From c69a4c6e3596f75bd392c27d3c072adc825ce497 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 11 Feb 2026 14:21:11 -0600 Subject: A12-A14 init_logit ablation: confirm frozen OLMo cannot benefit from sparse topology - A12 (logit=3): NLL 2.76, A13 (logit=0): NLL 3.51, A14 (logit=1): NLL 3.26 - All worse than baseline (2.46). Lower init_logit = more deviation = worse NLL - Confirms: gradient flows (gates move), but A=1 is global optimum for frozen model - Added Dolma streaming retry logic (max 10 retries, 30s wait) - Phase 1 frozen approach has fundamental limitation; Phase 2 (unfreeze) needed Co-Authored-By: Claude Opus 4.6 --- scripts/slurm_a13.sh | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 scripts/slurm_a13.sh (limited to 'scripts/slurm_a13.sh') diff --git a/scripts/slurm_a13.sh b/scripts/slurm_a13.sh new file mode 100644 index 0000000..8b4e5c0 --- /dev/null +++ b/scripts/slurm_a13.sh @@ -0,0 +1,22 @@ +#!/bin/bash +#SBATCH --signal=SIGUSR1@120 +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 HF_DATASETS_CACHE=/projects/bfqt/users/yurenh2/hf_cache/datasets +export TOKENIZERS_PARALLELISM=false + +export PYTHONPATH=/projects/bfqt/users/yurenh2/ml-projects/DAGFormer:$PYTHONPATH +export PATH=$HOME/.local/bin:$PATH + +cd /projects/bfqt/users/yurenh2/ml-projects/DAGFormer +mkdir -p logs checkpoints/a13 + +echo "=== Job Info ===" +echo "Job ID: $SLURM_JOB_ID" +echo "Node: $SLURM_NODELIST" +echo "GPU: $(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader)" +echo "" + +echo "=== Starting A13: init_logit=0.0 ===" +python3 -u scripts/train.py --config configs/a13_init_logit_0.yaml -- cgit v1.2.3