vit-base-patch16-384-finetuned-humid-classes-5

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: 0.1373
• Accuracy: 0.9857
• F1 Macro: 0.9908
• Precision Macro: 0.99
• Recall Macro: 0.992
• Precision Dry: 1.0
• Recall Dry: 1.0
• F1 Dry: 1.0
• Precision Firm: 1.0
• Recall Firm: 0.96
• F1 Firm: 0.9796
• Precision Humid: 1.0
• Recall Humid: 1.0
• F1 Humid: 1.0
• Precision Lump: 0.95
• Recall Lump: 1.0
• F1 Lump: 0.9744
• 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 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 Rockies	Recall Rockies	F1 Rockies
No log	1.0	6	1.2363	0.6	0.3819	0.3786	0.4043	0.75	0.5625	0.6429	0.5641	0.88	0.6875	0.0	0.0	0.0	0.5789	0.5789	0.5789	0.0	0.0	0.0
1.3734	2.0	12	0.8426	0.7857	0.5130	0.4805	0.5524	0.9412	1.0	0.9697	0.8214	0.92	0.8679	0.0	0.0	0.0	0.64	0.8421	0.7273	0.0	0.0	0.0
1.3734	3.0	18	0.5603	0.8143	0.5299	0.4954	0.5709	0.9412	1.0	0.9697	0.8276	0.96	0.8889	0.0	0.0	0.0	0.7083	0.8947	0.7907	0.0	0.0	0.0
0.7064	4.0	24	0.4073	0.8286	0.7533	0.8007	0.7288	1.0	1.0	1.0	0.7742	0.96	0.8571	0.75	0.6	0.6667	0.8125	0.6842	0.7429	0.6667	0.4	0.5
0.3606	5.0	30	0.2730	0.9143	0.8330	0.9503	0.792	1.0	1.0	1.0	0.96	0.96	0.96	1.0	0.4	0.5714	0.7917	1.0	0.8837	1.0	0.6	0.75
0.3606	6.0	36	0.1925	0.9286	0.9068	0.8964	0.9204	1.0	1.0	1.0	0.96	0.96	0.96	0.8	0.8	0.8	0.8889	0.8421	0.8649	0.8333	1.0	0.9091
0.1629	7.0	42	0.1624	0.9429	0.9051	0.9647	0.8720	1.0	1.0	1.0	0.96	0.96	0.96	1.0	0.8	0.8889	0.8636	1.0	0.9268	1.0	0.6	0.75
0.1629	8.0	48	0.1373	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0644	9.0	54	0.1421	0.9571	0.9354	0.9692	0.9120	0.9412	1.0	0.9697	1.0	0.96	0.9796	1.0	0.8	0.8889	0.9048	1.0	0.95	1.0	0.8	0.8889
0.027	10.0	60	0.2243	0.9429	0.9046	0.9652	0.8720	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	0.6	0.75	0.8261	1.0	0.9048	1.0	0.8	0.8889
0.027	11.0	66	0.1655	0.9429	0.9315	0.9386	0.9284	1.0	1.0	1.0	0.8929	1.0	0.9434	1.0	1.0	1.0	1.0	0.8421	0.9143	0.8	0.8	0.8
0.0263	12.0	72	0.1483	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0263	13.0	78	0.1119	0.9714	0.9815	0.9815	0.9815	1.0	1.0	1.0	0.96	0.96	0.96	1.0	1.0	1.0	0.9474	0.9474	0.9474	1.0	1.0	1.0
0.01	14.0	84	0.1262	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0137	15.0	90	0.2554	0.9429	0.9113	0.9139	0.9309	1.0	1.0	1.0	1.0	0.96	0.9796	0.625	1.0	0.7692	0.9444	0.8947	0.9189	1.0	0.8	0.8889
0.0137	16.0	96	0.1648	0.9571	0.9313	0.9727	0.9120	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	0.6	0.75	0.8636	1.0	0.9268	1.0	1.0	1.0
0.0079	17.0	102	0.1664	0.9714	0.9672	0.9561	0.9815	1.0	1.0	1.0	1.0	0.96	0.9796	0.8333	1.0	0.9091	0.9474	0.9474	0.9474	1.0	1.0	1.0
0.0079	18.0	108	0.2060	0.9429	0.9220	0.9634	0.9015	1.0	1.0	1.0	0.96	0.96	0.96	1.0	0.6	0.75	0.8571	0.9474	0.9	1.0	1.0	1.0
0.0094	19.0	114	0.1282	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0021	20.0	120	0.2166	0.9429	0.8960	0.9206	0.9015	0.9412	1.0	0.9697	1.0	0.96	0.9796	0.7143	1.0	0.8333	0.9474	0.9474	0.9474	1.0	0.6	0.75
