hushem_1x_deit_base_sgd_001_fold4

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

• Loss: 1.3500
• Accuracy: 0.3571

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: 0.001
• 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	1.4099	0.1667
1.4464	2.0	12	1.4056	0.1667
1.4464	3.0	18	1.4012	0.1667
1.409	4.0	24	1.3971	0.1667
1.405	5.0	30	1.3937	0.1905
1.405	6.0	36	1.3906	0.1905
1.3913	7.0	42	1.3880	0.1905
1.3913	8.0	48	1.3852	0.1905
1.3821	9.0	54	1.3824	0.1667
1.3709	10.0	60	1.3801	0.1667
1.3709	11.0	66	1.3778	0.1905
1.3643	12.0	72	1.3757	0.2143
1.3643	13.0	78	1.3738	0.2619
1.3452	14.0	84	1.3719	0.2619
1.3451	15.0	90	1.3702	0.2619
1.3451	16.0	96	1.3686	0.2619
1.3306	17.0	102	1.3669	0.2619
1.3306	18.0	108	1.3655	0.2857
1.3266	19.0	114	1.3643	0.2857
1.3291	20.0	120	1.3632	0.2857
1.3291	21.0	126	1.3620	0.2857
1.3218	22.0	132	1.3610	0.2857
1.3218	23.0	138	1.3598	0.3095
1.3151	24.0	144	1.3588	0.3333
1.3182	25.0	150	1.3578	0.3333
1.3182	26.0	156	1.3568	0.3333
1.3072	27.0	162	1.3559	0.3333
1.3072	28.0	168	1.3552	0.3333
1.3081	29.0	174	1.3545	0.3571
1.3087	30.0	180	1.3539	0.3571
1.3087	31.0	186	1.3532	0.3571
1.2983	32.0	192	1.3527	0.3571
1.2983	33.0	198	1.3521	0.3333
1.2931	34.0	204	1.3516	0.3571
1.2999	35.0	210	1.3512	0.3571
1.2999	36.0	216	1.3509	0.3571
1.2926	37.0	222	1.3506	0.3571
1.2926	38.0	228	1.3504	0.3571
1.2948	39.0	234	1.3502	0.3571
1.2828	40.0	240	1.3501	0.3571
1.2828	41.0	246	1.3500	0.3571
1.2878	42.0	252	1.3500	0.3571
1.2878	43.0	258	1.3500	0.3571
1.2878	44.0	264	1.3500	0.3571
1.2935	45.0	270	1.3500	0.3571
1.2935	46.0	276	1.3500	0.3571
1.289	47.0	282	1.3500	0.3571
1.289	48.0	288	1.3500	0.3571
1.2878	49.0	294	1.3500	0.3571
1.2975	50.0	300	1.3500	0.3571

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.14.7
• Tokenizers 0.15.0