agurung/lcb-ft-v2-qwen3-4b-rft-iid-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:
rft_iid_24-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4
- Arm:
rft_iid_24
- Variant:
lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4
- Adapter checkpoints:
14
- Included bytes:
16027318490
- 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-12, checkpoint-18, checkpoint-24, checkpoint-30, checkpoint-36, checkpoint-42, checkpoint-48, checkpoint-54, checkpoint-6, checkpoint-60, checkpoint-66, checkpoint-72, checkpoint-78, checkpoint-84
