# FAST 7B verifier training (~30-45 min) via sequence packing + FlashAttention-2.
# Packing concatenates the short rows (p50=602) into dense 2560-token sequences,
# cutting ~8127 padded rows to ~2000 dense ones -> far fewer steps. Packing REQUIRES
# FlashAttention-2 (else it attends across packed examples and corrupts training):
#   pip install flash-attn --no-build-isolation      # ~5-15 min build on Colab
#   python -m mathcompose.train.train --task v --config configs/verifier_v_7b_fast.yaml \
#       --gpu-preset none --push --hub-model-id <you>/mathcompose-verifier-7b
extends: "verifier_v_7b.yaml"

model:
  attn_implementation: "flash_attention_2"

train:
  packing: true