{
  "plan": {
    "active_roles": [
      "decomposer",
      "retriever",
      "builder",
      "verifier"
    ],
    "eval": {
      "batch_size": 12,
      "max_new_tokens": 1536,
      "role_batch_size": {
        "builder": 13,
        "decomposer": 25,
        "retriever": 25,
        "verifier": 17
      },
      "role_max_new_tokens": {
        "builder": 1472,
        "decomposer": 576,
        "retriever": 672,
        "verifier": 1440
      },
      "sanity_batch_size": 20,
      "sanity_max_new_tokens": 64
    },
    "full_scale_traces": 1600,
    "lora": {
      "alpha": 32,
      "dropout": 0.05,
      "r": 16,
      "target_modules": [
        "q_proj",
        "k_proj",
        "v_proj",
        "o_proj",
        "gate_proj",
        "up_proj",
        "down_proj"
      ]
    },
    "max_len": 3328,
    "phase": "kaggle-2xt4-modular-multi-lora-v1",
    "pip": [
      "transformers==5.22.0",
      "peft==0.21.2",
      "accelerate==1.15.0"
    ],
    "train_jobs": [
      {
        "adapter_key": "decomposer_1600",
        "gpu": 0,
        "grad_accum": 8,
        "kind": "sft",
        "lr": 0.00025,
        "micro_batch": 1,
        "persist_in_working": true,
        "public_name": "lora.task-decomposer",
        "role": "decomposer",
        "save_reload_probe": true,
        "scale": 1600,
        "seed": 101,
        "sft_steps": 44,
        "train_file": "sft_decomposer_1600.jsonl"
      },
      {
        "adapter_key": "retriever_1600",
        "gpu": 0,
        "grad_accum": 8,
        "kind": "sft",
        "lr": 0.00025,
        "micro_batch": 1,
        "persist_in_working": true,
        "public_name": "lora.shim-retriever",
        "role": "retriever",
        "scale": 1600,
        "seed": 102,
        "sft_steps": 44,
        "train_file": "sft_retriever_1600.jsonl"
      },
      {
        "adapter_key": "builder_1600",
        "gpu": 0,
        "grad_accum": 8,
        "kind": "sft",
        "lr": 0.00025,
        "micro_batch": 1,
        "persist_in_working": true,
        "public_name": "lora.builder-toolcalls",
        "role": "builder",
        "scale": 1600,
        "seed": 103,
        "sft_steps": 48,
        "train_file": "sft_builder_1600.jsonl"
      },
      {
        "adapter_key": "decomposer_256",
        "gpu": 0,
        "grad_accum": 8,
        "kind": "sft",
        "lr": 0.00022,
        "micro_batch": 1,
        "persist_in_working": false,
        "public_name": "lora.task-decomposer-256",
        "role": "decomposer",
        "scale": 256,
        "seed": 201,
        "sft_steps": 20,
        "train_file": "sft_decomposer_256.jsonl"
      },
      {
        "adapter_key": "retriever_256",
        "gpu": 0,
        "grad_accum": 8,
        "kind": "sft",
        "lr": 0.00022,
        "micro_batch": 1,
        "persist_in_working": false,
        "public_name": "lora.shim-retriever-256",
        "role": "retriever",
        "scale": 256,
        "seed": 202,
        "sft_steps": 20,
        "train_file": "sft_retriever_256.jsonl"
      },
      {
        "adapter_key": "builder_256",
        "gpu": 0,
        "grad_accum": 8,
        "kind": "sft",
        "lr": 0.00022,
        "micro_batch": 1,
        "persist_in_working": false,
        "public_name": "lora.builder-toolcalls-256",
        "role": "builder",
        "scale": 256,
        "seed": 203,
        "sft_steps": 22,
        "train_file": "sft_builder_256.jsonl"
      },
      {
        "adapter_key": "decomposer_64",
        "gpu": 0,
        "grad_accum": 4,
        "kind": "sft",
        "lr": 0.0002,
        "micro_batch": 1,
        "persist_in_working": false,
        "public_name": "lora.task-decomposer-64",
        "role": "decomposer",
        "scale": 64,
        "seed": 301,
        "sft_steps": 8,
        "train_file": "sft_decomposer_64.jsonl"
      },
      {
        "adapter_key": "retriever_64",
        "gpu": 0,
        "grad_accum": 4,
        "kind": "sft",
        "lr": 0.0002,
        "micro_batch": 1,
        "persist_in_working": false,
        "public_name": "lora.shim-retriever-64",
        "role": "retriever",
        "scale": 64,
        "seed": 302,
        "sft_steps": 8,
        "train_file": "sft_retriever_64.jsonl"
      },
      {
        "adapter_key": "builder_64",
        "gpu": 0,
        "grad_accum": 4,
        "kind": "sft",
        "lr": 0.0002,
        "micro_batch": 1,
        "persist_in_working": false,
        "public_name": "lora.builder-toolcalls-64",
        "role": "builder",
        "scale": 64,
        "seed": 303,
        "sft_steps": 8,
        "train_file": "sft_builder_64.jsonl"
      },
      {
        "adapter_key": "verifier_1600",
        "dpo_beta": 0.12,
        "dpo_file": "dpo_verifier_1600.jsonl",
        "dpo_grad_accum": 4,
        "dpo_lr": 8e-05,
        "dpo_micro_batch": 1,
        "dpo_nll_coef": 0.15,
        "dpo_steps": 28,
        "gpu": 1,
        "grad_accum": 8,
        "kind": "sft_dpo",
        "lr": 0.00024,
        "micro_batch": 1,
        "persist_in_working": true,
        "public_name": "lora.verifier-dpo",
        "role": "verifier",
        "scale": 1600,
        "seed": 104,
        "sft_steps": 24,
        "train_file": "sft_verifier_1600.jsonl"
      },
      {
        "adapter_key": "verifier_256",
        "dpo_beta": 0.12,
        "dpo_file": "dpo_verifier_256.jsonl",
        "dpo_grad_accum": 4,
        "dpo_lr": 7.5e-05,
        "dpo_micro_batch": 1,
        "dpo_nll_coef": 0.15,
        "dpo_steps": 16,
        "gpu": 1,
        "grad_accum": 8,
        "kind": "sft_dpo",
        "lr": 0.00022,
        "micro_batch": 1,
        "persist_in_working": false,
        "public_name": "lora.verifier-dpo-256",
        "role": "verifier",
        "scale": 256,
        "seed": 204,
        "sft_steps": 14,
        "train_file": "sft_verifier_256.jsonl"
      },
      {
        "adapter_key": "verifier_64",
        "dpo_beta": 0.12,
        "dpo_file": "dpo_verifier_64.jsonl",
        "dpo_grad_accum": 2,
        "dpo_lr": 7e-05,
        "dpo_micro_batch": 1,
        "dpo_nll_coef": 0.15,
        "dpo_steps": 8,
        "gpu": 1,
        "grad_accum": 4,
        "kind": "sft_dpo",
        "lr": 0.0002,
        "micro_batch": 1,
        "persist_in_working": false,
        "public_name": "lora.verifier-dpo-64",
        "role": "verifier",
        "scale": 64,
        "seed": 304,
        "sft_steps": 6,
        "train_file": "sft_verifier_64.jsonl"
      },
      {
        "adapter_key": "monolithic_1600",
        "gpu": 1,
        "grad_accum": 8,
        "kind": "sft",
        "lr": 0.00024,
        "micro_batch": 1,
        "persist_in_working": true,
        "public_name": "lora.monolithic-mixed",
        "role": "monolithic_mixed",
        "scale": 1600,
        "seed": 401,
        "sft_steps": 56,
        "train_file": "sft_monolithic_1600.jsonl"
      },
      {
        "adapter_key": "monolithic_256",
        "gpu": 1,
        "grad_accum": 8,
        "kind": "sft",
        "lr": 0.00022,
        "micro_batch": 1,
        "persist_in_working": false,
        "public_name": "lora.monolithic-mixed-256",
        "role": "monolithic_mixed",
        "scale": 256,
        "seed": 402,
        "sft_steps": 24,
        "train_file": "sft_monolithic_256.jsonl"
      },
      {
        "adapter_key": "monolithic_64",
        "gpu": 1,
        "grad_accum": 4,
        "kind": "sft",
        "lr": 0.0002,
        "micro_batch": 1,
        "persist_in_working": false,
        "public_name": "lora.monolithic-mixed-64",
        "role": "monolithic_mixed",
        "scale": 64,
        "seed": 403,
        "sft_steps": 10,
        "train_file": "sft_monolithic_64.jsonl"
      }
    ]
  },
  "cpu_rehearsal": false,
  "started_unix": 1793421691.408391,
  "stages": {
    "environment": {
      "status": "ok",
      "pip_tail": "ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\ngradio 6.26.0 requires pillow<13.0,>=8.0, but you have pillow 13.0.0 which is incompatible.",
      "pip_seconds": 17.17,
      "versions": {
        "torch": "2.11.0+cu128",
        "transformers": "5.22.0",
        "peft": "0.21.2",
        "accelerate": "1.15.0",
        "safetensors": "0.8.0",
        "tokenizers": "0.23.1"
      },
      "python": "3.13.15 (main, Aug  6 2026, 11:06:22) [GCC 13.3.0]",
      "nvidia_smi_gpus": "0, Tesla T4, 15360 MiB, 580.178.04\n1, Tesla T4, 15360 MiB, 580.178.04",
      "docker_image": "gcr.io/kaggle-gpu-images/python@sha256:9a6bcfda6d03b2cd9aa347ee8c1bae62043328ed0f4afe9bda014e4f8bbf9435",
      "seconds": 17.24
    },
    "model_and_data_integrity": {
      "status": "ok",
      "model_dir": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
      "model_small_files": {
        "config.json": {
          "sha256": "39fb36dc5416f445ebc4e71cb71fbcf6727e80a35836d8ba1a1474c318467b7a",
          "matches_official": true
        },
        "tokenizer.json": {
          "sha256": "bbc1904d35169c542dffbe1f7589a5994ec7426d9e5b609d07bab876f32e97ab",
          "matches_official": true
        },
        "tokenizer_config.json": {
          "sha256": "24e8a6dc2547164b7002e3125f10b415105644fcf02bf9ad8b674c87b1eaaed6",
          "matches_official": true
        }
      },
      "data_dir": "/kaggle/input/datasets/<kaggle-user>/ta-amps-modular-swarm-v1",
      "dataset_files_verified": {
        "dpo_holdout.jsonl": {
          "rows": 50,
          "sha256": "da79e1f8a01aa939b7cb7441001bf96d515f06fb737e419321ca0fbbfe700a29",
          "verified": true
        },
        "dpo_verifier_1600.jsonl": {
          "rows": 100,
          "sha256": "f0128314d18c5e5bebce58f90347d075543883a0b8411802ff8d066e445f298e",
          "verified": true
        },
        "dpo_verifier_256.jsonl": {
          "rows": 64,
          "sha256": "097824c13d1e15f003ce88648a4876212c7fcddbad8d6d56793fd7de47310dfc",
          "verified": true
        },
        "dpo_verifier_64.jsonl": {
          "rows": 16,
          "sha256": "f9ccd3c2c3cf0898968ee96a68f01b935d8e7695d36e7f69aca733f30ef20dd4",
          "verified": true
        },
        "holdout_eval.jsonl": {
          "rows": 200,
          "sha256": "0b67c1d0b7ddf3deeb2a8e5679da245607f2eef5a79883ff26db2b83d960bec3",
          "verified": true
        },
        "sanity_40.jsonl": {
          "rows": 40,
          "sha256": "1271140ebde3ef699234f152e979adde0b3729f605c5ab3d432ff90a34ddd7eb",
          "verified": true
        },
        "sft_builder_1600.jsonl": {
          "rows": 500,
          "sha256": "d526872956e8ea78998b8109e515392d21b0957d99dd4f99cedb67a5f8e03af4",
          "verified": true
        },
        "sft_builder_256.jsonl": {
          "rows": 64,
          "sha256": "5b6b4ebacb2747664a86ceeed2aed3612e086e2454d8584f0e806e8f13c1ea64",
          "verified": true
        },
        "sft_builder_64.jsonl": {
          "rows": 16,
          "sha256": "73bd18d7f7ba57ada1bd42a37634222605c89e19c046c993f4f6d28bc2c8ed61",
          "verified": true
        },
        "sft_decomposer_1600.jsonl": {
          "rows": 500,
          "sha256": "c5ab93f919b03d90ec2f76289977da7bb91d19bab557fd757d2b9de6f3f78fd3",
          "verified": true
        },
        "sft_decomposer_256.jsonl": {
          "rows": 64,
          "sha256": "6ff9e1d8f5e2f528e13cc120fb6920419e6627a5622b48fb24cf1bcdab0746a6",
          "verified": true
        },
        "sft_decomposer_64.jsonl": {
          "rows": 16,
          "sha256": "5978334261c6fe24b0dc2778a7f6c9ee7ad536a513d9933e6444be07ad414f92",
          "verified": true
        },
        "sft_monolithic_1600.jsonl": {
          "rows": 1600,
          "sha256": "6f31b4c08a697f8364641c2c0465544b6c70b1c31d983b164c26df7d5a902a25",
          "verified": true
        },
        "sft_monolithic_256.jsonl": {
          "rows": 256,
          "sha256": "d8086d999849065b3b3c73ad4d559432ccc4a541bb11d9027b8076949c81c65e",
          "verified": true
        },
        "sft_monolithic_64.jsonl": {
          "rows": 64,
          "sha256": "5c9c02172602bbf8eb5d8d631aa711fb9ea50ad0dae39585c8df166477ed2c12",
          "verified": true
        },
        "sft_retriever_1600.jsonl": {
          "rows": 500,
          "sha256": "41e98525a1540c69786ccba23b2e97cfede2931cc67e9c038892f0d293c29a88",
          "verified": true
        },
        "sft_retriever_256.jsonl": {
          "rows": 64,
          "sha256": "986faff47a4fc7a08f51fdc46bb389a029003b5acd85b2b31d1af035b93a6612",
          "verified": true
        },
        "sft_retriever_64.jsonl": {
          "rows": 16,
          "sha256": "d60f84a90c5a1328d7c487423363174a48df0ce7022b0ce3314e437c7263dd5e",
          "verified": true
        },
        "sft_verifier_1600.jsonl": {
          "rows": 100,
          "sha256": "afbee6754df5325b04db1cb7e9424e7ca9157516dafd811d4956d35ac80bdad4",
          "verified": true
        },
        "sft_verifier_256.jsonl": {
          "rows": 64,
          "sha256": "b68bec7941a57c8832dbb46c3322082a3cf8a50a42c4313631c8cbc014b5b5f8",
          "verified": true
        },
        "sft_verifier_64.jsonl": {
          "rows": 16,
          "sha256": "22a3bcfcecef93665375316cd2dd19dd4eb5efe6dceedcef54dcf6f2fc1422e1",
          "verified": true
        }
      },
      "zero_contamination_verified": {
        "gold_holdout_self_score": 1.0,
        "nested_subsets_verified": true,
        "prompt_fingerprint_overlap": 0,
        "workflow_id_overlap": 0
      },
      "seconds": 1.12
    },
    "parallel_train_2xt4": {
      "status": "ok",
      "gpu0": {
        "base_load": {
          "load_seconds": 8.48,
          "dtype": "torch.float16",
          "gpu_index": 0,
          "mem_alloc_mib": 6128
        },
        "fp16_headroom": {
          "logits_finite": true,
          "max_layer_maxabs": 422.0,
          "all_layers_finite": true
        },
        "peak_alloc_mib": 11275,
        "adapters_trained": {
          "lora.task-decomposer": {
            "adapter_key": "decomposer_1600",
            "public_name": "lora.task-decomposer",
            "saved_dir": "/kaggle/working/adapters/decomposer_1600",
            "persisted_in_working": true,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "9b8c1be09b50308e61b386695bbc4c53e243ed2f421fa6ae861d113353e57697"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "290e0c28a328c0afb4d33c47e03705a72cc8cc7c08bd62a41b65ee9805dd5ef4"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "o_proj",
                "up_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "down_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 1600,
            "role": "decomposer",
            "kind": "sft",
            "trainable_params": 24313856,
            "train_rows": 500,
            "sft_steps": 44,
            "dpo_steps": 0,
            "skipped_steps": 0,
            "train_seconds": 1227.27,
            "tokens_processed": 177782,
            "tokens_per_s": 144.9,
