You can deploy this model and start earning money today!

iqranaz230243/
swin-tiny-patch4-window7-224-finetuned-eurosat

Name: swin-tiny-patch4-window7-224-finetuned-eurosat
Rating: 2.5 (6 reviews)

generated_from_trainer

microsoft/swin-tiny-patch4-window7-224

Views

No views yet

swin-tiny-patch4-window7-224-finetuned-eurosat

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1758
Accuracy: 0.4685
F1: 0.2481
Precision: 0.4916
Recall: 0.1894
Auc Roc: 0.8295

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: 2e-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 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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Auc Roc
0.2027	1.0	1963	0.1984	0.3955	0.0496	0.1271	0.0500	0.7076
0.1966	2.0	3926	0.1890	0.4000	0.0776	0.1877	0.0655	0.7667
0.1899	3.0	5889	0.1839	0.4160	0.1013	0.3830	0.0821	0.7890
0.186	4.0	7852	0.1829	0.4555	0.1097	0.3752	0.0904	0.7985
0.1833	5.0	9815	0.1797	0.4205	0.1424	0.3515	0.1073	0.8092
0.1845	6.0	11778	0.1771	0.4400	0.1255	0.4225	0.1026	0.8153
0.1788	7.0	13741	0.1769	0.4430	0.1472	0.3464	0.1114	0.8186
0.1769	8.0	15704	0.1756	0.4426	0.1448	0.3627	0.1132	0.8227
0.1792	9.0	17667	0.1745	0.4323	0.1653	0.3995	0.1252	0.8250
0.1755	10.0	19630	0.1745	0.4319	0.1842	0.4664	0.1400	0.8261
0.171	11.0	21593	0.1735	0.4400	0.1868	0.5672	0.1441	0.8285
0.17	12.0	23556	0.1744	0.4540	0.1907	0.5407	0.1462	0.8293
0.1726	13.0	25519	0.1745	0.4630	0.1750	0.4862	0.1339	0.8304
0.1715	14.0	27482	0.1732	0.4362	0.2047	0.5735	0.1524	0.8308
0.17	15.0	29445	0.1734	0.4504	0.2080	0.4848	0.1581	0.8316
0.168	16.0	31408	0.1736	0.4515	0.2320	0.5226	0.1791	0.8299
0.1688	17.0	33371	0.1729	0.4524	0.2315	0.5568	0.1780	0.8317
0.1663	18.0	35334	0.1748	0.4683	0.2146	0.5260	0.1617	0.8295
0.1631	19.0	37297	0.1747	0.4529	0.2444	0.5011	0.1908	0.8285
0.1649	20.0	39260	0.1748	0.4522	0.2404	0.4746	0.1850	0.8298
0.1634	21.0	41223	0.1747	0.4486	0.2213	0.5125	0.1655	0.8295
0.1621	22.0	43186	0.1745	0.4499	0.2420	0.4825	0.1865	0.8297
0.1605	23.0	45149	0.1753	0.4676	0.2206	0.4963	0.1669	0.8298
0.1573	24.0	47112	0.1762	0.4605	0.2409	0.4814	0.1854	0.8286
0.161	25.0	49075	0.1758	0.4685	0.2481	0.4916	0.1894	0.8295
0.158	26.0	51038	0.1761	0.4604	0.2445	0.4856	0.1883	0.8274
0.1576	27.0	53001	0.1765	0.4608	0.2539	0.4742	0.1981	0.8290
0.1567	28.0	54964	0.1767	0.4558	0.2550	0.4835	0.1959	0.8285
0.1585	29.0	56927	0.1767	0.4602	0.2485	0.4882	0.1898	0.8276
0.1551	29.9851	58860	0.1768	0.4616	0.2527	0.4797	0.1941	0.8281

Framework versions

Transformers 4.51.3
Pytorch 2.5.1+cu121
Datasets 3.5.0
Tokenizers 0.21.1

iqranaz230243/swin-tiny-patch4-window7-224-finetuned-eurosat

swin-tiny-patch4-window7-224-finetuned-eurosat

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

iqranaz230243/
swin-tiny-patch4-window7-224-finetuned-eurosat