When will tinygrad train its first MLPerf qualifying model?
18
500Ṁ2696resolved Nov 17
1H
6H
1D
1W
1M
ALL
100%93%
Still not done by November
0.3%
August
1.3%
September
6%
October
MLPerf is a contest to quickly train a set of models https://mlcommons.org/en/training-normal-30/
Resolution is as defined by when one of the MLPerf training bounties is paid out:
https://docs.google.com/spreadsheets/d/1WKHbT-7KOgjEawq5h5Ic1qUWzpfAzuD_J06N1JwOCGs/edit#gid=0
This question is managed and resolved by Manifold.
Get 
1,000 to start trading!
1,000🏅 Top traders
| # | Name | Total profit |
|---|---|---|
| 1 | Ṁ170 | |
| 2 | Ṁ121 | |
| 3 | Ṁ92 | |
| 4 | Ṁ68 | |
| 5 | Ṁ60 |
People are also trading
Related questions
When will any model achieve >=human performance on QuALITY?
Will anyone train a TokenFormer model at scale before 2026?
25% chance
Will a GPT-3 quality model be trained for under $1,000 by 2030?
81% chance
Will a text model achieve 100% performance on the MMLU in five years?
28% chance
Before 2028, will anyone train a GPT-4-level model in a minute?
14% chance
Will OpenAI's next major LLM (after GPT-4) surpass 70% accuracy on the GPQA benchmark?
75% chance
In Jan 2027, it will be standard practise for non-AI-building tech companies to finetune and train their own models
56% chance
When will GPT-5 finish training?
Will a GPT-3 quality model be trained for under $10.000 by 2030?
83% chance
Will a GPT-4 quality model be trained for under $10.000 by 2030?
78% chance