squarerun_large_model

This model is a fine-tuned version of google/vit-large-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.5150
• F1 Macro: 0.4837
• F1 Micro: 0.5909
• F1 Weighted: 0.5569
• Precision Macro: 0.5183
• Precision Micro: 0.5909
• Precision Weighted: 0.5764
• Recall Macro: 0.5013
• Recall Micro: 0.5909
• Recall Weighted: 0.5909
• Accuracy: 0.5909

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 25

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
1.917	1.0	29	1.9115	0.1066	0.2197	0.1273	0.0780	0.2197	0.0923	0.1832	0.2197	0.2197	0.2197
1.6762	2.0	58	1.6722	0.2733	0.3561	0.3005	0.3141	0.3561	0.3684	0.3355	0.3561	0.3561	0.3561
1.9664	3.0	87	1.5057	0.3554	0.4545	0.4060	0.3734	0.4545	0.4129	0.3857	0.4545	0.4545	0.4545
1.1934	4.0	116	1.4217	0.3130	0.4091	0.3530	0.3414	0.4091	0.3818	0.3629	0.4091	0.4091	0.4091
1.0968	5.0	145	1.1879	0.4608	0.5758	0.5258	0.4807	0.5758	0.5438	0.5045	0.5758	0.5758	0.5758
1.1313	6.0	174	1.2307	0.4964	0.5530	0.5243	0.5850	0.5530	0.6114	0.5196	0.5530	0.5530	0.5530
1.0807	7.0	203	1.2771	0.4088	0.5303	0.4772	0.5393	0.5303	0.5816	0.4304	0.5303	0.5303	0.5303
1.1825	8.0	232	1.2339	0.4528	0.5682	0.5175	0.5544	0.5682	0.6169	0.4920	0.5682	0.5682	0.5682
0.4454	9.0	261	1.0474	0.6064	0.6970	0.6763	0.6334	0.6970	0.6868	0.6100	0.6970	0.6970	0.6970
0.5439	10.0	290	1.6815	0.4580	0.5152	0.4920	0.5394	0.5152	0.5951	0.4903	0.5152	0.5152	0.5152
0.4256	11.0	319	1.1378	0.5800	0.6667	0.6495	0.5801	0.6667	0.6435	0.5907	0.6667	0.6667	0.6667
0.4968	12.0	348	1.4229	0.5307	0.6136	0.6013	0.5348	0.6136	0.6095	0.5486	0.6136	0.6136	0.6136
0.3408	13.0	377	1.4445	0.5426	0.6288	0.6095	0.5559	0.6288	0.6307	0.5621	0.6288	0.6288	0.6288
0.2914	14.0	406	1.4277	0.6009	0.6515	0.6470	0.7068	0.6515	0.6868	0.5958	0.6515	0.6515	0.6515
0.2003	15.0	435	1.5517	0.5770	0.6288	0.6296	0.5890	0.6288	0.6475	0.5792	0.6288	0.6288	0.6288
0.0871	16.0	464	1.4812	0.5702	0.6515	0.6407	0.5777	0.6515	0.6491	0.5785	0.6515	0.6515	0.6515
0.0352	17.0	493	2.1052	0.5007	0.5985	0.5744	0.5466	0.5985	0.6130	0.5127	0.5985	0.5985	0.5985
0.0101	18.0	522	1.9978	0.5725	0.6212	0.6223	0.6152	0.6212	0.6559	0.5672	0.6212	0.6212	0.6212
0.0035	19.0	551	2.0304	0.5880	0.6439	0.6388	0.6698	0.6439	0.6936	0.5805	0.6439	0.6439	0.6439
0.0013	20.0	580	2.1374	0.5514	0.6364	0.6224	0.6025	0.6364	0.6765	0.5685	0.6364	0.6364	0.6364
0.0589	21.0	609	1.7676	0.5879	0.6439	0.6396	0.5940	0.6439	0.6407	0.5889	0.6439	0.6439	0.6439
0.0263	22.0	638	1.8416	0.5785	0.6439	0.6327	0.6016	0.6439	0.6454	0.5758	0.6439	0.6439	0.6439
0.0028	23.0	667	1.9843	0.6068	0.6667	0.6569	0.6631	0.6667	0.6882	0.6069	0.6667	0.6667	0.6667
0.0006	24.0	696	1.9432	0.6157	0.6742	0.6655	0.6603	0.6742	0.6853	0.6152	0.6742	0.6742	0.6742
0.0004	25.0	725	1.9346	0.6089	0.6667	0.6569	0.6548	0.6667	0.6763	0.6073	0.6667	0.6667	0.6667

Framework versions

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