smids_3x_deit_base_rms_00001_fold3

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: 0.9351
• Accuracy: 0.9083

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
0.2558	1.0	225	0.2380	0.9167
0.1474	2.0	450	0.2896	0.895
0.0478	3.0	675	0.3355	0.9067
0.0073	4.0	900	0.3566	0.9217
0.0246	5.0	1125	0.4526	0.9
0.0014	6.0	1350	0.5013	0.9067
0.0175	7.0	1575	0.6021	0.9017
0.0203	8.0	1800	0.5721	0.9083
0.0288	9.0	2025	0.5925	0.9083
0.0252	10.0	2250	0.6064	0.91
0.0051	11.0	2475	0.6439	0.9133
0.0001	12.0	2700	0.6659	0.9033
0.0001	13.0	2925	0.6695	0.9083
0.0001	14.0	3150	0.7344	0.9033
0.0001	15.0	3375	0.8923	0.8917
0.0001	16.0	3600	0.7237	0.905
0.0001	17.0	3825	0.7599	0.8983
0.0001	18.0	4050	0.7079	0.91
0.0	19.0	4275	0.6928	0.9117
0.012	20.0	4500	0.7517	0.9117
0.0009	21.0	4725	0.7047	0.9083
0.0065	22.0	4950	0.7383	0.9033
0.0	23.0	5175	0.8215	0.9017
0.0	24.0	5400	0.8602	0.9
0.004	25.0	5625	0.8484	0.8983
0.0	26.0	5850	0.7324	0.9017
0.0	27.0	6075	0.7794	0.9067
0.0	28.0	6300	0.7965	0.9067
0.0048	29.0	6525	0.7845	0.9017
0.0025	30.0	6750	0.8176	0.9067
0.0037	31.0	6975	0.8141	0.9067
0.0	32.0	7200	0.8318	0.9083
0.0	33.0	7425	0.8648	0.9067
0.0	34.0	7650	0.8665	0.9067
0.0	35.0	7875	0.8924	0.9067
0.0	36.0	8100	0.8743	0.9067
0.0	37.0	8325	0.8853	0.905
0.0	38.0	8550	0.9112	0.9083
0.0	39.0	8775	0.9104	0.905
0.0	40.0	9000	0.9178	0.9067
0.0	41.0	9225	0.9148	0.9067
0.0	42.0	9450	0.9212	0.905
0.0	43.0	9675	0.9285	0.905
0.0	44.0	9900	0.9313	0.905
0.0	45.0	10125	0.9285	0.9067
0.0	46.0	10350	0.9309	0.9067
0.0023	47.0	10575	0.9324	0.9067
0.0	48.0	10800	0.9333	0.9083
0.0	49.0	11025	0.9347	0.9083
0.0	50.0	11250	0.9351	0.9083

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2