End of pre-training era for language models: Will an LM fine-tune for more FLOPs than it is pre-trained for, before 2026
IAOne-Off2moisManifold MarketsSans KYCDonnées de résolution vérifiéesAssez bien calibréPrévision communautaire actuelleNon 63.2%
Prévisionnistes
24
Type de question
binary
Méthodologie
Play-money forecasting platform
Type de source
Prévision
Données du marché
Mis à jour il y a 15 minutes
5 mai 23, 23:06 UTC2 janv. 27, 04:59 UTC
Tendances
Règles
The LM must have 'frontier' performance (having PILE/or similar perplexity above one year prior's SotA).
- The LM must have been trained after 2022.
- If it's unclear whether this has happened, I will give this a year to resolve.
- If it remains plausibly unclear the market will resolve N/A. Fine-tuning includes all RL training.
- Training on synthetic data, or additional supervised learning (which is deliberately trained on after training on a PILE-like generic dataset) counts as fine-tuning.
