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: 0.8747
Accuracy: 0.92

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
0.1226	1.0	750	0.2826	0.89
0.1	2.0	1500	0.3891	0.9017
0.0601	3.0	2250	0.4750	0.9133
0.0263	4.0	3000	0.4903	0.9117
0.0141	5.0	3750	0.6938	0.905
0.0263	6.0	4500	0.7445	0.895
0.0152	7.0	5250	0.5895	0.92
0.0017	8.0	6000	0.6688	0.92
0.0043	9.0	6750	0.6499	0.9167
0.0	10.0	7500	0.7976	0.91
0.011	11.0	8250	0.6899	0.9183
0.0	12.0	9000	0.6947	0.905
0.0	13.0	9750	0.8213	0.9067
0.0	14.0	10500	0.6853	0.9217
0.0	15.0	11250	0.8220	0.9117
0.0	16.0	12000	0.6897	0.9217
0.0038	17.0	12750	0.7869	0.9167
0.0004	18.0	13500	0.7956	0.9233
0.0031	19.0	14250	0.8745	0.9067
0.0	20.0	15000	0.7439	0.92
0.0	21.0	15750	0.7389	0.9233
0.0	22.0	16500	0.7135	0.925
0.0028	23.0	17250	0.7301	0.925
0.0	24.0	18000	0.7434	0.9283
0.0	25.0	18750	0.7538	0.9233
0.0	26.0	19500	0.7620	0.9233
0.0	27.0	20250	0.7318	0.9233
0.0	28.0	21000	0.7471	0.92
0.0	29.0	21750	0.7685	0.9183
0.0046	30.0	22500	0.8050	0.92
0.0	31.0	23250	0.7778	0.92
0.0	32.0	24000	0.7888	0.9217
0.0	33.0	24750	0.7725	0.9233
0.0	34.0	25500	0.8185	0.9167
0.0	35.0	26250	0.8187	0.92
0.0	36.0	27000	0.8276	0.92
0.0031	37.0	27750	0.8218	0.9217
0.0	38.0	28500	0.8408	0.92
0.0	39.0	29250	0.8462	0.9183
0.0	40.0	30000	0.8525	0.92
0.0	41.0	30750	0.8553	0.92
0.0	42.0	31500	0.8584	0.92
0.0	43.0	32250	0.8634	0.9183
0.0	44.0	33000	0.8639	0.92
0.0	45.0	33750	0.8671	0.92
0.0	46.0	34500	0.8704	0.92
0.0	47.0	35250	0.8722	0.92
0.0	48.0	36000	0.8729	0.92
0.0	49.0	36750	0.8728	0.92
0.0	50.0	37500	0.8747	0.92

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_10x_deit_base_adamax_0001_fold5

smids_10x_deit_base_adamax_0001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_10x_deit_base_adamax_0001_fold5