            "initial_loss": 1.25769,
            "final_loss": 0.36004,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 0.36813,
            "max_abs_diff_tuned_vs_base": 34.84375,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.shim-retriever": {
            "adapter_key": "retriever_1600",
            "public_name": "lora.shim-retriever",
            "saved_dir": "/kaggle/working/adapters/retriever_1600",
            "persisted_in_working": true,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "9b8c1be09b50308e61b386695bbc4c53e243ed2f421fa6ae861d113353e57697"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "567596a253fad7ec6cba8ec796a8bc7de33aa28d6513609a83b1714c28c4cc86"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "o_proj",
                "up_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "down_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 1600,
            "role": "retriever",
            "kind": "sft",
            "trainable_params": 24313856,
            "train_rows": 500,
            "sft_steps": 44,
            "dpo_steps": 0,
            "skipped_steps": 0,
            "train_seconds": 1156.7,
            "tokens_processed": 201112,
            "tokens_per_s": 173.9,
            "initial_loss": 1.40856,
            "final_loss": 0.35491,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 1.88547,
            "max_abs_diff_tuned_vs_base": 21.47266,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.builder-toolcalls": {
            "adapter_key": "builder_1600",
            "public_name": "lora.builder-toolcalls",
            "saved_dir": "/kaggle/working/adapters/builder_1600",
            "persisted_in_working": true,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "9b8c1be09b50308e61b386695bbc4c53e243ed2f421fa6ae861d113353e57697"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "c855137afee481a9a3e7f4aa434b90fb6dc2815151d6d088436a471cddff6434"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "o_proj",
                "up_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "down_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 1600,
            "role": "builder",
            "kind": "sft",
            "trainable_params": 24313856,
            "train_rows": 500,
            "sft_steps": 48,
            "dpo_steps": 0,
            "skipped_steps": 0,
            "train_seconds": 3118.45,
            "tokens_processed": 302359,
            "tokens_per_s": 97.0,
            "initial_loss": 1.31247,
            "final_loss": 0.66591,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 1.63649,
            "max_abs_diff_tuned_vs_base": 23.25391,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.task-decomposer-256": {
            "adapter_key": "decomposer_256",
            "public_name": "lora.task-decomposer-256",
            "saved_dir": "/tmp/modular_llama32_run/adapters/decomposer_256",
            "persisted_in_working": false,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "9b8c1be09b50308e61b386695bbc4c53e243ed2f421fa6ae861d113353e57697"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "a5cae29f47245f6b7063e5b628be56b720d2176e4440a06ed63e9e63739b4769"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "o_proj",
                "up_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "down_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 256,
            "role": "decomposer",
            "kind": "sft",
            "trainable_params": 24313856,
            "train_rows": 64,
            "sft_steps": 20,
            "dpo_steps": 0,
            "skipped_steps": 0,
            "train_seconds": 570.97,
            "tokens_processed": 80853,
            "tokens_per_s": 141.6,
            "initial_loss": 1.243,
            "final_loss": 0.35068,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 0.37347,
            "max_abs_diff_tuned_vs_base": 27.03271,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.shim-retriever-256": {
            "adapter_key": "retriever_256",
            "public_name": "lora.shim-retriever-256",
            "saved_dir": "/tmp/modular_llama32_run/adapters/retriever_256",
            "persisted_in_working": false,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "9b8c1be09b50308e61b386695bbc4c53e243ed2f421fa6ae861d113353e57697"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "f78f92a8707e093994e0a034a0e8a608c56522b24cffdcd2c710dc7a7d46b6fd"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "o_proj",
                "up_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "down_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 256,
            "role": "retriever",
            "kind": "sft",
            "trainable_params": 24313856,
            "train_rows": 64,
            "sft_steps": 20,
            "dpo_steps": 0,
            "skipped_steps": 0,
            "train_seconds": 550.56,
            "tokens_processed": 91432,
            "tokens_per_s": 166.1,
            "initial_loss": 1.40697,
            "final_loss": 0.43977,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 1.59712,
            "max_abs_diff_tuned_vs_base": 16.79688,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.builder-toolcalls-256": {
            "adapter_key": "builder_256",
            "public_name": "lora.builder-toolcalls-256",
            "saved_dir": "/tmp/modular_llama32_run/adapters/builder_256",
            "persisted_in_working": false,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "9b8c1be09b50308e61b386695bbc4c53e243ed2f421fa6ae861d113353e57697"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "f1deb9a94fb522ecc0a0e3ff01c3d2b19193c17fe01e14ed446d4646e3c9af5a"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "o_proj",
                "up_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "down_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 256,
            "role": "builder",
            "kind": "sft",
            "trainable_params": 24313856,
            "train_rows": 64,
            "sft_steps": 22,
            "dpo_steps": 0,
            "skipped_steps": 0,
            "train_seconds": 1509.94,
            "tokens_processed": 141265,
            "tokens_per_s": 93.6,
            "initial_loss": 1.23977,
            "final_loss": 0.621,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 1.49375,
            "max_abs_diff_tuned_vs_base": 19.81641,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.task-decomposer-64": {
            "adapter_key": "decomposer_64",
            "public_name": "lora.task-decomposer-64",
            "saved_dir": "/tmp/modular_llama32_run/adapters/decomposer_64",
            "persisted_in_working": false,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "9b8c1be09b50308e61b386695bbc4c53e243ed2f421fa6ae861d113353e57697"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "aba06f0d381470754cce52df2d07dc4dad11808892e2992f1d9bd1274ead5f57"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "o_proj",
                "up_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "down_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 64,
            "role": "decomposer",
            "kind": "sft",
            "trainable_params": 24313856,
            "train_rows": 16,
            "sft_steps": 8,
            "dpo_steps": 0,
            "skipped_steps": 0,
            "train_seconds": 122.48,
            "tokens_processed": 16134,
            "tokens_per_s": 131.7,
            "initial_loss": 1.25579,
            "final_loss": 0.43129,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 0.43923,
            "max_abs_diff_tuned_vs_base": 20.19141,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.shim-retriever-64": {
            "adapter_key": "retriever_64",
            "public_name": "lora.shim-retriever-64",
            "saved_dir": "/tmp/modular_llama32_run/adapters/retriever_64",
            "persisted_in_working": false,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "9b8c1be09b50308e61b386695bbc4c53e243ed2f421fa6ae861d113353e57697"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "6edb086c99ef4f0df195a304a263b05b0d5dd66b3d0c6515071f76e989a36e77"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "o_proj",
                "up_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "down_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 64,
            "role": "retriever",
            "kind": "sft",
            "trainable_params": 24313856,
            "train_rows": 16,
            "sft_steps": 8,
            "dpo_steps": 0,
            "skipped_steps": 0,
            "train_seconds": 114.27,
            "tokens_processed": 18356,
            "tokens_per_s": 160.6,
            "initial_loss": 1.46724,
            "final_loss": 0.76865,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 1.21533,
            "max_abs_diff_tuned_vs_base": 12.28711,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.builder-toolcalls-64": {
            "adapter_key": "builder_64",
            "public_name": "lora.builder-toolcalls-64",
            "saved_dir": "/tmp/modular_llama32_run/adapters/builder_64",
            "persisted_in_working": false,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "9b8c1be09b50308e61b386695bbc4c53e243ed2f421fa6ae861d113353e57697"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "e13c88bd234b48ba7a3f9521d2538db510db61cff0f8fb5d04be25d8619ed168"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "o_proj",
                "up_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "down_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 64,
            "role": "builder",
            "kind": "sft",
            "trainable_params": 24313856,
            "train_rows": 16,
            "sft_steps": 8,
            "dpo_steps": 0,
            "skipped_steps": 0,
            "train_seconds": 283.72,
            "tokens_processed": 26452,
            "tokens_per_s": 93.2,
            "initial_loss": 1.05554,
            "final_loss": 0.74602,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 1.215,
            "max_abs_diff_tuned_vs_base": 13.85156,
            "max_abs_diff_disabled_vs_base": 0.0
          }
        }
      },
      "gpu1": {
        "base_load": {
          "load_seconds": 8.48,
          "dtype": "torch.float16",
          "gpu_index": 1,
          "mem_alloc_mib": 6128
        },
        "fp16_headroom": {
          "logits_finite": true,
          "max_layer_maxabs": 422.0,
          "all_layers_finite": true
        },
        "peak_alloc_mib": 11025,
        "adapters_trained": {
          "lora.verifier-dpo": {
            "adapter_key": "verifier_1600",
            "public_name": "lora.verifier-dpo",
            "saved_dir": "/kaggle/working/adapters/verifier_1600",
            "persisted_in_working": true,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "0f93046676d1a5d9c1a5efa0bd5ee344e81c870431f1611e570eab4037001f1d"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "795f41fdbf6e8acb977589809fd626db3c63721e26f482c4fb9fd45ae45e43be"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "down_proj",
                "o_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "up_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 1600,
            "role": "verifier",
            "kind": "sft_dpo",
            "trainable_params": 24313856,
            "train_rows": 100,
            "sft_steps": 24,
            "dpo_steps": 28,
            "skipped_steps": 0,
            "train_seconds": 1584.79,
            "tokens_processed": 438301,
            "tokens_per_s": 276.6,
            "initial_loss": 1.38837,
            "final_loss": 0.06535,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 1.76513,
            "max_abs_diff_tuned_vs_base": 21.43359,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.verifier-dpo-256": {
            "adapter_key": "verifier_256",
            "public_name": "lora.verifier-dpo-256",
            "saved_dir": "/tmp/modular_llama32_run/adapters/verifier_256",
            "persisted_in_working": false,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "0f93046676d1a5d9c1a5efa0bd5ee344e81c870431f1611e570eab4037001f1d"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "d914c72ad1db27d8ed0026ab4d6bbe3d96831a66d243bb7283727fc28d5b7728"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "down_proj",
                "o_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "up_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 256,
            "role": "verifier",
            "kind": "sft_dpo",
            "trainable_params": 24313856,
            "train_rows": 64,
            "sft_steps": 14,
            "dpo_steps": 16,
            "skipped_steps": 0,
            "train_seconds": 908.78,
            "tokens_processed": 248903,
            "tokens_per_s": 273.9,
            "initial_loss": 1.31308,
            "final_loss": 0.07016,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 1.64733,
            "max_abs_diff_tuned_vs_base": 19.13672,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.verifier-dpo-64": {
            "adapter_key": "verifier_64",
            "public_name": "lora.verifier-dpo-64",
            "saved_dir": "/tmp/modular_llama32_run/adapters/verifier_64",
            "persisted_in_working": false,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "0f93046676d1a5d9c1a5efa0bd5ee344e81c870431f1611e570eab4037001f1d"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "ec9304c3048a31e5d3612ed9c668d6f6e231ea8a2bdeb4fb9aff5a75ac300d80"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "down_proj",
                "o_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "up_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 64,
            "role": "verifier",
            "kind": "sft_dpo",
            "trainable_params": 24313856,
            "train_rows": 16,
            "sft_steps": 6,
            "dpo_steps": 8,
            "skipped_steps": 0,
            "train_seconds": 214.64,
            "tokens_processed": 59151,
            "tokens_per_s": 275.6,
            "initial_loss": 1.34558,
            "final_loss": 0.08316,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 1.3752,
            "max_abs_diff_tuned_vs_base": 18.53809,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.monolithic-mixed": {
            "adapter_key": "monolithic_1600",
            "public_name": "lora.monolithic-mixed",
            "saved_dir": "/kaggle/working/adapters/monolithic_1600",
            "persisted_in_working": true,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "0f93046676d1a5d9c1a5efa0bd5ee344e81c870431f1611e570eab4037001f1d"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "4dd4ed96ec0a2f835405ca03d95179b238dbc6a4eaea6e65d7fd13d1c9111ccf"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "down_proj",
