{
 "script": "charactereval_rm_server_check.py",
 "time_utc": "2026-10-28T16:38:21+00:00",
 "host": "[left out]",
 "python": "3.10.12",
 "probes_sha256": "8ad3fbaaa69a970a444065cc1f6c1a816644174116faae10f0e7b2b6672ec494",
 "criteria": {
  "weights": "every file matches",
  "endpoint": "same score in all three passes, all in [1, 5]",
  "endpoint_vs_reference": "EQUAL when every |diff| <= 1e-06; WITHIN ONE BF16 STEP when <= 0.016"
 },
 "A_weights": {
  "model_dir": "/data/llm/models/BaichuanCharRM",
  "revision": "e953da5f57b86db7adca3a2714b4c3720f5b96a2",
  "files": [
   {
    "file": "pytorch_model-00001-of-00003.bin",
    "kind": "sha256",
    "expected": "c868e1bdccfe16392538d8020ef3f27ccf74b47cfca3c867617e8a8e0f2aa700",
    "expected_size": 9973568983,
    "present": true,
    "size": 9973568983,
    "actual": "c868e1bdccfe16392538d8020ef3f27ccf74b47cfca3c867617e8a8e0f2aa700",
    "match": true
   },
   {
    "file": "pytorch_model-00002-of-00003.bin",
    "kind": "sha256",
    "expected": "e0681ed449fb183d836920340c791e3bb3351c5f031011d05f11322d0d77b912",
    "expected_size": 9947421360,
    "present": true,
    "size": 9947421360,
    "actual": "e0681ed449fb183d836920340c791e3bb3351c5f031011d05f11322d0d77b912",
    "match": true
   },
   {
    "file": "pytorch_model-00003-of-00003.bin",
    "kind": "sha256",
    "expected": "942a5e7322a87a7fb3c609db97c177f5e8835109a38c8dea01953c5c88e68dab",
    "expected_size": 6585330193,
    "present": true,
    "size": 6585330193,
    "actual": "942a5e7322a87a7fb3c609db97c177f5e8835109a38c8dea01953c5c88e68dab",
    "match": true
   },
   {
    "file": "pytorch_model.bin.index.json",
    "kind": "gitblob",
    "expected": "756e175126441f96764bf964461646516fc1ef3c",
    "expected_size": 23326,
    "present": true,
    "size": 23326,
    "actual": "756e175126441f96764bf964461646516fc1ef3c",
    "match": true
   },
   {
    "file": "tokenizer.model",
    "kind": "sha256",
    "expected": "79452955be6b419a65984273a9f08af86042e1c2a75ee3ba989cbf620a133cc2",
    "expected_size": 2001107,
    "present": true,
    "size": 2001107,
    "actual": "79452955be6b419a65984273a9f08af86042e1c2a75ee3ba989cbf620a133cc2",
    "match": true
   },
   {
    "file": "config.json",
    "kind": "gitblob",
    "expected": "040a315da9111f5d12ad6350c0d6230c29055a6b",
    "expected_size": 835,
    "present": true,
    "size": 835,
    "actual": "040a315da9111f5d12ad6350c0d6230c29055a6b",
    "match": true
   },
   {
    "file": "configuration_baichuan.py",
    "kind": "gitblob",
    "expected": "c5967ae712619bfbebaec545599c96db0c46a33e",
    "expected_size": 1490,
    "present": true,
    "size": 1490,
    "actual": "c5967ae712619bfbebaec545599c96db0c46a33e",
    "match": true
   },
   {
    "file": "modeling_baichuan.py",
    "kind": "gitblob",
    "expected": "e1b03ea793c9e00b6c1c3ef5d0f58503312ff4da",
    "expected_size": 22388,
    "present": true,
    "size": 22388,
    "actual": "e1b03ea793c9e00b6c1c3ef5d0f58503312ff4da",
    "match": true
