square_run_first_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: 1.6395
• F1 Macro: 0.2469
• F1 Micro: 0.3485
• F1 Weighted: 0.2801
• Precision Macro: 0.2428
• Precision Micro: 0.3485
• Precision Weighted: 0.2847
• Recall Macro: 0.3062
• Recall Micro: 0.3485
• Recall Weighted: 0.3485
• Accuracy: 0.3485

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
1.952	1.0	58	1.9331	0.1015	0.1894	0.1193	0.0782	0.1894	0.0909	0.1571	0.1894	0.1894	0.1894
1.8507	2.0	116	1.9609	0.0434	0.1364	0.0478	0.0314	0.1364	0.0344	0.1228	0.1364	0.1364	0.1364
1.8752	3.0	174	1.8530	0.1515	0.2197	0.1864	0.1396	0.2197	0.1747	0.1834	0.2197	0.2197	0.2197
1.6369	4.0	232	1.8198	0.1627	0.2652	0.2010	0.2272	0.2652	0.2553	0.2011	0.2652	0.2652	0.2652
1.9706	5.0	290	1.7950	0.2160	0.2955	0.2460	0.2685	0.2955	0.3249	0.2686	0.2955	0.2955	0.2955
1.738	6.0	348	1.6951	0.3343	0.4091	0.3811	0.4054	0.4091	0.4381	0.3537	0.4091	0.4091	0.4091
1.924	7.0	406	1.6492	0.3123	0.3636	0.3150	0.5154	0.3636	0.4299	0.3365	0.3636	0.3636	0.3636
1.8234	8.0	464	1.7347	0.3183	0.3712	0.3515	0.3698	0.3712	0.4277	0.3554	0.3712	0.3712	0.3712
1.5916	9.0	522	1.8146	0.2720	0.3712	0.3008	0.3597	0.3712	0.3850	0.3281	0.3712	0.3712	0.3712
1.578	10.0	580	1.7509	0.2703	0.3561	0.3033	0.3571	0.3561	0.4226	0.3217	0.3561	0.3561	0.3561
1.5857	11.0	638	1.8672	0.3019	0.3561	0.3520	0.3399	0.3561	0.4037	0.3121	0.3561	0.3561	0.3561
1.1684	12.0	696	1.8947	0.2724	0.3258	0.3168	0.2707	0.3258	0.3138	0.2793	0.3258	0.3258	0.3258
1.3507	13.0	754	1.9123	0.3161	0.3636	0.3651	0.3271	0.3636	0.3832	0.3189	0.3636	0.3636	0.3636
1.1413	14.0	812	1.9088	0.3210	0.3788	0.3659	0.3221	0.3788	0.3622	0.3287	0.3788	0.3788	0.3788
1.2466	15.0	870	2.0905	0.3428	0.4015	0.3831	0.3574	0.4015	0.4108	0.3649	0.4015	0.4015	0.4015
1.2063	16.0	928	2.2063	0.3331	0.3864	0.3746	0.3376	0.3864	0.3775	0.3418	0.3864	0.3864	0.3864
0.25	17.0	986	2.1276	0.3909	0.4242	0.4287	0.4100	0.4242	0.4593	0.3942	0.4242	0.4242	0.4242
0.3857	18.0	1044	2.3733	0.3631	0.4242	0.4119	0.3618	0.4242	0.4050	0.3701	0.4242	0.4242	0.4242
0.0546	19.0	1102	2.4860	0.3277	0.3864	0.3769	0.3432	0.3864	0.3902	0.3345	0.3864	0.3864	0.3864
0.0621	20.0	1160	2.5209	0.3879	0.4242	0.4119	0.4393	0.4242	0.4335	0.3850	0.4242	0.4242	0.4242
0.1491	21.0	1218	2.7192	0.3713	0.4242	0.4142	0.3740	0.4242	0.4124	0.3777	0.4242	0.4242	0.4242
0.4118	22.0	1276	2.9182	0.3327	0.3864	0.3752	0.3317	0.3864	0.3734	0.3427	0.3864	0.3864	0.3864
0.1833	23.0	1334	2.9567	0.3204	0.3636	0.3580	0.3325	0.3636	0.3805	0.3318	0.3636	0.3636	0.3636
0.0022	24.0	1392	3.0022	0.3432	0.4015	0.3824	0.3452	0.4015	0.3877	0.3643	0.4015	0.4015	0.4015
0.2174	25.0	1450	3.0656	0.3537	0.3864	0.3803	0.3574	0.3864	0.3796	0.3568	0.3864	0.3864	0.3864
0.0191	26.0	1508	3.1698	0.3451	0.4091	0.3920	0.3502	0.4091	0.3992	0.3627	0.4091	0.4091	0.4091
0.0051	27.0	1566	3.3015	0.3389	0.4015	0.3816	0.3394	0.4015	0.3844	0.3566	0.4015	0.4015	0.4015
0.0205	28.0	1624	3.2677	0.3457	0.4091	0.3893	0.3422	0.4091	0.3864	0.3634	0.4091	0.4091	0.4091
0.0016	29.0	1682	3.1995	0.3385	0.3939	0.3810	0.3324	0.3939	0.3723	0.3479	0.3939	0.3939	0.3939
0.0011	30.0	1740	3.2359	0.3495	0.4091	0.3927	0.3409	0.4091	0.3823	0.3634	0.4091	0.4091	0.4091

Framework versions

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