smids_3x_beit_base_rms_001_fold2

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

• Loss: 0.8871
• Accuracy: 0.7737

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
1.1063	1.0	225	1.1925	0.3627
0.8848	2.0	450	0.8623	0.5557
0.9929	3.0	675	0.7924	0.5774
0.7922	4.0	900	0.7743	0.5973
0.7804	5.0	1125	0.7554	0.5940
0.7536	6.0	1350	0.7911	0.5740
0.7389	7.0	1575	0.8973	0.5524
0.8004	8.0	1800	0.7349	0.6140
0.7283	9.0	2025	0.7228	0.6356
0.7381	10.0	2250	0.7154	0.6389
0.8566	11.0	2475	0.7154	0.6373
0.725	12.0	2700	0.6853	0.6539
0.7139	13.0	2925	0.6833	0.6722
0.708	14.0	3150	0.7156	0.6489
0.6892	15.0	3375	0.6841	0.6955
0.7392	16.0	3600	0.6648	0.6905
0.7123	17.0	3825	0.6864	0.6689
0.6752	18.0	4050	0.6534	0.7088
0.7193	19.0	4275	0.7054	0.6755
0.6734	20.0	4500	0.6500	0.6855
0.649	21.0	4725	0.6222	0.6872
0.7173	22.0	4950	0.6280	0.7321
0.6723	23.0	5175	0.6016	0.7587
0.6406	24.0	5400	0.6206	0.7221
0.6216	25.0	5625	0.6173	0.7338
0.6154	26.0	5850	0.5917	0.7488
0.6137	27.0	6075	0.6327	0.7304
0.597	28.0	6300	0.6319	0.7155
0.6292	29.0	6525	0.6003	0.7321
0.615	30.0	6750	0.5967	0.7554
0.5842	31.0	6975	0.5866	0.7587
0.5976	32.0	7200	0.5968	0.7388
0.5096	33.0	7425	0.5717	0.7671
0.4883	34.0	7650	0.5888	0.7804
0.5258	35.0	7875	0.6027	0.7820
0.49	36.0	8100	0.6052	0.7820
0.5271	37.0	8325	0.5944	0.7654
0.4464	38.0	8550	0.6867	0.7504
0.3796	39.0	8775	0.6032	0.7820
0.4175	40.0	9000	0.6446	0.7704
0.3633	41.0	9225	0.6564	0.7804
0.4496	42.0	9450	0.6467	0.7770
0.2811	43.0	9675	0.6703	0.7754
0.3066	44.0	9900	0.7311	0.7754
0.3558	45.0	10125	0.7685	0.7787
0.2645	46.0	10350	0.7874	0.7754
0.2214	47.0	10575	0.8226	0.7737
0.2321	48.0	10800	0.8600	0.7704
0.314	49.0	11025	0.8728	0.7770
0.1915	50.0	11250	0.8871	0.7737

Framework versions

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