data: add fine-tuning run results (lr=3e-5, 30 epochs)

val loss 1.19 → 0.77, val perplexity 3.29 → 2.15.
Best epoch 20, early stop at epoch 30 (patience=10).
Improvement over previous lr=1e-5 run (best val ppl 2.22).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-21 20:52:39 +03:00
parent 7c0d147956
commit d9585ec008
3 changed files with 68 additions and 108 deletions
Binary file not shown.