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: 0.6633
Accuracy: 0.9183

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
0.2813	1.0	375	0.3216	0.8783
0.2111	2.0	750	0.2635	0.905
0.0915	3.0	1125	0.2534	0.92
0.0599	4.0	1500	0.2640	0.92
0.1269	5.0	1875	0.2938	0.9217
0.0531	6.0	2250	0.3570	0.9133
0.0327	7.0	2625	0.3536	0.9183
0.0024	8.0	3000	0.4103	0.915
0.0012	9.0	3375	0.4352	0.92
0.0003	10.0	3750	0.4932	0.9133
0.0002	11.0	4125	0.4821	0.9167
0.0002	12.0	4500	0.5091	0.9133
0.0001	13.0	4875	0.5337	0.9167
0.0001	14.0	5250	0.5297	0.9167
0.0001	15.0	5625	0.5462	0.9117
0.0	16.0	6000	0.5551	0.92
0.0001	17.0	6375	0.5844	0.915
0.0	18.0	6750	0.5622	0.9133
0.0	19.0	7125	0.5918	0.9167
0.0	20.0	7500	0.5875	0.915
0.0	21.0	7875	0.5930	0.915
0.0	22.0	8250	0.6046	0.915
0.0049	23.0	8625	0.6585	0.9083
0.0	24.0	9000	0.6134	0.9183
0.0	25.0	9375	0.6543	0.91
0.0	26.0	9750	0.6179	0.9183
0.0	27.0	10125	0.6159	0.9167
0.0	28.0	10500	0.6181	0.9183
0.0	29.0	10875	0.6318	0.9167
0.0036	30.0	11250	0.6693	0.9133
0.0	31.0	11625	0.6325	0.9183
0.0	32.0	12000	0.6427	0.9183
0.0	33.0	12375	0.6557	0.915
0.0	34.0	12750	0.6550	0.915
0.0	35.0	13125	0.6439	0.915
0.0	36.0	13500	0.6513	0.915
0.0	37.0	13875	0.6496	0.915
0.0	38.0	14250	0.6546	0.915
0.0	39.0	14625	0.6548	0.9167
0.0036	40.0	15000	0.6572	0.9167
0.0	41.0	15375	0.6550	0.9183
0.0	42.0	15750	0.6572	0.9167
0.0	43.0	16125	0.6583	0.9183
0.0	44.0	16500	0.6596	0.9183
0.0	45.0	16875	0.6608	0.9183
0.0	46.0	17250	0.6619	0.9183
0.0	47.0	17625	0.6626	0.9183
0.0	48.0	18000	0.6632	0.9183
0.0	49.0	18375	0.6634	0.9183
0.0	50.0	18750	0.6633	0.9183

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_5x_deit_base_adamax_00001_fold3

smids_5x_deit_base_adamax_00001_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_deit_base_adamax_00001_fold3