smids_10x_beit_large_adamax_001_fold2

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

• Loss: 1.4058
• Accuracy: 0.8536

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
0.6414	1.0	750	0.6828	0.6639
0.5428	2.0	1500	0.5438	0.7754
0.4614	3.0	2250	0.4523	0.8336
0.4233	4.0	3000	0.4215	0.8236
0.4304	5.0	3750	0.4599	0.7903
0.3335	6.0	4500	0.4118	0.8336
0.3481	7.0	5250	0.4939	0.8253
0.3092	8.0	6000	0.4308	0.8486
0.2568	9.0	6750	0.4756	0.8353
0.331	10.0	7500	0.4715	0.8619
0.2403	11.0	8250	0.5349	0.8469
0.2162	12.0	9000	0.5922	0.8136
0.2489	13.0	9750	0.5818	0.8419
0.0972	14.0	10500	0.6218	0.8419
0.1212	15.0	11250	0.5371	0.8436
0.1175	16.0	12000	0.6818	0.8286
0.1011	17.0	12750	0.8719	0.8120
0.179	18.0	13500	0.7106	0.8486
0.1325	19.0	14250	0.6119	0.8552
0.111	20.0	15000	0.7905	0.8552
0.0431	21.0	15750	0.8636	0.8469
0.0973	22.0	16500	0.9921	0.8403
0.0529	23.0	17250	0.7563	0.8536
0.1212	24.0	18000	1.1228	0.8103
0.0377	25.0	18750	1.0572	0.8386
0.035	26.0	19500	0.8767	0.8536
0.0591	27.0	20250	0.9535	0.8652
0.0188	28.0	21000	1.1035	0.8536
0.0402	29.0	21750	1.1575	0.8586
0.0333	30.0	22500	1.1473	0.8669
0.0255	31.0	23250	1.0948	0.8469
0.0283	32.0	24000	1.4345	0.8419
0.0262	33.0	24750	1.1277	0.8552
0.0004	34.0	25500	1.2002	0.8519
0.0058	35.0	26250	1.1085	0.8586
0.0265	36.0	27000	1.2506	0.8436
0.0298	37.0	27750	1.1890	0.8602
0.0146	38.0	28500	1.5719	0.8486
0.0266	39.0	29250	1.2137	0.8486
0.0079	40.0	30000	1.2207	0.8586
0.0077	41.0	30750	1.1783	0.8636
0.0004	42.0	31500	1.2606	0.8552
0.0014	43.0	32250	1.6455	0.8453
0.0004	44.0	33000	1.4264	0.8436
0.015	45.0	33750	1.4403	0.8536
0.0002	46.0	34500	1.2419	0.8552
0.002	47.0	35250	1.3338	0.8536
0.0101	48.0	36000	1.5464	0.8469
0.0086	49.0	36750	1.3979	0.8536
0.0061	50.0	37500	1.4058	0.8536

Framework versions

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