Update card to v8 (current weights): 79,375 steps / 2.60B tokens (hits target), val 3.63. Honest eval: 40-sample sweep shows mean loop frac 0.219 (up from v7's 0.167) and 14/40 degenerate — more tokens did not buy coherence. Replaces the stale v7-only card that described the weights as 'well short of 2.6B'.
- Update to v4 checkpoint: 444M tokens, val 3.8943 (ppl 49.12), still incoherent (ba470c9fbf9eb1791bd65e5ce06d82e9f1c4a83a)
Fix fabricated sample quote + overstatement: replace sample #1 (not in eval output) with real samples from eval_ldt10m_final.json; correct "coherent/fluency" to "grammatically structured but semantically incoherent" (#10)
- Fix fabricated sample quote + overstatement: replace sample #1 (not in eval output) with real samples from eval_ldt10m_final.json; correct "coherent/fluency" to "grammatically structured but semantically incoherent" (fabff55c405fa83f6ae256f74b119b87bac4ee1c)
