初始化项目，由ModelHub XC社区提供模型

Model: SeongryongJung/Qwen3-8B-Chemistry-GRPO-TR
Source: Original Platform

results/hyperparameters.csv

@@ -0,0 +1,33 @@
+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,GRPO,run_qwen3_generalization.sh
+Run identity,Config,baseline_grpo,run_qwen3_generalization.sh
+Run identity,Experiment,qwen3gen-chemistry-GRPO-Qwen-Qwen3-8B-mbs8-train32-rollout8-lr1e-6-vllm0.8,run_qwen3_generalization.sh
+Run identity,W&B run,run-20260702_235814-ffovp19e,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,GRPO 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-GRPO-Qwen-Qwen3-8B-mbs8-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-GRPO-Qwen-Qwen3-8B-mbs8-train32-rollout8-lr1e-6-vllm0.8/_actor_archive,preserve_actor_checkpoints.py
+Checkpoint/Logging,Logger,"console, wandb",ppo_trainer.yaml
+PPO/GRPO,Policy loss mode,vanilla,method override
+PPO/GRPO,Actor KL loss coef,0.0,method override

results/summary.json

@@ -0,0 +1,29 @@
+{
+  "repo_id": "SeongryongJung/Qwen3-8B-Chemistry-GRPO-TR",
+  "output_dir": "/mnt/mole/SDPO/L2T/hf_upload_tr/Qwen3-8B-Chemistry-GRPO-TR",
+  "experiment": "qwen3gen-chemistry-GRPO-Qwen-Qwen3-8B-mbs8-train32-rollout8-lr1e-6-vllm0.8",
+  "best_step": 100,
+  "best_val_mean16": 0.6901785714285714,
+  "best_actor_dir": "/mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/chemistry/qwen3gen-chemistry-GRPO-Qwen-Qwen3-8B-mbs8-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actor",
+  "final_step": 100,
+  "final_val_mean16": 0.6901785714285714,
+  "final_actor_dir": "/mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/chemistry/qwen3gen-chemistry-GRPO-Qwen-Qwen3-8B-mbs8-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actor",
+  "train_rows": 90,
+  "val_rows": 10,
+  "hf_model_files": [
+    "added_tokens.json",
+    "chat_template.jinja",
+    "config.json",
+    "generation_config.json",
+    "merges.txt",
+    "model.safetensors.index.json",
+    "special_tokens_map.json",
+    "tokenizer.json",
+    "tokenizer_config.json",
+    "vocab.json",
+    "model-00001-of-00004.safetensors",
+    "model-00002-of-00004.safetensors",
+    "model-00003-of-00004.safetensors",
+    "model-00004-of-00004.safetensors"
+  ]
+}

results/training_score.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f072ea5e9df6fb097d5515ea9398afe986fe6bd773aae5b382afdd4915dc687
+size 121955

results/training_scores.csv

@@ -0,0 +1,91 @@
+step,critic_score_mean
+1,0.48046875
+2,0.375
+3,0.44921875
+4,0.42578125
+5,0.41015625
+6,0.4140625
+7,0.28125
+8,0.48828125
+9,0.35546875
+11,0.5078125
+12,0.44140625
+13,0.37109375
+14,0.39453125
+15,0.453125
+16,0.48828125
+17,0.3984375
+18,0.4609375
+19,0.4921875
+21,0.35546875
+22,0.44921875
+23,0.609375
+24,0.49609375
+25,0.5
+26,0.5546875
+27,0.515625
+28,0.5390625
+29,0.46484375
+31,0.51171875
+32,0.45703125
+33,0.57421875
+34,0.56640625
+35,0.4921875
+36,0.55859375
+37,0.46484375
+38,0.58203125
+39,0.47265625
+41,0.5625
+42,0.55859375
+43,0.5859375
+44,0.60546875
+45,0.58984375
+46,0.46484375
+47,0.5625
+48,0.58203125
+49,0.6484375
+51,0.59375
+52,0.5625
+53,0.61328125
+54,0.515625
+55,0.61328125
+56,0.5859375
+57,0.60546875
+58,0.63671875
+59,0.50390625
+61,0.6171875
+62,0.63671875
+63,0.46484375
+64,0.73046875
+65,0.66796875
+66,0.60546875
+67,0.6484375
+68,0.41796875
+69,0.5703125
+71,0.59765625
+72,0.69921875
+73,0.578125
+74,0.6796875
+75,0.73828125
+76,0.50390625
+77,0.671875
+78,0.671875
+79,0.62109375
+81,0.65625
+82,0.58203125
+83,0.55078125
+84,0.69140625
+85,0.71875
+86,0.609375
+87,0.59375
+88,0.5546875
+89,0.546875
+91,0.6171875
+92,0.62109375
+93,0.8515625
+94,0.72265625
+95,0.7421875
+96,0.640625
+97,0.5859375
+98,0.56640625
+99,0.58984375

results/validation_mean16.csv

@@ -0,0 +1,11 @@
+step,val_mean16
+10,0.42410714285714285
+20,0.48392857142857143
+30,0.549404761904762
+40,0.6053571428571428
+50,0.6223214285714286
+60,0.6589285714285714
+70,0.6714285714285714
+80,0.6782738095238096
+90,0.6815476190476191
+100,0.6901785714285714