{"pid": "L2_081", "split": "dev", "rep": 2, "arm": "livEng", "attempt": 0, "success": true, "score": 3.678, "correct": true, "status": "ok", "speedup": 3.678, "ref_ms": 8.23712, "cand_ms": 2.23955, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 68.2, "calls": 2, "tokens_in": 16175, "tokens_out": 4914, "ctx_chars": 11583, "ctx_sha": "bb093721f8760f3d", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "fe4167733f2d826a", "ts": 1791529301.204123} {"pid": "L2_067", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "success": true, "score": 2.0358, "correct": true, "status": "ok", "speedup": 2.0358, "ref_ms": 12.85727, "cand_ms": 6.31555, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 69.7, "calls": 2, "tokens_in": 18050, "tokens_out": 5131, "ctx_chars": 14070, "ctx_sha": "3d6ada40588e7cb1", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c91575c8e94f91c1", "ts": 1791529302.7240348} {"pid": "L2_063", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "success": true, "score": 4.5438, "correct": true, "status": "ok", "speedup": 4.5438, "ref_ms": 8.0026, "cand_ms": 1.7612, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 69.8, "calls": 2, "tokens_in": 273265, "tokens_out": 4007, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "891dfc8e5247a44f", "ts": 1791529302.7845569} {"pid": "L2_088", "split": "dev", "rep": 2, "arm": "livKF", "attempt": 0, "success": true, "score": 3.7572, "correct": true, "status": "ok", "speedup": 3.7572, "ref_ms": 8.44256, "cand_ms": 2.24701, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 72.2, "calls": 2, "tokens_in": 23681, "tokens_out": 5057, "ctx_chars": 18655, "ctx_sha": "bbf921975c58f49c", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "31cd98a3ba0f11fc", "ts": 1791529305.1730824} {"pid": "L2_040", "split": "dev", "rep": 0, "arm": "bare", "attempt": 0, "success": true, "score": 1.0435, "correct": true, "status": "ok", "speedup": 1.0435, "ref_ms": 30.40615, "cand_ms": 29.13805, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 82.4, "calls": 2, "tokens_in": 4325, "tokens_out": 2049, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "13337ffead92684f", "ts": 1791529315.404351} {"pid": "L1_078", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "success": true, "score": 2.2795, "correct": true, "status": "ok", "speedup": 2.2795, "ref_ms": 35.47595, "cand_ms": 15.563, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 89.7, "calls": 2, "tokens_in": 12199, "tokens_out": 2684, "ctx_chars": 7879, "ctx_sha": "f7c7999053853d91", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "49588df141a7d8f9", "ts": 1791529322.713876} {"pid": "L2_053", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "success": false, "score": 0.8011, "correct": true, "status": "ok", "speedup": 0.8011, "ref_ms": 15.86992, "cand_ms": 19.8096, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 101.4, "calls": 2, "tokens_in": 5406, "tokens_out": 4497, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "c2725a6f92d92a4e", "ts": 1791529334.3381217} {"pid": "L2_081", "split": "dev", "rep": 0, "arm": "ace", "attempt": 0, "success": true, "score": 1.2077, "correct": true, "status": "ok", "speedup": 1.2077, "ref_ms": 8.25077, "cand_ms": 6.83184, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 103.9, "calls": 2, "tokens_in": 266167, "tokens_out": 4903, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "e73aa19823059f69", "ts": 1791529336.8644803} {"pid": "L2_088", "split": "dev", "rep": 1, "arm": "livP1", "attempt": 0, "success": true, "score": 3.7458, "correct": true, "status": "ok", "speedup": 3.7458, "ref_ms": 8.63711, "cand_ms": 2.30584, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 106.5, "calls": 2, "tokens_in": 19227, "tokens_out": 4802, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "beac621142a731bc", "ts": 1791529339.478181} {"pid": "L2_039", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "success": true, "score": 1.0031, "correct": true, "status": "ok", "speedup": 1.0031, "ref_ms": 30.14781, "cand_ms": 30.05528, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 116.1, "calls": 2, "tokens_in": 6306, "tokens_out": 7109, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8a1cee3d5bac44fa", "ts": 1791529349.125184} {"pid": "L3_020", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "success": false, "score": 1.0034, "correct": true, "status": "ok", "speedup": 1.0034, "ref_ms": 7.42578, "cand_ms": 7.40062, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 233.6, "calls": 2, "tokens_in": 10096, "tokens_out": 10793, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2bcfe44a51f317a0", "ts": 1791529466.603364} {"pid": "L2_081", "split": "dev", "rep": 0, "arm": "stock", "attempt": 0, "success": true, "score": 1.0317, "correct": true, "status": "ok", "speedup": 1.0317, "ref_ms": 8.31317, "cand_ms": 8.05797, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 185.5, "calls": 2, "tokens_in": 11056, "tokens_out": 2009, "ctx_chars": 7359, "ctx_sha": "799b0b02bfe5b890", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "b00ce081f7fc4a77", "ts": 1791529500.9439747} {"pid": "L2_069", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "success": true, "score": 1.4024, "correct": true, "status": "ok", "speedup": 1.4024, "ref_ms": 3.63059, "cand_ms": 2.58893, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 270.1, "calls": 2, "tokens_in": 6529, "tokens_out": 8639, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "5457aaa2b4b56efb", "ts": 1791529503.058216} {"pid": "L3_047", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "success": true, "score": 2.5666, "correct": true, "status": "ok", "speedup": 2.5666, "ref_ms": 3.63027, "cand_ms": 1.41444, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 211.9, "calls": 2, "tokens_in": 14135, "tokens_out": 7270, "ctx_chars": 6833, "ctx_sha": "51e2cdabc27184da", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "9135074b667d26e6", "ts": 1791529514.591535} {"pid": "L2_053", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "success": true, "score": 4.0842, "correct": true, "status": "ok", "speedup": 4.0842, "ref_ms": 16.05877, "cand_ms": 3.93192, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 206.2, "calls": 2, "tokens_in": 23300, "tokens_out": 3519, "ctx_chars": 18655, "ctx_sha": "bbf921975c58f49c", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "93065fbdc9ee2e3f", "ts": 1791529543.078906} {"pid": "L2_062", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "success": true, "score": 1.0592, "correct": true, "status": "ok", "speedup": 1.0592, "ref_ms": 8.65163, "cand_ms": 8.16785, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 242.2, "calls": 2, "tokens_in": 9497, "tokens_out": 2309, "ctx_chars": 5389, "ctx_sha": "be81589e9761e178", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2a462ec5a46dfce1", "ts": 1791529545.0090797} {"pid": "L3_047", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "success": true, "score": 2.7403, "correct": true, "status": "ok", "speedup": 2.7403, "ref_ms": 3.62817, "cand_ms": 1.32399, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 312.1, "calls": 2, "tokens_in": 9849, "tokens_out": 13307, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "fa092a645f7b5e2e", "ts": 1791529545.073878} {"pid": "L2_040", "split": "dev", "rep": 2, "arm": "aceseed", "attempt": 0, "success": true, "score": 4.2482, "correct": true, "status": "ok", "speedup": 4.2482, "ref_ms": 30.52682, "cand_ms": 7.18588, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 312.9, "calls": 3, "tokens_in": 413173, "tokens_out": 8917, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "84563192f6d0f289", "ts": 1791529545.8762095} {"pid": "L3_020", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "success": true, "score": 1.2595, "correct": true, "status": "ok", "speedup": 1.2595, "ref_ms": 7.23075, "cand_ms": 5.74079, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 350.0, "calls": 2, "tokens_in": 20817, "tokens_out": 15048, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f625f5254b0c637b", "ts": 1791529583.0291154} {"pid": "L2_062", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 261.8, "calls": 3, "tokens_in": 39708, "tokens_out": 9955, "ctx_chars": 19121, "ctx_sha": "d421a9dea165588e", "uses_bf16": false, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "c6ef52566aee1592", "ts": 1791529584.533455} {"pid": "L1_078", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "success": true, "score": 2.4117, "correct": true, "status": "ok", "speedup": 2.4117, "ref_ms": 35.4967, "cand_ms": 14.71867, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 287.0, "calls": 2, "tokens_in": 6921, "tokens_out": 7910, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "32d9fdd6e2eb3f33", "ts": 1791529588.23979} {"pid": "L3_020", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "success": true, "score": 1.9034, "correct": true, "status": "ok", "speedup": 1.9034, "ref_ms": 6.92591, "cand_ms": 3.63873, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 359.2, "calls": 2, "tokens_in": 273310, "tokens_out": 21036, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "a1ac2bdef1f0e3ac", "ts": 1791529592.1604486} {"pid": "L2_069", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "success": true, "score": 2.895, "correct": true, "status": "ok", "speedup": 2.895, "ref_ms": 3.98947, "cand_ms": 1.37805, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 317.0, "calls": 3, "tokens_in": 13390, "tokens_out": 10902, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0abbb9581922ad26", "ts": 1791529651.3795154} {"pid": "L2_092", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "success": true, "score": 2.5525, "correct": true, "status": "ok", "speedup": 2.5525, "ref_ms": 8.50025, "cand_ms": 3.33022, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 358.2, "calls": 2, "tokens_in": 7140, "tokens_out": 12496, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "7388cdda61fa3570", "ts": 1791529663.380794} {"pid": "L3_020", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "success": true, "score": 1.6127, "correct": true, "status": "ok", "speedup": 1.6127, "ref_ms": 8.43198, "cand_ms": 5.22858, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 432.9, "calls": 2, "tokens_in": 21821, "tokens_out": 18309, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1c9598728c01e141", "ts": 1791529665.919214} {"pid": "L2_063", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "success": true, "score": 1.0058, "correct": true, "status": "ok", "speedup": 1.0058, "ref_ms": 7.97974, "cand_ms": 7.93353, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 51.0, "calls": 2, "tokens_in": 3883, "tokens_out": 1835, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "fb97476eb0170ea5", "ts": 1791529702.402624} {"pid": "L2_073", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "success": true, "score": 2.6522, "correct": true, "status": "ok", "speedup": 2.6522, "ref_ms": 5.61452, "cand_ms": 2.11689, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 354.0, "calls": 2, "tokens_in": 29720, "tokens_out": 14488, "ctx_chars": 22975, "ctx_sha": "4e003dc4030b57a1", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "07aa674391ff5764", "ts": 1791529703.0793228} {"pid": "L3_047", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "success": true, "score": 3.1376, "correct": true, "status": "ok", "speedup": 3.1376, "ref_ms": 3.6213, "cand_ms": 1.15418, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 382.6, "calls": 2, "tokens_in": 24632, "tokens_out": 10225, "ctx_chars": 14992, "ctx_sha": "82b6b58defdd0048", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "034e59fe09ce4b89", "ts": 1791529722.124582} {"pid": "L3_048", "split": "dev", "rep": 2, "arm": "livEng", "attempt": 0, "success": false, "score": 0.9513, "correct": true, "status": "ok", "speedup": 0.9513, "ref_ms": 15.89714, "cand_ms": 16.71014, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 489.6, "calls": 5, "tokens_in": 39807, "tokens_out": 20923, "ctx_chars": 3184, "ctx_sha": "e64357aa997958f6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e197dc446f33af28", "ts": 1791529722.608911} {"pid": "L2_040", "split": "dev", "rep": 0, "arm": "livP1", "attempt": 0, "success": true, "score": 4.4768, "correct": true, "status": "ok", "speedup": 4.4768, "ref_ms": 30.35298, "cand_ms": 6.7801, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 140.0, "calls": 2, "tokens_in": 19381, "tokens_out": 3298, "ctx_chars": 14516, "ctx_sha": "491a69f435bf3217", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "8d6154463f7a5e75", "ts": 1791529732.191464} {"pid": "L1_078", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "success": true, "score": 3.4556, "correct": true, "status": "ok", "speedup": 3.4556, "ref_ms": 35.49599, "cand_ms": 10.2721, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 177.0, "calls": 2, "tokens_in": 7930, "tokens_out": 12143, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "b8e5fe334a40ad99", "ts": 1791529760.0419116} {"pid": "L3_020", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "success": true, "score": 1.0355, "correct": true, "status": "ok", "speedup": 1.0355, "ref_ms": 6.68364, "cand_ms": 6.4547, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 258.8, "calls": 2, "tokens_in": 33419, "tokens_out": 24963, "ctx_chars": 21293, "ctx_sha": "c37e861435b5bbc4", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "69b67ebffdf0cc3b", "ts": 1791529761.8727515} {"pid": "L2_029", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "success": true, "score": 1.0059, "correct": true, "status": "ok", "speedup": 1.0059, "ref_ms": 8.08515, "cand_ms": 8.03763, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 45.6, "calls": 2, "tokens_in": 8603, "tokens_out": 1895, "ctx_chars": 5477, "ctx_sha": "8765bd9517445b21", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2156d589280570be", "ts": 1791529768.2238185} {"pid": "L2_073", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "success": true, "score": 1.6738, "correct": true, "status": "ok", "speedup": 1.6738, "ref_ms": 5.65492, "cand_ms": 3.37849, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 188.9, "calls": 2, "tokens_in": 11685, "tokens_out": 5891, "ctx_chars": 6744, "ctx_sha": "b92173e1465ccf4d", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2fe6d769e09c1749", "ts": 1791529777.1075635} {"pid": "L1_078", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "success": true, "score": 7.1451, "correct": true, "status": "ok", "speedup": 7.1451, "ref_ms": 35.66509, "cand_ms": 4.99154, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 232.7, "calls": 2, "tokens_in": 25371, "tokens_out": 6476, "ctx_chars": 19130, "ctx_sha": "0551daeb8a590834", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "eca4ccd71338d5a8", "ts": 1791529777.8179944} {"pid": "L2_073", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "success": true, "score": 1.7153, "correct": true, "status": "ok", "speedup": 1.7153, "ref_ms": 5.60484, "cand_ms": 3.26765, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 318.9, "calls": 2, "tokens_in": 267712, "tokens_out": 8010, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8cc97ade2a96a693", "ts": 1791529785.5478113} {"pid": "L2_058", "split": "dev", "rep": 1, "arm": "livKF", "attempt": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 11.7532, "ref_ms": 25.09525, "cand_ms": 2.13518, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 261.4, "calls": 2, "tokens_in": 25708, "tokens_out": 9453, "ctx_chars": 20061, "ctx_sha": "a0a8edb8b6ae64a6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "9676a018027142c2", "ts": 1791529807.267741} {"pid": "L3_020", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "success": true, "score": 1.7759, "correct": true, "status": "ok", "speedup": 1.7759, "ref_ms": 7.07996, "cand_ms": 3.98666, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 146.4, "calls": 2, "tokens_in": 10690, "tokens_out": 12971, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d1fb37f8a713c887", "ts": 1791529809.7458081} {"pid": "L2_039", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 280.4, "calls": 2, "tokens_in": 25956, "tokens_out": 11438, "ctx_chars": 19597, "ctx_sha": "e31c3ee202e0b25a", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "80d9dd82d0704ad0", "ts": 1791529823.4757428} {"pid": "L3_002", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "success": true, "score": 1.3182, "correct": true, "status": "ok", "speedup": 1.3182, "ref_ms": 33.56651, "cand_ms": 25.46427, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 323.2, "calls": 2, "tokens_in": 266069, "tokens_out": 4578, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "27d98b0545cd0d78", "ts": 1791529824.2024138} {"pid": "L2_062", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "success": true, "score": 1.476, "correct": true, "status": "ok", "speedup": 1.476, "ref_ms": 8.45235, "cand_ms": 5.72642, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 282.8, "calls": 2, "tokens_in": 6043, "tokens_out": 5995, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "83679e0db37cebea", "ts": 1791529827.7821622} {"pid": "L2_029", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0063, "correct": true, "status": "ok", "speedup": 1.0063, "ref_ms": 7.98026, "cand_ms": 7.93041, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 49.4, "calls": 2, "tokens_in": 4317, "tokens_out": 2351, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "6e2ad64d31910660", "ts": 1791529910.5969992} {"pid": "L2_053", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.013, "correct": true, "status": "ok", "speedup": 1.013, "ref_ms": 15.9441, "cand_ms": 15.73973, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 55.2, "calls": 2, "tokens_in": 10554, "tokens_out": 1373, "ctx_chars": 7198, "ctx_sha": "e66d522755f291d1", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1c85f1e0c14708cc", "ts": 1791529916.4097545} {"pid": "L2_053", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.1886, "correct": true, "status": "ok", "speedup": 4.1886, "ref_ms": 15.85902, "cand_ms": 3.78625, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 63.1, "calls": 2, "tokens_in": 18822, "tokens_out": 3390, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "b4044d2610da542d", "ts": 1791529924.2864661} {"pid": "L2_063", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.563, "correct": true, "status": "ok", "speedup": 3.563, "ref_ms": 7.99677, "cand_ms": 2.24442, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 65.3, "calls": 2, "tokens_in": 18516, "tokens_out": 3410, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "ff7bb1198de6d8ec", "ts": 1791529926.4935737} {"pid": "L2_081", "split": "dev", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.7469, "correct": true, "status": "ok", "speedup": 4.7469, "ref_ms": 8.22243, "cand_ms": 1.73216, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 66.8, "calls": 2, "tokens_in": 273681, "tokens_out": 4207, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "2f8bf69eece5f4ce", "ts": 1791529927.9734602} {"pid": "L2_062", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.3168, "correct": true, "status": "ok", "speedup": 1.3168, "ref_ms": 8.49017, "cand_ms": 6.4478, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 76.4, "calls": 2, "tokens_in": 266473, "tokens_out": 5406, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "d36ba0ec8d29a2d6", "ts": 1791529937.5547192} {"pid": "L2_081", "split": "dev", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.7415, "correct": true, "status": "ok", "speedup": 4.7415, "ref_ms": 8.2663, "cand_ms": 1.7434, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 79.0, "calls": 2, "tokens_in": 273661, "tokens_out": 4088, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "750cb7bc463a59e0", "ts": 1791529940.1972463} {"pid": "L2_053", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.0511, "correct": true, "status": "ok", "speedup": 1.0511, "ref_ms": 16.08261, "cand_ms": 15.30063, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 99.5, "calls": 2, "tokens_in": 266046, "tokens_out": 4601, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "9a26d73b6acb3376", "ts": 1791529960.6214466} {"pid": "L2_039", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0122, "correct": true, "status": "ok", "speedup": 1.0122, "ref_ms": 30.13511, "cand_ms": 29.77298, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 100.0, "calls": 2, "tokens_in": 12001, "tokens_out": 5381, "ctx_chars": 7281, "ctx_sha": "29172d84bddf7c5a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "5cd82afc60b9858e", "ts": 1791529961.1202793} {"pid": "L2_058", "split": "dev", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 12.492, "ref_ms": 25.18093, "cand_ms": 2.01577, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 102.4, "calls": 2, "tokens_in": 6639, "tokens_out": 7011, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "badeae9bb8faeec1", "ts": 1791529963.5108423} {"pid": "L2_037", "split": "dev", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.6937, "correct": true, "status": "ok", "speedup": 4.6937, "ref_ms": 19.77136, "cand_ms": 4.21233, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 112.5, "calls": 2, "tokens_in": 19944, "tokens_out": 4731, "ctx_chars": 14516, "ctx_sha": "491a69f435bf3217", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "216e6b4d8a3cc848", "ts": 1791529973.613422} {"pid": "L2_062", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0719, "correct": true, "status": "ok", "speedup": 1.0719, "ref_ms": 8.52477, "cand_ms": 7.95316, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 53.9, "calls": 2, "tokens_in": 4904, "tokens_out": 3054, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "80e7d885af8faa36", "ts": 1791529980.3608224} {"pid": "L2_058", "split": "dev", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 23.3307, "ref_ms": 25.13192, "cand_ms": 1.0772, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 123.0, "calls": 2, "tokens_in": 6842, "tokens_out": 8675, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "040e95acd491a76f", "ts": 1791529984.1759746} {"pid": "L2_067", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.3585, "correct": true, "status": "ok", "speedup": 2.3585, "ref_ms": 12.8321, "cand_ms": 5.44081, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 125.0, "calls": 2, "tokens_in": 6357, "tokens_out": 9915, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8a0c3736a0fbcd16", "ts": 1791529986.1469283} {"pid": "L2_040", "split": "dev", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.4154, "correct": true, "status": "ok", "speedup": 4.4154, "ref_ms": 30.42428, "cand_ms": 6.89049, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 95.6, "calls": 2, "tokens_in": 19586, "tokens_out": 4005, "ctx_chars": 