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: 0.9621
Accuracy: 0.8819

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
0.283	1.0	225	0.2854	0.8785
0.1203	2.0	450	0.3573	0.8719
0.0448	3.0	675	0.4385	0.8785
0.0289	4.0	900	0.5496	0.8719
0.0119	5.0	1125	0.6072	0.8785
0.0601	6.0	1350	0.7142	0.8752
0.0063	7.0	1575	0.6692	0.8835
0.0179	8.0	1800	0.6438	0.8802
0.007	9.0	2025	0.7381	0.8918
0.0008	10.0	2250	0.8145	0.8835
0.0007	11.0	2475	0.7915	0.8785
0.0001	12.0	2700	0.8073	0.8819
0.0002	13.0	2925	0.8884	0.8819
0.0	14.0	3150	0.8205	0.8902
0.0	15.0	3375	0.8044	0.8785
0.0	16.0	3600	0.8365	0.8752
0.0029	17.0	3825	0.8450	0.8785
0.0	18.0	4050	0.7920	0.8935
0.0	19.0	4275	0.8363	0.8819
0.0	20.0	4500	0.8889	0.8852
0.0	21.0	4725	0.8448	0.8852
0.0	22.0	4950	0.9311	0.8686
0.0029	23.0	5175	0.9101	0.8719
0.0	24.0	5400	0.8819	0.8835
0.004	25.0	5625	0.8836	0.8769
0.0	26.0	5850	0.8454	0.8869
0.0	27.0	6075	0.8634	0.8819
0.0	28.0	6300	0.8917	0.8852
0.0	29.0	6525	0.9393	0.8719
0.0031	30.0	6750	0.8807	0.8885
0.0	31.0	6975	0.9119	0.8719
0.0	32.0	7200	0.9056	0.8785
0.0	33.0	7425	0.9065	0.8785
0.0	34.0	7650	0.9233	0.8785
0.0	35.0	7875	0.9182	0.8835
0.0027	36.0	8100	0.9235	0.8752
0.0	37.0	8325	0.9102	0.8835
0.0	38.0	8550	0.9395	0.8819
0.0031	39.0	8775	0.9367	0.8819
0.0	40.0	9000	0.9527	0.8819
0.0	41.0	9225	0.9525	0.8769
0.0	42.0	9450	0.9483	0.8852
0.0	43.0	9675	0.9512	0.8819
0.0	44.0	9900	0.9531	0.8819
0.0	45.0	10125	0.9615	0.8802
0.0	46.0	10350	0.9575	0.8819
0.0	47.0	10575	0.9539	0.8819
0.0	48.0	10800	0.9592	0.8819
0.0023	49.0	11025	0.9609	0.8819
0.0023	50.0	11250	0.9621	0.8819

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_0001_fold2

smids_3x_deit_base_adamax_0001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_3x_deit_base_adamax_0001_fold2