vit-base-patch16-384-finetuned-humid-classes-14

This model is a fine-tuned version of google/vit-base-patch16-384 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0272
• Accuracy: 1.0
• F1 Macro: 1.0
• Precision Macro: 1.0
• Recall Macro: 1.0
• Precision Dry: 1.0
• Recall Dry: 1.0
• F1 Dry: 1.0
• Precision Notdry: 1.0
• Recall Notdry: 1.0
• F1 Notdry: 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: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Precision Macro	Recall Macro	Precision Dry	Recall Dry	F1 Dry	Precision Notdry	Recall Notdry	F1 Notdry
No log	1.0	5	0.4903	0.8387	0.4561	0.4194	0.5	0.0	0.0	0.0	0.8387	1.0	0.9123
0.5129	2.0	10	0.1949	0.9355	0.8565	0.9643	0.8	1.0	0.6	0.75	0.9286	1.0	0.9630
0.5129	3.0	15	0.0272	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0634	4.0	20	0.0054	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0634	5.0	25	0.0010	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0065	6.0	30	0.0020	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0065	7.0	35	0.0003	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0007	8.0	40	0.0002	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0007	9.0	45	0.0002	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0005	10.0	50	0.0001	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0005	11.0	55	0.0303	0.9839	0.9713	0.9545	0.9904	0.9091	1.0	0.9524	1.0	0.9808	0.9903
0.0002	12.0	60	0.0001	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0002	13.0	65	0.0001	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0001	14.0	70	0.0001	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0001	15.0	75	0.0001	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0001	16.0	80	0.0001	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0001	17.0	85	0.0001	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0001	18.0	90	0.0001	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0001	19.0	95	0.0001	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0001	20.0	100	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0001	21.0	105	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	22.0	110	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	23.0	115	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	24.0	120	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	25.0	125	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	26.0	130	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	27.0	135	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	28.0	140	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	29.0	145	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	30.0	150	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	31.0	155	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	32.0	160	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	33.0	165	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	34.0	170	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	35.0	175	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	36.0	180	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	37.0	185	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	38.0	190	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	39.0	195	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	40.0	200	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	41.0	205	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	42.0	210	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	43.0	215	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	44.0	220	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	45.0	225	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	46.0	230	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	47.0	235	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	48.0	240	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	49.0	245	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	50.0	250	0.0000	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.56.1
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0