Modal Research Exchange

you are

dimuon-lite vs AdamW, LoRA SFT on Qwen3.5-2B, no_robots held-out NLL

Succeeded not supported Devin Qwen/Qwen3.5-2B SFT 2.0 GPU-h budget started 6h ago 1h 09m
Redo
Pick where the agent works.
View session in Devin ↗

On fork spindle-fork-run_739abc9a8b, 100-step rank-32 LoRA SFT of Qwen3.5-2B on no_robots gave AdamW-minus-Dimuon test token-mean NLL +0.0006 nats (95% paired-t CI [-0.0006, +0.0019], 3 seeds) at selected LRs AdamW 0.0002 / Dimuon 0.003. Verdict inconclusive because both selected LRs sit at the upper grid edge (spec rule); the CI itself lies entirely below the 0.02-nat margin.

Full summary

On fork spindle-fork-run_739abc9a8b, 100-step rank-32 LoRA SFT of Qwen3.5-2B on no_robots gave AdamW-minus-Dimuon test token-mean NLL +0.0006 nats (95% paired-t CI [-0.0006, +0.0019], 3 seeds) at selected LRs AdamW 0.0002 / Dimuon 0.003. Verdict inconclusive because both selected LRs sit at the upper grid edge (spec rule); the CI itself lies entirely below the 0.02-nat margin. Loss comparison not usable for a verdict: arms were scored on different tokens or examples: sel_adamw_lr5e-05_s0 94328.0 tokens / 500 examples, sel_adamw_lr0.0001_s0 94328.0 tokens / 500 examples, sel_adamw_lr0.0002_s0 94328.0 tokens / 500 examples, sel_dimuon_lr0.0003_s0 94328.0 tokens / 500 examples, sel_dimuon_lr0.001_s0 94328.0 tokens / 500 examples, sel_dimuon_lr0.003_s0 94328.0 tokens / 500 examples, baseline_adamw_s0 97346.0 tokens / 500 examples, treatment_dimuon_s0 97346.0 tokens / 500 examples, baseline_adamw_s1 97346.0 tokens / 500 examples, treatment_dimuon_s1 97346.0 tokens / 500 examples, baseline_adamw_s2 97346.0 tokens / 500 examples, treatment_dimuon_s2 97346.0 tokens / 500 examples.

Not supported The agent found the evidence insufficient to show the claimed effect. Confidence is limited by: treatment activation unverified; initialization and optimizer verification unverified; decision evidence uncertain; held-out loss comparison not usable: arms were scored on different tokens or examples: sel_adamw_lr5e-05_s0 94328.0 tokens / 500 examples, sel_adamw_lr0.0001_s0 94328.0 tokens / 500 examples, sel_adamw_lr0.0002_s0 94328.0 tokens / 500 examples, sel_dimuon_lr0.0003_s0 94328.0 tokens / 500 examples, sel_dimuon_lr0.001_s0 94328.0 tokens / 500 examples, sel_dimuon_lr0.003_s0 94328.0 tokens / 500 examples, baseline_adamw_s0 97346.0 tokens / 500 examples, treatment_dimuon_s0 97346.0 tokens / 500 examples, baseline_adamw_s1 97346.0 tokens / 500 examples, treatment_dimuon_s1 97346.0 tokens / 500 examples, baseline_adamw_s2 97346.0 tokens / 500 examples, treatment_dimuon_s2 97346.0 tokens / 500 examples; feasibility evidence incomplete. Reclassified from inconclusive under the direction-plus-confidence rule.

Result test_token_mean_nll

sel mean — · 0 armsbaseline mean 2.032 · 3 armstreatment mean 2.031 · 3 arms
Lower is better · Axis from 2.03 to 2.033, not zero
armtest_token_mean_nll
sel_adamw_lr5e-05_s0—
sel_adamw_lr0.0001_s0—
sel_adamw_lr0.0002_s0—
sel_dimuon_lr0.0003_s0—
sel_dimuon_lr0.001_s0—
sel_dimuon_lr0.003_s0—
baseline_adamw_s02.033
baseline_adamw_s12.032
baseline_adamw_s22.031
treatment_dimuon_s02.032
treatment_dimuon_s12.03
treatment_dimuon_s22.031
3 more metrics under Evidence, All metrics.
Arms Devin reported complete: sel_adamw_lr5e-05_s0, sel_adamw_lr0.0001_s0, sel_adamw_lr0.0002_s0, sel_dimuon_lr0.0003_s0, sel_dimuon_lr0.001_s0, sel_dimuon_lr0.003_s0, baseline_adamw_s0, treatment_dimuon_s0, baseline_adamw_s1, treatment_dimuon_s1, baseline_adamw_s2, treatment_dimuon_s2
Changes from the spec 1
whatspecran withwhyrecorded
EvaluatorSecondary IFEval strict accuracy on 541 prompts (descriptive only)IFEval dropped; primary 500-item no_robots test token-mean NLL unchangedSpec downsizing order step 1: measured 6-arm step times (~7-48 s) left insufficient GPU-hour/wall reserve to also run inference sampling for 6 adapters x 541 prompts. before the run ended