14516, "ctx_sha": "491a69f435bf3217", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "22b315233cef75d4", "ts": 1791530006.1684206} {"pid": "L2_039", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.1542, "correct": true, "status": "ok", "speedup": 4.1542, "ref_ms": 30.15387, "cand_ms": 7.25861, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 151.5, "calls": 3, "tokens_in": 34150, "tokens_out": 10723, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "febb843185f69513", "ts": 1791530012.6748877} {"pid": "L2_063", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0046, "correct": true, "status": "ok", "speedup": 1.0046, "ref_ms": 7.99524, "cand_ms": 7.95875, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 59.2, "calls": 2, "tokens_in": 10279, "tokens_out": 1518, "ctx_chars": 7272, "ctx_sha": "862484e5300b7ff6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4c825d25fd0bd254", "ts": 1791530019.8138676} {"pid": "L2_092", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.0663, "correct": true, "status": "ok", "speedup": 4.0663, "ref_ms": 8.58596, "cand_ms": 2.11151, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 109.3, "calls": 2, "tokens_in": 20008, "tokens_out": 8132, "ctx_chars": 14961, "ctx_sha": "549d04579f777963", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4f42072a4f6c4a17", "ts": 1791530025.7457263} {"pid": "L3_044", "split": "dev", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 4.812, "correct": true, "status": "ok", "speedup": 4.812, "ref_ms": 75.281, "cand_ms": 15.64438, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 172.0, "calls": 2, "tokens_in": 26531, "tokens_out": 14367, "ctx_chars": 15252, "ctx_sha": "575b4fa0082f404b", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "d5cd5c2aa3283762", "ts": 1791530033.181392} {"pid": "L3_044", "split": "dev", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.3885, "correct": true, "status": "ok", "speedup": 1.3885, "ref_ms": 75.41467, "cand_ms": 54.31221, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 187.0, "calls": 2, "tokens_in": 10412, "tokens_out": 14978, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "3641423cf4e4e842", "ts": 1791530048.1349227} {"pid": "L2_069", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.7774, "correct": true, "status": "ok", "speedup": 3.7774, "ref_ms": 4.00698, "cand_ms": 1.06077, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 122.4, "calls": 2, "tokens_in": 19726, "tokens_out": 4802, "ctx_chars": 15668, "ctx_sha": "bb1fdfba7b87d1ff", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1a3a78f3f3948165", "ts": 1791530050.347535} {"pid": "L2_029", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.5614, "correct": true, "status": "ok", "speedup": 3.5614, "ref_ms": 7.98103, "cand_ms": 2.24097, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 72.6, "calls": 2, "tokens_in": 16211, "tokens_out": 4666, "ctx_chars": 12049, "ctx_sha": "cd92549f2b7fd121", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "375c6231e1fdf8a9", "ts": 1791530056.7477164} {"pid": "L3_050", "split": "dev", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.6821, "correct": true, "status": "ok", "speedup": 2.6821, "ref_ms": 12.69503, "cand_ms": 4.73323, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 132.9, "calls": 2, "tokens_in": 268045, "tokens_out": 7615, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "8be75eccb4648f70", "ts": 1791530057.1540222} {"pid": "L3_008", "split": "dev", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.3769, "correct": true, "status": "ok", "speedup": 1.3769, "ref_ms": 5.24565, "cand_ms": 3.80964, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 197.0, "calls": 2, "tokens_in": 18910, "tokens_out": 16467, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "48eda446b165f7dc", "ts": 1791530058.1449354} {"pid": "L2_088", "split": "dev", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.8855, "correct": true, "status": "ok", "speedup": 4.8855, "ref_ms": 8.49399, "cand_ms": 1.7386, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 84.8, "calls": 2, "tokens_in": 274080, "tokens_out": 5719, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "5ba406de6e8c4dd9", "ts": 1791530058.3780792} {"pid": "L2_039", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0117, "correct": true, "status": "ok", "speedup": 1.0117, "ref_ms": 30.08162, "cand_ms": 29.73281, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 114.8, "calls": 2, "tokens_in": 6295, "tokens_out": 6915, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "551d4d6bd7b3ee5d", "ts": 1791530075.9616787} {"pid": "L2_029", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.0806, "correct": true, "status": "ok", "speedup": 1.0806, "ref_ms": 8.01911, "cand_ms": 7.42121, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 73.6, "calls": 2, "tokens_in": 265787, "tokens_out": 4543, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "405c845b29a21ac8", "ts": 1791530079.7531416} {"pid": "L3_002", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.3022, "correct": true, "status": "ok", "speedup": 1.3022, "ref_ms": 33.75889, "cand_ms": 25.92504, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 142.6, "calls": 2, "tokens_in": 5316, "tokens_out": 4390, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "39e4544e2ca5726b", "ts": 1791530080.1763604} {"pid": "L2_081", "split": "dev", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.6786, "correct": true, "status": "ok", "speedup": 3.6786, "ref_ms": 8.24098, "cand_ms": 2.24027, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 70.2, "calls": 2, "tokens_in": 16352, "tokens_out": 4685, "ctx_chars": 11583, "ctx_sha": "bb093721f8760f3d", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "d6c8b2123e292bc2", "ts": 1791530103.4166908} {"pid": "L2_052", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.4389, "correct": true, "status": "ok", "speedup": 1.4389, "ref_ms": 10.98902, "cand_ms": 7.63696, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 249.6, "calls": 2, "tokens_in": 267785, "tokens_out": 10134, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d54a40eda65aaa28", "ts": 1791530110.7565703} {"pid": "L3_002", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 1.9452, "correct": true, "status": "ok", "speedup": 1.9452, "ref_ms": 33.60712, "cand_ms": 17.27681, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 171.0, "calls": 2, "tokens_in": 13026, "tokens_out": 9496, "ctx_chars": 7962, "ctx_sha": "19b168bb78ddbdc4", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "68cd1d751e873008", "ts": 1791530111.1692004} {"pid": "L2_092", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.8365, "correct": true, "status": "ok", "speedup": 2.8365, "ref_ms": 8.51795, "cand_ms": 3.00297, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 94.7, "calls": 2, "tokens_in": 10762, "tokens_out": 4425, "ctx_chars": 5747, "ctx_sha": "169afaa9eeb4d53a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "5e8b85c3c4dac30a", "ts": 1791530114.4876926} {"pid": "L3_044", "split": "dev", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": false, "score": 0.8138, "correct": true, "status": "ok", "speedup": 0.8138, "ref_ms": 75.37319, "cand_ms": 92.616, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 255.2, "calls": 2, "tokens_in": 10879, "tokens_out": 12557, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "b5578c2421b15a75", "ts": 1791530116.322103} {"pid": "L3_050", "split": "dev", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.8934, "correct": true, "status": "ok", "speedup": 2.8934, "ref_ms": 12.71182, "cand_ms": 4.39338, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 154.5, "calls": 2, "tokens_in": 268813, "tokens_out": 11579, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "ab32e10f9749df47", "ts": 1791530118.0276115} {"pid": "L2_088", "split": "dev", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0688, "correct": true, "status": "ok", "speedup": 1.0688, "ref_ms": 8.55759, "cand_ms": 8.00687, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 60.3, "calls": 2, "tokens_in": 5335, "tokens_out": 3123, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e18566b52c446924", "ts": 1791530118.6704934} {"pid": "L3_020", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0471, "correct": true, "status": "ok", "speedup": 1.0471, "ref_ms": 7.45607, "cand_ms": 7.12083, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 133.8, "calls": 2, "tokens_in": 9125, "tokens_out": 10401, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d84564abd81af8ae", "ts": 1791530119.9828215} {"pid": "L2_040", "split": "dev", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0396, "correct": true, "status": "ok", "speedup": 1.0396, "ref_ms": 30.29747, "cand_ms": 29.14372, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 72.4, "calls": 2, "tokens_in": 4670, "tokens_out": 2789, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "111ec1ccdbaa0760", "ts": 1791530122.7291503} {"pid": "L1_066", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.737, "correct": true, "status": "ok", "speedup": 1.737, "ref_ms": 7.81245, "cand_ms": 4.49755, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 268.9, "calls": 3, "tokens_in": 18951, "tokens_out": 16159, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "50097eabb86f0c9f", "ts": 1791530130.044217} {"pid": "L2_081", "split": "dev", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 1, "success": true, "score": 3.637, "correct": true, "status": "ok", "speedup": 3.637, "ref_ms": 8.20553, "cand_ms": 2.25615, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 75.8, "calls": 2, "tokens_in": 16231, "tokens_out": 6037, "ctx_chars": 11583, "ctx_sha": "bb093721f8760f3d", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "12b7416222e4c849", "ts": 1791530132.5226831} {"pid": "L2_081", "split": "dev", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0337, "correct": true, "status": "ok", "speedup": 1.0337, "ref_ms": 8.2294, "cand_ms": 7.96104, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 54.2, "calls": 2, "tokens_in": 11191, "tokens_out": 1807, "ctx_chars": 7359, "ctx_sha": "799b0b02bfe5b890", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c5769bdf8a8258a3", "ts": 1791530133.9266188} {"pid": "L3_033", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": false, "score": 0.9687, "correct": true, "status": "ok", "speedup": 0.9687, "ref_ms": 20.54905, "cand_ms": 21.21383, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 111.3, "calls": 2, "tokens_in": 10948, "tokens_out": 7637, "ctx_chars": 5350, "ctx_sha": "333d78223eeced7d", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "379dcb68a307b94b", "ts": 1791530137.0562997} {"pid": "L2_063", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.554, "correct": true, "status": "ok", "speedup": 3.554, "ref_ms": 7.98394, "cand_ms": 2.2465, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 53.4, "calls": 2, "tokens_in": 18461, "tokens_out": 3178, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "bb19b165eb36b487", "ts": 1791530172.0427768} {"pid": "L3_033", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.0285, "correct": true, "status": "ok", "speedup": 1.0285, "ref_ms": 20.48355, "cand_ms": 19.91512, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 126.5, "calls": 2, "tokens_in": 9911, "tokens_out": 3383, "ctx_chars": 5350, "ctx_sha": "333d78223eeced7d", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "a4da4ffa145443c5", "ts": 1791530174.669933} {"pid": "L2_081", "split": "dev", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0311, "correct": true, "status": "ok", "speedup": 1.0311, "ref_ms": 8.26307, "cand_ms": 8.01419, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 52.9, "calls": 2, "tokens_in": 4511, "tokens_out": 2192, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "41367e152cd4197b", "ts": 1791530185.4425187} {"pid": "L1_078", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.2935, "correct": true, "status": "ok", "speedup": 2.2935, "ref_ms": 35.50074, "cand_ms": 15.47857, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 90.0, "calls": 2, "tokens_in": 12163, "tokens_out": 2517, "ctx_chars": 7879, "ctx_sha": "f7c7999053853d91", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1066c1e3165f866d", "ts": 1791530201.1931024} {"pid": "L2_081", "split": "dev", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.6934, "correct": true, "status": "ok", "speedup": 3.6934, "ref_ms": 8.41545, "cand_ms": 2.27853, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 70.7, "calls": 2, "tokens_in": 23495, "tokens_out": 3620, "ctx_chars": 18655, "ctx_sha": "bbf921975c58f49c", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "d853d40f018b539d", "ts": 1791530204.6490126} {"pid": "L2_073", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.7149, "correct": true, "status": "ok", "speedup": 1.7149, "ref_ms": 5.62206, "cand_ms": 3.2784, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 240.7, "calls": 2, "tokens_in": 267400, "tokens_out": 7790, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "48f22a813cd58eb9", "ts": 1791530221.0954125} {"pid": "L2_069", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.4007, "correct": true, "status": "ok", "speedup": 2.4007, "ref_ms": 3.66758, "cand_ms": 1.52773, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 209.5, "calls": 3, "tokens_in": 12121, "tokens_out": 8993, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "81830a738f35ab63", "ts": 1791530222.1803896} {"pid": "L3_050", "split": "dev", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.7827, "correct": true, "status": "ok", "speedup": 2.7827, "ref_ms": 12.62927, "cand_ms": 4.53842, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 112.4, "calls": 2, "tokens_in": 267891, "tokens_out": 6954, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "21f74d29c67fe5a8", "ts": 1791530226.8729758} {"pid": "L2_053", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.0375, "correct": true, "status": "ok", "speedup": 1.0375, "ref_ms": 15.88879, "cand_ms": 15.3152, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 107.6, "calls": 3, "tokens_in": 402180, "tokens_out": 6859, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "80d34e96b85c7058", "ts": 1791530227.548539} {"pid": "L3_002", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.5255, "correct": true, "status": "ok", "speedup": 1.5255, "ref_ms": 33.6503, "cand_ms": 22.05914, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 177.6, "calls": 2, "tokens_in": 5901, "tokens_out": 6891, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "2fddbb4b844de7f7", "ts": 1791530234.7105205} {"pid": "L2_037", "split": "dev", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.6846, "correct": true, "status": "ok", "speedup": 4.6846, "ref_ms": 19.79527, "cand_ms": 4.22563, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 128.5, "calls": 2, "tokens_in": 273986, "tokens_out": 5404, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "78f24c35d821d822", "ts": 1791530246.4944954} {"pid": "L2_029", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.5752, "correct": true, "status": "ok", "speedup": 3.5752, "ref_ms": 8.07433, "cand_ms": 2.2584, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 120.2, "calls": 2, "tokens_in": 16482, "tokens_out": 6966, "ctx_chars": 12049, "ctx_sha": "cd92549f2b7fd121", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "c1277f0eb22a03ef", "ts": 1791530250.2414277} {"pid": "L3_002", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.3915, "correct": true, "status": "ok", "speedup": 2.3915, "ref_ms": 33.79955, "cand_ms": 14.13317, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 176.7, "calls": 2, "tokens_in": 274074, "tokens_out": 5653, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "557236eccbc80581", "ts": 1791530256.8991134} {"pid": "L2_037", "split": "dev", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.7002, "correct": true, "status": "ok", "speedup": 4.7002, "ref_ms": 19.77849, "cand_ms": 4.20799, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 134.2, "calls": 2, "tokens_in": 24264, "tokens_out": 4334, "ctx_chars": 19121, "ctx_sha": "d421a9dea165588e", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "e6e81e49745a51a4", "ts": 1791530256.9329994} {"pid": "L2_020", "split": "dev", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.4518, "correct": true, "status": "ok", "speedup": 1.4518, "ref_ms": 14.25605, "cand_ms": 9.81964, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 199.3, "calls": 2, "tokens_in": 266124, "tokens_out": 4358, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "20e8cae99648f21c", "ts": 1791530257.4442556} {"pid": "L1_078", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 7.9651, "correct": true, "status": "ok", "speedup": 7.9651, "ref_ms": 36.39165, "cand_ms": 4.5689, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 161.9, "calls": 2, "tokens_in": 25475, "tokens_out": 6841, "ctx_chars": 19130, "ctx_sha": "0551daeb8a590834", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "985c4e12c81d2dfd", "ts": 1791530272.6813638} {"pid": "L2_037", "split": "dev", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.2756, "correct": true, "status": "ok", "speedup": 1.2756, "ref_ms": 19.76944, "cand_ms": 15.49836, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 108.6, "calls": 2, "tokens_in": 5165, "tokens_out": 3260, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "272fb81a01063f4b", "ts": 1791530283.3193595} {"pid": "L3_050", "split": "dev", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.9558, "correct": true, "status": "ok", "speedup": 1.9558, "ref_ms": 12.66784, "cand_ms": 6.47695, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 90.2, "calls": 2, "tokens_in": 7376, "tokens_out": 5832, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2801629e256c5f7e", "ts": 1791530291.3611956} {"pid": "L2_052", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.3669, "correct": true, "status": "ok", "speedup": 1.3669, "ref_ms": 11.08277, "cand_ms": 8.10784, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 155.6, "calls": 2, "tokens_in": 11979, "tokens_out": 4104, "ctx_chars": 7687, "ctx_sha": "00b2f6d51bc8c639", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "81bac71105ba9169", "ts": 1791530292.6794198} {"pid": "L3_047", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 2.7637, "correct": true, "status": "ok", "speedup": 2.7637, "ref_ms": 3.64031, "cand_ms": 1.31719, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 121.9, "calls": 2, "tokens_in": 24522, "tokens_out": 10498, "ctx_chars": 14992, "ctx_sha": "82b6b58defdd0048", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "9f001f0a89abdc37", "ts": 1791530293.9820278} {"pid": "L3_008", "split": "dev", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.5497, "correct": true, "status": "ok", "speedup": 1.5497, "ref_ms": 5.21843, "cand_ms": 3.36733, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 227.6, "calls": 2, "tokens_in": 10829, "tokens_out": 19415, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0a31e80fb1b151a5", "ts": 1791530303.521421} {"pid": "L2_039", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.1068, "correct": true, "status": "ok", "speedup": 4.1068, "ref_ms": 30.02325, "cand_ms": 7.31061, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 214.3, "calls": 3, "tokens_in": 56807, "tokens_out": 17329, "ctx_chars": 26669, "ctx_sha": "3b6d6db80184b500", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "091cedf68d3dd272", "ts": 1791530317.698385} {"pid": "L2_037", "split": "dev", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.4607, "correct": true, "status": "ok", "speedup": 1.4607, "ref_ms": 19.69726, "cand_ms": 13.48519, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 142.5, "calls": 2, "tokens_in": 266649, "tokens_out": 6303, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "0f49d4e9d3a26e19", "ts": 1791530327.913019} {"pid": "L2_088", "split": "dev", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.3247, "correct": true, "status": "ok", "speedup": 3.3247, "ref_ms": 8.47553, "cand_ms": 2.54929, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 77.1, "calls": 2, "tokens_in": 16599, "tokens_out": 6072, "ctx_chars": 11583, "ctx_sha": "bb093721f8760f3d", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "bb462a16d9ab8960", "ts": 1791530334.0665822} {"pid": "L2_053", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": false, "score": 0.8447, "correct": true, "status": "ok", "speedup": 0.8447, "ref_ms": 16.00224, "cand_ms": 18.94414, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 111.8, "calls": 2, "tokens_in": 5538, "tokens_out": 5051, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "72a670f2dd18df93", "ts": 1791530338.6969483} {"pid": "L3_033", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.31, "correct": true, "status": "ok", "speedup": 1.31, "ref_ms": 20.4897, "cand_ms": 15.64052, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 133.5, "calls": 2, "tokens_in": 267294, "tokens_out": 7295, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "d960bd1fba4f5578", "ts": 1791530355.660179} {"pid": "L3_044", "split": "dev", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": false, "score": 0.2279, "correct": true, "status": "ok", "speedup": 0.2279, "ref_ms": 75.28384, "cand_ms": 330.35034, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 141.7, "calls": 2, "tokens_in": 9776, "tokens_out": 9989, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "bd5dfea7d5e53f6c", "ts": 1791530362.8363495} {"pid": "L3_002", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.3587, "correct": true, "status": "ok", "speedup": 2.3587, "ref_ms": 33.64157, "cand_ms": 14.26297, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 135.4, "calls": 2, "tokens_in": 20346, "tokens_out": 5120, "ctx_chars": 15055, "ctx_sha": "bf57b13b7f033578", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c2f289a1a3711c1b", "ts": 1791530362.9769902} {"pid": "L2_053", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.014, "correct": true, "status": "ok", "speedup": 1.014, "ref_ms": 15.97053, "cand_ms": 15.74975, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 69.5, "calls": 2, "tokens_in": 10644, "tokens_out": 1494, "ctx_chars": 7198, "ctx_sha": "e66d522755f291d1", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "7a1afc01ee86113b", "ts": 1791530363.469046} {"pid": "L2_088", "split": "dev", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.316, "correct": true, "status": "ok", "speedup": 1.316, "ref_ms": 8.45043, "cand_ms": 6.42132, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 89.9, "calls": 2, "tokens_in": 266961, "tokens_out": 6236, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "965fca88b96433ee", "ts": 