square_run_with_actual_16_batch_size

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: 1.2489
• F1 Macro: 0.5325
• F1 Micro: 0.6212
• F1 Weighted: 0.6021
• Precision Macro: 0.5262
• Precision Micro: 0.6212
• Precision Weighted: 0.5980
• Recall Macro: 0.5529
• Recall Micro: 0.6212
• Recall Weighted: 0.6212
• Accuracy: 0.6212

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 35

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
1.9666	1.0	15	1.9122	0.0522	0.1818	0.0701	0.0544	0.1818	0.0752	0.1367	0.1818	0.1818	0.1818
1.3456	2.0	30	1.8989	0.1141	0.2045	0.1357	0.0978	0.2045	0.1212	0.1792	0.2045	0.2045	0.2045
1.8934	3.0	45	1.8013	0.1472	0.25	0.1719	0.2585	0.25	0.3007	0.1956	0.25	0.25	0.25
1.0877	4.0	60	1.5598	0.3297	0.3864	0.3581	0.3466	0.3864	0.3737	0.3502	0.3864	0.3864	0.3864
1.2233	5.0	75	1.4987	0.3442	0.4318	0.3877	0.4069	0.4318	0.4401	0.3723	0.4318	0.4318	0.4318
1.0714	6.0	90	1.4548	0.3909	0.4848	0.4447	0.4532	0.4848	0.5043	0.4156	0.4848	0.4848	0.4848
1.0008	7.0	105	1.3781	0.4699	0.5455	0.5277	0.4927	0.5455	0.5384	0.4728	0.5455	0.5455	0.5455
0.8822	8.0	120	1.4939	0.4440	0.5076	0.4959	0.4501	0.5076	0.5066	0.4594	0.5076	0.5076	0.5076
0.6024	9.0	135	1.2516	0.4922	0.5682	0.5559	0.4841	0.5682	0.5477	0.5037	0.5682	0.5682	0.5682
0.2719	10.0	150	1.4020	0.4582	0.5455	0.5177	0.4610	0.5455	0.5195	0.4821	0.5455	0.5455	0.5455
0.2165	11.0	165	1.4121	0.4974	0.5758	0.5601	0.4906	0.5758	0.5530	0.5121	0.5758	0.5758	0.5758
0.2752	12.0	180	1.4315	0.5750	0.5909	0.5923	0.6618	0.5909	0.6319	0.5545	0.5909	0.5909	0.5909
0.4386	13.0	195	1.4823	0.5170	0.5606	0.5607	0.5515	0.5606	0.5955	0.5150	0.5606	0.5606	0.5606
0.2152	14.0	210	1.4962	0.5371	0.5833	0.5795	0.5796	0.5833	0.6003	0.5334	0.5833	0.5833	0.5833
0.2021	15.0	225	1.5027	0.4698	0.5606	0.5383	0.4781	0.5606	0.5353	0.4829	0.5606	0.5606	0.5606
0.1147	16.0	240	1.5977	0.4771	0.5606	0.5447	0.4901	0.5606	0.5638	0.4976	0.5606	0.5606	0.5606
0.0648	17.0	255	1.6214	0.4894	0.5682	0.5551	0.4829	0.5682	0.5474	0.5009	0.5682	0.5682	0.5682
0.0958	18.0	270	1.6267	0.4911	0.5379	0.5332	0.5140	0.5379	0.5539	0.4899	0.5379	0.5379	0.5379
0.0468	19.0	285	1.6385	0.5462	0.6061	0.5975	0.5685	0.6061	0.6104	0.5458	0.6061	0.6061	0.6061
0.0344	20.0	300	1.7048	0.5815	0.6136	0.6076	0.6000	0.6136	0.6225	0.5844	0.6136	0.6136	0.6136
0.1686	21.0	315	1.8050	0.5545	0.6061	0.5975	0.5939	0.6061	0.6116	0.5538	0.6061	0.6061	0.6061
0.044	22.0	330	1.7228	0.5362	0.5909	0.5779	0.5746	0.5909	0.5894	0.5380	0.5909	0.5909	0.5909
0.0185	23.0	345	1.9158	0.5024	0.6061	0.5756	0.5249	0.6061	0.6034	0.5363	0.6061	0.6061	0.6061
0.0065	24.0	360	1.7524	0.5881	0.6212	0.6111	0.6132	0.6212	0.6234	0.5850	0.6212	0.6212	0.6212
0.1169	25.0	375	1.7258	0.5801	0.6364	0.6246	0.6131	0.6364	0.6282	0.5780	0.6364	0.6364	0.6364
0.0092	26.0	390	1.8467	0.5427	0.5985	0.5849	0.5862	0.5985	0.5954	0.5379	0.5985	0.5985	0.5985
0.0286	27.0	405	1.8018	0.5670	0.6212	0.6108	0.6027	0.6212	0.6171	0.5636	0.6212	0.6212	0.6212
0.0263	28.0	420	1.8319	0.5621	0.6212	0.6079	0.5969	0.6212	0.6121	0.5598	0.6212	0.6212	0.6212
0.0049	29.0	435	1.8276	0.5637	0.6136	0.6066	0.5962	0.6136	0.6099	0.5574	0.6136	0.6136	0.6136
0.0039	30.0	450	1.8631	0.5480	0.5985	0.5900	0.5879	0.5985	0.5988	0.5405	0.5985	0.5985	0.5985
0.0636	31.0	465	1.8579	0.5697	0.6212	0.6118	0.6075	0.6212	0.6181	0.5629	0.6212	0.6212	0.6212
0.0023	32.0	480	1.8398	0.5773	0.6288	0.6204	0.6144	0.6288	0.6265	0.57	0.6288	0.6288	0.6288
0.0028	32.6897	490	1.8415	0.5773	0.6288	0.6204	0.6144	0.6288	0.6265	0.57	0.6288	0.6288	0.6288

Framework versions

• Transformers 4.48.2
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0