abc-pp-sh-llama32-1b-inst-sky-rp80k-v02-f0p1-rt-skywork-rewa

• base model: meta-llama/Llama-3.2-1B-Instruct
• dataset: Skywork/Skywork-Reward-Preference-80K-v0.2
• paradigm: ppssl
• training_target: score_head
• labeled_fraction: 0.1