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: 0.3897
Accuracy: 0.87

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
1.0499	1.0	750	1.0678	0.4483
1.0069	2.0	1500	1.0201	0.5333
0.9342	3.0	2250	0.9596	0.605
0.8668	4.0	3000	0.8944	0.65
0.8215	5.0	3750	0.8304	0.6833
0.7386	6.0	4500	0.7725	0.7233
0.7073	7.0	5250	0.7219	0.75
0.6732	8.0	6000	0.6781	0.7667
0.6382	9.0	6750	0.6410	0.7817
0.5894	10.0	7500	0.6100	0.795
0.5595	11.0	8250	0.5840	0.7967
0.5115	12.0	9000	0.5616	0.81
0.5204	13.0	9750	0.5423	0.8133
0.5584	14.0	10500	0.5257	0.8183
0.4766	15.0	11250	0.5110	0.8233
0.4665	16.0	12000	0.4984	0.825
0.4224	17.0	12750	0.4872	0.8267
0.4651	18.0	13500	0.4771	0.8283
0.4708	19.0	14250	0.4682	0.8333
0.4353	20.0	15000	0.4602	0.8367
0.3692	21.0	15750	0.4528	0.8417
0.4104	22.0	16500	0.4465	0.8433
0.4734	23.0	17250	0.4407	0.845
0.4505	24.0	18000	0.4355	0.8467
0.4228	25.0	18750	0.4307	0.85
0.4446	26.0	19500	0.4264	0.85
0.3547	27.0	20250	0.4224	0.85
0.3891	28.0	21000	0.4188	0.8517
0.4084	29.0	21750	0.4156	0.8533
0.3837	30.0	22500	0.4127	0.855
0.3728	31.0	23250	0.4101	0.8583
0.3097	32.0	24000	0.4075	0.8583
0.4329	33.0	24750	0.4053	0.8583
0.4029	34.0	25500	0.4033	0.86
0.3546	35.0	26250	0.4014	0.8617
0.3774	36.0	27000	0.3998	0.8633
0.3804	37.0	27750	0.3982	0.8633
0.3895	38.0	28500	0.3968	0.865
0.3722	39.0	29250	0.3955	0.8667
0.4041	40.0	30000	0.3944	0.8683
0.3565	41.0	30750	0.3935	0.87
0.4081	42.0	31500	0.3926	0.87
0.3738	43.0	32250	0.3919	0.87
0.3617	44.0	33000	0.3913	0.87
0.3447	45.0	33750	0.3908	0.87
0.3297	46.0	34500	0.3904	0.87
0.3716	47.0	35250	0.3901	0.87
0.3734	48.0	36000	0.3899	0.87
0.3771	49.0	36750	0.3898	0.87
0.3572	50.0	37500	0.3897	0.87

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_10x_deit_base_sgd_0001_fold3

smids_10x_deit_base_sgd_0001_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_10x_deit_base_sgd_0001_fold3