Loss is becoming negative

[jindongwang]

Very nice work! During my training, I found that loss can become negative:

Train Epoch: 198 [0/100 (0%)]	Loss1: 0.024868	 Loss2: 0.022132	  Discrepancy: 0.018226

Test set: Average loss: -0.0588, Accuracy C1: 9449/10000 (94%) Accuracy C2: 9509/10000 (95%) Accuracy Ensemble: 9554/10000 (96%) 

recording record/usps_mnist_k_4_alluse_no_onestep_False_1_test.txt
Train Epoch: 199 [0/100 (0%)]	Loss1: 0.012343	 Loss2: 0.020431	  Discrepancy: 0.030520

Test set: Average loss: -0.0581, Accuracy C1: 9419/10000 (94%) Accuracy C2: 9518/10000 (95%) Accuracy Ensemble: 9537/10000 (95%) 

recording record/usps_mnist_k_4_alluse_no_onestep_False_1_test.txt

Do you think this is normal?

[postBG]

I guess so.

[JiaoJinyang]

Because the author used the nll_loss...

[Dr-Zhou]

Very nice work! During my training, I found that loss can become negative:

Train Epoch: 198 [0/100 (0%)]	Loss1: 0.024868	 Loss2: 0.022132	  Discrepancy: 0.018226

Test set: Average loss: -0.0588, Accuracy C1: 9449/10000 (94%) Accuracy C2: 9509/10000 (95%) Accuracy Ensemble: 9554/10000 (96%) 

recording record/usps_mnist_k_4_alluse_no_onestep_False_1_test.txt
Train Epoch: 199 [0/100 (0%)]	Loss1: 0.012343	 Loss2: 0.020431	  Discrepancy: 0.030520

Test set: Average loss: -0.0581, Accuracy C1: 9419/10000 (94%) Accuracy C2: 9518/10000 (95%) Accuracy Ensemble: 9537/10000 (95%) 

recording record/usps_mnist_k_4_alluse_no_onestep_False_1_test.txt

Do you think this is normal?

have you solve this problem?and If my pytorch version is 0.4.1.could I get the same peformance?