   },
   {
    "file": "tokenization_baichuan.py",
    "kind": "gitblob",
    "expected": "1f0f192c59899e65ed7952b42dd0ce90c0ecbecf",
    "expected_size": 8720,
    "present": true,
    "size": 8720,
    "actual": "1f0f192c59899e65ed7952b42dd0ce90c0ecbecf",
    "match": true
   },
   {
    "file": "tokenizer_config.json",
    "kind": "gitblob",
    "expected": "6f6e083da07814405e1eca55dd76213d41123099",
    "expected_size": 987,
    "present": true,
    "size": 987,
    "actual": "6f6e083da07814405e1eca55dd76213d41123099",
    "match": true
   },
   {
    "file": "special_tokens_map.json",
    "kind": "gitblob",
    "expected": "16bdf0c6837427c80a810936ef0cae7bf98d80fb",
    "expected_size": 431,
    "present": true,
    "size": 431,
    "actual": "16bdf0c6837427c80a810936ef0cae7bf98d80fb",
    "match": true
   }
  ],
  "other_files": [
   "__pycache__"
  ],
  "result": "ALL FILES MATCH"
 },
 "B_reference": {
  "environment": {
   "torch": "2.7.0+cu126",
   "cuda": "12.6",
   "device": "NVIDIA A800 80GB PCIe",
   "transformers": "4.36.2"
  },
  "probes": [
   {
    "n": 0,
    "kind": "metric",
    "id": 7,
    "metric_en": "Accuracy",
    "score": 2.9140625,
    "tokens": 604
   },
   {
    "n": 1,
    "kind": "metric",
    "id": 249,
    "metric_en": "Accuracy",
    "score": 2.1796875,
    "tokens": 458
   },
   {
    "n": 2,
    "kind": "metric",
    "id": 45,
    "metric_en": "Behavior",
    "score": 1.0302734375,
    "tokens": 485
   },
   {
    "n": 3,
    "kind": "metric",
    "id": 130,
    "metric_en": "Behavior",
    "score": 1.10546875,
    "tokens": 936
   },
   {
    "n": 4,
    "kind": "metric",
    "id": 4,
    "metric_en": "Coherence",
    "score": 2.03125,
    "tokens": 475
   },
   {
    "n": 5,
    "kind": "metric",
    "id": 15,
    "metric_en": "Coherence",
    "score": 3.03125,
    "tokens": 517
   },
   {
    "n": 6,
    "kind": "metric",
    "id": 107,
    "metric_en": "Communication_skills",
    "score": 1.671875,
    "tokens": 422
   },
   {
    "n": 7,
    "kind": "metric",
    "id": 235,
    "metric_en": "Communication_skills",
    "score": 1.486328125,
    "tokens": 506
   },
   {
    "n": 8,
    "kind": "metric",
    "id": 37,
    "metric_en": "Consistency",
    "score": 3.78125,
    "tokens": 1486
   },
   {
    "n": 9,
    "kind": "metric",
    "id": 63,
    "metric_en": "Consistency",
    "score": 2.25,
    "tokens": 1057
   },
   {
    "n": 10,
    "kind": "metric",
    "id": 80,
    "metric_en": "Diversity",
    "score": 1.1630859375,
    "tokens": 1558
   },
   {
    "n": 11,
    "kind": "metric",
    "id": 130,
    "metric_en": "Diversity",
    "score": 1.1513671875,
    "tokens": 936
   },
   {
    "n": 12,
    "kind": "metric",
    "id": 3,
    "metric_en": "Empathy",
    "score": 2.6328125,
    "tokens": 466
   },
   {
    "n": 13,
    "kind": "metric",
    "id": 38,
    "metric_en": "Empathy",
    "score": 1.6875,
    "tokens": 1532
   },
   {
    "n": 14,
    "kind": "metric",
    "id": 37,
