sora 370953729b Fix perf stats (wrong import path), per-repeat checkpoints, README
- perf_stats aggregator lives in eval/, not model/: the import failed
  silently and EVERY perf column was empty (not just ttft). Now warns
  on stderr instead of swallowing.
- repeats > 1 get their own checkpoint key (:rep2, :rep3, ...): repeat 2
  previously restored repeat 1's predictions and finished instantly with
  identical scores. rep1 keeps the legacy key (existing checkpoints still
  resume).
- repeats summary: report the MEAN score and aggregate time/tokens over
  ALL runs (was: last run only).
- README: six-benchmark command as the primary example.

Co-Authored-By: Claude <noreply@anthropic.com>
2026-09-11 13:38:04 +00:00

173 lines
4.2 KiB
JSON

{
"formatVersion": 1,
"protocol": "one-token/v1",
"model": "Qwen3-8B",
"collectedAt": "2026-08-28T05:58:28.724Z",
"samplesPerCell": 25,
"postReasoning": false,
"cells": {
"random-number-1-100:en": {
"cellId": "random-number-1-100:en",
"counts": {
"42": 25
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0,
"normalizedEntropy": 0,
"medianLatencyMs": 9036.364354999998,
"meanCompletionTokens": 2,
"meanReasoningTokens": null
},
"random-number-1-100:zh": {
"cellId": "random-number-1-100:zh",
"counts": {
"42": 25
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0,
"normalizedEntropy": 0,
"medianLatencyMs": 9103.937199000007,
"meanCompletionTokens": 2,
"meanReasoningTokens": null
},
"random-color:en": {
"cellId": "random-color:en",
"counts": {
"blue": 13,
"indigo": 4,
"orange": 1,
"azure": 3,
"teal": 2,
"cyan": 1,
"turquoise": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.1294320362548183,
"normalizedEntropy": 0.43396770210458313,
"medianLatencyMs": 8225.354339000012,
"meanCompletionTokens": 4.72,
"meanReasoningTokens": null
},
"random-animal:en": {
"cellId": "random-animal:en",
"counts": {
"elephant": 11,
"seal": 1,
"platypus": 1,
"giraffe": 4,
"penguin": 5,
"zebra": 2,
"lion": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.257320658596841,
"normalizedEntropy": 0.3999606975611018,
"medianLatencyMs": 8505.359566999978,
"meanCompletionTokens": 7.08,
"meanReasoningTokens": null
},
"random-number-1-10:en": {
"cellId": "random-number-1-10:en",
"counts": {
"7": 25
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0,
"normalizedEntropy": 0,
"medianLatencyMs": 8840.802993999998,
"meanCompletionTokens": 1,
"meanReasoningTokens": null
},
"random-letter:en": {
"cellId": "random-letter:en",
"counts": {
"z": 3,
"q": 11,
"x": 6,
"t": 1,
"m": 1,
"y": 3
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.120924277228159,
"normalizedEntropy": 0.45121826986581004,
"medianLatencyMs": 8260.609531000024,
"meanCompletionTokens": 1,
"meanReasoningTokens": null
},
"random-color:zh": {
"cellId": "random-color:zh",
"counts": {
"蓝": 18,
"蓝紫": 1,
"靛蓝": 2,
"天蓝": 2,
"钴蓝": 1,
"珊瑚橙": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 1.4815101887362598,
"normalizedEntropy": 0.3019244386785708,
"medianLatencyMs": 8469.920075000031,
"meanCompletionTokens": 2.08,
"meanReasoningTokens": null
},
"coin-flip:en": {
"cellId": "coin-flip:en",
"counts": {
"heads": 17,
"tails": 2
},
"validCount": 19,
"invalidCount": 6,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.4854607607459134,
"normalizedEntropy": 0.4854607607459134,
"medianLatencyMs": 8714.726423000015,
"meanCompletionTokens": 5.24,
"meanReasoningTokens": null
}
},
"meta": {
"tool": "llm-fingerprint-detector"
}
}