                "o_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "up_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 1600,
            "role": "monolithic_mixed",
            "kind": "sft",
            "trainable_params": 24313856,
            "train_rows": 1600,
            "sft_steps": 56,
            "dpo_steps": 0,
            "skipped_steps": 0,
            "train_seconds": 2098.05,
            "tokens_processed": 284121,
            "tokens_per_s": 135.4,
            "initial_loss": 1.30531,
            "final_loss": 0.42555,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 0.36392,
            "max_abs_diff_tuned_vs_base": 30.14209,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.monolithic-mixed-256": {
            "adapter_key": "monolithic_256",
            "public_name": "lora.monolithic-mixed-256",
            "saved_dir": "/tmp/modular_llama32_run/adapters/monolithic_256",
            "persisted_in_working": false,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "0f93046676d1a5d9c1a5efa0bd5ee344e81c870431f1611e570eab4037001f1d"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "01662598ebb42fc89b6b3d70d76faf43ceb4f6fef1c5e5b9f85466df97573a5f"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "down_proj",
                "o_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "up_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 256,
            "role": "monolithic_mixed",
            "kind": "sft",
            "trainable_params": 24313856,
            "train_rows": 256,
            "sft_steps": 24,
            "dpo_steps": 0,
            "skipped_steps": 0,
            "train_seconds": 855.26,
            "tokens_processed": 122219,
            "tokens_per_s": 142.9,
            "initial_loss": 1.38583,
            "final_loss": 0.54069,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 0.37127,
            "max_abs_diff_tuned_vs_base": 28.50146,
            "max_abs_diff_disabled_vs_base": 0.0
          },
          "lora.monolithic-mixed-64": {
            "adapter_key": "monolithic_64",
            "public_name": "lora.monolithic-mixed-64",
            "saved_dir": "/tmp/modular_llama32_run/adapters/monolithic_64",
            "persisted_in_working": false,
            "files": {
              "adapter_config.json": {
                "bytes": 1226,
                "sha256": "0f93046676d1a5d9c1a5efa0bd5ee344e81c870431f1611e570eab4037001f1d"
              },
              "adapter_model.safetensors": {
                "bytes": 97307544,
                "sha256": "dcfc2bc735cf2af14740d476b0ef8a1c7391cb51e74285ade99585cd50921632"
              }
            },
            "adapter_config": {
              "alora_invocation_tokens": null,
              "alpha_pattern": {},
              "arrow_config": null,
              "auto_mapping": null,
              "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
              "bias": "none",
              "corda_config": null,
              "ensure_weight_tying": false,
              "eva_config": null,
              "exclude_modules": null,
              "fan_in_fan_out": false,
              "inference_mode": true,
              "init_lora_weights": true,
              "kasa_config": null,
              "layer_replication": null,
              "layers_pattern": null,
              "layers_to_transform": null,
              "loftq_config": {},
              "lora_alpha": 32,
              "lora_bias": false,
              "lora_dropout": 0.05,
              "lora_ga_config": null,
              "megatron_config": null,
              "megatron_core": "megatron.core",
              "modules_to_save": null,
              "monteclora_config": null,
              "peft_type": "LORA",
              "peft_version": "0.21.2",
              "qalora_group_size": 16,
              "r": 16,
              "rank_pattern": {},
              "revision": null,
              "target_modules": [
                "q_proj",
                "down_proj",
                "o_proj",
                "gate_proj",
                "v_proj",
                "k_proj",
                "up_proj"
              ],
              "target_parameters": null,
              "task_type": "CAUSAL_LM",
              "trainable_token_indices": null,
              "use_bdlora": null,
              "use_dora": false,
              "use_qalora": false,
              "use_rslora": false,
              "velora_config": null
            },
            "scale": 64,
            "role": "monolithic_mixed",
            "kind": "sft",
            "trainable_params": 24313856,
            "train_rows": 64,
            "sft_steps": 10,
            "dpo_steps": 0,
            "skipped_steps": 0,
            "train_seconds": 185.38,
            "tokens_processed": 25886,
            "tokens_per_s": 139.6,
            "initial_loss": 1.46099,
            "final_loss": 1.0088,
            "base_probe_loss": 1.30984,
            "tuned_probe_loss": 0.63205,
            "max_abs_diff_tuned_vs_base": 18.2998,
            "max_abs_diff_disabled_vs_base": 0.0
          }
        }
      },
      "training_curves": {
        "lora.task-decomposer": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.25769,
            "grad_norm": 0.8011,
            "tokens": 4032,
            "sec": 25.68
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.19142,
            "grad_norm": 0.6887,
            "tokens": 4056,
            "sec": 26.12
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.06602,
            "grad_norm": 0.6028,
            "tokens": 4003,
            "sec": 26.8
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 0.89445,
            "grad_norm": 0.6061,
            "tokens": 4001,
            "sec": 29.57
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.73522,
            "grad_norm": 1.1208,
            "tokens": 4014,
            "sec": 26.84
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.55501,
            "grad_norm": 0.9872,
            "tokens": 4014,
            "sec": 28.43
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.43725,
            "grad_norm": 0.9915,
            "tokens": 4074,
            "sec": 30.3
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.38414,
            "grad_norm": 0.8104,
            "tokens": 4052,
            "sec": 28.67
          },
          {
            "phase": "sft",
            "step": 9,
            "loss": 0.3662,
            "grad_norm": 0.2486,
            "tokens": 4038,
            "sec": 26.3
          },
          {
            "phase": "sft",
            "step": 10,
            "loss": 0.37048,
            "grad_norm": 0.6489,
            "tokens": 4060,
            "sec": 30.32
          },
          {
            "phase": "sft",
            "step": 11,
            "loss": 0.36292,
            "grad_norm": 0.2471,
            "tokens": 4056,
            "sec": 29.87
          },
          {
            "phase": "sft",
            "step": 12,
            "loss": 0.36413,
            "grad_norm": 0.2728,
            "tokens": 4012,
            "sec": 25.9
          },
          {
            "phase": "sft",
            "step": 13,
            "loss": 0.36519,
            "grad_norm": 0.1481,
            "tokens": 4006,
            "sec": 28.97
          },
          {
            "phase": "sft",
            "step": 14,
            "loss": 0.35939,
            "grad_norm": 0.0788,
            "tokens": 4034,
            "sec": 28.78
          },
          {
            "phase": "sft",
            "step": 15,
            "loss": 0.35777,
            "grad_norm": 0.0911,
            "tokens": 4026,
            "sec": 28.23
          },
          {
            "phase": "sft",
            "step": 16,
            "loss": 0.35899,
            "grad_norm": 0.0759,
            "tokens": 4053,
            "sec": 24.09
          },
          {
            "phase": "sft",
            "step": 17,
            "loss": 0.35779,
            "grad_norm": 0.0695,
            "tokens": 4056,
            "sec": 28.18
          },
          {
            "phase": "sft",
            "step": 18,
            "loss": 0.35699,
            "grad_norm": 0.0794,
            "tokens": 4064,
            "sec": 29.26
          },
          {
            "phase": "sft",
            "step": 19,
            "loss": 0.35843,
            "grad_norm": 0.1368,
            "tokens": 4034,
            "sec": 27.69
          },
          {
            "phase": "sft",
            "step": 20,
            "loss": 0.35615,
            "grad_norm": 0.0688,
            "tokens": 4028,
            "sec": 29.99
          },
          {
            "phase": "sft",
            "step": 21,
            "loss": 0.357,
            "grad_norm": 0.0555,
            "tokens": 4063,
            "sec": 26.23
          },
          {
            "phase": "sft",
            "step": 22,
            "loss": 0.35505,
            "grad_norm": 0.0737,
            "tokens": 4062,
            "sec": 26.73
          },
          {
            "phase": "sft",
            "step": 23,
            "loss": 0.35729,
            "grad_norm": 0.0932,
            "tokens": 4037,
            "sec": 26.24
          },
          {
            "phase": "sft",
            "step": 24,
            "loss": 0.36073,
            "grad_norm": 0.0734,
            "tokens": 4012,
            "sec": 25.8
          },
          {
            "phase": "sft",
            "step": 25,
            "loss": 0.35526,
            "grad_norm": 0.0778,
            "tokens": 4060,
            "sec": 27.97
          },
          {
            "phase": "sft",
            "step": 26,
            "loss": 0.36068,
            "grad_norm": 0.0637,
            "tokens": 4031,
            "sec": 26.83
          },
          {
            "phase": "sft",
            "step": 27,
            "loss": 0.35446,
            "grad_norm": 0.0612,
            "tokens": 4063,
            "sec": 28.53
          },
          {
            "phase": "sft",
            "step": 28,
            "loss": 0.35125,
            "grad_norm": 0.0545,
            "tokens": 4083,
            "sec": 28.48
          },
          {
            "phase": "sft",
            "step": 29,
            "loss": 0.36349,
            "grad_norm": 0.0547,
            "tokens": 3993,
            "sec": 26.18
          },
          {
            "phase": "sft",
            "step": 30,
            "loss": 0.35862,
            "grad_norm": 0.0632,
            "tokens": 4054,
            "sec": 28.14
          },
          {
            "phase": "sft",
            "step": 31,
            "loss": 0.3583,
            "grad_norm": 0.0705,
            "tokens": 4042,
            "sec": 30.58
          },
          {
            "phase": "sft",
            "step": 32,
            "loss": 0.35625,
            "grad_norm": 0.1472,
            "tokens": 4044,
            "sec": 28.42
          },
          {
            "phase": "sft",
            "step": 33,
            "loss": 0.35395,
            "grad_norm": 0.1007,
            "tokens": 4054,
            "sec": 27.79
          },
          {
            "phase": "sft",
            "step": 34,
            "loss": 0.35235,
            "grad_norm": 0.0512,
            "tokens": 4067,
            "sec": 31.27
          },
          {
            "phase": "sft",
            "step": 35,
            "loss": 0.35712,
            "grad_norm": 0.0932,
            "tokens": 4033,
            "sec": 26.53
          },
          {
            "phase": "sft",
            "step": 36,
            "loss": 0.35775,
            "grad_norm": 0.0551,
            "tokens": 4041,
            "sec": 26.71
          },
          {
            "phase": "sft",
            "step": 37,
            "loss": 0.35531,
            "grad_norm": 0.0526,
            "tokens": 4057,
            "sec": 24.64
          },
          {
            "phase": "sft",
            "step": 38,
            "loss": 0.35558,
            "grad_norm": 0.0965,
            "tokens": 4050,
            "sec": 29.98
          },
          {
            "phase": "sft",
            "step": 39,
            "loss": 0.35049,
            "grad_norm": 0.079,
            "tokens": 4101,
            "sec": 26.46
          },
          {
            "phase": "sft",
            "step": 40,
            "loss": 0.35798,
            "grad_norm": 0.0868,
            "tokens": 4025,
            "sec": 27.79
          },
          {
            "phase": "sft",
            "step": 41,
            "loss": 0.35689,
            "grad_norm": 0.0506,
            "tokens": 4004,
            "sec": 28.84
          },
          {
            "phase": "sft",
            "step": 42,
            "loss": 0.35406,
            "grad_norm": 0.0894,
            "tokens": 4062,
            "sec": 28.36
          },
          {
            "phase": "sft",
            "step": 43,
            "loss": 0.35687,
            "grad_norm": 0.0637,
            "tokens": 4040,
            "sec": 25.8
          },
          {
            "phase": "sft",
            "step": 44,
            "loss": 0.36004,
            "grad_norm": 0.0474,
            "tokens": 3991,
            "sec": 26.48
          }
        ],
        "lora.shim-retriever": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.40856,
            "grad_norm": 0.6824,
            "tokens": 4580,
            "sec": 25.33
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.36484,
            "grad_norm": 0.5784,
            "tokens": 4615,
            "sec": 26.21
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.18361,
            "grad_norm": 0.4604,
            "tokens": 4578,
            "sec": 26.19
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 1.06565,
            "grad_norm": 0.4585,
            "tokens": 4525,
            "sec": 25.84
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.97643,
            "grad_norm": 0.5312,
            "tokens": 4601,
            "sec": 26.29
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.81488,
            "grad_norm": 0.5273,
            "tokens": 4609,
            "sec": 26.44
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.73402,
            "grad_norm": 0.5641,
            "tokens": 4618,
            "sec": 26.68
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.61457,
            "grad_norm": 0.6566,
            "tokens": 4507,
            "sec": 26.24
          },
          {
            "phase": "sft",
            "step": 9,
            "loss": 0.53233,
            "grad_norm": 0.5182,
            "tokens": 4532,
            "sec": 25.96
          },
          {
            "phase": "sft",
            "step": 10,
            "loss": 0.51583,
            "grad_norm": 0.5603,
            "tokens": 4616,
            "sec": 26.5
          },
          {
            "phase": "sft",
            "step": 11,
            "loss": 0.51671,