Original hypothesis tested: yes

Checks · activation unverified · evaluator comparable · feasibility unknown
Custom implementation correctness: passed
Reported baseline and reference parity checks meet accepted tolerances.
Validates executor-reported evidence; autonomous training calls are not blocked by this server.
Executor reported inconclusive; shown as not supported.
Parity errors and accepted tolerances
[
  {
    "check": "baseline_update",
    "measured": {
      "cosine_similarity": 0.9999999999984652,
      "max_abs_error": 2.9103830456733704e-11,
      "reference_max_abs": 0.00010000001202570274,
      "relative_l2_error": 1.1838959207204277e-07
    },
    "path": "spindle_dimuon_lite_optimizer",
    "status": "passed",
    "tolerance": {
      "atol": 1e-06,
      "min_cosine": 0.99999,
      "rtol": 0.001
    }
  },
  {
    "check": "reference_update",
    "measured": {
      "cosine_similarity": 0.9999999999996416,
      "max_abs_error": 0.0,
      "reference_max_abs": 0.00043169609853066504,
      "relative_l2_error": 0.0
    },
    "path": "spindle_dimuon_lite_optimizer",
    "status": "passed",
    "tolerance": {
      "atol": 1e-05,
      "min_cosine": 0.999,
      "rtol": 0.01
    }
  },
  {
    "check": "lr_scaling",
    "path": "spindle_dimuon_lite_optimizer",
    "relative_error": 7.10453955665713e-08,
    "status": "passed",
    "tolerance": {
      "learning_rates": [
        0.0001,
        0.001,
        0.01
      ],
      "rtol": 0.01
    }
  }
]
Treatment activation: unverified
Not reported: executed_optimizer_step_type, batch_hash_match_across_arms, pilot_train_nll_drop_dimuon_10steps.
executed_base_model
Qwen/Qwen3.5-2B needs one of Qwen/Qwen3.5-2B · passed
executed_optimizer_step_type
not reported needs one of DimuonParams, AdamParams · missing
dimuon_B_update_normalized_stable_rank_step1
0.7930079444363333 needs >= 0.6 and <= 1.05 · passed
batch_hash_match_across_arms
not reported needs >= 1 and <= 1 · missing
pilot_train_nll_drop_dimuon_10steps
not reported needs >= 0 · missing
Initialization / optimizer verification: unverified
baseline_adamw_s0: missing or duplicate arm evidence.
Research decision: uncertain
Adaptive selection requires disjoint search and confirmation IDs.
Inference unit: training_seed · 3 scheduled seed(s). Student-t confidence interval.
Coverage assumes independent, identically distributed normal seed effects. These assumptions are declared, not verified.
Evaluator comparability: comparable
no_robots_test_token_mean_nll_at_step_100: comparable · baseline, treatment
Evaluator identities and per-arm scores
{
  "comparisons": [
    {
      "arms": [
        "baseline",
        "treatment"
      ],
      "metric": "no_robots_test_token_mean_nll_at_step_100"
    }
  ],
  "evaluators": {
    "a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744": {
      "code_sha256": "52b3d966475a14ba5b3d854d7e22134648b12c59b47ca24801c3b7f66d34fb90",
      "decoding": {
        "max_tokens": 0,
        "stop": [],
        "temperature": null,
        "type": "teacher_forced_forward"
      },
      "items": {
        "ids": [
          "no_robots_test:d6c011ffb1ff8a9abe9bd24caf3f9817454a1f054d5d0e0360d19bf50cf6b20c",
          "no_robots_test:7682c850c4e5979cef0ad966b8feb119de2bd323bb40819767a161040b59eb7a",
          "no_robots_test:45971bbe382b81644487690d2018bc3aec8c807f1be52a9744223e5492255928",
          "no_robots_test:ccdce774f24ede2e799686276e8b72e8b08a4aebf6ba75ecc450fc73cfedd1a8",
          "no_robots_test:c1f40447167a99977d745672c0c19cb2739b6f5208647af47fac16c94f88826e",
          "no_robots_test:f7128731ae16e9ccfbb888620c5d75564fb8d12350e9b47c781beeb64ebd04c7",
          "no_robots_test:f865f7581ddc128be8b79fa82e7fa9102362b6a7685d82f9116436280073695b",
          "no_robots_test:2e26a31997285dc001e683aec269ec9b0c4e3400b97a7cbb6367a08e374dfedc",
          "no_robots_test:3fad3d579a7259e0bbff20c18d4c72049a7b9378078c85188ba9b166216b4775",
          "no_robots_test:cc614a388398a30b28e3b18b9382a1438d8b8455377d6a65f902a709a75168a1",
          "no_robots_test:e038c9bbc2ec4556f6ab47f9651fa89cb5d7f72891a5fba4415e13f18f7ca0b7",
          "no_robots_test:37746cac882d406894272569214f6ede6ab7b78de88c01e6bea144234a4013bf",
          "no_robots_test:6ac710f1196bc72404d3e08e8acca16f7f144752544aa4af9a19736053fbda4b",
          "no_robots_test:f52ce291ce39c76f22e3771a091d24bb55b3831106506a3835c2a2e16a86d1c1",
          "no_robots_test:5a5c6035044f914d24e5fa5677048b7461bb3c3a4a7cfa474fbcfa29588670d8",
          "no_robots_test:c1c9a958b19539efc3ce03adb85c0c7811393e90d35f33f4d96e999d79e3e8a9",
          "no_robots_test:66e33c21f54193775c1fda86f9be739152462cea267969b838ed953956f4b631",
          "no_robots_test:3c338b2227c9f2922a94c730fc653d50dec826ea0febb228867efb3709a3f31d",
          "no_robots_test:85b810a2c52be481e2f79b741fb8a02142c18d9db329189689789240bad537a6",
          "no_robots_test:ba7cd3cea48952cd4f218fb4ba23a7a0d9f6d3e2b524eb897a063d567521bcbc",
          "no_robots_test:645c6de54016df90ea64d9b72a1686de2c682467cc0988ed2b8379e4af3a3b69",
          "no_robots_test:ba474c32c7c4db657376ec72136594729848d88a0423d0457e9f6eea6680e9c1",
          "no_robots_test:ebd302ba966ef926516b751f9d42bd52ed4b21747f424f147c33de05d5cb46a5",
          "no_robots_test:d555a1b6eab48b9f199186e30b6b691eafd4b0df80a6558b64c4c5d60509848a",
          "no_robots_test:1329aaafcece6e6674ee78a546492be7047a72bd8eed93a15490b517d195f8aa",
          "no_robots_test:ca2aefe6159c88ab4335e1b2a19e04bb70d2d096c8b6487946607a4fb57b9207",
          "no_robots_test:f8385c2bedf5af812b3e13ed50abf373552e551992c637acf8c341fb2bd4ef30",
          "no_robots_test:687e88746b34ab7a856e2d8795eb696de02b6909f8e68dd0c5595cf754eb22b2",
          "no_robots_test:b096cd3cc576e1df1bfc3ea2e8c1b89817a67e1f4d4209100e7e0ac03323b45a",
          "no_robots_test:503c617fbdab4576be1c79b421947a7c5f1a2b365808c6b6f8e31287d1aeb674",
          "no_robots_test:46ffb831bbb5717977280909d133272c1cda68f7769a58f18e83331e906c5aa0",
          "no_robots_test:d155ad5a56b452703abf0c54969f8cfd0372dcbe0befcd4a0af5a0fbdcbfe23b",
          "no_robots_test:d36d2dcd016969972e6ea69b0ad14f9ff2b6e341d9ff7565318d6082b0523ba6",
          "no_robots_test:9d2c280bd301ce2066b71f70cdfe03494262cf4f369010aea6e00f23f853cbc7",
          "no_robots_test:37ac631bf0d66b95a69519e58da6a3c4f1118d6960bace298e83087805422076",
          "no_robots_test:91e0052f1664f2e28d66653914c81a87f27e0b24a46b9136e4748a8c24545289",
          "no_robots_test:6f921864bd8b8123377fe29446547b0cfccf9882bda00e1ed0a11f99c7290799",
          "no_robots_test:06f8cec4f3a7a51087180e3fba0d8a2c19c0866cff613bbc7d044033f82467e5",
          "no_robots_test:41d3a40c684db02d115771774e75f6812745b96bfc8b26c6198f3537fa5bd7e8",
          "no_robots_test:71b63a042ad1e85efc91ec2ac3a88629d29d13978696515b1bc0d29bea1fae36",
          "no_robots_test:40f8e6e855826d7d7671f4dbb5f7c12ae99541888fe78e7b4d669adbe00b1151",
          "no_robots_test:0869a2536bae18939b4f62b6c026f631cc44083e1903bde4de0b1e7e339702e5",
          "no_robots_test:ac80dd9713747a25db3164ad15d37c61409a02257bd88433e1c254eb927a4372",
          "no_robots_test:2fb3649c9d992e39a4a394aeb16b91720ec8ae19dd43895b3914a6511144ca1e",
          "no_robots_test:bb96ffd53f0444b90e6fad698788ab9ccd24d6f63aa674494be21315ee7a2dd3",
          "no_robots_test:2beadd667769f5875ab256f7f840e2c6d26c1b667ba4ef11d814b61153da6e13",
          "no_robots_test:a9a8696c28ade7a3f9e0b3d8d97abb862ed987239887e988a2dd21cee1915cb2",
          "no_robots_test:bab1283b2cfd37eb5a264da47f0663cea09d18088cd4c48886d0174e1eba536e",
          "no_robots_test:b3b45db4ac4b90ae5fddacef19c5deb1a91dbee65068d9ab0d36d3e1aa92334b",
          "no_robots_test:c2596826a823a13939db48d0ee04bfb0083fdf8133eff4468550ca63ebb76864",
          "no_robots_test:069a404880fd7eebecec2132e04406f2858b71a7588237de0c546d826aa2cce3",
          "no_robots_test:151659a113f8a967eea7c23e19e96b0da262f736a3560b9dff28efb68b553978",
          "no_robots_test:0f861d5aa34b0dcfc2ddd35da09fc581aff25b042a2795f36bda290e00071378",
          "no_robots_test:498c6846aff34679bd2acaf9a40672c60df6dc00e30ecd2be181b233b23faf1e",
          "no_robots_test:3a2e37c1fe2d7c63b55330af7098035b4dc8142da2ff249f35820cd06b458cea",
          "no_robots_test:c97be73986b86b7bb444ba1402ece81e49a0e962be40a66a0021c293d0e48134",
          "no_robots_test:371d8db9eaa9687270ad0fab91513225fa7ce1c54e5a0d845f126a7ae386e735",
          "no_robots_test:2d0ff0f26fb8e8effcd4918c0653fcc0eee53226f4d13b79eee2fc03df6286aa",
          "no_robots_test:ad3ade87b53d6f4adc940e6f4ba711e65b73e7d2fc4a2aa4e15c0b733b110b29",
          "no_robots_test:716e64d1f2292720df26399fee0aaf5e015009178041a6ec8fedc17e2d9e9df6",
          "no_robots_test:569e694f8ad2b83ae1e997fd4b19849b0859d23873a4147bb31e7873ed29e086",
          "no_robots_test:3956cffb3efd15358c82ae59c24fdcbd58112173f6ff3f8c41888e6c4ed6c895",
          "no_robots_test:11cb75d074a4a74b12c17ea021dfe17d72909661a28ca255e000d86573e52f4a",
          "no_robots_test:7b69321f3a4e585a40ceba48e7b63685452a123e2cb64486ae5c54ffd3be0d23",
          "no_robots_test:ede0754a2e1b91497d9e4db2320edbb495c071f190098537eee95929972e17d1",
          "no_robots_test:66ada4a1b1b49410c7f8a6a27934b65139499a9c3e5c65549375068a70a3c51f",
          "no_robots_test:02c4f02245b627721c8a03184b85e95b2d7a2a3e2757fcaa53a3f227785f0277",
          "no_robots_test:2891116ede1751ddb26aaa9de499dc1149851f957873abcf2903132c62addab8",
          "no_robots_test:dc009733b4090c99c626a0b657377e2c3db4dc065ca522659356d8be020a4bdd",
          "no_robots_test:252b2127915bf0a3c04b2aa0e9cda42302f94b5feded11ae4d272b4d6d585c30",
          "no_robots_test:757b00e4f2279890ebb97605a867e4309c29fce4ddfd2035ff568c7be0bb6b6d",
          "no_robots_test:2ce87bfc5c427f720cb5f28f4099db60307f1ed844c4c8e61f1f046e06265fbd",
          "no_robots_test:2526b13cafe55ba808ebe720cc2ebfce41f9e0a12b7512ffe6dbf7eb41a559c5",
          "no_robots_test:4d0fa72d19e14c4e11a471ab3f0127fbaeee061a5ee6cc5ecf87142920bd0c24",
          "no_robots_test:d04ddb39eff5469b4b4b6d090b51e6f46e47dc4daec06702964c1f737f7e8123",
          "no_robots_test:525e28a56ceec00670ad602d6553ffdf08501e8a0ca7ea10027a2136bf135d54",
          "no_robots_test:a1415ff2282982ef44abfbbecf0503e4d6f0ea6186824ae56e2d438fb3fca23b",
          "no_robots_test:9ab2002a593fbbebdc2d4f4678bd21f8d4cd02cd15d65589c403319c8b5f4747",
          "no_robots_test:45678c64b9b9861841bb742e8e05cc4c421d21c9bf4dcdf637a96e827c661830",
          "no_robots_test:12751be5580238e093aab282dc8b994353b4c0643fae38656978e34fcab15b3e",
          "no_robots_test:412c1c7294d8b1d07ab2e23cc6e748d4f9e3ab6628ae1df5ab42c56c7414531e",
          "no_robots_test:a8395735b43fc5000483fbf3bb2662975b3ebe5bd83fad730c12cdf6404a41c1",
          "no_robots_test:7be45ddf4361ed9d86fc499ee2d6aa4174d7c5aa6db5cd799eec4d789aa9c838",
          "no_robots_test:b4ac421b07dd3cf8535f88666150b33d008b709eee6a0281f8b3d01d77e61b42",
          "no_robots_test:4d4f7a00621e23c1ef1e1ca6970dda6157a4a7afb000de94fc94163a6406f48c",
          "no_robots_test:c4c48bb83330aaf49d90f0673248fb903b29f16adad3efc331c17dd200202483",
          "no_robots_test:8c2b9b8240c2ce74726a939bf4c485b9fc3e7868c2f0e48a6a8489659a92168e",
          "no_robots_test:8c034a519e1533a7d544faf79099055f5b04c1207f6fbe265e4463dda40e0824",
          "no_robots_test:2f9354b6c63a3e550fbab16210d0d38fad27dadba62d375b4f35722a0a46c887",
          "no_robots_test:1af4443ea535d2f85009c7705db3081bfa675eda1ffcb4de92ac70102fe23448",
          "no_robots_test:8e4228fe80ce2c4c988f5c0a8c60d9672e46566e4f6fe05315a2c5e1f09dc990",
          "no_robots_test:b3a1e4ed83a6227f5050917a7059aa210538961b47c678f11fa33b2535467cf4",
          "no_robots_test:6936a6d57488b9b79a55bd677f2c130f3c36ba2dc348747826d0f3a5cb5b7027",
          "no_robots_test:a1d57c8b8a4d920e196c48e429468a951ee9125c447890b4d891ea3755f1dbd8",
          "no_robots_test:21bf1e34609a84aa6f41b73a534567fba26b13d5025844ef1ed9851ff3c35eda",
          "no_robots_test:c5bec6d10044644190ba466977bdab9375264adaae2d0c377ffa48410063fc80",
          "no_robots_test:798b01c27b9d7d5719cf411a678312f9676dc3845c4b6d3e99744b5d80c4dd6f",
          "no_robots_test:6ee94a135df17071b4b0c1f9e7f5ecddaaddd34b568a29642650c851a2def94c",
          "no_robots_test:e0eec4940165bbe26d1f4fcf7801fbc2578618f78dd649ab5a1f97258f7ff742",
          "no_robots_test:f39be8cff1abe33986b52a7e7aec5a1b8adf9552746697e972812e7babaf3b22",
          "no_robots_test:b72a4b2add1b1711109547a75c5318b94db761dc3cd2c08e73e11cfe14469e96",
          "no_robots_test:8e0ebb53a5dd1feafa657b34f39e15bfa8913e56f21d61542f7c1932da440426",
          "no_robots_test:1ecc678e8184e4ef5150ad3a51b05a3d29fc3b2672e74ff0fb98cc7249ce5883",
          "no_robots_test:703d0b37f6b9cc517692f8bcdec6988d82d20e9023b95c901225d206fcd7e5af",
          "no_robots_test:eb4fee5c685b36bffcd84b2c68db01fe4842302c24190e144f391b7016bb2330",
          "no_robots_test:7954bc81cf750c36c91d432a844a5f2ba689213263761bdebf866d28b3662f61",
          "no_robots_test:4f25dfe951a9ee72613ab2e8021ffb4e09871143628991c5fb560e0a3f8a3c67",
          "no_robots_test:b8c5dc22944151efd9e6642639973e1ca401e1a380fc0ff4d57a3b24a3173278",
          "no_robots_test:979520d6745fc9319044c901dbee403a6dcf48d253e710fb6db78dada2bf712a",
          "no_robots_test:47c6604c9b3b4e350ad5f546aa6f4748b59ef6275b4cc4ab99425518b2c7fd3f",
          "no_robots_test:d29b4a6069a7d535d79c44dcaacbe6d6f30289086ce2ace4897202dce919811a",
          "no_robots_test:f60bb67e4cb1d3dc680b634ea4bf50b3148231fb6e8cfea09aab9c0860eaf63e",
          "no_robots_test:4cb56274ed302cc7e7bb9f57bb3d7fe43df6265c6e226cd9fb2f6fd8287eec3e",
          "no_robots_test:86ad87691e5725d33d686118811d13876d192cf7525fb83c9e2434ee6d71be56",
          "no_robots_test:08d888907bbbb7d371248e13dab35000d0d971f1bd16112e732546226f0802cd",
          "no_robots_test:757ed7e67d03ef845a4dcb8b90666504e6bd4e14b2a3c5d954372e14ee5d9aec",
          "no_robots_test:290e88a34d533c83aa725c61b56a3f01f0b55db15ba6b332c4432f14634a9fe0",
          "no_robots_test:3d701bcf2811e91950d7766cdbd2660e2ee02be6825f8e5dbd569752cb7327b2",
          "no_robots_test:bc90d0b2dd1afcddd8de7b2e7ff4d4c770018190ad63c0d1de27cd6c0c046979",
          "no_robots_test:ef52784af72fdcb475ca17d2f444011bf89a4f73cba3627ef7a4a369a3dd39f4",
          "no_robots_test:2e7da2610042433c41b02cad24401c5c0f83bee93ed07d6f5807f7883d252c45",
          "no_robots_test:7f77538b92b924595ccd388f371d085841f926b3f436c964e0d94383ed97b780",
          "no_robots_test:076473b02f7f76619fb48bedc3a6295a3be8333d87f67983f0f05dd6f95fa7a0",
          "no_robots_test:7e8135ad15dc03710f78522d402a5b8d724706a1ba0445714a448e59a77c2ec9",
          "no_robots_test:3391c058e714734b2a349e66d6708733ff35e49cb4d22a521ae0b692e21a76e6",
          "no_robots_test:4bdf2305eb042d59d61126bd3018e2a216c7e46b98ba4d8be57f5ad86b82734c",
          "no_robots_test:cc1646d3f0fd7b1a8ba246dae952929e522158f26e0524b6f40126b68b34ec8b",
          "no_robots_test:0bfc23e86d05103d10342d234b31fe3613b93e7620e6c272b2687e08bfb9491e",
          "no_robots_test:dad92f898cd3f957f6a61c8dbbd70cfb6a5aee938edfc0b54af4f8ebdef4bb3c",
          "no_robots_test:51217435894e5a1bf8d0e87cfd74e24cbfff862a1f7a39d08596bfbe2c499d32",
          "no_robots_test:f5cc15a138584ced005ec845f5a40212cd1e4c389aaadb5db442b61637320d19",
          "no_robots_test:aef43863df74ba98f55bbf32bc780175e667b8af13b9308d6e54a35e1efb09bc",
          "no_robots_test:d9b5aaf8fb1c656a71df74fc73f1ac3b5e5d63810f5556295f1292cfe00bb87d",
          "no_robots_test:02ae13c831902dfa4f7aea6e89bb478d9a64e62c9cd1562334a614e35b62a483",
          "no_robots_test:4ec9bf682c8a288c825f56766b2743be9d768c12368980d81715ec0a9a293dbd",
          "no_robots_test:6c7f04a463f203983dcfc1b50cd819500d6d0e087c2e746c76714689567e19e7",
          "no_robots_test:1fa6007d33362ffd33bb07cb575d3286ae410da730da8f4d6e523d84be1a2332",
          "no_robots_test:f7dfc75f57c1c9022920cf1c26cb513280cb76c7d04d604ebdbd2ee95d04218c",
          "no_robots_test:95ab39c44458ecc1e254c4d2194c59d86dd455c7dbdec58797b2fcac0f7df839",
          "no_robots_test:d1c191631ff3e1bc89519fccf379faf48b2950d3960818b9d86fa7cbb36efb8b",
          "no_robots_test:2880e6d3dc46901576c9ff3bc55a3a1a950a0e2bf8a32606c51282995b7e9364",
          "no_robots_test:96a2891220d97cc3c1baca4ddf13121f17adbb908b72caf6e946e982d86fefe1",
          "no_robots_test:068f53051dcc214ec91622949ac1d49db7d3c6eb0e885172fb93513e45d883e0",
          "no_robots_test:5a6f31d9ba234bfecceee2b6db822077c30aa23d2dd40602fc94663bda4e1cd9",
          "no_robots_test:2830c95d42887be796a6c5e0cc1de1d29619cc4f33ecf1f2e0fd7b7319b041e2",
          "no_robots_test:4d06ff6439f54b7345b83b8bed2e689493104c9338efc5e21243ade63cabd1f7",
          "no_robots_test:326a5c2c6bbd8459c6e1edf67b56da08d0bbe39d1ee02dcf7dcb13518b9d44d6",
          "no_robots_test:a0cb5111b8e2d4fe6560ae67761862ab2e5608410668e0ea382bd68defff5d10",
          "no_robots_test:f2fb01116f39477efc5e0e8ab47809920621d6c74e9a4a60ec9aa1c7c8201410",
          "no_robots_test:2e24e4d095b5bb0dbcd738f61cb9a783c121ac44188937c846c800c4eca2fe60",
          "no_robots_test:967305b1921daa495ef581fdc52997046809ecc01ed6ca818f4c52c085c3dd2c",
          "no_robots_test:fd80e71474ab525762acf1d979f85ecb5a6fe83d34087d7baac7f108e31b4415",
          "no_robots_test:c421a5055d01c12bf1ca46211b65dd34e67d5111d502cce455d1e3e10dcd1c48",
          "no_robots_test:1789df91903365b9016e4015a62c0771379d0f6b1c12cde49c00deafd16e568b",
          "no_robots_test:d097f9337d9beae903165700e60c8107fdd5f4dbdcdeb718ff5ab38bde15460b",
          "no_robots_test:3b2803a605e122e0ab8e6626269ba570c29249d45ba58d7a54b63a7e0f97e5bc",
          "no_robots_test:89e44a65181076ab721592e13a69c971d9f067eb21db9a11468ed41430dadd2d",
          "no_robots_test:95c8a688253b51b33e956f0f62e143ba558a3494da559d8d35ea0ad544885ead",
          "no_robots_test:9d5e4c39e16efdc6470e674ed1523697946b836509ad4965c47726cc8f6cb6df",
          "no_robots_test:4d3216e0e9c5525fd3ff1b390fe9ddfe994eda332607d0fdb4986b19877dc6c0",
          "no_robots_test:eaea0c1080796440180027b3ddca45c68eca17d3b2070f65b50ff67b6393352f",
          "no_robots_test:213eb243af6ec6084438ae97c83acc1224eb51d005da0de0735b6eebbfa523c3",
          "no_robots_test:45242f3a7707cd505500f1026ea4840d01c833047ca5b677ce90ae7e029dcbdc",
          "no_robots_test:f119ab42649b334ed54181aa9d9e198678502b7f309a7f1b8021200ad43c7131",
          "no_robots_test:ec0ab0abc0cd6b428980887f7fdb6fdc36eae28ed284b484af3007a36aede555",
          "no_robots_test:da0c8826b1c9df28399772fbbbc00def6e24266ea4769395b086fb5212f858b4",
          "no_robots_test:f17e86e400862b58a8f76248b6a0516ef3258bdbcc14e2bf04973c276cb80adf",
          "no_robots_test:e8e0ae19872ede1c9e4f75e62a31cbd2008befe91b60b1efceec9d82a68068ee",
          "no_robots_test:a8bf210a9bbec3800386a7c5c31d74e89eb4331209ff9707c6ab6af269ffcf11",
          "no_robots_test:69d2b75a5774cf0cc7f61356d15f46ce5f7e847a6ae2fd7d80b844729ee66533",
          "no_robots_test:f390cc2e8411ec903c73f3f4f63d319ff38697806fc2e2cc3a919ee9f4de7df9",
          "no_robots_test:91c266537d1b7b14576858b3cffc0e0c64e067f25fc427b1ccd9f57deb3ab510",
          "no_robots_test:9bb61f01d987accca140d9b7a08cf663da8c4647707509d0f849e1a6d4618845",
          "no_robots_test:1b0d0852a3458d9e67d6aaee4a56ad43a02a5e06e0b7ce12d3f488768bffb453",
          "no_robots_test:c35fbe35a264b1d4bb9266ce6d88abb1d932379dd81c1adc52db0f2e41f6777b",
          "no_robots_test:601da7a0629ec217772580a3120ac9fc06a6df190ed10780e7da422cf7f9262a",
          "no_robots_test:cc3cdef5cb453bcfea86564234a8d2bbd1c5ee3806098531fcaf2014f25705b1",
          "no_robots_test:c1b58ea5e251db651f6ed3fc547f082837341e585d518ffe13b38f167216e57f",
          "no_robots_test:85b235f4feda83914fdb0cbb3829ceb72a67a0cad5db3385cd00342dd5c5adc7",
          "no_robots_test:f52d6383e3acbd487bdb7628e5e1f40615221a18987e99010a5a1ccd9f1d7cb0",
          "no_robots_test:e6fd684789090b25ab723bbdd2fffc97cb47f20ddab417d0fc0571f848734469",
          "no_robots_test:c4a9dd28310b012602050b7aebce6fc24ac6970da91c0606343724aa054f582a",
          "no_robots_test:abd71530ee6e630d3ec7d965c754e672013f3e08785c888ae03a54545ca06aea",
          "no_robots_test:6e2bfc6786ee24a14685bb3e2bff4e30c235573cce6a30e6a4f34648872945a3",
          "no_robots_test:0bd65e73a8f7bcc45be8767197aa1d949f05a16c544f4979662418a20974fb95",
          "no_robots_test:c5844637317399e7d5b233c18d7ac5cdbf35eb0c8828c5c9502a28c4702a7201",
          "no_robots_test:51113c20a33637c45ffa7790adf858b82411041fd590a33eb7237a8dcc20f759",
          "no_robots_test:ef8990846d162db707da43ce86ff6679aef342edf48271f8c56a6eaea6b757b2",
          "no_robots_test:9205274fb686fc486f4bcdebb1db6ff5ba082910ec126fe4e7a45b7c4e326502",
          "no_robots_test:12a51577fc8c8f57379974dff63caa82cfee85878af091db7e9ed8bef0c2dff7",
          "no_robots_test:1e2f3bba465c89ee6540b3fcbe41b69530214abc3a22c91f3abd3b0268dce6f7",
          "no_robots_test:59fd818054494e1765970af339112c6adf8fd23735c5d25d9737f96c3d0d915e",
          "no_robots_test:3fd1549f3fbcf76e94f71ab625d154f0de522d1a7d8bd50f010c440921de6a93",
          "no_robots_test:44ad24bcbe033d894271593fe623ca666021144e28ba110d46cd84435dba393d",
          "no_robots_test:96e2f8ebd4953035715526d9a61b0d821619b54e49dca59e0a27ac38660c1f30",
          "no_robots_test:e899cf5f0a16dfb8a99c24079edd1daf67e29471990a5dee209266b674594163",
          "no_robots_test:da0b52f4093106f56b7404adbb8159a61bcc8cb7941f53c70323e5d874e8875e",
          "no_robots_test:a2a9a52bff5d204d803b507d62782260485e0f99e39b462c864a9ced696daadb",
          "no_robots_test:b4626c5a09a0e78cd163ede5e329c94dcf7af010b4cb657b5e90e35fccd548cd",
          "no_robots_test:a711c95c8b8132371034deda9d96ebf86b4e3c7a6ad82fe08569725c74274079",
          "no_robots_test:8380a993af2c8f279ac14e503846912dfbcde296077027b9f33743ae3c8e77e2",
          "no_robots_test:ae7bbb65b9624d622a74937935bd701d475c1a178fe315de73b92e47ee9fd5f1",
          "no_robots_test:fafd92407ddf89c0194177a60f58a38a1407d1c0dfa055df0367a7853ed134b9",
          "no_robots_test:92dcd250215c49ee91f3bedffd13233cebc6883c582c00f9e5daa52ac0dd92b7",
          "no_robots_test:04f4e8dcb7a85d3d2942a5b8a88dba98e688b47fb767d15e5d6a6580cf920dd1",
          "no_robots_test:98256cd92ae4fa5dce574e0389c873fca0c1accc50ddb955b6a0159bca065620",
          "no_robots_test:140c8928abacd14de28e471f9b72ba39b1fd28d49f2901fe084745f4d2278ee5",
          "no_robots_test:2109bf5c5db973ca8ff4b138a9796e29e20be366383d585af45a84e05038ea39",
          "no_robots_test:5f66fef6384c7a95e3778c9c5f46cadd6318ce1888d9e2044c9e38a59192dcca",
          "no_robots_test:50402f52bfb645ff79958783d68aa9790de3615cb436dfe3ed8d46164a80bfd8",
          "no_robots_test:cdeb6dcc295cafe0ed298573af3444ac8fe409ca6032f0f5a1c52cae717e3187",
          "no_robots_test:1b2930d8d0408970b01f3d4522f10d8c1fe03a47ab6366f1d2370293ab74b326",
          "no_robots_test:1bf1accc704426d12687e1ba37ca0bece147d542dbef4e9ed0d5c3abc9fadc03",
          "no_robots_test:0b9b9d2cfbc490f3f45f1bf113df46f68e78ffe0689fe761740adb1e53f8b20c",
          "no_robots_test:76532c9fd99ea816721df2cef8b59592f80eb658ee02f3392aefc00f34da245a",
          "no_robots_test:5b77f923577ba1dd1c4a709eaf66597c54d52e7810be27543838e2f1314206f6",
          "no_robots_test:9f2696fa31f6f52d177f0acde38b92505c990b9a2cb440af41bababe680ca217",
          "no_robots_test:21d5e6f61e5d2258f80580d708ec4285fc824e07c92582b63b35988f019091e2",
          "no_robots_test:e0d5085e39c268c69847de78014edf194ea0fc5c2868c14fe5059390b7cb9940",
          "no_robots_test:bdfed4ee300d6bff796ae268f6f83bfaae10e71aa8ede3dde72554e7eaf79b55",
          "no_robots_test:7d5dc53024c3085f99c8102e249b7da704ba08b65f33f99bed3327ca3726f72f",
          "no_robots_test:63d767b55aa04b962cab270eee9e64b65aaf34af3aa9781167c228dd0e82f67c",
          "no_robots_test:9329174e2ac800db587384bd62c32bf99604ad657176f524f83263251d20bca5",
          "no_robots_test:7c4214e958ae2abd2be5d8b652d5915b494776dc94af3873d2d6c3344e851f62",
          "no_robots_test:0dc3429898c88946ff7e6b1d33b8ba1ca2fe61216f700a9d88df16e14a6b7d8d",
          "no_robots_test:5991d65bc74447559f555e0a808f886fb6645f3529656ddd63b8d087f2df7f27",
          "no_robots_test:9beb41a989ac57f4fdc979d80b3b65eb99d25b97c9f664eb42bcaa16ccd74267",
          "no_robots_test:aadb45cc8d2e48853f3e7d8f759532646d013559d46b7fc72c60042d3f154064",
          "no_robots_test:4f5195b9648dfb0a57f64f53e6afc60e78c7b65a7620943ffd98947c9170d628",
          "no_robots_test:8135293cb7bb33562aac0e08f4942f44ad7d7858ddbbcdda57ca83f234588846",
          "no_robots_test:d1e66a5ced13c36d30989f5776239534594765d1bf8cf40144eed2e913e24d52",
          "no_robots_test:a2cc15697d3bad72aa51063c3d8d42753ee59d965111cf28aecc97dded3d8376",
          "no_robots_test:3410cd90f220004a96c7f8bfa1396589594d36100f6b48c632238fd97c25f051",
          "no_robots_test:0512bb67304464c586c502af3dfc689a18a64da1493ac248b30782ceb219e103",
          "no_robots_test:4b535a929ec12ec2fa17ee650e3339a558e495254049d037bd55d881614b7993",
          "no_robots_test:dc1c6bf4a49f7ad4a1b65a21092307059639a4d54c70943c81f70ef5595acd00",
          "no_robots_test:f02e1582f19aceb3804c56a778dbe12f55fe8a8904e555c8b8f5854b2d2e2490",
          "no_robots_test:a45ba472e28e8ea090c83ab4d9d909c24591f06bfe9d7fa29b08eefc40fb486e",
          "no_robots_test:cb0115b30980ef2c67f726ee3b246b1a9a48c862cc96e9d5d7f932465113df15",
          "no_robots_test:21d96307542784354781725acfac689570738bbd4701d34d7fef620028a65ab3",
          "no_robots_test:cf187936417f4e620db64edacc001a21ea66cad7ce1632b3b695834e59937c36",
          "no_robots_test:ea03a22f943868af40ddde4838466261bc866a90f93ba57dc9762af5dd1d1f02",
          "no_robots_test:b1d03bc76343f1fed66b69110f521554c64cf85be99e8465fb9d683e712dbf2e",
          "no_robots_test:89b59d3fd692af01d07cffca31fa8206144455daef39e21834fa33fa717eccbd",
          "no_robots_test:3f57eb796307f7079b4b17d5ad1b373027a3d8d6effafe8195d7f07c0c3adc7d",
          "no_robots_test:5379c8e23f96ecbe07278583d4a1bf0cae261c8859f5eaf2fe71cd48dd372b19",
          "no_robots_test:5d57c71c8eb4151b7882399a736fa1f76cee5b963bd81df6c71449843d6a3a78",
          "no_robots_test:c1e734b7c9273ade357686249bef609292f02928f4d7e92aaf8e804903705dcf",
          "no_robots_test:acaf6bbf25fd178fbcec73c0c442c059764b5fb6574737f115be96448f0a949e",
          "no_robots_test:2bf1aaceb022d29d07b3592686801bc38669d7cc3b53a39a493b9fcbe341cba7",
          "no_robots_test:def95674a89f7c0af7e5effafea662aea97fab147eceb9c26522faf022f9c5fe",
          "no_robots_test:9aa4a72006d99dbfa3577a09727a94f45fe46287f36c6a57f05277c5ee7241ab",
          "no_robots_test:1f3fc92dfd7a802a4522cb83047fce264d858342bdd1ba74a6f1ec4b70670436",
          "no_robots_test:f027a06e3a6d9f8e7884505e882765afab994a7af76a45a17ff1ee2019b87935",
          "no_robots_test:58ff17be13248eac49ee8819e0c0932a24aa86ce83bae6c5a81606790fba7b35",
          "no_robots_test:d181278e1b38176c0969f3353fff5e6c420e04b575910d912fc520e607435836",
          "no_robots_test:18c97df1c8de043206f91f144ab63cbaaff8daf413e985c89e707dd3fec96e01",
          "no_robots_test:a8d7070f3b2eadd68ee04484aeee162965cfa87c8944030ddb201caa81afe852",
          "no_robots_test:57518a6bceea3fd9ffa74011999efd87493f1c5db060a4aa769b9be7848af626",
          "no_robots_test:87914ff0fe55338940f93023f9753fe82086fa3f6e8a9eda1a777acc015cf0ac",
          "no_robots_test:7559d264f51a24cb19d4f5975adfd3311da418ff021a7b34b425ae468c2f3a03",
          "no_robots_test:ac1507a57ad89bb7bc2bbc1c369c9b85a9e6eabd82d2fdb646a555dca07e8a8f",
          "no_robots_test:5cdc678ca7768ca7b56af0acd0bd8beed33e962c09fae12c4593ad3fb4e7b686",
          "no_robots_test:10d1712f547e45c910c0ace8c5df343bcfe60cb9674565c75f44c37c9ef27b4a",
          "no_robots_test:f23f7cbd01c6c31d2cf42ab2a77ccd8990c2df24aae4f7fea9333c169b1ebef5",
          "no_robots_test:62ad8ad2fb5e912a6a726ce97148ab183e00836f1f419cb36b40ce9b539f966b",
          "no_robots_test:f1c772697dfaaeac06b48f38adb234478015161fa3ff747863ab1a4fa52546c5",
          "no_robots_test:ac0d55915dbc688034a5fa10e0a0567a2e43baafed48b670e27a99a753d23c5d",
          "no_robots_test:12aab43789e2f7d3146b3176b50852a78331f6ab86ec81f83cc16f5f33ea9ccc",
          "no_robots_test:a47718eb12402f37e9fd94c2155173f37ff201f6e1023e1bec5fde1465a84024",
          "no_robots_test:4ad5e260eba22fdeba20d6e656bdfbc9b3594bee49a1bb22a595b51cd96992af",
          "no_robots_test:879a1ad0ecb760e10299434681ba0e095059acf521f96b016b7a3cde37bdb2b0",
          "no_robots_test:8bb586e839cef9a28ef6fa93a819eaf4c00c71772ab77b6dd895ad053536a777",
          "no_robots_test:df61fa815e8c0741d159d29c8942deabfeb19d84d7ebe78a5aa6ab18f9f0c1bb",
          "no_robots_test:7b9040b1d3b6856c5515e7c3d8d835e9d842b146723068447b4f4ba797e89c32",
          "no_robots_test:eed1bf7ddb070685755afefb800d9b3501a4d37c0dfb2dcff9b466f13e9a51b1",
          "no_robots_test:c2c3159fafc7d47e194430e37ebe9e1b7f624fca4b0f713e8796b14482fbd1e6",
          "no_robots_test:bd00fc3125a0b2024594521b7e88e01056379c60de1104cd3cd30b1d6b86018e",
          "no_robots_test:bdf651db6af463bac2baaa81cd5531391ee680381ab3ec527827f266704f87be",
          "no_robots_test:7a18aac879b7e987f2ac1e13262a9938bdcf98a10e9882b15432cb71c04b0e8c",
          "no_robots_test:6353dab1d3388095c5fa4bdfe6cb081ed487aa771b0295c592712ff348594cb1",
          "no_robots_test:bc3916b72a42f1e5762f0b6ec42187c26c4be4e1bdfc91ee538d2ca24a88e4d1",
          "no_robots_test:ad428e8ceee2a71a99099898cdc3502664f5ceff3546b24068980c1002fe61d1",
          "no_robots_test:73421e0bdb4bfeb54712175074ae883bda34be646e072d60c9ff7680629b1e72",
          "no_robots_test:99c31abd504316002052b5a4599e5ca23850b258e7712e71910e06f9a8f8ddca",
          "no_robots_test:edcbfaa28a53505efeb660324de996f5f87064f05f82c00a430b4bf693563e24",
          "no_robots_test:4d5a125c091b1330ad20f9c6266cef55a59d453c7faadc3f75b7f310d118f580",
          "no_robots_test:711dbf4713654879d2ed546e27e1758c4c41508cadf57b17f7098ec8d9cb4d32",
