hushem_5x_deit_small_sgd_00001_fold1

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: 1.6074
• Accuracy: 0.2222

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
1.4194	1.0	27	1.6162	0.2222
1.4315	2.0	54	1.6158	0.2222
1.4532	3.0	81	1.6154	0.2222
1.4652	4.0	108	1.6150	0.2222
1.4244	5.0	135	1.6147	0.2222
1.4622	6.0	162	1.6143	0.2222
1.4528	7.0	189	1.6140	0.2222
1.4262	8.0	216	1.6136	0.2222
1.4181	9.0	243	1.6133	0.2222
1.4163	10.0	270	1.6130	0.2222
1.4463	11.0	297	1.6127	0.2222
1.4137	12.0	324	1.6124	0.2222
1.4131	13.0	351	1.6121	0.2222
1.4148	14.0	378	1.6118	0.2222
1.444	15.0	405	1.6115	0.2222
1.4135	16.0	432	1.6113	0.2222
1.4356	17.0	459	1.6110	0.2222
1.4146	18.0	486	1.6108	0.2222
1.4096	19.0	513	1.6105	0.2222
1.4038	20.0	540	1.6103	0.2222
1.3926	21.0	567	1.6101	0.2222
1.4332	22.0	594	1.6099	0.2222
1.4214	23.0	621	1.6097	0.2222
1.4083	24.0	648	1.6095	0.2222
1.4271	25.0	675	1.6093	0.2222
1.4496	26.0	702	1.6091	0.2222
1.4117	27.0	729	1.6090	0.2222
1.403	28.0	756	1.6088	0.2222
1.3913	29.0	783	1.6087	0.2222
1.4302	30.0	810	1.6085	0.2222
1.4037	31.0	837	1.6084	0.2222
1.4442	32.0	864	1.6083	0.2222
1.4272	33.0	891	1.6082	0.2222
1.4095	34.0	918	1.6080	0.2222
1.4234	35.0	945	1.6079	0.2222
1.4343	36.0	972	1.6079	0.2222
1.4253	37.0	999	1.6078	0.2222
1.4109	38.0	1026	1.6077	0.2222
1.4096	39.0	1053	1.6076	0.2222
1.3772	40.0	1080	1.6076	0.2222
1.4046	41.0	1107	1.6075	0.2222
1.384	42.0	1134	1.6075	0.2222
1.4202	43.0	1161	1.6075	0.2222
1.3963	44.0	1188	1.6074	0.2222
1.4183	45.0	1215	1.6074	0.2222
1.3888	46.0	1242	1.6074	0.2222
1.4088	47.0	1269	1.6074	0.2222
1.393	48.0	1296	1.6074	0.2222
1.4397	49.0	1323	1.6074	0.2222
1.4472	50.0	1350	1.6074	0.2222

Framework versions

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