.1970	0.1970	0.1970
1.851	2.0	116	2.0049	0.1066	0.1818	0.1280	0.1010	0.1818	0.1322	0.1720	0.1818	0.1818	0.1818
1.6292	3.0	174	1.8533	0.0849	0.2197	0.1086	0.0673	0.2197	0.0808	0.1568	0.2197	0.2197	0.2197
1.7267	4.0	232	1.8215	0.1715	0.2803	0.2141	0.3136	0.2803	0.3357	0.2133	0.2803	0.2803	0.2803
1.7363	5.0	290	1.8649	0.1065	0.1894	0.1268	0.1423	0.1894	0.1728	0.1730	0.1894	0.1894	0.1894
1.5974	6.0	348	1.8716	0.0916	0.25	0.1212	0.0721	0.25	0.0900	0.1746	0.25	0.25	0.25
1.8537	7.0	406	1.7017	0.2792	0.3333	0.3191	0.3181	0.3333	0.3633	0.2977	0.3333	0.3333	0.3333
1.4206	8.0	464	1.7872	0.1898	0.2727	0.2361	0.2092	0.2727	0.2442	0.2089	0.2727	0.2727	0.2727
2.1512	9.0	522	1.7402	0.2806	0.3333	0.3177	0.3019	0.3333	0.3379	0.2985	0.3333	0.3333	0.3333
1.6426	10.0	580	1.7943	0.2511	0.3106	0.2867	0.2731	0.3106	0.3042	0.2713	0.3106	0.3106	0.3106
1.5341	11.0	638	1.8591	0.2551	0.3030	0.2945	0.2564	0.3030	0.2941	0.2623	0.3030	0.3030	0.3030
1.0766	12.0	696	1.9545	0.2281	0.2955	0.2800	0.2455	0.2955	0.2902	0.2341	0.2955	0.2955	0.2955
0.8697	13.0	754	2.3504	0.1614	0.2727	0.2089	0.1739	0.2727	0.2207	0.2027	0.2727	0.2727	0.2727
0.7089	14.0	812	1.9392	0.2557	0.3409	0.3160	0.2531	0.3409	0.3054	0.2705	0.3409	0.3409	0.3409
0.9405	15.0	870	2.1086	0.2788	0.3485	0.3362	0.2945	0.3485	0.3480	0.2866	0.3485	0.3485	0.3485
0.768	16.0	928	2.1161	0.2990	0.3636	0.3599	0.3112	0.3636	0.3779	0.3073	0.3636	0.3636	0.3636
0.5405	17.0	986	2.2513	0.2757	0.3258	0.3197	0.2851	0.3258	0.3370	0.2867	0.3258	0.3258	0.3258
0.6639	18.0	1044	2.4633	0.2542	0.3106	0.3033	0.2616	0.3106	0.3156	0.2668	0.3106	0.3106	0.3106
0.1962	19.0	1102	2.5737	0.2463	0.3258	0.2995	0.2654	0.3258	0.3085	0.2575	0.3258	0.3258	0.3258
0.2221	20.0	1160	2.7099	0.2449	0.2803	0.2825	0.2577	0.2803	0.3097	0.2521	0.2803	0.2803	0.2803
0.3077	21.0	1218	2.7888	0.2527	0.3106	0.2980	0.2673	0.3106	0.3100	0.2626	0.3106	0.3106	0.3106
0.1271	22.0	1276	2.9443	0.2291	0.2652	0.2661	0.2315	0.2652	0.2727	0.2319	0.2652	0.2652	0.2652
0.1309	23.0	1334	3.0628	0.2714	0.3409	0.3305	0.3025	0.3409	0.3511	0.2700	0.3409	0.3409	0.3409
0.2454	24.0	1392	3.1552	0.2497	0.3182	0.3009	0.2573	0.3182	0.3021	0.2578	0.3182	0.3182	0.3182
0.0606	25.0	1450	3.2449	0.2319	0.2879	0.2810	0.2294	0.2879	0.2790	0.2379	0.2879	0.2879	0.2879
0.0862	26.0	1508	3.2262	0.2554	0.3182	0.3119	0.2557	0.3182	0.3114	0.2608	0.3182	0.3182	0.3182
0.0062	27.0	1566	3.2928	0.2711	0.3258	0.3251	0.2740	0.3258	0.3278	0.2719	0.3258	0.3258	0.3258
0.0427	28.0	1624	3.3795	0.2599	0.3182	0.3121	0.2595	0.3182	0.3101	0.2644	0.3182	0.3182	0.3182
0.007	29.0	1682	3.3703	0.2412	0.2955	0.2917	0.2459	0.2955	0.2940	0.2427	0.2955	0.2955	0.2955
0.0051	30.0	1740	3.4040	0.2484	0.3030	0.3003	0.2530	0.3030	0.3037	0.2500	0.3030	0.3030	0.3030

Framework versions

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