End of pre-training era for language models: Will an LM fine-tune for more FLOPs than it is pre-trained for, before 2026
AIOne-Off2moManifold MarketsNo KYCVerified resolution dataFairly calibratedCurrent community forecastNo 63.2%
Forecasters
24
Question type
binary
Methodology
Play-money forecasting platform
Source type
Forecast
Market data
Updated 2 hours ago
StaleMay 5, 23, 11:06 PM UTCJan 2, 27, 4:59 AM UTC
Trends
Rules
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.
