learning_rate: 6e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
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
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
0.1022	3.3333	20	0.4204	0.3471	0.8163	0.6581	[0.6530308100792869, 0.041100380361457724]	[0.6532356038276368, 0.9793546043470364]
0.1234	6.6667	40	0.2997	0.4003	0.8705	0.7485	[0.7446855665173218, 0.05595585009979972]	[0.7447273429560723, 0.9963068353817279]
0.116	10.0	60	0.2426	0.3744	0.8502	0.7050	[0.7005221840869044, 0.048270520670456375]	[0.7005228283311338, 0.9999394563177333]
0.0713	13.3333	80	0.1847	0.4548	0.9134	0.8309	[0.8283848991291921, 0.08119565538497897]	[0.8284047068344745, 0.9984258642610644]
0.0613	16.6667	100	0.1679	0.4767	0.9266	0.8596	[0.8574643240091739, 0.09592692615038234]	[0.8575203130532347, 0.9957013985590604]
0.0606	20.0	120	0.1573	0.4844	0.9308	0.8689	[0.8668924560713012, 0.10192647743136342]	[0.8669634112134491, 0.9946116122782588]
0.0569	23.3333	140	0.1671	0.4696	0.9223	0.8507	[0.8483979036599507, 0.09074613365102478]	[0.8484478390222144, 0.9961252043349277]
0.0509	26.6667	160	0.1542	0.5033	0.9393	0.8897	[0.8880656029542663, 0.11847345933811282]	[0.888193828142603, 0.9904946418841194]
0.0457	30.0	180	0.1479	0.4980	0.9364	0.8843	[0.8825517210305678, 0.11351175025332796]	[0.882683208335824, 0.9901919234727856]
0.0549	33.3333	200	0.1521	0.4838	0.9302	0.8682	[0.8662130685188233, 0.10141069509468457]	[0.8662911376689306, 0.9940667191378579]
0.0432	36.6667	220	0.1453	0.4951	0.9361	0.8810	[0.8791674636220519, 0.11095925630235044]	[0.8792620625278773, 0.9929163891747896]
0.0479	40.0	240	0.1438	0.5018	0.9387	0.8882	[0.8865286508237181, 0.11708224519729546]	[0.8866533928661753, 0.9907368166131865]
0.0595	43.3333	260	0.1451	0.5006	0.9379	0.8870	[0.8853163134601609, 0.11595630816776416]	[0.8854449558791747, 0.9904340982018527]
0.0676	46.6667	280	0.1381	0.5114	0.9421	0.8979	[0.896406539783129, 0.12647991502360886]	[0.896574715709221, 0.9876490888175818]
0.1247	50.0	300	0.1388	0.5113	0.9419	0.8978	[0.8963151627718803, 0.12634131601986504]	[0.8964882674011707, 0.9872858267239814]

Framework versions

Transformers 4.52.4
Pytorch 2.7.1+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Jedrzej-Smok/2025-06-07_17-00-56

2025-06-07_17-00-56

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Jedrzej-Smok/
2025-06-07_17-00-56