            "grad_norm": 0.4049,
            "tokens": 4563,
            "sec": 26.32
          },
          {
            "phase": "sft",
            "step": 12,
            "loss": 0.51948,
            "grad_norm": 0.3722,
            "tokens": 4605,
            "sec": 26.49
          },
          {
            "phase": "sft",
            "step": 13,
            "loss": 0.47532,
            "grad_norm": 0.5356,
            "tokens": 4590,
            "sec": 26.39
          },
          {
            "phase": "sft",
            "step": 14,
            "loss": 0.47596,
            "grad_norm": 0.3395,
            "tokens": 4515,
            "sec": 26.06
          },
          {
            "phase": "sft",
            "step": 15,
            "loss": 0.43659,
            "grad_norm": 0.5246,
            "tokens": 4611,
            "sec": 26.53
          },
          {
            "phase": "sft",
            "step": 16,
            "loss": 0.44398,
            "grad_norm": 0.2845,
            "tokens": 4524,
            "sec": 26.23
          },
          {
            "phase": "sft",
            "step": 17,
            "loss": 0.42605,
            "grad_norm": 0.8949,
            "tokens": 4605,
            "sec": 26.45
          },
          {
            "phase": "sft",
            "step": 18,
            "loss": 0.42697,
            "grad_norm": 0.3062,
            "tokens": 4603,
            "sec": 26.23
          },
          {
            "phase": "sft",
            "step": 19,
            "loss": 0.43675,
            "grad_norm": 0.3678,
            "tokens": 4610,
            "sec": 26.56
          },
          {
            "phase": "sft",
            "step": 20,
            "loss": 0.41896,
            "grad_norm": 0.4871,
            "tokens": 4519,
            "sec": 26.27
          },
          {
            "phase": "sft",
            "step": 21,
            "loss": 0.41672,
            "grad_norm": 0.2827,
            "tokens": 4586,
            "sec": 26.23
          },
          {
            "phase": "sft",
            "step": 22,
            "loss": 0.39999,
            "grad_norm": 0.2245,
            "tokens": 4614,
            "sec": 26.5
          },
          {
            "phase": "sft",
            "step": 23,
            "loss": 0.37943,
            "grad_norm": 0.3075,
            "tokens": 4598,
            "sec": 26.61
          },
          {
            "phase": "sft",
            "step": 24,
            "loss": 0.38534,
            "grad_norm": 0.2657,
            "tokens": 4622,
            "sec": 26.6
          },
          {
            "phase": "sft",
            "step": 25,
            "loss": 0.37833,
            "grad_norm": 0.2839,
            "tokens": 4618,
            "sec": 26.51
          },
          {
            "phase": "sft",
            "step": 26,
            "loss": 0.39622,
            "grad_norm": 0.4169,
            "tokens": 4451,
            "sec": 25.78
          },
          {
            "phase": "sft",
            "step": 27,
            "loss": 0.38594,
            "grad_norm": 0.3433,
            "tokens": 4538,
            "sec": 25.95
          },
          {
            "phase": "sft",
            "step": 28,
            "loss": 0.36354,
            "grad_norm": 0.3363,
            "tokens": 4620,
            "sec": 26.39
          },
          {
            "phase": "sft",
            "step": 29,
            "loss": 0.37069,
            "grad_norm": 0.2521,
            "tokens": 4615,
            "sec": 26.31
          },
          {
            "phase": "sft",
            "step": 30,
            "loss": 0.37161,
            "grad_norm": 0.2314,
            "tokens": 4497,
            "sec": 25.69
          },
          {
            "phase": "sft",
            "step": 31,
            "loss": 0.38064,
            "grad_norm": 0.2663,
            "tokens": 4521,
            "sec": 25.62
          },
          {
            "phase": "sft",
            "step": 32,
            "loss": 0.37019,
            "grad_norm": 0.2223,
            "tokens": 4564,
            "sec": 25.79
          },
          {
            "phase": "sft",
            "step": 33,
            "loss": 0.374,
            "grad_norm": 0.2539,
            "tokens": 4533,
            "sec": 25.86
          },
          {
            "phase": "sft",
            "step": 34,
            "loss": 0.35743,
            "grad_norm": 0.2141,
            "tokens": 4558,
            "sec": 25.83
          },
          {
            "phase": "sft",
            "step": 35,
            "loss": 0.36053,
            "grad_norm": 0.2325,
            "tokens": 4576,
            "sec": 25.97
          },
          {
            "phase": "sft",
            "step": 36,
            "loss": 0.35593,
            "grad_norm": 0.2233,
            "tokens": 4578,
            "sec": 26.07
          },
          {
            "phase": "sft",
            "step": 37,
            "loss": 0.35346,
            "grad_norm": 0.234,
            "tokens": 4558,
            "sec": 25.91
          },
          {
            "phase": "sft",
            "step": 38,
            "loss": 0.3486,
            "grad_norm": 0.187,
            "tokens": 4514,
            "sec": 25.78
          },
          {
            "phase": "sft",
            "step": 39,
            "loss": 0.34072,
            "grad_norm": 0.2219,
            "tokens": 4615,
            "sec": 26.22
          },
          {
            "phase": "sft",
            "step": 40,
            "loss": 0.35537,
            "grad_norm": 0.2689,
            "tokens": 4611,
            "sec": 26.09
          },
          {
            "phase": "sft",
            "step": 41,
            "loss": 0.34613,
            "grad_norm": 0.1957,
            "tokens": 4556,
            "sec": 26.21
          },
          {
            "phase": "sft",
            "step": 42,
            "loss": 0.37335,
            "grad_norm": 0.3108,
            "tokens": 4605,
            "sec": 26.08
          },
          {
            "phase": "sft",
            "step": 43,
            "loss": 0.35866,
            "grad_norm": 0.2311,
            "tokens": 4449,
            "sec": 25.87
          },
          {
            "phase": "sft",
            "step": 44,
            "loss": 0.35491,
            "grad_norm": 0.2301,
            "tokens": 4589,
            "sec": 26.16
          }
        ],
        "lora.builder-toolcalls": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.31247,
            "grad_norm": 0.61,
            "tokens": 6081,
            "sec": 56.72
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.20799,
            "grad_norm": 0.5054,
            "tokens": 6158,
            "sec": 61.8
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.19373,
            "grad_norm": 0.4124,
            "tokens": 5844,
            "sec": 63.78
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 1.06694,
            "grad_norm": 0.372,
            "tokens": 6181,
            "sec": 62.69
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.9024,
            "grad_norm": 0.4087,
            "tokens": 7230,
            "sec": 73.66
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.80472,
            "grad_norm": 0.4852,
            "tokens": 7307,
            "sec": 72.12
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.80992,
            "grad_norm": 0.814,
            "tokens": 6125,
            "sec": 65.59
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.72467,
            "grad_norm": 0.3964,
            "tokens": 6292,
            "sec": 62.57
          },
          {
            "phase": "sft",
            "step": 9,
            "loss": 0.70818,
            "grad_norm": 0.4173,
            "tokens": 6627,
            "sec": 68.85
          },
          {
            "phase": "sft",
            "step": 10,
            "loss": 0.65491,
            "grad_norm": 0.2663,
            "tokens": 7632,
            "sec": 73.1
          },
          {
            "phase": "sft",
            "step": 11,
            "loss": 0.73315,
            "grad_norm": 0.5219,
            "tokens": 6028,
            "sec": 63.92
          },
          {
            "phase": "sft",
            "step": 12,
            "loss": 0.7195,
            "grad_norm": 0.3145,
            "tokens": 5801,
            "sec": 59.66
          },
          {
            "phase": "sft",
            "step": 13,
            "loss": 0.68595,
            "grad_norm": 0.3172,
            "tokens": 6428,
            "sec": 61.88
          },
          {
            "phase": "sft",
            "step": 14,
            "loss": 0.67953,
            "grad_norm": 0.1941,
            "tokens": 6538,
            "sec": 71.04
          },
          {
            "phase": "sft",
            "step": 15,
            "loss": 0.67057,
            "grad_norm": 0.2079,
            "tokens": 6851,
            "sec": 65.65
          },
          {
            "phase": "sft",
            "step": 16,
            "loss": 0.71484,
            "grad_norm": 0.2421,
            "tokens": 5579,
            "sec": 57.52
          },
          {
            "phase": "sft",
            "step": 17,
            "loss": 0.73825,
            "grad_norm": 0.1502,
            "tokens": 5184,
            "sec": 56.94
          },
          {
            "phase": "sft",
            "step": 18,
            "loss": 0.70499,
            "grad_norm": 0.1824,
            "tokens": 5589,
            "sec": 60.95
          },
          {
            "phase": "sft",
            "step": 19,
            "loss": 0.65253,
            "grad_norm": 0.1618,
            "tokens": 6562,
            "sec": 69.07
          },
          {
            "phase": "sft",
            "step": 20,
            "loss": 0.67704,
            "grad_norm": 0.1559,
            "tokens": 6176,
            "sec": 63.17
          },
          {
            "phase": "sft",
            "step": 21,
            "loss": 0.70599,
            "grad_norm": 0.1474,
            "tokens": 5729,
            "sec": 68.05
          },
          {
            "phase": "sft",
            "step": 22,
            "loss": 0.70474,
            "grad_norm": 0.1468,
            "tokens": 5730,
            "sec": 59.75
          },
          {
            "phase": "sft",
            "step": 23,
            "loss": 0.67502,
            "grad_norm": 0.225,
            "tokens": 6236,
            "sec": 60.55
          },
          {
            "phase": "sft",
            "step": 24,
            "loss": 0.64337,
            "grad_norm": 0.1319,
            "tokens": 6299,
            "sec": 64.29
          },
          {
            "phase": "sft",
            "step": 25,
            "loss": 0.62034,
            "grad_norm": 0.155,
            "tokens": 6975,
            "sec": 68.98
          },
          {
            "phase": "sft",
            "step": 26,
            "loss": 0.67504,
            "grad_norm": 0.1376,
            "tokens": 5848,
            "sec": 63.56
          },
          {
            "phase": "sft",
            "step": 27,
            "loss": 0.65384,
            "grad_norm": 0.1251,
            "tokens": 5971,
            "sec": 63.36
          },
          {
            "phase": "sft",
            "step": 28,
            "loss": 0.68474,
            "grad_norm": 0.1471,
            "tokens": 5903,
            "sec": 64.57
          },
          {
            "phase": "sft",
            "step": 29,
            "loss": 0.62922,
            "grad_norm": 0.172,
            "tokens": 6955,
            "sec": 67.65
          },
          {
            "phase": "sft",
            "step": 30,
            "loss": 0.69005,
            "grad_norm": 0.1045,
            "tokens": 6013,
            "sec": 65.14
          },
          {
            "phase": "sft",
            "step": 31,
            "loss": 0.66853,
            "grad_norm": 0.0992,
            "tokens": 6184,
            "sec": 63.36
          },
          {
            "phase": "sft",
            "step": 32,
            "loss": 0.68819,
            "grad_norm": 0.1484,
            "tokens": 5838,
            "sec": 62.99
          },
          {
            "phase": "sft",
            "step": 33,
            "loss": 0.65845,
            "grad_norm": 0.1114,
            "tokens": 6264,
            "sec": 64.39
          },
          {
            "phase": "sft",
            "step": 34,
            "loss": 0.63466,
            "grad_norm": 0.0959,
            "tokens": 6427,
            "sec": 63.05
          },
          {
            "phase": "sft",
            "step": 35,
            "loss": 0.64772,
            "grad_norm": 0.1497,
            "tokens": 7088,
            "sec": 69.47
          },
          {
            "phase": "sft",
            "step": 36,
            "loss": 0.63838,
            "grad_norm": 0.1011,
            "tokens": 6864,
            "sec": 68.38
          },
          {
            "phase": "sft",
            "step": 37,
            "loss": 0.72517,
            "grad_norm": 0.1245,
            "tokens": 5656,
            "sec": 59.19
          },
          {
            "phase": "sft",
            "step": 38,
            "loss": 0.65279,
            "grad_norm": 0.1071,
            "tokens": 6324,
            "sec": 62.31
          },
          {
            "phase": "sft",
            "step": 39,
            "loss": 0.67317,
            "grad_norm": 0.1086,
            "tokens": 6405,
            "sec": 67.29
          },
          {
            "phase": "sft",
            "step": 40,
            "loss": 0.70037,
            "grad_norm": 0.1128,
            "tokens": 5733,
            "sec": 70.07
          },
          {
            "phase": "sft",
            "step": 41,
            "loss": 0.62094,
            "grad_norm": 0.0855,
            "tokens": 6983,
            "sec": 67.38
          },
          {
            "phase": "sft",
            "step": 42,
            "loss": 0.67874,
            "grad_norm": 0.0934,
            "tokens": 5626,
            "sec": 59.95
          },
          {
            "phase": "sft",
            "step": 43,
            "loss": 0.72276,
            "grad_norm": 0.0968,
            "tokens": 5395,
            "sec": 54.04
          },
          {
            "phase": "sft",
            "step": 44,
            "loss": 0.62202,
            "grad_norm": 0.0792,
            "tokens": 6644,
            "sec": 64.02
          },
          {
            "phase": "sft",
            "step": 45,
            "loss": 0.64198,
            "grad_norm": 0.0926,
            "tokens": 7132,
            "sec": 73.44
          },
          {
            "phase": "sft",
            "step": 46,
            "loss": 0.57714,
            "grad_norm": 0.0813,
            "tokens": 7224,
