hushem_1x_beit_base_sgd_0001_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: 1.5102
• Accuracy: 0.2326

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: 0.0001
• 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
No log	1.0	6	1.5815	0.2558
1.5795	2.0	12	1.5768	0.2558
1.5795	3.0	18	1.5725	0.2558
1.5843	4.0	24	1.5685	0.2558
1.5064	5.0	30	1.5650	0.2558
1.5064	6.0	36	1.5613	0.2558
1.5264	7.0	42	1.5577	0.2558
1.5264	8.0	48	1.5544	0.2558
1.5341	9.0	54	1.5511	0.2558
1.5468	10.0	60	1.5482	0.2558
1.5468	11.0	66	1.5458	0.2558
1.5265	12.0	72	1.5432	0.2558
1.5265	13.0	78	1.5409	0.2558
1.4949	14.0	84	1.5386	0.2558
1.5252	15.0	90	1.5362	0.2558
1.5252	16.0	96	1.5341	0.2558
1.5295	17.0	102	1.5321	0.2558
1.5295	18.0	108	1.5302	0.2558
1.4916	19.0	114	1.5284	0.2558
1.4984	20.0	120	1.5267	0.2326
1.4984	21.0	126	1.5250	0.2326
1.5211	22.0	132	1.5235	0.2326
1.5211	23.0	138	1.5222	0.2326
1.506	24.0	144	1.5209	0.2326
1.483	25.0	150	1.5197	0.2326
1.483	26.0	156	1.5185	0.2326
1.5184	27.0	162	1.5173	0.2326
1.5184	28.0	168	1.5163	0.2326
1.536	29.0	174	1.5154	0.2326
1.4949	30.0	180	1.5146	0.2326
1.4949	31.0	186	1.5138	0.2326
1.5188	32.0	192	1.5132	0.2326
1.5188	33.0	198	1.5126	0.2326
1.4387	34.0	204	1.5120	0.2326
1.4953	35.0	210	1.5116	0.2326
1.4953	36.0	216	1.5112	0.2326
1.4703	37.0	222	1.5108	0.2326
1.4703	38.0	228	1.5106	0.2326
1.5017	39.0	234	1.5104	0.2326
1.4757	40.0	240	1.5103	0.2326
1.4757	41.0	246	1.5102	0.2326
1.4714	42.0	252	1.5102	0.2326
1.4714	43.0	258	1.5102	0.2326
1.4776	44.0	264	1.5102	0.2326
1.4921	45.0	270	1.5102	0.2326
1.4921	46.0	276	1.5102	0.2326
1.4896	47.0	282	1.5102	0.2326
1.4896	48.0	288	1.5102	0.2326
1.4789	49.0	294	1.5102	0.2326
1.4671	50.0	300	1.5102	0.2326

Framework versions

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