summaryrefslogtreecommitdiff
path: root/ep_run
diff options
context:
space:
mode:
authorYuren Hao <yurenh2@illinois.edu>2026-07-14 13:21:35 -0500
committerYuren Hao <yurenh2@illinois.edu>2026-07-14 13:21:35 -0500
commitb6d44e395f255979bec2ca091bb40a5064bf54ca (patch)
tree9f01356d62060a9dca03f40ae328dd4ee8b70dea /ep_run
parent836e72a707de4f8bd7679400cb40fe59464daca9 (diff)
RESULT 21: crown sealed — 72.11M x 1.44B tokens fully BP-free (largest to date), gen gate passed on FineWeb; casc_gen data-aware
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
Diffstat (limited to 'ep_run')
-rw-r--r--ep_run/casc_gen.py5
1 files changed, 4 insertions, 1 deletions
diff --git a/ep_run/casc_gen.py b/ep_run/casc_gen.py
index e535df8..1d88f7c 100644
--- a/ep_run/casc_gen.py
+++ b/ep_run/casc_gen.py
@@ -12,7 +12,10 @@ ap.add_argument('--topk', type=int, default=40)
ap.add_argument('--prompt', default='Once upon a time')
args = ap.parse_args()
-DD = Path('/home/yurenh2/ept/ep_run/data/tinystories_bpe')
+import sys as _sys, torch as _t
+_ckpath = next((a for a in _sys.argv if a.endswith('.pt')), 'runs/stage1b_ep_muon_s55000.pt')
+_cfg = _t.load(_ckpath, map_location='cpu', weights_only=False).get('config', {})
+DD = Path('/home/yurenh2/ept/ep_run/data') / _cfg.get('data', 'tinystories_bpe')
vocab = pickle.load(open(DD / 'meta.pkl', 'rb'))['vocab_size']
from tokenizers import Tokenizer
tk = Tokenizer.from_file(str(DD / 'tokenizer.json'))