smids_1x_deit_small_adamax_0001_fold1

This model is a fine-tuned version of facebook/deit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.6387
• Accuracy: 0.8982

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
0.4614	1.0	76	0.3156	0.8831
0.2855	2.0	152	0.2885	0.8915
0.1652	3.0	228	0.3412	0.8781
0.0912	4.0	304	0.3542	0.8965
0.1011	5.0	380	0.5346	0.8798
0.038	6.0	456	0.4288	0.8982
0.0075	7.0	532	0.5068	0.8998
0.0075	8.0	608	0.5044	0.9098
0.0143	9.0	684	0.4561	0.9032
0.0021	10.0	760	0.5259	0.8982
0.0314	11.0	836	0.5405	0.8932
0.0002	12.0	912	0.5496	0.8965
0.0052	13.0	988	0.5683	0.9098
0.0001	14.0	1064	0.5233	0.9015
0.0093	15.0	1140	0.5621	0.9032
0.0001	16.0	1216	0.5647	0.9048
0.0001	17.0	1292	0.5914	0.8965
0.0072	18.0	1368	0.5464	0.9032
0.0001	19.0	1444	0.5470	0.8982
0.0035	20.0	1520	0.6054	0.8965
0.004	21.0	1596	0.5757	0.9015
0.0036	22.0	1672	0.5664	0.8982
0.0001	23.0	1748	0.6187	0.8948
0.0	24.0	1824	0.5774	0.9048
0.0072	25.0	1900	0.5831	0.8915
0.0032	26.0	1976	0.5874	0.9015
0.0042	27.0	2052	0.5879	0.8998
0.0028	28.0	2128	0.6082	0.8965
0.0055	29.0	2204	0.6022	0.8965
0.0	30.0	2280	0.5996	0.8965
0.0046	31.0	2356	0.6176	0.8948
0.0082	32.0	2432	0.5942	0.8965
0.0	33.0	2508	0.6226	0.8948
0.0	34.0	2584	0.6117	0.8982
0.0101	35.0	2660	0.6208	0.8932
0.0032	36.0	2736	0.6175	0.8948
0.006	37.0	2812	0.6334	0.8932
0.0	38.0	2888	0.6155	0.8982
0.0031	39.0	2964	0.6236	0.8982
0.0	40.0	3040	0.6141	0.8998
0.0026	41.0	3116	0.6351	0.8948
0.0	42.0	3192	0.6313	0.8965
0.0047	43.0	3268	0.6395	0.8932
0.0	44.0	3344	0.6247	0.8998
0.0	45.0	3420	0.6367	0.8982
0.0	46.0	3496	0.6347	0.8982
0.0	47.0	3572	0.6365	0.8982
0.0024	48.0	3648	0.6411	0.8982
0.0	49.0	3724	0.6383	0.8982
0.0	50.0	3800	0.6387	0.8982

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0