{
  "status": "completed",
  "proof_type": "full_1000row_900step_training_log_plus_parameter_hash_change",
  "created_at_utc": "2026-05-18T15:31:41.771274+00:00",
  "MAX_PPO_ROWS": null,
  "train_rows": 900,
  "valid_rows": 100,
  "NUM_PPO_EPOCHS": 2,
  "MAX_PPO_STEPS_PER_EPOCH": null,
  "planned_steps_per_epoch": 450,
  "total_planned_steps": 900,
  "actual_training_log_records": 900,
  "pre_train_fingerprint_path": "/scr/user/kevin2002/TensorCat/NLP/UM_Handbook/outputs/ppo_qwen3_um_handbook_stage3_rule_reward_ppo/ppo_pre_train_parameter_fingerprint.json",
  "post_train_fingerprint_path": "/scr/user/kevin2002/TensorCat/NLP/UM_Handbook/outputs/ppo_qwen3_um_handbook_stage3_rule_reward_ppo/ppo_post_train_parameter_fingerprint.json",
  "parameter_change_proof_path": "/scr/user/kevin2002/TensorCat/NLP/UM_Handbook/outputs/ppo_qwen3_um_handbook_stage3_rule_reward_ppo/ppo_parameter_change_proof.json",
  "parameter_change_proof": {
    "before_aggregate_hash": "086742fb4d02c45f73bb69c33217b92824761227b2a262fc9065bd7f6fe8daea",
    "after_aggregate_hash": "51892ec00ece48c1208e5bd81e40ea5605bb6f45ae856b73842ab26cfafe788c",
    "aggregate_hash_changed": true,
    "common_trainable_tensors": 506,
    "changed_trainable_tensors": 506,
    "unchanged_trainable_tensors": 0,
    "sample_changed_tensors": [
      "pretrained_model.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight",
      "pretrained_model.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight",
      "pretrained_model.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight"
    ],
    "sample_unchanged_tensors": []
  },
  "training_log_path": "/scr/user/kevin2002/TensorCat/NLP/UM_Handbook/outputs/ppo_qwen3_um_handbook_stage3_rule_reward_ppo/ppo_training_log_stable_anticollapse.json",
  "progress_log_path": "/scr/user/kevin2002/TensorCat/NLP/UM_Handbook/outputs/ppo_qwen3_um_handbook_stage3_rule_reward_ppo/ppo_training_progress_eta_log.json",
  "live_status_path": "/scr/user/kevin2002/TensorCat/NLP/UM_Handbook/outputs/ppo_qwen3_um_handbook_stage3_rule_reward_ppo/ppo_training_status_live.json"
}