{
  "repo_id": "SeongryongJung/Qwen3-4B-Biology-RLSD-TR",
  "output_dir": "/mnt/mole/SDPO/L2T/hf_upload_tr/Qwen3-4B-Biology-RLSD-TR",
  "root_checkpoint_step": 90,
  "root_checkpoint_kind": "best_validation",
  "best_step": 90,
  "best_val_mean16": 0.485,
  "best_actor_dir": "/mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/biology/qwen3gen-biology-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/_actor_archive/global_step_90/actor",
  "final_step": 100,
  "final_val_mean16": 0.42875,
  "final_actor_dir": "/mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/biology/qwen3gen-biology-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-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-00002.safetensors",
    "model-00002-of-00002.safetensors"
  ],
  "hf_last_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-00002.safetensors",
    "model-00002-of-00002.safetensors"
  ]
}