hushem_1x_beit_base_sgd_00001_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: 1.5773
• Accuracy: 0.2558

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
No log	1.0	6	1.5860	0.2558
1.5832	2.0	12	1.5856	0.2558
1.5832	3.0	18	1.5851	0.2558
1.5961	4.0	24	1.5847	0.2558
1.5221	5.0	30	1.5843	0.2558
1.5221	6.0	36	1.5839	0.2558
1.5495	7.0	42	1.5835	0.2558
1.5495	8.0	48	1.5831	0.2558
1.5657	9.0	54	1.5828	0.2558
1.5842	10.0	60	1.5824	0.2558
1.5842	11.0	66	1.5821	0.2558
1.5665	12.0	72	1.5818	0.2558
1.5665	13.0	78	1.5815	0.2558
1.536	14.0	84	1.5812	0.2558
1.572	15.0	90	1.5809	0.2558
1.572	16.0	96	1.5807	0.2558
1.5843	17.0	102	1.5804	0.2558
1.5843	18.0	108	1.5802	0.2558
1.5423	19.0	114	1.5799	0.2558
1.5549	20.0	120	1.5797	0.2558
1.5549	21.0	126	1.5794	0.2558
1.5883	22.0	132	1.5792	0.2558
1.5883	23.0	138	1.5791	0.2558
1.5691	24.0	144	1.5789	0.2558
1.5489	25.0	150	1.5787	0.2558
1.5489	26.0	156	1.5785	0.2558
1.5874	27.0	162	1.5784	0.2558
1.5874	28.0	168	1.5782	0.2558
1.6141	29.0	174	1.5781	0.2558
1.5647	30.0	180	1.5780	0.2558
1.5647	31.0	186	1.5779	0.2558
1.5987	32.0	192	1.5778	0.2558
1.5987	33.0	198	1.5777	0.2558
1.504	34.0	204	1.5776	0.2558
1.5743	35.0	210	1.5775	0.2558
1.5743	36.0	216	1.5775	0.2558
1.5471	37.0	222	1.5774	0.2558
1.5471	38.0	228	1.5774	0.2558
1.5808	39.0	234	1.5774	0.2558
1.5531	40.0	240	1.5774	0.2558
1.5531	41.0	246	1.5773	0.2558
1.5447	42.0	252	1.5773	0.2558
1.5447	43.0	258	1.5773	0.2558
1.5547	44.0	264	1.5773	0.2558
1.5706	45.0	270	1.5773	0.2558
1.5706	46.0	276	1.5773	0.2558
1.569	47.0	282	1.5773	0.2558
1.569	48.0	288	1.5773	0.2558
1.5551	49.0	294	1.5773	0.2558
1.5471	50.0	300	1.5773	0.2558

Framework versions

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