1791530373.1942742} {"pid": "L2_088", "split": "dev", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.9076, "correct": true, "status": "ok", "speedup": 4.9076, "ref_ms": 8.52794, "cand_ms": 1.73769, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 92.3, "calls": 2, "tokens_in": 273965, "tokens_out": 4435, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "4dec6ace49b9873e", "ts": 1791530383.6567967} {"pid": "L1_078", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 7.9356, "correct": true, "status": "ok", "speedup": 7.9356, "ref_ms": 35.50945, "cand_ms": 4.47471, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 153.2, "calls": 2, "tokens_in": 25977, "tokens_out": 7797, "ctx_chars": 19130, "ctx_sha": "0551daeb8a590834", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2a194405b1edd76d", "ts": 1791530387.8688867} {"pid": "L2_063", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0048, "correct": true, "status": "ok", "speedup": 1.0048, "ref_ms": 7.98097, "cand_ms": 7.94266, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 70.3, "calls": 2, "tokens_in": 4480, "tokens_out": 3473, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "fd130105402d8ce9", "ts": 1791530398.2114818} {"pid": "L3_048", "split": "dev", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.0507, "correct": true, "status": "ok", "speedup": 3.0507, "ref_ms": 15.89085, "cand_ms": 5.20888, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 298.5, "calls": 4, "tokens_in": 43749, "tokens_out": 17579, "ctx_chars": 10330, "ctx_sha": "4725ef765672a6e6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8428c620e162a26e", "ts": 1791530414.8164418} {"pid": "L3_033", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.1896, "correct": true, "status": "ok", "speedup": 1.1896, "ref_ms": 20.58973, "cand_ms": 17.30775, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 132.3, "calls": 2, "tokens_in": 6530, "tokens_out": 6307, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "a0df9e4fb1ce78f0", "ts": 1791530424.9550438} {"pid": "L2_040", "split": "dev", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0297, "correct": true, "status": "ok", "speedup": 1.0297, "ref_ms": 30.42417, "cand_ms": 29.54717, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 73.1, "calls": 2, "tokens_in": 9156, "tokens_out": 2604, "ctx_chars": 5438, "ctx_sha": "5bb43e4b3db56789", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0d90a3c018cbedcd", "ts": 1791530435.9354663} {"pid": "L2_020", "split": "dev", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 9.8183, "correct": true, "status": "ok", "speedup": 9.8183, "ref_ms": 14.09236, "cand_ms": 1.43532, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 192.7, "calls": 2, "tokens_in": 26667, "tokens_out": 12289, "ctx_chars": 20061, "ctx_sha": "a0a8edb8b6ae64a6", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2ed5947868ac4f8d", "ts": 1791530439.1645908} {"pid": "L2_040", "split": "dev", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.4697, "correct": true, "status": "ok", "speedup": 4.4697, "ref_ms": 30.32001, "cand_ms": 6.78341, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 103.5, "calls": 2, "tokens_in": 24018, "tokens_out": 4155, "ctx_chars": 19121, "ctx_sha": "d421a9dea165588e", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "dac8e2ceee25c0ab", "ts": 1791530442.2195919} {"pid": "L1_078", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 3.288, "correct": true, "status": "ok", "speedup": 3.288, "ref_ms": 35.76034, "cand_ms": 10.8759, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 204.6, "calls": 2, "tokens_in": 6922, "tokens_out": 10537, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4fea9333218b94f8", "ts": 1791530454.8253605} {"pid": "L3_002", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.3685, "correct": true, "status": "ok", "speedup": 2.3685, "ref_ms": 33.72822, "cand_ms": 14.24006, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 140.6, "calls": 2, "tokens_in": 20403, "tokens_out": 5244, "ctx_chars": 15055, "ctx_sha": "bf57b13b7f033578", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "b0fa55a9a917182b", "ts": 1791530458.2794282} {"pid": "L2_040", "split": "dev", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.0354, "correct": true, "status": "ok", "speedup": 1.0354, "ref_ms": 30.40062, "cand_ms": 29.36196, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 104.0, "calls": 2, "tokens_in": 266092, "tokens_out": 5301, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "2da14cba249f2c17", "ts": 1791530467.0118427} {"pid": "L2_058", "split": "dev", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 9.4229, "correct": true, "status": "ok", "speedup": 9.4229, "ref_ms": 25.13643, "cand_ms": 2.6676, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 133.0, "calls": 2, "tokens_in": 13746, "tokens_out": 6947, "ctx_chars": 8031, "ctx_sha": "8e7ee93b3140d14f", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2e6992bdcd980bd0", "ts": 1791530467.0726867} {"pid": "L2_063", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.5823, "correct": true, "status": "ok", "speedup": 3.5823, "ref_ms": 8.07525, "cand_ms": 2.25418, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 61.8, "calls": 2, "tokens_in": 22920, "tokens_out": 3084, "ctx_chars": 18655, "ctx_sha": "bbf921975c58f49c", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "a0830310d6ac45d1", "ts": 1791530476.5669615} {"pid": "L1_066", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.4088, "correct": true, "status": "ok", "speedup": 1.4088, "ref_ms": 7.80182, "cand_ms": 5.53791, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 227.7, "calls": 3, "tokens_in": 16910, "tokens_out": 13829, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "71b6e2536f0bd7ab", "ts": 1791530484.5688674} {"pid": "L2_037", "split": "dev", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.6915, "correct": true, "status": "ok", "speedup": 4.6915, "ref_ms": 19.76459, "cand_ms": 4.21289, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 130.1, "calls": 2, "tokens_in": 273866, "tokens_out": 5040, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "5aa2ccf596a76dde", "ts": 1791530485.7155538} {"pid": "L2_037", "split": "dev", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.7436, "correct": true, "status": "ok", "speedup": 4.7436, "ref_ms": 19.85409, "cand_ms": 4.18549, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 125.2, "calls": 2, "tokens_in": 19906, "tokens_out": 4260, "ctx_chars": 14516, "ctx_sha": "491a69f435bf3217", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "b8ce9accccbabb83", "ts": 1791530488.6364486} {"pid": "L2_069", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.2585, "correct": true, "status": "ok", "speedup": 1.2585, "ref_ms": 3.64029, "cand_ms": 2.89259, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 216.2, "calls": 2, "tokens_in": 265566, "tokens_out": 3491, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0352bb7581f22254", "ts": 1791530488.892358} {"pid": "L3_002", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.3666, "correct": true, "status": "ok", "speedup": 3.3666, "ref_ms": 33.57706, "cand_ms": 9.9737, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 300.8, "calls": 4, "tokens_in": 35366, "tokens_out": 15541, "ctx_chars": 7962, "ctx_sha": "19b168bb78ddbdc4", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "67b6b27556da0ee3", "ts": 1791530505.4067943} {"pid": "L2_058", "split": "dev", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 8.6799, "correct": true, "status": "ok", "speedup": 8.6799, "ref_ms": 25.11367, "cand_ms": 2.89332, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 108.9, "calls": 2, "tokens_in": 13575, "tokens_out": 6985, "ctx_chars": 8031, "ctx_sha": "8e7ee93b3140d14f", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "fa9ae1dadad7212b", "ts": 1791530507.0704997} {"pid": "L3_050", "split": "dev", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.6906, "correct": true, "status": "ok", "speedup": 2.6906, "ref_ms": 12.75854, "cand_ms": 4.74186, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 91.5, "calls": 2, "tokens_in": 6713, "tokens_out": 3984, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "017d2f10dca05ce0", "ts": 1791530516.4361598} {"pid": "L3_050", "split": "dev", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 138.8, "calls": 3, "tokens_in": 38171, "tokens_out": 11503, "ctx_chars": 15252, "ctx_sha": "575b4fa0082f404b", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "9cfc04719724802e", "ts": 1791530522.4632106} {"pid": "L2_088", "split": "dev", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.5208, "correct": true, "status": "ok", "speedup": 1.5208, "ref_ms": 8.48516, "cand_ms": 5.57947, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 92.5, "calls": 2, "tokens_in": 5877, "tokens_out": 5241, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "303c84d5e654ffcb", "ts": 1791530528.4350188} {"pid": "L2_052", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.3523, "correct": true, "status": "ok", "speedup": 1.3523, "ref_ms": 11.07459, "cand_ms": 8.18938, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 232.1, "calls": 2, "tokens_in": 267509, "tokens_out": 8733, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "dd2a022d48605afa", "ts": 1791530535.6475866} {"pid": "L3_047", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.6767, "correct": true, "status": "ok", "speedup": 2.6767, "ref_ms": 3.64316, "cand_ms": 1.36107, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 152.6, "calls": 2, "tokens_in": 9267, "tokens_out": 13755, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "c9e836497ce828b5", "ts": 1791530540.5044422} {"pid": "L3_050", "split": "dev", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.1073, "correct": true, "status": "ok", "speedup": 2.1073, "ref_ms": 12.69125, "cand_ms": 6.0225, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 79.2, "calls": 2, "tokens_in": 9375, "tokens_out": 5015, "ctx_chars": 3184, "ctx_sha": "e64357aa997958f6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d5692399e77b3f1e", "ts": 1791530546.2493947} {"pid": "L3_050", "split": "dev", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.4827, "correct": true, "status": "ok", "speedup": 4.4827, "ref_ms": 12.81186, "cand_ms": 2.85809, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 183.0, "calls": 3, "tokens_in": 31229, "tokens_out": 15176, "ctx_chars": 10330, "ctx_sha": "4725ef765672a6e6", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "602ebd47081af4ab", "ts": 1791530556.213478} {"pid": "L2_067", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.6583, "correct": true, "status": "ok", "speedup": 3.6583, "ref_ms": 12.92726, "cand_ms": 3.5337, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 80.4, "calls": 2, "tokens_in": 18460, "tokens_out": 5582, "ctx_chars": 14070, "ctx_sha": "3d6ada40588e7cb1", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d61f2a423c394560", "ts": 1791530557.0137432} {"pid": "L2_037", "split": "dev", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.2735, "correct": true, "status": "ok", "speedup": 1.2735, "ref_ms": 19.71913, "cand_ms": 15.484, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 92.4, "calls": 2, "tokens_in": 10384, "tokens_out": 3037, "ctx_chars": 6342, "ctx_sha": "c3ce68171bb279a4", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "cfbd54ea1ca6d83e", "ts": 1791530559.4494872} {"pid": "L2_088", "split": "dev", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.7746, "correct": true, "status": "ok", "speedup": 3.7746, "ref_ms": 8.49138, "cand_ms": 2.24962, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 72.0, "calls": 2, "tokens_in": 23823, "tokens_out": 5235, "ctx_chars": 18655, "ctx_sha": "bbf921975c58f49c", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "e3cd0b2605ee44af", "ts": 1791530560.92636} {"pid": "L2_092", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.7308, "correct": true, "status": "ok", "speedup": 2.7308, "ref_ms": 8.51444, "cand_ms": 3.11788, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 132.0, "calls": 2, "tokens_in": 7868, "tokens_out": 11941, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "069cd6159a0d8b1c", "ts": 1791530574.1970785} {"pid": "L3_033", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.5004, "correct": true, "status": "ok", "speedup": 2.5004, "ref_ms": 20.54483, "cand_ms": 8.21663, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 122.5, "calls": 2, "tokens_in": 13983, "tokens_out": 9559, "ctx_chars": 7910, "ctx_sha": "434d12593ff4fff3", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "241e62566390b6bc", "ts": 1791530608.1982234} {"pid": "L3_020", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.9555, "correct": true, "status": "ok", "speedup": 1.9555, "ref_ms": 7.10236, "cand_ms": 3.63199, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 357.3, "calls": 3, "tokens_in": 417203, "tokens_out": 24196, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "b0136d6da8982bc5", "ts": 1791530614.7277918} {"pid": "L2_062", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.3171, "correct": true, "status": "ok", "speedup": 1.3171, "ref_ms": 8.5366, "cand_ms": 6.48118, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 102.1, "calls": 2, "tokens_in": 266525, "tokens_out": 5818, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "0684f2d57b90fc11", "ts": 1791530624.5658941} {"pid": "L2_053", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.0736, "correct": true, "status": "ok", "speedup": 4.0736, "ref_ms": 16.03448, "cand_ms": 3.93618, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 82.5, "calls": 2, "tokens_in": 23469, "tokens_out": 3629, "ctx_chars": 18655, "ctx_sha": "bbf921975c58f49c", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "0a032d3c9f056411", "ts": 1791530639.5441363} {"pid": "L2_062", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "outputs produced during timing do not match the reference (output mismatch beyond atol=rtol=0.0001); results must not be cached or skipped", "wall_s": 134.3, "calls": 3, "tokens_in": 32939, "tokens_out": 10534, "ctx_chars": 14516, "ctx_sha": "491a69f435bf3217", "uses_bf16": false, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "04c939ac51578043", "ts": 1791530639.7322223} {"pid": "L2_063", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.546, "correct": true, "status": "ok", "speedup": 3.546, "ref_ms": 8.10469, "cand_ms": 2.28557, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 82.0, "calls": 2, "tokens_in": 22848, "tokens_out": 3252, "ctx_chars": 18655, "ctx_sha": "bbf921975c58f49c", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "d5c6d98cf5dfdbb0", "ts": 1791530642.9194098} {"pid": "L1_066", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.241, "correct": true, "status": "ok", "speedup": 2.241, "ref_ms": 7.77074, "cand_ms": 3.46753, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 185.8, "calls": 2, "tokens_in": 268022, "tokens_out": 10231, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "97e9f9e20c49c1ea", "ts": 1791530644.060281} {"pid": "L2_073", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.1575, "correct": true, "status": "ok", "speedup": 4.1575, "ref_ms": 6.38884, "cand_ms": 1.53669, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 190.0, "calls": 2, "tokens_in": 29525, "tokens_out": 12745, "ctx_chars": 22975, "ctx_sha": "4e003dc4030b57a1", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8fc81e3623341d20", "ts": 1791530644.8279881} {"pid": "L3_044", "split": "dev", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.2942, "correct": true, "status": "ok", "speedup": 1.2942, "ref_ms": 75.38292, "cand_ms": 58.24712, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 130.0, "calls": 2, "tokens_in": 11612, "tokens_out": 9120, "ctx_chars": 3184, "ctx_sha": "e64357aa997958f6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e09f0ba4f502e046", "ts": 1791530646.4093835} {"pid": "L1_066", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.6767, "correct": true, "status": "ok", "speedup": 1.6767, "ref_ms": 7.8085, "cand_ms": 4.65694, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 164.3, "calls": 2, "tokens_in": 15263, "tokens_out": 8383, "ctx_chars": 8854, "ctx_sha": "420ebf050379abd1", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "7f3f876aac5f5a74", "ts": 1791530652.9735012} {"pid": "L2_040", "split": "dev", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.3961, "correct": true, "status": "ok", "speedup": 4.3961, "ref_ms": 30.46734, "cand_ms": 6.93048, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 79.9, "calls": 2, "tokens_in": 19445, "tokens_out": 3671, "ctx_chars": 14516, "ctx_sha": "491a69f435bf3217", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "3f3dfefb9702ad66", "ts": 1791530654.0681946} {"pid": "L2_020", "split": "dev", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.4363, "correct": true, "status": "ok", "speedup": 1.4363, "ref_ms": 13.98175, "cand_ms": 9.73441, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 108.4, "calls": 2, "tokens_in": 11000, "tokens_out": 1559, "ctx_chars": 7394, "ctx_sha": "632a38c7eee085c0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "053c6a66ee8daa72", "ts": 1791530654.6344948} {"pid": "L3_008", "split": "dev", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.2407, "correct": true, "status": "ok", "speedup": 1.2407, "ref_ms": 5.25824, "cand_ms": 4.23809, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 128.4, "calls": 2, "tokens_in": 17094, "tokens_out": 9635, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ef76bbefa20cba0c", "ts": 1791530656.8111382} {"pid": "L2_053", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.0473, "correct": true, "status": "ok", "speedup": 1.0473, "ref_ms": 15.99329, "cand_ms": 15.27102, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 100.9, "calls": 2, "tokens_in": 266012, "tokens_out": 5060, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "b4ec589ec69dd6a7", "ts": 1791530660.3908577} {"pid": "L2_029", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0054, "correct": true, "status": "ok", "speedup": 1.0054, "ref_ms": 7.98362, "cand_ms": 7.94041, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 51.6, "calls": 2, "tokens_in": 4008, "tokens_out": 2213, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "5fbdf8ff71bf09af", "ts": 1791530666.3192096} {"pid": "L2_039", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.1994, "correct": true, "status": "ok", "speedup": 1.1994, "ref_ms": 30.133, "cand_ms": 25.12259, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 227.5, "calls": 2, "tokens_in": 268256, "tokens_out": 10979, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "0701b4e5296d3a04", "ts": 1791530666.7011647} {"pid": "L2_058", "split": "dev", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 6.6066, "correct": true, "status": "ok", "speedup": 6.6066, "ref_ms": 25.19705, "cand_ms": 3.81395, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 205.4, "calls": 2, "tokens_in": 267584, "tokens_out": 8901, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "bfea51b791baa3ea", "ts": 1791530689.9437284} {"pid": "L2_052", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.3938, "correct": true, "status": "ok", "speedup": 1.3938, "ref_ms": 10.9766, "cand_ms": 7.8755, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 157.0, "calls": 2, "tokens_in": 5787, "tokens_out": 6502, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "16fe7a2e0e1fae4b", "ts": 1791530713.2631311} {"pid": "L3_050", "split": "dev", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.7964, "correct": true, "status": "ok", "speedup": 1.7964, "ref_ms": 12.66721, "cand_ms": 7.05135, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 75.3, "calls": 2, "tokens_in": 6977, "tokens_out": 4489, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c81b5d010b94bf34", "ts": 1791530721.7508216} {"pid": "L3_002", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.1603, "correct": true, "status": "ok", "speedup": 1.1603, "ref_ms": 33.58198, "cand_ms": 28.9434, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 138.3, "calls": 2, "tokens_in": 15298, "tokens_out": 5167, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "133ae6090ca21a94", "ts": 1791530746.4715455} {"pid": "L2_029", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.6254, "correct": true, "status": "ok", "speedup": 4.6254, "ref_ms": 8.00213, "cand_ms": 1.73002, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 83.4, "calls": 2, "tokens_in": 273221, "tokens_out": 4485, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "139db7595da8daea", "ts": 1791530750.0704002} {"pid": "L2_067", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.7412, "correct": true, "status": "ok", "speedup": 3.7412, "ref_ms": 12.92816, "cand_ms": 3.45562, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 126.0, "calls": 3, "tokens_in": 30674, "tokens_out": 8219, "ctx_chars": 14070, "ctx_sha": "3d6ada40588e7cb1", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "63e345b5ee17b3b1", "ts": 1791530750.607815} {"pid": "L2_092", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.6105, "correct": true, "status": "ok", "speedup": 2.6105, "ref_ms": 8.61375, "cand_ms": 3.29971, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 115.3, "calls": 2, "tokens_in": 20243, "tokens_out": 8497, "ctx_chars": 14961, "ctx_sha": "549d04579f777963", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "942b3d74a3a67562", "ts": 1791530754.821748} {"pid": "L3_050", "split": "dev", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.7015, "correct": true, "status": "ok", "speedup": 2.7015, "ref_ms": 12.67832, "cand_ms": 4.69308, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 101.9, "calls": 2, "tokens_in": 9469, "tokens_out": 5867, "ctx_chars": 3184, "ctx_sha": "e64357aa997958f6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "602d9c6c3817c3cb", "ts": 1791530756.0136352} {"pid": "L2_029", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.5098, "correct": true, "status": "ok", "speedup": 1.5098, "ref_ms": 8.04805, "cand_ms": 5.33061, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 106.8, "calls": 2, "tokens_in": 5377, "tokens_out": 5347, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "7235f7e2f9804837", "ts": 1791530761.435104} {"pid": "L2_037", "split": "dev", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.7535, "correct": true, "status": "ok", "speedup": 4.7535, "ref_ms": 20.03137, "cand_ms": 4.21402, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 142.1, "calls": 2, "tokens_in": 273841, "tokens_out": 5211, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "dc23587ac2b8cb4a", "ts": 1791530786.163303} {"pid": "L2_052", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.3454, "correct": true, "status": "ok", "speedup": 