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
0.7414	3.3333	20	0.6209	0.3992	0.8508	0.7511	[0.7477178392760251, 0.05065796974271984]	[0.7482103681055993, 0.9533810143042913]
0.6089	6.6667	40	0.5275	0.4764	0.8995	0.8660	[0.8642165676769401, 0.08850784340303879]	[0.8650224347078344, 0.9340052015604682]
0.517	10.0	60	0.3998	0.5088	0.8955	0.9044	[0.9031587598304224, 0.11436576241045515]	[0.9046074752960978, 0.8864759427828348]
0.5871	13.3333	80	0.3450	0.5283	0.8973	0.9223	[0.9213860470917075, 0.13521638252799353]	[0.9230586903716335, 0.8715214564369311]
0.3965	16.6667	100	0.3205	0.5188	0.9020	0.9134	[0.9123392467298979, 0.12531805451317066]	[0.913754074444277, 0.8902470741222367]
0.3443	20.0	120	0.3047	0.5325	0.8952	0.9260	[0.9251324738009505, 0.1398834918728734]	[0.9269181583328128, 0.8633940182054617]
0.3276	23.3333	140	0.2844	0.5377	0.8866	0.9310	[0.9301903499557261, 0.14517577335787726]	[0.9322806231005832, 0.8409622886866059]
0.3731	26.6667	160	0.2697	0.5292	0.9010	0.9227	[0.9217238741771051, 0.13669421320413097]	[0.9233039838602397, 0.8786736020806242]
0.2375	30.0	180	0.2632	0.5582	0.8737	0.9460	[0.9454203497868684, 0.17104256236868834]	[0.9481015937645844, 0.7992847854356306]
0.3766	33.3333	200	0.2491	0.5473	0.8905	0.9374	[0.9366662419483023, 0.1578767749405814]	[0.9387547175358202, 0.8421976592977893]
0.3007	36.6667	220	0.2485	0.5547	0.8838	0.9429	[0.9422258145514996, 0.16720826398245753]	[0.9445820456190767, 0.8230169050715215]
0.2649	40.0	240	0.2435	0.5601	0.8780	0.9467	[0.9460545290960498, 0.17417282634612957]	[0.9486289288299776, 0.8074122236671001]
0.2646	43.3333	260	0.2448	0.5655	0.8697	0.9504	[0.9498796452006463, 0.18108350793175695]	[0.9527419585996039, 0.7867360208062418]
0.2366	46.6667	280	0.2481	0.5679	0.8711	0.9515	[0.9509886448050693, 0.18473938415126537]	[0.9538324581163665, 0.7883615084525357]
0.3606	50.0	300	0.2428	0.5681	0.8738	0.9514	[0.9508537456717293, 0.18541517999483778]	[0.9536211566093274, 0.7940182054616385]

Framework versions

Transformers 4.52.4
Pytorch 2.7.0+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Jedrzej-Smok/2025-06-07_15-28-05

2025-06-07_15-28-05

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Jedrzej-Smok/
2025-06-07_15-28-05