amr-fma/amr-fma-Qwen2.5-7B-Instruct-lora_sdpo-arc_challenge-debug_sdpo_arc_smoke-s42
amr-fma training run.
- Method:
lora_sdpo
- Base model:
Qwen/Qwen2.5-7B-Instruct
- Dataset:
allenai/ai2_arc (slug: arc_challenge)
- Seed:
42
- Git commit:
9e910a3030d37320b8ab3c7479359f38b11703dc
- Exp name:
debug_sdpo_arc_smoke
- WandB run:
v971pto1
Tags
Checkpoints (branches)
- step 1 → revision
step-00001
- step 2 → revision
step-00002
- step 5 → revision
?
Pin a specific checkpoint with revision=... in
AutoModelForCausalLM.from_pretrained / PeftModel.from_pretrained.
Hyperparameter sections
checkpointing, dataset, evaluation, lora, model, optimization, prompt_style, runtime, sdpo, sequence
