hushem_1x_beit_base_sgd_0001_fold2

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: 1.4763
• Accuracy: 0.2667

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	1.5508	0.2667
1.5993	2.0	12	1.5460	0.2667
1.5993	3.0	18	1.5415	0.2667
1.5379	4.0	24	1.5376	0.2667
1.5842	5.0	30	1.5337	0.2667
1.5842	6.0	36	1.5302	0.2667
1.5559	7.0	42	1.5267	0.2667
1.5559	8.0	48	1.5233	0.2667
1.5583	9.0	54	1.5200	0.2667
1.5216	10.0	60	1.5170	0.2667
1.5216	11.0	66	1.5141	0.2667
1.5475	12.0	72	1.5116	0.2667
1.5475	13.0	78	1.5088	0.2667
1.5228	14.0	84	1.5063	0.2667
1.5337	15.0	90	1.5038	0.2667
1.5337	16.0	96	1.5015	0.2667
1.5424	17.0	102	1.4994	0.2667
1.5424	18.0	108	1.4973	0.2667
1.5261	19.0	114	1.4953	0.2667
1.5374	20.0	120	1.4936	0.2667
1.5374	21.0	126	1.4921	0.2667
1.5211	22.0	132	1.4905	0.2667
1.5211	23.0	138	1.4888	0.2667
1.5308	24.0	144	1.4875	0.2667
1.501	25.0	150	1.4863	0.2667
1.501	26.0	156	1.4851	0.2667
1.4969	27.0	162	1.4841	0.2667
1.4969	28.0	168	1.4832	0.2667
1.4796	29.0	174	1.4822	0.2667
1.5135	30.0	180	1.4813	0.2667
1.5135	31.0	186	1.4804	0.2667
1.4924	32.0	192	1.4797	0.2667
1.4924	33.0	198	1.4791	0.2667
1.4838	34.0	204	1.4785	0.2667
1.4833	35.0	210	1.4779	0.2667
1.4833	36.0	216	1.4775	0.2667
1.4826	37.0	222	1.4771	0.2667
1.4826	38.0	228	1.4768	0.2667
1.5058	39.0	234	1.4766	0.2667
1.4814	40.0	240	1.4764	0.2667
1.4814	41.0	246	1.4764	0.2667
1.4809	42.0	252	1.4763	0.2667
1.4809	43.0	258	1.4763	0.2667
1.5264	44.0	264	1.4763	0.2667
1.4935	45.0	270	1.4763	0.2667
1.4935	46.0	276	1.4763	0.2667
1.4909	47.0	282	1.4763	0.2667
1.4909	48.0	288	1.4763	0.2667
1.4851	49.0	294	1.4763	0.2667
1.5045	50.0	300	1.4763	0.2667

Framework versions

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