smids_1x_beit_base_adamax_001_fold1

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: 1.2333
• Accuracy: 0.8531

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
0.6722	1.0	76	0.7068	0.7346
0.5257	2.0	152	0.7906	0.6978
0.3766	3.0	228	0.4936	0.8030
0.4703	4.0	304	0.5194	0.8047
0.3758	5.0	380	0.4944	0.8047
0.3685	6.0	456	0.4662	0.8364
0.2812	7.0	532	0.5286	0.8314
0.2831	8.0	608	0.4636	0.8331
0.2359	9.0	684	0.5034	0.8063
0.1426	10.0	760	0.5477	0.8280
0.2668	11.0	836	0.6880	0.8130
0.182	12.0	912	0.6113	0.8280
0.1925	13.0	988	0.5781	0.8280
0.1404	14.0	1064	0.8189	0.8114
0.0795	15.0	1140	0.8425	0.8230
0.0585	16.0	1216	0.6551	0.8481
0.0935	17.0	1292	0.7044	0.8347
0.0369	18.0	1368	0.9110	0.8414
0.0816	19.0	1444	0.9853	0.8414
0.063	20.0	1520	0.7577	0.8464
0.0166	21.0	1596	0.8613	0.8381
0.0172	22.0	1672	0.7211	0.8548
0.0101	23.0	1748	0.9887	0.8297
0.059	24.0	1824	1.1066	0.8414
0.0163	25.0	1900	0.8966	0.8481
0.0425	26.0	1976	0.9615	0.8364
0.0118	27.0	2052	1.0527	0.8481
0.0022	28.0	2128	1.0163	0.8464
0.0009	29.0	2204	1.0736	0.8514
0.0005	30.0	2280	1.0490	0.8531
0.0032	31.0	2356	1.1469	0.8514
0.0106	32.0	2432	1.1588	0.8497
0.06	33.0	2508	1.1292	0.8514
0.0041	34.0	2584	1.0765	0.8531
0.0193	35.0	2660	1.2132	0.8548
0.0004	36.0	2736	1.1489	0.8481
0.0134	37.0	2812	1.2292	0.8464
0.0047	38.0	2888	1.1921	0.8514
0.0036	39.0	2964	1.2034	0.8464
0.0001	40.0	3040	1.1597	0.8481
0.0065	41.0	3116	1.1753	0.8548
0.0001	42.0	3192	1.1808	0.8548
0.0	43.0	3268	1.1898	0.8564
0.0001	44.0	3344	1.2021	0.8581
0.0061	45.0	3420	1.2174	0.8564
0.0	46.0	3496	1.2210	0.8548
0.0025	47.0	3572	1.2289	0.8531
0.0025	48.0	3648	1.2311	0.8548
0.0023	49.0	3724	1.2330	0.8531
0.0044	50.0	3800	1.2333	0.8531

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0