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: 0.3532
Accuracy: 0.8571

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	1.3457	0.4048
1.2924	2.0	12	0.9334	0.5952
1.2924	3.0	18	0.6841	0.6667
0.6444	4.0	24	0.7302	0.6429
0.1694	5.0	30	0.5848	0.7619
0.1694	6.0	36	0.6575	0.7619
0.0382	7.0	42	0.4727	0.8333
0.0382	8.0	48	0.7729	0.7381
0.0125	9.0	54	0.6089	0.7619
0.0034	10.0	60	0.3189	0.9048
0.0034	11.0	66	0.2852	0.8810
0.0011	12.0	72	0.3340	0.8571
0.0011	13.0	78	0.3522	0.8571
0.0007	14.0	84	0.3495	0.8571
0.0005	15.0	90	0.3442	0.8571
0.0005	16.0	96	0.3406	0.8571
0.0004	17.0	102	0.3391	0.8571
0.0004	18.0	108	0.3391	0.8571
0.0004	19.0	114	0.3401	0.8571
0.0004	20.0	120	0.3412	0.8571
0.0004	21.0	126	0.3433	0.8571
0.0003	22.0	132	0.3444	0.8571
0.0003	23.0	138	0.3456	0.8571
0.0003	24.0	144	0.3474	0.8571
0.0003	25.0	150	0.3486	0.8571
0.0003	26.0	156	0.3489	0.8571
0.0003	27.0	162	0.3489	0.8571
0.0003	28.0	168	0.3500	0.8571
0.0003	29.0	174	0.3510	0.8571
0.0003	30.0	180	0.3511	0.8571
0.0003	31.0	186	0.3517	0.8571
0.0003	32.0	192	0.3522	0.8571
0.0003	33.0	198	0.3523	0.8571
0.0003	34.0	204	0.3526	0.8571
0.0003	35.0	210	0.3526	0.8571
0.0003	36.0	216	0.3527	0.8571
0.0003	37.0	222	0.3530	0.8571
0.0003	38.0	228	0.3531	0.8571
0.0002	39.0	234	0.3531	0.8571
0.0003	40.0	240	0.3531	0.8571
0.0003	41.0	246	0.3531	0.8571
0.0003	42.0	252	0.3532	0.8571
0.0003	43.0	258	0.3532	0.8571
0.0002	44.0	264	0.3532	0.8571
0.0003	45.0	270	0.3532	0.8571
0.0003	46.0	276	0.3532	0.8571
0.0003	47.0	282	0.3532	0.8571
0.0003	48.0	288	0.3532	0.8571
0.0002	49.0	294	0.3532	0.8571
0.0003	50.0	300	0.3532	0.8571

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_fold4

hushem_1x_deit_small_adamax_0001_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_deit_small_adamax_0001_fold4