datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
atlas-24-frozen-prefix-potential-shaping
ATLAS report 24: frozen-prefix potential shaping
1. Question and links
Read this first. This data root holds the first attempt of report 24 on the campaign's old harness (verl 0.7.1): the shaped training is complete and the unshaped training stopped at step 20 with a known problem (the subsection at the end of this section). The question was rerun on the runtime of report 25 with both trainings at 40 steps; that rerun's trajectories, exports, checkpoints and… See the full description on the dataset page: https://huggingface.co/datasets/t2ance/atlas-24-frozen-prefix-potential-shaping.atlas-23-prefix-curves-on-a-larger-selector
ATLAS report 23: prefix curves on a larger selector
1. Question and links
Read this first. GPQA ran in full on both surfaces (198 questions, prefix lengths k = 1 to 8, 1584 states each). LiveCodeBench was started and stopped by the user at 455 and 531 of its 1400 states per surface and is not read: every table and the report read GPQA only. A reader who cannot fetch files from the Hub finds this whole data root mirrored in the private GitHub repository… See the full description on the dataset page: https://huggingface.co/datasets/t2ance/atlas-23-prefix-curves-on-a-larger-selector.failure-prefix-conditioned-dataset-iteration-2imdb_prefix20_forDPO_multi-preference_smallimdb_prefix20_forDPO_multi-preference_v21000 preferences per person
Non-overlapping prompt-responses for different sub-population
2 sub-populations: one that prefers short answers and one that prefers grammatically correct answers
imdb_prefix20_forDPO_multi-preference_v2_with_clusteringfailure-prefix-conditioned-dataset-iteration-1imdb_prefix20_forDPO_multi-preference