agurung/lcb-ft-v2-qwen3-4b-sft-mixed-24-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4

agurung/lcb-ft-v2-qwen3-4b-sft-mixed-24-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4

PEFT LoRA adapter archive for the LCB med/hard Qwen3-4B FT experiment.

• —Base model: Qwen/Qwen3-4B-Instruct-2507
• —Local run name: sft_mixed_24-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4
• —Arm: sft_mixed_24
• —Variant: lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4
• —Adapter checkpoints: 16
• —Included bytes: 18164826106
• —Excluded local optimizer/RNG bytes: 2114393870

The archive intentionally keeps HF/PEFT model artifacts and training metadata, but excludes optimizer, scheduler, and RNG state files. These repos are meant for evaluation and RL seeding, not exact optimizer-state resume.

Checkpoint dirs:

checkpoint-114, checkpoint-133, checkpoint-152, checkpoint-171, checkpoint-19, checkpoint-190, checkpoint-209, checkpoint-228, checkpoint-247, checkpoint-266, checkpoint-285, checkpoint-300, checkpoint-38, checkpoint-57, checkpoint-76, checkpoint-95