          "no_robots_test:1d206f2103e90eac0254aa1d3274e9b01645c4a4ba106d87dfe15c1f1e034965",
          "no_robots_test:27af0d850d8bd239b4d44d381f524807db5aad1e39b1a652b58fbfc63a766892",
          "no_robots_test:a2acba4442cc04a98acb1e4ec53cd5677d85e55f0e539f3346597bf85f07d694",
          "no_robots_test:2d91dcc129303876668ca3ebd2082ad0fb4ce76ae99951d801f94e95a7a60404",
          "no_robots_test:2065b3c57f02d3e7fb4e531ee740a7abd4715d4c4bf462f910f7d07f8ed49c7b",
          "no_robots_test:163bae12e8c1649f03d00c75f1f14392d3a165a705e130e2c8c2ef8072900298",
          "no_robots_test:627f3274d200d6ebff294410bddd5bdd289e739ab0eec10e2f12b86e9ba1d2c2",
          "no_robots_test:6da2d4509f61ee54c1e1517dbd90130732b33323b86eb203bd802506eef0f6f5",
          "no_robots_test:f0bfe3f8637787f7feade76b0b4542f98eaa7a6979db99717babbe6d773e2dc8",
          "no_robots_test:aa7f0e5cdfb6901d2d90d3e7208e66ef152eb4c375d6ca49f11c8595426fb5fa",
          "no_robots_test:359c18b053c7ee99c28aaef1489af3e7fdec5696b9c396819469c0fae0abac37",
          "no_robots_test:292ac83dea709c12c9fac33c85cd40881cc9bcf5ed4afdbfd63debfd61077bf6",
          "no_robots_test:0613f4755ddc2493e8e837f455e836df25da9bfa3ff7af7b3730a27b6f5e6b45",
          "no_robots_test:49432f201791c5d2f041d3a9f15fbe8f040e2ee6c3538e3681828d966db63c97",
          "no_robots_test:a3bb1debb936705b1ef7521ef1e9c15e800b67be60014884374f9b5036de27c0",
          "no_robots_test:e20eeb892f54c4810c7d93f54778f1d76df20c699cc7bc3df0c25e283a595a83",
          "no_robots_test:489ec38b91c95df5035c1d889c2a32ed40ca97fa306732d72589217906a120a2",
          "no_robots_test:d1510c80a8ab1d3336f8a94e68efeda4ac4e0c72357b810ff368b0625a7278dd",
          "no_robots_test:376025d76297c587ce811b6f6d21599fbb25cf1af8dc4ed92e18aecbbcc40fe3",
          "no_robots_test:ebca3e652be5cfb23f84fa73480f2f853fd04daa2fdb50575ead2a53b146d443",
          "no_robots_test:38aa0c7bb0970bf91add7d33abdfe187e34a094b55fc66d2a4536c3edccc5a23",
          "no_robots_test:3c75021b544b5c17b1bc159a46bf68c84f3c3f6985a3a45e0534c42dede8ed30",
          "no_robots_test:a74836ebd3c90c383a4008391560ec957dfa0b5da9e29f37cbcb25aa03162300",
          "no_robots_test:ed7b90363e2b3e866e549e4cad67bfbe47b984f6d424dfc5c6ef43bcbc744545",
          "no_robots_test:59b4cee67aabb257050e24350386b215c61af9a4e00bf1b6044bedd14ab864f8",
          "no_robots_test:7bc58574708b8a53410195e1d914dc5a86428b8cc02a383a0f47ddb0c211064c",
          "no_robots_test:17b62a7ecf91cae6ab14f5504d18da30b44396a30219e2b824a59607e58053a5",
          "no_robots_test:832d80a522ed3d18ad84965c457e919336a091b5b525f105cedc909a1a6b42c7",
          "no_robots_test:1ab776c45860a736c7a65b2070dc7d57a58f64ecccffd8c5e0b5220163d129b2",
          "no_robots_test:0dde5c58440c2832f06ee8b7bdbb39e7eb7e703d3722d3903e37972b98f758d6",
          "no_robots_test:dbbe795ab6edb4b0b00d7dc488041c666a0050c0630291a71ac00a77311013e9",
          "no_robots_test:0b8225dc73fa4c390080ebee2a1f6c1aefda82980c02ade6aabe003b2a607778",
          "no_robots_test:4402a30e69c901a660fb7000be2a91ae4fb85d240762156b252fbbaebfcb35c4",
          "no_robots_test:190800e5fe6ec8102868c2a20fe72c3bcce3d47b09e9ce6f89378df9d69d8a55",
          "no_robots_test:2933db9a81070f5a3a907dddc7bfb53954204e9ce6accdbe16fa8236e73702bd",
          "no_robots_test:9b99f22ca3ad129385462592c43ee852b5bc1b143116c69f4a498cc2716b2f37",
          "no_robots_test:f15bf5f600fde612c62aac19aacc96fec9d5492ea20cd882fcf438f7da528fdc",
          "no_robots_test:3c75dd3b9c443c578595c6e6254bab4a402af66ae303c3adcd7d7b0d12fe356f",
          "no_robots_test:6977eba7eabf93213bdb09bbd79c76d48d40f5495b61e60cac9d7251107dd65e",
          "no_robots_test:2e174209ec79d2c77551ad995f0793a105c2a276aba6e540a734b46c376b95ac",
          "no_robots_test:dc9914ebb51f869a655d2c711c3026c5a946e7f5a5f0c4207e5e59996f28fc3a",
          "no_robots_test:6c6e51c01ed43bf768cd647ee633051ba964018ba50398b94778a6336d79cc7d",
          "no_robots_test:8e459a433eee96c1489749574fdb1251cf6160e0867970d21b57f8a0c07bcd5b",
          "no_robots_test:396b9869a1bcf5dc03b28b5b7d9beca4bcba0e336601de2c72d753a5581c0e7e",
          "no_robots_test:ba3186534d194b706f2fafd73ffeba8eaf369eb1b8bc7cd5735f6b832eb63345",
          "no_robots_test:8ca28b279177640a66bba4418407eaac428b4b9929be2621053e528c4787d678",
          "no_robots_test:0d085a2a920a21efe14671cf9783a18cedbf443a371982632b2daf77b745e63c",
          "no_robots_test:0aff4c8b522ebeeb637127bcc660272fc3be476548731845e0a98d0d7252c6a8",
          "no_robots_test:034aeca97edb0026c8f6b28015f96f80e64ed2185e47ca5953bb3558544bf677",
          "no_robots_test:8e748b973a0f9ca774a7fafc2cfb916b4b3fff17f2aa52dbdc4efd99a78a0f42",
          "no_robots_test:9620fd7c9182bde749653ef79cfadcfbb0114013d649300cb1137c70fbbbf2aa",
          "no_robots_test:7e5c5cd4c0281d3379244965dc6614199c6da3e959135a65dc64b8fe9bfbe3c6",
          "no_robots_test:e8d7adc6514830d95bd6d2eefdab4c5f4ab86135aa4f6fb94c57f45965d8bf44",
          "no_robots_test:04a42213adc94ff11ab0c8f2b9d3c1b6a09ab88a018ff2674ac46cc776245585",
          "no_robots_test:43e34875cd8505e545ce6578bacc3f0a0731d1871f829dedb3ebcfedbc125ab3",
          "no_robots_test:079e49e7313d18925ddc6d79ee2bfdaa6efe110fd5e5154d68eb30a3aeb303ce",
          "no_robots_test:b1538637e504a357ff8f6187d26c774dabf66c820133e7386de0ef4b9939a9ff",
          "no_robots_test:9637d09548e7cfb3a2254681d76b906f6736834dc7bb56bc30d30e3ef122ff92",
          "no_robots_test:4e780fcb9b95852d4003a3125728cd59ac9eaa361574de7b424e834429b2f94b",
          "no_robots_test:ebe773c8ce5b980e8534de968460abea42946f338700cab3952e745f1edf34c1",
          "no_robots_test:f40b5870f2b4637108f9e0e624e635b87b8a481c570e561213cfb83997c71fcf",
          "no_robots_test:a457eaad92c901bfa6b421dbca85a0187a55a0c1d3db5c3190118b0f9762840e",
          "no_robots_test:4a35736bd4adcf4f2738d714126f7e1ee631b270854f5f9caf763ee6b0b914ed",
          "no_robots_test:ff458369e71a6c78f6c963ef11c04a41df465ef908baa09bc39c2fd608ebb047",
          "no_robots_test:6d04c2f474c12831ca516bc6b570f14380577896c9430fc0f50c5189b50a61c7",
          "no_robots_test:4fda661d52da94ab5575570229f0fcfbc5d07d86da03f3c689a44bbc7e9183ff",
          "no_robots_test:7d1a1e1b267ad0722a86ca4fad6ddbebd51176842040b291e0008de019ce5379",
          "no_robots_test:24e9ac536dfc2c36b548475cbfdc400ae21c9b5566d6152a3d126f52b43fee25",
          "no_robots_test:02f3e506860f9c0a76c25e040d4ab0104d61bf6759c0aa85ad31ee64bf721eb1",
          "no_robots_test:c79fdcbd3dfb18027a63eded6f242968c518642e7862334f825cadbe2007f1d1",
          "no_robots_test:0e414e0a370e42b00e9e292c176ab1216c7a51b8347c465e2be9d8e10f44af3b",
          "no_robots_test:e9c46210587c0ce455a20422f65d5471275eb38dc4b6db98fd2144bcff13ae72",
          "no_robots_test:3f7aa67c5e926f3901db8fbaf16761392bd403ef426125b223631ec3b2517ac8",
          "no_robots_test:a6deacccb8af5a3a0ea0346c92c9370bdd52ac9227fe360ac5596c76d1bbbd8c",
          "no_robots_test:e825b5cbbaba4c14f72a0856896dd5b523a871ab2b9f2dcd15d776a2b4aabfa4",
          "no_robots_test:2bbd6906c056a90062a8ae36294c8d919482503c574113afdc86f13f14fd837b",
          "no_robots_test:072f282c80b080141098970c3b463d29c5aae2f69ddd2dac7455badcfc5a89c3",
          "no_robots_test:244ecb6b0826574c23d978c03ca05300669ceecf65734363fe097610a6ca25bc",
          "no_robots_test:e507dd4c9d1df15f476426251e5a1d650a207b6a5584f7bd4744f0903093600e",
          "no_robots_test:2b3cdffb047fc350416d9b20e25c4e70590df1c3c868ffdd44fa545ce0d67610",
          "no_robots_test:4c949fbda37ddfda58554ff73a2e224deed8df66695c36a40f8a2d4a134cb9e3",
          "no_robots_test:6d6dfc83c69f55a856b1e0b758eaddf68b5543e14cb2ae617743a0d4881824e8",
          "no_robots_test:9cc02849ca26fe5b9121d46077bb34eff04fb3e2ea2f82305367c9154d1237b7",
          "no_robots_test:2153e9b17536a047acf8a0614c91ab45c9450839e4b2c7660ab25251c173e1c3",
          "no_robots_test:8dc045dcc46374809265fe389a46803a26afafe333fa77dc70a1f8c3acdc3963",
          "no_robots_test:288e444047682b25ddb5ff63898e6a0d48cb1de3c6c06a65261f8bdb60931468",
          "no_robots_test:1905bb8ba7ffff2cff8875d6ddb7a2d85c4fd48873bcfef5c4f71670fa118b68",
          "no_robots_test:042108b7bf148d0831e5665ce92715f156541ee00c56b0adbd330b4cd63dcd99",
          "no_robots_test:3715688d26cc3544beca7d717c5c663cf2a05625d9ae13d1fdb39cf508f77446",
          "no_robots_test:dab34dff6549458647c89e02da31b00b2339599ede1deb6799587b4bd0209106",
          "no_robots_test:ee1bf2cb4729ec1e998907fd521b642b8fa17f54dcd3c4ecfd61994b3935b289",
          "no_robots_test:e3d7cc21f696e9727960b47df92da81cd681c36ee389272b24cb82839f66d9b8",
          "no_robots_test:79cedc57b4ca1fb97ea15691a996378a147499a6e1de0b0e50d9c4c7caf96ea2",
          "no_robots_test:d95f75bba38b5fb8923367b6c8149cae81ba5d31e76f960e55db774d641f3ae9",
          "no_robots_test:1f1c25dd4f795b151f180ab18467385fd533988876fb5303fb5bb3459e35c23a",
          "no_robots_test:09d47615e1590057bac2dc5ce27d3ff90f20db6b531672e5ad57699382a0da08",
          "no_robots_test:a6416ec59f8e7fe9867476cbb4f5f44bfdd6e962fce1bb00814a141cb3780234",
          "no_robots_test:e2caa2ddf7d8e2f8b2c23d288d2b6efc376a4e823ffe09a8af191a44659a4b7b",
          "no_robots_test:a1f930ab77dda26f05c58851efc4c27dbc6e180ec529c04a8ed40e43cd8d0304",
          "no_robots_test:c721adad90dcd07ebbf863bbbd0c4912f833fab99ac96db9f1d5f833c51eb896",
          "no_robots_test:9aec927595bd10316b1df8dcc0df499655280e584a0576047e056f1cb4366d9c",
          "no_robots_test:3efd76547ebd59f65357d2040a3b63b92ada7655b9d2c4de25872503038cb13e",
          "no_robots_test:3cf7583809cc9110e00c65652f69c9235ecb294741c261595eb4ef71d9fd537c",
          "no_robots_test:1b8ef3dce83ad90f2c1a18eb70b97ec2cbc3c25663448c05014503d1a4fd3ed5",
          "no_robots_test:c4eace49f52ea1066fe19654a8d625211ec377ad9901c86888dc5ad4be6fdcee",
          "no_robots_test:0907eb27ebbf46386b02ca9314935c115cdbdd8382c6370817438e4fc2097819",
          "no_robots_test:fb551f033bfede2b3cd283a2628bb5c46f4dfb47a97e6f477b5288d358ad4b72",
          "no_robots_test:95b5066b66039db0dbb8ab6788922e68fde8517e20552c6cda3fc0e3499d316a",
          "no_robots_test:c27801ad6b5ebadf46dd97da83476952a72b99495ebc85677516437e49c09fbf",
          "no_robots_test:e31053f7b489a3ba30b1011663175d1a13fc350b94840af286aea356c829599e",
          "no_robots_test:a88b3d44f1598abfb32011ef71e859618a69c60e54d77ac0477a29d649036625",
          "no_robots_test:a210dfc781291b83f2b82a299e82c61d90617500e34395c42a53220b22fb32b0",
          "no_robots_test:756d31fa74b296203c9450a5ded21a07492f0f99caf7c982abf61a93a9c3ec56",
          "no_robots_test:470dce010416538f33aaeb18822ccbdf5f5e1da5749326a11100cab5b54f44db",
          "no_robots_test:d9f074817f0647ebb6d9d6a879598fc4394ae7c63b56cc55a147a2b8ef27aa27",
          "no_robots_test:fdcc2616f33ae53e0f3121b5cf7cc998b31a8657f3581552a2646c28702f302b",
          "no_robots_test:9a9300da4935003f03f16f85b9697b58b533353f121a8be641e1c46aaea3d6f3",
          "no_robots_test:93f3c8cc7dece34fdca51a61199b09bd96d8a2d0d5526bae764c07a97602a921",
          "no_robots_test:0b93de1a6ea093a5807b24dd5c14f32a952d548e14cdbc92d20d5cbc831546b8",
          "no_robots_test:36674ceea31c0eefa67d12528bf92ddd91263cfb12fbe08bcd2631a52dd61188",
          "no_robots_test:e266e32ac7319880ff40641c9ea49f61154ce74ce396876cc973d70708946f7d",
          "no_robots_test:a1521cb0aa1aa83ec0dc5e3a52234a27e14576e75751b4704480ebd16ac6e396",
          "no_robots_test:a794f05f5d6687b8a2e78d904a89209812a47276ad51ed1405043d45b1500cab",
          "no_robots_test:27d5c23de1b1d5746a570fcb287b947bf3abec3a5a2948cb081f8daf5c285b6b",
          "no_robots_test:9f63c208fe95b14e13899e0207f0d42a9a816b8674a3892c3c8de74b07b70c7d",
          "no_robots_test:04795cf6ec37a7dd935c1de66d84d8ac0d764cdf12fac297d129f48dcfaa8d79",
          "no_robots_test:afd6af67cc1816d99f86b3e059ab2e77aea944c07b1838c27e6eef57a1400985",
          "no_robots_test:cbec88e3309b7648c023d9e2114e2d7595cc9aa18067c25391252004042c8eb9",
          "no_robots_test:5a0a73e9962d364ed3eeb4d132f2499e7047e2272808600a290a2fdab270f074",
          "no_robots_test:f74746e22e3b69428e9f6bc6ea0561480c8f0ed4bd977656197db9521368fee8",
          "no_robots_test:e0b1ce063570abea18f6ed8dbeadb06d796c243f7e6a2a1f49379e74384d5ba6",
          "no_robots_test:66b6335c0c576b405ed1668e632edbedd0eb09146dd4e4d84aca2b6043511aea",
          "no_robots_test:079c5a5713af4f78a53df64e7b0464359e30f5fedcfa1fee25cc46b177c44367",
          "no_robots_test:d436fce6076f3110e1b20da47f43d8fd0e643a43d36af478ed325f1061eddc79",
          "no_robots_test:da13290dda7f6ac430bdd317de487a6f9fa79e1b0ce8b353f948980a519cf952",
          "no_robots_test:f044562dab2d66d59ffa187a93db0a4d4eef2217a7c143f944312254e82913cc",
          "no_robots_test:940e3ea02beb3b61613794d1b427bf37f30078633244e2a2d3a3a17a169d2350",
          "no_robots_test:749dd218364d72a3c4022bc6665491204d016ba8717793b88665219a4b4d9c70",
          "no_robots_test:e10eb2e3fd3cbcbc45858578621b9b4e64aca3dd8f3b0ad39a472fa3c490f660",
          "no_robots_test:36e1d930e74392cca2528fe06bd8f0d38befdde3c3781b8922041dd688d55235",
          "no_robots_test:ecdb34794b24ea6e65ac66a1700160f4864589bb77a5def4591fe996701cb06e",
          "no_robots_test:47e591d09b7363112580b3eefe8ed4da5f274dccd3619a2704027db79f941198",
          "no_robots_test:f68dd2578ad9dfebdec7bcd8caae2e5d4459159dcfbce130fb6ee6902c18b836",
          "no_robots_test:c2abe99df0a43a558ebb63151afd3f8a96f884b33495437b5917b0d6099fd599",
          "no_robots_test:3ab7f8ff8f4372b640737a33505112b854b4d6bc35d9e87a4cf73ca9dbbe2f14",
          "no_robots_test:1045319c37d98f4f7462681fc50423762cafeb00bd2925484b3d429718e8ff8c",
          "no_robots_test:9d3f9dc6ca94a0bdba137665cb1d8d9e4b76d78fdd9a79e7e4ac963bda7e0f38",
          "no_robots_test:d8e91a51b7e31c9367cb2bfc5f4418870271355df0d3048599ed2f1d61bac77f",
          "no_robots_test:5a911dae756fdfd96b80d4406b261fe658cf900bf6ea2281c59b2e87df796a24",
          "no_robots_test:070995ef4c7e899b073a6b1e03a1c0a91d8f6e2917b867ebf75bce02027b2653",
          "no_robots_test:51e7e7e69771e152110bd3673461509ee7e0c513dcf590703f6d587bb65ed706",
          "no_robots_test:4377ce8bd0f44aa7114983c2d48b23862106b0f247b9199a0ab9926f50dfd80b",
          "no_robots_test:4969e6d2e7da9be81ccbbdb18b575ba0b363066b5365ca134b59285bf5c6afd3",
          "no_robots_test:2f4b66e0168b2cf7e7c260d3f3b7a18df48f4984fdae0a895561c6a01fd77c88",
          "no_robots_test:dc306933ec2a6f7ee590c6de309bbdad91d0f668aca834db27cdc4ecfb5ac7d8",
          "no_robots_test:3232792c0b1f58bb36128a00bbe8a2abdf24fddac8c92ba386018ebe34756dae",
          "no_robots_test:5ee45f9ebff4e75410b1128889f9d0ca7556b223e69df33334075761d1c7a57e",
          "no_robots_test:f6c76517ce8ed01ce548ea7c86ffc53a5fe7afe7984a166755b5e35eeb99099c",
          "no_robots_test:57a499002a099639b52fb3dfdf516feb745c14457182340aebbb3546de7eec77",
          "no_robots_test:1c5db2224424da86a908bfc9f21425d8669300e88205241d97d0c7a9b4324a6a",
          "no_robots_test:2ace06c7fd726671319de8192f3fe5480f5297faab8f09753c1cfe7d6df294fd",
          "no_robots_test:a3b22afe88af8a1377646606f9f4df393ac0bc931a643220a32095285895de97",
          "no_robots_test:86c835efe40d8ef93ca1608e77a2268143da853d0f60a714e1284fe606e6b4df",
          "no_robots_test:0e43302941845c64fb7ba5fca1ef39612a906c9fc81c3fb7753ff7ba3b30687d",
          "no_robots_test:d63dd41a84b46571478cb5a4903d5efce1b77515b3e3e5acee602f4a56d0783a",
          "no_robots_test:07727af96427cfb80e78aba4d505f97dde11e3c5969f44fe5664b45e8b4e7df7",
          "no_robots_test:d0aede9a69080a3131f709faa0ec3d99aecd603e981414ee70d2df4d39bea02d",
          "no_robots_test:0ca28e9e453502956ead1128cec5019004c58e33cba5929f5301f3763428216c",
          "no_robots_test:764691c4fe0c71bcacf5e05c3b4a120547e80d8c365e6edeefa6a40298f04faa",
          "no_robots_test:c221a1f994cff9c2f34b9aa9e41a55163172ddae96767c1d20c1965b48080017",
          "no_robots_test:4ac2c6de8b0e256bde22bd47ede3e8ce6b1c3df1b1e2dd0e3eb286e2bb325bef",
          "no_robots_test:6a07c07c04281930a7048bda680a6241c65710437584d777401158b0c57554c8",
          "no_robots_test:c6c5baccf1fd2a97d0043db12d7d33d85377a8a924e43eee946b3bc18ed8ebb1",
          "no_robots_test:50afd036b32ea68be44204ffab02e3f5cb85068de3d905b820844c09b77e17a5",
          "no_robots_test:7d8b08737912472872ed2932afe7af99bc72e16457a76b9f91f6b6e376284f24",
          "no_robots_test:585e892fa64acb013514af77c36f63c776983e5cfef4563790464fc6cfdfbfde",
          "no_robots_test:690738484383e06723019f31ae210f7306246191c01c3d5a09c4f665b7624f1f",
          "no_robots_test:4464c320e01db719e51909b974243edc0e7b45f08cc6b30d4d31ac6f13f2e67c",
          "no_robots_test:700bc710519bc0de70046303a32891ac5542679ef6ca1030f3bbc8bfefdc2a17",
          "no_robots_test:8b6453aa02539744c0b316eb03e2d64aa90369280a65da600f6c391472b94963",
          "no_robots_test:3e0a50a9d76572aed087981deeb71f851ea0e9ce59ef7a79dd5b14ac82c38c84",
          "no_robots_test:6367ce45caa5d0f0b1acb41b2f53e424f993478d1466f4448a4a97dc495a7222",
          "no_robots_test:e473b2438fd9d0a06a40ad46f9a3ffeccd8d0ad4e5749b9d1ccba0eeac5a3025",
          "no_robots_test:40995aedb42a2ce8a74fdc801dc7a3c7a4e50206d0820dfaa35b47f5bb76bf9a",
          "no_robots_test:c0e4991c7c924b78a5cff690c322f7cdd0e82062b55130fb63c19f2b4da79188",
          "no_robots_test:45c8c3c63e02bf5ed5c99b208cdf423a53371f41e59d852c2678ee637aea8ba5",
          "no_robots_test:ed6df8fada20e3613a2ee2142eb619726f7389f0b6464480a37e7f675dacf148",
          "no_robots_test:76aee18285d18dabcec5cb59f7aa2a0190bbdb0a4f64eb6a4db95976e8d227ca",
          "no_robots_test:62829e5b79946e964e3a04465f37d7f8d3d702e2fa342dbf7fbe4441aa05ff23",
          "no_robots_test:c14c3c4b63794c8b534c6a60fa3338b1cadc10b24bf8ef69bdb04854b5224333",
          "no_robots_test:9ea362fd9c2b04083756e2c03b02b4d5d334826313b7c36eb45f922068ccdb80",
          "no_robots_test:446c0186eeb24e8a43d0ab7dd13d314a20e86b3523aa23dc1d8e68422e7b7cce",
          "no_robots_test:489c7abb740ed0b9bb6bc704595edf4c94f1f9f4ac797ff1d6f55d8ea956d8e6",
          "no_robots_test:002ab8b85a36e6c5464c96594c1046aaad0832b2b7ba59b7c60f8d5bf1839d14",
          "no_robots_test:73d6f61d9fc2261b5ff4fc6a130ce46e5f759fdd82536f4458150cc9abe67453",
          "no_robots_test:f3f094b2aaa7c46b1dc50d4975a008bd30230089ebefafa9724184be73f84d17",
          "no_robots_test:c70281f8e81ec2249e2b6ec296b0d5158860523a83a3d6ece0c11d534f24fc3d",
          "no_robots_test:23b988274475e59d97dfeaf717327a13d9e3d4df2e73c30cbbca59c1ea842860",
          "no_robots_test:9283abbe02ec6e09f3ce2719b02aa2b1dc2f887425a2d5144f923403fb9b54db",
          "no_robots_test:a08e2b36113e5d71feb47d60494b84029dec93aab7e1ad658b433eebff8e0ba3",
          "no_robots_test:3f02ff68fb4cacef7ce3877c019b13187ab2739d5dd1a82f850852a67025a9b1",
          "no_robots_test:0335e3ebae248cd378edc4479b1f7a885172da22e70da830aeaf9622978feec4",
          "no_robots_test:02697bcf2ecb738e9532ddba8b7079aa21d8bb9744456dcde524871c3eb728f8",
          "no_robots_test:5b34963157310ae9936fd14ff22daa343a9529b3c193544d754eea0a73e5760e",
          "no_robots_test:12fe37ce674a2f79d7f2f36211393d9d9d4b97d1a431be0b27000b64a5bb16cd",
          "no_robots_test:0c30072a27e82c8fc2f6009a0d08214fb1552c42b1917aa9acbcfe3d1c5d9e91",
          "no_robots_test:0d24b407ea10dd9173e8fbb377609559e820302a1bc8ea15f42b5c0356266a1b",
          "no_robots_test:602272a99566bf68a5b48979478bceb0b56f74915925ed8a1b0a558935df3584",
          "no_robots_test:ecdac8f179582eb850ec28155ea59279e445c219d7bcccc6753cef24a7199a42",
          "no_robots_test:46b880155fdd947f395a3009a313bf8cbfe8e137c37b3a614c49585112e0aa0f",
          "no_robots_test:65b835d2335e23cf908b10817be1eb5c1bd5dcd3b80bd3e7a46c72d2cd479e8d",
          "no_robots_test:48363ab6108604ad6812a9dbe0f17fc52dc68532d3b3bf4d83bfadcea7b99f9a"
        ]
      },
      "parser": "token NLL = -sum(logprobs[weights>0]); token_mean = sum NLL / sum counted tokens over 500 items",
      "prompt_template": "tinker_cookbook renderer for Qwen/Qwen3.5-2B (renderers.get_recommended_renderer_name), conversation_to_datum(messages, renderer, max_length=2048), TrainOnWhat=ALL_ASSISTANT_MESSAGES default; teacher-forced cross_entropy forward; NLL counted where weight>0"
    }
  },
  "scores": [
    {
      "arm": "baseline",
      "evaluator_id": "a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744",
      "metric": "no_robots_test_token_mean_nll_at_step_100",
      "predictions_ref": "predictions-confirm-test.jsonl",
      "seed": 0,
      "value": 2.0330268793696935
    },
    {
      "arm": "treatment",
      "evaluator_id": "a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744",
      "metric": "no_robots_test_token_mean_nll_at_step_100",
      "predictions_ref": "predictions-confirm-test.jsonl",
      "seed": 0,
      "value": 2.0323170273395057
    },
    {
      "arm": "baseline",
      "evaluator_id": "a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744",
      "metric": "no_robots_test_token_mean_nll_at_step_100",
      "predictions_ref": "predictions-confirm-test.jsonl",
      "seed": 1,
      "value": 2.0315072699517907
    },
    {
      "arm": "treatment",
      "evaluator_id": "a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744",
      "metric": "no_robots_test_token_mean_nll_at_step_100",
      "predictions_ref": "predictions-confirm-test.jsonl",
      "seed": 1,
      "value": 2.0304049240877835
    },
    {
      "arm": "baseline",
      "evaluator_id": "a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744",
      "metric": "no_robots_test_token_mean_nll_at_step_100",
      "predictions_ref": "predictions-confirm-test.jsonl",
      "seed": 2,
      "value": 2.030763545006581
    },
    {
      "arm": "treatment",
      "evaluator_id": "a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744",
      "metric": "no_robots_test_token_mean_nll_at_step_100",
      "predictions_ref": "predictions-confirm-test.jsonl",
      "seed": 2,
      "value": 2.030674625589407
    }
  ],
  "version": 1
}
Held-out loss aggregation
Spec asks for token mean (summed NLL / loss tokens) · run reported token mean (summed NLL / loss tokens)
  • arms were scored on different tokens or examples: sel_adamw_lr5e-05_s0 94328.0 tokens / 500 examples, sel_adamw_lr0.0001_s0 94328.0 tokens / 500 examples, sel_adamw_lr0.0002_s0 94328.0 tokens / 500 examples, sel_dimuon_lr0.0003_s0 94328.0 tokens / 500 examples, sel_dimuon_lr0.001_s0 94328.0 tokens / 500 examples, sel_dimuon_lr0.003_s0 94328.0 tokens / 500 examples, baseline_adamw_s0 97346.0 tokens / 500 examples, treatment_dimuon_s0 97346.0 tokens / 500 examples, baseline_adamw_s1 97346.0 tokens / 500 examples, treatment_dimuon_s1 97346.0 tokens / 500 examples, baseline_adamw_s2 97346.0 tokens / 500 examples, treatment_dimuon_s2 97346.0 tokens / 500 examples
armvaluetoken meanexample meanloss tokensexamples
sel_adamw_lr5e-05_s02.0712.0711.93594,328500
sel_adamw_lr0.0001_s02.0662.0661.92794,328500
sel_adamw_lr0.0002_s02.0632.0631.92294,328500
sel_dimuon_lr0.0003_s02.252.252.20194,328500
sel_dimuon_lr0.001_s02.1062.1061.98194,328500
sel_dimuon_lr0.003_s02.0672.0671.92994,328500
baseline_adamw_s02.0332.0331.91297,346500
treatment_dimuon_s02.0322.0321.91197,346500
baseline_adamw_s12.0322.0321.91297,346500
treatment_dimuon_s12.032.031.90997,346500
baseline_adamw_s22.0312.0311.9197,346500
treatment_dimuon_s22.0312.0311.9197,346500
Feasibility projection: unknown
Projected costs, not measured GPU usage.
Projected wall time
unknown
Projected GPU allocation
unknown
  • Re-projection required: lora_rank changed or was not recorded
  • Re-projection required: dataset changed or was not recorded
  • Re-projection required: steps changed or was not recorded
  • Re-projection required: n_examples changed or was not recorded
  • Re-projection required: n_eval changed or was not recorded
  • Representative evaluation timing not recorded
  • Representative setup timing not recorded
  • Representative training timing not recorded
  • Unknown timing phase: setup_pilot
  • Unknown timing phase: training_pilot
  • Unknown timing phase: heldout_eval_pilot
  • Unknown timing phase: setup_selection
  • Unknown timing phase: training_selection
  • Unknown timing phase: heldout_eval_selection
  • Unknown timing phase: setup_confirmation
  • Unknown timing phase: training_confirmation
  • Unknown timing phase: heldout_eval_confirmation
Timing, sample counts and allocation evidence
{
  "generation_applicability": {
    "check": "generation_audit",
    "enforce": false,
    "features": {
      "generated_training_data": false
    },
    "reasons": [
      "spec.generation_audit opts out and no feature it covers is true"
    ],
    "status": "not_applicable"
  },
  "generation_counts": null,
  "gpu_hours": null,
  "known_gpu_hours": 1.3603800910049015,
  "phases": {
    "recovery": {
      "gpu_hours": 1.3603800910049015,
      "wall_seconds": 4897.368327617645
    }
  },
  "problems": [
    "Re-projection required: lora_rank changed or was not recorded",
    "Re-projection required: dataset changed or was not recorded",
    "Re-projection required: steps changed or was not recorded",
    "Re-projection required: n_examples changed or was not recorded",
    "Re-projection required: n_eval changed or was not recorded",
    "Representative evaluation timing not recorded",
    "Representative setup timing not recorded",
    "Representative training timing not recorded",
    "Unknown timing phase: setup_pilot",
    "Unknown timing phase: training_pilot",
    "Unknown timing phase: heldout_eval_pilot",
    "Unknown timing phase: setup_selection",
    "Unknown timing phase: training_selection",
    "Unknown timing phase: heldout_eval_selection",
    "Unknown timing phase: setup_confirmation",
    "Unknown timing phase: training_confirmation",
    "Unknown timing phase: heldout_eval_confirmation"
  ],
  "record": {
    "config": {
      "arms": 12,
      "base_model": "Qwen/Qwen3.5-2B",
      "batch_size": 32,
      "confirmation_steps": 100,
      "max_seq_len": 2048,
      "n_eval_test": 500,
      "n_eval_validation": 500,
      "n_ifeval_secondary": 541,
      "planned_arm_steps": 840,
      "selection_steps": 40
    },
    "effective_config": {
      "arms": 12,
      "base_model": "Qwen/Qwen3.5-2B",
      "batch_size": 32,
      "confirmation_steps": 100,
      "max_seq_len": 2048,
      "n_eval_test": 500,
      "n_eval_validation": 500,
      "n_ifeval_secondary": 0,
      "note": "IFEval dropped (downsizing step 1); LR grid, selection steps, seeds, test NLL unchanged",
      "pilot_arms": 2,
      "pilot_steps": 10,
      "planned_arm_steps": 840,
      "selection_steps": 40
    },
    "generation": null,
    "measurements": {
      "heldout_eval_confirmation": {
        "allocation_source": "fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)",
        "gpu_count": 1,
        "planned_units": 3000,
        "samples": 3000,
        "seconds": 134.40599060058594,
        "units": 3000
      },
      "heldout_eval_pilot": {
        "allocation_source": "fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)",
        "gpu_count": 1,
        "planned_units": 1000,
        "samples": 1000,
        "seconds": 80.4703094959259,
        "units": 1000
      },
      "heldout_eval_selection": {
        "allocation_source": "fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)",
        "gpu_count": 1,
        "planned_units": 3000,
        "samples": 3000,
        "seconds": 127.7629702091217,
        "units": 3000
      },
      "setup_confirmation": {
        "allocation_source": "fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)",
        "gpu_count": 1,
        "planned_units": 6,
        "samples": 6,
        "seconds": 266.957839012146,
        "units": 6
      },
      "setup_pilot": {
        "allocation_source": "fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)",
        "gpu_count": 1,
        "planned_units": 2,
        "samples": 2,
        "seconds": 252.8196606636047,
        "units": 2
      },
      "setup_selection": {
        "allocation_source": "fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)",
        "gpu_count": 1,
        "planned_units": 6,
        "samples": 6,
        "seconds": 48.95686173439026,
        "units": 6
      },
      "training_confirmation": {
        "allocation_source": "fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)",
        "gpu_count": 1,
        "planned_units": 600,
        "samples": 19200,
        "seconds": 786.5640952587128,
        "units": 600
      },
      "training_pilot": {
        "allocation_source": "fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)",
        "gpu_count": 1,
        "planned_units": 20,
        "samples": 640,
        "seconds": 161.3649604320526,
        "units": 20
      },
      "training_selection": {
        "allocation_source": "fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)",
        "gpu_count": 1,
        "planned_units": 240,
        "samples": 7680,
        "seconds": 749.6906819343567,
        "units": 240
      }
    },
    "primary_endpoint": "no_robots_test_token_mean_nll_at_step_100",
    "recovery": {
      "allocation_source": "fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)",
      "gpu_count": 1,
      "note": "wall used 68.4 of 150 min; trainer GPU-h used ~1.02 of 2.0 (deploy to now, 1 GPU)",
      "seconds": 4897.368327617645
    },
    "source": "pilot_log.jsonl (10-step 2-arm representative pilot); select_log.jsonl and confirm_log.jsonl measured"
  },
  "recorded_at": 1793745777.0760796,
  "status": "unknown",
  "wall_seconds": null
}
Generated task audit: not applicable
spec.generation_audit opts out and no feature it covers is true
Answer agreement with recorded independent solutions does not establish semantic correctness. Normalized exact overlap does not detect paraphrases.
Spec exp_71911f0fb9
Experiment version
exp_71911f0fb9
Execute the selected saved experiment version.

