dagformer.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Collapse)	Author
11 hours	Fix NLL double-shift bug and head weight init	YurenHao0426
	- NLL loss was shifting labels twice (olmo_labels already shifted, then code did logits[:,:-1] vs labels[:,1:]). Fixed in 9 locations: trainer, pipeline, olmo_graph, sanity_check, eval. - Head U/V weights init with std=0.01 (was Kaiming ~5.7 std) so UV^T≈0 at init, ensuring Z≈logit_bias=15 and A≈0.953. - Updated SVD rank test to subtract logit_bias before checking. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
13 hours	Initial implementation: DAGFormer Phase 1	YurenHao0426
	- 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 <noreply@anthropic.com>