squarerun2

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4284
• F1 Macro: 0.4676
• F1 Micro: 0.5606
• F1 Weighted: 0.5361
• Precision Macro: 0.4718
• Precision Micro: 0.5606
• Precision Weighted: 0.5334
• Recall Macro: 0.4835
• Recall Micro: 0.5606
• Recall Weighted: 0.5606
• Accuracy: 0.5606

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: 20

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
1.9016	1.0	29	1.8764	0.1011	0.2424	0.1401	0.0721	0.2424	0.1001	0.1761	0.2424	0.2424	0.2424
1.8787	2.0	58	1.8750	0.0485	0.2045	0.0695	0.0292	0.2045	0.0418	0.1429	0.2045	0.2045	0.2045
1.9345	3.0	87	1.8624	0.0485	0.2045	0.0695	0.0292	0.2045	0.0418	0.1429	0.2045	0.2045	0.2045
1.6663	4.0	116	1.7239	0.2230	0.3561	0.2738	0.3173	0.3561	0.3549	0.2725	0.3561	0.3561	0.3561
1.3847	5.0	145	1.4880	0.3420	0.4697	0.4038	0.4521	0.4697	0.4846	0.3893	0.4697	0.4697	0.4697
1.6559	6.0	174	1.4056	0.3479	0.4773	0.4108	0.3865	0.4773	0.4276	0.3870	0.4773	0.4773	0.4773
1.335	7.0	203	1.3768	0.3875	0.5152	0.4527	0.3933	0.5152	0.4447	0.4265	0.5152	0.5152	0.5152
1.2514	8.0	232	1.2345	0.4536	0.5606	0.5207	0.4701	0.5606	0.5257	0.4766	0.5606	0.5606	0.5606
0.6979	9.0	261	1.1501	0.5305	0.6364	0.6097	0.5491	0.6364	0.6127	0.5391	0.6364	0.6364	0.6364
1.0417	10.0	290	1.1654	0.5206	0.6136	0.5900	0.5215	0.6136	0.5935	0.5464	0.6136	0.6136	0.6136
0.7314	11.0	319	1.1566	0.5376	0.6212	0.6109	0.5387	0.6212	0.6154	0.5514	0.6212	0.6212	0.6212
0.7902	12.0	348	1.1624	0.5397	0.6212	0.6140	0.5422	0.6212	0.6209	0.5505	0.6212	0.6212	0.6212
0.7503	13.0	377	1.1359	0.5377	0.6288	0.6126	0.5472	0.6288	0.6143	0.5455	0.6288	0.6288	0.6288
0.586	14.0	406	1.1512	0.5441	0.6288	0.6141	0.5361	0.6288	0.6033	0.5557	0.6288	0.6288	0.6288
0.6869	15.0	435	1.1306	0.5323	0.6288	0.6117	0.5270	0.6288	0.6043	0.5475	0.6288	0.6288	0.6288
0.5498	16.0	464	1.1293	0.5373	0.6288	0.6117	0.5353	0.6288	0.6039	0.5471	0.6288	0.6288	0.6288
0.5037	17.0	493	1.1635	0.5290	0.6212	0.6005	0.5374	0.6212	0.6022	0.5398	0.6212	0.6212	0.6212
0.3624	18.0	522	1.0994	0.5700	0.6591	0.6414	0.5815	0.6591	0.6409	0.5743	0.6591	0.6591	0.6591
0.3387	19.0	551	1.0944	0.5643	0.6515	0.6367	0.5556	0.6515	0.6268	0.5781	0.6515	0.6515	0.6515
0.4052	20.0	580	1.0934	0.5683	0.6591	0.6432	0.5681	0.6591	0.6393	0.5798	0.6591	0.6591	0.6591

Framework versions

• Transformers 4.48.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0