hushem_1x_deit_base_sgd_0001_fold2

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: 1.4779
• Accuracy: 0.1333

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	1.4794	0.1333
1.4241	2.0	12	1.4793	0.1333
1.4241	3.0	18	1.4793	0.1333
1.4299	4.0	24	1.4792	0.1333
1.4212	5.0	30	1.4791	0.1333
1.4212	6.0	36	1.4790	0.1333
1.4284	7.0	42	1.4790	0.1333
1.4284	8.0	48	1.4789	0.1333
1.4338	9.0	54	1.4788	0.1333
1.417	10.0	60	1.4788	0.1333
1.417	11.0	66	1.4787	0.1333
1.4253	12.0	72	1.4786	0.1333
1.4253	13.0	78	1.4786	0.1333
1.4157	14.0	84	1.4785	0.1333
1.4129	15.0	90	1.4785	0.1333
1.4129	16.0	96	1.4784	0.1333
1.4248	17.0	102	1.4784	0.1333
1.4248	18.0	108	1.4784	0.1333
1.4287	19.0	114	1.4783	0.1333
1.4283	20.0	120	1.4783	0.1333
1.4283	21.0	126	1.4782	0.1333
1.4273	22.0	132	1.4782	0.1333
1.4273	23.0	138	1.4782	0.1333
1.4431	24.0	144	1.4781	0.1333
1.4247	25.0	150	1.4781	0.1333
1.4247	26.0	156	1.4781	0.1333
1.4236	27.0	162	1.4781	0.1333
1.4236	28.0	168	1.4780	0.1333
1.426	29.0	174	1.4780	0.1333
1.4223	30.0	180	1.4780	0.1333
1.4223	31.0	186	1.4780	0.1333
1.418	32.0	192	1.4779	0.1333
1.418	33.0	198	1.4779	0.1333
1.4337	34.0	204	1.4779	0.1333
1.4133	35.0	210	1.4779	0.1333
1.4133	36.0	216	1.4779	0.1333
1.4229	37.0	222	1.4779	0.1333
1.4229	38.0	228	1.4779	0.1333
1.4393	39.0	234	1.4779	0.1333
1.4246	40.0	240	1.4779	0.1333
1.4246	41.0	246	1.4779	0.1333
1.4293	42.0	252	1.4779	0.1333
1.4293	43.0	258	1.4779	0.1333
1.4096	44.0	264	1.4779	0.1333
1.4337	45.0	270	1.4779	0.1333
1.4337	46.0	276	1.4779	0.1333
1.428	47.0	282	1.4779	0.1333
1.428	48.0	288	1.4779	0.1333
1.4333	49.0	294	1.4779	0.1333
1.4174	50.0	300	1.4779	0.1333

Framework versions

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