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: 0.6560
Accuracy: 0.9017

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
0.3528	1.0	225	0.3515	0.845
0.2402	2.0	450	0.2867	0.88
0.1984	3.0	675	0.2729	0.8917
0.0996	4.0	900	0.2824	0.8917
0.0553	5.0	1125	0.2965	0.89
0.0276	6.0	1350	0.3082	0.8833
0.0633	7.0	1575	0.3636	0.8917
0.0425	8.0	1800	0.3934	0.8917
0.0389	9.0	2025	0.4319	0.8867
0.0013	10.0	2250	0.4665	0.885
0.002	11.0	2475	0.4939	0.89
0.0291	12.0	2700	0.5069	0.8983
0.0096	13.0	2925	0.5116	0.8967
0.0004	14.0	3150	0.5365	0.89
0.0003	15.0	3375	0.5451	0.8933
0.0001	16.0	3600	0.5523	0.9017
0.0001	17.0	3825	0.5663	0.895
0.0002	18.0	4050	0.6978	0.88
0.0158	19.0	4275	0.5838	0.8983
0.0001	20.0	4500	0.6267	0.8917
0.0001	21.0	4725	0.6223	0.8833
0.0001	22.0	4950	0.5930	0.8983
0.0001	23.0	5175	0.6068	0.8967
0.01	24.0	5400	0.5979	0.895
0.0001	25.0	5625	0.6216	0.885
0.0001	26.0	5850	0.6186	0.89
0.0001	27.0	6075	0.6718	0.88
0.0001	28.0	6300	0.6180	0.8917
0.0037	29.0	6525	0.6199	0.895
0.0	30.0	6750	0.6476	0.8933
0.0	31.0	6975	0.6341	0.8933
0.0	32.0	7200	0.6370	0.895
0.0032	33.0	7425	0.6400	0.895
0.0	34.0	7650	0.6373	0.8933
0.0026	35.0	7875	0.6425	0.8967
0.0	36.0	8100	0.6390	0.8983
0.0053	37.0	8325	0.6460	0.895
0.0	38.0	8550	0.6514	0.8933
0.0	39.0	8775	0.6474	0.8983
0.0	40.0	9000	0.6511	0.8933
0.0	41.0	9225	0.6568	0.8933
0.0	42.0	9450	0.6574	0.8933
0.0026	43.0	9675	0.6562	0.8967
0.0	44.0	9900	0.6548	0.8983
0.0	45.0	10125	0.6524	0.895
0.0	46.0	10350	0.6552	0.8983
0.0	47.0	10575	0.6559	0.8983
0.0	48.0	10800	0.6560	0.8983
0.0	49.0	11025	0.6556	0.9017
0.0	50.0	11250	0.6560	0.9017

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_3x_deit_base_adamax_00001_fold5

smids_3x_deit_base_adamax_00001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_3x_deit_base_adamax_00001_fold5