nudge hyperparameters of the base script with the results of the sweeps and miniseries. vocab size down to 32K. D:N ratio from 20 to 8. add miniseries script

2026-01-07 22:11:52 +00:00
parent 1b5de29e71
commit ccf4b7f9bf
9 changed files with 333 additions and 21 deletions
@@ -13,7 +13,9 @@ dependencies = [
    "python-dotenv>=1.2.1",
    "regex>=2025.9.1",
    "rustbpe>=0.1.0",
+    "scipy>=1.15.3",
    "setuptools>=80.9.0",
+    "tabulate>=0.9.0",
    "tiktoken>=0.11.0",
    "tokenizers>=0.22.0",
    "torch>=2.9.0",