1.3454, "ref_ms": 11.11535, "cand_ms": 8.26158, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 252.8, "calls": 2, "tokens_in": 267578, "tokens_out": 8848, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4100c9df019539ac", "ts": 1791530793.2779822} {"pid": "L2_073", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.6306, "correct": true, "status": "ok", "speedup": 1.6306, "ref_ms": 5.60246, "cand_ms": 3.43581, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 139.3, "calls": 2, "tokens_in": 10888, "tokens_out": 4328, "ctx_chars": 6744, "ctx_sha": "b92173e1465ccf4d", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c3fe57fcc24d829e", "ts": 1791530799.6429884} {"pid": "L3_048", "split": "dev", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.1804, "correct": true, "status": "ok", "speedup": 1.1804, "ref_ms": 15.96785, "cand_ms": 13.52712, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 299.6, "calls": 5, "tokens_in": 31786, "tokens_out": 16251, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "300d877d6030dff3", "ts": 1791530806.6464486} {"pid": "L2_092", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.3504, "correct": true, "status": "ok", "speedup": 2.3504, "ref_ms": 8.56542, "cand_ms": 3.64427, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 69.3, "calls": 2, "tokens_in": 10728, "tokens_out": 4987, "ctx_chars": 5747, "ctx_sha": "169afaa9eeb4d53a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "5f232cd49e4b3a33", "ts": 1791530825.315682} {"pid": "L3_033", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 1, "success": true, "score": 1.5189, "correct": true, "status": "ok", "speedup": 1.5189, "ref_ms": 20.56996, "cand_ms": 13.54265, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 159.6, "calls": 2, "tokens_in": 11059, "tokens_out": 7623, "ctx_chars": 5350, "ctx_sha": "333d78223eeced7d", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "657436d57648e2f4", "ts": 1791530825.9342077} {"pid": "L1_066", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.8603, "correct": true, "status": "ok", "speedup": 1.8603, "ref_ms": 7.76572, "cand_ms": 4.1745, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 192.0, "calls": 2, "tokens_in": 15046, "tokens_out": 8099, "ctx_chars": 8854, "ctx_sha": "420ebf050379abd1", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "5992d4d0f24fc3bf", "ts": 1791530836.8750718} {"pid": "L2_062", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.3349, "correct": true, "status": "ok", "speedup": 1.3349, "ref_ms": 8.65413, "cand_ms": 6.48302, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 116.4, "calls": 2, "tokens_in": 266517, "tokens_out": 5682, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "cede9c75a49226d8", "ts": 1791530838.1564522} {"pid": "L3_033", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 2.7128, "correct": true, "status": "ok", "speedup": 2.7128, "ref_ms": 20.58436, "cand_ms": 7.58777, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 157.0, "calls": 2, "tokens_in": 14215, "tokens_out": 12251, "ctx_chars": 7910, "ctx_sha": "434d12593ff4fff3", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "a04ddf671abced4a", "ts": 1791530846.8958426} {"pid": "L2_029", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.5505, "correct": true, "status": "ok", "speedup": 3.5505, "ref_ms": 8.00427, "cand_ms": 2.25443, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 64.9, "calls": 2, "tokens_in": 23720, "tokens_out": 4215, "ctx_chars": 19121, "ctx_sha": "d421a9dea165588e", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "cf221db4c0768b78", "ts": 1791530858.1745865} {"pid": "L3_047", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": false, "score": 0.2525, "correct": true, "status": "ok", "speedup": 0.2525, "ref_ms": 3.63923, "cand_ms": 14.41052, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 215.7, "calls": 2, "tokens_in": 278075, "tokens_out": 14922, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "b380f22da7087597", "ts": 1791530868.6338048} {"pid": "L2_073", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.7116, "correct": true, "status": "ok", "speedup": 1.7116, "ref_ms": 5.60506, "cand_ms": 3.27485, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 236.9, "calls": 2, "tokens_in": 267917, "tokens_out": 9217, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "62ad0183644e3881", "ts": 1791530879.8420298} {"pid": "L2_092", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.4241, "correct": true, "status": "ok", "speedup": 2.4241, "ref_ms": 8.57667, "cand_ms": 3.53803, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 72.5, "calls": 2, "tokens_in": 10534, "tokens_out": 4009, "ctx_chars": 5747, "ctx_sha": "169afaa9eeb4d53a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c9b79977c64b09e8", "ts": 1791530897.7682693} {"pid": "L2_020", "split": "dev", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.4305, "correct": true, "status": "ok", "speedup": 1.4305, "ref_ms": 14.0005, "cand_ms": 9.78689, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 144.0, "calls": 2, "tokens_in": 4854, "tokens_out": 2369, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2d62c50936845f6e", "ts": 1791530898.8219945} {"pid": "L2_063", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.5916, "correct": true, "status": "ok", "speedup": 3.5916, "ref_ms": 8.04084, "cand_ms": 2.23879, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 95.9, "calls": 2, "tokens_in": 15877, "tokens_out": 6175, "ctx_chars": 11583, "ctx_sha": "bb093721f8760f3d", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "000369874e866268", "ts": 1791530902.5523405} {"pid": "L2_020", "split": "dev", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.4482, "correct": true, "status": "ok", "speedup": 1.4482, "ref_ms": 14.30983, "cand_ms": 9.8809, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 167.8, "calls": 2, "tokens_in": 4916, "tokens_out": 2388, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "48e87ede50f46284", "ts": 1791530914.274168} {"pid": "L1_066", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.619, "correct": true, "status": "ok", "speedup": 1.619, "ref_ms": 7.76618, "cand_ms": 4.79695, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 276.5, "calls": 2, "tokens_in": 268769, "tokens_out": 13778, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c19de0548975c1c0", "ts": 1791530916.236664} {"pid": "L3_033", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.1771, "correct": true, "status": "ok", "speedup": 2.1771, "ref_ms": 20.76207, "cand_ms": 9.53636, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 387.7, "calls": 4, "tokens_in": 41117, "tokens_out": 27384, "ctx_chars": 7910, "ctx_sha": "434d12593ff4fff3", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "092dc451b07f4a41", "ts": 1791530923.323209} {"pid": "L3_044", "split": "dev", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.2491, "correct": true, "status": "ok", "speedup": 1.2491, "ref_ms": 75.38653, "cand_ms": 60.35406, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 171.0, "calls": 2, "tokens_in": 10732, "tokens_out": 11973, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4c0497f38b7c4e8e", "ts": 1791530932.401896} {"pid": "L2_039", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.2287, "correct": true, "status": "ok", "speedup": 4.2287, "ref_ms": 30.21004, "cand_ms": 7.14401, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 223.1, "calls": 3, "tokens_in": 56534, "tokens_out": 15783, "ctx_chars": 26669, "ctx_sha": "3b6d6db80184b500", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "f10a38505d7910b6", "ts": 1791530973.1483274} {"pid": "L3_002", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0289, "correct": true, "status": "ok", "speedup": 1.0289, "ref_ms": 33.70144, "cand_ms": 32.75612, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 128.5, "calls": 2, "tokens_in": 14997, "tokens_out": 4474, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "19cefa76efb02a53", "ts": 1791530975.360211} {"pid": "L2_073", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.6184, "correct": true, "status": "ok", "speedup": 1.6184, "ref_ms": 5.60169, "cand_ms": 3.46119, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 118.9, "calls": 2, "tokens_in": 10901, "tokens_out": 4462, "ctx_chars": 6744, "ctx_sha": "b92173e1465ccf4d", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "a4691b84dbbd719e", "ts": 1791530977.0576084} {"pid": "L3_033", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0333, "correct": true, "status": "ok", "speedup": 1.0333, "ref_ms": 20.59226, "cand_ms": 19.92804, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 99.4, "calls": 2, "tokens_in": 9894, "tokens_out": 3358, "ctx_chars": 5350, "ctx_sha": "333d78223eeced7d", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "7ed1076a9bea4649", "ts": 1791530979.2825787} {"pid": "L3_002", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.3687, "correct": true, "status": "ok", "speedup": 1.3687, "ref_ms": 33.62953, "cand_ms": 24.57113, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 142.7, "calls": 2, "tokens_in": 5626, "tokens_out": 5495, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "d9f81d9476cd8969", "ts": 1791530980.9017754} {"pid": "L2_081", "split": "dev", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.033, "correct": true, "status": "ok", "speedup": 1.033, "ref_ms": 8.25092, "cand_ms": 7.98705, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 72.1, "calls": 2, "tokens_in": 4898, "tokens_out": 2390, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "15f965ea732b75cb", "ts": 1791530988.336675} {"pid": "L3_008", "split": "dev", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.5249, "correct": true, "status": "ok", "speedup": 1.5249, "ref_ms": 5.23638, "cand_ms": 3.43391, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 279.5, "calls": 2, "tokens_in": 11816, "tokens_out": 21762, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "82ca39a2677515e7", "ts": 1791530992.7544518} {"pid": "L2_092", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.7059, "correct": true, "status": "ok", "speedup": 2.7059, "ref_ms": 8.53111, "cand_ms": 3.15282, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 203.6, "calls": 2, "tokens_in": 267667, "tokens_out": 7751, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d767b0ea055297fe", "ts": 1791531003.2494528} {"pid": "L1_066", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.9015, "correct": true, "status": "ok", "speedup": 1.9015, "ref_ms": 7.7895, "cand_ms": 4.09658, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 351.6, "calls": 3, "tokens_in": 408015, "tokens_out": 15011, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "06cdaf97895c69ae", "ts": 1791531008.448501} {"pid": "L2_037", "split": "dev", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.2845, "correct": true, "status": "ok", "speedup": 1.2845, "ref_ms": 19.8395, "cand_ms": 15.44475, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 111.6, "calls": 2, "tokens_in": 4699, "tokens_out": 2491, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c0bd31f87bf43554", "ts": 1791531010.4023788} {"pid": "L3_002", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.3187, "correct": true, "status": "ok", "speedup": 1.3187, "ref_ms": 33.66876, "cand_ms": 25.53257, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 225.9, "calls": 2, "tokens_in": 265994, "tokens_out": 4266, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "b3e8c35470a2db86", "ts": 1791531012.0690918} {"pid": "L2_067", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 2.4736, "correct": true, "status": "ok", "speedup": 2.4736, "ref_ms": 12.91948, "cand_ms": 5.22285, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 188.9, "calls": 3, "tokens_in": 14570, "tokens_out": 12798, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "cb4eb91a1f5ec9f3", "ts": 1791531014.7962236} {"pid": "L3_050", "split": "dev", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 5.8292, "correct": true, "status": "ok", "speedup": 5.8292, "ref_ms": 12.77137, "cand_ms": 2.19091, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 272.1, "calls": 4, "tokens_in": 71710, "tokens_out": 21701, "ctx_chars": 22253, "ctx_sha": "e98f6866890474ec", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "60a1a9a501745e90", "ts": 1791531022.7029626} {"pid": "L2_029", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.5667, "correct": true, "status": "ok", "speedup": 3.5667, "ref_ms": 8.01628, "cand_ms": 2.24752, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 61.8, "calls": 2, "tokens_in": 19461, "tokens_out": 3970, "ctx_chars": 14516, "ctx_sha": "491a69f435bf3217", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "09e8228a4ac3090a", "ts": 1791531037.2094529} {"pid": "L2_020", "split": "dev", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.4188, "correct": true, "status": "ok", "speedup": 1.4188, "ref_ms": 14.05863, "cand_ms": 9.90886, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 216.3, "calls": 2, "tokens_in": 266324, "tokens_out": 4617, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1c6080d047d91ffb", "ts": 1791531053.1721737} {"pid": "L2_052", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.4086, "correct": true, "status": "ok", "speedup": 1.4086, "ref_ms": 11.03825, "cand_ms": 7.83606, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 131.2, "calls": 2, "tokens_in": 12008, "tokens_out": 4294, "ctx_chars": 7687, "ctx_sha": "00b2f6d51bc8c639", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "85ba9e7164f8170f", "ts": 1791531054.5685325} {"pid": "L2_029", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": false, "score": 1.0053, "correct": true, "status": "ok", "speedup": 1.0053, "ref_ms": 8.08014, "cand_ms": 8.03775, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 60.9, "calls": 2, "tokens_in": 8631, "tokens_out": 2161, "ctx_chars": 5477, "ctx_sha": "8765bd9517445b21", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "9b4068d4beed8e73", "ts": 1791531064.1136034} {"pid": "L3_047", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.2495, "correct": true, "status": "ok", "speedup": 2.2495, "ref_ms": 3.66682, "cand_ms": 1.63005, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 162.1, "calls": 2, "tokens_in": 22482, "tokens_out": 11238, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "73767b3474203309", "ts": 1791531064.606707} {"pid": "L2_037", "split": "dev", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.2796, "correct": true, "status": "ok", "speedup": 1.2796, "ref_ms": 19.76611, "cand_ms": 15.44659, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 138.5, "calls": 2, "tokens_in": 5117, "tokens_out": 3303, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d5eb4cb0c4b939f0", "ts": 1791531070.877662} {"pid": "L3_044", "split": "dev", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.4933, "correct": true, "status": "ok", "speedup": 4.4933, "ref_ms": 75.4636, "cand_ms": 16.79459, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 176.0, "calls": 2, "tokens_in": 34109, "tokens_out": 14287, "ctx_chars": 22253, "ctx_sha": "e98f6866890474ec", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "14f2afbc5194b527", "ts": 1791531073.7582836} {"pid": "L2_029", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.567, "correct": true, "status": "ok", "speedup": 3.567, "ref_ms": 8.11204, "cand_ms": 2.27419, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 89.0, "calls": 2, "tokens_in": 23653, "tokens_out": 3790, "ctx_chars": 19121, "ctx_sha": "d421a9dea165588e", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "c6c4810c3091791e", "ts": 1791531077.3185194} {"pid": "L2_069", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.2426, "correct": true, "status": "ok", "speedup": 1.2426, "ref_ms": 3.67264, "cand_ms": 2.95556, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 118.6, "calls": 2, "tokens_in": 12421, "tokens_out": 1998, "ctx_chars": 9026, "ctx_sha": "a3512fc398ca432b", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "273400610c693966", "ts": 1791531091.7968884} {"pid": "L2_063", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0044, "correct": true, "status": "ok", "speedup": 1.0044, "ref_ms": 8.00531, "cand_ms": 7.96986, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 91.0, "calls": 2, "tokens_in": 3916, "tokens_out": 1829, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "7737fa9d83da616e", "ts": 1791531099.468771} {"pid": "L2_069", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.263, "correct": true, "status": "ok", "speedup": 1.263, "ref_ms": 3.63617, "cand_ms": 2.87908, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 238.7, "calls": 2, "tokens_in": 265395, "tokens_out": 3141, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "119b4f9a4cada048", "ts": 1791531107.3162794} {"pid": "L2_029", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.3832, "correct": true, "status": "ok", "speedup": 3.3832, "ref_ms": 8.07228, "cand_ms": 2.38598, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 87.3, "calls": 2, "tokens_in": 19330, "tokens_out": 3729, "ctx_chars": 14516, "ctx_sha": "491a69f435bf3217", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "1367d1a017be32a0", "ts": 1791531109.988302} {"pid": "L2_092", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.6856, "correct": true, "status": "ok", "speedup": 2.6856, "ref_ms": 8.67742, "cand_ms": 3.23105, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 201.8, "calls": 2, "tokens_in": 267274, "tokens_out": 7186, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "7bcfdebf05ed63e5", "ts": 1791531116.0846124} {"pid": "L2_081", "split": "dev", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.1689, "correct": true, "status": "ok", "speedup": 1.1689, "ref_ms": 8.23932, "cand_ms": 7.049, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 139.2, "calls": 3, "tokens_in": 402522, "tokens_out": 7527, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "580ed25d8eee2164", "ts": 1791531120.0998585} {"pid": "L2_029", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0056, "correct": true, "status": "ok", "speedup": 1.0056, "ref_ms": 8.00747, "cand_ms": 7.96316, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 46.1, "calls": 2, "tokens_in": 4004, "tokens_out": 2075, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "fd277c51b7557b61", "ts": 1791531137.9251797} {"pid": "L1_078", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 8.1811, "correct": true, "status": "ok", "speedup": 8.1811, "ref_ms": 35.56035, "cand_ms": 4.34666, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 143.8, "calls": 2, "tokens_in": 25449, "tokens_out": 6721, "ctx_chars": 19130, "ctx_sha": "0551daeb8a590834", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ab146301f7a7bd43", "ts": 1791531158.5491242} {"pid": "L3_002", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.2908, "correct": true, "status": "ok", "speedup": 1.2908, "ref_ms": 33.72589, "cand_ms": 26.12715, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 168.8, "calls": 2, "tokens_in": 5482, "tokens_out": 4977, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "62a19b5fd860b203", "ts": 1791531179.2518892} {"pid": "L2_062", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.6905, "correct": true, "status": "ok", "speedup": 3.6905, "ref_ms": 8.55092, "cand_ms": 2.31701, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 206.1, "calls": 3, "tokens_in": 28908, "tokens_out": 11633, "ctx_chars": 12049, "ctx_sha": "cd92549f2b7fd121", "uses_bf16": false, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "b8035fc6f7cdfe09", "ts": 1791531183.1382897} {"pid": "L2_037", "split": "dev", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.2827, "correct": true, "status": "ok", "speedup": 1.2827, "ref_ms": 19.74643, "cand_ms": 15.39409, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 109.1, "calls": 2, "tokens_in": 5327, "tokens_out": 3759, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "25260de269336190", "ts": 1791531186.464798} {"pid": "L2_067", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.0856, "correct": true, "status": "ok", "speedup": 2.0856, "ref_ms": 12.85412, "cand_ms": 6.16318, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 127.4, "calls": 3, "tokens_in": 402157, "tokens_out": 9525, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "53b6c17bb33d8136", "ts": 1791531191.9681168} {"pid": "L3_002", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.2553, "correct": true, "status": "ok", "speedup": 1.2553, "ref_ms": 33.69771, "cand_ms": 26.84508, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 142.7, "calls": 2, "tokens_in": 15097, "tokens_out": 4967, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "6dad3048ee7b8eae", "ts": 1791531216.471558} {"pid": "L3_020", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.1861, "correct": true, "status": "ok", "speedup": 1.1861, "ref_ms": 6.9786, "cand_ms": 5.88361, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 166.0, "calls": 2, "tokens_in": 19884, "tokens_out": 10425, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "847a37bce7f0ddcc", "ts": 1791531219.1227667} {"pid": "L2_069", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.3383, "correct": true, "status": "ok", "speedup": 3.3383, "ref_ms": 4.03704, "cand_ms": 1.2093, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 172.1, "calls": 2, "tokens_in": 20054, "tokens_out": 4987, "ctx_chars": 15668, "ctx_sha": "bb1fdfba7b87d1ff", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "5a46025519a4d567", "ts": 1791531226.656127} {"pid": "L3_002", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.3195, "correct": true, "status": "ok", "speedup": 1.3195, "ref_ms": 33.69816, "cand_ms": 25.53861, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 215.7, "calls": 2, "tokens_in": 266266, "tokens_out": 5071, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "23b8115d80152c79", "ts": 1791531227.8015647} {"pid": "L2_053", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 4.1918, "correct": true, "status": "ok", "speedup": 4.1918, "ref_ms": 15.90211, "cand_ms": 3.79365, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 127.8, "calls": 2, "tokens_in": 16119, "tokens_out": 5112, "ctx_chars": 11583, "ctx_sha": "bb093721f8760f3d", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "e8418f0f1e46f262", "ts": 1791531235.0964375} {"pid": "L3_044", "split": "dev", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.1466, "correct": true, "status": "ok", "speedup": 4.1466, "ref_ms": 75.28741, "cand_ms": 18.15661, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 166.7, "calls": 2, "tokens_in": 21162, "tokens_out": 14428, "ctx_chars": 