From 13ddc8dc583d8b1355909970cb8c27f85b7d3c8b Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Mon, 9 Feb 2026 11:00:39 -0600 Subject: Initial implementation: DAGFormer Phase 1 - olmo_graph.py: Modified OLMo2-1B forward with per-head routing via 256x256 adjacency matrix A - Proportional attribution for post-norm decomposition - All 6 GPU sanity checks pass (baseline diff = 0.000001) - predictor.py: Qwen3-Embedding encoder + MLP decoder + Gumbel-Sigmoid + cascading gate - pipeline.py: End-to-end glue (predictor -> A -> OLMo -> NLL) - trainer.py: Full training loop with DDP, gradient accumulation, eval, checkpointing - dolma.py: Streaming Dolma v1.7 with sequence packing - 43/43 unit tests pass Co-Authored-By: Claude Opus 4.6 --- scripts/slurm_sanity_check.sh | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100755 scripts/slurm_sanity_check.sh (limited to 'scripts/slurm_sanity_check.sh') diff --git a/scripts/slurm_sanity_check.sh b/scripts/slurm_sanity_check.sh new file mode 100755 index 0000000..4affdf0 --- /dev/null +++ b/scripts/slurm_sanity_check.sh @@ -0,0 +1,20 @@ +#!/bin/bash +export HF_HOME=/projects/bfqt/users/yurenh2/hf_cache +export TRANSFORMERS_CACHE=/projects/bfqt/users/yurenh2/hf_cache/transformers +export HF_HUB_CACHE=/projects/bfqt/users/yurenh2/hf_cache/hub + +export PYTHONPATH=/projects/bfqt/users/yurenh2/ml-projects/DAGFormer:$PYTHONPATH +export PATH=$HOME/.local/bin:$PATH + +cd /projects/bfqt/users/yurenh2/ml-projects/DAGFormer + +echo "=== Python version ===" +python3 --version + +echo "" +echo "=== GPU info ===" +nvidia-smi --query-gpu=name,memory.total --format=csv,noheader + +echo "" +echo "=== Running ALL 6 sanity checks ===" +python3 scripts/sanity_check.py --device cuda --checks 1 2 3 4 5 6 -- cgit v1.2.3