    "metric_en": "Exposure",
    "score": 1.2333984375,
    "tokens": 1487
   },
   {
    "n": 15,
    "kind": "metric",
    "id": 98,
    "metric_en": "Exposure",
    "score": 1.53125,
    "tokens": 1142
   },
   {
    "n": 16,
    "kind": "metric",
    "id": 18,
    "metric_en": "Fluency",
    "score": 3.796875,
    "tokens": 644
   },
   {
    "n": 17,
    "kind": "metric",
    "id": 19,
    "metric_en": "Fluency",
    "score": 2.71875,
    "tokens": 668
   },
   {
    "n": 18,
    "kind": "metric",
    "id": 75,
    "metric_en": "Hallucination",
    "score": 3.234375,
    "tokens": 1568
   },
   {
    "n": 19,
    "kind": "metric",
    "id": 238,
    "metric_en": "Hallucination",
    "score": 1.84375,
    "tokens": 685
   },
   {
    "n": 20,
    "kind": "metric",
    "id": 105,
    "metric_en": "Humanlikeness",
    "score": 4.890625,
    "tokens": 1139
   },
   {
    "n": 21,
    "kind": "metric",
    "id": 112,
    "metric_en": "Humanlikeness",
    "score": 4.546875,
    "tokens": 1122
   },
   {
    "n": 22,
    "kind": "metric",
    "id": 9,
    "metric_en": "Utterance",
    "score": 1.41015625,
    "tokens": 654
   },
   {
    "n": 23,
    "kind": "metric",
    "id": 32,
    "metric_en": "Utterance",
    "score": 2.4375,
    "tokens": 613
   },
   {
    "n": 24,
    "kind": "longest",
    "id": 5244,
    "metric_en": "Hallucination",
    "score": 1.53515625,
    "tokens": 7931
   },
   {
    "n": 25,
    "kind": "over-window",
    "id": 5244,
    "metric_en": "Hallucination",
    "score": 1.53515625,
    "tokens": 13385
   }
  ]
 },
 "C_endpoint": {
  "base_url": "[operator endpoint, left out]",
  "model": "baichuan-char-rm",
  "batch": [
   2.9140625,
   2.1796875,
   1.0302734375,
   1.10546875,
   2.03125,
   3.03125,
   1.671875,
   1.486328125,
   3.78125,
   2.25,
   1.1630859375,
   1.1513671875,
   2.6328125,
   1.6875,
   1.2333984375,
   1.53125,
   3.796875,
   2.71875,
   3.234375,
   1.84375,
   4.890625,
   4.546875,
   1.41015625,
   2.4375,
   1.53515625,
   1.53515625
  ],
  "reversed": [
   2.9140625,
   2.1796875,
   1.0302734375,
   1.10546875,
   2.03125,
   3.03125,
   1.671875,
   1.486328125,
   3.78125,
   2.25,
   1.1630859375,
   1.1513671875,
   2.6328125,
   1.6875,
   1.2333984375,
   1.53125,
   3.796875,
   2.71875,
   3.234375,
   1.84375,
   4.890625,
   4.546875,
   1.41015625,
   2.4375,
   1.53515625,
   1.53515625
  ],
  "single": [
   2.9140625,
   2.1796875,
   1.0302734375,
   1.10546875,
   2.03125,
   3.03125,
   1.671875,
   1.486328125,
   3.78125,
   2.25,
   1.1630859375,
   1.1513671875,
   2.6328125,
   1.6875,
   1.2333984375,
   1.53125,
   3.796875,
   2.71875,
   3.234375,
   1.84375,
   4.890625,
   4.546875,
   1.41015625,
   2.4375,
   1.53515625,
   1.53515625
  ],
  "deterministic": true,
  "in_range": true,
  "seconds": {
   "batch": 6.4,
   "reversed": 6.75
  }
 },
 "B_vs_C": {
  "max_abs_diff": 0.0,
  "exact": 26,
  "within_bf16_step": 26,
  "n": 26,
  "verdict": "EQUAL"
 },
 "result": "PASS"
}