10330, "ctx_sha": "4725ef765672a6e6", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "c64289b4e6eeb981", "ts": 1791531237.570372} {"pid": "L3_002", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 2.5366, "correct": true, "status": "ok", "speedup": 2.5366, "ref_ms": 33.6661, "cand_ms": 13.27201, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 192.9, "calls": 2, "tokens_in": 13261, "tokens_out": 8072, "ctx_chars": 7962, "ctx_sha": "19b168bb78ddbdc4", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "75d4b8c1425a975a", "ts": 1791531257.0029507} {"pid": "L2_058", "split": "dev", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 22.4941, "ref_ms": 25.12576, "cand_ms": 1.11699, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 270.6, "calls": 2, "tokens_in": 268149, "tokens_out": 11953, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ca51366fd1450ce4", "ts": 1791531263.3780422} {"pid": "L1_078", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.3137, "correct": true, "status": "ok", "speedup": 2.3137, "ref_ms": 35.66015, "cand_ms": 15.41281, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 98.8, "calls": 2, "tokens_in": 12194, "tokens_out": 2676, "ctx_chars": 7879, "ctx_sha": "f7c7999053853d91", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f181c33fa05d5a8c", "ts": 1791531285.286467} {"pid": "L2_092", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.7212, "correct": true, "status": "ok", "speedup": 2.7212, "ref_ms": 8.58479, "cand_ms": 3.15478, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 178.6, "calls": 2, "tokens_in": 267249, "tokens_out": 6448, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1187bcb7fa543ad4", "ts": 1791531298.669497} {"pid": "L3_033", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.6428, "correct": true, "status": "ok", "speedup": 1.6428, "ref_ms": 20.59826, "cand_ms": 12.53886, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 143.1, "calls": 2, "tokens_in": 6904, "tokens_out": 9139, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "c64400e9bb68550c", "ts": 1791531322.3671649} {"pid": "L3_044", "split": "dev", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 4.5078, "correct": true, "status": "ok", "speedup": 4.5078, "ref_ms": 75.29129, "cand_ms": 16.70227, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 208.0, "calls": 2, "tokens_in": 26198, "tokens_out": 13722, "ctx_chars": 15252, "ctx_sha": "575b4fa0082f404b", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "214f47b7dded0aef", "ts": 1791531324.048401} {"pid": "L2_062", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 110.4, "calls": 3, "tokens_in": 40329, "tokens_out": 9218, "ctx_chars": 19121, "ctx_sha": "d421a9dea165588e", "uses_bf16": false, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "3609cc751e28fbd1", "ts": 1791531337.052565} {"pid": "L2_088", "split": "dev", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0699, "correct": true, "status": "ok", "speedup": 1.0699, "ref_ms": 8.47226, "cand_ms": 7.91879, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 60.1, "calls": 2, "tokens_in": 5185, "tokens_out": 3256, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "003817c43208b71d", "ts": 1791531345.3917472} {"pid": "L2_040", "split": "dev", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 4.1655, "correct": true, "status": "ok", "speedup": 4.1655, "ref_ms": 30.43313, "cand_ms": 7.30592, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 153.8, "calls": 3, "tokens_in": 28233, "tokens_out": 9713, "ctx_chars": 12049, "ctx_sha": "cd92549f2b7fd121", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "b5a78e83caf9f97e", "ts": 1791531345.8078732} {"pid": "L3_033", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.5344, "correct": true, "status": "ok", "speedup": 1.5344, "ref_ms": 20.47891, "cand_ms": 13.34641, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 137.0, "calls": 2, "tokens_in": 11301, "tokens_out": 8308, "ctx_chars": 5350, "ctx_sha": "333d78223eeced7d", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "180c434920bff859", "ts": 1791531356.091486} {"pid": "L3_048", "split": "dev", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 3.7418, "correct": true, "status": "ok", "speedup": 3.7418, "ref_ms": 15.98756, "cand_ms": 4.27274, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 377.4, "calls": 4, "tokens_in": 25306, "tokens_out": 20206, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "89e439d3dd1f8ad6", "ts": 1791531356.711834} {"pid": "L3_020", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 1.3535, "correct": true, "status": "ok", "speedup": 1.3535, "ref_ms": 6.90804, "cand_ms": 5.10399, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 322.2, "calls": 2, "tokens_in": 32749, "tokens_out": 25199, "ctx_chars": 21293, "ctx_sha": "c37e861435b5bbc4", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "40a856785427fbb0", "ts": 1791531359.3706536} {"pid": "L2_092", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.7461, "correct": true, "status": "ok", "speedup": 2.7461, "ref_ms": 8.56316, "cand_ms": 3.11833, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 178.0, "calls": 2, "tokens_in": 267348, "tokens_out": 6717, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "9c8c00a3de891aa2", "ts": 1791531361.109831} {"pid": "L2_067", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.5912, "correct": true, "status": "ok", "speedup": 2.5912, "ref_ms": 12.88005, "cand_ms": 4.97071, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 131.6, "calls": 2, "tokens_in": 266221, "tokens_out": 7703, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "78026e64ef2abfe4", "ts": 1791531369.1982014} {"pid": "L2_063", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0042, "correct": true, "status": "ok", "speedup": 1.0042, "ref_ms": 7.98182, "cand_ms": 7.94808, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 42.4, "calls": 2, "tokens_in": 10222, "tokens_out": 1716, "ctx_chars": 7272, "ctx_sha": "862484e5300b7ff6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f7dba70a221852de", "ts": 1791531399.0756226} {"pid": "L2_029", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 2.9978, "correct": true, "status": "ok", "speedup": 2.9978, "ref_ms": 7.98972, "cand_ms": 2.66519, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 151.0, "calls": 3, "tokens_in": 27580, "tokens_out": 8767, "ctx_chars": 12049, "ctx_sha": "cd92549f2b7fd121", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "c79dd7366ffc59d6", "ts": 1791531408.0393515} {"pid": "L2_029", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.5755, "correct": true, "status": "ok", "speedup": 3.5755, "ref_ms": 8.01111, "cand_ms": 2.24058, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 63.6, "calls": 2, "tokens_in": 19336, "tokens_out": 3953, "ctx_chars": 14516, "ctx_sha": "491a69f435bf3217", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "8cc24b098525da7f", "ts": 1791531408.9838552} {"pid": "L3_044", "split": "dev", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.2271, "correct": true, "status": "ok", "speedup": 1.2271, "ref_ms": 75.28464, "cand_ms": 61.34985, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 194.1, "calls": 2, "tokens_in": 9970, "tokens_out": 10914, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8fd61d5fcda2a99d", "ts": 1791531410.584919} {"pid": "L2_081", "split": "dev", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.6761, "correct": true, "status": "ok", "speedup": 3.6761, "ref_ms": 8.22169, "cand_ms": 2.23655, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 55.7, "calls": 2, "tokens_in": 23512, "tokens_out": 3619, "ctx_chars": 18655, "ctx_sha": "bbf921975c58f49c", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "6d1d9ec09ebeb008", "ts": 1791531416.7817376} {"pid": "L2_039", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 176.6, "calls": 3, "tokens_in": 417409, "tokens_out": 13311, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "fa0f8d9167614469", "ts": 1791531439.9817355} {"pid": "L2_037", "split": "dev", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 5.7905, "correct": true, "status": "ok", "speedup": 5.7905, "ref_ms": 24.40317, "cand_ms": 4.21432, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 207.9, "calls": 2, "tokens_in": 16909, "tokens_out": 5081, "ctx_chars": 12049, "ctx_sha": "cd92549f2b7fd121", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "0742b9c7356469b7", "ts": 1791531442.9950926} {"pid": "L3_048", "split": "dev", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 285.1, "calls": 5, "tokens_in": 40898, "tokens_out": 20605, "ctx_chars": 3184, "ctx_sha": "e64357aa997958f6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0609997c9b0287f1", "ts": 1791531443.6672738} {"pid": "L3_008", "split": "dev", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.4849, "correct": true, "status": "ok", "speedup": 1.4849, "ref_ms": 5.24909, "cand_ms": 3.53496, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 354.4, "calls": 2, "tokens_in": 272752, "tokens_out": 25106, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d7b0afdccb3bac54", "ts": 1791531453.8919683} {"pid": "L2_069", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 2.3237, "correct": true, "status": "ok", "speedup": 2.3237, "ref_ms": 3.78469, "cand_ms": 1.62871, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 235.6, "calls": 3, "tokens_in": 12780, "tokens_out": 9795, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4b28687e4b038507", "ts": 1791531463.3677497} {"pid": "L3_033", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.2975, "correct": true, "status": "ok", "speedup": 1.2975, "ref_ms": 20.43963, "cand_ms": 15.75299, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 130.4, "calls": 2, "tokens_in": 267019, "tokens_out": 6160, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "fca328966288dbeb", "ts": 1791531467.4573846} {"pid": "L3_047", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 1, "success": true, "score": 2.8425, "correct": true, "status": "ok", "speedup": 2.8425, "ref_ms": 3.63656, "cand_ms": 1.27936, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 131.1, "calls": 2, "tokens_in": 24582, "tokens_out": 10483, "ctx_chars": 14992, "ctx_sha": "82b6b58defdd0048", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e70a29195c4af3d7", "ts": 1791531476.911701} {"pid": "L3_033", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.7463, "correct": true, "status": "ok", "speedup": 2.7463, "ref_ms": 20.53007, "cand_ms": 7.47552, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 208.8, "calls": 3, "tokens_in": 26054, "tokens_out": 16558, "ctx_chars": 7910, "ctx_sha": "434d12593ff4fff3", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "68d56b005741d84f", "ts": 1791531507.4832182} {"pid": "L3_048", "split": "dev", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.9899, "correct": true, "status": "ok", "speedup": 1.9899, "ref_ms": 15.90108, "cand_ms": 7.99081, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 401.1, "calls": 5, "tokens_in": 33524, "tokens_out": 22362, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "fa14f8026a71a3c2", "ts": 1791531511.049498} {"pid": "L2_039", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "outputs produced during timing do not match the reference (output mismatch beyond atol=rtol=0.0001); results must not be cached or skipped", "wall_s": 155.2, "calls": 2, "tokens_in": 25845, "tokens_out": 11572, "ctx_chars": 19597, "ctx_sha": "e31c3ee202e0b25a", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "c6c18742338df896", "ts": 1791531511.2837796} {"pid": "L3_008", "split": "dev", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.4137, "correct": true, "status": "ok", "speedup": 1.4137, "ref_ms": 5.26908, "cand_ms": 3.72715, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 195.4, "calls": 2, "tokens_in": 17931, "tokens_out": 14118, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3b309b363befc604", "ts": 1791531517.7602916} {"pid": "L3_048", "split": "dev", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.1515, "correct": true, "status": "ok", "speedup": 1.1515, "ref_ms": 15.97579, "cand_ms": 13.87422, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 380.3, "calls": 4, "tokens_in": 547103, "tokens_out": 17351, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2d09398541644124", "ts": 1791531518.2483056} {"pid": "L2_020", "split": "dev", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.4612, "correct": true, "status": "ok", "speedup": 1.4612, "ref_ms": 14.26346, "cand_ms": 9.76119, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 120.1, "calls": 2, "tokens_in": 11116, "tokens_out": 1715, "ctx_chars": 7394, "ctx_sha": "632a38c7eee085c0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "7ca24f4c30fc6b8f", "ts": 1791531530.693294} {"pid": "L3_050", "split": "dev", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 2.0882, "correct": true, "status": "ok", "speedup": 2.0882, "ref_ms": 12.71377, "cand_ms": 6.08836, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 94.4, "calls": 2, "tokens_in": 7292, "tokens_out": 5651, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3410d0dec8b3032a", "ts": 1791531538.0374515} {"pid": "L2_063", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 1, "success": true, "score": 3.4967, "correct": true, "status": "ok", "speedup": 3.4967, "ref_ms": 8.08081, "cand_ms": 2.31099, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 64.4, "calls": 2, "tokens_in": 23000, "tokens_out": 3345, "ctx_chars": 18655, "ctx_sha": "bbf921975c58f49c", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "b8f97d88f42df544", "ts": 1791531541.3541038} {"pid": "L2_092", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.0949, "correct": true, "status": "ok", "speedup": 2.0949, "ref_ms": 8.62776, "cand_ms": 4.11853, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 136.6, "calls": 2, "tokens_in": 20892, "tokens_out": 9588, "ctx_chars": 14961, "ctx_sha": "549d04579f777963", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1c618e060ff779fd", "ts": 1791531545.5513973} {"pid": "L2_088", "split": "dev", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.7408, "correct": true, "status": "ok", "speedup": 3.7408, "ref_ms": 8.47406, "cand_ms": 2.2653, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 110.3, "calls": 2, "tokens_in": 19506, "tokens_out": 4978, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "b86c7454fcaf7899", "ts": 1791531553.3382437} {"pid": "L2_062", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.4161, "correct": true, "status": "ok", "speedup": 2.4161, "ref_ms": 8.55447, "cand_ms": 3.54055, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 142.2, "calls": 3, "tokens_in": 33134, "tokens_out": 8618, "ctx_chars": 14516, "ctx_sha": "491a69f435bf3217", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "fcab345353a33cb7", "ts": 1791531558.9364774} {"pid": "L2_069", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": false, "score": 0.1946, "correct": true, "status": "ok", "speedup": 0.1946, "ref_ms": 3.6525, "cand_ms": 18.77116, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 205.5, "calls": 2, "tokens_in": 6018, "tokens_out": 8239, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1e5a7d0392ea8bd7", "ts": 1791531564.9053924} {"pid": "L2_062", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.5845, "correct": true, "status": "ok", "speedup": 2.5845, "ref_ms": 8.6241, "cand_ms": 3.33679, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 167.4, "calls": 3, "tokens_in": 414703, "tokens_out": 10012, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "c0d504ffbcee0bd6", "ts": 1791531566.520345} {"pid": "L2_069", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.5568, "correct": true, "status": "ok", "speedup": 3.5568, "ref_ms": 4.01231, "cand_ms": 1.12806, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 146.5, "calls": 2, "tokens_in": 20094, "tokens_out": 5204, "ctx_chars": 15668, "ctx_sha": "bb1fdfba7b87d1ff", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c863e3c8d32f0c9d", "ts": 1791531586.5304835} {"pid": "L2_053", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0114, "correct": true, "status": "ok", "speedup": 1.0114, "ref_ms": 15.94418, "cand_ms": 15.7652, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 48.6, "calls": 2, "tokens_in": 10650, "tokens_out": 1507, "ctx_chars": 7198, "ctx_sha": "e66d522755f291d1", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "442708042156c816", "ts": 1791531589.9181373} {"pid": "L3_033", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.3605, "correct": true, "status": "ok", "speedup": 1.3605, "ref_ms": 20.47552, "cand_ms": 15.05015, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 185.6, "calls": 2, "tokens_in": 267244, "tokens_out": 6876, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "09cfc6304de29925", "ts": 1791531593.6715987} {"pid": "L2_067", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.8702, "correct": true, "status": "ok", "speedup": 1.8702, "ref_ms": 12.9246, "cand_ms": 6.9108, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 135.4, "calls": 3, "tokens_in": 402589, "tokens_out": 10456, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "8017177c725d7bdc", "ts": 1791531598.8015757} {"pid": "L3_048", "split": "dev", "rep": 2, "arm": "bare", "attempt": 0, "restart": 1, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 280.4, "calls": 5, "tokens_in": 32941, "tokens_out": 18525, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1775b8123df41ea5", "ts": 1791531604.4467447} {"pid": "L2_063", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.6106, "correct": true, "status": "ok", "speedup": 4.6106, "ref_ms": 7.96805, "cand_ms": 1.7282, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 66.7, "calls": 2, "tokens_in": 273106, "tokens_out": 3730, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "8bd182b17e1d8dcf", "ts": 1791531612.3011804} {"pid": "L2_040", "split": "dev", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 4.4807, "correct": true, "status": "ok", "speedup": 4.4807, "ref_ms": 30.50348, "cand_ms": 6.8077, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 111.1, "calls": 2, "tokens_in": 16716, "tokens_out": 5440, "ctx_chars": 12049, "ctx_sha": "cd92549f2b7fd121", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "923b84f45de53269", "ts": 1791531622.3448024} {"pid": "L2_052", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.3648, "correct": true, "status": "ok", "speedup": 1.3648, "ref_ms": 10.99608, "cand_ms": 8.05715, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 120.9, "calls": 2, "tokens_in": 12056, "tokens_out": 4306, "ctx_chars": 7687, "ctx_sha": "00b2f6d51bc8c639", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "184ccec4a47c0cd4", "ts": 1791531638.7065363} {"pid": "L2_088", "split": "dev", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.3184, "correct": true, "status": "ok", "speedup": 1.3184, "ref_ms": 8.51833, "cand_ms": 6.46113, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 128.9, "calls": 2, "tokens_in": 266898, "tokens_out": 6422, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "78327db6c9ac2224", "ts": 1791531639.9154685} {"pid": "L2_052", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.4207, "correct": true, "status": "ok", "speedup": 1.4207, "ref_ms": 11.08102, "cand_ms": 7.79978, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 190.0, "calls": 2, "tokens_in": 6059, "tokens_out": 6462, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2644de431f3b4cfd", "ts": 1791531643.89449} {"pid": "L2_081", "split": "dev", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0328, "correct": true, "status": "ok", "speedup": 1.0328, "ref_ms": 8.23073, "cand_ms": 7.96969, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 45.0, "calls": 2, "tokens_in": 11040, "tokens_out": 1964, "ctx_chars": 7359, "ctx_sha": "799b0b02bfe5b890", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "35fa9f0bf29ea289", "ts": 1791531649.460197} {"pid": "L2_088", "split": "dev", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.3227, "correct": true, "status": "ok", "speedup": 1.3227, "ref_ms": 8.52788, "cand_ms": 6.44736, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 100.3, "calls": 2, "tokens_in": 266932, "tokens_out": 6633, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "07c12bf1e59f5b6b", "ts": 1791531653.6177218} {"pid": "L3_033", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.3, "correct": true, "status": "ok", "speedup": 1.3, "ref_ms": 20.46431, "cand_ms": 15.74148, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 150.0, "calls": 2, "tokens_in": 267061, "tokens_out": 7380, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "8224d5c1a6647bff", "ts": 1791531657.4936273} {"pid": "L3_020", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.3346, "correct": true, "status": "ok", "speedup": 2.3346, "ref_ms": 7.51252, "cand_ms": 3.21784, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 288.4, "calls": 2, "tokens_in": 22125, "tokens_out": 21377, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ac414801701aae4c", "ts": 1791531657.5643227} {"pid": "L2_020", "split": "dev", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.4545, "correct": true, "status": "ok", "speedup": 1.4545, "ref_ms": 14.28489, "cand_ms": 9.82102, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 140.1, "calls": 2, "tokens_in": 10984, "tokens_out": 1990, "ctx_chars": 7394, "ctx_sha": "632a38c7eee085c0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "cb1f888dbf9f8333", "ts": 1791531658.3639667} {"pid": "L2_029", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.353, "correct": true, "status": "ok", "speedup": 1.353, "ref_ms": 8.00419, "cand_ms": 5.91606, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 109.3, "calls": 2, "tokens_in": 5063, "tokens_out": 4214, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "883f8c90e970babd", "ts": 1791531674.217689} {"pid": "L2_053", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.196, "correct": true, "status": "ok", "speedup": 4.196, "ref_ms": 15.92525, "cand_ms": 3.79536, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 87.3, "calls": 2, "tokens_in": 18812, "tokens_out": 3431, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "db3a5637efdf05aa", "ts": 1791531677.247457} {"pid": "L2_073", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.0441, "correct": true, "status": "ok", "speedup": 2.0441, "ref_ms": 5.60515, "cand_ms": 2.74215, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 153.7, "calls": 2, "tokens_in": 5265, "tokens_out": 5382, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "b56cf4cb95b8b404", "ts": 1791531691.7057009} {"pid": "L2_069", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.2457, "correct": true, "status": "ok", "speedup": 