Hypothesis

With per-optimizer learning rates picked on a validation split, LoRA SFT with dimuon-lite cuts held-out no_robots token_mean NLL by at least 0.02 nats versus AdamW. Both arms use the same 100 steps, batches and seeds.

Success criterion

Validated if the simultaneous 95% paired_t interval, across 3 training seeds, for (AdamW NLL − DiMuon NLL) on no_robots test token_mean NLL at step 100 lies entirely above 0.02 nats. Failed if it lies entirely below 0.02. Otherwise inconclusive. IFEval strict accuracy is reported descriptively and does not decide.

no_robots 100 steps batch 32 LoRA r32 lr 0.001 150 min wall budget
Method
Train a rank-32 LoRA on Qwen/Qwen3.5-2B over HuggingFaceH4/no_robots, using one tinker SDK script for both arms so the only difference is the optimizer. The cookbook chat_sl recipe is AdamW-only, so running AdamW through the same script removes any recipe difference. DiMuon is selected at creation with optimizer=tinker.types.DimuonOptimizerConfig() and stepped with DimuonParams(learning_rate, beta1=0.9, grad_clip_norm=0.0). AdamW uses tinker.AdamParams(learning_rate, beta1=0.9, beta2=0.95, eps=1e-8). dimuon-lite is a recently landed reverse-engineered update rule: Polar Express orthogonalization with about 5 iterations, rank_lr_correction_exponent 0.175, Muon on LoRA B, and no beta2. Its update is checked against the trusted DiMuon reconstruction before the comparison runs. Phase 1, LR selection: each optimizer runs 40 steps at seed 0 on a 3-point LR grid fixed now (AdamW {5e-5, 1e-4, 2e-4}; DiMuon {3e-4, 1e-3, 3e-3}). Each run is scored by token_mean NLL on 500 validation items held out from the train split, and the best LR per optimizer is frozen. Phase 2, confirmation: each optimizer trains 100 steps at its frozen LR for seeds {0,1,2}. Batches are identical across arms within a seed: the same shuffled order of the remaining 9,000 train rows, batch_size 32, max_seq_len 2048. Data order and LoRA init seed are shared per seed. Primary eval is token_mean NLL on the full 500-example no_robots test split, computed from per-example summed logprobs times loss weights via forward(). Secondary, descriptive only: IFEval prompt-level strict accuracy (541 prompts, greedy, max_tokens 1024) on each final checkpoint. IFEval is dropped first if feasibility does not fit.
Baseline
AdamW (tinker.AdamParams, beta1 0.9, beta2 0.95, eps 1e-8) through the same SDK script, with the same model, LoRA rank, init seed, batches and order, 100 steps, and eval. Its LR is chosen by the same 3-point validation search.
Full spec
{
  "activation_gate": {
    "applicable": true,
    "checks": [
      {
        "measures": "model name passed to create_lora_training_client in every arm",
        "metric": "executed_base_model",
        "one_of": [
          "Qwen/Qwen3.5-2B"
        ]
      },
      {
        "measures": "type of params object passed to optim_step in each arm (logged client-side)",
        "metric": "executed_optimizer_step_type",
        "one_of": [
          "DimuonParams",
          "AdamParams"
        ]
      },
      {
        "max": 1.05,
        "measures": "||dB||_F^2 / (||dB||_2^2 * r) for the first DiMuon update of LoRA B, averaged over layers, from downloaded checkpoints at step 0 and 1",
        "metric": "dimuon_B_update_normalized_stable_rank_step1",
        "min": 0.6
      },
      {
        "max": 1.0,
        "measures": "fraction of the 100 training batches whose token-id hash is identical between paired arms within a seed",
        "metric": "batch_hash_match_across_arms",
        "min": 1.0
      },
      {
        "measures": "train token_mean NLL at step 0 minus step 10 in the DiMuon pilot at the middle LR; must be finite and positive",
        "metric": "pilot_train_nll_drop_dimuon_10steps",
        "min": 0.0
      }
    ],
    "reason": "The paired comparison only tests DiMuon if the executed optimizer really orthogonalizes LoRA B updates and both arms ran the declared configuration. Polar Express makes the first-step B update near-orthogonal (flat singular spectrum); AdamW's is not. This is measured from saved weight diffs, not SDK introspection."
  },
  "arms": [
    {
      "lr": 5e-05,
      "name": "lrsearch_adamw_5e-5_s0",
      "optimizer": "adam",
      "phase": "selection",
      "seed": 0,
      "steps": 40
    },
    {
      "lr": 0.0001,
      "name": "lrsearch_adamw_1e-4_s0",
      "optimizer": "adam",
      "phase": "selection",
      "seed": 0,
      "steps": 40
    },
    {
      "lr": 0.0002,
      "name": "lrsearch_adamw_2e-4_s0",
      "optimizer": "adam",
      "phase": "selection",
      "seed": 0,
      "steps": 40
    },
    {
      "lr": 0.0003,
      "name": "lrsearch_dimuon_3e-4_s0",
      "optimizer": "dimuon-lite",
      "phase": "selection",
      "seed": 0,
      "steps": 40
    },
    {
      "lr": 0.001,
      "name": "lrsearch_dimuon_1e-3_s0",
      "optimizer": "dimuon-lite",
      "phase": "selection",
      "seed": 0,
      "steps": 40
    },
    {
      "lr": 0.003,
      "name": "lrsearch_dimuon_3e-3_s0",
      "optimizer": "dimuon-lite",
      "phase": "selection",
      "seed": 0,
      "steps": 40
    },
    {
      "lr": "frozen from selection",
      "name": "baseline_adamw_s0",
      "optimizer": "adam",
      "phase": "confirmation",
      "seed": 0,
      "steps": 100
    },
    {
      "lr": "frozen from selection",
      "name": "baseline_adamw_s1",
      "optimizer": "adam",
      "phase": "confirmation",
      "seed": 1,
      "steps": 100
    },
    {
      "lr": "frozen from selection",
      "name": "baseline_adamw_s2",
      "optimizer": "adam",
      "phase": "confirmation",
      "seed": 2,
      "steps": 100
    },
    {
      "lr": "frozen from selection",
      "name": "treatment_dimuon_s0",
      "optimizer": "dimuon-lite",
      "phase": "confirmation",
      "seed": 0,
      "steps": 100
    },
    {
      "lr": "frozen from selection",
      "name": "treatment_dimuon_s1",
      "optimizer": "dimuon-lite",
      "phase": "confirmation",
      "seed": 1,
      "steps": 100
    },
    {
      "lr": "frozen from selection",
      "name": "treatment_dimuon_s2",
      "optimizer": "dimuon-lite",
      "phase": "confirmation",
      "seed": 2,
      "steps": 100
    }
  ],
  "base_model": "Qwen/Qwen3.5-2B",
  "baseline": "AdamW (tinker.AdamParams, beta1 0.9, beta2 0.95, eps 1e-8) through the same SDK script, with the same model, LoRA rank, init seed, batches and order, 100 steps, and eval. Its LR is chosen by the same 3-point validation search.",
  "batch_size": 32,
  "budget": {
    "gpu_hours": 2.0,
    "max_wall_minutes": 150
  },
  "command": "# Custom part: one SDK SFT loop shared by both optimizers (cookbook chat_sl is AdamW-only).\nimport os, sys, tinker, datasets, random\nfrom tinker_cookbook import renderers, tokenizer_utils\nfrom tinker_cookbook.supervised.data import conversation_to_datum\nOPT, LR, SEED, STEPS = sys.argv[1], float(sys.argv[2]), int(sys.argv[3]), int(sys.argv[4])\nMODEL='Qwen/Qwen3.5-2B'; BS=32; MAXLEN=2048\ntok=tokenizer_utils.get_tokenizer(MODEL); rend=renderers.get_renderer(renderers.get_recommended_renderer_name(MODEL) if hasattr(renderers,'get_recommended_renderer_name') else 'qwen3', tok)\nds=datasets.load_dataset('HuggingFaceH4/no_robots'); tr=list(ds['train']); random.Random(1234).shuffle(tr)\nval, train = tr[:500], tr[500:]; random.Random(SEED).shuffle(train)\nmk=lambda r: conversation_to_datum(r['messages'], rend, MAXLEN)\nsc=tinker.ServiceClient(base_url=os.environ['TINKER_BASE_URL'])\nkw={'optimizer': tinker.types.DimuonOptimizerConfig()} if OPT=='dimuon' else {}\ntc=sc.create_lora_training_client(base_model=MODEL, rank=32, seed=SEED, **kw)\ntc.save_weights_for_sampler(name=f'init-{OPT}-s{SEED}').result()  # hash for restoration preflight\nstep_params = (lambda: tinker.types.DimuonParams(learning_rate=LR, beta1=0.9, grad_clip_norm=0.0)) if OPT=='dimuon' else (lambda: tinker.AdamParams(learning_rate=LR, beta1=0.9, beta2=0.95, eps=1e-8))\nfor s in range(STEPS):\n    batch=[mk(r) for r in train[s*BS:(s+1)*BS]]\n    tc.forward_backward(batch, loss_fn='cross_entropy').result(); tc.optim_step(step_params()).result()\ndef nll(rows):  # token_mean from per-example totals, never batch loss:mean\n    tot=0.0; n=0.0\n    for i in range(0,len(rows),32):\n        d=[mk(r) for r in rows[i:i+32]]; out=tc.forward(d, loss_fn='cross_entropy').result()\n        for di,o in zip(d,out.loss_fn_outputs):\n            w=di.loss_fn_inputs['weights'].to_numpy(); lp=o['logprobs'].to_numpy(); tot+=-(lp*w).sum(); n+=w.sum()\n    return tot/n\nsplit = val if STEPS==40 else list(ds['test'])\nprint({'opt':OPT,'lr':LR,'seed':SEED,'steps':STEPS,'token_mean_nll':nll(split)})\ntc.save_weights_for_sampler(name=f'final-{OPT}-lr{LR}-s{SEED}').result()\n# run: python sft_opt.py {adam|dimuon} <lr> <seed> {40|100}",
  "correctness_preflight": {
    "notes": "Tolerances are fixed for bf16 LoRA weights with fp32 optimizer math before measuring. reference_update rtol 1e-2 leaves headroom over the reported 0.09% error. Feed the same LoRA state and gradient to the Spindle DiMuon step and to the reference for one step. With grad_clip_norm=0 and beta1 momentum seeded from the first gradient, the update should scale linearly in LR across a 100x span.",
    "paths": [
      {
        "baseline_revision": "UNRESOLVED: pin the modal-projects/spindle commit deployed at the shared Spindle URL (post-#85). AdamW updates on this deployment must match the pre-#85 AdamW update on identical grads/state.",
        "id": "spindle_dimuon_lite_optimizer",
        "kind": "optimizer",
        "lr_scaling": {
          "learning_rates": [
            0.0001,
            0.001,
            0.01
          ],
          "rtol": 0.01
        },
        "reference_revision": "UNRESOLVED: pin the commit of Aaron's DiMuon reconstruction (0.09% relative update error vs Tinker) and the modal-projects/miles commit of #17",
        "tolerances": {
          "baseline_update": {
            "atol": 1e-06,
            "min_cosine": 0.99999,
            "rtol": 0.001
          },
          "reference_update": {
            "atol": 1e-05,
            "min_cosine": 0.999,
            "rtol": 0.01
          }
        }
      }
    ],
    "required": true,
    "status": "unresolved: spindle and miles commits for #85/#17 and the commit of Aaron's DiMuon reconstruction must be pinned before any full sweep"
  },
  "dataset": {
    "hf_path": "HuggingFaceH4/no_robots",
    "n_examples": 9500,
    "name": "no_robots",
    "split": "train (9000 for training, 500 held out for LR selection); test (500) for confirmation"
  },
  "decision_rule": {
    "adaptive_selection": {
      "confirmation_item_ids": "all 500 rows of no_robots split=test",
      "kind": "hyperparameter",
      "rationale": "Muon-family and AdamW LoRA optimizers have very different good LRs. Each gets a prespecified 3-point grid, scored only on validation items held out from train, and the choice is frozen before the single confirmation eval on the test split.",
      "search_item_ids": "no_robots train rows held out by seeded shuffle (seed 1234), first 500 after shuffle; never used for training"
    },
    "alpha": 0.05,
    "assumptions": {
      "identically_distributed_seed_effects": true,
      "independent_seed_effects": true,
      "normal_seed_effects": true
    },
    "criteria": [
      {
        "id": "primary",
        "margin": 0.02,
        "metric": "no_robots_test_token_mean_nll_at_step_100",
        "weights": {
          "baseline": 1,
          "treatment": -1
        }
      }
    ],
    "estimand": "Reduction in held-out no_robots test token_mean NLL at step 100 from replacing AdamW with dimuon-lite (each at its validation-selected LR) for rank-32 LoRA SFT on Qwen3.5-2B; larger is better for dimuon-lite.",
    "method": "paired_t",
    "seeds": [
      0,
      1,
      2
    ],
    "unit": "training_seed",
    "version": 1
  },
  "eval": {
    "aggregation": "token_mean",
    "benchmark": "no_robots test split (HuggingFaceH4/no_robots, split=test)",
    "metric": "held-out token_mean NLL (nats per assistant loss token)",
    "n_examples": 500
  },
  "experiment_features": {
    "adaptive_selection": true,
    "checkpoint_restore": false,
    "custom_loss": false,
    "custom_optimizer": true,
    "generated_training_data": false,
    "heldout_loss": true,
    "learned_generator": false,
    "paired_comparison": true,
    "paired_training_arms": true,
    "warmup_adaptation": false
  },
  "feasibility": {
    "config": null,
    "downsizing_order": "drop IFEval secondary, then shrink LR grid to 2 points per optimizer, then shorten selection runs to 25 steps; keep 3 seeds and the 100-step test NLL. If that still does not fit, report inconclusive.",
    "effective_config": {
      "arms": 12,
      "base_model": "Qwen/Qwen3.5-2B",
      "batch_size": 32,
      "confirmation_steps": 100,
      "max_seq_len": 2048,
      "n_eval_test": 500,
      "n_eval_validation": 500,
      "n_ifeval_secondary": 541,
      "planned_arm_steps": 840,
      "selection_steps": 40
    },
    "generation": null,
    "measurements": null,
    "primary_endpoint": "no_robots_test_token_mean_nll_at_step_100",
    "recovery": null,
    "source": null
  },
  "feasibility_check": {
    "generation_applicability": {
      "check": "generation_audit",
      "enforce": false,
      "features": {
        "generated_training_data": false
      },
      "reasons": [
        "spec.generation_audit opts out and no feature it covers is true"
      ],
      "status": "not_applicable"
    },
    "generation_counts": null,
    "gpu_hours": null,
    "known_gpu_hours": 0,
    "phases": {},
    "problems": [
      "Effective configuration not recorded",
      "Pilot evidence source not recorded",
      "Representative training timing not recorded",
      "Representative setup timing not recorded",
      "Representative evaluation timing not recorded",
      "Positive recovery reserve not recorded"
    ],
    "status": "unknown",
    "wall_seconds": null
  },
  "feasibility_required": true,
  "generation_audit": {
    "answer_comparison": null,
    "max_eval_overlaps": 0,
    "max_label_errors": 0,
    "min_sample_size": 0,
    "reason": "fixed public dataset; no generated training data",
    "required": false
  },
  "hypothesis": "With per-optimizer learning rates picked on a validation split, LoRA SFT with dimuon-lite cuts held-out no_robots token_mean NLL by at least 0.02 nats versus AdamW. Both arms use the same 100 steps, batches and seeds.",
  "lora_rank": 32,
  "max_seq_len": 2048,
  "method": "Train a rank-32 LoRA on Qwen/Qwen3.5-2B over HuggingFaceH4/no_robots, using one tinker SDK script for both arms so the only difference is the optimizer. The cookbook chat_sl recipe is AdamW-only, so running AdamW through the same script removes any recipe difference. DiMuon is selected at creation with optimizer=tinker.types.DimuonOptimizerConfig() and stepped with DimuonParams(learning_rate, beta1=0.9, grad_clip_norm=0.0). AdamW uses tinker.AdamParams(learning_rate, beta1=0.9, beta2=0.95, eps=1e-8). dimuon-lite is a recently landed reverse-engineered update rule: Polar Express orthogonalization with about 5 iterations, rank_lr_correction_exponent 0.175, Muon on LoRA B, and no beta2. Its update is checked against the trusted DiMuon reconstruction before the comparison runs. Phase 1, LR selection: each optimizer runs 40 steps at seed 0 on a 3-point LR grid fixed now (AdamW {5e-5, 1e-4, 2e-4}; DiMuon {3e-4, 1e-3, 3e-3}). Each run is scored by token_mean NLL on 500 validation items held out from the train split, and the best LR per optimizer is frozen. Phase 2, confirmation: each optimizer trains 100 steps at its frozen LR for seeds {0,1,2}. Batches are identical across arms within a seed: the same shuffled order of the remaining 9,000 train rows, batch_size 32, max_seq_len 2048. Data order and LoRA init seed are shared per seed. Primary eval is token_mean NLL on the full 500-example no_robots test split, computed from per-example summed logprobs times loss weights via forward(). Secondary, descriptive only: IFEval prompt-level strict accuracy (541 prompts, greedy, max_tokens 1024) on each final checkpoint. IFEval is dropped first if feasibility does not fit.",
  "optimizer": {
    "lr": 0.001,
    "name": "dimuon-lite"
  },
  "primary_endpoint": "no_robots_test_token_mean_nll_at_step_100",
  "restoration_preflight": {
    "applicable": true,
    "fixed_batch_required": true,
    "groups": [
      {
        "arms": [
          {
            "name": "baseline_adamw_s0",
            "optimizer": "adam",
            "optimizer_config": {
              "beta1": 0.9,
              "beta2": 0.95,
              "eps": 1e-08,
              "lr": "frozen"
            }
          },
          {
            "name": "treatment_dimuon_s0",
            "optimizer": "dimuon-lite",
            "optimizer_config": {
              "beta1": 0.9,
              "grad_clip_norm": 0.0,
              "lr": "frozen"
            }
          }
        ]
      },
      {
        "arms": [
          {
            "name": "baseline_adamw_s1",
            "optimizer": "adam",
            "optimizer_config": {
              "beta1": 0.9,
              "beta2": 0.95,
              "eps": 1e-08,
              "lr": "frozen"
            }
          },
          {
            "name": "treatment_dimuon_s1",
            "optimizer": "dimuon-lite",
            "optimizer_config": {
              "beta1": 0.9,
              "grad_clip_norm": 0.0,
              "lr": "frozen"
            }
          }
        ]
      },
      {
        "arms": [
          {
            "name": "baseline_adamw_s2",
            "optimizer": "adam",
            "optimizer_config": {
              "beta1": 0.9,
              "beta2": 0.95,
              "eps": 1e-08,
              "lr": "frozen"
            }
          },
          {
            "name": "treatment_dimuon_s2",
            "optimizer": "dimuon-lite",
            "optimizer_config": {
              "beta1": 0.9,
              "grad_clip_norm": 0.0,
              "lr": "frozen"
            }
          }
        ]
      }
    ],
    "reason": "AdamW and DiMuon arms are trained from a shared fresh-LoRA start within each seed. Before the first update, each arm calls save_weights and downloads the adapter. The SHA-256 of the LoRA tensors must match across the paired arms; B=0 at init, and A comes from the seeded init. Base-model logprobs on a fixed tokenized batch must also match. A hash mismatch makes that seed inconclusive. Optimizer type is verified by the activation-gate step-1 spectrum check, not by invented introspection."
  },
  "steps": 100,
  "success_criterion": "Validated if the simultaneous 95% paired_t interval, across 3 training seeds, for (AdamW NLL \u2212 DiMuon NLL) on no_robots test token_mean NLL at step 100 lies entirely above 0.02 nats. Failed if it lies entirely below 0.02. Otherwise inconclusive. IFEval strict accuracy is reported descriptively and does not decide.",
  "title": "dimuon-lite vs AdamW, LoRA SFT on Qwen3.5-2B, no_robots held-out NLL",
  "training_type": "sft"
}
Evidence 32

Recorded · Download manifest. Recorded files are retained copies; checkpoint references do not include model weights.

