smids_5x_beit_base_adamax_00001_fold3

This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.7903
• Accuracy: 0.9133

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2779	1.0	375	0.3054	0.8733
0.2162	2.0	750	0.2359	0.92
0.1285	3.0	1125	0.2539	0.9217
0.0945	4.0	1500	0.2722	0.9233
0.101	5.0	1875	0.3077	0.92
0.0634	6.0	2250	0.3559	0.915
0.0294	7.0	2625	0.3959	0.9167
0.0374	8.0	3000	0.4694	0.9117
0.0228	9.0	3375	0.4761	0.9217
0.0104	10.0	3750	0.5190	0.925
0.0112	11.0	4125	0.5753	0.9183
0.0112	12.0	4500	0.5854	0.92
0.0095	13.0	4875	0.6151	0.9117
0.015	14.0	5250	0.6292	0.91
0.0156	15.0	5625	0.6403	0.9167
0.0162	16.0	6000	0.6509	0.9183
0.0041	17.0	6375	0.6568	0.9183
0.0184	18.0	6750	0.6884	0.915
0.0009	19.0	7125	0.7500	0.9083
0.0067	20.0	7500	0.7058	0.9183
0.0003	21.0	7875	0.6969	0.915
0.0024	22.0	8250	0.7459	0.915
0.0561	23.0	8625	0.6852	0.9183
0.0018	24.0	9000	0.6779	0.9233
0.0005	25.0	9375	0.7388	0.9183
0.0019	26.0	9750	0.7333	0.9217
0.0279	27.0	10125	0.7591	0.9133
0.0247	28.0	10500	0.7516	0.92
0.0017	29.0	10875	0.7698	0.9183
0.0267	30.0	11250	0.7550	0.9183
0.0002	31.0	11625	0.7870	0.9167
0.0313	32.0	12000	0.7814	0.9133
0.0004	33.0	12375	0.7692	0.915
0.0293	34.0	12750	0.7888	0.915
0.0001	35.0	13125	0.7707	0.915
0.0004	36.0	13500	0.7961	0.915
0.0001	37.0	13875	0.7594	0.9133
0.0	38.0	14250	0.7716	0.92
0.0004	39.0	14625	0.7795	0.92
0.0058	40.0	15000	0.7828	0.915
0.0005	41.0	15375	0.7680	0.9117
0.0001	42.0	15750	0.7737	0.915
0.0001	43.0	16125	0.7805	0.915
0.003	44.0	16500	0.7912	0.915
0.0003	45.0	16875	0.7859	0.9167
0.0104	46.0	17250	0.7879	0.9167
0.0006	47.0	17625	0.7848	0.915
0.0	48.0	18000	0.7845	0.915
0.0	49.0	18375	0.7887	0.915
0.0	50.0	18750	0.7903	0.9133

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2