1.2457, "ref_ms": 3.67166, "cand_ms": 2.94751, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 233.7, "calls": 2, "tokens_in": 265507, "tokens_out": 3373, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "55001eaa48f475f3", "ts": 1791531701.1710794} {"pid": "L2_081", "split": "dev", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.6918, "correct": true, "status": "ok", "speedup": 3.6918, "ref_ms": 8.3938, "cand_ms": 2.27364, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 89.2, "calls": 2, "tokens_in": 19026, "tokens_out": 3766, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "96f21c0658f068b6", "ts": 1791531701.5016394} {"pid": "L2_069", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.2506, "correct": true, "status": "ok", "speedup": 1.2506, "ref_ms": 3.63828, "cand_ms": 2.90933, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 103.0, "calls": 2, "tokens_in": 12298, "tokens_out": 1625, "ctx_chars": 9026, "ctx_sha": "a3512fc398ca432b", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "7112a42b14e7a8b0", "ts": 1791531725.347508} {"pid": "L2_063", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0123, "correct": true, "status": "ok", "speedup": 1.0123, "ref_ms": 8.09621, "cand_ms": 7.99795, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 86.1, "calls": 2, "tokens_in": 4128, "tokens_out": 1999, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "bc98fd4fdf9bf7e8", "ts": 1791531729.9829817} {"pid": "L2_067", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": false, "score": 0.0244, "correct": true, "status": "ok", "speedup": 0.0244, "ref_ms": 13.10386, "cand_ms": 537.47784, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 144.6, "calls": 2, "tokens_in": 11614, "tokens_out": 4401, "ctx_chars": 7583, "ctx_sha": "5300ffdccc59e7fb", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d7bc15fedacd0b3a", "ts": 1791531731.1592276} {"pid": "L3_044", "split": "dev", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.3725, "correct": true, "status": "ok", "speedup": 1.3725, "ref_ms": 75.4387, "cand_ms": 54.96471, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 166.1, "calls": 2, "tokens_in": 270417, "tokens_out": 12291, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "8ef1deff7e7739a2", "ts": 1791531732.5806565} {"pid": "L2_092", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.3248, "correct": true, "status": "ok", "speedup": 2.3248, "ref_ms": 8.5422, "cand_ms": 3.67433, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 86.1, "calls": 2, "tokens_in": 10662, "tokens_out": 4657, "ctx_chars": 5747, "ctx_sha": "169afaa9eeb4d53a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2d2d750ec2a312b8", "ts": 1791531760.2787106} {"pid": "L2_037", "split": "dev", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.2829, "correct": true, "status": "ok", "speedup": 1.2829, "ref_ms": 19.75738, "cand_ms": 15.40015, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 163.0, "calls": 2, "tokens_in": 10115, "tokens_out": 2385, "ctx_chars": 6342, "ctx_sha": "c3ce68171bb279a4", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4b1ae9bc74127440", "ts": 1791531761.8437932} {"pid": "L2_063", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.5594, "correct": true, "status": "ok", "speedup": 1.5594, "ref_ms": 8.02026, "cand_ms": 5.14307, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 74.1, "calls": 2, "tokens_in": 5197, "tokens_out": 4347, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "b38cd27d57874ab9", "ts": 1791531775.6428132} {"pid": "L2_037", "split": "dev", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.574, "correct": true, "status": "ok", "speedup": 4.574, "ref_ms": 19.81923, "cand_ms": 4.33305, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 183.3, "calls": 2, "tokens_in": 24410, "tokens_out": 4223, "ctx_chars": 19121, "ctx_sha": "d421a9dea165588e", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "9ec2dc37502b3f2d", "ts": 1791531776.9823923} {"pid": "L2_062", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 128.3, "calls": 3, "tokens_in": 33273, "tokens_out": 10018, "ctx_chars": 14516, "ctx_sha": "491a69f435bf3217", "uses_bf16": false, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "b5117ba49efc8a57", "ts": 1791531777.8087342} {"pid": "L2_037", "split": "dev", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.2836, "correct": true, "status": "ok", "speedup": 1.2836, "ref_ms": 19.69001, "cand_ms": 15.33976, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 102.5, "calls": 2, "tokens_in": 4792, "tokens_out": 2760, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "b25458eb729b48cd", "ts": 1791531779.776197} {"pid": "L2_052", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.3702, "correct": true, "status": "ok", "speedup": 1.3702, "ref_ms": 10.93903, "cand_ms": 7.98365, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 121.5, "calls": 2, "tokens_in": 11968, "tokens_out": 4227, "ctx_chars": 7687, "ctx_sha": "00b2f6d51bc8c639", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "96e3ef74f0349a9c", "ts": 1791531779.8548617} {"pid": "L2_039", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0105, "correct": true, "status": "ok", "speedup": 1.0105, "ref_ms": 30.17775, "cand_ms": 29.86341, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 129.5, "calls": 2, "tokens_in": 6728, "tokens_out": 8105, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d5918e6f6fe12b58", "ts": 1791531787.032486} {"pid": "L2_039", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 89.2, "calls": 2, "tokens_in": 19721, "tokens_out": 6985, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "1fbfc179643ebc87", "ts": 1791531790.4206338} {"pid": "L1_078", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 3.0982, "correct": true, "status": "ok", "speedup": 3.0982, "ref_ms": 35.87883, "cand_ms": 11.58072, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 267.4, "calls": 2, "tokens_in": 7563, "tokens_out": 10350, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "85136428c37bff50", "ts": 1791531826.300151} {"pid": "L3_044", "split": "dev", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.3738, "correct": true, "status": "ok", "speedup": 1.3738, "ref_ms": 75.30298, "cand_ms": 54.81549, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 180.9, "calls": 2, "tokens_in": 270199, "tokens_out": 10935, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "baa4fb6c4cc95d03", "ts": 1791531838.3850965} {"pid": "L2_020", "split": "dev", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 1, "success": true, "score": 1.4332, "correct": true, "status": "ok", "speedup": 1.4332, "ref_ms": 14.05487, "cand_ms": 9.80645, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 198.5, "calls": 2, "tokens_in": 10960, "tokens_out": 1841, "ctx_chars": 7394, "ctx_sha": "632a38c7eee085c0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f8440bce873bf99d", "ts": 1791531838.421694} {"pid": "L3_008", "split": "dev", "rep": 1, "arm": "stock", "attempt": 0, "restart": 1, "success": true, "score": 1.2059, "correct": true, "status": "ok", "speedup": 1.2059, "ref_ms": 5.29262, "cand_ms": 4.38905, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 198.8, "calls": 2, "tokens_in": 18757, "tokens_out": 16681, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8887ae759bf20294", "ts": 1791531852.36835} {"pid": "L2_040", "split": "dev", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.2547, "correct": true, "status": "ok", "speedup": 1.2547, "ref_ms": 30.43567, "cand_ms": 24.25742, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 98.0, "calls": 2, "tokens_in": 266111, "tokens_out": 5391, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "72b81af121d8bbc0", "ts": 1791531859.842063} {"pid": "L3_044", "split": "dev", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 3.3799, "correct": true, "status": "ok", "speedup": 3.3799, "ref_ms": 75.29665, "cand_ms": 22.27769, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 224.9, "calls": 2, "tokens_in": 280795, "tokens_out": 19933, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "a10817b41f08dd38", "ts": 1791531863.5844886} {"pid": "L2_058", "split": "dev", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 18.9543, "ref_ms": 25.13124, "cand_ms": 1.32589, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 88.8, "calls": 2, "tokens_in": 25320, "tokens_out": 6929, "ctx_chars": 20061, "ctx_sha": "a0a8edb8b6ae64a6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "b0b23d181558cc28", "ts": 1791531864.443449} {"pid": "L3_047", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.4742, "correct": true, "status": "ok", "speedup": 1.4742, "ref_ms": 3.65837, "cand_ms": 2.48157, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 134.3, "calls": 2, "tokens_in": 8909, "tokens_out": 9003, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "272260141dcecd5d", "ts": 1791531866.8535676} {"pid": "L3_050", "split": "dev", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.8182, "correct": true, "status": "ok", "speedup": 2.8182, "ref_ms": 12.64837, "cand_ms": 4.48807, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 154.7, "calls": 3, "tokens_in": 48789, "tokens_out": 11825, "ctx_chars": 22253, "ctx_sha": "e98f6866890474ec", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1be95f64a3c14f2f", "ts": 1791531884.6868155} {"pid": "L2_052", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 1, "success": true, "score": 2.0562, "correct": true, "status": "ok", "speedup": 2.0562, "ref_ms": 11.01878, "cand_ms": 5.35887, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 193.6, "calls": 2, "tokens_in": 28030, "tokens_out": 10140, "ctx_chars": 22084, "ctx_sha": "9cc43a100b1de8c3", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "428129d57f464e3b", "ts": 1791531885.279896} {"pid": "L2_069", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.2567, "correct": true, "status": "ok", "speedup": 1.2567, "ref_ms": 3.66261, "cand_ms": 2.91441, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 95.6, "calls": 2, "tokens_in": 12457, "tokens_out": 2078, "ctx_chars": 9026, "ctx_sha": "a3512fc398ca432b", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "334674f1d134e940", "ts": 1791531886.070578} {"pid": "L3_047", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.1207, "correct": true, "status": "ok", "speedup": 3.1207, "ref_ms": 3.63027, "cand_ms": 1.16329, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 112.0, "calls": 2, "tokens_in": 32143, "tokens_out": 10054, "ctx_chars": 22064, "ctx_sha": "47c729252530dc44", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "22605509bc774a54", "ts": 1791531899.0012891} {"pid": "L2_088", "split": "dev", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0503, "correct": true, "status": "ok", "speedup": 1.0503, "ref_ms": 8.57813, "cand_ms": 8.16697, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 46.6, "calls": 2, "tokens_in": 4867, "tokens_out": 2497, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1676cc36496e8ff3", "ts": 1791531913.446879} {"pid": "L2_081", "split": "dev", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.6715, "correct": true, "status": "ok", "speedup": 3.6715, "ref_ms": 8.29657, "cand_ms": 2.2597, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 76.1, "calls": 2, "tokens_in": 18970, "tokens_out": 3729, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "ca6fc94f28ace9f3", "ts": 1791531914.5145366} {"pid": "L2_040", "split": "dev", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.5506, "correct": true, "status": "ok", "speedup": 1.5506, "ref_ms": 30.41393, "cand_ms": 19.61486, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 154.8, "calls": 2, "tokens_in": 5768, "tokens_out": 5384, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "e6fc9854651e77a9", "ts": 1791531931.746261} {"pid": "L3_020", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.8506, "correct": true, "status": "ok", "speedup": 1.8506, "ref_ms": 7.85409, "cand_ms": 4.24407, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 162.3, "calls": 2, "tokens_in": 11920, "tokens_out": 15300, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "424f0d413557aeb0", "ts": 1791531940.101419} {"pid": "L3_044", "split": "dev", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.5162, "correct": true, "status": "ok", "speedup": 4.5162, "ref_ms": 75.30582, "cand_ms": 16.67478, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 163.4, "calls": 2, "tokens_in": 33960, "tokens_out": 13588, "ctx_chars": 22253, "ctx_sha": "e98f6866890474ec", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "ead11312e139166f", "ts": 1791531943.2672937} {"pid": "L3_020", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.023, "correct": true, "status": "ok", "speedup": 2.023, "ref_ms": 7.22821, "cand_ms": 3.57307, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 419.0, "calls": 3, "tokens_in": 420809, "tokens_out": 31590, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "93707877d70f142c", "ts": 1791531949.6973367} {"pid": "L2_067", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.338, "correct": true, "status": "ok", "speedup": 2.338, "ref_ms": 12.9209, "cand_ms": 5.5264, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 99.1, "calls": 2, "tokens_in": 265973, "tokens_out": 6636, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "6d27566dee40a586", "ts": 1791531958.9883687} {"pid": "L3_047", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.9124, "correct": true, "status": "ok", "speedup": 2.9124, "ref_ms": 3.63791, "cand_ms": 1.2491, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 182.5, "calls": 2, "tokens_in": 277411, "tokens_out": 16742, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "ad046057743555d8", "ts": 1791531962.322728} {"pid": "L2_092", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 3.1204, "correct": true, "status": "ok", "speedup": 3.1204, "ref_ms": 8.53956, "cand_ms": 2.73673, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 238.1, "calls": 3, "tokens_in": 19725, "tokens_out": 22638, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f9882991a8946c17", "ts": 1791531969.2733803} {"pid": "L2_040", "split": "dev", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.0261, "correct": true, "status": "ok", "speedup": 1.0261, "ref_ms": 30.40465, "cand_ms": 29.63232, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 118.5, "calls": 2, "tokens_in": 265993, "tokens_out": 4788, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "c601396f5cd54675", "ts": 1791531982.9733107} {"pid": "L3_044", "split": "dev", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.493, "correct": true, "status": "ok", "speedup": 4.493, "ref_ms": 75.33048, "cand_ms": 16.76601, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 176.9, "calls": 2, "tokens_in": 33608, "tokens_out": 13345, "ctx_chars": 22253, "ctx_sha": "e98f6866890474ec", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "2d4e8d1a687c4ef9", "ts": 1791532003.1855705} {"pid": "L3_047", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.633, "correct": true, "status": "ok", "speedup": 2.633, "ref_ms": 3.6325, "cand_ms": 1.3796, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 111.1, "calls": 2, "tokens_in": 32105, "tokens_out": 10103, "ctx_chars": 22064, "ctx_sha": "47c729252530dc44", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "71e37dcdf0071ae6", "ts": 1791532010.1297178} {"pid": "L2_020", "split": "dev", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 1.4669, "correct": true, "status": "ok", "speedup": 1.4669, "ref_ms": 14.17268, "cand_ms": 9.66193, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 102.6, "calls": 2, "tokens_in": 23879, "tokens_out": 2368, "ctx_chars": 20061, "ctx_sha": "a0a8edb8b6ae64a6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "30d3ddfd1f16abc8", "ts": 1791532042.7272282} {"pid": "L2_062", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 2.4082, "correct": true, "status": "ok", "speedup": 2.4082, "ref_ms": 8.61815, "cand_ms": 3.57866, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 189.8, "calls": 3, "tokens_in": 28788, "tokens_out": 9419, "ctx_chars": 12049, "ctx_sha": "cd92549f2b7fd121", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "8222214d4b747e87", "ts": 1791532053.3554673} {"pid": "L2_058", "split": "dev", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 14.99, "ref_ms": 25.17657, "cand_ms": 1.67955, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 152.0, "calls": 2, "tokens_in": 13975, "tokens_out": 8283, "ctx_chars": 8031, "ctx_sha": "8e7ee93b3140d14f", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "aa08a90ffb31b041", "ts": 1791532066.492178} {"pid": "L1_066", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": false, "score": 0.0111, "correct": true, "status": "ok", "speedup": 0.0111, "ref_ms": 7.95922, "cand_ms": 716.35429, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 217.0, "calls": 2, "tokens_in": 14397, "tokens_out": 6458, "ctx_chars": 8854, "ctx_sha": "420ebf050379abd1", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "cd3a38255bb9fcff", "ts": 1791532069.4082263} {"pid": "L2_069", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.2451, "correct": true, "status": "ok", "speedup": 1.2451, "ref_ms": 3.65174, "cand_ms": 2.93285, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 123.0, "calls": 2, "tokens_in": 12493, "tokens_out": 2119, "ctx_chars": 9026, "ctx_sha": "a3512fc398ca432b", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "a54b250db91a985d", "ts": 1791532072.7429643} {"pid": "L3_002", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.3534, "correct": true, "status": "ok", "speedup": 2.3534, "ref_ms": 33.70028, "cand_ms": 14.3196, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 148.3, "calls": 2, "tokens_in": 15941, "tokens_out": 5296, "ctx_chars": 10450, "ctx_sha": "b62926c8e92a5539", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "931eebeb66eaea42", "ts": 1791532079.99856} {"pid": "L2_063", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": false, "score": 1.0013, "correct": true, "status": "ok", "speedup": 1.0013, "ref_ms": 8.05964, "cand_ms": 8.04932, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 125.4, "calls": 2, "tokens_in": 265731, "tokens_out": 4578, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "ac79ca4a94d88c02", "ts": 1791532084.4090545} {"pid": "L1_066", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.6185, "correct": true, "status": "ok", "speedup": 1.6185, "ref_ms": 7.81559, "cand_ms": 4.82887, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 202.7, "calls": 2, "tokens_in": 8206, "tokens_out": 12622, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d9df43220f34cbdb", "ts": 1791532087.983594} {"pid": "L2_039", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 92.2, "calls": 2, "tokens_in": 19867, "tokens_out": 7341, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "c6862d9bd648b547", "ts": 1791532095.3978584} {"pid": "L2_039", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 1, "success": false, "score": 0.9574, "correct": true, "status": "ok", "speedup": 0.9574, "ref_ms": 30.09946, "cand_ms": 31.44037, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 128.9, "calls": 2, "tokens_in": 6614, "tokens_out": 9110, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "902cfc6e1a78a1cb", "ts": 1791532098.2150855} {"pid": "L2_092", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.7983, "correct": true, "status": "ok", "speedup": 2.7983, "ref_ms": 8.4941, "cand_ms": 3.0355, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 76.2, "calls": 2, "tokens_in": 5848, "tokens_out": 5560, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0a98a534d0ad910a", "ts": 1791532118.8898199} {"pid": "L2_052", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.4025, "correct": true, "status": "ok", "speedup": 1.4025, "ref_ms": 11.0237, "cand_ms": 7.85996, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 234.7, "calls": 2, "tokens_in": 267503, "tokens_out": 8469, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "dd3b2075f3677d64", "ts": 1791532120.7800474} {"pid": "L3_048", "split": "dev", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.1777, "correct": true, "status": "ok", "speedup": 1.1777, "ref_ms": 15.92216, "cand_ms": 13.51995, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 374.7, "calls": 5, "tokens_in": 35215, "tokens_out": 22976, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2ffcb40af6769600", "ts": 1791532134.978298} {"pid": "L2_073", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.4667, "correct": true, "status": "ok", "speedup": 1.4667, "ref_ms": 5.6091, "cand_ms": 3.82433, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 133.1, "calls": 2, "tokens_in": 11017, "tokens_out": 4548, "ctx_chars": 6744, "ctx_sha": "b92173e1465ccf4d", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "29ff3cee90dea928", "ts": 1791532143.2368407} {"pid": "L2_081", "split": "dev", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.6484, "correct": true, "status": "ok", "speedup": 3.6484, "ref_ms": 8.23983, "cand_ms": 2.25849, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 60.4, "calls": 2, "tokens_in": 23361, "tokens_out": 3656, "ctx_chars": 18655, "ctx_sha": "bbf921975c58f49c", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "e7cb31f403baeacb", "ts": 1791532148.35653} {"pid": "L2_067", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.3166, "correct": true, "status": "ok", "speedup": 2.3166, "ref_ms": 12.92195, "cand_ms": 5.57802, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 167.3, "calls": 2, "tokens_in": 13300, "tokens_out": 12279, "ctx_chars": 7583, "ctx_sha": "5300ffdccc59e7fb", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ee1549c6d6367d6a", "ts": 1791532150.279795} {"pid": "L3_048", "split": "dev", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.1772, "correct": true, "status": "ok", "speedup": 1.1772, "ref_ms": 15.92048, "cand_ms": 13.52368, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 426.1, "calls": 5, "tokens_in": 62216, "tokens_out": 27710, "ctx_chars": 10330, "ctx_sha": "4725ef765672a6e6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "931bc1e5fb2913a7", "ts": 1791532151.4925737} {"pid": "L1_066", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.6947, "correct": true, "status": "ok", "speedup": 1.6947, "ref_ms": 7.79111, "cand_ms": 4.59721, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 290.3, "calls": 3, "tokens_in": 18414, "tokens_out": 18650, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "fa5e5acd687bb7af", "ts": 1791532175.0281873} {"pid": "L1_066", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.6206, "correct": true, "status": "ok", "speedup": 1.6206, "ref_ms": 7.76952, "cand_ms": 4.7941, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 