vit-base-beans-demo-v5

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.3663
• Accuracy: 0.4856

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: 0.0002
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.4389	0.1894	100	2.5163	0.4748
2.1742	0.3788	200	2.4580	0.4802
2.1934	0.5682	300	2.4167	0.4836
2.4634	0.7576	400	2.4232	0.4789
2.5892	0.9470	500	2.4008	0.4829
2.3142	1.1364	600	2.3910	0.4849
2.6178	1.3258	700	2.3910	0.4849
2.5871	1.5152	800	2.3954	0.4856
2.5426	1.7045	900	2.3848	0.4856
2.077	1.8939	1000	2.3795	0.4849
2.3489	2.0833	1100	2.3777	0.4849
2.6511	2.2727	1200	2.3717	0.4856
2.4127	2.4621	1300	2.3727	0.4856
2.4054	2.6515	1400	2.3753	0.4849
2.628	2.8409	1500	2.3736	0.4856
2.5406	3.0303	1600	2.3688	0.4856
2.4249	3.2197	1700	2.3726	0.4856
2.3137	3.4091	1800	2.3719	0.4856
2.4248	3.5985	1900	2.3667	0.4856
2.0676	3.7879	2000	2.3666	0.4856
2.2021	3.9773	2100	2.3663	0.4856

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1