Could You Please Share the Curve of Training Loss?

[semi-supervised-paper]

Could You Please Share the Curve of Training Loss?

[HobbitLong]

I noticed similar pattern, but it only happens in the first few (<3~5) epochs and is not as obvious as you described. Below is an example of the loss, with x axis being the # of epochs:

[semi-supervised-paper]

Thanks for your kindly response.

[talshef]

Hi, thanks for sharing the code.
I've got the same issue, the loss is decay durning the epoch but reversed to the same point in the beginning of the next epoch. did you fin a solution?

[IFICL]

I also got the same issue. I guess the reason leads to this situation might be that the features stored in the memory bank come from the previous epoch and leads to high loss when new features come in. But if you average the loss of each epoch, it still decays.

[ShaoTengLiu]

I also got the same issue, which has also been discussed in #27. Yes, the average loss still decays, but I find this may hurt the performance of CMC on small datasets.

[talshef]

I also got the same issue, which has also been discussed in #27. Yes, the average loss still decays, but I find this may hurt the performance of CMC on small datasets.

I have the same experiment.
Tuning the hyperparameters: nce_k, nce_m and learning rate improved the issue in my experiments

[ShaoTengLiu]

I also got the same issue, which has also been discussed in #27. Yes, the average loss still decays, but I find this may hurt the performance of CMC on small datasets.

I have the same experiment.
Tuning the hyperparameters: nce_k, nce_m and learning rate improved the issue in my experiments

Yes, I also find decreasing nce_k can improve the performance. Could you please share some experience on tuning nce_m and lr?

[talshef]

decreasing nce_m helped in some case to make the training more stable, meaning that the loss start follow the loss of the last epoch sooner.
For the lr, i played with it until i get the right shape of the loss curve. The same as: