ViT_bean_leaves_model

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0320
• 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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0335	0.0769	10	0.9775	0.6165
0.8744	0.1538	20	0.8419	0.8647
0.7576	0.2308	30	0.6803	0.9248
0.5918	0.3077	40	0.5376	0.9624
0.4833	0.3846	50	0.4257	0.9699
0.3873	0.4615	60	0.3395	0.9624
0.3508	0.5385	70	0.2656	0.9774
0.3008	0.6154	80	0.2369	0.9549
0.2282	0.6923	90	0.1895	0.9925
0.204	0.7692	100	0.1596	0.9699
0.213	0.8462	110	0.1350	0.9925
0.1618	0.9231	120	0.1679	0.9624
0.1657	1.0	130	0.1061	0.9925
0.0997	1.0769	140	0.1020	0.9925
0.1185	1.1538	150	0.0892	0.9925
0.1329	1.2308	160	0.0903	1.0
0.0671	1.3077	170	0.0767	1.0
0.0634	1.3846	180	0.0696	0.9925
0.0618	1.4615	190	0.0631	1.0
0.0896	1.5385	200	0.0687	0.9925
0.0519	1.6154	210	0.0641	0.9925
0.052	1.6923	220	0.0580	0.9925
0.049	1.7692	230	0.0707	0.9925
0.1221	1.8462	240	0.0723	0.9925
0.0798	1.9231	250	0.0645	0.9850
0.043	2.0	260	0.0590	0.9925
0.0461	2.0769	270	0.0549	0.9850
0.0391	2.1538	280	0.0626	0.9925
0.0368	2.2308	290	0.0612	0.9925
0.0357	2.3077	300	0.0510	0.9925
0.035	2.3846	310	0.0448	1.0
0.0339	2.4615	320	0.0437	1.0
0.0352	2.5385	330	0.0454	0.9925
0.0315	2.6154	340	0.0457	0.9925
0.1151	2.6923	350	0.0390	1.0
0.0324	2.7692	360	0.0386	1.0
0.0298	2.8462	370	0.0370	1.0
0.0316	2.9231	380	0.0363	1.0
0.0295	3.0	390	0.0363	1.0
0.0284	3.0769	400	0.0363	1.0
0.0278	3.1538	410	0.0357	1.0
0.0296	3.2308	420	0.0352	1.0
0.0299	3.3077	430	0.0348	1.0
0.0277	3.3846	440	0.0351	1.0
0.0301	3.4615	450	0.0331	1.0
0.0281	3.5385	460	0.0328	1.0
0.0279	3.6154	470	0.0325	1.0
0.0283	3.6923	480	0.0324	1.0
0.0278	3.7692	490	0.0323	1.0
0.0286	3.8462	500	0.0322	1.0
0.0267	3.9231	510	0.0321	1.0
0.0276	4.0	520	0.0320	1.0

Framework versions

• Transformers 4.57.2
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1