Checkpoint references
[
  {
    "arm": "baseline_adamw_s0",
    "step": 100,
    "uri": "tinker://b61dfd929fd09745b512c7224450cbde/weights/confirm-baseline_adamw_s0-final"
  },
  {
    "arm": "treatment_dimuon_s0",
    "step": 100,
    "uri": "tinker://d331297013cae43230697585afa80dc5/weights/confirm-treatment_dimuon_s0-final"
  },
  {
    "arm": "baseline_adamw_s1",
    "step": 100,
    "uri": "tinker://9c18b804f21a06705c6da69577f80b4e/weights/confirm-baseline_adamw_s1-final"
  },
  {
    "arm": "treatment_dimuon_s1",
    "step": 100,
    "uri": "tinker://64eea06e33ba66329c486ce2de950f32/weights/confirm-treatment_dimuon_s1-final"
  },
  {
    "arm": "baseline_adamw_s2",
    "step": 100,
    "uri": "tinker://581c1850d38ffa76474e2c6c7f2a3fb1/weights/confirm-baseline_adamw_s2-final"
  },
  {
    "arm": "treatment_dimuon_s2",
    "step": 100,
    "uri": "tinker://8e9fef4c99e9c1af8d68a14c2c921011/weights/confirm-treatment_dimuon_s2-final"
  },
  {
    "arm": "sel_adamw_lr5e-05_s0",
    "step": 40,
    "uri": "tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-sel_adamw_lr5e-05_s0-final"
  },
  {
    "arm": "sel_adamw_lr0.0001_s0",
    "step": 40,
    "uri": "tinker://34671def1a8e798b05dd051092ac4307/weights/select-sel_adamw_lr0.0001_s0-final"
  },
  {
    "arm": "sel_adamw_lr0.0002_s0",
    "step": 40,
    "uri": "tinker://99ddc7356a2150f7dbafc5262693978b/weights/select-sel_adamw_lr0.0002_s0-final"
  },
  {
    "arm": "sel_dimuon_lr0.0003_s0",
    "step": 40,
    "uri": "tinker://3f4f84e3c9c6567b09cde46deae56415/weights/select-sel_dimuon_lr0.0003_s0-final"
  },
  {
    "arm": "sel_dimuon_lr0.001_s0",
    "step": 40,
    "uri": "tinker://4d27e2e59c33df3015a266e8878b457d/weights/select-sel_dimuon_lr0.001_s0-final"
  },
  {
    "arm": "sel_dimuon_lr0.003_s0",
    "step": 40,
    "uri": "tinker://38efef6933464782c8204a61c7fec196/weights/select-sel_dimuon_lr0.003_s0-final"
  }
]
Per-arm evidence metrics
{
  "baseline_adamw_s0": {
    "lr": 0.0002,
    "test_example_mean_nll_step100": 1.911837178105109,
    "test_token_mean_nll_step100": 2.0330268793696935
  },
  "baseline_adamw_s1": {
    "lr": 0.0002,
    "test_example_mean_nll_step100": 1.9122966738185496,
    "test_token_mean_nll_step100": 2.0315072699517907
  },
  "baseline_adamw_s2": {
    "lr": 0.0002,
    "test_example_mean_nll_step100": 1.9098644363144257,
    "test_token_mean_nll_step100": 2.030763545006581
  },
  "sel_adamw_lr0.0001_s0": {
    "val_token_mean_nll_step40": 2.0661315833516616
  },
  "sel_adamw_lr0.0002_s0": {
    "val_token_mean_nll_step40": 2.063218484765968
  },
  "sel_adamw_lr5e-05_s0": {
    "val_token_mean_nll_step40": 2.0706255712024144
  },
  "sel_dimuon_lr0.0003_s0": {
    "val_token_mean_nll_step40": 2.250428290149688
  },
  "sel_dimuon_lr0.001_s0": {
    "val_token_mean_nll_step40": 2.1062885413010375
  },
  "sel_dimuon_lr0.003_s0": {
    "val_token_mean_nll_step40": 2.0673232168471443
  },
  "treatment_dimuon_s0": {
    "lr": 0.003,
    "test_example_mean_nll_step100": 1.9111400255469455,
    "test_token_mean_nll_step100": 2.0323170273395057
  },
  "treatment_dimuon_s1": {
    "lr": 0.003,
    "test_example_mean_nll_step100": 1.909386036657386,
    "test_token_mean_nll_step100": 2.0304049240877835
  },
  "treatment_dimuon_s2": {
    "lr": 0.003,
    "test_example_mean_nll_step100": 1.9099000514950917,
    "test_token_mean_nll_step100": 2.030674625589407
  }
}
All metrics
metricsel_adamw_lr5e-05_s0sel_adamw_lr0.0001_s0sel_adamw_lr0.0002_s0sel_dimuon_lr0.0003_s0sel_dimuon_lr0.001_s0sel_dimuon_lr0.003_s0baseline_adamw_s0treatment_dimuon_s0baseline_adamw_s1treatment_dimuon_s1baseline_adamw_s2treatment_dimuon_s2
val_token_mean_nll_step402.0712.0662.0632.252.1062.067——————
test_token_mean_nll_step100——————2.0332.0322.0322.032.0312.031
test_example_mean_nll_step100——————1.9121.9111.9121.9091.911.91
lr——————0.00020.0030.00020.0030.00020.003
primary_mean_adamw_minus_dimuon
0.0006337
primary_ci95_low
-0.0006357
primary_ci95_high
0.001903
primary_sd
0.000511
margin
0.02
diff_adamw_minus_dimuon_s0
0.0007099
diff_adamw_minus_dimuon_s1
0.001102
diff_adamw_minus_dimuon_s2
8.892e-05
selected_lr_adamw
0.0002
selected_lr_dimuon
0.003
paired_batch_hash_match_confirmation
1
wall_minutes
68.38
trainer_gpu_hours
1.02
Interim updates from Devin (5, first Nov 3, 21:51 UTC)
Artifact references
  • checkpoint · baseline_adamw_s0 · step 100 · tinker://b61dfd929fd09745b512c7224450cbde/weights/confirm-baseline_adamw_s0-final
  • checkpoint · treatment_dimuon_s0 · step 100 · tinker://d331297013cae43230697585afa80dc5/weights/confirm-treatment_dimuon_s0-final
  • checkpoint · baseline_adamw_s1 · step 100 · tinker://9c18b804f21a06705c6da69577f80b4e/weights/confirm-baseline_adamw_s1-final
  • checkpoint · treatment_dimuon_s1 · step 100 · tinker://64eea06e33ba66329c486ce2de950f32/weights/confirm-treatment_dimuon_s1-final
  • checkpoint · baseline_adamw_s2 · step 100 · tinker://581c1850d38ffa76474e2c6c7f2a3fb1/weights/confirm-baseline_adamw_s2-final
  • checkpoint · treatment_dimuon_s2 · step 100 · tinker://8e9fef4c99e9c1af8d68a14c2c921011/weights/confirm-treatment_dimuon_s2-final
  • checkpoint · sel_adamw_lr5e-05_s0 · step 40 · tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-sel_adamw_lr5e-05_s0-final
  • checkpoint · sel_adamw_lr0.0001_s0 · step 40 · tinker://34671def1a8e798b05dd051092ac4307/weights/select-sel_adamw_lr0.0001_s0-final
  • checkpoint · sel_adamw_lr0.0002_s0 · step 40 · tinker://99ddc7356a2150f7dbafc5262693978b/weights/select-sel_adamw_lr0.0002_s0-final
  • checkpoint · sel_dimuon_lr0.0003_s0 · step 40 · tinker://3f4f84e3c9c6567b09cde46deae56415/weights/select-sel_dimuon_lr0.0003_s0-final
  • checkpoint · sel_dimuon_lr0.001_s0 · step 40 · tinker://4d27e2e59c33df3015a266e8878b457d/weights/select-sel_dimuon_lr0.001_s0-final
  • checkpoint · sel_dimuon_lr0.003_s0 · step 40 · tinker://38efef6933464782c8204a61c7fec196/weights/select-sel_dimuon_lr0.003_s0-final
  • script · run.py sha256 8480b967ec29
  • script · common.py sha256 e4258da51051
  • script · fork_config.py sha256 83939e181c12
  • script · preflight.py sha256 466afac60991
  • script · analyze_preflight.py sha256 4574d9d3d7c5
  • script · analyze2.py sha256 abf7fc94170c
  • script · local_parity.py sha256 9c79b2ed02ff
  • script · build_preflight.py sha256 c74c0017b314
  • script · launch_confirm.py sha256 0b448f42bedd
  • script · final_analysis.py sha256 a0eb6a3e00fe
  • script · restore_check.py sha256 995a05bc7fcf
  • script · build_output.py sha256 137937f13a7d
  • script · smoke.py sha256 c3c36f5a2e18
  • script · probe_shared.py sha256 20499f5b52d3
  • instructions · launch-instructions.md sha256 8e52fc8e31fe
  • effective_config · effective-config.json sha256 1d9e8504b61c
  • code_revision · code-revision.txt sha256 561d1418f25e
  • code_patch · spindle_fork.patch sha256 e99d856d7c3d
  • script · dimuon_candidate.py sha256 31c5f60cb273
  • predictions · predictions-confirm-test.jsonl sha256 12d303555ef2
  • metrics · scored-observations-final.jsonl sha256 620c1d8cea25
  • metrics · select_log.jsonl sha256 30fde247db6d
  • metrics · confirm_log.jsonl sha256 6e81489e1ae7
  • metrics · pilot_log.jsonl sha256 76c36589a1f8
  • metrics · correctness_preflight.json sha256 c644004dfc54
  • metrics · preflight_results.json sha256 a81ba4bccec2
  • metrics · local_parity.json sha256 b86d75974be2
  • metrics · restore_check.json sha256 94bb1e212364
  • metrics · selection_frozen.json sha256 757269f012e6
  • metrics · final_numbers.json sha256 3d1e2943d353
  • metrics · cleanup.json sha256 64945a4c8629
  1. Nov 3, 22:42 UTC · succeeded · done: sel_adamw_lr5e-05_s0, sel_adamw_lr0.0001_s0, sel_adamw_lr0.0002_s0, sel_dimuon_lr0.0003_s0, sel_dimuon_lr0.001_s0, sel_dimuon_lr0.003_s0, baseline_adamw_s0, treatment_dimuon_s0, baseline_adamw_s1, treatment_dimuon_s1, baseline_adamw_s2, treatment_dimuon_s2 · On fork spindle-fork-run_739abc9a8b, 100-step rank-32 LoRA SFT of Qwen3.5-2B on no_robots gave AdamW-minus-Dimuon test token-mean NLL +0.0006 nats (95% paired-t CI [-0.0006, +0.0019], 3 seeds) at sel…
  2. Nov 3, 22:21 UTC · running · done: sel_adamw_lr5e-05_s0, sel_adamw_lr0.0001_s0, sel_adamw_lr0.0002_s0, sel_dimuon_lr0.0003_s0, sel_dimuon_lr0.001_s0, sel_dimuon_lr0.003_s0 · Correctness preflight and activation gate passed on fork spindle-fork-run_739abc9a8b. LR selection (40 steps, 500 val items) picked AdamW 2e-4 and Dimuon 3e-3, both at the upper grid edge (makes the …
  3. Nov 3, 22:09 UTC · running · Fork spindle-fork-run_739abc9a8b deployed (Spindle 5148cb6 + proxy-auth patch, Miles 228b59d). Correctness preflight passed research_exchange.correctness; activation gate passed; LR selection (6 arms…
  4. Nov 3, 22:04 UTC · running · Fork spindle-fork-run_739abc9a8b deployed (Spindle 5148cb6 + proxy-auth patch, Miles 228b59d). Correctness preflight passed research_exchange.correctness validator (AdamW vs torch AdamW max_abs 2.9e-…
  5. Nov 3, 21:51 UTC · running · Launch instructions downloaded, SHA256 verified, fully read. Shared Spindle rejects Dimuon (HTTP 400), so a throwaway fork spindle-fork-run_739abc9a8b (Spindle PR #85 branch + Miles PR #17 dimuon-lit…
Artifacts
adaptation_manifests
[]
correctness_preflight
{'required': True, 'paths': [{'id': 'spindle_dimuon_lite_optimizer', 'fixed_input': {'sha256': 'd989d2d28d1a32103662ca010d0652a1e0ec111b370e20df63a9cf7c0aaed3a8', 'description': 'Step-1 fixture: seed-0 first no_robots train batch (32 seqs, sha256 d9ce572e4cf770c21e54e31f0cd523d578343475316b862f1453171ae1c3c6eb, cross_entropy, cookbook weights), fork init state tinker://43f94846bfb916692227a10acb4ae578/weights/pf-init (fp32 sha256 3388743efeef0e9eb77f61bc1fc018db7bb82e5e6a313f707ad028d9b95e1bd0, LoRA B=0), optimizer state reset per client. Hash covers the exact fp32 gradient fixture (AdamW client exp_avg). Stale-scale step 2 uses a second fixed fp32 gradient. Retrieved via modal volume get run_739abc9a8b-checkpoints.'}, 'baseline_revision': 'UNRESOLVED: pin the modal-projects/spindle commit deployed at the shared Spindle URL (post-#85). AdamW updates on this deployment must match the pre-#85 AdamW update on identical grads/state.', 'reference_revision': "UNRESOLVED: pin the commit of Aaron's DiMuon reconstruction (0.09% relative update error vs Tinker) and the modal-projects/miles commit of #17", 'resolved_revisions': {'baseline_executed': 'fork spindle-fork-run_739abc9a8b: modal-projects/spindle 5148cb62a019862ef9b50d76b7be55cddb288e8a (PR #85 branch claude/dimuon-spindle-wiring) + spindle_fork.patch (requires_proxy_auth=True); shared Spindle deployment 4af4dd2c46c009fcf8661e625195d4bf6c5dde81 is pre-#85 (rejects dimuon), so no post-#85 shared deployment exists. AdamW reference = stock torch.optim.AdamW on identical exp_avg-derived gradient and init.', 'reference_executed': "Aaron's DiMuon reconstruction has no git commit; pinned by content sha256 31c5f60cb273ca53a0adfda9b88b8ff8fd1efd05c497114dbd0cb1f99673c51e (dimuon_candidate.py, code block of Notion page 3fe1e7f169498132903de1b12bfe4205). Miles PR #17 = modal-projects/miles 228b59d90074e6cec48090e033202c5a4aff3ff3 (dimuon.py sha256 8c5268543094cc6677a4606ecbd5902749c34a5e2f95fa7ba29890e732e86519), mounted via SPINDLE_MILES_TREE."}, 'implementation_revision': 'spindle 5148cb62a019862ef9b50d76b7be55cddb288e8a+proxy-auth patch; miles 228b59d90074e6cec48090e033202c5a4aff3ff3 (dimuon.py sha256 8c5268543094cc6677a4606ecbd5902749c34a5e2f95fa7ba29890e732e86519)', 'precision': 'fp32 master params and gradients; Dimuon working momentum fp32, persisted momentum bf16, Polar Express 5 iters horner_fp16; AdamW fp32 exp_avg/exp_avg_sq; model forward/backward bf16', 'normalization': 'cross_entropy sum of weighted token NLL (cookbook weights, counted by weight>0); Dimuon per-projection-block direction scaled to Frobenius sqrt(rank=32), update lr*(32/32)^0.175, damping 1e-4, beta1 0.9, no grad clip; AdamW bias-corrected first step lr*m_hat/(sqrt(v_hat)+1e-8)', 'errors': {'baseline_update': {'max_abs_error': 2.9103830456733704e-11, 'reference_max_abs': 0.00010000001202570274, 'relative_l2_error': 1.1838959207204277e-07, 'cosine_similarity': 0.9999999999984652}, 'reference_update': {'max_abs_error': 0.0, 'reference_max_abs': 0.00043169609853066504, 'relative_l2_error': 0.0, 'cosine_similarity': 0.9999999999996416}}, 'diagnostic_errors': {'reference_update_stale_scales_step2_packed_vs_unpacked': {'max_abs_error': 5.820766091346741e-11, 'reference_max_abs': 0.0004482679651118815, 'relative_l2_error': 7.763380802737512e-08, 'cosine_similarity': 1.000000000005693}, 'server_dimuon_vs_reference_bf16_momentum_reconstructed_grad': {'max_abs_error': 1.619606337044388e-05, 'reference_max_abs': 0.00043122234637849033, 'relative_l2_error': 0.008914503668966067, 'cosine_similarity': 0.999960265766336}, 'server_dimuon_vs_local_miles_same_bf16_input': {'max_abs_error': 1.619606337044388e-05, 'reference_max_abs': 0.00043122234637849033, 'relative_l2_error': 0.008914503668966067, 'cosine_similarity': 0.9999602657663412}, 'server_dimuon_vs_reference_other_client_fp32_grad': {'max_abs_error': 1.3311757356859744e-05, 'reference_max_abs': 0.00043169609853066504, 'relative_l2_error': 0.01112447649318528, 'cosine_similarity': 0.9999381229397716}, 'server_cross_client_noise_floor_lr1e-4x10_vs_lr1e-3': {'max_abs_error': 1.1148425983265042e-05, 'reference_max_abs': 0.0004318455175962299, 'relative_l2_error': 0.008873499902993041, 'cosine_similarity': 0.9999606304975468}, 'server_cross_client_gradient_agreement': {'max_abs_error': 0.003906428813934326, 'reference_max_abs': 0.9726564288139344, 'relative_l2_error': 0.00445943772141835, 'cosine_similarity': 0.9999900624438804}, 'restore_replay_update_vs_uninterrupted': {'max_abs_error': 2.4998094886541367e-05, 'reference_max_abs': 0.000484729214804247, 'relative_l2_error': 0.009888607172079344, 'cosine_similarity': 0.999951107737341}}, 'reference_update_note': "reference_update compares the deployed Miles Dimuon code (packed fused qkv/fc1 B) against Aaron's reference (unpacked per-projection blocks) on bitwise-identical fp32 inputs. The server-executed update cannot be fed an identical fp32 gradient; vs reference it shows max_abs 1.62e-5 (> 1.43e-5 threshold) with bf16-reconstructed input, identical to its error vs local Miles code on the same input, and 1.33e-5 (passes) with another client's fp32 gradient; server cross-client noise floor is 1.11e-5.", 'lr_scaling': [{'learning_rate': 0.0001, 'update_norm': 0.005571355047044043}, {'learning_rate': 0.001, 'update_norm': 0.05571355442863166}, {'learning_rate': 0.01, 'update_norm': 0.5571355017914699}]}]}
correctness_validation
{'status': 'passed', 'required': True, 'checks': [{'path': 'spindle_dimuon_lite_optimizer', 'check': 'baseline_update', 'status': 'passed', 'tolerance': {'atol': 1e-06, 'rtol': 0.001, 'min_cosine': 0.99999}, 'measured': {'max_abs_error': 2.9103830456733704e-11, 'reference_max_abs': 0.00010000001202570274, 'relative_l2_error': 1.1838959207204277e-07, 'cosine_similarity': 0.9999999999984652}}, {'path': 'spindle_dimuon_lite_optimizer', 'check': 'reference_update', 'status': 'passed', 'tolerance': {'atol': 1e-05, 'rtol': 0.01, 'min_cosine': 0.999}, 'measured': {'max_abs_error': 0.0, 'reference_max_abs': 0.00043169609853066504, 'relative_l2_error': 0.0, 'cosine_similarity': 0.9999999999996416}}, {'path': 'spindle_dimuon_lite_optimizer', 'check': 'lr_scaling', 'status': 'passed', 'relative_error': 7.10453955665713e-08, 'tolerance': {'learning_rates': [0.0001, 0.001, 0.01], 'rtol': 0.01}}], 'reason': 'Reported baseline and reference parity checks meet accepted tolerances.', 'evidence_source': 'executor report; remote execution is not attested', 'applicability': 'required', 'reported_verdict': 'inconclusive'}
decision
{'version': 1, 'observations_file': {'name': 'scored-observations-final.jsonl', 'sha256': '620c1d8cea254438c9e1d250282fcd7b4fb4aba7fd4a919569d089c9f1d78faf'}, 'selection': {'frozen_before_confirmation': True, 'selection_split': '500 held-out no_robots train rows (Random(1234) shuffle, first 500), disjoint from training rows', 'selection_steps': 40, 'adamw': {'scores': {'5e-05': 2.0706255712024144, '0.0001': 2.0661315833516616, '0.0002': 2.063218484765968}, 'selected_lr': 0.0002, 'edge': True}, 'dimuon': {'scores': {'0.0003': 2.250428290149688, '0.001': 2.1062885413010375, '0.003': 2.0673232168471443}, 'selected_lr': 0.003, 'edge': True}, 'grid_edge_selected': True}}
decision_validation
{'status': 'uncertain', 'issues': ['Adaptive selection requires disjoint search and confirmation IDs.'], 'criteria': [], 'outcome_reason': 'insufficient_evidence', 'observations_file': {'name': 'scored-observations-final.jsonl', 'sha256': '620c1d8cea254438c9e1d250282fcd7b4fb4aba7fd4a919569d089c9f1d78faf', 'size': 1501, 'n_observations': 6}, 'unit': 'training_seed', 'n_seeds': 3, 'alpha': 0.05, 'method': 'paired_t', 'assumptions': {'independent_seed_effects': True, 'identically_distributed_seed_effects': True, 'normal_seed_effects': True}, 'applicability': {'check': 'decision_rule', 'status': 'required', 'enforce': True, 'reasons': ['experiment_features: paired_comparison, adaptive_selection is true'], 'features': {'paired_comparison': True, 'adaptive_selection': True}}}
evaluation
