vit-base-patch32-384-finetuned-humid-classes-23

This model is a fine-tuned version of google/vit-base-patch32-384 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.3280
• Accuracy: 0.975
• F1 Macro: 0.9429
• Precision Macro: 0.9583
• Recall Macro: 0.9444
• Precision Dry: 0.75
• Recall Dry: 1.0
• F1 Dry: 0.8571
• Precision Firm: 1.0
• Recall Firm: 1.0
• F1 Firm: 1.0
• Precision Humid: 1.0
• Recall Humid: 1.0
• F1 Humid: 1.0
• Precision Lump: 1.0
• Recall Lump: 1.0
• F1 Lump: 1.0
• Precision Moist: 1.0
• Recall Moist: 1.0
• F1 Moist: 1.0
• Precision Rockies: 1.0
• Recall Rockies: 0.6667
• F1 Rockies: 0.8

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 Firm	Recall Firm	F1 Firm	Precision Humid	Recall Humid	F1 Humid	Precision Lump	Recall Lump	F1 Lump	Precision Moist	Recall Moist	F1 Moist	Precision Rockies	Recall Rockies	F1 Rockies
No log	1.0	3	1.5435	0.5	0.3556	0.3492	0.4702	0.3333	1.0	0.5	0.9091	0.7143	0.8	0.3529	0.8571	0.5	0.0	0.0	0.0	0.5	0.25	0.3333	0.0	0.0	0.0
No log	2.0	6	1.2110	0.625	0.4181	0.3860	0.4815	0.6667	0.6667	0.6667	0.7778	1.0	0.875	0.5385	1.0	0.7	0.3333	0.2222	0.2667	0.0	0.0	0.0	0.0	0.0	0.0
No log	3.0	9	0.8478	0.8	0.6987	0.7397	0.6918	1.0	0.6667	0.8	0.8667	0.9286	0.8966	1.0	1.0	1.0	0.5714	0.8889	0.6957	0.0	0.0	0.0	1.0	0.6667	0.8
1.3406	4.0	12	0.5639	0.95	0.9458	0.9792	0.9259	1.0	0.6667	0.8	0.875	1.0	0.9333	1.0	1.0	1.0	1.0	0.8889	0.9412	1.0	1.0	1.0	1.0	1.0	1.0
1.3406	5.0	15	0.3280	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
1.3406	6.0	18	0.1772	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.4007	7.0	21	0.1064	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.4007	8.0	24	0.0869	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.4007	9.0	27	0.0793	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0472	10.0	30	0.1017	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0472	11.0	33	0.0910	0.975	0.9481	0.9667	0.9444	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.8	1.0	0.8889	1.0	0.6667	0.8
0.0472	12.0	36	0.0987	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0472	13.0	39	0.1177	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0081	14.0	42	0.1150	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0081	15.0	45	0.0849	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0081	16.0	48	0.0781	0.975	0.9481	0.9667	0.9444	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.8	1.0	0.8889	1.0	0.6667	0.8
0.0034	17.0	51	0.0792	0.975	0.9481	0.9667	0.9444	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.8	1.0	0.8889	1.0	0.6667	0.8
0.0034	18.0	54	0.0728	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0034	19.0	57	0.0811	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0018	20.0	60	0.0928	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0018	21.0	63	0.1002	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0018	22.0	66	0.1039	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0018	23.0	69	0.1021	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0013	24.0	72	0.0999	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0013	25.0	75	0.0973	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0013	26.0	78	0.0931	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0011	27.0	81	0.0901	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0011	28.0	84	0.0875	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0011	29.0	87	0.0861	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0009	30.0	90	0.0856	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0009	31.0	93	0.0854	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0009	32.0	96	0.0853	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0009	33.0	99	0.0853	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0009	34.0	102	0.0856	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0009	35.0	105	0.0860	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0009	36.0	108	0.0869	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0008	37.0	111	0.0875	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0008	38.0	114	0.0882	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0008	39.0	117	0.0887	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0008	40.0	120	0.0894	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0008	41.0	123	0.0898	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0008	42.0	126	0.0901	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0008	43.0	129	0.0903	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0007	44.0	132	0.0907	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0007	45.0	135	0.0907	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0007	46.0	138	0.0907	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0007	47.0	141	0.0906	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0007	48.0	144	0.0905	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0007	49.0	147	0.0905	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8
0.0007	50.0	150	0.0905	0.975	0.9429	0.9583	0.9444	0.75	1.0	0.8571	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6667	0.8

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0