square_run_first_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: 1.7586
• F1 Macro: 0.4234
• F1 Micro: 0.5152
• F1 Weighted: 0.4789
• Precision Macro: 0.4562
• Precision Micro: 0.5152
• Precision Weighted: 0.5061
• Recall Macro: 0.4488
• Recall Micro: 0.5152
• Recall Weighted: 0.5152
• Accuracy: 0.5152

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
1.9675	1.0	58	1.9322	0.1051	0.1894	0.1204	0.1047	0.1894	0.1191	0.1661	0.1894	0.1894	0.1894
1.8921	2.0	116	1.9534	0.0786	0.1818	0.0855	0.0551	0.1818	0.0597	0.1656	0.1818	0.1818	0.1818
1.9081	3.0	174	1.8370	0.1526	0.2803	0.1976	0.1283	0.2803	0.1642	0.2117	0.2803	0.2803	0.2803
1.5193	4.0	232	1.7240	0.1963	0.3258	0.2445	0.2948	0.3258	0.3289	0.2476	0.3258	0.3258	0.3258
1.7743	5.0	290	1.5478	0.3382	0.4318	0.3920	0.3494	0.4318	0.4204	0.3837	0.4318	0.4318	0.4318
1.9879	6.0	348	1.5070	0.3157	0.4470	0.3865	0.4597	0.4470	0.5200	0.3499	0.4470	0.4470	0.4470
1.9096	7.0	406	1.4281	0.3859	0.4545	0.4410	0.4248	0.4545	0.4763	0.3931	0.4545	0.4545	0.4545
1.4577	8.0	464	1.4558	0.3862	0.4773	0.4381	0.3827	0.4773	0.4425	0.4346	0.4773	0.4773	0.4773
1.9664	9.0	522	1.5863	0.3757	0.4773	0.4227	0.3967	0.4773	0.4530	0.4288	0.4773	0.4773	0.4773
0.7655	10.0	580	1.3785	0.4015	0.5	0.4621	0.5175	0.5	0.5866	0.4427	0.5	0.5	0.5
0.707	11.0	638	1.3441	0.4772	0.5530	0.5356	0.4915	0.5530	0.5453	0.4861	0.5530	0.5530	0.5530
0.782	12.0	696	1.3983	0.4716	0.5530	0.5325	0.4860	0.5530	0.5432	0.4877	0.5530	0.5530	0.5530
0.7316	13.0	754	1.6155	0.4880	0.5530	0.5497	0.5085	0.5530	0.5892	0.5080	0.5530	0.5530	0.5530
1.0819	14.0	812	1.4869	0.4936	0.5379	0.5312	0.5124	0.5379	0.5370	0.4900	0.5379	0.5379	0.5379
0.8757	15.0	870	1.6936	0.4741	0.5303	0.5300	0.4809	0.5303	0.5481	0.4847	0.5303	0.5303	0.5303
0.7228	16.0	928	1.7370	0.4442	0.5227	0.4986	0.4401	0.5227	0.4939	0.4646	0.5227	0.5227	0.5227
0.3016	17.0	986	1.6977	0.5279	0.5682	0.5642	0.6353	0.5682	0.5994	0.5176	0.5682	0.5682	0.5682
0.2097	18.0	1044	1.9026	0.4769	0.5606	0.5414	0.5384	0.5606	0.5783	0.4819	0.5606	0.5606	0.5606
0.0388	19.0	1102	1.8276	0.5259	0.6136	0.5981	0.5252	0.6136	0.5945	0.5382	0.6136	0.6136	0.6136
0.4837	20.0	1160	1.8658	0.5336	0.5985	0.5863	0.5502	0.5985	0.5866	0.5342	0.5985	0.5985	0.5985
0.1531	21.0	1218	2.0415	0.4703	0.5606	0.5384	0.4917	0.5606	0.5489	0.4762	0.5606	0.5606	0.5606
0.0142	22.0	1276	2.0812	0.4969	0.5303	0.5260	0.5067	0.5303	0.5364	0.5008	0.5303	0.5303	0.5303
0.0036	23.0	1334	2.0662	0.5315	0.5758	0.5781	0.5480	0.5758	0.5925	0.5316	0.5758	0.5758	0.5758
0.0065	24.0	1392	2.1023	0.5090	0.5606	0.5516	0.5140	0.5606	0.5550	0.5154	0.5606	0.5606	0.5606
0.1359	25.0	1450	2.0555	0.4994	0.5455	0.5440	0.5018	0.5455	0.5474	0.5021	0.5455	0.5455	0.5455
0.0037	26.0	1508	2.1745	0.5206	0.5758	0.5691	0.5289	0.5758	0.5695	0.5204	0.5758	0.5758	0.5758
0.0391	27.0	1566	2.2087	0.5204	0.5758	0.5676	0.5335	0.5758	0.5745	0.5228	0.5758	0.5758	0.5758
0.0017	28.0	1624	2.1219	0.5178	0.5682	0.5633	0.5218	0.5682	0.5649	0.5212	0.5682	0.5682	0.5682
0.0015	29.0	1682	2.1455	0.5198	0.5682	0.5618	0.5342	0.5682	0.5641	0.5190	0.5682	0.5682	0.5682
0.0015	30.0	1740	2.1308	0.5192	0.5682	0.5617	0.5315	0.5682	0.5621	0.5190	0.5682	0.5682	0.5682

Framework versions

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