            "sec": 72.41
          },
          {
            "phase": "sft",
            "step": 47,
            "loss": 0.62515,
            "grad_norm": 0.0846,
            "tokens": 6458,
            "sec": 66.43
          },
          {
            "phase": "sft",
            "step": 48,
            "loss": 0.66591,
            "grad_norm": 0.1388,
            "tokens": 6242,
            "sec": 66.39
          }
        ],
        "lora.task-decomposer-256": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.243,
            "grad_norm": 0.7817,
            "tokens": 4081,
            "sec": 24.87
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.13711,
            "grad_norm": 0.6182,
            "tokens": 4053,
            "sec": 26.21
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 0.95018,
            "grad_norm": 0.5966,
            "tokens": 4005,
            "sec": 27.39
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 0.80772,
            "grad_norm": 0.925,
            "tokens": 4017,
            "sec": 32.01
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.63308,
            "grad_norm": 1.0427,
            "tokens": 4069,
            "sec": 29.09
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.49567,
            "grad_norm": 0.9094,
            "tokens": 4014,
            "sec": 29.65
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.40543,
            "grad_norm": 0.7315,
            "tokens": 4030,
            "sec": 26.64
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.37602,
            "grad_norm": 0.6581,
            "tokens": 4041,
            "sec": 28.7
          },
          {
            "phase": "sft",
            "step": 9,
            "loss": 0.36759,
            "grad_norm": 0.5758,
            "tokens": 4066,
            "sec": 28.64
          },
          {
            "phase": "sft",
            "step": 10,
            "loss": 0.3613,
            "grad_norm": 0.1428,
            "tokens": 4015,
            "sec": 27.66
          },
          {
            "phase": "sft",
            "step": 11,
            "loss": 0.35714,
            "grad_norm": 0.0948,
            "tokens": 4050,
            "sec": 26.44
          },
          {
            "phase": "sft",
            "step": 12,
            "loss": 0.35395,
            "grad_norm": 0.09,
            "tokens": 4087,
            "sec": 29.44
          },
          {
            "phase": "sft",
            "step": 13,
            "loss": 0.36385,
            "grad_norm": 0.1212,
            "tokens": 3981,
            "sec": 26.28
          },
          {
            "phase": "sft",
            "step": 14,
            "loss": 0.35516,
            "grad_norm": 0.1982,
            "tokens": 4074,
            "sec": 29.17
          },
          {
            "phase": "sft",
            "step": 15,
            "loss": 0.35538,
            "grad_norm": 0.0842,
            "tokens": 4057,
            "sec": 30.61
          },
          {
            "phase": "sft",
            "step": 16,
            "loss": 0.36373,
            "grad_norm": 0.0632,
            "tokens": 3980,
            "sec": 27.64
          },
          {
            "phase": "sft",
            "step": 17,
            "loss": 0.35951,
            "grad_norm": 0.0697,
            "tokens": 4031,
            "sec": 28.64
          },
          {
            "phase": "sft",
            "step": 18,
            "loss": 0.35053,
            "grad_norm": 0.0736,
            "tokens": 4080,
            "sec": 32.0
          },
          {
            "phase": "sft",
            "step": 19,
            "loss": 0.35593,
            "grad_norm": 0.1226,
            "tokens": 4040,
            "sec": 26.61
          },
          {
            "phase": "sft",
            "step": 20,
            "loss": 0.35068,
            "grad_norm": 0.0628,
            "tokens": 4082,
            "sec": 29.13
          }
        ],
        "lora.shim-retriever-256": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.40697,
            "grad_norm": 0.6933,
            "tokens": 4565,
            "sec": 27.29
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.33197,
            "grad_norm": 0.5423,
            "tokens": 4613,
            "sec": 27.71
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.12989,
            "grad_norm": 0.4448,
            "tokens": 4594,
            "sec": 27.26
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 1.04305,
            "grad_norm": 0.494,
            "tokens": 4576,
            "sec": 27.61
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.87149,
            "grad_norm": 0.514,
            "tokens": 4435,
            "sec": 26.89
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.81469,
            "grad_norm": 0.5215,
            "tokens": 4590,
            "sec": 27.5
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.67351,
            "grad_norm": 0.5238,
            "tokens": 4604,
            "sec": 27.48
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.63471,
            "grad_norm": 0.7025,
            "tokens": 4617,
            "sec": 27.51
          },
          {
            "phase": "sft",
            "step": 9,
            "loss": 0.58528,
            "grad_norm": 0.5839,
            "tokens": 4608,
            "sec": 27.46
          },
          {
            "phase": "sft",
            "step": 10,
            "loss": 0.51855,
            "grad_norm": 0.4629,
            "tokens": 4612,
            "sec": 27.31
          },
          {
            "phase": "sft",
            "step": 11,
            "loss": 0.51869,
            "grad_norm": 0.396,
            "tokens": 4582,
            "sec": 27.18
          },
          {
            "phase": "sft",
            "step": 12,
            "loss": 0.48399,
            "grad_norm": 0.3984,
            "tokens": 4558,
            "sec": 27.26
          },
          {
            "phase": "sft",
            "step": 13,
            "loss": 0.47531,
            "grad_norm": 0.3381,
            "tokens": 4578,
            "sec": 27.26
          },
          {
            "phase": "sft",
            "step": 14,
            "loss": 0.47979,
            "grad_norm": 0.2956,
            "tokens": 4556,
            "sec": 27.18
          },
          {
            "phase": "sft",
            "step": 15,
            "loss": 0.45845,
            "grad_norm": 0.3487,
            "tokens": 4546,
            "sec": 27.11
          },
          {
            "phase": "sft",
            "step": 16,
            "loss": 0.45636,
            "grad_norm": 0.3528,
            "tokens": 4554,
            "sec": 27.15
          },
          {
            "phase": "sft",
            "step": 17,
            "loss": 0.4309,
            "grad_norm": 0.324,
            "tokens": 4562,
            "sec": 27.15
          },
          {
            "phase": "sft",
            "step": 18,
            "loss": 0.43981,
            "grad_norm": 0.3682,
            "tokens": 4586,
            "sec": 27.4
          },
          {
            "phase": "sft",
            "step": 19,
            "loss": 0.43783,
            "grad_norm": 0.2881,
            "tokens": 4520,
            "sec": 27.43
          },
          {
            "phase": "sft",
            "step": 20,
            "loss": 0.43977,
            "grad_norm": 0.2519,
            "tokens": 4576,
            "sec": 27.33
          }
        ],
        "lora.builder-toolcalls-256": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.23977,
            "grad_norm": 0.5488,
            "tokens": 6607,
            "sec": 68.16
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.17607,
            "grad_norm": 0.4368,
            "tokens": 6598,
            "sec": 70.65
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.10631,
            "grad_norm": 0.3812,
            "tokens": 6342,
            "sec": 66.56
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 0.97155,
            "grad_norm": 0.3753,
            "tokens": 6610,
            "sec": 67.52
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.83272,
            "grad_norm": 0.4306,
            "tokens": 7300,
            "sec": 74.96
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.76634,
            "grad_norm": 0.4938,
            "tokens": 6954,
            "sec": 71.6
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.81523,
            "grad_norm": 0.4741,
            "tokens": 5217,
            "sec": 61.97
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.7602,
            "grad_norm": 0.3281,
            "tokens": 5825,
            "sec": 66.31
          },
          {
            "phase": "sft",
            "step": 9,
            "loss": 0.6477,
            "grad_norm": 0.2749,
            "tokens": 7649,
            "sec": 74.63
          },
          {
            "phase": "sft",
            "step": 10,
            "loss": 0.73033,
            "grad_norm": 0.3007,
            "tokens": 6077,
            "sec": 68.58
          },
          {
            "phase": "sft",
            "step": 11,
            "loss": 0.68864,
            "grad_norm": 0.2937,
            "tokens": 6077,
            "sec": 62.61
          },
          {
            "phase": "sft",
            "step": 12,
            "loss": 0.6611,
            "grad_norm": 0.1815,
            "tokens": 6717,
            "sec": 70.67
          },
          {
            "phase": "sft",
            "step": 13,
            "loss": 0.70125,
            "grad_norm": 0.2392,
            "tokens": 6112,
            "sec": 68.68
          },
          {
            "phase": "sft",
            "step": 14,
            "loss": 0.74631,
            "grad_norm": 0.29,
            "tokens": 5314,
            "sec": 58.4
          },
          {
            "phase": "sft",
            "step": 15,
            "loss": 0.65757,
            "grad_norm": 0.2093,
            "tokens": 6878,
            "sec": 71.89
          },
          {
            "phase": "sft",
            "step": 16,
            "loss": 0.65799,
            "grad_norm": 0.1788,
            "tokens": 6629,
            "sec": 73.08
          },
          {
            "phase": "sft",
            "step": 17,
            "loss": 0.62136,
            "grad_norm": 0.155,
            "tokens": 6960,
            "sec": 71.58
          },
          {
            "phase": "sft",
            "step": 18,
            "loss": 0.56964,
            "grad_norm": 0.1535,
            "tokens": 8163,
            "sec": 79.87
          },
          {
            "phase": "sft",
            "step": 19,
            "loss": 0.7374,
            "grad_norm": 0.1348,
            "tokens": 5061,
            "sec": 59.84
          },
          {
            "phase": "sft",
            "step": 20,
            "loss": 0.6889,
            "grad_norm": 0.1809,
            "tokens": 5848,
            "sec": 66.41
          },
          {
            "phase": "sft",
            "step": 21,
            "loss": 0.72442,
            "grad_norm": 0.2132,
            "tokens": 5088,
            "sec": 57.08
          },
          {
            "phase": "sft",
            "step": 22,
            "loss": 0.621,
            "grad_norm": 0.1876,
            "tokens": 7239,
            "sec": 74.5
          }
        ],
        "lora.task-decomposer-64": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.25579,
            "grad_norm": 0.7814,
            "tokens": 2012,
            "sec": 14.36
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.0879,
            "grad_norm": 0.5377,
            "tokens": 2013,
            "sec": 13.47
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 0.92377,
            "grad_norm": 0.5394,
            "tokens": 2035,
            "sec": 14.89
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 0.79574,
            "grad_norm": 0.7674,
            "tokens": 2007,
            "sec": 16.6
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.65459,
            "grad_norm": 0.8241,
            "tokens": 1974,
            "sec": 13.56
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.53752,
            "grad_norm": 0.6663,
            "tokens": 2027,
            "sec": 12.83
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.4781,
            "grad_norm": 0.7194,
            "tokens": 2009,
            "sec": 16.39
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.43129,
            "grad_norm": 0.6526,
            "tokens": 2057,
            "sec": 16.34
          }
        ],
        "lora.shim-retriever-64": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.46724,
            "grad_norm": 0.699,
            "tokens": 2310,
            "sec": 13.43
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.24885,
            "grad_norm": 0.4887,
            "tokens": 2254,
            "sec": 13.76
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.17349,
            "grad_norm": 0.4995,
            "tokens": 2309,
            "sec": 13.96
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 1.02686,
            "grad_norm": 0.5153,
            "tokens": 2305,
            "sec": 13.96
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.92132,
            "grad_norm": 0.5558,
            "tokens": 2297,
            "sec": 13.83
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.85217,
            "grad_norm": 0.583,
            "tokens": 2270,
            "sec": 13.53
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.79219,
            "grad_norm": 0.514,
            "tokens": 2306,
            "sec": 13.78
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.76865,
            "grad_norm": 0.505,
            "tokens": 2305,
            "sec": 13.94
          }
        ],
        "lora.builder-toolcalls-64": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.05554,
            "grad_norm": 0.464,
            "tokens": 4122,
            "sec": 40.48
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.18841,
            "grad_norm": 0.431,
            "tokens": 3163,
            "sec": 31.43
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.14027,
            "grad_norm": 0.3912,
            "tokens": 2613,
            "sec": 30.77
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 0.95696,
            "grad_norm": 0.3714,
            "tokens": 3328,
            "sec": 36.84
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.93722,
            "grad_norm": 0.4462,
            "tokens": 3162,
            "sec": 34.72
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.83228,
            "grad_norm": 0.4812,
            "tokens": 2750,
            "sec": 29.48
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.74431,
            "grad_norm": 0.5003,
            "tokens": 3674,
