Boya1_RMSProp_1-e5_20Epoch_09Momentum_Beit-base-patch16_fold2

This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 3.1168
• Accuracy: 0.6438

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0678	1.0	923	1.1860	0.5962
0.9795	2.0	1846	1.0466	0.6414
0.6213	3.0	2769	1.0577	0.6403
0.3941	4.0	3692	1.2437	0.6424
0.3011	5.0	4615	1.4589	0.6443
0.1999	6.0	5538	1.7644	0.63
0.039	7.0	6461	1.9747	0.64
0.0664	8.0	7384	2.2470	0.6368
0.0635	9.0	8307	2.4483	0.6451
0.0688	10.0	9230	2.6192	0.6516
0.0389	11.0	10153	2.7333	0.6470
0.0075	12.0	11076	2.8548	0.6446
0.0085	13.0	11999	2.9858	0.6416
0.0018	14.0	12922	2.9790	0.6424
0.0034	15.0	13845	3.0326	0.6443
0.009	16.0	14768	3.0570	0.6473
0.0005	17.0	15691	3.1227	0.6419
0.0	18.0	16614	3.1155	0.6449
0.0002	19.0	17537	3.1130	0.6454
0.0002	20.0	18460	3.1168	0.6438

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0
• Datasets 2.14.6
• Tokenizers 0.14.1