370.5, "calls": 3, "tokens_in": 408610, "tokens_out": 17466, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "80636a57671a74d1", "ts": 1791532208.905757} {"pid": "L2_067", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.7248, "correct": true, "status": "ok", "speedup": 1.7248, "ref_ms": 12.91653, "cand_ms": 7.48861, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 140.5, "calls": 2, "tokens_in": 266769, "tokens_out": 11406, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "01a618a74f975dea", "ts": 1791532209.8906236} {"pid": "L3_033", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.2343, "correct": true, "status": "ok", "speedup": 1.2343, "ref_ms": 20.65961, "cand_ms": 16.7385, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 268.3, "calls": 4, "tokens_in": 31135, "tokens_out": 14122, "ctx_chars": 5350, "ctx_sha": "333d78223eeced7d", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "84316ef36a68002a", "ts": 1791532211.5414023} {"pid": "L3_002", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.4415, "correct": true, "status": "ok", "speedup": 3.4415, "ref_ms": 33.78091, "cand_ms": 9.81565, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 157.0, "calls": 2, "tokens_in": 20678, "tokens_out": 6905, "ctx_chars": 15055, "ctx_sha": "bf57b13b7f033578", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1b7213bcdee91e03", "ts": 1791532236.9886856} {"pid": "L2_067", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 2.5263, "correct": true, "status": "ok", "speedup": 2.5263, "ref_ms": 13.01707, "cand_ms": 5.15262, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 120.0, "calls": 2, "tokens_in": 18452, "tokens_out": 6712, "ctx_chars": 14070, "ctx_sha": "3d6ada40588e7cb1", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8bf623c1de5a2a38", "ts": 1791532238.926689} {"pid": "L2_039", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0119, "correct": true, "status": "ok", "speedup": 1.0119, "ref_ms": 30.07245, "cand_ms": 29.71772, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 144.6, "calls": 2, "tokens_in": 7325, "tokens_out": 9879, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "a88d6842bb650a1a", "ts": 1791532242.8055682} {"pid": "L2_092", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.8691, "correct": true, "status": "ok", "speedup": 3.8691, "ref_ms": 8.52581, "cand_ms": 2.20358, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 150.4, "calls": 2, "tokens_in": 20508, "tokens_out": 9013, "ctx_chars": 14961, "ctx_sha": "549d04579f777963", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d789e35a9f9b8331", "ts": 1791532245.8419013} {"pid": "L2_088", "split": "dev", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.5974, "correct": true, "status": "ok", "speedup": 3.5974, "ref_ms": 8.65127, "cand_ms": 2.40484, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 102.5, "calls": 2, "tokens_in": 16456, "tokens_out": 6215, "ctx_chars": 11583, "ctx_sha": "bb093721f8760f3d", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "ac8495d7c7093a6e", "ts": 1791532252.7911122} {"pid": "L2_062", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.5868, "correct": true, "status": "ok", "speedup": 1.5868, "ref_ms": 8.63275, "cand_ms": 5.4403, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 112.9, "calls": 2, "tokens_in": 5906, "tokens_out": 5869, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "d6d61b891ff709ef", "ts": 1791532264.422939} {"pid": "L2_067", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.054, "correct": true, "status": "ok", "speedup": 2.054, "ref_ms": 12.89804, "cand_ms": 6.27947, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 181.9, "calls": 3, "tokens_in": 14628, "tokens_out": 13889, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "bce8a63cecc60baa", "ts": 1791532266.355614} {"pid": "L2_037", "split": "dev", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 4.7467, "correct": true, "status": "ok", "speedup": 4.7467, "ref_ms": 19.8366, "cand_ms": 4.17902, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 130.9, "calls": 2, "tokens_in": 16802, "tokens_out": 5142, "ctx_chars": 12049, "ctx_sha": "cd92549f2b7fd121", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "65abf987d865d9d6", "ts": 1791532274.1171181} {"pid": "L3_033", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 139.8, "calls": 2, "tokens_in": 13402, "tokens_out": 9805, "ctx_chars": 7910, "ctx_sha": "434d12593ff4fff3", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "5f2996ead5508b38", "ts": 1791532274.8143268} {"pid": "L3_020", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 1.25, "correct": true, "status": "ok", "speedup": 1.25, "ref_ms": 6.66012, "cand_ms": 5.32827, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 317.5, "calls": 3, "tokens_in": 58763, "tokens_out": 29588, "ctx_chars": 21293, "ctx_sha": "c37e861435b5bbc4", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e9a69ccac516645d", "ts": 1791532279.796373} {"pid": "L2_092", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.1565, "correct": true, "status": "ok", "speedup": 2.1565, "ref_ms": 8.50789, "cand_ms": 3.94523, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 71.6, "calls": 2, "tokens_in": 10750, "tokens_out": 4730, "ctx_chars": 5747, "ctx_sha": "169afaa9eeb4d53a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0a70d1151deeca3e", "ts": 1791532283.0956044} {"pid": "L2_040", "split": "dev", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 4.4666, "correct": true, "status": "ok", "speedup": 4.4666, "ref_ms": 30.43077, "cand_ms": 6.81295, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 98.3, "calls": 2, "tokens_in": 16688, "tokens_out": 5214, "ctx_chars": 12049, "ctx_sha": "cd92549f2b7fd121", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "2e2e6288bf3f740e", "ts": 1791532307.1573565} {"pid": "L2_067", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": false, "score": 0.4976, "correct": true, "status": "ok", "speedup": 0.4976, "ref_ms": 12.96099, "cand_ms": 26.04687, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 412.1, "calls": 3, "tokens_in": 404650, "tokens_out": 18964, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f5c03e25e5d2e394", "ts": 1791532325.560815} {"pid": "L2_063", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.6169, "correct": true, "status": "ok", "speedup": 4.6169, "ref_ms": 8.00797, "cand_ms": 1.73447, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 77.6, "calls": 2, "tokens_in": 273409, "tokens_out": 4598, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "c597d404e59e1c75", "ts": 1791532330.359543} {"pid": "L2_069", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.2541, "correct": true, "status": "ok", "speedup": 2.2541, "ref_ms": 4.01988, "cand_ms": 1.78335, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 183.6, "calls": 2, "tokens_in": 13973, "tokens_out": 6776, "ctx_chars": 9026, "ctx_sha": "a3512fc398ca432b", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "5351189e324cbdff", "ts": 1791532331.907587} {"pid": "L2_020", "split": "dev", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.4624, "correct": true, "status": "ok", "speedup": 1.4624, "ref_ms": 14.15148, "cand_ms": 9.67683, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 220.8, "calls": 2, "tokens_in": 266185, "tokens_out": 4346, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "068f99b5ae54910d", "ts": 1791532341.5393512} {"pid": "L2_058", "split": "dev", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 8.9421, "correct": true, "status": "ok", "speedup": 8.9421, "ref_ms": 25.10821, "cand_ms": 2.80786, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 270.7, "calls": 3, "tokens_in": 405889, "tokens_out": 12345, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "733a8360e5e6ef8e", "ts": 1791532343.4235058} {"pid": "L2_073", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 1, "success": true, "score": 2.5518, "correct": true, "status": "ok", "speedup": 2.5518, "ref_ms": 5.7699, "cand_ms": 2.26115, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 279.6, "calls": 3, "tokens_in": 47687, "tokens_out": 14354, "ctx_chars": 22975, "ctx_sha": "4e003dc4030b57a1", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3a5741fe2e64c7b0", "ts": 1791532346.1195788} {"pid": "L3_048", "split": "dev", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": false, "score": 0.9521, "correct": true, "status": "ok", "speedup": 0.9521, "ref_ms": 15.88145, "cand_ms": 16.68105, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 292.9, "calls": 5, "tokens_in": 41824, "tokens_out": 17685, "ctx_chars": 3184, "ctx_sha": "e64357aa997958f6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8130d201c0a394ad", "ts": 1791532346.217587} {"pid": "L2_063", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.3957, "correct": true, "status": "ok", "speedup": 1.3957, "ref_ms": 7.99666, "cand_ms": 5.72957, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 95.9, "calls": 2, "tokens_in": 5180, "tokens_out": 4342, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "132597bc363c9a4a", "ts": 1791532360.3579028} {"pid": "L3_044", "split": "dev", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0464, "correct": true, "status": "ok", "speedup": 1.0464, "ref_ms": 75.29475, "cand_ms": 71.95439, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 133.6, "calls": 2, "tokens_in": 11381, "tokens_out": 9250, "ctx_chars": 3184, "ctx_sha": "e64357aa997958f6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3525b7c5d0f221d9", "ts": 1791532370.5937746} {"pid": "L2_020", "split": "dev", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 1.4181, "correct": true, "status": "ok", "speedup": 1.4181, "ref_ms": 14.02222, "cand_ms": 9.88792, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 105.8, "calls": 2, "tokens_in": 23924, "tokens_out": 2462, "ctx_chars": 20061, "ctx_sha": "a0a8edb8b6ae64a6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "bcd9402a175b004a", "ts": 1791532380.5971382} {"pid": "L2_053", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": false, "score": 0.7898, "correct": true, "status": "ok", "speedup": 0.7898, "ref_ms": 15.9834, "cand_ms": 20.23729, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 106.3, "calls": 2, "tokens_in": 5663, "tokens_out": 5061, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "0e1cadad9a1a2260", "ts": 1791532389.37581} {"pid": "L2_052", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.1824, "correct": true, "status": "ok", "speedup": 2.1824, "ref_ms": 11.03781, "cand_ms": 5.05755, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 181.0, "calls": 2, "tokens_in": 28269, "tokens_out": 10576, "ctx_chars": 22084, "ctx_sha": "9cc43a100b1de8c3", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2cbe5882811abf16", "ts": 1791532390.8991008} {"pid": "L2_088", "split": "dev", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0656, "correct": true, "status": "ok", "speedup": 1.0656, "ref_ms": 8.51907, "cand_ms": 7.99489, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 57.9, "calls": 2, "tokens_in": 10210, "tokens_out": 2130, "ctx_chars": 6231, "ctx_sha": "4e345ad7f535c321", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "9224aa699512e2b0", "ts": 1791532399.4202156} {"pid": "L3_020", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.3382, "correct": true, "status": "ok", "speedup": 1.3382, "ref_ms": 7.11689, "cand_ms": 5.31834, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 182.3, "calls": 2, "tokens_in": 20351, "tokens_out": 13701, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3b81257a413ecc06", "ts": 1791532421.2298846} {"pid": "L2_092", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 2.6386, "correct": true, "status": "ok", "speedup": 2.6386, "ref_ms": 8.56449, "cand_ms": 3.24587, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 180.5, "calls": 2, "tokens_in": 8210, "tokens_out": 14077, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3e0ca58409529851", "ts": 1791532423.3302786} {"pid": "L2_067", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.5374, "correct": true, "status": "ok", "speedup": 3.5374, "ref_ms": 13.02013, "cand_ms": 3.6807, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 89.1, "calls": 2, "tokens_in": 18375, "tokens_out": 6167, "ctx_chars": 14070, "ctx_sha": "3d6ada40588e7cb1", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "54acbc0a60c78d48", "ts": 1791532432.5471454} {"pid": "L2_073", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.3421, "correct": true, "status": "ok", "speedup": 3.3421, "ref_ms": 5.61872, "cand_ms": 1.68118, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 165.8, "calls": 2, "tokens_in": 28775, "tokens_out": 10513, "ctx_chars": 22975, "ctx_sha": "4e003dc4030b57a1", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3c87faeddcf675a5", "ts": 1791532439.8945448} {"pid": "L1_066", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 1.6131, "correct": true, "status": "ok", "speedup": 1.6131, "ref_ms": 7.80149, "cand_ms": 4.83622, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 129.4, "calls": 2, "tokens_in": 21398, "tokens_out": 6348, "ctx_chars": 15787, "ctx_sha": "304d3d83d624cb50", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e7ed12f066ae6307", "ts": 1791532454.9328015} {"pid": "L3_050", "split": "dev", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.786, "correct": true, "status": "ok", "speedup": 2.786, "ref_ms": 12.65657, "cand_ms": 4.54293, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 159.7, "calls": 3, "tokens_in": 418030, "tokens_out": 12208, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "49a4a56aab98939f", "ts": 1791532466.8128085} {"pid": "L2_053", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.1983, "correct": true, "status": "ok", "speedup": 4.1983, "ref_ms": 15.89803, "cand_ms": 3.78676, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 58.3, "calls": 2, "tokens_in": 23347, "tokens_out": 3565, "ctx_chars": 18655, "ctx_sha": "bbf921975c58f49c", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "e658ac7243c2a03a", "ts": 1791532481.651193} {"pid": "L2_020", "split": "dev", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.4347, "correct": true, "status": "ok", "speedup": 1.4347, "ref_ms": 14.16936, "cand_ms": 9.87618, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 124.5, "calls": 2, "tokens_in": 4535, "tokens_out": 2094, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0f0d9d685b75172f", "ts": 1791532484.852399} {"pid": "L3_008", "split": "dev", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": false, "score": 0.2321, "correct": true, "status": "ok", "speedup": 0.2321, "ref_ms": 5.24524, "cand_ms": 22.59787, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 210.8, "calls": 2, "tokens_in": 25839, "tokens_out": 18368, "ctx_chars": 16688, "ctx_sha": "1d0209b1f4f44f83", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "6f5efb29eb357815", "ts": 1791532490.5486634} {"pid": "L1_078", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.2969, "correct": true, "status": "ok", "speedup": 2.2969, "ref_ms": 35.77393, "cand_ms": 15.57511, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 227.8, "calls": 2, "tokens_in": 266513, "tokens_out": 3734, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "bcb2a2f0a32fb402", "ts": 1791532494.1608968} {"pid": "L3_050", "split": "dev", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.8219, "correct": true, "status": "ok", "speedup": 2.8219, "ref_ms": 12.69491, "cand_ms": 4.49875, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 162.5, "calls": 3, "tokens_in": 30348, "tokens_out": 11203, "ctx_chars": 10330, "ctx_sha": "4725ef765672a6e6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "fe5644c6ee297a81", "ts": 1791532494.418324} {"pid": "L3_002", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.5386, "correct": true, "status": "ok", "speedup": 1.5386, "ref_ms": 33.67411, "cand_ms": 21.88669, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 154.9, "calls": 2, "tokens_in": 5510, "tokens_out": 4801, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "f015038537ccf416", "ts": 1791532501.1519542} {"pid": "L3_008", "split": "dev", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.6088, "correct": true, "status": "ok", "speedup": 1.6088, "ref_ms": 5.68269, "cand_ms": 3.53224, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 353.5, "calls": 2, "tokens_in": 273828, "tokens_out": 29602, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "b85c112789a77e34", "ts": 1791532528.4918175} {"pid": "L3_044", "split": "dev", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.4394, "correct": true, "status": "ok", "speedup": 4.4394, "ref_ms": 75.30826, "cand_ms": 16.96353, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 188.8, "calls": 2, "tokens_in": 21929, "tokens_out": 17736, "ctx_chars": 10330, "ctx_sha": "4725ef765672a6e6", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "63985ef53ceacf96", "ts": 1791532534.958853} {"pid": "L2_058", "split": "dev", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 18.8711, "ref_ms": 25.09007, "cand_ms": 1.32955, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 120.5, "calls": 2, "tokens_in": 26000, "tokens_out": 9949, "ctx_chars": 20061, "ctx_sha": "a0a8edb8b6ae64a6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1ab37f22ced00569", "ts": 1791532553.0526884} {"pid": "L2_053", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0106, "correct": true, "status": "ok", "speedup": 1.0106, "ref_ms": 15.92217, "cand_ms": 15.75536, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 63.0, "calls": 2, "tokens_in": 4241, "tokens_out": 1931, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4bf7a22c22bc2875", "ts": 1791532557.4585297} {"pid": "L2_063", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.548, "correct": true, "status": "ok", "speedup": 3.548, "ref_ms": 8.11226, "cand_ms": 2.2864, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 72.6, "calls": 2, "tokens_in": 18357, "tokens_out": 2978, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "edd50a43a94bbe9f", "ts": 1791532563.1667728} {"pid": "L2_081", "split": "dev", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0346, "correct": true, "status": "ok", "speedup": 1.0346, "ref_ms": 8.21529, "cand_ms": 7.94081, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 64.4, "calls": 2, "tokens_in": 4826, "tokens_out": 2399, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4bc4289b5b700e38", "ts": 1791532565.545724} {"pid": "L2_073", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.6249, "correct": true, "status": "ok", "speedup": 1.6249, "ref_ms": 5.61786, "cand_ms": 3.45729, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 124.4, "calls": 2, "tokens_in": 10960, "tokens_out": 4465, "ctx_chars": 6744, "ctx_sha": "b92173e1465ccf4d", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f1cc28fafc08bff4", "ts": 1791532579.3152468} {"pid": "L2_020", "split": "dev", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.4578, "correct": true, "status": "ok", "speedup": 1.4578, "ref_ms": 14.15516, "cand_ms": 9.71027, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 96.7, "calls": 2, "tokens_in": 4940, "tokens_out": 2408, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "078ff6967e33e695", "ts": 1791532581.5736146} {"pid": "L2_063", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": false, "score": 1.0005, "correct": true, "status": "ok", "speedup": 1.0005, "ref_ms": 8.04867, "cand_ms": 8.04444, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 47.3, "calls": 2, "tokens_in": 10248, "tokens_out": 1398, "ctx_chars": 7272, "ctx_sha": "862484e5300b7ff6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "014266f516d9648d", "ts": 1791532582.2669706} {"pid": "L3_002", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.5908, "correct": true, "status": "ok", "speedup": 1.5908, "ref_ms": 33.64927, "cand_ms": 21.15236, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 194.0, "calls": 2, "tokens_in": 5679, "tokens_out": 6212, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "5190ec148b7903a8", "ts": 1791532584.946289} {"pid": "L2_040", "split": "dev", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.4817, "correct": true, "status": "ok", "speedup": 4.4817, "ref_ms": 30.42286, "cand_ms": 6.78822, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 94.9, "calls": 2, "tokens_in": 24034, "tokens_out": 3853, "ctx_chars": 19121, "ctx_sha": "d421a9dea165588e", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "67acb541e3905d1e", "ts": 1791532589.050883} {"pid": "L3_020", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 1.785, "correct": true, "status": "ok", "speedup": 1.785, "ref_ms": 7.42062, "cand_ms": 4.15723, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 349.5, "calls": 3, "tokens_in": 57236, "tokens_out": 32133, "ctx_chars": 21293, "ctx_sha": "c37e861435b5bbc4", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4eb704ac476244ba", "ts": 1791532595.320449} {"pid": "L2_088", "split": "dev", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.7387, "correct": true, "status": "ok", "speedup": 3.7387, "ref_ms": 8.47343, "cand_ms": 2.26639, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 128.8, "calls": 3, "tokens_in": 39040, "tokens_out": 8254, "ctx_chars": 18655, "ctx_sha": "bbf921975c58f49c", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "2a815c0d5cac5ca4", "ts": 1791532610.4999623} {"pid": "L2_020", "split": "dev", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.44, "correct": true, "status": "ok", "speedup": 1.44, "ref_ms": 14.21035, "cand_ms": 9.8681, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 229.6, "calls": 2, "tokens_in": 266338, "tokens_out": 4675, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "bcd4b72754926c48", "ts": 1791532619.0129778} {"pid": "L2_069", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.8854, "correct": true, "status": "ok", "speedup": 1.8854, "ref_ms": 4.00642, "cand_ms": 2.125, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 187.0, "calls": 3, "tokens_in": 13765, "tokens_out": 9994, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0ab5ed74f146d9f8", "ts": 1791532626.8642685} {"pid": "L3_020", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 1.843, "correct": true, "status": "ok", "speedup": 1.843, "ref_ms": 7.58397, "cand_ms": 4.11497, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 330.0, "calls": 3, "tokens_in": 58562, "tokens_out": 30762, "ctx_chars": 21293, "ctx_sha": "c37e861435b5bbc4", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d3f602abc98d1ca2", "ts": 1791532660.3476913} {"pid": "L2_052", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 1, "success": true, "score": 2.1789, "correct": true, "status": "ok", "speedup": 2.1789, "ref_ms": 11.12059, "cand_ms": 