smids_5x_deit_base_adamax_001_fold2

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

• Loss: 1.1252
• Accuracy: 0.8852

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: 0.001
• 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
0.3593	1.0	375	0.2868	0.8902
0.3012	2.0	750	0.2473	0.9085
0.3836	3.0	1125	0.3500	0.8619
0.1484	4.0	1500	0.3561	0.8819
0.142	5.0	1875	0.3496	0.8619
0.1054	6.0	2250	0.5030	0.8519
0.1132	7.0	2625	0.4021	0.8769
0.0387	8.0	3000	0.5600	0.8752
0.0412	9.0	3375	0.4804	0.8935
0.049	10.0	3750	0.4670	0.8902
0.0223	11.0	4125	0.5161	0.8852
0.0227	12.0	4500	0.5268	0.8802
0.029	13.0	4875	0.5511	0.8819
0.0101	14.0	5250	0.5655	0.8935
0.0239	15.0	5625	0.5903	0.8885
0.0204	16.0	6000	0.6826	0.8869
0.0387	17.0	6375	0.6581	0.8835
0.0045	18.0	6750	0.5940	0.8869
0.0004	19.0	7125	0.7563	0.8885
0.0271	20.0	7500	0.5791	0.9035
0.0211	21.0	7875	0.5981	0.8869
0.0086	22.0	8250	0.6990	0.8869
0.0146	23.0	8625	0.6527	0.8935
0.0006	24.0	9000	0.5903	0.8885
0.02	25.0	9375	0.6548	0.8952
0.0007	26.0	9750	0.7230	0.8952
0.0	27.0	10125	0.7646	0.9002
0.0	28.0	10500	0.8095	0.8852
0.0	29.0	10875	0.8926	0.8835
0.0	30.0	11250	0.8629	0.8819
0.0041	31.0	11625	0.8782	0.8819
0.0047	32.0	12000	0.8948	0.8819
0.0063	33.0	12375	0.9158	0.8752
0.0001	34.0	12750	0.9726	0.8918
0.0	35.0	13125	1.0164	0.8819
0.0	36.0	13500	1.0004	0.8869
0.0	37.0	13875	1.0193	0.8869
0.0	38.0	14250	1.0151	0.8935
0.0	39.0	14625	1.0231	0.8902
0.0035	40.0	15000	1.0298	0.8852
0.0	41.0	15375	1.0402	0.8902
0.0028	42.0	15750	1.0577	0.8869
0.0026	43.0	16125	1.0687	0.8819
0.0027	44.0	16500	1.0626	0.8852
0.0029	45.0	16875	1.0972	0.8835
0.0	46.0	17250	1.0976	0.8819
0.0055	47.0	17625	1.1056	0.8819
0.0	48.0	18000	1.1143	0.8852
0.0025	49.0	18375	1.1213	0.8835
0.0024	50.0	18750	1.1252	0.8852

Framework versions

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