square_run_first_vote_full_pic_50

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: 1.8395
• F1 Macro: 0.2931
• F1 Micro: 0.3182
• F1 Weighted: 0.3126
• Precision Macro: 0.3510
• Precision Micro: 0.3182
• Precision Weighted: 0.3702
• Recall Macro: 0.2978
• 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
1.9357	1.0	58	1.9251	0.1142	0.2045	0.1326	0.2916	0.2045	0.3719	0.1805	0.2045	0.2045	0.2045
1.8428	2.0	116	1.9975	0.0864	0.1894	0.0941	0.0690	0.1894	0.0756	0.1762	0.1894	0.1894	0.1894
1.8324	3.0	174	1.8298	0.1725	0.2727	0.2132	0.1532	0.2727	0.1894	0.2191	0.2727	0.2727	0.2727
1.5574	4.0	232	1.7557	0.1128	0.2652	0.1548	0.0798	0.2652	0.1095	0.1928	0.2652	0.2652	0.2652
1.9434	5.0	290	1.7244	0.3019	0.3939	0.3572	0.2839	0.3939	0.3404	0.3375	0.3939	0.3939	0.3939
1.9357	6.0	348	1.6611	0.3208	0.3712	0.3669	0.3285	0.3712	0.3749	0.3253	0.3712	0.3712	0.3712
1.8454	7.0	406	1.6835	0.3043	0.3939	0.3397	0.3472	0.3939	0.3939	0.3515	0.3939	0.3939	0.3939
1.7616	8.0	464	1.8893	0.2312	0.2803	0.2544	0.3179	0.2803	0.3702	0.2728	0.2803	0.2803	0.2803
1.5512	9.0	522	1.7856	0.2366	0.3182	0.2696	0.2788	0.3182	0.3172	0.2820	0.3182	0.3182	0.3182
1.777	10.0	580	1.9182	0.3136	0.3864	0.3465	0.3176	0.3864	0.3434	0.3525	0.3864	0.3864	0.3864
1.3075	11.0	638	1.7205	0.3324	0.3939	0.3795	0.3461	0.3939	0.3893	0.3407	0.3939	0.3939	0.3939
0.8476	12.0	696	1.8083	0.3203	0.3788	0.3495	0.3297	0.3788	0.3672	0.3581	0.3788	0.3788	0.3788
1.0324	13.0	754	1.9825	0.3046	0.3485	0.3341	0.3316	0.3485	0.3807	0.3315	0.3485	0.3485	0.3485
1.154	14.0	812	2.0418	0.2869	0.3333	0.3151	0.2847	0.3333	0.3140	0.3064	0.3333	0.3333	0.3333
0.5406	15.0	870	2.1651	0.3242	0.3561	0.3453	0.3366	0.3561	0.3561	0.3313	0.3561	0.3561	0.3561
1.5052	16.0	928	2.3796	0.2814	0.3561	0.3228	0.3189	0.3561	0.3611	0.3127	0.3561	0.3561	0.3561
0.1641	17.0	986	2.2210	0.3286	0.3864	0.3741	0.3346	0.3864	0.3768	0.3361	0.3864	0.3864	0.3864
0.1201	18.0	1044	2.2744	0.3384	0.3939	0.3852	0.3331	0.3939	0.3811	0.3474	0.3939	0.3939	0.3939
0.1059	19.0	1102	2.4881	0.3198	0.3712	0.3485	0.3702	0.3712	0.3640	0.3244	0.3712	0.3712	0.3712
0.0828	20.0	1160	2.6911	0.3369	0.4091	0.3897	0.3378	0.4091	0.3826	0.3473	0.4091	0.4091	0.4091
0.0903	21.0	1218	2.9249	0.3351	0.3561	0.3564	0.3430	0.3561	0.3614	0.3341	0.3561	0.3561	0.3561
0.0455	22.0	1276	3.1538	0.2830	0.3409	0.3261	0.2951	0.3409	0.3330	0.2889	0.3409	0.3409	0.3409
0.0137	23.0	1334	3.0196	0.3147	0.3712	0.3598	0.3095	0.3712	0.3530	0.3246	0.3712	0.3712	0.3712
0.0088	24.0	1392	3.0033	0.3512	0.4015	0.3958	0.3562	0.4015	0.4024	0.3586	0.4015	0.4015	0.4015
0.205	25.0	1450	3.1499	0.3854	0.4091	0.3978	0.3923	0.4091	0.4032	0.3939	0.4091	0.4091	0.4091
0.0072	26.0	1508	3.2906	0.3440	0.3712	0.3651	0.3438	0.3712	0.3663	0.3516	0.3712	0.3712	0.3712
0.0019	27.0	1566	3.3223	0.3542	0.3712	0.3663	0.3524	0.3712	0.3673	0.3627	0.3712	0.3712	0.3712
0.0043	28.0	1624	3.2986	0.3729	0.3864	0.3840	0.3726	0.3864	0.3838	0.3753	0.3864	0.3864	0.3864
0.0016	29.0	1682	3.3453	0.3469	0.3788	0.3741	0.3504	0.3788	0.3744	0.3483	0.3788	0.3788	0.3788
0.0031	30.0	1740	3.3308	0.3465	0.3788	0.3753	0.3514	0.3788	0.3760	0.3456	0.3788	0.3788	0.3788

Framework versions

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