swin-base-patch4-window12-384-finetuned-humid-classes-1

This model is a fine-tuned version of microsoft/swin-base-patch4-window12-384 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0096
• 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 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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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 Rockies	Recall Rockies	F1 Rockies
1.4441	1.0	10	1.3328	0.5238	0.2903	0.2337	0.4	0.0	0.0	0.0	0.7368	1.0	0.8485	0.0	0.0	0.0	0.4318	1.0	0.6032	0.0	0.0	0.0
1.0125	2.0	20	0.7622	0.6984	0.5484	0.6673	0.5922	1.0	0.8182	0.9	0.7778	1.0	0.875	0.0	0.0	0.0	0.5588	1.0	0.7170	1.0	0.1429	0.25
0.4585	3.0	30	0.3032	0.8571	0.7864	0.9251	0.7723	1.0	1.0	1.0	0.9333	1.0	0.9655	1.0	0.2	0.3333	0.6923	0.9474	0.8	1.0	0.7143	0.8333
0.2434	4.0	40	0.4579	0.8571	0.8227	0.8926	0.8131	1.0	1.0	1.0	0.8235	1.0	0.9032	1.0	0.4	0.5714	0.875	0.7368	0.8	0.7647	0.9286	0.8387
0.171	5.0	50	0.1754	0.9365	0.9152	0.9523	0.8989	1.0	1.0	1.0	0.9333	1.0	0.9655	1.0	0.6	0.75	0.8947	0.8947	0.8947	0.9333	1.0	0.9655
0.0951	6.0	60	0.1278	0.9683	0.9638	0.9533	0.9789	1.0	1.0	1.0	1.0	1.0	1.0	0.8333	1.0	0.9091	1.0	0.8947	0.9444	0.9333	1.0	0.9655
0.2476	7.0	70	0.1856	0.9365	0.8874	0.9581	0.8695	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.4	0.5714	0.8571	0.9474	0.9	0.9333	1.0	0.9655
0.0706	8.0	80	0.2010	0.9206	0.8749	0.9433	0.8589	1.0	1.0	1.0	0.9333	1.0	0.9655	1.0	0.4	0.5714	0.85	0.8947	0.8718	0.9333	1.0	0.9655
0.1555	9.0	90	0.5145	0.8413	0.8034	0.89	0.7875	1.0	1.0	1.0	0.7	1.0	0.8235	1.0	0.4	0.5714	0.85	0.8947	0.8718	0.9	0.6429	0.75
0.0746	10.0	100	0.3848	0.9365	0.8874	0.9581	0.8695	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.4	0.5714	0.8571	0.9474	0.9	0.9333	1.0	0.9655
0.2615	11.0	110	0.5946	0.8571	0.7836	0.9190	0.7723	1.0	1.0	1.0	0.875	1.0	0.9333	1.0	0.2	0.3333	0.72	0.9474	0.8182	1.0	0.7143	0.8333
0.1522	12.0	120	0.2942	0.9206	0.8735	0.9464	0.8552	1.0	1.0	1.0	0.875	1.0	0.9333	1.0	0.4	0.5714	0.8571	0.9474	0.9	1.0	0.9286	0.9630
0.0401	13.0	130	0.1079	0.9524	0.8997	0.9727	0.8800	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.4	0.5714	0.8636	1.0	0.9268	1.0	1.0	1.0
0.0526	14.0	140	0.0778	0.9683	0.9495	0.9495	0.9495	1.0	1.0	1.0	1.0	1.0	1.0	0.8	0.8	0.8	0.9474	0.9474	0.9474	1.0	1.0	1.0
0.0078	15.0	150	0.0907	0.9524	0.9179	0.93	0.9095	1.0	1.0	1.0	1.0	1.0	1.0	0.75	0.6	0.6667	0.9	0.9474	0.9231	1.0	1.0	1.0
0.0256	16.0	160	0.1176	0.9524	0.9509	0.9400	0.9684	1.0	1.0	1.0	0.9333	1.0	0.9655	0.8333	1.0	0.9091	1.0	0.8421	0.9143	0.9333	1.0	0.9655
0.0168	17.0	170	0.1039	0.9524	0.9298	0.925	0.9571	1.0	1.0	1.0	1.0	1.0	1.0	0.625	1.0	0.7692	1.0	1.0	1.0	1.0	0.7857	0.88
0.0004	18.0	180	0.1826	0.9524	0.8997	0.9727	0.8800	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.4	0.5714	0.8636	1.0	0.9268	1.0	1.0	1.0
0.002	19.0	190	0.1104	0.9683	0.9539	0.9429	0.9752	1.0	1.0	1.0	1.0	1.0	1.0	0.7143	1.0	0.8333	1.0	0.9474	0.9730	1.0	0.9286	0.9630
0.0176	20.0	200	1.0026	0.8889	0.8116	0.9462	0.7971	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.2	0.3333	0.7308	1.0	0.8444	1.0	0.7857	0.88
0.0328	21.0	210	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
0.0001	22.0	220	0.1568	0.9524	0.8997	0.9727	0.8800	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.4	0.5714	0.8636	1.0	0.9268	1.0	1.0	1.0
0.0005	23.0	230	0.0403	0.9683	0.9638	0.9533	0.9789	1.0	1.0	1.0	1.0	1.0	1.0	0.8333	1.0	0.9091	1.0	0.8947	0.9444	0.9333	1.0	0.9655
0.0002	24.0	240	0.0450	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0002	25.0	250	0.1338	0.9524	0.8997	0.9727	0.8800	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.4	0.5714	0.8636	1.0	0.9268	1.0	1.0	1.0
0.0	26.0	260	0.0212	0.9841	0.9764	0.9667	0.9895	1.0	1.0	1.0	1.0	1.0	1.0	0.8333	1.0	0.9091	1.0	0.9474	0.9730	1.0	1.0	1.0
0.0	27.0	270	0.0644	0.9683	0.9556	0.9429	0.9789	1.0	1.0	1.0	1.0	1.0	1.0	0.7143	1.0	0.8333	1.0	0.8947	0.9444	1.0	1.0	1.0
0.0001	28.0	280	0.0017	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0	29.0	290	0.0342	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	30.0	300	0.0710	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	31.0	310	0.0844	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	32.0	320	0.0876	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	33.0	330	0.0894	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	34.0	340	0.0896	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	35.0	350	0.0823	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	36.0	360	0.0757	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	37.0	370	0.0721	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	38.0	380	0.0705	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	39.0	390	0.0669	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	40.0	400	0.0660	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0001	41.0	410	0.0691	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	42.0	420	0.0700	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	43.0	430	0.0711	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	44.0	440	0.0716	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0002	45.0	450	0.0804	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	46.0	460	0.0911	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	47.0	470	0.0935	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	48.0	480	0.0938	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0	49.0	490	0.0938	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	1.0	1.0	1.0
0.0041	50.0	500	0.0941	0.9683	0.9400	0.9810	0.9200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	0.6	0.75	0.9048	1.0	0.95	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