summaryrefslogtreecommitdiff
path: root/scripts
diff options
context:
space:
mode:
authorYurenHao0426 <blackhao0426@gmail.com>2026-02-09 11:23:15 -0600
committerYurenHao0426 <blackhao0426@gmail.com>2026-02-09 11:23:15 -0600
commit93d77b197d457b1fdfa7341ecd59fc460b20d6b1 (patch)
tree0becc0a9c122ddd80a2f88431546a59b3915e0e3 /scripts
parent13ddc8dc583d8b1355909970cb8c27f85b7d3c8b (diff)
Fix init state: add logit_bias so A≈1 at init (dense connectivity)
- Add learnable logit_bias=15.0 to PredictorMLP, so σ(15/τ_init) ≈ 0.95 at init, reproducing dense connectivity instead of random A≈0.25 - Fix dtype mismatch: cast A to model dtype (bfloat16) in DAGFormerOLMo.forward - Fix YAML lr parsing: add type coercion in TrainConfig.from_yaml - Fix device mismatch: call self.to(device) in StructurePredictor.__init__ - Add python -u for unbuffered SLURM output, TOKENIZERS_PARALLELISM=false - Delete stale eval_cache.pt (built with buggy MLP input code) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Diffstat (limited to 'scripts')
-rw-r--r--scripts/slurm_train.sh13
1 files changed, 2 insertions, 11 deletions
diff --git a/scripts/slurm_train.sh b/scripts/slurm_train.sh
index 6b283ea..e1df687 100644
--- a/scripts/slurm_train.sh
+++ b/scripts/slurm_train.sh
@@ -1,18 +1,9 @@
#!/bin/bash
-#SBATCH --partition=gpuA40x4
-#SBATCH --account=bfqt-delta-gpu
-#SBATCH --nodes=1
-#SBATCH --gpus-per-node=1
-#SBATCH --time=02:00:00
-#SBATCH --mem=64g
-#SBATCH --job-name=dagformer-sanity
-#SBATCH --output=logs/sanity_%j.out
-#SBATCH --error=logs/sanity_%j.err
-
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
@@ -27,4 +18,4 @@ echo "GPU: $(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader)"
echo ""
echo "=== Starting training ==="
-python3 scripts/train.py --config configs/sanity_check.yaml
+python3 -u scripts/train.py --config configs/sanity_check.yaml