{
  "repo_id": "SeongryongJung/Qwen3-8B-Physics-GRPO-TR",
  "output_dir": "/mnt/mole/SDPO/L2T/hf_upload_tr/Qwen3-8B-Physics-GRPO-TR",
  "experiment": "qwen3gen-physics-GRPO-Qwen-Qwen3-8B-mbs8-train32-rollout8-lr1e-6-vllm0.8",
  "best_step": 100,
  "best_val_mean16": 0.7296875,
  "best_actor_dir": "/mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/physics/qwen3gen-physics-GRPO-Qwen-Qwen3-8B-mbs8-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actor",
  "final_step": 100,
  "final_val_mean16": 0.7296875,
  "final_actor_dir": "/mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/physics/qwen3gen-physics-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"
  ]
}