hushem_1x_deit_tiny_sgd_00001_fold4

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

• Loss: 1.6751
• 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	1.6974	0.2857
1.71	2.0	12	1.6962	0.2857
1.71	3.0	18	1.6951	0.2857
1.7036	4.0	24	1.6940	0.2857
1.7465	5.0	30	1.6930	0.2857
1.7465	6.0	36	1.6921	0.2857
1.709	7.0	42	1.6911	0.2857
1.709	8.0	48	1.6901	0.2857
1.712	9.0	54	1.6892	0.2857
1.7048	10.0	60	1.6882	0.2857
1.7048	11.0	66	1.6874	0.2857
1.6828	12.0	72	1.6866	0.2857
1.6828	13.0	78	1.6858	0.2857
1.7139	14.0	84	1.6850	0.2857
1.719	15.0	90	1.6842	0.2857
1.719	16.0	96	1.6835	0.2857
1.6904	17.0	102	1.6828	0.2857
1.6904	18.0	108	1.6821	0.2857
1.7154	19.0	114	1.6815	0.2857
1.7326	20.0	120	1.6809	0.2857
1.7326	21.0	126	1.6804	0.2857
1.6942	22.0	132	1.6799	0.2857
1.6942	23.0	138	1.6794	0.2857
1.6945	24.0	144	1.6789	0.2857
1.728	25.0	150	1.6784	0.2857
1.728	26.0	156	1.6780	0.2857
1.7026	27.0	162	1.6776	0.2857
1.7026	28.0	168	1.6772	0.2857
1.7403	29.0	174	1.6769	0.2857
1.6716	30.0	180	1.6766	0.2857
1.6716	31.0	186	1.6764	0.2857
1.6806	32.0	192	1.6761	0.2857
1.6806	33.0	198	1.6759	0.2857
1.6988	34.0	204	1.6757	0.2857
1.6893	35.0	210	1.6755	0.2857
1.6893	36.0	216	1.6754	0.2857
1.6718	37.0	222	1.6753	0.2857
1.6718	38.0	228	1.6752	0.2857
1.7279	39.0	234	1.6751	0.2857
1.6803	40.0	240	1.6751	0.2857
1.6803	41.0	246	1.6751	0.2857
1.6785	42.0	252	1.6751	0.2857
1.6785	43.0	258	1.6751	0.2857
1.7169	44.0	264	1.6751	0.2857
1.6924	45.0	270	1.6751	0.2857
1.6924	46.0	276	1.6751	0.2857
1.6961	47.0	282	1.6751	0.2857
1.6961	48.0	288	1.6751	0.2857
1.7415	49.0	294	1.6751	0.2857
1.681	50.0	300	1.6751	0.2857

Framework versions

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