beitv2-base-beans

This model is a fine-tuned version of timm/beitv2_base_patch16_224.in1k_ft_in22k on the AI-Lab-Makerere/beans dataset. It achieves the following results on the evaluation set:

• Loss: 0.0003
• Accuracy: 1.0

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 1337
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 50.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0435	1.0	130	0.1193	0.9624
0.1536	2.0	260	0.0023	1.0
0.183	3.0	390	0.0015	1.0
0.2256	4.0	520	0.0386	0.9850
0.0555	5.0	650	0.0340	0.9850
0.0713	6.0	780	0.0728	0.9925
0.0082	7.0	910	0.0411	0.9925
0.0085	8.0	1040	0.1002	0.9850
0.0733	9.0	1170	0.0004	1.0
0.0215	10.0	1300	0.0003	1.0
0.0501	11.0	1430	0.0634	0.9774
0.0338	12.0	1560	0.0248	0.9925
0.0045	13.0	1690	0.0939	0.9850
0.0013	14.0	1820	0.0373	0.9850
0.0002	15.0	1950	0.0515	0.9925
0.0074	16.0	2080	0.0017	1.0
0.0005	17.0	2210	0.0588	0.9925
0.0046	18.0	2340	0.0715	0.9850
0.0618	19.0	2470	0.0003	1.0
0.0007	20.0	2600	0.0697	0.9850
0.0001	21.0	2730	0.1105	0.9774
0.0214	22.0	2860	0.0930	0.9850
0.0004	23.0	2990	0.0272	0.9925
0.1619	24.0	3120	0.0024	1.0
0.0015	25.0	3250	0.0003	1.0
0.0148	26.0	3380	0.1312	0.9774
0.0482	27.0	3510	0.0873	0.9850
0.0001	28.0	3640	0.0721	0.9850
0.0954	29.0	3770	0.0143	0.9925
0.1373	30.0	3900	0.0449	0.9925
0.0076	31.0	4030	0.0435	0.9925
0.0028	32.0	4160	0.0101	0.9925
0.0001	33.0	4290	0.0414	0.9850
0.001	34.0	4420	0.0017	1.0
0.0055	35.0	4550	0.0733	0.9925
0.1471	36.0	4680	0.1221	0.9774
0.0484	37.0	4810	0.1473	0.9850
0.0014	38.0	4940	0.0748	0.9925
0.1825	39.0	5070	0.1072	0.9850
0.0	40.0	5200	0.0687	0.9925
0.0081	41.0	5330	0.1147	0.9850
0.0557	42.0	5460	0.0630	0.9850
0.0	43.0	5590	0.0162	0.9925
0.0	44.0	5720	0.0463	0.9925
0.0197	45.0	5850	0.0757	0.9850
0.1442	46.0	5980	0.0941	0.9850
0.0019	47.0	6110	0.0760	0.9850
0.0001	48.0	6240	0.0885	0.9850
0.0854	49.0	6370	0.0788	0.9850
0.0005	50.0	6500	0.0707	0.9850

Framework versions

• Transformers 4.54.1
• Pytorch 2.7.1+cu126
• Datasets 4.0.0
• Tokenizers 0.21.4