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
0.6562	3.3333	20	0.5566	0.4987	0.8429	0.9133	[0.9125895998838364, 0.08476764199655766]	[0.9147900945922318, 0.7709366031828855]
0.5271	6.6667	40	0.4555	0.5455	0.9145	0.9460	[0.9454982326469336, 0.14544985377601927]	[0.9466693153345972, 0.8823375945734412]
0.4616	10.0	60	0.3066	0.5725	0.9123	0.9604	[0.9600099456372201, 0.1849195111044865]	[0.9613932237431719, 0.8631185320462649]
0.3821	13.3333	80	0.2667	0.5687	0.9242	0.9578	[0.957396401009473, 0.18006159260888693]	[0.9585068470202028, 0.8898165057831116]
0.3448	16.6667	100	0.2202	0.5912	0.9124	0.9675	[0.967178140941677, 0.21517714685375822]	[0.9686425790458021, 0.8561614053395947]
0.3275	20.0	120	0.1745	0.6220	0.8940	0.9769	[0.9766966785892113, 0.2673349801803872]	[0.9786565577874957, 0.809374728237238]
0.2942	23.3333	140	0.1737	0.6040	0.9195	0.9710	[0.9707003003925397, 0.23726232122034221]	[0.9720589945009626, 0.8670319158187668]
0.2722	26.6667	160	0.1659	0.6129	0.9148	0.9736	[0.9733996073284072, 0.25245312098638584]	[0.9748886140539907, 0.8546830159144273]
0.2543	30.0	180	0.1671	0.6099	0.9222	0.9724	[0.9721855781880081, 0.24765084075173097]	[0.973506302334459, 0.8709452995912688]
0.2434	33.3333	200	0.1546	0.6118	0.9220	0.9729	[0.9726959992467106, 0.2508903937797843]	[0.9740281021226266, 0.8699017305852683]
0.2364	36.6667	220	0.1450	0.6256	0.9149	0.9766	[0.9763736705676753, 0.2748211530368916]	[0.9778958286226408, 0.8519001652317593]
0.241	40.0	240	0.1386	0.6237	0.9161	0.9761	[0.9758866661426161, 0.27146447212173097]	[0.9773776905873727, 0.8548569440820941]
0.2324	43.3333	260	0.1380	0.6259	0.9135	0.9767	[0.9765032766358045, 0.2752184945023964]	[0.9780560303119905, 0.8489433863814245]
0.2225	46.6667	280	0.1390	0.6294	0.9096	0.9776	[0.977452246413169, 0.28139108146681036]	[0.9790968835736511, 0.8401600139142534]
0.2273	50.0	300	0.1396	0.6243	0.9172	0.9762	[0.9759748011458678, 0.2726769605401516]	[0.977444517577787, 0.8569440820940951]

Framework versions

Transformers 4.52.4
Pytorch 2.7.1+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Jedrzej-Smok/2025-06-07_18-48-28

2025-06-07_18-48-28

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Jedrzej-Smok/
2025-06-07_18-48-28