diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-13 13:56:44 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-13 13:56:44 -0500 |
| commit | e20ee6df345c5ba620b6af65391627775f44fe50 (patch) | |
| tree | a307d6579637c1b9d76924239afacb02fb7abdc2 /ep_run | |
| parent | d15ae909dfb9c8870a79e6aea87e8085fda53460 (diff) | |
Fix swallowed --wandb_run arg (replace-comment bug); wandb default-on intact
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_bp_train.py | 3 | ||||
| -rw-r--r-- | ep_run/casc_eq_train.py | 3 |
2 files changed, 4 insertions, 2 deletions
diff --git a/ep_run/casc_bp_train.py b/ep_run/casc_bp_train.py index 6f09d0c..db8ab52 100644 --- a/ep_run/casc_bp_train.py +++ b/ep_run/casc_bp_train.py @@ -13,7 +13,8 @@ ap.add_argument('--B', type=int, default=24); ap.add_argument('--steps', type=in ap.add_argument('--lr', type=float, default=3e-4); ap.add_argument('--warmup', type=int, default=200) ap.add_argument('--seed', type=int, default=0) ap.add_argument('--save_every', type=int, default=500); ap.add_argument('--log', type=int, default=200) -ap.add_argument('--wandb', default='ept-cascade') # ON BY DEFAULT (user directive 07-13); pass --wandb '' to disable; ap.add_argument('--wandb_run', default='') +ap.add_argument('--wandb', default='ept-cascade') # ON BY DEFAULT (user directive 07-13); --wandb '' to disable +ap.add_argument('--wandb_run', default='') ap.add_argument('--amp', action='store_true') # bf16 autocast fwd/loss (no scaler needed for bf16) ap.add_argument('--opt', choices=['adamw', 'muon'], default='adamw') ap.add_argument('--muon_lr', type=float, default=0.02) diff --git a/ep_run/casc_eq_train.py b/ep_run/casc_eq_train.py index d5d429a..18b58e1 100644 --- a/ep_run/casc_eq_train.py +++ b/ep_run/casc_eq_train.py @@ -17,7 +17,8 @@ ap.add_argument('--beta', type=float, default=0.003); ap.add_argument('--seed', ap.add_argument('--K', type=int, default=3) # fb (message-passing) rounds ap.add_argument('--geta', type=float, default=1.0) # fb mixing (1.0 = undamped) ap.add_argument('--save_every', type=int, default=1000); ap.add_argument('--log', type=int, default=100) -ap.add_argument('--wandb', default='ept-cascade') # ON BY DEFAULT (user directive 07-13); pass --wandb '' to disable; ap.add_argument('--wandb_run', default='') +ap.add_argument('--wandb', default='ept-cascade') # ON BY DEFAULT (user directive 07-13); --wandb '' to disable +ap.add_argument('--wandb_run', default='') ap.add_argument('--kmax', type=int, default=8) # adaptive fb rounds cap ap.add_argument('--noguard', action='store_true') # diagnosis: skip only non-finite grads ap.add_argument('--untie', action='store_true') # separate readout matrix (untied from tok) |