hushem_1x_deit_small_sgd_00001_fold4

This model is a fine-tuned version of facebook/deit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.4772
• Accuracy: 0.2857

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	1.4838	0.2619
1.5238	2.0	12	1.4835	0.2619
1.5238	3.0	18	1.4831	0.2619
1.5534	4.0	24	1.4828	0.2619
1.5381	5.0	30	1.4825	0.2619
1.5381	6.0	36	1.4822	0.2619
1.5402	7.0	42	1.4819	0.2619
1.5402	8.0	48	1.4816	0.2619
1.5343	9.0	54	1.4813	0.2619
1.5296	10.0	60	1.4811	0.2619
1.5296	11.0	66	1.4808	0.2619
1.5185	12.0	72	1.4805	0.2619
1.5185	13.0	78	1.4803	0.2619
1.5511	14.0	84	1.4801	0.2619
1.5137	15.0	90	1.4798	0.2619
1.5137	16.0	96	1.4796	0.2619
1.5299	17.0	102	1.4794	0.2619
1.5299	18.0	108	1.4792	0.2857
1.4899	19.0	114	1.4790	0.2857
1.5822	20.0	120	1.4789	0.2857
1.5822	21.0	126	1.4787	0.2857
1.5002	22.0	132	1.4786	0.2857
1.5002	23.0	138	1.4784	0.2857
1.5297	24.0	144	1.4783	0.2857
1.5406	25.0	150	1.4781	0.2857
1.5406	26.0	156	1.4780	0.2857
1.5241	27.0	162	1.4779	0.2857
1.5241	28.0	168	1.4778	0.2857
1.5379	29.0	174	1.4777	0.2857
1.5253	30.0	180	1.4776	0.2857
1.5253	31.0	186	1.4775	0.2857
1.549	32.0	192	1.4775	0.2857
1.549	33.0	198	1.4774	0.2857
1.5016	34.0	204	1.4774	0.2857
1.4996	35.0	210	1.4773	0.2857
1.4996	36.0	216	1.4773	0.2857
1.533	37.0	222	1.4772	0.2857
1.533	38.0	228	1.4772	0.2857
1.5136	39.0	234	1.4772	0.2857
1.5288	40.0	240	1.4772	0.2857
1.5288	41.0	246	1.4772	0.2857
1.5195	42.0	252	1.4772	0.2857
1.5195	43.0	258	1.4772	0.2857
1.5432	44.0	264	1.4772	0.2857
1.5238	45.0	270	1.4772	0.2857
1.5238	46.0	276	1.4772	0.2857
1.544	47.0	282	1.4772	0.2857
1.544	48.0	288	1.4772	0.2857
1.5337	49.0	294	1.4772	0.2857
1.5345	50.0	300	1.4772	0.2857

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1