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: 0.6280
Accuracy: 0.7917

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
1.1036	1.0	225	1.0989	0.3817
1.0669	2.0	450	1.0855	0.4283
1.054	3.0	675	1.0721	0.4483
1.0504	4.0	900	1.0584	0.4933
1.0338	5.0	1125	1.0440	0.5167
1.0048	6.0	1350	1.0283	0.535
1.0001	7.0	1575	1.0115	0.57
0.9895	8.0	1800	0.9932	0.59
0.9628	9.0	2025	0.9742	0.6033
0.944	10.0	2250	0.9544	0.6283
0.9313	11.0	2475	0.9345	0.63
0.9444	12.0	2700	0.9144	0.6383
0.8913	13.0	2925	0.8947	0.6667
0.8686	14.0	3150	0.8758	0.6783
0.8767	15.0	3375	0.8579	0.7
0.8703	16.0	3600	0.8412	0.7083
0.8299	17.0	3825	0.8255	0.7217
0.8366	18.0	4050	0.8106	0.7267
0.8333	19.0	4275	0.7965	0.735
0.8046	20.0	4500	0.7834	0.7417
0.7972	21.0	4725	0.7709	0.7467
0.7678	22.0	4950	0.7592	0.7533
0.7921	23.0	5175	0.7481	0.755
0.7726	24.0	5400	0.7377	0.76
0.7352	25.0	5625	0.7280	0.7633
0.7455	26.0	5850	0.7189	0.7683
0.7316	27.0	6075	0.7102	0.7733
0.6935	28.0	6300	0.7023	0.7733
0.7272	29.0	6525	0.6948	0.7733
0.6961	30.0	6750	0.6878	0.7783
0.6838	31.0	6975	0.6813	0.7817
0.684	32.0	7200	0.6752	0.7817
0.6981	33.0	7425	0.6696	0.785
0.6903	34.0	7650	0.6644	0.7867
0.6587	35.0	7875	0.6596	0.7883
0.6872	36.0	8100	0.6552	0.7883
0.6671	37.0	8325	0.6511	0.7883
0.6452	38.0	8550	0.6474	0.7883
0.6514	39.0	8775	0.6441	0.7883
0.6682	40.0	9000	0.6412	0.7883
0.6552	41.0	9225	0.6385	0.7883
0.6851	42.0	9450	0.6362	0.79
0.6234	43.0	9675	0.6341	0.79
0.6753	44.0	9900	0.6324	0.79
0.6452	45.0	10125	0.6310	0.7917
0.6292	46.0	10350	0.6298	0.7917
0.6474	47.0	10575	0.6290	0.7917
0.6437	48.0	10800	0.6284	0.7917
0.6514	49.0	11025	0.6281	0.7917
0.6703	50.0	11250	0.6280	0.7917

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_3x_deit_base_sgd_0001_fold4

smids_3x_deit_base_sgd_0001_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_3x_deit_base_sgd_0001_fold4