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: 0.0812
Accuracy: 1.0

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: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	2.3241	0.0833
No log	2.0	2	1.8900	0.0833
No log	3.0	3	1.1748	0.3333
No log	4.0	4	0.5751	0.9167
No log	5.0	5	0.4224	0.9167
No log	6.0	6	0.3931	0.9167
No log	7.0	7	0.3635	0.9167
No log	8.0	8	0.5637	0.8333
No log	9.0	9	0.4256	0.9167
0.4996	10.0	10	0.2830	0.9167
0.4996	11.0	11	0.2743	0.9167
0.4996	12.0	12	0.4505	0.9167
0.4996	13.0	13	0.3552	0.9167
0.4996	14.0	14	0.2453	0.9167
0.4996	15.0	15	0.2528	0.9167
0.4996	16.0	16	0.2926	0.9167
0.4996	17.0	17	0.3253	0.8333
0.4996	18.0	18	0.3367	0.8333
0.4996	19.0	19	0.3681	0.8333
0.1796	20.0	20	0.2677	0.9167
0.1796	21.0	21	0.2704	0.9167
0.1796	22.0	22	0.3116	0.9167
0.1796	23.0	23	0.3650	0.9167
0.1796	24.0	24	0.2170	0.9167
0.1796	25.0	25	0.2114	0.9167
0.1796	26.0	26	0.1976	0.9167
0.1796	27.0	27	0.1619	0.9167
0.1796	28.0	28	0.1646	0.9167
0.1796	29.0	29	0.1432	0.9167
0.1179	30.0	30	0.0812	1.0
0.1179	31.0	31	0.1163	1.0
0.1179	32.0	32	0.0898	1.0
0.1179	33.0	33	0.1190	0.9167
0.1179	34.0	34	0.1464	0.9167
0.1179	35.0	35	0.1136	1.0
0.1179	36.0	36	0.2270	0.9167
0.1179	37.0	37	0.2265	0.9167
0.1179	38.0	38	0.0995	1.0
0.1179	39.0	39	0.0853	1.0
0.1084	40.0	40	0.0858	1.0
0.1084	41.0	41	0.0970	1.0
0.1084	42.0	42	0.0949	1.0
0.1084	43.0	43	0.0709	1.0
0.1084	44.0	44	0.0807	0.9167
0.1084	45.0	45	0.1052	0.9167
0.1084	46.0	46	0.0629	1.0
0.1084	47.0	47	0.0272	1.0
0.1084	48.0	48	0.0775	1.0
0.1084	49.0	49	0.1113	1.0
0.0591	50.0	50	0.1189	1.0
0.0591	51.0	51	0.0526	1.0
0.0591	52.0	52	0.0262	1.0
0.0591	53.0	53	0.1035	0.9167
0.0591	54.0	54	0.1508	0.9167
0.0591	55.0	55	0.1280	0.9167
0.0591	56.0	56	0.0652	0.9167
0.0591	57.0	57	0.0357	1.0
0.0591	58.0	58	0.0407	1.0
0.0591	59.0	59	0.0430	1.0
0.0637	60.0	60	0.0468	1.0
0.0637	61.0	61	0.0997	0.9167
0.0637	62.0	62	0.2200	0.9167
0.0637	63.0	63	0.2979	0.9167
0.0637	64.0	64	0.3167	0.9167
0.0637	65.0	65	0.2611	0.9167
0.0637	66.0	66	0.1697	0.9167
0.0637	67.0	67	0.0669	0.9167
0.0637	68.0	68	0.0313	1.0
0.0637	69.0	69	0.0255	1.0
0.0446	70.0	70	0.0243	1.0
0.0446	71.0	71	0.0188	1.0
0.0446	72.0	72	0.0210	1.0
0.0446	73.0	73	0.0261	1.0
0.0446	74.0	74	0.0378	1.0
0.0446	75.0	75	0.0492	1.0
0.0446	76.0	76	0.0679	0.9167
0.0446	77.0	77	0.0958	0.9167
0.0446	78.0	78	0.0803	0.9167
0.0446	79.0	79	0.0455	1.0
0.0489	80.0	80	0.0194	1.0
0.0489	81.0	81	0.0141	1.0
0.0489	82.0	82	0.0109	1.0
0.0489	83.0	83	0.0104	1.0
0.0489	84.0	84	0.0108	1.0
0.0489	85.0	85	0.0121	1.0
0.0489	86.0	86	0.0118	1.0
0.0489	87.0	87	0.0109	1.0
0.0489	88.0	88	0.0107	1.0
0.0489	89.0	89	0.0107	1.0
0.0322	90.0	90	0.0107	1.0
0.0322	91.0	91	0.0107	1.0
0.0322	92.0	92	0.0106	1.0
0.0322	93.0	93	0.0105	1.0
0.0322	94.0	94	0.0105	1.0
0.0322	95.0	95	0.0105	1.0
0.0322	96.0	96	0.0106	1.0
0.0322	97.0	97	0.0106	1.0
0.0322	98.0	98	0.0106	1.0
0.0322	99.0	99	0.0108	1.0
0.0405	100.0	100	0.0109	1.0

Framework versions

Transformers 4.41.0
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

BilalMuftuoglu/beit-base-patch16-224-hasta-75-fold4

beit-base-patch16-224-hasta-75-fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

BilalMuftuoglu/
beit-base-patch16-224-hasta-75-fold4