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: 2.0748
Accuracy: 0.6

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: 0.0001
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	1.2729	0.4
1.2121	2.0	12	1.1250	0.6222
1.2121	3.0	18	1.2362	0.5556
0.4291	4.0	24	1.2042	0.6444
0.1116	5.0	30	1.1861	0.6
0.1116	6.0	36	1.6632	0.5556
0.0196	7.0	42	1.7499	0.6
0.0196	8.0	48	1.7915	0.5556
0.0051	9.0	54	1.8168	0.5778
0.0016	10.0	60	1.8187	0.6222
0.0016	11.0	66	1.8480	0.6222
0.0008	12.0	72	1.8621	0.6222
0.0008	13.0	78	1.8730	0.6222
0.0006	14.0	84	1.8908	0.6222
0.0005	15.0	90	1.9136	0.6222
0.0005	16.0	96	1.9335	0.6222
0.0004	17.0	102	1.9501	0.6222
0.0004	18.0	108	1.9655	0.6222
0.0004	19.0	114	1.9783	0.6222
0.0003	20.0	120	1.9900	0.6222
0.0003	21.0	126	1.9990	0.6222
0.0003	22.0	132	2.0067	0.6222
0.0003	23.0	138	2.0139	0.6
0.0003	24.0	144	2.0208	0.6
0.0003	25.0	150	2.0271	0.6
0.0003	26.0	156	2.0322	0.6
0.0003	27.0	162	2.0367	0.6
0.0003	28.0	168	2.0419	0.6
0.0003	29.0	174	2.0471	0.6
0.0003	30.0	180	2.0520	0.6
0.0003	31.0	186	2.0560	0.6
0.0002	32.0	192	2.0593	0.6
0.0002	33.0	198	2.0621	0.6
0.0003	34.0	204	2.0649	0.6
0.0003	35.0	210	2.0672	0.6
0.0003	36.0	216	2.0692	0.6
0.0002	37.0	222	2.0710	0.6
0.0002	38.0	228	2.0723	0.6
0.0002	39.0	234	2.0735	0.6
0.0002	40.0	240	2.0742	0.6
0.0002	41.0	246	2.0747	0.6
0.0002	42.0	252	2.0748	0.6
0.0002	43.0	258	2.0748	0.6
0.0002	44.0	264	2.0748	0.6
0.0002	45.0	270	2.0748	0.6
0.0002	46.0	276	2.0748	0.6
0.0002	47.0	282	2.0748	0.6
0.0002	48.0	288	2.0748	0.6
0.0002	49.0	294	2.0748	0.6
0.0002	50.0	300	2.0748	0.6

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

hkivancoral/hushem_1x_deit_small_adamax_0001_fold2

hushem_1x_deit_small_adamax_0001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_deit_small_adamax_0001_fold2