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: 0.9415
Accuracy: 0.9067

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
0.3501	1.0	225	0.3758	0.8567
0.1897	2.0	450	0.3539	0.89
0.192	3.0	675	0.3659	0.87
0.1205	4.0	900	0.5440	0.87
0.0584	5.0	1125	0.5709	0.8783
0.0533	6.0	1350	0.5437	0.8933
0.1081	7.0	1575	0.4958	0.8917
0.0507	8.0	1800	0.5623	0.89
0.0576	9.0	2025	0.6335	0.8733
0.0323	10.0	2250	0.7129	0.8867
0.0328	11.0	2475	0.6336	0.8933
0.1145	12.0	2700	0.6382	0.885
0.0008	13.0	2925	0.6581	0.8983
0.0337	14.0	3150	0.7043	0.91
0.0295	15.0	3375	0.6839	0.905
0.0175	16.0	3600	0.6638	0.8983
0.0432	17.0	3825	0.6947	0.8883
0.0184	18.0	4050	0.7199	0.8867
0.0276	19.0	4275	0.8282	0.8767
0.011	20.0	4500	0.7312	0.8933
0.0094	21.0	4725	0.7792	0.8817
0.008	22.0	4950	0.8134	0.8833
0.0128	23.0	5175	0.6449	0.8917
0.0051	24.0	5400	0.9415	0.8983
0.0033	25.0	5625	0.9520	0.8833
0.0003	26.0	5850	0.8717	0.875
0.0001	27.0	6075	0.8347	0.9
0.0178	28.0	6300	0.8466	0.8883
0.0036	29.0	6525	0.9051	0.9
0.0021	30.0	6750	0.9411	0.89
0.0	31.0	6975	0.8526	0.895
0.0	32.0	7200	0.9459	0.8883
0.0028	33.0	7425	0.8486	0.8967
0.0016	34.0	7650	0.8125	0.9083
0.0029	35.0	7875	0.8544	0.9
0.0	36.0	8100	0.7896	0.9
0.0049	37.0	8325	0.8566	0.9033
0.0022	38.0	8550	0.9049	0.9017
0.0	39.0	8775	0.8095	0.9083
0.0	40.0	9000	0.8266	0.91
0.0	41.0	9225	0.8487	0.91
0.0	42.0	9450	0.8743	0.9117
0.0027	43.0	9675	0.9417	0.9067
0.0	44.0	9900	0.9107	0.905
0.0	45.0	10125	0.9200	0.905
0.0	46.0	10350	0.9166	0.905
0.0	47.0	10575	0.9308	0.905
0.0	48.0	10800	0.9335	0.9067
0.0	49.0	11025	0.9388	0.9067
0.0	50.0	11250	0.9415	0.9067

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_3x_deit_small_rms_0001_fold5

smids_3x_deit_small_rms_0001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_3x_deit_small_rms_0001_fold5