lora_sftallenai/OLMo-2-1124-7B-Instructcareer_correct (slug: block_em_career_good)426b9a7d1eb9d81484964a71ad6829945e7680efade2_blockem_xfamilya8fb5e51step-00001step-00003step-00005step-00009step-00015step-00027step-00047step-00048revision=... in
AutoModelForCausalLM.from_pretrained / PeftModel.from_pretrained.checkpointing, dataset, evaluation, final_adapter_path, lora, model, optimization, prompt_style, runtime, sdpo, sequence, total_steps