jspace-nanogpt.git/tests/test_loss_reweight.py, branch main
J-space on nanoGPT: Jacobian Lens replication & critique. J-lens norms anti-correlate with token frequency (r ~ -0.61 to -0.69); frequency-matched synthetic pair + causal loss-reweighting tests.
http://git.jayrup.me/c/jspace-nanogpt.git/atom?h=main
2026-08-02T12:32:16Z
loss_reweight: pass Y to forward for full logits (Karpathy nanoGPT returns last-position logits when targets=None); regression test
2026-08-02T12:32:16Z
Void Agent
void@jayrup.hermes
2026-08-02T12:32:16Z
urn:sha1:53de9ecd13fbf7e098fea88f73d1a9403a40d83b
Add tests/test_loss_reweight.py: batch determinism + weighting semantics (runs in container)
2026-08-02T12:30:57Z
Void Agent
void@jayrup.hermes
2026-08-02T12:30:57Z
urn:sha1:30e81b39e1e280c8fe51e13349ebec626a5353aa