smids_1x_beit_base_rms_0001_fold5

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: 0.6915
• Accuracy: 0.72

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
1.2962	1.0	75	0.9009	0.4967
0.8616	2.0	150	0.8829	0.5333
0.8905	3.0	225	0.8472	0.5367
0.8302	4.0	300	0.9953	0.5067
0.8678	5.0	375	0.8690	0.525
0.8529	6.0	450	0.8769	0.5283
0.8841	7.0	525	0.8786	0.53
0.8327	8.0	600	0.8584	0.5367
0.8106	9.0	675	0.8478	0.5817
0.8163	10.0	750	0.8420	0.54
0.8203	11.0	825	0.8233	0.615
0.849	12.0	900	0.8207	0.56
0.7448	13.0	975	0.9969	0.48
0.8104	14.0	1050	0.8107	0.5717
0.8455	15.0	1125	0.8387	0.56
0.7497	16.0	1200	0.7795	0.5983
0.7595	17.0	1275	0.7579	0.63
0.7118	18.0	1350	0.7723	0.63
0.7898	19.0	1425	0.7567	0.635
0.7627	20.0	1500	0.7797	0.6367
0.8345	21.0	1575	0.7467	0.6217
0.745	22.0	1650	0.7264	0.655
0.7402	23.0	1725	0.7241	0.6633
0.6239	24.0	1800	0.7183	0.665
0.6855	25.0	1875	0.7858	0.6333
0.7229	26.0	1950	0.7404	0.6333
0.7229	27.0	2025	0.7258	0.68
0.7197	28.0	2100	0.6990	0.6917
0.7057	29.0	2175	0.7035	0.68
0.7315	30.0	2250	0.7188	0.6683
0.6562	31.0	2325	0.7484	0.6283
0.6918	32.0	2400	0.6817	0.6917
0.6871	33.0	2475	0.7362	0.6717
0.6724	34.0	2550	0.6752	0.7
0.6677	35.0	2625	0.6742	0.6933
0.6138	36.0	2700	0.6850	0.6867
0.582	37.0	2775	0.6804	0.6817
0.6731	38.0	2850	0.6827	0.6917
0.5577	39.0	2925	0.7025	0.6833
0.5702	40.0	3000	0.6473	0.7117
0.578	41.0	3075	0.6455	0.72
0.6074	42.0	3150	0.6478	0.715
0.6019	43.0	3225	0.6442	0.7
0.5836	44.0	3300	0.6632	0.6983
0.5466	45.0	3375	0.6605	0.68
0.4891	46.0	3450	0.6690	0.715
0.5107	47.0	3525	0.6729	0.7167
0.3981	48.0	3600	0.7111	0.7017
0.434	49.0	3675	0.6850	0.7183
0.3741	50.0	3750	0.6915	0.72

Framework versions

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