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: 0.3080
Accuracy: 0.8835

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: 0.001
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
0.848	1.0	375	0.8270	0.6972
0.5847	2.0	750	0.5900	0.7787
0.4307	3.0	1125	0.4834	0.8087
0.3555	4.0	1500	0.4305	0.8170
0.3374	5.0	1875	0.3988	0.8386
0.2952	6.0	2250	0.3778	0.8419
0.2869	7.0	2625	0.3638	0.8469
0.3216	8.0	3000	0.3556	0.8519
0.2811	9.0	3375	0.3457	0.8502
0.2716	10.0	3750	0.3402	0.8536
0.2527	11.0	4125	0.3330	0.8586
0.2868	12.0	4500	0.3315	0.8586
0.2215	13.0	4875	0.3264	0.8569
0.2463	14.0	5250	0.3210	0.8652
0.2529	15.0	5625	0.3196	0.8702
0.2264	16.0	6000	0.3180	0.8702
0.2664	17.0	6375	0.3174	0.8686
0.2072	18.0	6750	0.3154	0.8719
0.2246	19.0	7125	0.3137	0.8735
0.2657	20.0	7500	0.3140	0.8785
0.2076	21.0	7875	0.3137	0.8752
0.2093	22.0	8250	0.3110	0.8752
0.2136	23.0	8625	0.3099	0.8802
0.1894	24.0	9000	0.3103	0.8752
0.1535	25.0	9375	0.3079	0.8802
0.2471	26.0	9750	0.3091	0.8785
0.1996	27.0	10125	0.3086	0.8785
0.1679	28.0	10500	0.3082	0.8802
0.2106	29.0	10875	0.3091	0.8819
0.1991	30.0	11250	0.3064	0.8852
0.2072	31.0	11625	0.3086	0.8869
0.1837	32.0	12000	0.3065	0.8852
0.1829	33.0	12375	0.3083	0.8869
0.146	34.0	12750	0.3077	0.8852
0.2024	35.0	13125	0.3064	0.8885
0.1685	36.0	13500	0.3081	0.8852
0.1849	37.0	13875	0.3080	0.8852
0.1672	38.0	14250	0.3074	0.8835
0.1673	39.0	14625	0.3082	0.8835
0.1726	40.0	15000	0.3082	0.8852
0.1673	41.0	15375	0.3089	0.8835
0.177	42.0	15750	0.3082	0.8835
0.1916	43.0	16125	0.3076	0.8835
0.1782	44.0	16500	0.3080	0.8835
0.1543	45.0	16875	0.3089	0.8835
0.2141	46.0	17250	0.3081	0.8835
0.1912	47.0	17625	0.3084	0.8835
0.1718	48.0	18000	0.3084	0.8835
0.1897	49.0	18375	0.3080	0.8835
0.1329	50.0	18750	0.3080	0.8835

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_5x_deit_base_sgd_001_fold2

smids_5x_deit_base_sgd_001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_deit_base_sgd_001_fold2