            "sec": 36.44
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.74602,
            "grad_norm": 0.4693,
            "tokens": 3640,
            "sec": 39.39
          }
        ],
        "lora.verifier-dpo": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.38837,
            "grad_norm": 0.6888,
            "tokens": 4576,
            "sec": 31.33
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.1864,
            "grad_norm": 0.5324,
            "tokens": 5842,
            "sec": 31.71
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.11601,
            "grad_norm": 0.5102,
            "tokens": 5769,
            "sec": 30.41
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 1.03376,
            "grad_norm": 0.4531,
            "tokens": 5238,
            "sec": 28.32
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.95107,
            "grad_norm": 0.5096,
            "tokens": 5101,
            "sec": 30.87
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.79447,
            "grad_norm": 0.6072,
            "tokens": 5484,
            "sec": 32.97
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.74258,
            "grad_norm": 0.715,
            "tokens": 5250,
            "sec": 31.7
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.57482,
            "grad_norm": 0.5852,
            "tokens": 6220,
            "sec": 35.42
          },
          {
            "phase": "sft",
            "step": 9,
            "loss": 0.58235,
            "grad_norm": 0.6061,
            "tokens": 4767,
            "sec": 27.38
          },
          {
            "phase": "sft",
            "step": 10,
            "loss": 0.57668,
            "grad_norm": 0.3791,
            "tokens": 4469,
            "sec": 30.42
          },
          {
            "phase": "sft",
            "step": 11,
            "loss": 0.53585,
            "grad_norm": 0.44,
            "tokens": 4812,
            "sec": 27.97
          },
          {
            "phase": "sft",
            "step": 12,
            "loss": 0.50513,
            "grad_norm": 0.2292,
            "tokens": 5445,
            "sec": 28.96
          },
          {
            "phase": "sft",
            "step": 13,
            "loss": 0.50641,
            "grad_norm": 0.4144,
            "tokens": 5124,
            "sec": 31.47
          },
          {
            "phase": "sft",
            "step": 14,
            "loss": 0.4656,
            "grad_norm": 0.1935,
            "tokens": 5851,
            "sec": 32.86
          },
          {
            "phase": "sft",
            "step": 15,
            "loss": 0.47974,
            "grad_norm": 0.2203,
            "tokens": 5193,
            "sec": 28.1
          },
          {
            "phase": "sft",
            "step": 16,
            "loss": 0.4859,
            "grad_norm": 0.1873,
            "tokens": 5350,
            "sec": 31.53
          },
          {
            "phase": "sft",
            "step": 17,
            "loss": 0.50176,
            "grad_norm": 0.2198,
            "tokens": 4919,
            "sec": 27.66
          },
          {
            "phase": "sft",
            "step": 18,
            "loss": 0.44664,
            "grad_norm": 0.1716,
            "tokens": 5849,
            "sec": 33.22
          },
          {
            "phase": "sft",
            "step": 19,
            "loss": 0.50617,
            "grad_norm": 0.2255,
            "tokens": 4633,
            "sec": 26.31
          },
          {
            "phase": "sft",
            "step": 20,
            "loss": 0.49241,
            "grad_norm": 0.1745,
            "tokens": 4955,
            "sec": 31.23
          },
          {
            "phase": "sft",
            "step": 21,
            "loss": 0.49095,
            "grad_norm": 0.1189,
            "tokens": 4718,
            "sec": 29.75
          },
          {
            "phase": "sft",
            "step": 22,
            "loss": 0.48508,
            "grad_norm": 0.1334,
            "tokens": 4898,
            "sec": 29.03
          },
          {
            "phase": "sft",
            "step": 23,
            "loss": 0.48429,
            "grad_norm": 0.1935,
            "tokens": 4802,
            "sec": 30.32
          },
          {
            "phase": "sft",
            "step": 24,
            "loss": 0.43534,
            "grad_norm": 0.1628,
            "tokens": 5662,
            "sec": 32.68
          },
          {
            "phase": "dpo",
            "step": 1,
            "loss": 0.07757,
            "margin": 21.8278,
            "pref_acc": 1.0,
            "grad_norm": 0.0425,
            "tokens": 11448,
            "sec": 31.38
          },
          {
            "phase": "dpo",
            "step": 2,
            "loss": 0.07207,
            "margin": 23.9953,
            "pref_acc": 1.0,
            "grad_norm": 0.0316,
            "tokens": 11624,
            "sec": 31.79
          },
          {
            "phase": "dpo",
            "step": 3,
            "loss": 0.06542,
            "margin": 25.8489,
            "pref_acc": 1.0,
            "grad_norm": 0.0317,
            "tokens": 12854,
            "sec": 36.67
          },
          {
            "phase": "dpo",
            "step": 4,
            "loss": 0.06803,
            "margin": 25.9619,
            "pref_acc": 1.0,
            "grad_norm": 0.0457,
            "tokens": 11106,
            "sec": 30.38
          },
          {
            "phase": "dpo",
            "step": 5,
            "loss": 0.07594,
            "margin": 22.1175,
            "pref_acc": 1.0,
            "grad_norm": 0.0291,
            "tokens": 9558,
            "sec": 24.18
          },
          {
            "phase": "dpo",
            "step": 6,
            "loss": 0.06342,
            "margin": 23.2016,
            "pref_acc": 1.0,
            "grad_norm": 0.034,
            "tokens": 10576,
            "sec": 28.21
          },
          {
            "phase": "dpo",
            "step": 7,
            "loss": 0.06326,
            "margin": 21.4167,
            "pref_acc": 1.0,
            "grad_norm": 0.0298,
            "tokens": 11986,
            "sec": 33.57
          },
          {
            "phase": "dpo",
            "step": 8,
            "loss": 0.06761,
            "margin": 22.0851,
            "pref_acc": 1.0,
            "grad_norm": 0.0409,
            "tokens": 11871,
            "sec": 32.8
          },
          {
            "phase": "dpo",
            "step": 9,
            "loss": 0.06494,
            "margin": 25.5773,
            "pref_acc": 1.0,
            "grad_norm": 0.0318,
            "tokens": 11479,
            "sec": 31.61
          },
          {
            "phase": "dpo",
            "step": 10,
            "loss": 0.07274,
            "margin": 20.8222,
            "pref_acc": 1.0,
            "grad_norm": 0.0207,
            "tokens": 9557,
            "sec": 24.57
          },
          {
            "phase": "dpo",
            "step": 11,
            "loss": 0.06626,
            "margin": 23.488,
            "pref_acc": 1.0,
            "grad_norm": 0.0219,
            "tokens": 10703,
            "sec": 28.55
          },
          {
            "phase": "dpo",
            "step": 12,
            "loss": 0.07567,
            "margin": 20.3354,
            "pref_acc": 1.0,
            "grad_norm": 0.0244,
            "tokens": 10492,
            "sec": 27.85
          },
          {
            "phase": "dpo",
            "step": 13,
            "loss": 0.06816,
            "margin": 24.516,
            "pref_acc": 1.0,
            "grad_norm": 0.0229,
            "tokens": 10534,
            "sec": 27.96
          },
          {
            "phase": "dpo",
            "step": 14,
            "loss": 0.06898,
            "margin": 22.4854,
            "pref_acc": 1.0,
            "grad_norm": 0.0241,
            "tokens": 12110,
            "sec": 33.45
          },
          {
            "phase": "dpo",
            "step": 15,
            "loss": 0.06898,
            "margin": 19.0129,
            "pref_acc": 1.0,
            "grad_norm": 0.0209,
            "tokens": 10745,
            "sec": 28.13
          },
          {
            "phase": "dpo",
            "step": 16,
            "loss": 0.06842,
            "margin": 23.0025,
            "pref_acc": 1.0,
            "grad_norm": 0.0323,
            "tokens": 11890,
            "sec": 32.65
          },
          {
            "phase": "dpo",
            "step": 17,
            "loss": 0.07462,
            "margin": 21.6456,
            "pref_acc": 1.0,
            "grad_norm": 0.0245,
            "tokens": 9644,
            "sec": 24.35
          },
          {
            "phase": "dpo",
            "step": 18,
            "loss": 0.06587,
            "margin": 21.1822,
            "pref_acc": 1.0,
            "grad_norm": 0.0194,
            "tokens": 10566,
            "sec": 27.36
          },
          {
            "phase": "dpo",
            "step": 19,
            "loss": 0.07118,
            "margin": 22.1801,
            "pref_acc": 1.0,
            "grad_norm": 0.0325,
            "tokens": 13457,
            "sec": 38.51
          },
          {
            "phase": "dpo",
            "step": 20,
            "loss": 0.07579,
            "margin": 18.1518,
            "pref_acc": 1.0,
            "grad_norm": 0.0294,
            "tokens": 11768,
            "sec": 32.51
          },
          {
            "phase": "dpo",
            "step": 21,
            "loss": 0.06651,
            "margin": 21.3409,
            "pref_acc": 1.0,
            "grad_norm": 0.0208,
            "tokens": 11850,
            "sec": 32.84
          },
          {
            "phase": "dpo",
            "step": 22,
            "loss": 0.07208,
            "margin": 20.07,
            "pref_acc": 1.0,
            "grad_norm": 0.0239,
            "tokens": 11884,
            "sec": 32.6
          },
          {
            "phase": "dpo",
            "step": 23,
            "loss": 0.06242,
            "margin": 24.1042,
            "pref_acc": 1.0,
            "grad_norm": 0.0191,
            "tokens": 11936,
            "sec": 33.18
          },
          {
            "phase": "dpo",
            "step": 24,
            "loss": 0.06832,
            "margin": 20.9069,
            "pref_acc": 1.0,
            "grad_norm": 0.0185,
            "tokens": 9521,
            "sec": 24.25
          },
          {
            "phase": "dpo",
            "step": 25,
            "loss": 0.07289,
            "margin": 21.9539,
            "pref_acc": 1.0,
            "grad_norm": 0.02,
            "tokens": 9216,
            "sec": 23.38
          },
          {
            "phase": "dpo",
            "step": 26,
            "loss": 0.07164,
            "margin": 24.5443,
            "pref_acc": 1.0,
            "grad_norm": 0.0192,
            "tokens": 10253,
            "sec": 26.87
          },
          {
            "phase": "dpo",
            "step": 27,
            "loss": 0.06893,
            "margin": 23.0543,
            "pref_acc": 1.0,
            "grad_norm": 0.0222,
            "tokens": 12066,
            "sec": 33.37
          },
          {
            "phase": "dpo",
            "step": 28,
            "loss": 0.06535,
            "margin": 24.5428,
            "pref_acc": 1.0,
            "grad_norm": 0.0236,
            "tokens": 12680,
            "sec": 36.05
          }
        ],
        "lora.verifier-dpo-256": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.31308,
            "grad_norm": 0.6146,
            "tokens": 5284,
            "sec": 30.87
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.24197,
            "grad_norm": 0.5526,
            "tokens": 5084,
            "sec": 30.37
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.14595,
            "grad_norm": 0.4859,
            "tokens": 5000,
            "sec": 28.93
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 0.95326,
            "grad_norm": 0.4539,
            "tokens": 5231,
            "sec": 28.35
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.8445,
            "grad_norm": 0.5584,
            "tokens": 5181,
            "sec": 30.28
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.71505,
            "grad_norm": 0.6044,
            "tokens": 5820,
            "sec": 30.61
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.62801,
            "grad_norm": 0.6182,
            "tokens": 5483,
            "sec": 32.97
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.64364,
            "grad_norm": 0.702,
            "tokens": 4472,
            "sec": 29.65
          },
          {
            "phase": "sft",
            "step": 9,
            "loss": 0.53283,
            "grad_norm": 0.6819,
            "tokens": 4839,
            "sec": 26.86
          },
          {
            "phase": "sft",
            "step": 10,
            "loss": 0.54267,
            "grad_norm": 0.381,
            "tokens": 5594,
            "sec": 32.99
          },
          {
            "phase": "sft",
            "step": 11,
            "loss": 0.52766,
            "grad_norm": 0.3352,
            "tokens": 5411,
            "sec": 31.02
          },
          {
            "phase": "sft",
            "step": 12,
            "loss": 0.53424,
            "grad_norm": 0.2683,
            "tokens": 4505,
            "sec": 29.16
          },
          {
            "phase": "sft",
            "step": 13,
            "loss": 0.48789,
            "grad_norm": 0.2476,
            "tokens": 5482,
            "sec": 32.85
          },
          {
            "phase": "sft",
            "step": 14,
            "loss": 0.49928,
            "grad_norm": 0.1902,
            "tokens": 5103,
            "sec": 29.59
          },
          {
            "phase": "dpo",
            "step": 1,
            "loss": 0.07629,
            "margin": 15.0385,
            "pref_acc": 1.0,
            "grad_norm": 0.0481,
            "tokens": 11910,
            "sec": 33.3
          },
          {
            "phase": "dpo",
            "step": 2,
            "loss": 0.07129,
            "margin": 15.5162,
            "pref_acc": 1.0,
            "grad_norm": 0.0548,
            "tokens": 12656,
            "sec": 36.3
          },
          {
            "phase": "dpo",
            "step": 3,
            "loss": 0.07668,
            "margin": 16.5176,
            "pref_acc": 1.0,
            "grad_norm": 0.0293,
            "tokens": 10456,
            "sec": 27.98
          },
          {
            "phase": "dpo",
            "step": 4,
            "loss": 0.07591,
            "margin": 16.4218,
            "pref_acc": 1.0,
            "grad_norm": 0.0496,
            "tokens": 10265,
            "sec": 27.46
          },
          {
