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
0.6235	3.3333	20	0.6735	0.4360	0.8549	0.8601	[0.8598607304064863, 0.012132624348700612]	[0.8601228013774828, 0.8495973028657052]
0.4787	6.6667	40	0.5766	0.4885	0.7779	0.9523	[0.9521936027299954, 0.024900598728282562]	[0.9529597925501611, 0.602921895486046]
0.4501	10.0	60	0.4254	0.4951	0.7711	0.9610	[0.9609663009722398, 0.029228404085751742]	[0.9617833186129069, 0.5804457763626147]
0.3437	13.3333	80	0.2676	0.5105	0.6187	0.9860	[0.9860270303251719, 0.03491780965343943]	[0.9875259094054225, 0.24985952425547855]
0.2987	16.6667	100	0.2780	0.5066	0.6678	0.9794	[0.9794212133330553, 0.03372846361953581]	[0.9807015020148703, 0.35493538115752016]
0.2937	20.0	120	0.2586	0.5055	0.6962	0.9765	[0.9765106039686313, 0.034499953252095865]	[0.9776688537918161, 0.4146843978273085]
0.2291	23.3333	140	0.2194	0.5168	0.6445	0.9875	[0.9874492021294741, 0.04614586933978569]	[0.988849798892533, 0.30005619029780856]
0.2277	26.6667	160	0.2228	0.5121	0.7012	0.9811	[0.9810896151540873, 0.04303200061392065]	[0.9822424972320917, 0.42011612661547104]
0.1897	30.0	180	0.1919	0.5197	0.6498	0.9884	[0.9883578575365021, 0.05109669447018845]	[0.989740236030366, 0.30979584191796217]
0.221	33.3333	200	0.2141	0.5205	0.7557	0.9827	[0.982724741788773, 0.05825202579791632]	[0.98366507114198, 0.5278141974152463]
0.2053	36.6667	220	0.1692	0.5245	0.6840	0.9882	[0.9881788293235086, 0.06086432766149676]	[0.9894233072110605, 0.37853530623712306]
0.1787	40.0	240	0.1696	0.5241	0.7223	0.9860	[0.9860313972242506, 0.06216113020236731]	[0.9871156099399505, 0.4573890241618281]
0.1767	43.3333	260	0.1760	0.5223	0.7422	0.9843	[0.9842822394576343, 0.060406183417199326]	[0.9852812183427014, 0.4991571455328713]
0.181	46.6667	280	0.1706	0.5254	0.7296	0.9862	[0.9861655822982544, 0.06460213289581625]	[0.987220746805756, 0.4719985015920584]
0.1993	50.0	300	0.1608	0.5271	0.6974	0.9884	[0.9883605349233235, 0.06584111723004837]	[0.9895515969606716, 0.40531934819254545]

Framework versions

Transformers 4.52.4
Pytorch 2.7.0+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Jedrzej-Smok/2025-06-01_23-28-04

2025-06-01_23-28-04

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Jedrzej-Smok/
2025-06-01_23-28-04