vit-base-patch32-384-finetuned-humid-classes-32

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: 0.0547
• 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 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: 1.0
• F1 Rockies: 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 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	1.7800	0.2368	0.1544	0.2569	0.2667	0.0	0.0	0.0	1.0	0.1	0.1818	0.0	0.0	0.0	0.3333	0.5	0.4	0.0	0.0	0.0	0.2083	1.0	0.3448
No log	2.0	6	1.4470	0.6053	0.4436	0.4783	0.5417	0.0	0.0	0.0	0.8333	1.0	0.9091	0.4118	1.0	0.5833	0.0	0.0	0.0	1.0	0.25	0.4	0.625	1.0	0.7692
No log	3.0	9	1.2255	0.5526	0.3879	0.4432	0.4917	0.0	0.0	0.0	0.9091	1.0	0.9524	0.5	1.0	0.6667	0.0	0.0	0.0	0.25	0.75	0.375	1.0	0.2	0.3333
1.6327	4.0	12	0.9398	0.7632	0.6865	0.6746	0.7361	1.0	0.6667	0.8	0.9091	1.0	0.9524	0.5385	1.0	0.7	0.0	0.0	0.0	0.6	0.75	0.6667	1.0	1.0	1.0
1.6327	5.0	15	0.6232	0.8947	0.8751	0.8963	0.875	1.0	0.6667	0.8	1.0	1.0	1.0	0.7778	1.0	0.875	1.0	0.8333	0.9091	0.6	0.75	0.6667	1.0	1.0	1.0
1.6327	6.0	18	0.3273	0.9737	0.9651	0.9792	0.9583	1.0	1.0	1.0	1.0	1.0	1.0	0.875	1.0	0.9333	1.0	1.0	1.0	1.0	0.75	0.8571	1.0	1.0	1.0
0.6436	7.0	21	0.2521	0.9211	0.9038	0.9213	0.8972	1.0	1.0	1.0	1.0	1.0	1.0	0.7778	1.0	0.875	1.0	0.8333	0.9091	0.75	0.75	0.75	1.0	0.8	0.8889
0.6436	8.0	24	0.1373	0.9474	0.9167	0.9524	0.9167	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	0.5	0.6667	0.7143	1.0	0.8333
0.6436	9.0	27	0.1552	0.9474	0.9287	0.9375	0.9250	1.0	1.0	1.0	1.0	1.0	1.0	0.875	1.0	0.9333	1.0	1.0	1.0	0.75	0.75	0.75	1.0	0.8	0.8889
0.1165	10.0	30	0.0547	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.1165	11.0	33	0.0510	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.1165	12.0	36	0.0959	0.9737	0.9630	0.9667	0.9667	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	0.8	0.8889
0.1165	13.0	39	0.0668	0.9474	0.9287	0.9375	0.9250	1.0	1.0	1.0	1.0	1.0	1.0	0.875	1.0	0.9333	1.0	1.0	1.0	0.75	0.75	0.75	1.0	0.8	0.8889
0.023	14.0	42	0.0748	0.9737	0.9651	0.9792	0.9583	1.0	1.0	1.0	1.0	1.0	1.0	0.875	1.0	0.9333	1.0	1.0	1.0	1.0	0.75	0.8571	1.0	1.0	1.0
0.023	15.0	45	0.0459	0.9737	0.9651	0.9792	0.9583	1.0	1.0	1.0	1.0	1.0	1.0	0.875	1.0	0.9333	1.0	1.0	1.0	1.0	0.75	0.8571	1.0	1.0	1.0
0.023	16.0	48	0.0526	0.9737	0.9630	0.9667	0.9667	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	0.8	0.8889
0.0091	17.0	51	0.0736	0.9737	0.9651	0.9792	0.9583	1.0	1.0	1.0	1.0	1.0	1.0	0.875	1.0	0.9333	1.0	1.0	1.0	1.0	0.75	0.8571	1.0	1.0	1.0
0.0091	18.0	54	0.0861	0.9474	0.9402	0.9630	0.9306	1.0	1.0	1.0	1.0	1.0	1.0	0.7778	1.0	0.875	1.0	0.8333	0.9091	1.0	0.75	0.8571	1.0	1.0	1.0
0.0091	19.0	57	0.0599	0.9737	0.9737	0.9792	0.9722	1.0	1.0	1.0	1.0	1.0	1.0	0.875	1.0	0.9333	1.0	0.8333	0.9091	1.0	1.0	1.0	1.0	1.0	1.0
0.0036	20.0	60	0.0223	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0036	21.0	63	0.0082	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0036	22.0	66	0.0048	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0036	23.0	69	0.0039	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0021	24.0	72	0.0036	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0021	25.0	75	0.0036	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0021	26.0	78	0.0041	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0016	27.0	81	0.0051	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0016	28.0	84	0.0067	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0016	29.0	87	0.0087	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0013	30.0	90	0.0108	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0013	31.0	93	0.0129	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0013	32.0	96	0.0139	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0013	33.0	99	0.0143	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0011	34.0	102	0.0144	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0011	35.0	105	0.0143	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0011	36.0	108	0.0140	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.001	37.0	111	0.0134	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.001	38.0	114	0.0126	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.001	39.0	117	0.0118	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.001	40.0	120	0.0110	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.001	41.0	123	0.0104	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.001	42.0	126	0.0100	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.001	43.0	129	0.0098	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0009	44.0	132	0.0096	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0009	45.0	135	0.0095	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0009	46.0	138	0.0093	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0009	47.0	141	0.0092	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0009	48.0	144	0.0092	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0009	49.0	147	0.0092	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0009	50.0	150	0.0091	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	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0

Framework versions

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