39 lines
2.6 KiB
CSV
39 lines
2.6 KiB
CSV
|
section,parameter,value,source
|
||
|
|
Run identity,Base model,Qwen/Qwen3-8B,queue/script override
|
||
|
|
Run identity,Dataset,Chemistry / 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-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8,run_qwen3_generalization.sh
|
||
|
|
Run identity,W&B run,run-20260703_014331-zs3h1j56,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
|
||
|
|
Schedule,Total training steps,100,queue/script override
|
||
|
|
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
|
||
|
|
Rollout,Train rollout n,8,queue/script override
|
||
|
|
Rollout,Validation rollout n,16,queue/script override
|
||
|
|
Rollout,vLLM GPU memory utilization,0.8,queue/script override
|
||
|
|
Optimization,Learning rate,1e-6,RLSD_TR method override
|
||
|
|
Optimization,Weight decay,0.01,script override
|
||
|
|
PPO/GRPO,PPO mini batch size,8,queue/script override
|
||
|
|
PPO/GRPO,Normalize GRPO advantages by std,False,baseline_grpo.yaml / script override
|
||
|
|
Rollout correction,Importance sampling mode,token,script override
|
||
|
|
Rollout correction,IS threshold,2.0,script override
|
||
|
|
Checkpoint/Logging,Checkpoint root,checkpoints/datasets/sciknoweval/chemistry/qwen3gen-chemistry-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8,script override
|
||
|
|
Checkpoint/Logging,Latest checkpointed iteration,100,latest_checkpointed_iteration.txt
|
||
|
|
Checkpoint/Logging,External actor archive,checkpoints/datasets/sciknoweval/chemistry/qwen3gen-chemistry-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/_actor_archive,preserve_actor_checkpoints.py
|
||
|
|
Checkpoint/Logging,Logger,"console, wandb",ppo_trainer.yaml
|
||
|
|
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,Fused kernels,False,method override
|