0.0021	21.0	126	0.2326	0.9429	0.9030	0.9610	0.8720	0.9412	1.0	0.9697	1.0	0.96	0.9796	1.0	0.6	0.75	0.8636	1.0	0.9268	1.0	0.8	0.8889
0.0028	22.0	132	0.1260	0.9429	0.9478	0.9395	0.9604	1.0	1.0	1.0	0.9231	0.96	0.9412	1.0	1.0	1.0	0.9412	0.8421	0.8889	0.8333	1.0	0.9091
0.0028	23.0	138	0.1338	0.9714	0.9504	0.9567	0.952	1.0	1.0	1.0	1.0	0.96	0.9796	0.8333	1.0	0.9091	0.95	1.0	0.9744	1.0	0.8	0.8889
0.0013	24.0	144	0.1150	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0009	25.0	150	0.0915	0.9571	0.9720	0.9735	0.9709	1.0	1.0	1.0	0.9231	0.96	0.9412	1.0	1.0	1.0	0.9444	0.8947	0.9189	1.0	1.0	1.0
0.0009	26.0	156	0.0875	0.9571	0.9720	0.9735	0.9709	1.0	1.0	1.0	0.9231	0.96	0.9412	1.0	1.0	1.0	0.9444	0.8947	0.9189	1.0	1.0	1.0
0.0006	27.0	162	0.0835	0.9571	0.9720	0.9735	0.9709	1.0	1.0	1.0	0.9231	0.96	0.9412	1.0	1.0	1.0	0.9444	0.8947	0.9189	1.0	1.0	1.0
0.0006	28.0	168	0.0799	0.9571	0.9720	0.9735	0.9709	1.0	1.0	1.0	0.9231	0.96	0.9412	1.0	1.0	1.0	0.9444	0.8947	0.9189	1.0	1.0	1.0
0.0005	29.0	174	0.0780	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0005	30.0	180	0.0782	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0005	31.0	186	0.0799	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0004	32.0	192	0.0815	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0004	33.0	198	0.0828	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0004	34.0	204	0.0838	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0004	35.0	210	0.0842	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0004	36.0	216	0.0847	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0004	37.0	222	0.0849	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0004	38.0	228	0.0852	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0004	39.0	234	0.0855	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0003	40.0	240	0.0855	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0003	41.0	246	0.0855	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0003	42.0	252	0.0855	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0003	43.0	258	0.0857	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0003	44.0	264	0.0859	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0003	45.0	270	0.0859	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0003	46.0	276	0.0859	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0003	47.0	282	0.0860	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0003	48.0	288	0.0860	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0003	49.0	294	0.0860	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0
0.0003	50.0	300	0.0860	0.9857	0.9908	0.99	0.992	1.0	1.0	1.0	1.0	0.96	0.9796	1.0	1.0	1.0	0.95	1.0	0.9744	1.0	1.0	1.0

Framework versions

• Transformers 4.56.1
• Pytorch 2.5.1+cu124
• Datasets 4.0.0
• Tokenizers 0.22.0