hushem_1x_deit_small_sgd_00001_fold5

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: 1.5124
• Accuracy: 0.2439

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	1.5202	0.2195
1.5388	2.0	12	1.5198	0.2195
1.5388	3.0	18	1.5194	0.2195
1.5264	4.0	24	1.5190	0.2195
1.5345	5.0	30	1.5186	0.2195
1.5345	6.0	36	1.5183	0.2195
1.526	7.0	42	1.5179	0.2195
1.526	8.0	48	1.5176	0.2195
1.5157	9.0	54	1.5173	0.2195
1.5235	10.0	60	1.5170	0.2195
1.5235	11.0	66	1.5167	0.2195
1.5297	12.0	72	1.5164	0.2439
1.5297	13.0	78	1.5161	0.2439
1.4988	14.0	84	1.5158	0.2439
1.5228	15.0	90	1.5155	0.2439
1.5228	16.0	96	1.5153	0.2439
1.5206	17.0	102	1.5150	0.2439
1.5206	18.0	108	1.5148	0.2439
1.5425	19.0	114	1.5146	0.2439
1.5252	20.0	120	1.5144	0.2439
1.5252	21.0	126	1.5142	0.2439
1.5165	22.0	132	1.5140	0.2439
1.5165	23.0	138	1.5139	0.2439
1.5451	24.0	144	1.5137	0.2439
1.5198	25.0	150	1.5135	0.2439
1.5198	26.0	156	1.5134	0.2439
1.5047	27.0	162	1.5132	0.2439
1.5047	28.0	168	1.5131	0.2439
1.5384	29.0	174	1.5130	0.2439
1.5271	30.0	180	1.5129	0.2439
1.5271	31.0	186	1.5128	0.2439
1.5283	32.0	192	1.5127	0.2439
1.5283	33.0	198	1.5127	0.2439
1.4864	34.0	204	1.5126	0.2439
1.5229	35.0	210	1.5125	0.2439
1.5229	36.0	216	1.5125	0.2439
1.513	37.0	222	1.5125	0.2439
1.513	38.0	228	1.5124	0.2439
1.4969	39.0	234	1.5124	0.2439
1.5399	40.0	240	1.5124	0.2439
1.5399	41.0	246	1.5124	0.2439
1.5142	42.0	252	1.5124	0.2439
1.5142	43.0	258	1.5124	0.2439
1.5226	44.0	264	1.5124	0.2439
1.538	45.0	270	1.5124	0.2439
1.538	46.0	276	1.5124	0.2439
1.5217	47.0	282	1.5124	0.2439
1.5217	48.0	288	1.5124	0.2439
1.5124	49.0	294	1.5124	0.2439
1.5354	50.0	300	1.5124	0.2439

Framework versions

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