{'version': 1, 'evaluators': {'a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744': {'code_sha256': '52b3d966475a14ba5b3d854d7e22134648b12c59b47ca24801c3b7f66d34fb90', 'prompt_template': 'tinker_cookbook renderer for Qwen/Qwen3.5-2B (renderers.get_recommended_renderer_name), conversation_to_datum(messages, renderer, max_length=2048), TrainOnWhat=ALL_ASSISTANT_MESSAGES default; teacher-forced cross_entropy forward; NLL counted where weight>0', 'decoding': {'type': 'teacher_forced_forward', 'temperature': None, 'max_tokens': 0, 'stop': []}, 'parser': 'token NLL = -sum(logprobs[weights>0]); token_mean = sum NLL / sum counted tokens over 500 items', 'items': {'ids': ['no_robots_test:d6c011ffb1ff8a9abe9bd24caf3f9817454a1f054d5d0e0360d19bf50cf6b20c', 'no_robots_test:7682c850c4e5979cef0ad966b8feb119de2bd323bb40819767a161040b59eb7a', 'no_robots_test:45971bbe382b81644487690d2018bc3aec8c807f1be52a9744223e5492255928', 'no_robots_test:ccdce774f24ede2e799686276e8b72e8b08a4aebf6ba75ecc450fc73cfedd1a8', 'no_robots_test:c1f40447167a99977d745672c0c19cb2739b6f5208647af47fac16c94f88826e', 'no_robots_test:f7128731ae16e9ccfbb888620c5d75564fb8d12350e9b47c781beeb64ebd04c7', 'no_robots_test:f865f7581ddc128be8b79fa82e7fa9102362b6a7685d82f9116436280073695b', 'no_robots_test:2e26a31997285dc001e683aec269ec9b0c4e3400b97a7cbb6367a08e374dfedc', 'no_robots_test:3fad3d579a7259e0bbff20c18d4c72049a7b9378078c85188ba9b166216b4775', 'no_robots_test:cc614a388398a30b28e3b18b9382a1438d8b8455377d6a65f902a709a75168a1', 'no_robots_test:e038c9bbc2ec4556f6ab47f9651fa89cb5d7f72891a5fba4415e13f18f7ca0b7', 'no_robots_test:37746cac882d406894272569214f6ede6ab7b78de88c01e6bea144234a4013bf', 'no_robots_test:6ac710f1196bc72404d3e08e8acca16f7f144752544aa4af9a19736053fbda4b', 'no_robots_test:f52ce291ce39c76f22e3771a091d24bb55b3831106506a3835c2a2e16a86d1c1', 'no_robots_test:5a5c6035044f914d24e5fa5677048b7461bb3c3a4a7cfa474fbcfa29588670d8', 'no_robots_test:c1c9a958b19539efc3ce03adb85c0c7811393e90d35f33f4d96e999d79e3e8a9', 'no_robots_test:66e33c21f54193775c1fda86f9be739152462cea267969b838ed953956f4b631', 'no_robots_test:3c338b2227c9f2922a94c730fc653d50dec826ea0febb228867efb3709a3f31d', 'no_robots_test:85b810a2c52be481e2f79b741fb8a02142c18d9db329189689789240bad537a6', 'no_robots_test:ba7cd3cea48952cd4f218fb4ba23a7a0d9f6d3e2b524eb897a063d567521bcbc', 'no_robots_test:645c6de54016df90ea64d9b72a1686de2c682467cc0988ed2b8379e4af3a3b69', 'no_robots_test:ba474c32c7c4db657376ec72136594729848d88a0423d0457e9f6eea6680e9c1', 'no_robots_test:ebd302ba966ef926516b751f9d42bd52ed4b21747f424f147c33de05d5cb46a5', 'no_robots_test:d555a1b6eab48b9f199186e30b6b691eafd4b0df80a6558b64c4c5d60509848a', 'no_robots_test:1329aaafcece6e6674ee78a546492be7047a72bd8eed93a15490b517d195f8aa', 'no_robots_test:ca2aefe6159c88ab4335e1b2a19e04bb70d2d096c8b6487946607a4fb57b9207', 'no_robots_test:f8385c2bedf5af812b3e13ed50abf373552e551992c637acf8c341fb2bd4ef30', 'no_robots_test:687e88746b34ab7a856e2d8795eb696de02b6909f8e68dd0c5595cf754eb22b2', 'no_robots_test:b096cd3cc576e1df1bfc3ea2e8c1b89817a67e1f4d4209100e7e0ac03323b45a', 'no_robots_test:503c617fbdab4576be1c79b421947a7c5f1a2b365808c6b6f8e31287d1aeb674', 'no_robots_test:46ffb831bbb5717977280909d133272c1cda68f7769a58f18e83331e906c5aa0', 'no_robots_test:d155ad5a56b452703abf0c54969f8cfd0372dcbe0befcd4a0af5a0fbdcbfe23b', 'no_robots_test:d36d2dcd016969972e6ea69b0ad14f9ff2b6e341d9ff7565318d6082b0523ba6', 'no_robots_test:9d2c280bd301ce2066b71f70cdfe03494262cf4f369010aea6e00f23f853cbc7', 'no_robots_test:37ac631bf0d66b95a69519e58da6a3c4f1118d6960bace298e83087805422076', 'no_robots_test:91e0052f1664f2e28d66653914c81a87f27e0b24a46b9136e4748a8c24545289', 'no_robots_test:6f921864bd8b8123377fe29446547b0cfccf9882bda00e1ed0a11f99c7290799', 'no_robots_test:06f8cec4f3a7a51087180e3fba0d8a2c19c0866cff613bbc7d044033f82467e5', 'no_robots_test:41d3a40c684db02d115771774e75f6812745b96bfc8b26c6198f3537fa5bd7e8', 'no_robots_test:71b63a042ad1e85efc91ec2ac3a88629d29d13978696515b1bc0d29bea1fae36', 'no_robots_test:40f8e6e855826d7d7671f4dbb5f7c12ae99541888fe78e7b4d669adbe00b1151', 'no_robots_test:0869a2536bae18939b4f62b6c026f631cc44083e1903bde4de0b1e7e339702e5', 'no_robots_test:ac80dd9713747a25db3164ad15d37c61409a02257bd88433e1c254eb927a4372', 'no_robots_test:2fb3649c9d992e39a4a394aeb16b91720ec8ae19dd43895b3914a6511144ca1e', 'no_robots_test:bb96ffd53f0444b90e6fad698788ab9ccd24d6f63aa674494be21315ee7a2dd3', 'no_robots_test:2beadd667769f5875ab256f7f840e2c6d26c1b667ba4ef11d814b61153da6e13', 'no_robots_test:a9a8696c28ade7a3f9e0b3d8d97abb862ed987239887e988a2dd21cee1915cb2', 'no_robots_test:bab1283b2cfd37eb5a264da47f0663cea09d18088cd4c48886d0174e1eba536e', 'no_robots_test:b3b45db4ac4b90ae5fddacef19c5deb1a91dbee65068d9ab0d36d3e1aa92334b', 'no_robots_test:c2596826a823a13939db48d0ee04bfb0083fdf8133eff4468550ca63ebb76864', 'no_robots_test:069a404880fd7eebecec2132e04406f2858b71a7588237de0c546d826aa2cce3', 'no_robots_test:151659a113f8a967eea7c23e19e96b0da262f736a3560b9dff28efb68b553978', 'no_robots_test:0f861d5aa34b0dcfc2ddd35da09fc581aff25b042a2795f36bda290e00071378', 'no_robots_test:498c6846aff34679bd2acaf9a40672c60df6dc00e30ecd2be181b233b23faf1e', 'no_robots_test:3a2e37c1fe2d7c63b55330af7098035b4dc8142da2ff249f35820cd06b458cea', 'no_robots_test:c97be73986b86b7bb444ba1402ece81e49a0e962be40a66a0021c293d0e48134', 'no_robots_test:371d8db9eaa9687270ad0fab91513225fa7ce1c54e5a0d845f126a7ae386e735', 'no_robots_test:2d0ff0f26fb8e8effcd4918c0653fcc0eee53226f4d13b79eee2fc03df6286aa', 'no_robots_test:ad3ade87b53d6f4adc940e6f4ba711e65b73e7d2fc4a2aa4e15c0b733b110b29', 'no_robots_test:716e64d1f2292720df26399fee0aaf5e015009178041a6ec8fedc17e2d9e9df6', 'no_robots_test:569e694f8ad2b83ae1e997fd4b19849b0859d23873a4147bb31e7873ed29e086', 'no_robots_test:3956cffb3efd15358c82ae59c24fdcbd58112173f6ff3f8c41888e6c4ed6c895', 'no_robots_test:11cb75d074a4a74b12c17ea021dfe17d72909661a28ca255e000d86573e52f4a', 'no_robots_test:7b69321f3a4e585a40ceba48e7b63685452a123e2cb64486ae5c54ffd3be0d23', 'no_robots_test:ede0754a2e1b91497d9e4db2320edbb495c071f190098537eee95929972e17d1', 'no_robots_test:66ada4a1b1b49410c7f8a6a27934b65139499a9c3e5c65549375068a70a3c51f', 'no_robots_test:02c4f02245b627721c8a03184b85e95b2d7a2a3e2757fcaa53a3f227785f0277', 'no_robots_test:2891116ede1751ddb26aaa9de499dc1149851f957873abcf2903132c62addab8', 'no_robots_test:dc009733b4090c99c626a0b657377e2c3db4dc065ca522659356d8be020a4bdd', 'no_robots_test:252b2127915bf0a3c04b2aa0e9cda42302f94b5feded11ae4d272b4d6d585c30', 'no_robots_test:757b00e4f2279890ebb97605a867e4309c29fce4ddfd2035ff568c7be0bb6b6d', 'no_robots_test:2ce87bfc5c427f720cb5f28f4099db60307f1ed844c4c8e61f1f046e06265fbd', 'no_robots_test:2526b13cafe55ba808ebe720cc2ebfce41f9e0a12b7512ffe6dbf7eb41a559c5', 'no_robots_test:4d0fa72d19e14c4e11a471ab3f0127fbaeee061a5ee6cc5ecf87142920bd0c24', 'no_robots_test:d04ddb39eff5469b4b4b6d090b51e6f46e47dc4daec06702964c1f737f7e8123', 'no_robots_test:525e28a56ceec00670ad602d6553ffdf08501e8a0ca7ea10027a2136bf135d54', 'no_robots_test:a1415ff2282982ef44abfbbecf0503e4d6f0ea6186824ae56e2d438fb3fca23b', 'no_robots_test:9ab2002a593fbbebdc2d4f4678bd21f8d4cd02cd15d65589c403319c8b5f4747', 'no_robots_test:45678c64b9b9861841bb742e8e05cc4c421d21c9bf4dcdf637a96e827c661830', 'no_robots_test:12751be5580238e093aab282dc8b994353b4c0643fae38656978e34fcab15b3e', 'no_robots_test:412c1c7294d8b1d07ab2e23cc6e748d4f9e3ab6628ae1df5ab42c56c7414531e', 'no_robots_test:a8395735b43fc5000483fbf3bb2662975b3ebe5bd83fad730c12cdf6404a41c1', 'no_robots_test:7be45ddf4361ed9d86fc499ee2d6aa4174d7c5aa6db5cd799eec4d789aa9c838', 'no_robots_test:b4ac421b07dd3cf8535f88666150b33d008b709eee6a0281f8b3d01d77e61b42', 'no_robots_test:4d4f7a00621e23c1ef1e1ca6970dda6157a4a7afb000de94fc94163a6406f48c', 'no_robots_test:c4c48bb83330aaf49d90f0673248fb903b29f16adad3efc331c17dd200202483', 'no_robots_test:8c2b9b8240c2ce74726a939bf4c485b9fc3e7868c2f0e48a6a8489659a92168e', 'no_robots_test:8c034a519e1533a7d544faf79099055f5b04c1207f6fbe265e4463dda40e0824', 'no_robots_test:2f9354b6c63a3e550fbab16210d0d38fad27dadba62d375b4f35722a0a46c887', 'no_robots_test:1af4443ea535d2f85009c7705db3081bfa675eda1ffcb4de92ac70102fe23448', 'no_robots_test:8e4228fe80ce2c4c988f5c0a8c60d9672e46566e4f6fe05315a2c5e1f09dc990', 'no_robots_test:b3a1e4ed83a6227f5050917a7059aa210538961b47c678f11fa33b2535467cf4', 'no_robots_test:6936a6d57488b9b79a55bd677f2c130f3c36ba2dc348747826d0f3a5cb5b7027', 'no_robots_test:a1d57c8b8a4d920e196c48e429468a951ee9125c447890b4d891ea3755f1dbd8', 'no_robots_test:21bf1e34609a84aa6f41b73a534567fba26b13d5025844ef1ed9851ff3c35eda', 'no_robots_test:c5bec6d10044644190ba466977bdab9375264adaae2d0c377ffa48410063fc80', 'no_robots_test:798b01c27b9d7d5719cf411a678312f9676dc3845c4b6d3e99744b5d80c4dd6f', 'no_robots_test:6ee94a135df17071b4b0c1f9e7f5ecddaaddd34b568a29642650c851a2def94c', 'no_robots_test:e0eec4940165bbe26d1f4fcf7801fbc2578618f78dd649ab5a1f97258f7ff742', 'no_robots_test:f39be8cff1abe33986b52a7e7aec5a1b8adf9552746697e972812e7babaf3b22', 'no_robots_test:b72a4b2add1b1711109547a75c5318b94db761dc3cd2c08e73e11cfe14469e96', 'no_robots_test:8e0ebb53a5dd1feafa657b34f39e15bfa8913e56f21d61542f7c1932da440426', 'no_robots_test:1ecc678e8184e4ef5150ad3a51b05a3d29fc3b2672e74ff0fb98cc7249ce5883', 'no_robots_test:703d0b37f6b9cc517692f8bcdec6988d82d20e9023b95c901225d206fcd7e5af', 'no_robots_test:eb4fee5c685b36bffcd84b2c68db01fe4842302c24190e144f391b7016bb2330', 'no_robots_test:7954bc81cf750c36c91d432a844a5f2ba689213263761bdebf866d28b3662f61', 'no_robots_test:4f25dfe951a9ee72613ab2e8021ffb4e09871143628991c5fb560e0a3f8a3c67', 'no_robots_test:b8c5dc22944151efd9e6642639973e1ca401e1a380fc0ff4d57a3b24a3173278', 'no_robots_test:979520d6745fc9319044c901dbee403a6dcf48d253e710fb6db78dada2bf712a', 'no_robots_test:47c6604c9b3b4e350ad5f546aa6f4748b59ef6275b4cc4ab99425518b2c7fd3f', 'no_robots_test:d29b4a6069a7d535d79c44dcaacbe6d6f30289086ce2ace4897202dce919811a', 'no_robots_test:f60bb67e4cb1d3dc680b634ea4bf50b3148231fb6e8cfea09aab9c0860eaf63e', 'no_robots_test:4cb56274ed302cc7e7bb9f57bb3d7fe43df6265c6e226cd9fb2f6fd8287eec3e', 'no_robots_test:86ad87691e5725d33d686118811d13876d192cf7525fb83c9e2434ee6d71be56', 'no_robots_test:08d888907bbbb7d371248e13dab35000d0d971f1bd16112e732546226f0802cd', 'no_robots_test:757ed7e67d03ef845a4dcb8b90666504e6bd4e14b2a3c5d954372e14ee5d9aec', 'no_robots_test:290e88a34d533c83aa725c61b56a3f01f0b55db15ba6b332c4432f14634a9fe0', 'no_robots_test:3d701bcf2811e91950d7766cdbd2660e2ee02be6825f8e5dbd569752cb7327b2', 'no_robots_test:bc90d0b2dd1afcddd8de7b2e7ff4d4c770018190ad63c0d1de27cd6c0c046979', 'no_robots_test:ef52784af72fdcb475ca17d2f444011bf89a4f73cba3627ef7a4a369a3dd39f4', 'no_robots_test:2e7da2610042433c41b02cad24401c5c0f83bee93ed07d6f5807f7883d252c45', 'no_robots_test:7f77538b92b924595ccd388f371d085841f926b3f436c964e0d94383ed97b780', 'no_robots_test:076473b02f7f76619fb48bedc3a6295a3be8333d87f67983f0f05dd6f95fa7a0', 'no_robots_test:7e8135ad15dc03710f78522d402a5b8d724706a1ba0445714a448e59a77c2ec9', 'no_robots_test:3391c058e714734b2a349e66d6708733ff35e49cb4d22a521ae0b692e21a76e6', 'no_robots_test:4bdf2305eb042d59d61126bd3018e2a216c7e46b98ba4d8be57f5ad86b82734c', 'no_robots_test:cc1646d3f0fd7b1a8ba246dae952929e522158f26e0524b6f40126b68b34ec8b', 'no_robots_test:0bfc23e86d05103d10342d234b31fe3613b93e7620e6c272b2687e08bfb9491e', 'no_robots_test:dad92f898cd3f957f6a61c8dbbd70cfb6a5aee938edfc0b54af4f8ebdef4bb3c', 'no_robots_test:51217435894e5a1bf8d0e87cfd74e24cbfff862a1f7a39d08596bfbe2c499d32', 'no_robots_test:f5cc15a138584ced005ec845f5a40212cd1e4c389aaadb5db442b61637320d19', 'no_robots_test:aef43863df74ba98f55bbf32bc780175e667b8af13b9308d6e54a35e1efb09bc', 'no_robots_test:d9b5aaf8fb1c656a71df74fc73f1ac3b5e5d63810f5556295f1292cfe00bb87d', 'no_robots_test:02ae13c831902dfa4f7aea6e89bb478d9a64e62c9cd1562334a614e35b62a483', 'no_robots_test:4ec9bf682c8a288c825f56766b2743be9d768c12368980d81715ec0a9a293dbd', 'no_robots_test:6c7f04a463f203983dcfc1b50cd819500d6d0e087c2e746c76714689567e19e7', 'no_robots_test:1fa6007d33362ffd33bb07cb575d3286ae410da730da8f4d6e523d84be1a2332', 'no_robots_test:f7dfc75f57c1c9022920cf1c26cb513280cb76c7d04d604ebdbd2ee95d04218c', 'no_robots_test:95ab39c44458ecc1e254c4d2194c59d86dd455c7dbdec58797b2fcac0f7df839', 'no_robots_test:d1c191631ff3e1bc89519fccf379faf48b2950d3960818b9d86fa7cbb36efb8b', 'no_robots_test:2880e6d3dc46901576c9ff3bc55a3a1a950a0e2bf8a32606c51282995b7e9364', 'no_robots_test:96a2891220d97cc3c1baca4ddf13121f17adbb908b72caf6e946e982d86fefe1', 'no_robots_test:068f53051dcc214ec91622949ac1d49db7d3c6eb0e885172fb93513e45d883e0', 'no_robots_test:5a6f31d9ba234bfecceee2b6db822077c30aa23d2dd40602fc94663bda4e1cd9', 'no_robots_test:2830c95d42887be796a6c5e0cc1de1d29619cc4f33ecf1f2e0fd7b7319b041e2', 'no_robots_test:4d06ff6439f54b7345b83b8bed2e689493104c9338efc5e21243ade63cabd1f7', 'no_robots_test:326a5c2c6bbd8459c6e1edf67b56da08d0bbe39d1ee02dcf7dcb13518b9d44d6', 'no_robots_test:a0cb5111b8e2d4fe6560ae67761862ab2e5608410668e0ea382bd68defff5d10', 'no_robots_test:f2fb01116f39477efc5e0e8ab47809920621d6c74e9a4a60ec9aa1c7c8201410', 'no_robots_test:2e24e4d095b5bb0dbcd738f61cb9a783c121ac44188937c846c800c4eca2fe60', 'no_robots_test:967305b1921daa495ef581fdc52997046809ecc01ed6ca818f4c52c085c3dd2c', 'no_robots_test:fd80e71474ab525762acf1d979f85ecb5a6fe83d34087d7baac7f108e31b4415', 'no_robots_test:c421a5055d01c12bf1ca46211b65dd34e67d5111d502cce455d1e3e10dcd1c48', 'no_robots_test:1789df91903365b9016e4015a62c0771379d0f6b1c12cde49c00deafd16e568b', 'no_robots_test:d097f9337d9beae903165700e60c8107fdd5f4dbdcdeb718ff5ab38bde15460b', 'no_robots_test:3b2803a605e122e0ab8e6626269ba570c29249d45ba58d7a54b63a7e0f97e5bc', 'no_robots_test:89e44a65181076ab721592e13a69c971d9f067eb21db9a11468ed41430dadd2d', 'no_robots_test:95c8a688253b51b33e956f0f62e143ba558a3494da559d8d35ea0ad544885ead', 'no_robots_test:9d5e4c39e16efdc6470e674ed1523697946b836509ad4965c47726cc8f6cb6df', 'no_robots_test:4d3216e0e9c5525fd3ff1b390fe9ddfe994eda332607d0fdb4986b19877dc6c0', 'no_robots_test:eaea0c1080796440180027b3ddca45c68eca17d3b2070f65b50ff67b6393352f', 'no_robots_test:213eb243af6ec6084438ae97c83acc1224eb51d005da0de0735b6eebbfa523c3', 'no_robots_test:45242f3a7707cd505500f1026ea4840d01c833047ca5b677ce90ae7e029dcbdc', 'no_robots_test:f119ab42649b334ed54181aa9d9e198678502b7f309a7f1b8021200ad43c7131', 'no_robots_test:ec0ab0abc0cd6b428980887f7fdb6fdc36eae28ed284b484af3007a36aede555', 'no_robots_test:da0c8826b1c9df28399772fbbbc00def6e24266ea4769395b086fb5212f858b4', 'no_robots_test:f17e86e400862b58a8f76248b6a0516ef3258bdbcc14e2bf04973c276cb80adf', 'no_robots_test:e8e0ae19872ede1c9e4f75e62a31cbd2008befe91b60b1efceec9d82a68068ee', 'no_robots_test:a8bf210a9bbec3800386a7c5c31d74e89eb4331209ff9707c6ab6af269ffcf11', 'no_robots_test:69d2b75a5774cf0cc7f61356d15f46ce5f7e847a6ae2fd7d80b844729ee66533', 'no_robots_test:f390cc2e8411ec903c73f3f4f63d319ff38697806fc2e2cc3a919ee9f4de7df9', 'no_robots_test:91c266537d1b7b14576858b3cffc0e0c64e067f25fc427b1ccd9f57deb3ab510', 'no_robots_test:9bb61f01d987accca140d9b7a08cf663da8c4647707509d0f849e1a6d4618845', 'no_robots_test:1b0d0852a3458d9e67d6aaee4a56ad43a02a5e06e0b7ce12d3f488768bffb453', 'no_robots_test:c35fbe35a264b1d4bb9266ce6d88abb1d932379dd81c1adc52db0f2e41f6777b', 'no_robots_test:601da7a0629ec217772580a3120ac9fc06a6df190ed10780e7da422cf7f9262a', 'no_robots_test:cc3cdef5cb453bcfea86564234a8d2bbd1c5ee3806098531fcaf2014f25705b1', 'no_robots_test:c1b58ea5e251db651f6ed3fc547f082837341e585d518ffe13b38f167216e57f', 'no_robots_test:85b235f4feda83914fdb0cbb3829ceb72a67a0cad5db3385cd00342dd5c5adc7', 'no_robots_test:f52d6383e3acbd487bdb7628e5e1f40615221a18987e99010a5a1ccd9f1d7cb0', 'no_robots_test:e6fd684789090b25ab723bbdd2fffc97cb47f20ddab417d0fc0571f848734469', 'no_robots_test:c4a9dd28310b012602050b7aebce6fc24ac6970da91c0606343724aa054f582a', 'no_robots_test:abd71530ee6e630d3ec7d965c754e672013f3e08785c888ae03a54545ca06aea', 'no_robots_test:6e2bfc6786ee24a14685bb3e2bff4e30c235573cce6a30e6a4f34648872945a3', 'no_robots_test:0bd65e73a8f7bcc45be8767197aa1d949f05a16c544f4979662418a20974fb95', 'no_robots_test:c5844637317399e7d5b233c18d7ac5cdbf35eb0c8828c5c9502a28c4702a7201', 'no_robots_test:51113c20a33637c45ffa7790adf858b82411041fd590a33eb7237a8dcc20f759', 'no_robots_test:ef8990846d162db707da43ce86ff6679aef342edf48271f8c56a6eaea6b757b2', 'no_robots_test:9205274fb686fc486f4bcdebb1db6ff5ba082910ec126fe4e7a45b7c4e326502', 'no_robots_test:12a51577fc8c8f57379974dff63caa82cfee85878af091db7e9ed8bef0c2dff7', 'no_robots_test:1e2f3bba465c89ee6540b3fcbe41b69530214abc3a22c91f3abd3b0268dce6f7', 'no_robots_test:59fd818054494e1765970af339112c6adf8fd23735c5d25d9737f96c3d0d915e', 'no_robots_test:3fd1549f3fbcf76e94f71ab625d154f0de522d1a7d8bd50f010c440921de6a93', 'no_robots_test:44ad24bcbe033d894271593fe623ca666021144e28ba110d46cd84435dba393d', 'no_robots_test:96e2f8ebd4953035715526d9a61b0d821619b54e49dca59e0a27ac38660c1f30', 'no_robots_test:e899cf5f0a16dfb8a99c24079edd1daf67e29471990a5dee209266b674594163', 'no_robots_test:da0b52f4093106f56b7404adbb8159a61bcc8cb7941f53c70323e5d874e8875e', 'no_robots_test:a2a9a52bff5d204d803b507d62782260485e0f99e39b462c864a9ced696daadb', 'no_robots_test:b4626c5a09a0e78cd163ede5e329c94dcf7af010b4cb657b5e90e35fccd548cd', 'no_robots_test:a711c95c8b8132371034deda9d96ebf86b4e3c7a6ad82fe08569725c74274079', 'no_robots_test:8380a993af2c8f279ac14e503846912dfbcde296077027b9f33743ae3c8e77e2', 'no_robots_test:ae7bbb65b9624d622a74937935bd701d475c1a178fe315de73b92e47ee9fd5f1', 'no_robots_test:fafd92407ddf89c0194177a60f58a38a1407d1c0dfa055df0367a7853ed134b9', 'no_robots_test:92dcd250215c49ee91f3bedffd13233cebc6883c582c00f9e5daa52ac0dd92b7', 'no_robots_test:04f4e8dcb7a85d3d2942a5b8a88dba98e688b47fb767d15e5d6a6580cf920dd1', 'no_robots_test:98256cd92ae4fa5dce574e0389c873fca0c1accc50ddb955b6a0159bca065620', 'no_robots_test:140c8928abacd14de28e471f9b72ba39b1fd28d49f2901fe084745f4d2278ee5', 'no_robots_test:2109bf5c5db973ca8ff4b138a9796e29e20be366383d585af45a84e05038ea39', 'no_robots_test:5f66fef6384c7a95e3778c9c5f46cadd6318ce1888d9e2044c9e38a59192dcca', 'no_robots_test:50402f52bfb645ff79958783d68aa9790de3615cb436dfe3ed8d46164a80bfd8', 'no_robots_test:cdeb6dcc295cafe0ed298573af3444ac8fe409ca6032f0f5a1c52cae717e3187', 'no_robots_test:1b2930d8d0408970b01f3d4522f10d8c1fe03a47ab6366f1d2370293ab74b326', 'no_robots_test:1bf1accc704426d12687e1ba37ca0bece147d542dbef4e9ed0d5c3abc9fadc03', 'no_robots_test:0b9b9d2cfbc490f3f45f1bf113df46f68e78ffe0689fe761740adb1e53f8b20c', 'no_robots_test:76532c9fd99ea816721df2cef8b59592f80eb658ee02f3392aefc00f34da245a', 'no_robots_test:5b77f923577ba1dd1c4a709eaf66597c54d52e7810be27543838e2f1314206f6', 'no_robots_test:9f2696fa31f6f52d177f0acde38b92505c990b9a2cb440af41bababe680ca217', 'no_robots_test:21d5e6f61e5d2258f80580d708ec4285fc824e07c92582b63b35988f019091e2', 'no_robots_test:e0d5085e39c268c69847de78014edf194ea0fc5c2868c14fe5059390b7cb9940', 'no_robots_test:bdfed4ee300d6bff796ae268f6f83bfaae10e71aa8ede3dde72554e7eaf79b55', 'no_robots_test:7d5dc53024c3085f99c8102e249b7da704ba08b65f33f99bed3327ca3726f72f', 'no_robots_test:63d767b55aa04b962cab270eee9e64b65aaf34af3aa9781167c228dd0e82f67c', 'no_robots_test:9329174e2ac800db587384bd62c32bf99604ad657176f524f83263251d20bca5', 'no_robots_test:7c4214e958ae2abd2be5d8b652d5915b494776dc94af3873d2d6c3344e851f62', 'no_robots_test:0dc3429898c88946ff7e6b1d33b8ba1ca2fe61216f700a9d88df16e14a6b7d8d', 'no_robots_test:5991d65bc74447559f555e0a808f886fb6645f3529656ddd63b8d087f2df7f27', 'no_robots_test:9beb41a989ac57f4fdc979d80b3b65eb99d25b97c9f664eb42bcaa16ccd74267', 'no_robots_test:aadb45cc8d2e48853f3e7d8f759532646d013559d46b7fc72c60042d3f154064', 'no_robots_test:4f5195b9648dfb0a57f64f53e6afc60e78c7b65a7620943ffd98947c9170d628', 'no_robots_test:8135293cb7bb33562aac0e08f4942f44ad7d7858ddbbcdda57ca83f234588846', 'no_robots_test:d1e66a5ced13c36d30989f5776239534594765d1bf8cf40144eed2e913e24d52', 'no_robots_test:a2cc15697d3bad72aa51063c3d8d42753ee59d965111cf28aecc97dded3d8376', 'no_robots_test:3410cd90f220004a96c7f8bfa1396589594d36100f6b48c632238fd97c25f051', 'no_robots_test:0512bb67304464c586c502af3dfc689a18a64da1493ac248b30782ceb219e103', 'no_robots_test:4b535a929ec12ec2fa17ee650e3339a558e495254049d037bd55d881614b7993', 'no_robots_test:dc1c6bf4a49f7ad4a1b65a21092307059639a4d54c70943c81f70ef5595acd00', 'no_robots_test:f02e1582f19aceb3804c56a778dbe12f55fe8a8904e555c8b8f5854b2d2e2490', 'no_robots_test:a45ba472e28e8ea090c83ab4d9d909c24591f06bfe9d7fa29b08eefc40fb486e', 'no_robots_test:cb0115b30980ef2c67f726ee3b246b1a9a48c862cc96e9d5d7f932465113df15', 'no_robots_test:21d96307542784354781725acfac689570738bbd4701d34d7fef620028a65ab3', 'no_robots_test:cf187936417f4e620db64edacc001a21ea66cad7ce1632b3b695834e59937c36', 'no_robots_test:ea03a22f943868af40ddde4838466261bc866a90f93ba57dc9762af5dd1d1f02', 'no_robots_test:b1d03bc76343f1fed66b69110f521554c64cf85be99e8465fb9d683e712dbf2e', 'no_robots_test:89b59d3fd692af01d07cffca31fa8206144455daef39e21834fa33fa717eccbd', 'no_robots_test:3f57eb796307f7079b4b17d5ad1b373027a3d8d6effafe8195d7f07c0c3adc7d', 'no_robots_test:5379c8e23f96ecbe07278583d4a1bf0cae261c8859f5eaf2fe71cd48dd372b19', 'no_robots_test:5d57c71c8eb4151b7882399a736fa1f76cee5b963bd81df6c71449843d6a3a78', 'no_robots_test:c1e734b7c9273ade357686249bef609292f02928f4d7e92aaf8e804903705dcf', 'no_robots_test:acaf6bbf25fd178fbcec73c0c442c059764b5fb6574737f115be96448f0a949e', 'no_robots_test:2bf1aaceb022d29d07b3592686801bc38669d7cc3b53a39a493b9fcbe341cba7', 'no_robots_test:def95674a89f7c0af7e5effafea662aea97fab147eceb9c26522faf022f9c5fe', 'no_robots_test:9aa4a72006d99dbfa3577a09727a94f45fe46287f36c6a57f05277c5ee7241ab', 'no_robots_test:1f3fc92dfd7a802a4522cb83047fce264d858342bdd1ba74a6f1ec4b70670436', 'no_robots_test:f027a06e3a6d9f8e7884505e882765afab994a7af76a45a17ff1ee2019b87935', 'no_robots_test:58ff17be13248eac49ee8819e0c0932a24aa86ce83bae6c5a81606790fba7b35', 