hushem_1x_deit_base_sgd_0001_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: 1.4144
• Accuracy: 0.1429

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	1.4153	0.1667
1.4547	2.0	12	1.4153	0.1667
1.4547	3.0	18	1.4153	0.1667
1.4314	4.0	24	1.4152	0.1667
1.4443	5.0	30	1.4152	0.1667
1.4443	6.0	36	1.4151	0.1667
1.4414	7.0	42	1.4151	0.1667
1.4414	8.0	48	1.4150	0.1667
1.443	9.0	54	1.4150	0.1667
1.4464	10.0	60	1.4150	0.1667
1.4464	11.0	66	1.4149	0.1667
1.4495	12.0	72	1.4149	0.1667
1.4495	13.0	78	1.4148	0.1667
1.4302	14.0	84	1.4148	0.1667
1.4411	15.0	90	1.4148	0.1667
1.4411	16.0	96	1.4147	0.1667
1.4348	17.0	102	1.4147	0.1429
1.4348	18.0	108	1.4147	0.1429
1.4295	19.0	114	1.4147	0.1429
1.4389	20.0	120	1.4146	0.1429
1.4389	21.0	126	1.4146	0.1429
1.4508	22.0	132	1.4146	0.1429
1.4508	23.0	138	1.4146	0.1429
1.4342	24.0	144	1.4146	0.1429
1.4514	25.0	150	1.4145	0.1429
1.4514	26.0	156	1.4145	0.1429
1.4469	27.0	162	1.4145	0.1429
1.4469	28.0	168	1.4145	0.1429
1.4285	29.0	174	1.4145	0.1429
1.4574	30.0	180	1.4145	0.1429
1.4574	31.0	186	1.4145	0.1429
1.442	32.0	192	1.4144	0.1429
1.442	33.0	198	1.4144	0.1429
1.4418	34.0	204	1.4144	0.1429
1.4436	35.0	210	1.4144	0.1429
1.4436	36.0	216	1.4144	0.1429
1.4418	37.0	222	1.4144	0.1429
1.4418	38.0	228	1.4144	0.1429
1.4476	39.0	234	1.4144	0.1429
1.4324	40.0	240	1.4144	0.1429
1.4324	41.0	246	1.4144	0.1429
1.438	42.0	252	1.4144	0.1429
1.438	43.0	258	1.4144	0.1429
1.4299	44.0	264	1.4144	0.1429
1.4491	45.0	270	1.4144	0.1429
1.4491	46.0	276	1.4144	0.1429
1.4409	47.0	282	1.4144	0.1429
1.4409	48.0	288	1.4144	0.1429
1.4306	49.0	294	1.4144	0.1429
1.4383	50.0	300	1.4144	0.1429

Framework versions

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