            "phase": "dpo",
            "step": 5,
            "loss": 0.07826,
            "margin": 16.1018,
            "pref_acc": 1.0,
            "grad_norm": 0.0429,
            "tokens": 10017,
            "sec": 26.55
          },
          {
            "phase": "dpo",
            "step": 6,
            "loss": 0.07317,
            "margin": 17.7902,
            "pref_acc": 1.0,
            "grad_norm": 0.0322,
            "tokens": 10748,
            "sec": 29.11
          },
          {
            "phase": "dpo",
            "step": 7,
            "loss": 0.07122,
            "margin": 14.8159,
            "pref_acc": 1.0,
            "grad_norm": 0.0523,
            "tokens": 9986,
            "sec": 26.25
          },
          {
            "phase": "dpo",
            "step": 8,
            "loss": 0.06973,
            "margin": 18.4075,
            "pref_acc": 1.0,
            "grad_norm": 0.0475,
            "tokens": 12495,
            "sec": 35.71
          },
          {
            "phase": "dpo",
            "step": 9,
            "loss": 0.06482,
            "margin": 17.1869,
            "pref_acc": 1.0,
            "grad_norm": 0.0351,
            "tokens": 10417,
            "sec": 27.42
          },
          {
            "phase": "dpo",
            "step": 10,
            "loss": 0.07575,
            "margin": 17.9484,
            "pref_acc": 1.0,
            "grad_norm": 0.0388,
            "tokens": 12241,
            "sec": 34.64
          },
          {
            "phase": "dpo",
            "step": 11,
            "loss": 0.07195,
            "margin": 17.441,
            "pref_acc": 1.0,
            "grad_norm": 0.0244,
            "tokens": 9935,
            "sec": 25.58
          },
          {
            "phase": "dpo",
            "step": 12,
            "loss": 0.06539,
            "margin": 18.2145,
            "pref_acc": 1.0,
            "grad_norm": 0.0245,
            "tokens": 11165,
            "sec": 30.1
          },
          {
            "phase": "dpo",
            "step": 13,
            "loss": 0.07108,
            "margin": 18.3672,
            "pref_acc": 1.0,
            "grad_norm": 0.031,
            "tokens": 11313,
            "sec": 30.8
          },
          {
            "phase": "dpo",
            "step": 14,
            "loss": 0.07103,
            "margin": 17.1734,
            "pref_acc": 1.0,
            "grad_norm": 0.0252,
            "tokens": 10010,
            "sec": 25.88
          },
          {
            "phase": "dpo",
            "step": 15,
            "loss": 0.07324,
            "margin": 17.9662,
            "pref_acc": 1.0,
            "grad_norm": 0.0274,
            "tokens": 10354,
            "sec": 27.76
          },
          {
            "phase": "dpo",
            "step": 16,
            "loss": 0.07016,
            "margin": 20.1166,
            "pref_acc": 1.0,
            "grad_norm": 0.0334,
            "tokens": 12446,
            "sec": 35.52
          }
        ],
        "lora.verifier-dpo-64": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.34558,
            "grad_norm": 0.6258,
            "tokens": 2612,
            "sec": 15.7
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.1708,
            "grad_norm": 0.5087,
            "tokens": 2411,
            "sec": 12.76
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.05333,
            "grad_norm": 0.4709,
            "tokens": 2369,
            "sec": 14.82
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 0.88947,
            "grad_norm": 0.4667,
            "tokens": 2747,
            "sec": 16.57
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.78029,
            "grad_norm": 0.5195,
            "tokens": 2739,
            "sec": 14.94
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.70168,
            "grad_norm": 0.5864,
            "tokens": 2716,
            "sec": 16.3
          },
          {
            "phase": "dpo",
            "step": 1,
            "loss": 0.10887,
            "margin": 6.1073,
            "pref_acc": 1.0,
            "grad_norm": 0.2062,
            "tokens": 5941,
            "sec": 16.85
          },
          {
            "phase": "dpo",
            "step": 2,
            "loss": 0.08025,
            "margin": 11.7074,
            "pref_acc": 1.0,
            "grad_norm": 0.0907,
            "tokens": 5940,
            "sec": 16.78
          },
          {
            "phase": "dpo",
            "step": 3,
            "loss": 0.08487,
            "margin": 12.0201,
            "pref_acc": 1.0,
            "grad_norm": 0.1125,
            "tokens": 5968,
            "sec": 16.79
          },
          {
            "phase": "dpo",
            "step": 4,
            "loss": 0.09553,
            "margin": 9.9296,
            "pref_acc": 1.0,
            "grad_norm": 0.1668,
            "tokens": 4691,
            "sec": 12.33
          },
          {
            "phase": "dpo",
            "step": 5,
            "loss": 0.09813,
            "margin": 14.368,
            "pref_acc": 1.0,
            "grad_norm": 0.1448,
            "tokens": 4331,
            "sec": 10.88
          },
          {
            "phase": "dpo",
            "step": 6,
            "loss": 0.09249,
            "margin": 11.5965,
            "pref_acc": 1.0,
            "grad_norm": 0.1271,
            "tokens": 5024,
            "sec": 13.19
          },
          {
            "phase": "dpo",
            "step": 7,
            "loss": 0.08155,
            "margin": 15.1085,
            "pref_acc": 1.0,
            "grad_norm": 0.098,
            "tokens": 6807,
            "sec": 20.08
          },
          {
            "phase": "dpo",
            "step": 8,
            "loss": 0.08316,
            "margin": 13.6435,
            "pref_acc": 1.0,
            "grad_norm": 0.0906,
            "tokens": 4855,
            "sec": 12.79
          }
        ],
        "lora.monolithic-mixed": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.30531,
            "grad_norm": 0.4681,
            "tokens": 4971,
            "sec": 33.18
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.28106,
            "grad_norm": 0.467,
            "tokens": 5286,
            "sec": 39.53
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.18914,
            "grad_norm": 0.4215,
            "tokens": 4793,
            "sec": 30.94
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 1.07113,
            "grad_norm": 0.3328,
            "tokens": 5707,
            "sec": 42.96
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 1.10641,
            "grad_norm": 0.3918,
            "tokens": 4559,
            "sec": 30.06
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.95491,
            "grad_norm": 0.4904,
            "tokens": 4682,
            "sec": 34.46
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.94354,
            "grad_norm": 0.4947,
            "tokens": 4813,
            "sec": 35.99
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.80766,
            "grad_norm": 0.5609,
            "tokens": 4950,
            "sec": 37.46
          },
          {
            "phase": "sft",
            "step": 9,
            "loss": 0.8708,
            "grad_norm": 0.5357,
            "tokens": 5277,
            "sec": 39.25
          },
          {
            "phase": "sft",
            "step": 10,
            "loss": 0.70369,
            "grad_norm": 0.4629,
            "tokens": 5997,
            "sec": 45.34
          },
          {
            "phase": "sft",
            "step": 11,
            "loss": 0.74137,
            "grad_norm": 0.494,
            "tokens": 4770,
            "sec": 34.81
          },
          {
            "phase": "sft",
            "step": 12,
            "loss": 0.61066,
            "grad_norm": 0.7382,
            "tokens": 4570,
            "sec": 32.63
          },
          {
            "phase": "sft",
            "step": 13,
            "loss": 0.57298,
            "grad_norm": 0.4033,
            "tokens": 4829,
            "sec": 36.05
          },
          {
            "phase": "sft",
            "step": 14,
            "loss": 0.55547,
            "grad_norm": 0.5132,
            "tokens": 4562,
            "sec": 32.01
          },
          {
            "phase": "sft",
            "step": 15,
            "loss": 0.59261,
            "grad_norm": 0.4761,
            "tokens": 4566,
            "sec": 33.44
          },
          {
            "phase": "sft",
            "step": 16,
            "loss": 0.63745,
            "grad_norm": 0.2791,
            "tokens": 5524,
            "sec": 44.75
          },
          {
            "phase": "sft",
            "step": 17,
            "loss": 0.41126,
            "grad_norm": 0.4674,
            "tokens": 4194,
            "sec": 24.79
          },
          {
            "phase": "sft",
            "step": 18,
            "loss": 0.62937,
            "grad_norm": 0.3744,
            "tokens": 5505,
            "sec": 50.7
          },
          {
            "phase": "sft",
            "step": 19,
            "loss": 0.57061,
            "grad_norm": 0.2334,
            "tokens": 5376,
            "sec": 43.78
          },
          {
            "phase": "sft",
            "step": 20,
            "loss": 0.54964,
            "grad_norm": 0.4971,
            "tokens": 5850,
            "sec": 39.23
          },
          {
            "phase": "sft",
            "step": 21,
            "loss": 0.51162,
            "grad_norm": 0.254,
            "tokens": 4811,
            "sec": 40.17
          },
          {
            "phase": "sft",
            "step": 22,
            "loss": 0.57424,
            "grad_norm": 0.2864,
            "tokens": 4842,
            "sec": 34.38
          },
          {
            "phase": "sft",
            "step": 23,
            "loss": 0.49221,
            "grad_norm": 0.1801,
            "tokens": 5261,
            "sec": 37.12
          },
          {
            "phase": "sft",
            "step": 24,
            "loss": 0.5,
            "grad_norm": 0.1945,
            "tokens": 4564,
            "sec": 37.34
          },
          {
            "phase": "sft",
            "step": 25,
            "loss": 0.52829,
            "grad_norm": 0.2382,
            "tokens": 5004,
            "sec": 31.49
          },
          {
            "phase": "sft",
            "step": 26,
            "loss": 0.57821,
            "grad_norm": 0.2061,
            "tokens": 4587,
            "sec": 32.38
          },
          {
            "phase": "sft",
            "step": 27,
            "loss": 0.50549,
            "grad_norm": 0.2052,
            "tokens": 5426,
            "sec": 40.97
          },
          {
            "phase": "sft",
            "step": 28,
            "loss": 0.55622,
            "grad_norm": 0.1717,
            "tokens": 5131,
            "sec": 38.48
          },
          {
            "phase": "sft",
            "step": 29,
            "loss": 0.55713,
            "grad_norm": 0.1606,
            "tokens": 4960,
            "sec": 40.47
          },
          {
            "phase": "sft",
            "step": 30,
            "loss": 0.57229,
            "grad_norm": 0.1728,
            "tokens": 5919,
            "sec": 48.73
          },
          {
            "phase": "sft",
            "step": 31,
            "loss": 0.50686,
            "grad_norm": 0.2244,
            "tokens": 4675,
            "sec": 29.98
          },
          {
            "phase": "sft",
            "step": 32,
            "loss": 0.43736,
            "grad_norm": 0.1348,
            "tokens": 6136,
            "sec": 46.17
          },
          {
            "phase": "sft",
            "step": 33,
            "loss": 0.41255,
            "grad_norm": 0.1807,
            "tokens": 6020,
            "sec": 41.49
          },
          {
            "phase": "sft",
            "step": 34,
            "loss": 0.41198,
            "grad_norm": 0.1257,
            "tokens": 4337,
            "sec": 26.5
          },
          {
            "phase": "sft",
            "step": 35,
            "loss": 0.47043,
            "grad_norm": 0.165,
            "tokens": 6114,
            "sec": 47.55
          },
          {
            "phase": "sft",
            "step": 36,
            "loss": 0.48003,
            "grad_norm": 0.1689,
            "tokens": 5004,
            "sec": 34.71
          },
          {
            "phase": "sft",
            "step": 37,
            "loss": 0.4979,
            "grad_norm": 0.1461,
            "tokens": 4675,
            "sec": 33.23
          },
          {
            "phase": "sft",
            "step": 38,
            "loss": 0.52897,
            "grad_norm": 0.1661,
            "tokens": 5095,
            "sec": 39.65
          },
          {
            "phase": "sft",
            "step": 39,
            "loss": 0.49298,
            "grad_norm": 0.1403,
            "tokens": 4910,
            "sec": 35.52
          },
          {
            "phase": "sft",
            "step": 40,
            "loss": 0.43041,
            "grad_norm": 0.09,
            "tokens": 4515,
            "sec": 32.8
          },
          {
            "phase": "sft",
            "step": 41,
            "loss": 0.50644,
            "grad_norm": 0.1405,
            "tokens": 6552,
            "sec": 53.43
          },
          {
            "phase": "sft",
            "step": 42,
            "loss": 0.46412,
            "grad_norm": 0.1421,
            "tokens": 4548,
            "sec": 34.89
          },
          {
            "phase": "sft",
            "step": 43,
            "loss": 0.52919,
            "grad_norm": 0.1644,
            "tokens": 5487,
            "sec": 44.46
          },
          {
            "phase": "sft",
            "step": 44,
            "loss": 0.56932,
            "grad_norm": 0.1949,
            "tokens": 4939,
            "sec": 38.76
          },
          {
            "phase": "sft",
            "step": 45,
            "loss": 0.52451,
            "grad_norm": 0.1859,
            "tokens": 5316,
            "sec": 39.45
          },
          {
            "phase": "sft",
            "step": 46,
            "loss": 0.45294,
            "grad_norm": 0.1684,
            "tokens": 4924,
            "sec": 31.91
          },
          {
            "phase": "sft",
            "step": 47,
            "loss": 0.40412,
            "grad_norm": 0.1515,
            "tokens": 4467,
            "sec": 29.67
          },
          {
            "phase": "sft",
            "step": 48,
            "loss": 0.52796,
            "grad_norm": 0.1596,
            "tokens": 5167,
            "sec": 34.64
          },
          {
            "phase": "sft",
            "step": 49,
