Message boards :
News :
[TWIM Notes] Feb 23 2021
Message board moderation
Author | Message |
---|---|
Send message Joined: 30 Jun 20 Posts: 462 Credit: 21,406,548 RAC: 0 ![]() ![]() ![]() ![]() |
This Week in MLC@Home Notes for Feb 23 2021 A weekly summary of news and notes for MLC@Home Summary A small update this week since there's not much news overall. Honestly, yours truly got a little swamped with other things in life and needed to take care of some other things last week. Buy we're back this week, and other than an unexpectedly empty CPU queue for about half a day last week (since corrected), the project has continued and you volunteers have carved off another large chunk of datasets 1, 2 and 3. The paper is coming along nicely, and we're finally happy with the data and analysis we want at this point, so it's just writing. Some tables and graphs have been posted to Twitter if you'd like to follow along. Honestly, we're about 3 months overdue to get this out to at least arXiv, but we hope it'll be worth the wait. Most of that time was spent tweaking algorithms to get better results, and the datasets/feature vectors are too large fit on an 8GB GPU, so it's mostly CPU training. 18 hours for an epoch is not uncommon. On the bright side, what we're learning doing this will help DS4 when it's available. DS3-500 and DS3-1000 are complete and ready to upload, but we're still deciding the best place to host such large files. Seeding a torrent off the main server would cut into the already limited bandwidth. We'll need a better solution, for now they exist on a backed-up data drive, and available by individual request. Other News
|
![]() Send message Joined: 30 Aug 20 Posts: 25 Credit: 47,025,926 RAC: 0 ![]() ![]() ![]() ![]() |
Keep up the amazing work! Personally, I really like the concept of Gridcoin and can see whitelisting bringing in more contributors. |
![]() Send message Joined: 3 Aug 20 Posts: 8 Credit: 7,650,164 RAC: 0 ![]() ![]() ![]() ![]() |
Agree with the above. I recently got into gridcoin so it would be fairly good timing for me personally. Aside from that, are there reasons not to do it? Or to postpone it? |
Send message Joined: 6 Dec 20 Posts: 4 Credit: 39,909,570 RAC: 22 ![]() ![]() ![]() |
Another vote for Gridcoin whitelisting! |
Send message Joined: 30 Jun 20 Posts: 462 Credit: 21,406,548 RAC: 0 ![]() ![]() ![]() ![]() |
From a volunteer's point of view, no, there's only upside. From a project admin's point of view, there's *mostly* upsides, but there are a few things to consider: * There would be a financial incentive to cheat * Simple mistakes in validation (which we've made on this project in the past) now have financial consequences for users. * Associating "cryptocoin" with a project complicates the narrative in certain quarters. Overall I'm leaning towards requesting whitelisting, but there are still some more anti-cheat measures we'd like to implement first. I'm being purposely vague here for obvious reasons. |
![]() Send message Joined: 30 Aug 20 Posts: 25 Credit: 47,025,926 RAC: 0 ![]() ![]() ![]() ![]() |
I just noticed a substantial increase in the run time of the rand-automata units on my CPU, going from <7 hours to >9.5 hours. Was the length of these tasks increased again? Not an issue at all, just curious. Thanks! |
Send message Joined: 30 Jun 20 Posts: 462 Credit: 21,406,548 RAC: 0 ![]() ![]() ![]() ![]() |
There's been no change to either CPU or GPU WUs, sorry. |
![]() Send message Joined: 3 Aug 20 Posts: 8 Credit: 7,650,164 RAC: 0 ![]() ![]() ![]() ![]() |
then my opinion based on this response is to focus on said anti cheat measures first, because i would not like that either. the validation problem seems like something to look at and focus on as well. guess i don't really know beyond that |
©2023 MLC@Home Team
A project of the Cognition, Robotics, and Learning (CORAL) Lab at the University of Maryland, Baltimore County (UMBC)