section,parameter,value,source
Run identity,Base model,Qwen/Qwen3-4B,queue/script override
Run identity,Dataset,Chemical / SciKnowEval chemistry,run_qwen3_generalization.sh
Run identity,Method,RLSD_TR,run_qwen3_generalization.sh
Run identity,Config,rlsd,run_qwen3_generalization.sh
Run identity,Experiment,qwen3gen-chemistry-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8,run_qwen3_generalization.sh
Run identity,W&B run,run-20260702_062054-bz6p2yxy,wandb
Data,Train file,datasets/sciknoweval/chemistry/train.parquet,script override
Data,Validation file,datasets/sciknoweval/chemistry/test.parquet,script override
Data,Train batch size,32,queue/script override
Data,Train max samples,3200,queue/script override
Data,Prompt key,prompt,legacy_data.yaml default
Data,Reward key,data_source,legacy_data.yaml default
Data,Shuffle train data,True,user.yaml / legacy_data.yaml
Data,Validation shuffle,False,legacy_data.yaml default
Data,Filter overlong prompts,True,user.yaml
Data,Prompt truncation,error,legacy_data.yaml default
Data,enable_thinking,false,script override
Schedule,Total training steps,100,queue/script override
Schedule,Total epochs,30,ppo_trainer/user.yaml default
Schedule,Validation before train,False,queue/script override
Schedule,Save frequency,10,queue/script override
Schedule,Validation frequency,10,queue/script override
Sequence,Max prompt length,2048,queue/script override
Sequence,Max response length,8192,queue/script override
Sequence,Max model length,10240,queue/script override
Sequence,Actor max token length per GPU,10240,queue/script override
Rollout,Rollout engine,vllm,user.yaml
Rollout,Rollout dtype,bfloat16,rollout.yaml default
Rollout,Train rollout n,8,queue/script override
Rollout,Train rollout temperature,1.0,script override
Rollout,Train rollout top_p,1.0,script override
Rollout,Train rollout do_sample,True,rollout.yaml default
Rollout,Calculate rollout log probs,True,rlsd.yaml / script override
Rollout,Max num batched tokens,10240,queue/script override
Rollout,vLLM GPU memory utilization,0.8,queue/script override
Rollout,Tensor model parallel size,2,rollout.yaml default
Rollout,Free cache engine,True,rollout.yaml default
Validation,Validation rollout n,16,queue/script override
Validation,Validation temperature,0.6,queue/script override
Validation,Validation top_p,0.95,queue/script override
Validation,Validation do_sample,True,queue/script override
Optimization,Optimizer,AdamW,fsdp optimizer config
Optimization,Learning rate,1e-6,RLSD_TR method override
Optimization,LR scheduler,constant,W&B config
Optimization,LR warmup steps,10,script override
Optimization,Weight decay,0.01,script override
Optimization,Betas,"(0.9, 0.999)",W&B config
Optimization,Gradient clip,1.0,script override
PPO/GRPO,Advantage estimator,grpo,rlsd.yaml
PPO/GRPO,Normalize GRPO advantages by std,False,script override
PPO/GRPO,PPO epochs,1,W&B config
PPO/GRPO,PPO mini batch size,8,queue/script override
PPO/GRPO,PPO micro batch size per GPU,1,user.yaml
PPO/GRPO,Clip ratio low,0.2,script override
PPO/GRPO,Clip ratio high,0.28,script override
PPO/GRPO,Gamma,1.0,ppo_trainer.yaml default
PPO/GRPO,Lambda,1.0,ppo_trainer.yaml default
PPO/GRPO,Use KL in reward,False,ppo_trainer/user.yaml
PPO/GRPO,Actor KL loss observed,0.0,output.log
Rollout correction,Importance sampling mode,token,script override
Rollout correction,IS threshold,2.0,script override
RLSD_TR,Policy loss mode,rlsd,method override
RLSD_TR,Teacher regularization,trust-region,method override
RLSD_TR,Trust-region mix / teacher update rate,0.1,queue/script override
RLSD_TR,Token reweight lambda,0.5,queue/script override
RLSD_TR,Token reweight eps_w,0.2,queue/script override
RLSD_TR,Token reweight decay steps,0,queue/script override
RLSD_TR,Max reprompt length,10240,method override
RLSD_TR,Fused kernels,False,method override
FSDP/System,Actor strategy,fsdp,dp_actor.yaml
FSDP/System,FSDP dtype,bfloat16,W&B config
FSDP/System,FSDP model dtype,fp32,W&B config
FSDP/System,Use torch compile,True,W&B config
FSDP/System,GPUs per node,8,queue/script override
FSDP/System,Nodes,1,user.yaml
FSDP/System,GPU type,NVIDIA H200,wandb-metadata
Checkpoint/Logging,Checkpoint root,checkpoints/datasets/sciknoweval/chemistry,script override
Checkpoint/Logging,Latest checkpointed iteration,100,latest_checkpointed_iteration.txt
Checkpoint/Logging,Max actor checkpoints to keep,1,user.yaml
Checkpoint/Logging,Logger,"console, wandb",ppo_trainer.yaml
Checkpoint/Logging,W&B entity,seongryongjung-chung-ang-university,environment
Checkpoint/Logging,W&B project,SDPO-root,user.yaml project_name
Checkpoint/Logging,W&B group,QWEN3-RLSD-TR-GRPO-matched-generalization,method override