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
0.6745	3.3333	20	0.5978	0.4486	0.9073	0.8795	[0.8792585725695995, 0.017860506479991847]	[0.879392440243525, 0.9351657235246564]
0.5496	6.6667	40	0.5022	0.4738	0.9272	0.9209	[0.920770655213334, 0.02692067399595304]	[0.9209143390860786, 0.9335489086499595]
0.4703	10.0	60	0.3784	0.4871	0.9258	0.9400	[0.9399072716657771, 0.03438979163616845]	[0.9401024749270545, 0.9115602263540824]
0.4141	13.3333	80	0.3172	0.4931	0.9218	0.9477	[0.9475581134494786, 0.03856030397294307]	[0.9477898030043872, 0.8958771220695231]
0.3792	16.6667	100	0.3023	0.4984	0.9291	0.9534	[0.9532926789920304, 0.043493132049657574]	[0.9535062257599718, 0.904607922392886]
0.4068	20.0	120	0.2513	0.5013	0.9171	0.9570	[0.956923618828988, 0.045613562970936494]	[0.9572001070690235, 0.87696038803557]
0.2992	23.3333	140	0.2545	0.4963	0.9317	0.9510	[0.9508551802204485, 0.04176658673061551]	[0.9510508520909783, 0.9123686337914308]
0.2685	26.6667	160	0.2388	0.4997	0.9269	0.9549	[0.954843551250531, 0.044643072252873006]	[0.9550704965990398, 0.8987873888439774]
0.3352	30.0	180	0.2262	0.5005	0.9317	0.9555	[0.9554249073598174, 0.0456266965751532]	[0.9556320394560742, 0.90767987065481]
0.274	33.3333	200	0.2221	0.5018	0.9309	0.9569	[0.9567826347059905, 0.04684883798807849]	[0.9569965999889893, 0.9047696038803557]
0.2603	36.6667	220	0.2015	0.5081	0.9181	0.9634	[0.9633527328405835, 0.05293875308981049]	[0.9636409542811473, 0.8725949878738885]
0.2332	40.0	240	0.2070	0.5055	0.9269	0.9606	[0.9605173856205181, 0.05042906700748585]	[0.9607584435505151, 0.8931285367825385]
0.2724	43.3333	260	0.2003	0.5066	0.9231	0.9618	[0.96176435198523, 0.05149620534453212]	[0.9620258066720707, 0.8842360549717058]
0.2289	46.6667	280	0.2068	0.5039	0.9318	0.9589	[0.9588259967620772, 0.04905140973488568]	[0.9590407830466453, 0.904607922392886]
0.2335	50.0	300	0.2025	0.5066	0.9250	0.9617	[0.9616451958563784, 0.051558584180440965]	[0.9618978553922732, 0.8881164106709781]

Framework versions

Transformers 4.52.4
Pytorch 2.7.0+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Jedrzej-Smok/2025-06-01_23-17-44

2025-06-01_23-17-44

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Jedrzej-Smok/
2025-06-01_23-17-44