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: 2.7210
Accuracy: 0.5778

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	1.9817	0.2889
2.1535	2.0	12	1.8640	0.4444
2.1535	3.0	18	1.7102	0.4
1.6029	4.0	24	1.4150	0.2444
1.4466	5.0	30	1.4955	0.2444
1.4466	6.0	36	1.3473	0.2889
1.3072	7.0	42	1.3569	0.3333
1.3072	8.0	48	1.3132	0.3556
1.2227	9.0	54	1.3267	0.3556
1.1717	10.0	60	1.2287	0.4444
1.1717	11.0	66	1.0870	0.6
0.9512	12.0	72	1.2334	0.5111
0.9512	13.0	78	0.9647	0.5333
0.8377	14.0	84	1.3738	0.4444
0.7118	15.0	90	1.3877	0.5111
0.7118	16.0	96	1.7638	0.4222
0.4998	17.0	102	1.5390	0.5333
0.4998	18.0	108	2.3269	0.5111
0.355	19.0	114	1.9285	0.5556
0.2288	20.0	120	1.7817	0.5556
0.2288	21.0	126	2.2836	0.4667
0.1125	22.0	132	2.1054	0.5556
0.1125	23.0	138	2.1539	0.5333
0.1094	24.0	144	2.3111	0.5556
0.021	25.0	150	2.1092	0.5778
0.021	26.0	156	2.3965	0.6
0.0019	27.0	162	2.4763	0.5778
0.0019	28.0	168	2.5156	0.5778
0.0007	29.0	174	2.5560	0.5778
0.0006	30.0	180	2.5890	0.5778
0.0006	31.0	186	2.6141	0.5778
0.0005	32.0	192	2.6346	0.5778
0.0005	33.0	198	2.6539	0.5778
0.0004	34.0	204	2.6673	0.5778
0.0004	35.0	210	2.6785	0.5778
0.0004	36.0	216	2.6902	0.5778
0.0004	37.0	222	2.6990	0.5778
0.0004	38.0	228	2.7082	0.5778
0.0003	39.0	234	2.7139	0.5778
0.0003	40.0	240	2.7183	0.5778
0.0003	41.0	246	2.7203	0.5778
0.0003	42.0	252	2.7210	0.5778
0.0003	43.0	258	2.7210	0.5778
0.0003	44.0	264	2.7210	0.5778
0.0003	45.0	270	2.7210	0.5778
0.0003	46.0	276	2.7210	0.5778
0.0003	47.0	282	2.7210	0.5778
0.0003	48.0	288	2.7210	0.5778
0.0003	49.0	294	2.7210	0.5778
0.0003	50.0	300	2.7210	0.5778

Framework versions

Transformers 4.35.1
Pytorch 2.1.0+cu118
Datasets 2.14.7
Tokenizers 0.14.1

hkivancoral/hushem_1x_deit_small_rms_0001_fold2

hushem_1x_deit_small_rms_0001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_deit_small_rms_0001_fold2