square_run_second_vote_full_pic_75

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: 1.4672
• F1 Macro: 0.3451
• F1 Micro: 0.4545
• F1 Weighted: 0.4226
• Precision Macro: 0.3766
• Precision Micro: 0.4545
• Precision Weighted: 0.4564
• Recall Macro: 0.3721
• Recall Micro: 0.4545
• Recall Weighted: 0.4545
• Accuracy: 0.4545

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
1.7944	1.0	58	1.8560	0.1268	0.2424	0.1788	0.1005	0.2424	0.1425	0.1734	0.2424	0.2424	0.2424
1.8983	2.0	116	1.8865	0.1533	0.2197	0.1705	0.1708	0.2197	0.1813	0.1858	0.2197	0.2197	0.2197
1.4428	3.0	174	1.8035	0.2270	0.3030	0.2733	0.2740	0.3030	0.3193	0.2427	0.3030	0.3030	0.3030
1.5854	4.0	232	1.7041	0.2293	0.3333	0.2630	0.2292	0.3333	0.2516	0.2763	0.3333	0.3333	0.3333
1.644	5.0	290	1.6834	0.2759	0.4242	0.3362	0.2453	0.4242	0.3082	0.3601	0.4242	0.4242	0.4242
1.7673	6.0	348	1.7508	0.2257	0.3333	0.2896	0.2153	0.3333	0.2776	0.2611	0.3333	0.3333	0.3333
1.8791	7.0	406	1.6072	0.3200	0.4167	0.3759	0.3171	0.4167	0.3666	0.3494	0.4167	0.4167	0.4167
1.3323	8.0	464	1.6554	0.3265	0.4015	0.3794	0.3576	0.4015	0.4045	0.3323	0.4015	0.4015	0.4015
1.7047	9.0	522	1.7295	0.3186	0.3864	0.3716	0.3364	0.3864	0.3884	0.3275	0.3864	0.3864	0.3864
1.1897	10.0	580	1.7238	0.2782	0.3561	0.3224	0.2981	0.3561	0.3401	0.3110	0.3561	0.3561	0.3561
0.8908	11.0	638	2.1481	0.2774	0.3333	0.3266	0.3840	0.3333	0.4285	0.2900	0.3333	0.3333	0.3333
0.4492	12.0	696	1.9300	0.2862	0.3636	0.3330	0.3623	0.3636	0.3947	0.2959	0.3636	0.3636	0.3636
0.6555	13.0	754	1.8931	0.3053	0.3788	0.3670	0.3329	0.3788	0.3854	0.3084	0.3788	0.3788	0.3788
0.3586	14.0	812	2.0316	0.3475	0.4242	0.4103	0.3722	0.4242	0.4360	0.3616	0.4242	0.4242	0.4242
0.6805	15.0	870	2.0638	0.3389	0.4091	0.3917	0.3613	0.4091	0.4150	0.3572	0.4091	0.4091	0.4091
0.8902	16.0	928	2.2817	0.2992	0.3636	0.3466	0.3388	0.3636	0.4092	0.3156	0.3636	0.3636	0.3636
0.3393	17.0	986	2.4104	0.3031	0.3485	0.3527	0.3116	0.3485	0.3658	0.3015	0.3485	0.3485	0.3485
0.2469	18.0	1044	2.4341	0.3373	0.3939	0.3980	0.3472	0.3939	0.4130	0.3381	0.3939	0.3939	0.3939
0.0485	19.0	1102	2.5798	0.3454	0.4015	0.3908	0.3639	0.4015	0.4075	0.3545	0.4015	0.4015	0.4015
0.0693	20.0	1160	2.4961	0.3781	0.4470	0.4350	0.4173	0.4470	0.4664	0.3837	0.4470	0.4470	0.4470
0.0095	21.0	1218	2.7183	0.3840	0.4621	0.4510	0.4268	0.4621	0.4916	0.3868	0.4621	0.4621	0.4621
0.0078	22.0	1276	2.7620	0.3520	0.4091	0.4091	0.3617	0.4091	0.4199	0.3528	0.4091	0.4091	0.4091
0.0083	23.0	1334	2.8349	0.3507	0.4167	0.4058	0.3826	0.4167	0.4324	0.3560	0.4167	0.4167	0.4167
0.0024	24.0	1392	2.7839	0.3630	0.4167	0.4169	0.4041	0.4167	0.4515	0.3594	0.4167	0.4167	0.4167
0.0107	25.0	1450	2.8616	0.3600	0.4242	0.4212	0.3597	0.4242	0.4236	0.3653	0.4242	0.4242	0.4242
0.0014	26.0	1508	2.9104	0.3790	0.4394	0.4343	0.3870	0.4394	0.4386	0.3810	0.4394	0.4394	0.4394
0.0021	27.0	1566	2.9763	0.3778	0.4394	0.4342	0.3989	0.4394	0.4515	0.3785	0.4394	0.4394	0.4394
0.0106	28.0	1624	2.9525	0.3866	0.4545	0.4479	0.3957	0.4545	0.4533	0.3892	0.4545	0.4545	0.4545
0.0044	29.0	1682	2.9417	0.3862	0.4545	0.4438	0.3911	0.4545	0.4447	0.3930	0.4545	0.4545	0.4545
0.0019	30.0	1740	2.9399	0.3876	0.4545	0.4461	0.3937	0.4545	0.4485	0.3928	0.4545	0.4545	0.4545

Framework versions

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