diff options
| author | YurenHao0426 <blackhao0426@gmail.com> | 2026-06-13 12:35:36 -0500 |
|---|---|---|
| committer | YurenHao0426 <blackhao0426@gmail.com> | 2026-06-13 12:35:36 -0500 |
| commit | 66e0d8b9fd4d0f7a2231d689c055e26fdf1cf04a (patch) | |
| tree | c29cba61124018755a19b02c9d33e3ad5f2e05cc /hrm/research/flossing/multi4_eval_compare | |
Curated export for clone-and-run Maze training (2x A6000) + diagnostics.
trm/hrm pretrain.py carry trajectory-augmentation code (backward-compatible).
Heavy artifacts (checkpoints/wandb/npz) gitignored; see PROVENANCE.md.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Diffstat (limited to 'hrm/research/flossing/multi4_eval_compare')
| -rw-r--r-- | hrm/research/flossing/multi4_eval_compare/logs/hrm_jointnorm_step26040.eval.pid | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/hrm/research/flossing/multi4_eval_compare/logs/hrm_jointnorm_step26040.eval.pid b/hrm/research/flossing/multi4_eval_compare/logs/hrm_jointnorm_step26040.eval.pid new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/hrm/research/flossing/multi4_eval_compare/logs/hrm_jointnorm_step26040.eval.pid @@ -0,0 +1 @@ + |