square_run_second_vote_full_pic_75_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: 1.3432
• F1 Macro: 0.3328
• F1 Micro: 0.4697
• F1 Weighted: 0.4098
• Precision Macro: 0.3270
• Precision Micro: 0.4697
• Precision Weighted: 0.4161
• Recall Macro: 0.3849
• Recall Micro: 0.4697
• Recall Weighted: 0.4697
• Accuracy: 0.4697

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
1.874	1.0	58	1.8367	0.1624	0.2576	0.2032	0.1524	0.2576	0.1870	0.2024	0.2576	0.2576	0.2576
1.9776	2.0	116	1.9333	0.0771	0.1439	0.0881	0.0743	0.1439	0.0940	0.1402	0.1439	0.1439	0.1439
1.645	3.0	174	1.8058	0.1674	0.2803	0.1932	0.1766	0.2803	0.1880	0.2217	0.2803	0.2803	0.2803
1.6353	4.0	232	1.6974	0.2498	0.3636	0.2906	0.2124	0.3636	0.2464	0.3095	0.3636	0.3636	0.3636
1.6165	5.0	290	1.6144	0.2440	0.3409	0.2804	0.2940	0.3409	0.3290	0.2857	0.3409	0.3409	0.3409
1.7496	6.0	348	1.7440	0.2610	0.3636	0.3308	0.2845	0.3636	0.3528	0.2888	0.3636	0.3636	0.3636
1.8783	7.0	406	1.5126	0.3535	0.4167	0.3994	0.3637	0.4167	0.4048	0.3646	0.4167	0.4167	0.4167
1.2903	8.0	464	1.5240	0.3589	0.4167	0.4036	0.3702	0.4167	0.4107	0.3644	0.4167	0.4167	0.4167
1.8885	9.0	522	1.5423	0.3727	0.4470	0.4283	0.3800	0.4470	0.4329	0.3856	0.4470	0.4470	0.4470
1.0726	10.0	580	1.8002	0.3168	0.4015	0.3651	0.3364	0.4015	0.3788	0.3456	0.4015	0.4015	0.4015
1.2297	11.0	638	1.9532	0.3087	0.3788	0.3653	0.3752	0.3788	0.4335	0.3300	0.3788	0.3788	0.3788
0.7152	12.0	696	1.8452	0.3120	0.3864	0.3677	0.3922	0.3864	0.4313	0.3156	0.3864	0.3864	0.3864
0.7479	13.0	754	1.7619	0.3686	0.4394	0.4348	0.3981	0.4394	0.4546	0.3645	0.4394	0.4394	0.4394
0.2766	14.0	812	1.8000	0.3931	0.4924	0.4657	0.4146	0.4924	0.4792	0.4080	0.4924	0.4924	0.4924
0.4092	15.0	870	2.0428	0.3611	0.4318	0.4252	0.3772	0.4318	0.4421	0.3673	0.4318	0.4318	0.4318
0.1272	16.0	928	2.1450	0.3493	0.4242	0.4203	0.3651	0.4242	0.4419	0.3598	0.4242	0.4242	0.4242
0.2751	17.0	986	2.3002	0.3782	0.4394	0.4357	0.4548	0.4394	0.5101	0.3712	0.4394	0.4394	0.4394
0.3277	18.0	1044	2.2109	0.3832	0.4470	0.4450	0.4073	0.4470	0.4770	0.3856	0.4470	0.4470	0.4470
0.0134	19.0	1102	2.4450	0.3585	0.4470	0.4219	0.3987	0.4470	0.4533	0.3729	0.4470	0.4470	0.4470
0.0737	20.0	1160	2.5434	0.3468	0.4091	0.4054	0.3581	0.4091	0.4161	0.3508	0.4091	0.4091	0.4091
0.0203	21.0	1218	2.8118	0.3895	0.4773	0.4493	0.4176	0.4773	0.4699	0.4098	0.4773	0.4773	0.4773
0.0072	22.0	1276	2.7996	0.3620	0.4242	0.4165	0.3783	0.4242	0.4359	0.3729	0.4242	0.4242	0.4242
0.1251	23.0	1334	2.9001	0.4009	0.4394	0.4291	0.4500	0.4394	0.4703	0.4067	0.4394	0.4394	0.4394
0.0054	24.0	1392	2.8660	0.4011	0.4470	0.4327	0.4245	0.4470	0.4535	0.4147	0.4470	0.4470	0.4470
0.0091	25.0	1450	2.8868	0.3852	0.4167	0.4086	0.3965	0.4167	0.4115	0.3858	0.4167	0.4167	0.4167
0.002	26.0	1508	2.9311	0.3952	0.4394	0.4272	0.4054	0.4394	0.4343	0.4043	0.4394	0.4394	0.4394
0.0008	27.0	1566	2.9526	0.4052	0.4470	0.4388	0.4173	0.4470	0.4483	0.4118	0.4470	0.4470	0.4470
0.002	28.0	1624	3.0159	0.4074	0.4470	0.4389	0.4227	0.4470	0.4489	0.4116	0.4470	0.4470	0.4470
0.0017	29.0	1682	2.9797	0.4121	0.4545	0.4431	0.4192	0.4545	0.4464	0.4193	0.4545	0.4545	0.4545
0.0016	30.0	1740	2.9981	0.3677	0.4394	0.4256	0.3741	0.4394	0.4271	0.3761	0.4394	0.4394	0.4394

Framework versions

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