'no_robots_test:d181278e1b38176c0969f3353fff5e6c420e04b575910d912fc520e607435836', 'no_robots_test:18c97df1c8de043206f91f144ab63cbaaff8daf413e985c89e707dd3fec96e01', 'no_robots_test:a8d7070f3b2eadd68ee04484aeee162965cfa87c8944030ddb201caa81afe852', 'no_robots_test:57518a6bceea3fd9ffa74011999efd87493f1c5db060a4aa769b9be7848af626', 'no_robots_test:87914ff0fe55338940f93023f9753fe82086fa3f6e8a9eda1a777acc015cf0ac', 'no_robots_test:7559d264f51a24cb19d4f5975adfd3311da418ff021a7b34b425ae468c2f3a03', 'no_robots_test:ac1507a57ad89bb7bc2bbc1c369c9b85a9e6eabd82d2fdb646a555dca07e8a8f', 'no_robots_test:5cdc678ca7768ca7b56af0acd0bd8beed33e962c09fae12c4593ad3fb4e7b686', 'no_robots_test:10d1712f547e45c910c0ace8c5df343bcfe60cb9674565c75f44c37c9ef27b4a', 'no_robots_test:f23f7cbd01c6c31d2cf42ab2a77ccd8990c2df24aae4f7fea9333c169b1ebef5', 'no_robots_test:62ad8ad2fb5e912a6a726ce97148ab183e00836f1f419cb36b40ce9b539f966b', 'no_robots_test:f1c772697dfaaeac06b48f38adb234478015161fa3ff747863ab1a4fa52546c5', 'no_robots_test:ac0d55915dbc688034a5fa10e0a0567a2e43baafed48b670e27a99a753d23c5d', 'no_robots_test:12aab43789e2f7d3146b3176b50852a78331f6ab86ec81f83cc16f5f33ea9ccc', 'no_robots_test:a47718eb12402f37e9fd94c2155173f37ff201f6e1023e1bec5fde1465a84024', 'no_robots_test:4ad5e260eba22fdeba20d6e656bdfbc9b3594bee49a1bb22a595b51cd96992af', 'no_robots_test:879a1ad0ecb760e10299434681ba0e095059acf521f96b016b7a3cde37bdb2b0', 'no_robots_test:8bb586e839cef9a28ef6fa93a819eaf4c00c71772ab77b6dd895ad053536a777', 'no_robots_test:df61fa815e8c0741d159d29c8942deabfeb19d84d7ebe78a5aa6ab18f9f0c1bb', 'no_robots_test:7b9040b1d3b6856c5515e7c3d8d835e9d842b146723068447b4f4ba797e89c32', 'no_robots_test:eed1bf7ddb070685755afefb800d9b3501a4d37c0dfb2dcff9b466f13e9a51b1', 'no_robots_test:c2c3159fafc7d47e194430e37ebe9e1b7f624fca4b0f713e8796b14482fbd1e6', 'no_robots_test:bd00fc3125a0b2024594521b7e88e01056379c60de1104cd3cd30b1d6b86018e', 'no_robots_test:bdf651db6af463bac2baaa81cd5531391ee680381ab3ec527827f266704f87be', 'no_robots_test:7a18aac879b7e987f2ac1e13262a9938bdcf98a10e9882b15432cb71c04b0e8c', 'no_robots_test:6353dab1d3388095c5fa4bdfe6cb081ed487aa771b0295c592712ff348594cb1', 'no_robots_test:bc3916b72a42f1e5762f0b6ec42187c26c4be4e1bdfc91ee538d2ca24a88e4d1', 'no_robots_test:ad428e8ceee2a71a99099898cdc3502664f5ceff3546b24068980c1002fe61d1', 'no_robots_test:73421e0bdb4bfeb54712175074ae883bda34be646e072d60c9ff7680629b1e72', 'no_robots_test:99c31abd504316002052b5a4599e5ca23850b258e7712e71910e06f9a8f8ddca', 'no_robots_test:edcbfaa28a53505efeb660324de996f5f87064f05f82c00a430b4bf693563e24', 'no_robots_test:4d5a125c091b1330ad20f9c6266cef55a59d453c7faadc3f75b7f310d118f580', 'no_robots_test:711dbf4713654879d2ed546e27e1758c4c41508cadf57b17f7098ec8d9cb4d32', 'no_robots_test:1d206f2103e90eac0254aa1d3274e9b01645c4a4ba106d87dfe15c1f1e034965', 'no_robots_test:27af0d850d8bd239b4d44d381f524807db5aad1e39b1a652b58fbfc63a766892', 'no_robots_test:a2acba4442cc04a98acb1e4ec53cd5677d85e55f0e539f3346597bf85f07d694', 'no_robots_test:2d91dcc129303876668ca3ebd2082ad0fb4ce76ae99951d801f94e95a7a60404', 'no_robots_test:2065b3c57f02d3e7fb4e531ee740a7abd4715d4c4bf462f910f7d07f8ed49c7b', 'no_robots_test:163bae12e8c1649f03d00c75f1f14392d3a165a705e130e2c8c2ef8072900298', 'no_robots_test:627f3274d200d6ebff294410bddd5bdd289e739ab0eec10e2f12b86e9ba1d2c2', 'no_robots_test:6da2d4509f61ee54c1e1517dbd90130732b33323b86eb203bd802506eef0f6f5', 'no_robots_test:f0bfe3f8637787f7feade76b0b4542f98eaa7a6979db99717babbe6d773e2dc8', 'no_robots_test:aa7f0e5cdfb6901d2d90d3e7208e66ef152eb4c375d6ca49f11c8595426fb5fa', 'no_robots_test:359c18b053c7ee99c28aaef1489af3e7fdec5696b9c396819469c0fae0abac37', 'no_robots_test:292ac83dea709c12c9fac33c85cd40881cc9bcf5ed4afdbfd63debfd61077bf6', 'no_robots_test:0613f4755ddc2493e8e837f455e836df25da9bfa3ff7af7b3730a27b6f5e6b45', 'no_robots_test:49432f201791c5d2f041d3a9f15fbe8f040e2ee6c3538e3681828d966db63c97', 'no_robots_test:a3bb1debb936705b1ef7521ef1e9c15e800b67be60014884374f9b5036de27c0', 'no_robots_test:e20eeb892f54c4810c7d93f54778f1d76df20c699cc7bc3df0c25e283a595a83', 'no_robots_test:489ec38b91c95df5035c1d889c2a32ed40ca97fa306732d72589217906a120a2', 'no_robots_test:d1510c80a8ab1d3336f8a94e68efeda4ac4e0c72357b810ff368b0625a7278dd', 'no_robots_test:376025d76297c587ce811b6f6d21599fbb25cf1af8dc4ed92e18aecbbcc40fe3', 'no_robots_test:ebca3e652be5cfb23f84fa73480f2f853fd04daa2fdb50575ead2a53b146d443', 'no_robots_test:38aa0c7bb0970bf91add7d33abdfe187e34a094b55fc66d2a4536c3edccc5a23', 'no_robots_test:3c75021b544b5c17b1bc159a46bf68c84f3c3f6985a3a45e0534c42dede8ed30', 'no_robots_test:a74836ebd3c90c383a4008391560ec957dfa0b5da9e29f37cbcb25aa03162300', 'no_robots_test:ed7b90363e2b3e866e549e4cad67bfbe47b984f6d424dfc5c6ef43bcbc744545', 'no_robots_test:59b4cee67aabb257050e24350386b215c61af9a4e00bf1b6044bedd14ab864f8', 'no_robots_test:7bc58574708b8a53410195e1d914dc5a86428b8cc02a383a0f47ddb0c211064c', 'no_robots_test:17b62a7ecf91cae6ab14f5504d18da30b44396a30219e2b824a59607e58053a5', 'no_robots_test:832d80a522ed3d18ad84965c457e919336a091b5b525f105cedc909a1a6b42c7', 'no_robots_test:1ab776c45860a736c7a65b2070dc7d57a58f64ecccffd8c5e0b5220163d129b2', 'no_robots_test:0dde5c58440c2832f06ee8b7bdbb39e7eb7e703d3722d3903e37972b98f758d6', 'no_robots_test:dbbe795ab6edb4b0b00d7dc488041c666a0050c0630291a71ac00a77311013e9', 'no_robots_test:0b8225dc73fa4c390080ebee2a1f6c1aefda82980c02ade6aabe003b2a607778', 'no_robots_test:4402a30e69c901a660fb7000be2a91ae4fb85d240762156b252fbbaebfcb35c4', 'no_robots_test:190800e5fe6ec8102868c2a20fe72c3bcce3d47b09e9ce6f89378df9d69d8a55', 'no_robots_test:2933db9a81070f5a3a907dddc7bfb53954204e9ce6accdbe16fa8236e73702bd', 'no_robots_test:9b99f22ca3ad129385462592c43ee852b5bc1b143116c69f4a498cc2716b2f37', 'no_robots_test:f15bf5f600fde612c62aac19aacc96fec9d5492ea20cd882fcf438f7da528fdc', 'no_robots_test:3c75dd3b9c443c578595c6e6254bab4a402af66ae303c3adcd7d7b0d12fe356f', 'no_robots_test:6977eba7eabf93213bdb09bbd79c76d48d40f5495b61e60cac9d7251107dd65e', 'no_robots_test:2e174209ec79d2c77551ad995f0793a105c2a276aba6e540a734b46c376b95ac', 'no_robots_test:dc9914ebb51f869a655d2c711c3026c5a946e7f5a5f0c4207e5e59996f28fc3a', 'no_robots_test:6c6e51c01ed43bf768cd647ee633051ba964018ba50398b94778a6336d79cc7d', 'no_robots_test:8e459a433eee96c1489749574fdb1251cf6160e0867970d21b57f8a0c07bcd5b', 'no_robots_test:396b9869a1bcf5dc03b28b5b7d9beca4bcba0e336601de2c72d753a5581c0e7e', 'no_robots_test:ba3186534d194b706f2fafd73ffeba8eaf369eb1b8bc7cd5735f6b832eb63345', 'no_robots_test:8ca28b279177640a66bba4418407eaac428b4b9929be2621053e528c4787d678', 'no_robots_test:0d085a2a920a21efe14671cf9783a18cedbf443a371982632b2daf77b745e63c', 'no_robots_test:0aff4c8b522ebeeb637127bcc660272fc3be476548731845e0a98d0d7252c6a8', 'no_robots_test:034aeca97edb0026c8f6b28015f96f80e64ed2185e47ca5953bb3558544bf677', 'no_robots_test:8e748b973a0f9ca774a7fafc2cfb916b4b3fff17f2aa52dbdc4efd99a78a0f42', 'no_robots_test:9620fd7c9182bde749653ef79cfadcfbb0114013d649300cb1137c70fbbbf2aa', 'no_robots_test:7e5c5cd4c0281d3379244965dc6614199c6da3e959135a65dc64b8fe9bfbe3c6', 'no_robots_test:e8d7adc6514830d95bd6d2eefdab4c5f4ab86135aa4f6fb94c57f45965d8bf44', 'no_robots_test:04a42213adc94ff11ab0c8f2b9d3c1b6a09ab88a018ff2674ac46cc776245585', 'no_robots_test:43e34875cd8505e545ce6578bacc3f0a0731d1871f829dedb3ebcfedbc125ab3', 'no_robots_test:079e49e7313d18925ddc6d79ee2bfdaa6efe110fd5e5154d68eb30a3aeb303ce', 'no_robots_test:b1538637e504a357ff8f6187d26c774dabf66c820133e7386de0ef4b9939a9ff', 'no_robots_test:9637d09548e7cfb3a2254681d76b906f6736834dc7bb56bc30d30e3ef122ff92', 'no_robots_test:4e780fcb9b95852d4003a3125728cd59ac9eaa361574de7b424e834429b2f94b', 'no_robots_test:ebe773c8ce5b980e8534de968460abea42946f338700cab3952e745f1edf34c1', 'no_robots_test:f40b5870f2b4637108f9e0e624e635b87b8a481c570e561213cfb83997c71fcf', 'no_robots_test:a457eaad92c901bfa6b421dbca85a0187a55a0c1d3db5c3190118b0f9762840e', 'no_robots_test:4a35736bd4adcf4f2738d714126f7e1ee631b270854f5f9caf763ee6b0b914ed', 'no_robots_test:ff458369e71a6c78f6c963ef11c04a41df465ef908baa09bc39c2fd608ebb047', 'no_robots_test:6d04c2f474c12831ca516bc6b570f14380577896c9430fc0f50c5189b50a61c7', 'no_robots_test:4fda661d52da94ab5575570229f0fcfbc5d07d86da03f3c689a44bbc7e9183ff', 'no_robots_test:7d1a1e1b267ad0722a86ca4fad6ddbebd51176842040b291e0008de019ce5379', 'no_robots_test:24e9ac536dfc2c36b548475cbfdc400ae21c9b5566d6152a3d126f52b43fee25', 'no_robots_test:02f3e506860f9c0a76c25e040d4ab0104d61bf6759c0aa85ad31ee64bf721eb1', 'no_robots_test:c79fdcbd3dfb18027a63eded6f242968c518642e7862334f825cadbe2007f1d1', 'no_robots_test:0e414e0a370e42b00e9e292c176ab1216c7a51b8347c465e2be9d8e10f44af3b', 'no_robots_test:e9c46210587c0ce455a20422f65d5471275eb38dc4b6db98fd2144bcff13ae72', 'no_robots_test:3f7aa67c5e926f3901db8fbaf16761392bd403ef426125b223631ec3b2517ac8', 'no_robots_test:a6deacccb8af5a3a0ea0346c92c9370bdd52ac9227fe360ac5596c76d1bbbd8c', 'no_robots_test:e825b5cbbaba4c14f72a0856896dd5b523a871ab2b9f2dcd15d776a2b4aabfa4', 'no_robots_test:2bbd6906c056a90062a8ae36294c8d919482503c574113afdc86f13f14fd837b', 'no_robots_test:072f282c80b080141098970c3b463d29c5aae2f69ddd2dac7455badcfc5a89c3', 'no_robots_test:244ecb6b0826574c23d978c03ca05300669ceecf65734363fe097610a6ca25bc', 'no_robots_test:e507dd4c9d1df15f476426251e5a1d650a207b6a5584f7bd4744f0903093600e', 'no_robots_test:2b3cdffb047fc350416d9b20e25c4e70590df1c3c868ffdd44fa545ce0d67610', 'no_robots_test:4c949fbda37ddfda58554ff73a2e224deed8df66695c36a40f8a2d4a134cb9e3', 'no_robots_test:6d6dfc83c69f55a856b1e0b758eaddf68b5543e14cb2ae617743a0d4881824e8', 'no_robots_test:9cc02849ca26fe5b9121d46077bb34eff04fb3e2ea2f82305367c9154d1237b7', 'no_robots_test:2153e9b17536a047acf8a0614c91ab45c9450839e4b2c7660ab25251c173e1c3', 'no_robots_test:8dc045dcc46374809265fe389a46803a26afafe333fa77dc70a1f8c3acdc3963', 'no_robots_test:288e444047682b25ddb5ff63898e6a0d48cb1de3c6c06a65261f8bdb60931468', 'no_robots_test:1905bb8ba7ffff2cff8875d6ddb7a2d85c4fd48873bcfef5c4f71670fa118b68', 'no_robots_test:042108b7bf148d0831e5665ce92715f156541ee00c56b0adbd330b4cd63dcd99', 'no_robots_test:3715688d26cc3544beca7d717c5c663cf2a05625d9ae13d1fdb39cf508f77446', 'no_robots_test:dab34dff6549458647c89e02da31b00b2339599ede1deb6799587b4bd0209106', 'no_robots_test:ee1bf2cb4729ec1e998907fd521b642b8fa17f54dcd3c4ecfd61994b3935b289', 'no_robots_test:e3d7cc21f696e9727960b47df92da81cd681c36ee389272b24cb82839f66d9b8', 'no_robots_test:79cedc57b4ca1fb97ea15691a996378a147499a6e1de0b0e50d9c4c7caf96ea2', 'no_robots_test:d95f75bba38b5fb8923367b6c8149cae81ba5d31e76f960e55db774d641f3ae9', 'no_robots_test:1f1c25dd4f795b151f180ab18467385fd533988876fb5303fb5bb3459e35c23a', 'no_robots_test:09d47615e1590057bac2dc5ce27d3ff90f20db6b531672e5ad57699382a0da08', 'no_robots_test:a6416ec59f8e7fe9867476cbb4f5f44bfdd6e962fce1bb00814a141cb3780234', 'no_robots_test:e2caa2ddf7d8e2f8b2c23d288d2b6efc376a4e823ffe09a8af191a44659a4b7b', 'no_robots_test:a1f930ab77dda26f05c58851efc4c27dbc6e180ec529c04a8ed40e43cd8d0304', 'no_robots_test:c721adad90dcd07ebbf863bbbd0c4912f833fab99ac96db9f1d5f833c51eb896', 'no_robots_test:9aec927595bd10316b1df8dcc0df499655280e584a0576047e056f1cb4366d9c', 'no_robots_test:3efd76547ebd59f65357d2040a3b63b92ada7655b9d2c4de25872503038cb13e', 'no_robots_test:3cf7583809cc9110e00c65652f69c9235ecb294741c261595eb4ef71d9fd537c', 'no_robots_test:1b8ef3dce83ad90f2c1a18eb70b97ec2cbc3c25663448c05014503d1a4fd3ed5', 'no_robots_test:c4eace49f52ea1066fe19654a8d625211ec377ad9901c86888dc5ad4be6fdcee', 'no_robots_test:0907eb27ebbf46386b02ca9314935c115cdbdd8382c6370817438e4fc2097819', 'no_robots_test:fb551f033bfede2b3cd283a2628bb5c46f4dfb47a97e6f477b5288d358ad4b72', 'no_robots_test:95b5066b66039db0dbb8ab6788922e68fde8517e20552c6cda3fc0e3499d316a', 'no_robots_test:c27801ad6b5ebadf46dd97da83476952a72b99495ebc85677516437e49c09fbf', 'no_robots_test:e31053f7b489a3ba30b1011663175d1a13fc350b94840af286aea356c829599e', 'no_robots_test:a88b3d44f1598abfb32011ef71e859618a69c60e54d77ac0477a29d649036625', 'no_robots_test:a210dfc781291b83f2b82a299e82c61d90617500e34395c42a53220b22fb32b0', 'no_robots_test:756d31fa74b296203c9450a5ded21a07492f0f99caf7c982abf61a93a9c3ec56', 'no_robots_test:470dce010416538f33aaeb18822ccbdf5f5e1da5749326a11100cab5b54f44db', 'no_robots_test:d9f074817f0647ebb6d9d6a879598fc4394ae7c63b56cc55a147a2b8ef27aa27', 'no_robots_test:fdcc2616f33ae53e0f3121b5cf7cc998b31a8657f3581552a2646c28702f302b', 'no_robots_test:9a9300da4935003f03f16f85b9697b58b533353f121a8be641e1c46aaea3d6f3', 'no_robots_test:93f3c8cc7dece34fdca51a61199b09bd96d8a2d0d5526bae764c07a97602a921', 'no_robots_test:0b93de1a6ea093a5807b24dd5c14f32a952d548e14cdbc92d20d5cbc831546b8', 'no_robots_test:36674ceea31c0eefa67d12528bf92ddd91263cfb12fbe08bcd2631a52dd61188', 'no_robots_test:e266e32ac7319880ff40641c9ea49f61154ce74ce396876cc973d70708946f7d', 'no_robots_test:a1521cb0aa1aa83ec0dc5e3a52234a27e14576e75751b4704480ebd16ac6e396', 'no_robots_test:a794f05f5d6687b8a2e78d904a89209812a47276ad51ed1405043d45b1500cab', 'no_robots_test:27d5c23de1b1d5746a570fcb287b947bf3abec3a5a2948cb081f8daf5c285b6b', 'no_robots_test:9f63c208fe95b14e13899e0207f0d42a9a816b8674a3892c3c8de74b07b70c7d', 'no_robots_test:04795cf6ec37a7dd935c1de66d84d8ac0d764cdf12fac297d129f48dcfaa8d79', 'no_robots_test:afd6af67cc1816d99f86b3e059ab2e77aea944c07b1838c27e6eef57a1400985', 'no_robots_test:cbec88e3309b7648c023d9e2114e2d7595cc9aa18067c25391252004042c8eb9', 'no_robots_test:5a0a73e9962d364ed3eeb4d132f2499e7047e2272808600a290a2fdab270f074', 'no_robots_test:f74746e22e3b69428e9f6bc6ea0561480c8f0ed4bd977656197db9521368fee8', 'no_robots_test:e0b1ce063570abea18f6ed8dbeadb06d796c243f7e6a2a1f49379e74384d5ba6', 'no_robots_test:66b6335c0c576b405ed1668e632edbedd0eb09146dd4e4d84aca2b6043511aea', 'no_robots_test:079c5a5713af4f78a53df64e7b0464359e30f5fedcfa1fee25cc46b177c44367', 'no_robots_test:d436fce6076f3110e1b20da47f43d8fd0e643a43d36af478ed325f1061eddc79', 'no_robots_test:da13290dda7f6ac430bdd317de487a6f9fa79e1b0ce8b353f948980a519cf952', 'no_robots_test:f044562dab2d66d59ffa187a93db0a4d4eef2217a7c143f944312254e82913cc', 'no_robots_test:940e3ea02beb3b61613794d1b427bf37f30078633244e2a2d3a3a17a169d2350', 'no_robots_test:749dd218364d72a3c4022bc6665491204d016ba8717793b88665219a4b4d9c70', 'no_robots_test:e10eb2e3fd3cbcbc45858578621b9b4e64aca3dd8f3b0ad39a472fa3c490f660', 'no_robots_test:36e1d930e74392cca2528fe06bd8f0d38befdde3c3781b8922041dd688d55235', 'no_robots_test:ecdb34794b24ea6e65ac66a1700160f4864589bb77a5def4591fe996701cb06e', 'no_robots_test:47e591d09b7363112580b3eefe8ed4da5f274dccd3619a2704027db79f941198', 'no_robots_test:f68dd2578ad9dfebdec7bcd8caae2e5d4459159dcfbce130fb6ee6902c18b836', 'no_robots_test:c2abe99df0a43a558ebb63151afd3f8a96f884b33495437b5917b0d6099fd599', 'no_robots_test:3ab7f8ff8f4372b640737a33505112b854b4d6bc35d9e87a4cf73ca9dbbe2f14', 'no_robots_test:1045319c37d98f4f7462681fc50423762cafeb00bd2925484b3d429718e8ff8c', 'no_robots_test:9d3f9dc6ca94a0bdba137665cb1d8d9e4b76d78fdd9a79e7e4ac963bda7e0f38', 'no_robots_test:d8e91a51b7e31c9367cb2bfc5f4418870271355df0d3048599ed2f1d61bac77f', 'no_robots_test:5a911dae756fdfd96b80d4406b261fe658cf900bf6ea2281c59b2e87df796a24', 'no_robots_test:070995ef4c7e899b073a6b1e03a1c0a91d8f6e2917b867ebf75bce02027b2653', 'no_robots_test:51e7e7e69771e152110bd3673461509ee7e0c513dcf590703f6d587bb65ed706', 'no_robots_test:4377ce8bd0f44aa7114983c2d48b23862106b0f247b9199a0ab9926f50dfd80b', 'no_robots_test:4969e6d2e7da9be81ccbbdb18b575ba0b363066b5365ca134b59285bf5c6afd3', 'no_robots_test:2f4b66e0168b2cf7e7c260d3f3b7a18df48f4984fdae0a895561c6a01fd77c88', 'no_robots_test:dc306933ec2a6f7ee590c6de309bbdad91d0f668aca834db27cdc4ecfb5ac7d8', 'no_robots_test:3232792c0b1f58bb36128a00bbe8a2abdf24fddac8c92ba386018ebe34756dae', 'no_robots_test:5ee45f9ebff4e75410b1128889f9d0ca7556b223e69df33334075761d1c7a57e', 'no_robots_test:f6c76517ce8ed01ce548ea7c86ffc53a5fe7afe7984a166755b5e35eeb99099c', 'no_robots_test:57a499002a099639b52fb3dfdf516feb745c14457182340aebbb3546de7eec77', 'no_robots_test:1c5db2224424da86a908bfc9f21425d8669300e88205241d97d0c7a9b4324a6a', 'no_robots_test:2ace06c7fd726671319de8192f3fe5480f5297faab8f09753c1cfe7d6df294fd', 'no_robots_test:a3b22afe88af8a1377646606f9f4df393ac0bc931a643220a32095285895de97', 'no_robots_test:86c835efe40d8ef93ca1608e77a2268143da853d0f60a714e1284fe606e6b4df', 'no_robots_test:0e43302941845c64fb7ba5fca1ef39612a906c9fc81c3fb7753ff7ba3b30687d', 'no_robots_test:d63dd41a84b46571478cb5a4903d5efce1b77515b3e3e5acee602f4a56d0783a', 'no_robots_test:07727af96427cfb80e78aba4d505f97dde11e3c5969f44fe5664b45e8b4e7df7', 'no_robots_test:d0aede9a69080a3131f709faa0ec3d99aecd603e981414ee70d2df4d39bea02d', 'no_robots_test:0ca28e9e453502956ead1128cec5019004c58e33cba5929f5301f3763428216c', 'no_robots_test:764691c4fe0c71bcacf5e05c3b4a120547e80d8c365e6edeefa6a40298f04faa', 'no_robots_test:c221a1f994cff9c2f34b9aa9e41a55163172ddae96767c1d20c1965b48080017', 'no_robots_test:4ac2c6de8b0e256bde22bd47ede3e8ce6b1c3df1b1e2dd0e3eb286e2bb325bef', 'no_robots_test:6a07c07c04281930a7048bda680a6241c65710437584d777401158b0c57554c8', 'no_robots_test:c6c5baccf1fd2a97d0043db12d7d33d85377a8a924e43eee946b3bc18ed8ebb1', 'no_robots_test:50afd036b32ea68be44204ffab02e3f5cb85068de3d905b820844c09b77e17a5', 'no_robots_test:7d8b08737912472872ed2932afe7af99bc72e16457a76b9f91f6b6e376284f24', 'no_robots_test:585e892fa64acb013514af77c36f63c776983e5cfef4563790464fc6cfdfbfde', 'no_robots_test:690738484383e06723019f31ae210f7306246191c01c3d5a09c4f665b7624f1f', 'no_robots_test:4464c320e01db719e51909b974243edc0e7b45f08cc6b30d4d31ac6f13f2e67c', 'no_robots_test:700bc710519bc0de70046303a32891ac5542679ef6ca1030f3bbc8bfefdc2a17', 'no_robots_test:8b6453aa02539744c0b316eb03e2d64aa90369280a65da600f6c391472b94963', 'no_robots_test:3e0a50a9d76572aed087981deeb71f851ea0e9ce59ef7a79dd5b14ac82c38c84', 'no_robots_test:6367ce45caa5d0f0b1acb41b2f53e424f993478d1466f4448a4a97dc495a7222', 'no_robots_test:e473b2438fd9d0a06a40ad46f9a3ffeccd8d0ad4e5749b9d1ccba0eeac5a3025', 'no_robots_test:40995aedb42a2ce8a74fdc801dc7a3c7a4e50206d0820dfaa35b47f5bb76bf9a', 'no_robots_test:c0e4991c7c924b78a5cff690c322f7cdd0e82062b55130fb63c19f2b4da79188', 'no_robots_test:45c8c3c63e02bf5ed5c99b208cdf423a53371f41e59d852c2678ee637aea8ba5', 'no_robots_test:ed6df8fada20e3613a2ee2142eb619726f7389f0b6464480a37e7f675dacf148', 'no_robots_test:76aee18285d18dabcec5cb59f7aa2a0190bbdb0a4f64eb6a4db95976e8d227ca', 'no_robots_test:62829e5b79946e964e3a04465f37d7f8d3d702e2fa342dbf7fbe4441aa05ff23', 'no_robots_test:c14c3c4b63794c8b534c6a60fa3338b1cadc10b24bf8ef69bdb04854b5224333', 'no_robots_test:9ea362fd9c2b04083756e2c03b02b4d5d334826313b7c36eb45f922068ccdb80', 'no_robots_test:446c0186eeb24e8a43d0ab7dd13d314a20e86b3523aa23dc1d8e68422e7b7cce', 'no_robots_test:489c7abb740ed0b9bb6bc704595edf4c94f1f9f4ac797ff1d6f55d8ea956d8e6', 'no_robots_test:002ab8b85a36e6c5464c96594c1046aaad0832b2b7ba59b7c60f8d5bf1839d14', 'no_robots_test:73d6f61d9fc2261b5ff4fc6a130ce46e5f759fdd82536f4458150cc9abe67453', 'no_robots_test:f3f094b2aaa7c46b1dc50d4975a008bd30230089ebefafa9724184be73f84d17', 'no_robots_test:c70281f8e81ec2249e2b6ec296b0d5158860523a83a3d6ece0c11d534f24fc3d', 'no_robots_test:23b988274475e59d97dfeaf717327a13d9e3d4df2e73c30cbbca59c1ea842860', 'no_robots_test:9283abbe02ec6e09f3ce2719b02aa2b1dc2f887425a2d5144f923403fb9b54db', 'no_robots_test:a08e2b36113e5d71feb47d60494b84029dec93aab7e1ad658b433eebff8e0ba3', 'no_robots_test:3f02ff68fb4cacef7ce3877c019b13187ab2739d5dd1a82f850852a67025a9b1', 'no_robots_test:0335e3ebae248cd378edc4479b1f7a885172da22e70da830aeaf9622978feec4', 'no_robots_test:02697bcf2ecb738e9532ddba8b7079aa21d8bb9744456dcde524871c3eb728f8', 'no_robots_test:5b34963157310ae9936fd14ff22daa343a9529b3c193544d754eea0a73e5760e', 'no_robots_test:12fe37ce674a2f79d7f2f36211393d9d9d4b97d1a431be0b27000b64a5bb16cd', 'no_robots_test:0c30072a27e82c8fc2f6009a0d08214fb1552c42b1917aa9acbcfe3d1c5d9e91', 'no_robots_test:0d24b407ea10dd9173e8fbb377609559e820302a1bc8ea15f42b5c0356266a1b', 'no_robots_test:602272a99566bf68a5b48979478bceb0b56f74915925ed8a1b0a558935df3584', 'no_robots_test:ecdac8f179582eb850ec28155ea59279e445c219d7bcccc6753cef24a7199a42', 'no_robots_test:46b880155fdd947f395a3009a313bf8cbfe8e137c37b3a614c49585112e0aa0f', 'no_robots_test:65b835d2335e23cf908b10817be1eb5c1bd5dcd3b80bd3e7a46c72d2cd479e8d', 'no_robots_test:48363ab6108604ad6812a9dbe0f17fc52dc68532d3b3bf4d83bfadcea7b99f9a']}}}, 'scores': [{'arm': 'baseline', 'seed': 0, 'metric': 'no_robots_test_token_mean_nll_at_step_100', 'value': 2.0330268793696935, 'evaluator_id': 'a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744', 'predictions_ref': 'predictions-confirm-test.jsonl'}, {'arm': 'treatment', 'seed': 0, 'metric': 'no_robots_test_token_mean_nll_at_step_100', 'value': 2.0323170273395057, 'evaluator_id': 'a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744', 'predictions_ref': 'predictions-confirm-test.jsonl'}, {'arm': 'baseline', 'seed': 1, 'metric': 'no_robots_test_token_mean_nll_at_step_100', 'value': 2.0315072699517907, 'evaluator_id': 'a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744', 'predictions_ref': 'predictions-confirm-test.jsonl'}, {'arm': 'treatment', 'seed': 1, 'metric': 'no_robots_test_token_mean_nll_at_step_100', 'value': 2.0304049240877835, 'evaluator_id': 'a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744', 'predictions_ref': 'predictions-confirm-test.jsonl'}, {'arm': 'baseline', 'seed': 2, 'metric': 'no_robots_test_token_mean_nll_at_step_100', 'value': 2.030763545006581, 'evaluator_id': 'a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744', 'predictions_ref': 'predictions-confirm-test.jsonl'}, {'arm': 'treatment', 'seed': 2, 'metric': 'no_robots_test_token_mean_nll_at_step_100', 'value': 2.030674625589407, 'evaluator_id': 'a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744', 'predictions_ref': 'predictions-confirm-test.jsonl'}], 'comparisons': [{'metric': 'no_robots_test_token_mean_nll_at_step_100', 'arms': ['baseline', 'treatment']}]}
