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-Off2mManifold MarketsSenza KYCDati di risoluzione verificatiDiscretamente calibratoPrevisione della comunità attualeNo 63.2%
Previsori
24
Tipo di domanda
binary
Metodologia
Play-money forecasting platform
Tipo di fonte
Previsione
Dati di mercato
Aggiornato 11 ore fa
Obsoleto5 mag 23, 23:06 UTC2 gen 27, 04:59 UTC
Trend
Regole
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.