            "loss": 0.45857,
            "grad_norm": 0.1217,
            "tokens": 4690,
            "sec": 31.61
          },
          {
            "phase": "sft",
            "step": 50,
            "loss": 0.48102,
            "grad_norm": 0.1425,
            "tokens": 4884,
            "sec": 36.98
          },
          {
            "phase": "sft",
            "step": 51,
            "loss": 0.45782,
            "grad_norm": 0.2547,
            "tokens": 4919,
            "sec": 32.88
          },
          {
            "phase": "sft",
            "step": 52,
            "loss": 0.48343,
            "grad_norm": 0.1824,
            "tokens": 4564,
            "sec": 35.52
          },
          {
            "phase": "sft",
            "step": 53,
            "loss": 0.47353,
            "grad_norm": 0.2176,
            "tokens": 4653,
            "sec": 32.89
          },
          {
            "phase": "sft",
            "step": 54,
            "loss": 0.48463,
            "grad_norm": 0.1627,
            "tokens": 5940,
            "sec": 45.65
          },
          {
            "phase": "sft",
            "step": 55,
            "loss": 0.47211,
            "grad_norm": 0.1297,
            "tokens": 5830,
            "sec": 43.61
          },
          {
            "phase": "sft",
            "step": 56,
            "loss": 0.42555,
            "grad_norm": 0.1237,
            "tokens": 4474,
            "sec": 29.96
          }
        ],
        "lora.monolithic-mixed-256": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.38583,
            "grad_norm": 0.5145,
            "tokens": 5504,
            "sec": 46.92
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.15964,
            "grad_norm": 0.434,
            "tokens": 5687,
            "sec": 40.13
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.14323,
            "grad_norm": 0.3525,
            "tokens": 5402,
            "sec": 37.61
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 1.09732,
            "grad_norm": 0.3795,
            "tokens": 5387,
            "sec": 41.75
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 1.04403,
            "grad_norm": 0.5127,
            "tokens": 4465,
            "sec": 23.53
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.85653,
            "grad_norm": 0.5946,
            "tokens": 5456,
            "sec": 44.57
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.93701,
            "grad_norm": 0.4383,
            "tokens": 4947,
            "sec": 37.47
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.72395,
            "grad_norm": 0.7616,
            "tokens": 4467,
            "sec": 30.77
          },
          {
            "phase": "sft",
            "step": 9,
            "loss": 0.72148,
            "grad_norm": 0.5224,
            "tokens": 4761,
            "sec": 25.33
          },
          {
            "phase": "sft",
            "step": 10,
            "loss": 0.7985,
            "grad_norm": 0.5588,
            "tokens": 4964,
            "sec": 29.03
          },
          {
            "phase": "sft",
            "step": 11,
            "loss": 0.55481,
            "grad_norm": 0.5231,
            "tokens": 5017,
            "sec": 32.25
          },
          {
            "phase": "sft",
            "step": 12,
            "loss": 0.72177,
            "grad_norm": 0.4123,
            "tokens": 5029,
            "sec": 36.78
          },
          {
            "phase": "sft",
            "step": 13,
            "loss": 0.61806,
            "grad_norm": 0.3845,
            "tokens": 5783,
            "sec": 45.85
          },
          {
            "phase": "sft",
            "step": 14,
            "loss": 0.45872,
            "grad_norm": 0.3163,
            "tokens": 4714,
            "sec": 29.23
          },
          {
            "phase": "sft",
            "step": 15,
            "loss": 0.47651,
            "grad_norm": 0.382,
            "tokens": 5295,
            "sec": 37.36
          },
          {
            "phase": "sft",
            "step": 16,
            "loss": 0.54243,
            "grad_norm": 0.3303,
            "tokens": 4541,
            "sec": 26.51
          },
          {
            "phase": "sft",
            "step": 17,
            "loss": 0.47539,
            "grad_norm": 0.173,
            "tokens": 4476,
            "sec": 33.82
          },
          {
            "phase": "sft",
            "step": 18,
            "loss": 0.54566,
            "grad_norm": 0.3338,
            "tokens": 4939,
            "sec": 29.63
          },
          {
            "phase": "sft",
            "step": 19,
            "loss": 0.47723,
            "grad_norm": 0.2158,
            "tokens": 4490,
            "sec": 31.19
          },
          {
            "phase": "sft",
            "step": 20,
            "loss": 0.56727,
            "grad_norm": 0.2817,
            "tokens": 5709,
            "sec": 41.43
          },
          {
            "phase": "sft",
            "step": 21,
            "loss": 0.56848,
            "grad_norm": 0.2466,
            "tokens": 4994,
            "sec": 37.83
          },
          {
            "phase": "sft",
            "step": 22,
            "loss": 0.53689,
            "grad_norm": 0.2704,
            "tokens": 4994,
            "sec": 32.76
          },
          {
            "phase": "sft",
            "step": 23,
            "loss": 0.55321,
            "grad_norm": 0.2543,
            "tokens": 5927,
            "sec": 41.62
          },
          {
            "phase": "sft",
            "step": 24,
            "loss": 0.54069,
            "grad_norm": 0.3031,
            "tokens": 5271,
            "sec": 36.78
          }
        ],
        "lora.monolithic-mixed-64": [
          {
            "phase": "sft",
            "step": 1,
            "loss": 1.46099,
            "grad_norm": 0.5415,
            "tokens": 2333,
            "sec": 14.28
          },
          {
            "phase": "sft",
            "step": 2,
            "loss": 1.29558,
            "grad_norm": 0.45,
            "tokens": 2188,
            "sec": 14.37
          },
          {
            "phase": "sft",
            "step": 3,
            "loss": 1.17551,
            "grad_norm": 0.437,
            "tokens": 2243,
            "sec": 12.19
          },
          {
            "phase": "sft",
            "step": 4,
            "loss": 0.87664,
            "grad_norm": 0.3422,
            "tokens": 3864,
            "sec": 29.35
          },
          {
            "phase": "sft",
            "step": 5,
            "loss": 0.95992,
            "grad_norm": 0.3838,
            "tokens": 2663,
            "sec": 18.21
          },
          {
            "phase": "sft",
            "step": 6,
            "loss": 0.84688,
            "grad_norm": 0.7069,
            "tokens": 2188,
            "sec": 13.84
          },
          {
            "phase": "sft",
            "step": 7,
            "loss": 0.96583,
            "grad_norm": 0.5245,
            "tokens": 2514,
            "sec": 18.88
          },
          {
            "phase": "sft",
            "step": 8,
            "loss": 0.67453,
            "grad_norm": 0.6357,
            "tokens": 2903,
            "sec": 20.44
          },
          {
            "phase": "sft",
            "step": 9,
            "loss": 0.8223,
            "grad_norm": 0.5301,
            "tokens": 2711,
            "sec": 20.33
          },
          {
            "phase": "sft",
            "step": 10,
            "loss": 1.0088,
            "grad_norm": 0.6442,
            "tokens": 2279,
            "sec": 19.25
          }
        ]
      },
      "seconds": 8703.08
    },
    "parallel_eval_and_composition": {
      "status": "failed",
      "seconds": 1123.71,
      "error": "RuntimeError: Parallel 2xT4 workers failed in phase=eval: rc0=1, rc1=1",
      "traceback": "Traceback (most recent call last):\n  File \"/kaggle/src/script.py\", line 331, in <module>\n    run_dual_workers(\"eval\")\n    ~~~~~~~~~~~~~~~~^^^^^^^^\n  File \"/kaggle/src/script.py\", line 303, in run_dual_workers\n    raise RuntimeError(f\"Parallel 2xT4 workers failed in phase={phase}: rc0={rc0}, rc1={rc1}\")\nRuntimeError: Parallel 2xT4 workers failed in phase=eval: rc0=1, rc1=1\n"
    }
  },
  "errors": [
    {
      "stage": "parallel_eval_and_composition",
      "error": "RuntimeError: Parallel 2xT4 workers failed in phase=eval: rc0=1, rc1=1"
    }
  ],
  "modular_common_sha256": "f1294836ac134bd49554515f5dfe141ddc7026e32e1be569f0090074ff338e3e",
  "worker_gpu_unit_sha256": "540730b81fcd424745a8c47c6b4791ac7958e87d89943c805f7384574720eb8c",
  "elapsed_s": 9845.19,
  "swarm_source_manifest": {
    "contamination_checks": {
      "gold_holdout_self_score": 1.0,
      "nested_subsets_verified": true,
      "prompt_fingerprint_overlap": 0,
      "workflow_id_overlap": 0
    },
    "files": {
      "dpo_holdout.jsonl": {
        "bytes": 907751,
        "rows": 50,
        "sha256": "da79e1f8a01aa939b7cb7441001bf96d515f06fb737e419321ca0fbbfe700a29"
      },
      "dpo_verifier_1600.jsonl": {
        "bytes": 1572890,
        "rows": 100,
        "sha256": "f0128314d18c5e5bebce58f90347d075543883a0b8411802ff8d066e445f298e"
      },
      "dpo_verifier_256.jsonl": {
        "bytes": 996205,
        "rows": 64,
        "sha256": "097824c13d1e15f003ce88648a4876212c7fcddbad8d6d56793fd7de47310dfc"
      },
      "dpo_verifier_64.jsonl": {
        "bytes": 245913,
        "rows": 16,
        "sha256": "f9ccd3c2c3cf0898968ee96a68f01b935d8e7695d36e7f69aca733f30ef20dd4"
      },
      "holdout_eval.jsonl": {
        "bytes": 1650486,
        "rows": 200,
        "sha256": "0b67c1d0b7ddf3deeb2a8e5679da245607f2eef5a79883ff26db2b83d960bec3"
      },
      "sanity_40.jsonl": {
        "bytes": 16626,
        "rows": 40,
        "sha256": "1271140ebde3ef699234f152e979adde0b3729f605c5ab3d432ff90a34ddd7eb"
      },
      "sft_builder_1600.jsonl": {
        "bytes": 4970727,
        "rows": 500,
        "sha256": "d526872956e8ea78998b8109e515392d21b0957d99dd4f99cedb67a5f8e03af4"
      },
      "sft_builder_256.jsonl": {
        "bytes": 644031,
        "rows": 64,
        "sha256": "5b6b4ebacb2747664a86ceeed2aed3612e086e2454d8584f0e806e8f13c1ea64"
      },
      "sft_builder_64.jsonl": {
        "bytes": 163482,
        "rows": 16,
        "sha256": "73bd18d7f7ba57ada1bd42a37634222605c89e19c046c993f4f6d28bc2c8ed61"
      },
      "sft_decomposer_1600.jsonl": {
        "bytes": 2948424,
        "rows": 500,
        "sha256": "c5ab93f919b03d90ec2f76289977da7bb91d19bab557fd757d2b9de6f3f78fd3"
      },
      "sft_decomposer_256.jsonl": {
        "bytes": 378231,
        "rows": 64,
        "sha256": "6ff9e1d8f5e2f528e13cc120fb6920419e6627a5622b48fb24cf1bcdab0746a6"
      },
      "sft_decomposer_64.jsonl": {
        "bytes": 94966,
        "rows": 16,
        "sha256": "5978334261c6fe24b0dc2778a7f6c9ee7ad536a513d9933e6444be07ad414f92"
      },
      "sft_monolithic_1600.jsonl": {
        "bytes": 11417633,
        "rows": 1600,
        "sha256": "6f31b4c08a697f8364641c2c0465544b6c70b1c31d983b164c26df7d5a902a25"
      },
      "sft_monolithic_256.jsonl": {
        "bytes": 1813507,
        "rows": 256,
        "sha256": "d8086d999849065b3b3c73ad4d559432ccc4a541bb11d9027b8076949c81c65e"
      },
      "sft_monolithic_64.jsonl": {
        "bytes": 454869,
        "rows": 64,
        "sha256": "5c9c02172602bbf8eb5d8d631aa711fb9ea50ad0dae39585c8df166477ed2c12"
      },
      "sft_retriever_1600.jsonl": {
        "bytes": 2820986,
        "rows": 500,
        "sha256": "41e98525a1540c69786ccba23b2e97cfede2931cc67e9c038892f0d293c29a88"
      },
      "sft_retriever_256.jsonl": {
        "bytes": 361578,
        "rows": 64,
        "sha256": "986faff47a4fc7a08f51fdc46bb389a029003b5acd85b2b31d1af035b93a6612"
      },
      "sft_retriever_64.jsonl": {
        "bytes": 90590,
        "rows": 16,
        "sha256": "d60f84a90c5a1328d7c487423363174a48df0ce7022b0ce3314e437c7263dd5e"
      },
      "sft_verifier_1600.jsonl": {
        "bytes": 677496,
        "rows": 100,
        "sha256": "afbee6754df5325b04db1cb7e9424e7ca9157516dafd811d4956d35ac80bdad4"
      },
      "sft_verifier_256.jsonl": {
        "bytes": 429667,
        "rows": 64,
        "sha256": "b68bec7941a57c8832dbb46c3322082a3cf8a50a42c4313631c8cbc014b5b5f8"
      },
      "sft_verifier_64.jsonl": {
        "bytes": 105831,
        "rows": 16,
        "sha256": "22a3bcfcecef93665375316cd2dd19dd4eb5efe6dceedcef54dcf6f2fc1422e1"
      }
    },
    "scale_counts": {
      "dpo_holdout": 50,
      "holdout_eval": 200,
      "sanity_40": 40,
      "scale_1600": 1600,
      "scale_256": 256,
      "scale_64": 64
    },
    "schema": "ta-amps.modular-swarm-dataset.v1",
    "source_datasets": {
      "swarm_dpo_verifier_pairs": {
        "bytes": 1639220,
        "filename": "swarm_dpo_verifier_pairs.jsonl",
        "path": "<workspace>/notes/work-2026-10-30/opencode-swarm/out/datasets/swarm_dpo_verifier_pairs.jsonl",
        "row_count": 100,
        "sha256": "508f5c7bd9a56fc4fd5c316fde94e8a12284c0066797f03d8abd5cb2dd4c0dc8"
      },
      "swarm_holdout_eval": {
        "bytes": 2743962,
        "filename": "swarm_holdout_eval.jsonl",
        "path": "<workspace>/notes/work-2026-10-30/opencode-swarm/out/datasets/swarm_holdout_eval.jsonl",
        "row_count": 200,
        "sha256": "5f7cdcc8b5e935b8e3ec95fd5310bab41e8bf494718bcf1a084bfcd432dc2a1f"
      },
      "swarm_sft_builder_toolcalls": {
        "bytes": 12193474,
        "filename": "swarm_sft_builder_toolcalls.jsonl",
        "path": "<workspace>/notes/work-2026-10-30/opencode-swarm/out/datasets/swarm_sft_builder_toolcalls.jsonl",
        "row_count": 800,
        "sha256": "f5f3d5dde8c5629bd1d67adaf9e0e0ccdcf0a08dc1cabb1d211d2ebb90496381"
      },
      "swarm_sft_decomposer": {
        "bytes": 6840504,
        "filename": "swarm_sft_decomposer.jsonl",
        "path": "<workspace>/notes/work-2026-10-30/opencode-swarm/out/datasets/swarm_sft_decomposer.jsonl",
        "row_count": 800,
        "sha256": "39c79f772ae40e9bc41d8fd8bc98b5eae72cfac87db7056f1e958419ae5c8da7"
      },
      "swarm_sft_retriever_shim": {
        "bytes": 6177880,
        "filename": "swarm_sft_retriever_shim.jsonl",
        "path": "<workspace>/notes/work-2026-10-30/opencode-swarm/out/datasets/swarm_sft_retriever_shim.jsonl",
        "row_count": 800,
        "sha256": "c0f5ea6df320d1388129df615a8cb7fd0e6f22ddf8ada1fb65edba994ef393d1"
      }
    },
    "source_ready_manifest_sha256": "464b0aef993d3a3e3798d292987a3938944d6819a1fd7b0f0d69a879c00f7ba9",
    "token_stats": {
      "configured_max_len": 3328,
      "configured_max_new_tokens": 1536,
      "max_observed_holdout_target_tokens": 1401,
      "max_observed_seq_tokens": 2991
    }
  }
}