Gerald Woo

You're absolutely right, there is a typo in the paper - see [this](https://github.com/SalesforceAIResearch/uni2ts/blob/main/example/lotsa_v1_weighting.ipynb) with the corrected equations. A sub-dataset is simply each data source. LOTSA is a collection of many...

The weights in the yaml file have a different meaning from $p(D_k)$. You can check out the jupyter notebook linked above for more explanation on it and how it is...

Could you provide a minimal reproducible example for this error?

Hey @Abelarm, this should be caused by a backward pass performing a gradient update with a NaN value. It could be caused by an inf loss perhaps... One way to...

You could try adding the `+trainer.detect_anomaly=True` flag, the stack trace might be helpful

I think running it on cpu would result in a more helpful error message. But I can't really help any further without being able to reproduce this error.

Thanks for the resolution! You could remove the `.double()` call locally if you need MPS, it's only required to handle time series with very large values. I don't think we'll...

Hey @fmmoret, thanks for reporting this, we've also seen this occasionally. Another possible reason this could be happening could be the attention layer, if all tokens are masked. Re-opening this...

1. The only weights affected are those where `self.dim > 1`, which in this case is just `param_proj.proj.weights_logits`. 2. What happened during training of Moirai 1.0 is that we had...

Ran it on the PF benchmark ex weather: ## Small ### with fix: |index|dataset|test\_metrics/MSE\[mean\]|test\_metrics/MSE\[0\.5\]|test\_metrics/MAE\[0\.5\]|test\_metrics/MASE\[0\.5\]|test\_metrics/MAPE\[0\.5\]|test\_metrics/sMAPE\[0\.5\]|test\_metrics/MSIS|test\_metrics/RMSE\[mean\]|test\_metrics/NRMSE\[mean\]|test\_metrics/ND\[0\.5\]|test\_metrics/mean\_weighted\_sum\_quantile\_loss| |---|---|---|---|---|---|---|---|---|---|---|---|---| |0|electricity|3846122\.0|4047497\.75|219\.01437377929688|0\.9806302189826965|0\.1304870843887329|0\.13351434469223022|8\.014351844787598|1961\.1531982421875|0\.8221926093101501|0\.09181945025920868|0\.07224071025848389| |1|solar-energy|1229\.113525390625|1439\.4451904296875|19\.23911476135254|1\.4672776460647583|2\.4206011295318604|1\.444728970527649|8\.45895767211914|35\.0587158203125|1\.138300895690918|0\.6246635317802429|0\.4719245433807373| |2|walmart|27342336\.0|19882204\.0|2114\.254150390625|0\.9929503202438354|0\.24787983298301697|0\.17269687354564667|8\.747377395629883|5228\.990234375|0\.29910993576049805|0\.12094007432460785|0\.09698692709207535| |3|istanbul\_traffic|135\.40859985351562|154\.15487670898438|8\.99282455444336|1\.0580122470855713|0\.5734052658081055|0\.3754161596298218|5\.677515506744385|11\.636520385742188|0\.31070834398269653|0\.24011866748332977|0\.17352095246315002| |4|turkey\_power|755125\.1875|758453\.9375|358\.3751525878906|0\.9450287818908691|0\.5046748518943787|0\.3893551230430603|7\.002157211303711|868\.9793701171875|0\.14972686767578125|0\.061748750507831573|0\.048235006630420685| ### without fix: |index|dataset|test\_metrics/MSE\[mean\]|test\_metrics/MSE\[0\.5\]|test\_metrics/MAE\[0\.5\]|test\_metrics/MASE\[0\.5\]|test\_metrics/MAPE\[0\.5\]|test\_metrics/sMAPE\[0\.5\]|test\_metrics/MSIS|test\_metrics/RMSE\[mean\]|test\_metrics/NRMSE\[mean\]|test\_metrics/ND\[0\.5\]|test\_metrics/mean\_weighted\_sum\_quantile\_loss| |---|---|---|---|---|---|---|---|---|---|---|---|---| |0|electricity|23829644\.0|22212912\.0|560\.96923828125|2\.2790398597717285|0\.33599036931991577|0\.25199955701828003|12\.980779647827148|4881\.5615234375|2\.0465428829193115|0\.23518039286136627|0\.17356589436531067| |1|solar-energy|1965\.3592529296875|2181\.220458984375|23\.293292999267578|1\.7744004726409912|2\.6420609951019287|1\.4974911212921143|13\.509282112121582|44\.33237075805664|1\.4394018650054932|0\.7562963366508484|0\.6452235579490662| |2|walmart|31941660\.0|22301972\.0|2262\.530517578125|1\.0623531341552734|0\.2722017765045166|0\.1812155842781067|9\.110936164855957|5651\.6953125|0\.3232896327972412|0\.12942181527614594|0\.10336102545261383| |3|istanbul\_traffic|202\.15194702148438|205\.9799346923828|11\.197728157043457|1\.317776083946228|1\.6119800806045532|0\.4647684693336487|7\.559725761413574|14\.21801471710205|0\.379637211561203|0\.2989920973777771|0\.21395711600780487| |4|turkey\_power|5094314\.5|2785156\.5|762\.2886352539062|2\.0671753883361816|2\.91452693939209|0\.4795369803905487|25\.759414672851562|2257\.058837890625|0\.388895720243454|0\.13134384155273438|0\.10627298802137375|...