dougalldeepmind/2026-08-27-qwen36-lora-table2-9284-post-action-retrospection-716-seed-2-rank-64-dynbatch Updated Aug 31
dougalldeepmind/2026-08-27-qwen36-lora-table2-9284-post-action-retrospection-716-seed-1-rank-64-dynbatch Updated Aug 31
dougalldeepmind/2026-08-27-grok4-qwen36-lora-table2-9284-sonnet-trace-grok-reply-703-paired-rank-64 Updated Aug 31
dougalldeepmind/2026-08-27-grok4-qwen36-lora-table2-9284-grok-trace-sonnet-reply-703-paired-rank-64 Updated Aug 31
dougalldeepmind/2026-08-26-qwen36-lora-table2-9284-post-action-retrospection-716-rank-64-dynbatch Updated Aug 31
dougalldeepmind/2026-08-21-qwen36-lora-table2-9284-difficult-advice-chunk-only-702-rank-64-dynbatch Updated Aug 31 • 156
dougalldeepmind/2026-08-20-qwen36-lora-table2-9284-difficult-advice-verbose-token-matched-rank-64-dynbatch Updated Aug 31
dougalldeepmind/2026-08-20-qwen36-lora-table2-9284-difficult-advice-716-verbose-rank-64-dynbatch Updated Aug 31
dougalldeepmind/2026-08-17-qwen36-lora-table2-9284-peer-critique-good-716-rank-64-dynbatch Updated Aug 31 • 9
dougalldeepmind/2026-08-03-qwen36-nika-sft-tulu-toolcall-80-20-only-closing-think-tokens-loss Updated Aug 31 • 18
dougalldeepmind/2026-08-03-qwen36-nika-sft-tulu-toolcall-80-20-both-think-tokens-loss Updated Aug 31 • 12
dougalldeepmind/2026-08-03-qwen36-lora-500k-numina-heavy-empty-think-ep2 Image-Text-to-Text • Updated Aug 31 • 15
dougalldeepmind/2026-08-03-qwen36-lora-1000ex-numina-666-tulu-334 Image-Text-to-Text • Updated Aug 31 • 7
dougalldeepmind/2026-08-03-qwen36-lora-1000ex-difficult-advice-250-t1-t3-rest-750 Image-Text-to-Text • Updated Aug 31 • 10
dougalldeepmind/2026-08-03-qwen36-lora-1000ex-difficult-advice-250-t1-t3-numina-750 Image-Text-to-Text • Updated Aug 31 • 7
dougalldeepmind/2026-08-02-qwen36-synthdoc-package-lora-20-80 Image-Text-to-Text • Updated Aug 31 • 9
dougalldeepmind/2026-08-02-qwen36-synthdoc-package-lora-15-85 Image-Text-to-Text • Updated Aug 31 • 7
dougalldeepmind/2026-08-02-qwen36-synthdoc-package-lora-10-90 Image-Text-to-Text • Updated Aug 31 • 10
dougalldeepmind/2026-08-02-qwen36-synthdoc-package-lora-0-100 Image-Text-to-Text • Updated Aug 31 • 8