learning_rate: 5e-06
train_batch_size: 2
eval_batch_size: 2
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 Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Bg	Accuracy Head	Iou Bg	Iou Head
0.5565	2.5641	100	0.3927	0.4967	0.5584	0.9241	0.9510	0.1659	0.9237	0.0697
0.4096	5.1282	200	0.2417	0.4908	0.5078	0.9647	0.9973	0.0183	0.9647	0.0169
0.1814	7.6923	300	0.1784	0.4843	0.5014	0.9657	0.9998	0.0030	0.9657	0.0030
0.2171	10.2564	400	0.1415	0.4839	0.5000	0.9678	1.0000	0.0	0.9678	0.0
0.2484	12.8205	500	0.1329	0.4888	0.5051	0.9672	0.9999	0.0104	0.9672	0.0104
0.1531	15.3846	600	0.1211	0.5441	0.5619	0.9692	0.9981	0.1258	0.9691	0.1191
0.1601	17.9487	700	0.1141	0.5646	0.5846	0.9699	0.9974	0.1717	0.9697	0.1595
0.251	20.5128	800	0.0988	0.6005	0.6294	0.9708	0.9951	0.2637	0.9705	0.2305
0.1685	23.0769	900	0.0949	0.6359	0.6772	0.9719	0.9930	0.3615	0.9716	0.3002
0.0764	25.6410	1000	0.0969	0.6266	0.6652	0.9719	0.9933	0.3371	0.9716	0.2816
0.0915	28.2051	1100	0.0855	0.6589	0.7059	0.9737	0.9926	0.4192	0.9734	0.3444
0.1204	30.7692	1200	0.0849	0.6736	0.7274	0.9737	0.9916	0.4631	0.9732	0.3740
0.1037	33.3333	1300	0.0811	0.6619	0.7132	0.9734	0.9918	0.4345	0.9731	0.3507
0.1096	35.8974	1400	0.0856	0.6720	0.7410	0.9729	0.9890	0.4930	0.9725	0.3716
0.1051	38.4615	1500	0.0836	0.6800	0.7603	0.9725	0.9873	0.5332	0.9720	0.3880
0.2067	41.0256	1600	0.0786	0.6785	0.7414	0.9739	0.9903	0.4924	0.9735	0.3835
0.102	43.5897	1700	0.0786	0.6719	0.7272	0.9742	0.9915	0.4629	0.9738	0.3701
0.1705	46.1538	1800	0.0784	0.6733	0.7315	0.9738	0.9910	0.4720	0.9734	0.3732
0.0728	48.7179	1900	0.0778	0.6685	0.7265	0.9735	0.9908	0.4621	0.9731	0.3638

ypark-bioinfo/segformer-b5-finetuned-ce-head-image2

segformer-b5-finetuned-ce-head-image2