evaluator_validation
{'status': 'comparable', 'issues': [], 'comparisons': [{'metric': 'no_robots_test_token_mean_nll_at_step_100', 'status': 'comparable', 'arms': ['baseline', 'treatment'], 'evaluator_ids': ['a4a7f46a521c63887b23a3366c4f5246f66c98d26fe8bdeea93b6303b1555744'], 'missing_arms': []}]}
feasibility
{'status': 'unknown', 'problems': ['Re-projection required: lora_rank changed or was not recorded', 'Re-projection required: dataset changed or was not recorded', 'Re-projection required: steps changed or was not recorded', 'Re-projection required: n_examples changed or was not recorded', 'Re-projection required: n_eval changed or was not recorded', 'Representative evaluation timing not recorded', 'Representative setup timing not recorded', 'Representative training timing not recorded', 'Unknown timing phase: setup_pilot', 'Unknown timing phase: training_pilot', 'Unknown timing phase: heldout_eval_pilot', 'Unknown timing phase: setup_selection', 'Unknown timing phase: training_selection', 'Unknown timing phase: heldout_eval_selection', 'Unknown timing phase: setup_confirmation', 'Unknown timing phase: training_confirmation', 'Unknown timing phase: heldout_eval_confirmation'], 'wall_seconds': None, 'gpu_hours': None, 'known_gpu_hours': 1.3603800910049015, 'phases': {'recovery': {'wall_seconds': 4897.368327617645, 'gpu_hours': 1.3603800910049015}}, 'generation_counts': None, 'generation_applicability': {'check': 'generation_audit', 'status': 'not_applicable', 'enforce': False, 'reasons': ['spec.generation_audit opts out and no feature it covers is true'], 'features': {'generated_training_data': False}}, 'record': {'config': {'base_model': 'Qwen/Qwen3.5-2B', 'arms': 12, 'selection_steps': 40, 'confirmation_steps': 100, 'batch_size': 32, 'max_seq_len': 2048, 'n_eval_validation': 500, 'n_eval_test': 500, 'n_ifeval_secondary': 541, 'planned_arm_steps': 840}, 'effective_config': {'base_model': 'Qwen/Qwen3.5-2B', 'arms': 12, 'selection_steps': 40, 'confirmation_steps': 100, 'batch_size': 32, 'max_seq_len': 2048, 'n_eval_validation': 500, 'n_eval_test': 500, 'n_ifeval_secondary': 0, 'planned_arm_steps': 840, 'pilot_arms': 2, 'pilot_steps': 10, 'note': 'IFEval dropped (downsizing step 1); LR grid, selection steps, seeds, test NLL unchanged'}, 'primary_endpoint': 'no_robots_test_token_mean_nll_at_step_100', 'source': 'pilot_log.jsonl (10-step 2-arm representative pilot); select_log.jsonl and confirm_log.jsonl measured', 'measurements': {'setup_pilot': {'seconds': 252.8196606636047, 'units': 2, 'planned_units': 2, 'samples': 2, 'gpu_count': 1, 'allocation_source': 'fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)'}, 'training_pilot': {'seconds': 161.3649604320526, 'units': 20, 'planned_units': 20, 'samples': 640, 'gpu_count': 1, 'allocation_source': 'fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)'}, 'heldout_eval_pilot': {'seconds': 80.4703094959259, 'units': 1000, 'planned_units': 1000, 'samples': 1000, 'gpu_count': 1, 'allocation_source': 'fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)'}, 'setup_selection': {'seconds': 48.95686173439026, 'units': 6, 'planned_units': 6, 'samples': 6, 'gpu_count': 1, 'allocation_source': 'fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)'}, 'training_selection': {'seconds': 749.6906819343567, 'units': 240, 'planned_units': 240, 'samples': 7680, 'gpu_count': 1, 'allocation_source': 'fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)'}, 'heldout_eval_selection': {'seconds': 127.7629702091217, 'units': 3000, 'planned_units': 3000, 'samples': 3000, 'gpu_count': 1, 'allocation_source': 'fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)'}, 'setup_confirmation': {'seconds': 266.957839012146, 'units': 6, 'planned_units': 6, 'samples': 6, 'gpu_count': 1, 'allocation_source': 'fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)'}, 'training_confirmation': {'seconds': 786.5640952587128, 'units': 600, 'planned_units': 600, 'samples': 19200, 'gpu_count': 1, 'allocation_source': 'fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)'}, 'heldout_eval_confirmation': {'seconds': 134.40599060058594, 'units': 3000, 'planned_units': 3000, 'samples': 3000, 'gpu_count': 1, 'allocation_source': 'fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)'}}, 'generation': None, 'recovery': {'seconds': 4897.368327617645, 'gpu_count': 1, 'allocation_source': 'fork_config.py trainer_gpus_per_node=1 (single trainer GPU; inference replicas 0)', 'note': 'wall used 68.4 of 150 min; trainer GPU-h used ~1.02 of 2.0 (deploy to now, 1 GPU)'}}, 'recorded_at': 1793745777.0760796}
feasibility_required
True
generation_audit_validation
{'status': 'not_applicable', 'reasons': ['spec.generation_audit opts out and no feature it covers is true'], 'applicability': {'check': 'generation_audit', 'status': 'not_applicable', 'enforce': False, 'reasons': ['spec.generation_audit opts out and no feature it covers is true'], 'features': {'generated_training_data': False}}}
initialization_provenance
{'version': 1, 'arms': [{'arm': 'sel_adamw_lr5e-05_s0', 'phase': 'select', 'base_checkpoint': 'Qwen/Qwen3.5-2B', 'initialization_checkpoint': 'tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0', 'before_first_update': True, 'restore_count': 0, 'optimizer_checks': [{'restores': 0, 'optimizer': 'adamw', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}], 'initial_output_sha256': 'd7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7', 'evidence_ref': 'select_log.jsonl', 'adapter_sha256': None, 'adapter_note': 'selection arms all restored from one saved state select-init-s0; adapter hash not downloaded per arm, only initial output hash'}, {'arm': 'sel_adamw_lr0.0001_s0', 'phase': 'select', 'base_checkpoint': 'Qwen/Qwen3.5-2B', 'initialization_checkpoint': 'tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0', 'before_first_update': True, 'restore_count': 1, 'optimizer_checks': [{'restores': 0, 'optimizer': 'adamw', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}, {'restores': 1, 'optimizer': 'adamw', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}], 'initial_output_sha256': 'd7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7', 'evidence_ref': 'select_log.jsonl', 'adapter_sha256': None, 'adapter_note': 'selection arms all restored from one saved state select-init-s0; adapter hash not downloaded per arm, only initial output hash'}, {'arm': 'sel_adamw_lr0.0002_s0', 'phase': 'select', 'base_checkpoint': 'Qwen/Qwen3.5-2B', 'initialization_checkpoint': 'tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0', 'before_first_update': True, 'restore_count': 1, 'optimizer_checks': [{'restores': 0, 'optimizer': 'adamw', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}, {'restores': 1, 'optimizer': 'adamw', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}], 'initial_output_sha256': 'd7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7', 'evidence_ref': 'select_log.jsonl', 'adapter_sha256': None, 'adapter_note': 'selection arms all restored from one saved state select-init-s0; adapter hash not downloaded per arm, only initial output hash'}, {'arm': 'sel_dimuon_lr0.0003_s0', 'phase': 'select', 'base_checkpoint': 'Qwen/Qwen3.5-2B', 'initialization_checkpoint': 'tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0', 'before_first_update': True, 'restore_count': 1, 'optimizer_checks': [{'restores': 0, 'optimizer': 'dimuon', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}, {'restores': 1, 'optimizer': 'dimuon', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}], 'initial_output_sha256': 'd7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7', 'evidence_ref': 'select_log.jsonl', 'adapter_sha256': None, 'adapter_note': 'selection arms all restored from one saved state select-init-s0; adapter hash not downloaded per arm, only initial output hash'}, {'arm': 'sel_dimuon_lr0.001_s0', 'phase': 'select', 'base_checkpoint': 'Qwen/Qwen3.5-2B', 'initialization_checkpoint': 'tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0', 'before_first_update': True, 'restore_count': 1, 'optimizer_checks': [{'restores': 0, 'optimizer': 'dimuon', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}, {'restores': 1, 'optimizer': 'dimuon', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}], 'initial_output_sha256': 'd7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7', 'evidence_ref': 'select_log.jsonl', 'adapter_sha256': None, 'adapter_note': 'selection arms all restored from one saved state select-init-s0; adapter hash not downloaded per arm, only initial output hash'}, {'arm': 'sel_dimuon_lr0.003_s0', 'phase': 'select', 'base_checkpoint': 'Qwen/Qwen3.5-2B', 'initialization_checkpoint': 'tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0', 'before_first_update': True, 'restore_count': 1, 'optimizer_checks': [{'restores': 0, 'optimizer': 'dimuon', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}, {'restores': 1, 'optimizer': 'dimuon', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}], 'initial_output_sha256': 'd7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7', 'evidence_ref': 'select_log.jsonl', 'adapter_sha256': None, 'adapter_note': 'selection arms all restored from one saved state select-init-s0; adapter hash not downloaded per arm, only initial output hash'}, {'arm': 'baseline_adamw_s0', 'phase': 'confirm', 'base_checkpoint': 'Qwen/Qwen3.5-2B', 'initialization_checkpoint': 'tinker://b61dfd929fd09745b512c7224450cbde/weights/confirm-init-s0', 'before_first_update': True, 'restore_count': 0, 'optimizer_checks': [{'restores': 0, 'optimizer': 'adamw', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}], 'initial_output_sha256': '6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc', 'evidence_ref': 'restore_check.json', 'step0_checkpoint': 'tinker://b61dfd929fd09745b512c7224450cbde/weights/confirm-baseline_adamw_s0-step0', 'adapter_sha256': '380d38d8c1f3dde5e19b20aa642b3e30986c4b68738a2ec20df210e40caa8b10', 'fp32_param_sha256': 'cffcdbe0c5da48f60f9d55d7bcfc4d55931425af27f6c12a6185b0c029d7d089', 'init_adapter_sha256': '380d38d8c1f3dde5e19b20aa642b3e30986c4b68738a2ec20df210e40caa8b10', 'adapter_matches_init': True, 'server_checkpoint_optimizer': 'adamw'}, {'arm': 'treatment_dimuon_s0', 'phase': 'confirm', 'base_checkpoint': 'Qwen/Qwen3.5-2B', 'initialization_checkpoint': 'tinker://b61dfd929fd09745b512c7224450cbde/weights/confirm-init-s0', 'before_first_update': True, 'restore_count': 1, 'optimizer_checks': [{'restores': 0, 'optimizer': 'dimuon', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}, {'restores': 1, 'optimizer': 'dimuon', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}], 'initial_output_sha256': '6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc', 'evidence_ref': 'restore_check.json', 'step0_checkpoint': 'tinker://d331297013cae43230697585afa80dc5/weights/confirm-treatment_dimuon_s0-step0', 'adapter_sha256': '380d38d8c1f3dde5e19b20aa642b3e30986c4b68738a2ec20df210e40caa8b10', 'fp32_param_sha256': 'cffcdbe0c5da48f60f9d55d7bcfc4d55931425af27f6c12a6185b0c029d7d089', 'init_adapter_sha256': '380d38d8c1f3dde5e19b20aa642b3e30986c4b68738a2ec20df210e40caa8b10', 'adapter_matches_init': True, 'server_checkpoint_optimizer': 'dimuon'}, {'arm': 'baseline_adamw_s1', 'phase': 'confirm', 'base_checkpoint': 'Qwen/Qwen3.5-2B', 'initialization_checkpoint': 'tinker://9c18b804f21a06705c6da69577f80b4e/weights/confirm-init-s1', 'before_first_update': True, 'restore_count': 0, 'optimizer_checks': [{'restores': 0, 'optimizer': 'adamw', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}], 'initial_output_sha256': '6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc', 'evidence_ref': 'restore_check.json', 'step0_checkpoint': 'tinker://9c18b804f21a06705c6da69577f80b4e/weights/confirm-baseline_adamw_s1-step0', 'adapter_sha256': 'c8a11ec8d00edf4b6b45d3feac3e799de096e46a9e3176aac67fdb14f0d8592b', 'fp32_param_sha256': 'fb777da03b0c3b627613a59d27d60508134ad05cb58b83a04a598c9b9c7d1908', 'init_adapter_sha256': 'c8a11ec8d00edf4b6b45d3feac3e799de096e46a9e3176aac67fdb14f0d8592b', 'adapter_matches_init': True, 'server_checkpoint_optimizer': 'adamw'}, {'arm': 'treatment_dimuon_s1', 'phase': 'confirm', 'base_checkpoint': 'Qwen/Qwen3.5-2B', 'initialization_checkpoint': 'tinker://9c18b804f21a06705c6da69577f80b4e/weights/confirm-init-s1', 'before_first_update': True, 'restore_count': 1, 'optimizer_checks': [{'restores': 0, 'optimizer': 'dimuon', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}, {'restores': 1, 'optimizer': 'dimuon', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}], 'initial_output_sha256': '6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc', 'evidence_ref': 'restore_check.json', 'step0_checkpoint': 'tinker://64eea06e33ba66329c486ce2de950f32/weights/confirm-treatment_dimuon_s1-step0', 'adapter_sha256': 'c8a11ec8d00edf4b6b45d3feac3e799de096e46a9e3176aac67fdb14f0d8592b', 'fp32_param_sha256': 'fb777da03b0c3b627613a59d27d60508134ad05cb58b83a04a598c9b9c7d1908', 'init_adapter_sha256': 'c8a11ec8d00edf4b6b45d3feac3e799de096e46a9e3176aac67fdb14f0d8592b', 'adapter_matches_init': True, 'server_checkpoint_optimizer': 'dimuon'}, {'arm': 'baseline_adamw_s2', 'phase': 'confirm', 'base_checkpoint': 'Qwen/Qwen3.5-2B', 'initialization_checkpoint': 'tinker://581c1850d38ffa76474e2c6c7f2a3fb1/weights/confirm-init-s2', 'before_first_update': True, 'restore_count': 0, 'optimizer_checks': [{'restores': 0, 'optimizer': 'adamw', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}], 'initial_output_sha256': '6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc', 'evidence_ref': 'restore_check.json', 'step0_checkpoint': 'tinker://581c1850d38ffa76474e2c6c7f2a3fb1/weights/confirm-baseline_adamw_s2-step0', 'adapter_sha256': '0c1377ebc59ba6d47f890fe6f1b04c3f019054b02af31da4bbca3f66e0c1fc0a', 'fp32_param_sha256': '6d3b9c3d0659410a206fe85843af48ad08a195d32987ccd2c83c3b6b10bf2db6', 'init_adapter_sha256': '0c1377ebc59ba6d47f890fe6f1b04c3f019054b02af31da4bbca3f66e0c1fc0a', 'adapter_matches_init': True, 'server_checkpoint_optimizer': 'adamw'}, {'arm': 'treatment_dimuon_s2', 'phase': 'confirm', 'base_checkpoint': 'Qwen/Qwen3.5-2B', 'initialization_checkpoint': 'tinker://581c1850d38ffa76474e2c6c7f2a3fb1/weights/confirm-init-s2', 'before_first_update': True, 'restore_count': 1, 'optimizer_checks': [{'restores': 0, 'optimizer': 'dimuon', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}, {'restores': 1, 'optimizer': 'dimuon', 'model': 'Qwen/Qwen3.5-2B', 'rank': 32}], 'initial_output_sha256': '6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc', 'evidence_ref': 'restore_check.json', 'step0_checkpoint': 'tinker://8e9fef4c99e9c1af8d68a14c2c921011/weights/confirm-treatment_dimuon_s2-step0', 'adapter_sha256': '0c1377ebc59ba6d47f890fe6f1b04c3f019054b02af31da4bbca3f66e0c1fc0a', 'fp32_param_sha256': '6d3b9c3d0659410a206fe85843af48ad08a195d32987ccd2c83c3b6b10bf2db6', 'init_adapter_sha256': '0c1377ebc59ba6d47f890fe6f1b04c3f019054b02af31da4bbca3f66e0c1fc0a', 'adapter_matches_init': True, 'server_checkpoint_optimizer': 'dimuon'}], 'paired_init_matched_all_seeds': True}
launch
{'experiment_id': 'exp_71911f0fb9', 'context_status': 'snapshotted', 'superseded': False, 'mode': 'ordinary', 'purpose': 'Execute the selected saved experiment version.'}
launch_instructions
{'name': 'launch-instructions-8e52fc8e31fe.md', 'sha256': '8e52fc8e31fecddfff670ff7003e766ab25bb9c42a201d33a1edc5ccea1d95ea', 'url': 'https://ta-01m6fva5db548f5skm214fepcr-8000-oah9l7x00jpo7186eb6cix5v0.w.modal.host/api/runs/run_739abc9a8b/evidence/8e52fc8e31fecddfff670ff7003e766ab25bb9c42a201d33a1edc5ccea1d95ea'}
reported_outcome_reason
insufficient_evidence
reported_verdict
inconclusive
restoration_validation
{'status': 'unverified', 'required': True, 'checks': [{'check': 'baseline_adamw_s0', 'status': 'unverified', 'reason': 'baseline_adamw_s0: missing or duplicate arm evidence.'}, {'check': 'treatment_dimuon_s0', 'status': 'unverified', 'reason': 'treatment_dimuon_s0: missing or duplicate arm evidence.'}, {'check': 'baseline_adamw_s1', 'status': 'unverified', 'reason': 'baseline_adamw_s1: missing or duplicate arm evidence.'}, {'check': 'treatment_dimuon_s1', 'status': 'unverified', 'reason': 'treatment_dimuon_s1: missing or duplicate arm evidence.'}, {'check': 'baseline_adamw_s2', 'status': 'unverified', 'reason': 'baseline_adamw_s2: missing or duplicate arm evidence.'}, {'check': 'treatment_dimuon_s2', 'status': 'unverified', 'reason': 'treatment_dimuon_s2: missing or duplicate arm evidence.'}], 'reason': 'baseline_adamw_s0: missing or duplicate arm evidence.', 'applicability': 'required'}
Agent trace full trace with commands in Devin ↗
Details
run
run_739abc9a8b
backend
Devin
session
devin-00a0185747d54596a3fb0403496b0380
experiment
exp_71911f0fb9
created
Nov 3, 21:12 UTC
started
Nov 3, 21:33 UTC
finished
Nov 3, 22:42 UTC
duration
1h 09m
GPU-h budget
2.0
wall budget
150 min
base model
Qwen/Qwen3.5-2B
training
SFT
dataset
no_robots
result
final
outcome reason
insufficient evidence
Other runs of this idea

Submit an idea

Most ideas come in from Slack threads. Use this when yours is not in one yet; the triage agent picks it up.