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: 1.1248
Accuracy: 0.3967

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
1.2551	1.0	375	1.3211	0.3167
1.2561	2.0	750	1.3119	0.32
1.2134	3.0	1125	1.3028	0.325
1.226	4.0	1500	1.2942	0.325
1.1635	5.0	1875	1.2859	0.3267
1.2304	6.0	2250	1.2778	0.3333
1.1734	7.0	2625	1.2702	0.3383
1.1724	8.0	3000	1.2625	0.3417
1.1336	9.0	3375	1.2554	0.3467
1.1266	10.0	3750	1.2486	0.3517
1.1276	11.0	4125	1.2419	0.355
1.1538	12.0	4500	1.2355	0.355
1.1425	13.0	4875	1.2292	0.3567
1.1463	14.0	5250	1.2233	0.36
1.1661	15.0	5625	1.2174	0.3633
1.1118	16.0	6000	1.2118	0.365
1.123	17.0	6375	1.2063	0.3667
1.1065	18.0	6750	1.2010	0.3667
1.1074	19.0	7125	1.1959	0.365
1.0742	20.0	7500	1.1911	0.3717
1.0616	21.0	7875	1.1865	0.3717
1.0745	22.0	8250	1.1820	0.3717
1.0871	23.0	8625	1.1777	0.3717
1.031	24.0	9000	1.1737	0.3717
1.0843	25.0	9375	1.1697	0.375
1.0616	26.0	9750	1.1660	0.3767
1.0414	27.0	10125	1.1624	0.3783
1.0303	28.0	10500	1.1590	0.3783
0.9887	29.0	10875	1.1558	0.38
1.0267	30.0	11250	1.1528	0.38
1.0792	31.0	11625	1.1499	0.3833
1.0736	32.0	12000	1.1472	0.3883
1.0868	33.0	12375	1.1446	0.39
1.0257	34.0	12750	1.1422	0.3883
1.0237	35.0	13125	1.1400	0.39
1.0201	36.0	13500	1.1379	0.39
1.0769	37.0	13875	1.1360	0.3917
1.032	38.0	14250	1.1343	0.3933
1.0317	39.0	14625	1.1327	0.395
1.0402	40.0	15000	1.1312	0.395
0.957	41.0	15375	1.1300	0.395
1.0445	42.0	15750	1.1288	0.395
1.0399	43.0	16125	1.1278	0.395
1.0323	44.0	16500	1.1270	0.3967
1.0444	45.0	16875	1.1263	0.3967
0.9983	46.0	17250	1.1257	0.3967
1.042	47.0	17625	1.1253	0.3967
1.0685	48.0	18000	1.1250	0.3967
1.0486	49.0	18375	1.1249	0.3967
1.0457	50.0	18750	1.1248	0.3967

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_5x_beit_base_sgd_00001_fold3

smids_5x_beit_base_sgd_00001_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_beit_base_sgd_00001_fold3