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
0.5743	3.3333	20	0.6017	0.4759	0.7859	0.8586	[0.8564118834462178, 0.0954557567752326]	[0.861742124554327, 0.7101236909020385]
0.4711	6.6667	40	0.4817	0.5298	0.8729	0.9049	[0.9031873130866761, 0.15650560010284265]	[0.9062997087914986, 0.8395035124768349]
0.3848	10.0	60	0.3339	0.5689	0.8582	0.9358	[0.934774800660872, 0.20295302617659636]	[0.9392459670815023, 0.7772270827048227]
0.3405	13.3333	80	0.3063	0.5535	0.8810	0.9228	[0.9213677105234038, 0.1855898533007335]	[0.9245828278594093, 0.8374779123389217]
0.2973	16.6667	100	0.2701	0.5692	0.8691	0.9347	[0.9335508469578806, 0.20482286394760346]	[0.9375479448378736, 0.8005861311037366]
0.2777	20.0	120	0.2441	0.5845	0.8536	0.9451	[0.9441671982980432, 0.22485078537377146]	[0.9490685862183518, 0.7582209197086583]
0.2456	23.3333	140	0.2327	0.5996	0.8429	0.9533	[0.9525597775138479, 0.2466471877282688]	[0.9581305654182733, 0.7276214282635866]
0.2404	26.6667	160	0.2407	0.5930	0.8479	0.9498	[0.949018373630904, 0.2369776602484643]	[0.9542847995084527, 0.7415420419773305]
0.2251	30.0	180	0.2278	0.5944	0.8507	0.9502	[0.9493567200869548, 0.23952070981383972]	[0.9545152123360622, 0.7469292763866742]
0.2351	33.3333	200	0.2208	0.6115	0.8303	0.9593	[0.9586956321881349, 0.26431963320779434]	[0.9649596685016412, 0.6956859026849976]
0.2075	36.6667	220	0.2222	0.6064	0.8433	0.9560	[0.9553426620902953, 0.2575440099108331]	[0.9609686222145727, 0.7257251217514976]
0.2097	40.0	240	0.2152	0.6118	0.8369	0.9587	[0.9581012059892993, 0.26546503941831784]	[0.9640741059473344, 0.7096496142740163]
0.1953	43.3333	260	0.2225	0.6168	0.8199	0.9622	[0.9616694355212185, 0.2718751636382678]	[0.9684565764355229, 0.6712925052794897]
0.2011	46.6667	280	0.2155	0.6113	0.8408	0.9582	[0.9575186693978239, 0.2651509124755374]	[0.9633116153049639, 0.7182260914536913]
0.2061	50.0	300	0.2162	0.6159	0.8314	0.9607	[0.96015408447985, 0.2715553463981983]	[0.9664143229795618, 0.6963323708141189]

Framework versions

Transformers 4.52.4
Pytorch 2.7.1+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Jedrzej-Smok/2025-06-07_18-37-40

2025-06-07_18-37-40

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Jedrzej-Smok/
2025-06-07_18-37-40