smids_1x_deit_small_rms_0001_fold3

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: 1.1553
• Accuracy: 0.7017

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
1.14	1.0	75	1.1120	0.335
1.2072	2.0	150	1.0986	0.3333
0.9539	3.0	225	0.9334	0.4917
0.9512	4.0	300	0.9203	0.4983
0.911	5.0	375	1.0159	0.445
0.9061	6.0	450	0.9432	0.5133
0.8557	7.0	525	0.9707	0.5517
0.796	8.0	600	0.8853	0.5633
0.837	9.0	675	0.8169	0.5667
0.8343	10.0	750	0.8015	0.5867
0.8478	11.0	825	0.8424	0.5533
0.7471	12.0	900	0.8480	0.5733
0.7041	13.0	975	0.8701	0.55
0.7689	14.0	1050	0.7602	0.625
0.6385	15.0	1125	0.8263	0.5933
0.7131	16.0	1200	0.7809	0.595
0.7152	17.0	1275	0.8940	0.565
0.7023	18.0	1350	0.7651	0.66
0.6514	19.0	1425	0.7331	0.6783
0.7116	20.0	1500	0.7305	0.6883
0.6713	21.0	1575	0.7155	0.6733
0.634	22.0	1650	0.7520	0.6883
0.664	23.0	1725	0.7448	0.6767
0.5579	24.0	1800	0.7383	0.6967
0.6505	25.0	1875	0.7438	0.69
0.6223	26.0	1950	0.7719	0.65
0.5322	27.0	2025	0.7151	0.7017
0.5674	28.0	2100	0.7078	0.6817
0.493	29.0	2175	0.7341	0.71
0.585	30.0	2250	0.7150	0.6867
0.534	31.0	2325	0.7507	0.6967
0.458	32.0	2400	0.7455	0.6983
0.512	33.0	2475	0.6902	0.6967
0.5074	34.0	2550	0.6773	0.6983
0.512	35.0	2625	0.6981	0.7083
0.452	36.0	2700	0.7620	0.7083
0.4013	37.0	2775	0.7597	0.7033
0.4319	38.0	2850	0.7472	0.705
0.4551	39.0	2925	0.8012	0.7067
0.4136	40.0	3000	0.7673	0.7133
0.4092	41.0	3075	0.8184	0.7067
0.412	42.0	3150	0.8145	0.7183
0.4199	43.0	3225	0.8148	0.725
0.3632	44.0	3300	0.8661	0.69
0.2849	45.0	3375	0.9491	0.7167
0.3044	46.0	3450	0.9227	0.7017
0.2713	47.0	3525	0.9951	0.6983
0.22	48.0	3600	1.0641	0.7017
0.2276	49.0	3675	1.1632	0.6983
0.2183	50.0	3750	1.1553	0.7017

Framework versions

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