5.10374, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 193.8, "calls": 2, "tokens_in": 28622, "tokens_out": 12706, "ctx_chars": 22084, "ctx_sha": "9cc43a100b1de8c3", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "987b01a8150740fc", "ts": 1791532660.589292} {"pid": "L2_092", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.5626, "correct": true, "status": "ok", "speedup": 3.5626, "ref_ms": 8.52156, "cand_ms": 2.39192, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 112.6, "calls": 2, "tokens_in": 20505, "tokens_out": 9620, "ctx_chars": 14961, "ctx_sha": "549d04579f777963", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8f4fd015eca325ba", "ts": 1791532675.8008115} {"pid": "L2_053", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 4.196, "correct": true, "status": "ok", "speedup": 4.196, "ref_ms": 15.92053, "cand_ms": 3.79425, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 66.4, "calls": 2, "tokens_in": 16019, "tokens_out": 4555, "ctx_chars": 11583, "ctx_sha": "bb093721f8760f3d", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "87bc7ff2cafdf1e5", "ts": 1791532676.9394753} {"pid": "L3_020", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": false, "score": 0.2952, "correct": true, "status": "ok", "speedup": 0.2952, "ref_ms": 7.27413, "cand_ms": 24.63722, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 283.4, "calls": 2, "tokens_in": 13220, "tokens_out": 25099, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0f719ba12fbb5978", "ts": 1791532682.852207} {"pid": "L3_008", "split": "dev", "rep": 0, "arm": "ace", "attempt": 0, "restart": 1, "success": true, "score": 1.5148, "correct": true, "status": "ok", "speedup": 1.5148, "ref_ms": 5.26257, "cand_ms": 3.47411, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 313.9, "calls": 2, "tokens_in": 272998, "tokens_out": 23089, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "483ad612c4e10977", "ts": 1791532684.5139346} {"pid": "L2_058", "split": "dev", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 14.9425, "ref_ms": 25.17028, "cand_ms": 1.68448, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 116.9, "calls": 2, "tokens_in": 13213, "tokens_out": 7605, "ctx_chars": 8031, "ctx_sha": "8e7ee93b3140d14f", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "6e3ab7dc963a53b5", "ts": 1791532696.2571461} {"pid": "L2_029", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.3053, "correct": true, "status": "ok", "speedup": 3.3053, "ref_ms": 8.05505, "cand_ms": 2.43699, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 77.2, "calls": 2, "tokens_in": 23734, "tokens_out": 3703, "ctx_chars": 19121, "ctx_sha": "d421a9dea165588e", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "f9fa5564d2764c93", "ts": 1791532696.2577143} {"pid": "L3_048", "split": "dev", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": false, "score": 0.9531, "correct": true, "status": "ok", "speedup": 0.9531, "ref_ms": 15.9204, "cand_ms": 16.70365, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 288.7, "calls": 5, "tokens_in": 40196, "tokens_out": 17741, "ctx_chars": 3184, "ctx_sha": "e64357aa997958f6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "6ee7e3e155cff0d5", "ts": 1791532709.9454176} {"pid": "L2_058", "split": "dev", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 19.9534, "ref_ms": 25.18345, "cand_ms": 1.26211, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 128.9, "calls": 2, "tokens_in": 13757, "tokens_out": 8592, "ctx_chars": 8031, "ctx_sha": "8e7ee93b3140d14f", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "909f11727684108f", "ts": 1791532710.4456913} {"pid": "L2_052", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 2.2654, "correct": true, "status": "ok", "speedup": 2.2654, "ref_ms": 11.06436, "cand_ms": 4.88406, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 162.5, "calls": 2, "tokens_in": 28325, "tokens_out": 10156, "ctx_chars": 22084, "ctx_sha": "9cc43a100b1de8c3", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c0eda6d9af78899d", "ts": 1791532715.556872} {"pid": "L2_062", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0652, "correct": true, "status": "ok", "speedup": 1.0652, "ref_ms": 8.52769, "cand_ms": 8.00541, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 47.8, "calls": 2, "tokens_in": 9697, "tokens_out": 2649, "ctx_chars": 5389, "ctx_sha": "be81589e9761e178", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "748b6c2453fc56d5", "ts": 1791532723.5698376} {"pid": "L2_088", "split": "dev", "rep": 0, "arm": "stock", "attempt": 0, "restart": 1, "success": true, "score": 1.0673, "correct": true, "status": "ok", "speedup": 1.0673, "ref_ms": 8.49271, "cand_ms": 7.95705, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 47.0, "calls": 2, "tokens_in": 10415, "tokens_out": 2379, "ctx_chars": 6231, "ctx_sha": "4e345ad7f535c321", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1213b377b2517c2a", "ts": 1791532723.933325} {"pid": "L2_020", "split": "dev", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.4405, "correct": true, "status": "ok", "speedup": 1.4405, "ref_ms": 14.30685, "cand_ms": 9.93195, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 205.8, "calls": 2, "tokens_in": 266172, "tokens_out": 4279, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "cc7320607fdd9d25", "ts": 1791532734.267225} {"pid": "L3_048", "split": "dev", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": false, "score": 0.3488, "correct": true, "status": "ok", "speedup": 0.3488, "ref_ms": 15.93057, "cand_ms": 45.67441, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 357.5, "calls": 5, "tokens_in": 38607, "tokens_out": 22197, "ctx_chars": 3184, "ctx_sha": "e64357aa997958f6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "37fa33ac424ee525", "ts": 1791532738.0733125} {"pid": "L2_062", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 154.9, "calls": 3, "tokens_in": 414071, "tokens_out": 10760, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": false, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "567dcc902b00cc1b", "ts": 1791532739.813834} {"pid": "L2_053", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 4.1917, "correct": true, "status": "ok", "speedup": 4.1917, "ref_ms": 15.87616, "cand_ms": 3.78749, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 80.2, "calls": 2, "tokens_in": 15946, "tokens_out": 5219, "ctx_chars": 11583, "ctx_sha": "bb093721f8760f3d", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "8298585e8f6651f3", "ts": 1791532740.7808003} {"pid": "L3_047", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.7495, "correct": true, "status": "ok", "speedup": 2.7495, "ref_ms": 3.63637, "cand_ms": 1.32255, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 154.9, "calls": 2, "tokens_in": 32041, "tokens_out": 9864, "ctx_chars": 22064, "ctx_sha": "47c729252530dc44", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "b11a4f8b3dc1523a", "ts": 1791532743.9288673} {"pid": "L2_073", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.2773, "correct": true, "status": "ok", "speedup": 3.2773, "ref_ms": 5.66034, "cand_ms": 1.72712, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 200.6, "calls": 2, "tokens_in": 29546, "tokens_out": 13190, "ctx_chars": 22975, "ctx_sha": "4e003dc4030b57a1", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "03d5b398337a0336", "ts": 1791532758.052497} {"pid": "L2_092", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.6872, "correct": true, "status": "ok", "speedup": 2.6872, "ref_ms": 8.62971, "cand_ms": 3.2114, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 170.1, "calls": 2, "tokens_in": 267318, "tokens_out": 7732, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2e3cb0f406531965", "ts": 1791532765.4297416} {"pid": "L2_069", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 1, "success": true, "score": 1.2721, "correct": true, "status": "ok", "speedup": 1.2721, "ref_ms": 3.66485, "cand_ms": 2.88086, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 186.3, "calls": 2, "tokens_in": 265562, "tokens_out": 3308, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "76f53f9d62b8da98", "ts": 1791532768.6142318} {"pid": "L3_002", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.3192, "correct": true, "status": "ok", "speedup": 2.3192, "ref_ms": 33.67014, "cand_ms": 14.51813, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 143.4, "calls": 2, "tokens_in": 15732, "tokens_out": 5106, "ctx_chars": 10450, "ctx_sha": "b62926c8e92a5539", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1251467359b1b2b3", "ts": 1791532770.2795124} {"pid": "L2_081", "split": "dev", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0354, "correct": true, "status": "ok", "speedup": 1.0354, "ref_ms": 8.33329, "cand_ms": 8.04853, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 46.0, "calls": 2, "tokens_in": 4413, "tokens_out": 2079, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2319ebc3a1c0a4cb", "ts": 1791532780.3093565} {"pid": "L2_088", "split": "dev", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0658, "correct": true, "status": "ok", "speedup": 1.0658, "ref_ms": 8.45436, "cand_ms": 7.9327, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 53.1, "calls": 2, "tokens_in": 5381, "tokens_out": 2981, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "bb90519a5f4826b9", "ts": 1791532793.9241323} {"pid": "L2_062", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0708, "correct": true, "status": "ok", "speedup": 1.0708, "ref_ms": 8.48483, "cand_ms": 7.92409, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 57.4, "calls": 2, "tokens_in": 4901, "tokens_out": 2902, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ddeb8dfe5a8ca322", "ts": 1791532795.440161} {"pid": "L3_044", "split": "dev", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.2166, "correct": true, "status": "ok", "speedup": 1.2166, "ref_ms": 75.31576, "cand_ms": 61.90727, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 135.1, "calls": 2, "tokens_in": 9774, "tokens_out": 10316, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e9ac68fc69cb4824", "ts": 1791532795.470255} {"pid": "L1_066", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.2602, "correct": true, "status": "ok", "speedup": 1.2602, "ref_ms": 7.77204, "cand_ms": 6.16724, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 115.3, "calls": 2, "tokens_in": 14495, "tokens_out": 5818, "ctx_chars": 8854, "ctx_sha": "420ebf050379abd1", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "35a9f10f896d96ce", "ts": 1791532798.1405175} {"pid": "L2_053", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.8579, "correct": true, "status": "ok", "speedup": 4.8579, "ref_ms": 16.01454, "cand_ms": 3.29662, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 80.8, "calls": 2, "tokens_in": 273632, "tokens_out": 4388, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "7e5ac251b6b4a5f1", "ts": 1791532804.759598} {"pid": "L2_040", "split": "dev", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0318, "correct": true, "status": "ok", "speedup": 1.0318, "ref_ms": 30.39067, "cand_ms": 29.45504, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 69.7, "calls": 2, "tokens_in": 4364, "tokens_out": 2047, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "520a3519ea72c9c1", "ts": 1791532809.4875546} {"pid": "L2_037", "split": "dev", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.4566, "correct": true, "status": "ok", "speedup": 1.4566, "ref_ms": 19.69196, "cand_ms": 13.51914, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 139.9, "calls": 2, "tokens_in": 266899, "tokens_out": 7398, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "33a79751740e098a", "ts": 1791532836.139462} {"pid": "L3_050", "split": "dev", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 3.5093, "correct": true, "status": "ok", "speedup": 3.5093, "ref_ms": 12.63753, "cand_ms": 3.60118, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 112.9, "calls": 2, "tokens_in": 8299, "tokens_out": 8773, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "d9a8a7699be7dbcb", "ts": 1791532836.5136786} {"pid": "L2_067", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 2.5151, "correct": true, "status": "ok", "speedup": 2.5151, "ref_ms": 12.88995, "cand_ms": 5.12506, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 137.6, "calls": 2, "tokens_in": 7146, "tokens_out": 11200, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3be516f2cdb0c81c", "ts": 1791532848.0531545} {"pid": "L2_067", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 2.451, "correct": true, "status": "ok", "speedup": 2.451, "ref_ms": 12.9317, "cand_ms": 5.27618, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 154.0, "calls": 2, "tokens_in": 6825, "tokens_out": 11951, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "cfbc42f6652dbc74", "ts": 1791532850.2099066} {"pid": "L2_088", "split": "dev", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.7612, "correct": true, "status": "ok", "speedup": 3.7612, "ref_ms": 8.49666, "cand_ms": 2.25903, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 81.0, "calls": 2, "tokens_in": 16367, "tokens_out": 6361, "ctx_chars": 11583, "ctx_sha": "bb093721f8760f3d", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "4b1f9d7e34b6caf3", "ts": 1791532851.2365103} {"pid": "L3_047", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.6166, "correct": true, "status": "ok", "speedup": 2.6166, "ref_ms": 3.63794, "cand_ms": 1.39031, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 110.4, "calls": 2, "tokens_in": 14275, "tokens_out": 8757, "ctx_chars": 6833, "ctx_sha": "51e2cdabc27184da", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4a72b2dbb53be769", "ts": 1791532854.2809484} {"pid": "L2_062", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0728, "correct": true, "status": "ok", "speedup": 1.0728, "ref_ms": 8.48272, "cand_ms": 7.90682, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 58.2, "calls": 2, "tokens_in": 5284, "tokens_out": 3908, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "12bc8dbab6458e5b", "ts": 1791532856.3801644} {"pid": "L2_081", "split": "dev", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 3.615, "correct": true, "status": "ok", "speedup": 3.615, "ref_ms": 8.28232, "cand_ms": 2.29111, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 81.5, "calls": 2, "tokens_in": 273760, "tokens_out": 4149, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "79969159c9d1fd9b", "ts": 1791532861.790885} {"pid": "L2_020", "split": "dev", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 1.4367, "correct": true, "status": "ok", "speedup": 1.4367, "ref_ms": 14.15483, "cand_ms": 9.85201, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 103.2, "calls": 2, "tokens_in": 23962, "tokens_out": 2484, "ctx_chars": 20061, "ctx_sha": "a0a8edb8b6ae64a6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c82f0abc7de8b8a2", "ts": 1791532868.6529026} {"pid": "L2_058", "split": "dev", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 21.0144, "ref_ms": 25.13639, "cand_ms": 1.19615, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 155.9, "calls": 3, "tokens_in": 16343, "tokens_out": 12337, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d5b5441ff0bf97ce", "ts": 1791532871.4755974} {"pid": "L3_008", "split": "dev", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 2.8736, "correct": true, "status": "ok", "speedup": 2.8736, "ref_ms": 5.29778, "cand_ms": 1.84364, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 179.4, "calls": 2, "tokens_in": 25740, "tokens_out": 17400, "ctx_chars": 16688, "ctx_sha": "1d0209b1f4f44f83", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3ff41bdf6f6c221e", "ts": 1791532889.37627} {"pid": "L2_092", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 2.7983, "correct": true, "status": "ok", "speedup": 2.7983, "ref_ms": 8.49435, "cand_ms": 3.03557, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 100.4, "calls": 2, "tokens_in": 20844, "tokens_out": 8980, "ctx_chars": 14961, "ctx_sha": "549d04579f777963", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "7cda751e76ea4aec", "ts": 1791532895.8843286} {"pid": "L2_053", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.8393, "correct": true, "status": "ok", "speedup": 4.8393, "ref_ms": 15.96441, "cand_ms": 3.29888, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 71.6, "calls": 2, "tokens_in": 273643, "tokens_out": 4344, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "d8fcfde57b038460", "ts": 1791532908.133936} {"pid": "L3_008", "split": "dev", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": false, "score": 0.2044, "correct": true, "status": "ok", "speedup": 0.2044, "ref_ms": 5.27066, "cand_ms": 25.7883, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 230.8, "calls": 2, "tokens_in": 25568, "tokens_out": 17835, "ctx_chars": 16688, "ctx_sha": "1d0209b1f4f44f83", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e8a2916aa2b1414a", "ts": 1791532915.2793374} {"pid": "L2_037", "split": "dev", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.4638, "correct": true, "status": "ok", "speedup": 1.4638, "ref_ms": 19.75619, "cand_ms": 13.49688, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 134.0, "calls": 2, "tokens_in": 266779, "tokens_out": 6512, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "5b8984ab944ed04f", "ts": 1791532927.9300153} {"pid": "L1_066", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 2.6774, "correct": true, "status": "ok", "speedup": 2.6774, "ref_ms": 7.79186, "cand_ms": 2.91024, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 126.6, "calls": 2, "tokens_in": 21673, "tokens_out": 7068, "ctx_chars": 15787, "ctx_sha": "304d3d83d624cb50", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1c6a7e5a5289b876", "ts": 1791532931.408318} {"pid": "L1_078", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.2565, "correct": true, "status": "ok", "speedup": 2.2565, "ref_ms": 35.58153, "cand_ms": 15.76876, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 103.8, "calls": 2, "tokens_in": 12209, "tokens_out": 2660, "ctx_chars": 7879, "ctx_sha": "f7c7999053853d91", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1066c1e3165f866d", "ts": 1791532954.0078354} {"pid": "L3_047", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 3.21, "correct": true, "status": "ok", "speedup": 3.21, "ref_ms": 3.63376, "cand_ms": 1.13202, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 156.0, "calls": 2, "tokens_in": 269666, "tokens_out": 12685, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "5f2fba9b78feeee5", "ts": 1791532965.4814816} {"pid": "L2_069", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.8248, "correct": true, "status": "ok", "speedup": 2.8248, "ref_ms": 4.00656, "cand_ms": 1.41834, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 404.3, "calls": 4, "tokens_in": 543399, "tokens_out": 16762, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0e97e79479a36788", "ts": 1791532969.8332725} {"pid": "L3_033", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.4512, "correct": true, "status": "ok", "speedup": 1.4512, "ref_ms": 20.44427, "cand_ms": 14.08822, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 141.3, "calls": 2, "tokens_in": 6739, "tokens_out": 7502, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "49f1ee968dae8785", "ts": 1791532995.5343149} {"pid": "L2_058", "split": "dev", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 12.2674, "ref_ms": 25.09248, "cand_ms": 2.04547, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 139.0, "calls": 2, "tokens_in": 25383, "tokens_out": 8287, "ctx_chars": 20061, "ctx_sha": "a0a8edb8b6ae64a6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "6ec90455bedae1d3", "ts": 1791533000.7831056} {"pid": "L3_033", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0697, "correct": true, "status": "ok", "speedup": 1.0697, "ref_ms": 20.58375, "cand_ms": 19.24184, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 142.2, "calls": 2, "tokens_in": 6767, "tokens_out": 9696, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "378142c9ddb3f4f9", "ts": 1791533013.6804798} {"pid": "L3_047", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.5097, "correct": true, "status": "ok", "speedup": 2.5097, "ref_ms": 3.64546, "cand_ms": 1.45257, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 180.2, "calls": 2, "tokens_in": 277969, "tokens_out": 15933, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "31de866a9b7b20ee", "ts": 1791533016.3114831} {"pid": "L3_044", "split": "dev", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.2405, "correct": true, "status": "ok", "speedup": 1.2405, "ref_ms": 75.38348, "cand_ms": 60.7676, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 133.3, "calls": 2, "tokens_in": 11210, "tokens_out": 6536, "ctx_chars": 3184, "ctx_sha": "e64357aa997958f6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "5198fefe70819a18", "ts": 1791533022.7081296} {"pid": "L2_069", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.2572, "correct": true, "status": "ok", "speedup": 1.2572, "ref_ms": 3.65464, "cand_ms": 2.90692, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 172.2, "calls": 2, "tokens_in": 265452, "tokens_out": 3189, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "18654a4d296f9b32", "ts": 1791533028.6201372} {"pid": "L2_052", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.4117, "correct": true, "status": "ok", "speedup": 1.4117, "ref_ms": 11.05444, "cand_ms": 7.83055, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 116.2, "calls": 2, "tokens_in": 12062, "tokens_out": 4757, "ctx_chars": 7687, "ctx_sha": "00b2f6d51bc8c639", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e0819b34f6781d9a", "ts": 1791533031.5055227} {"pid": "L3_047", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.024, "correct": true, "status": "ok", "speedup": 3.024, "ref_ms": 3.63297, "cand_ms": 1.20138, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 125.3, "calls": 2, "tokens_in": 22298, "tokens_out": 9927, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e432919b391eefdd", "ts": 1791533033.463165} {"pid": "L1_078", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.3157, "correct": true, "status": "ok", "speedup": 2.3157, "ref_ms": 35.79879, "cand_ms": 15.459, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 186.8, "calls": 2, "tokens_in": 266266, "tokens_out": 3536, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3bb054183e2e4a00", "ts": 1791533034.8784156} {"pid": "L3_020", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.9167, "correct": true, "status": "ok", "speedup": 1.9167, "ref_ms": 7.03515, "cand_ms": 3.6704, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 274.7, "calls": 2, "tokens_in": 272263, "tokens_out": 20114, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "13fc598f2438a333", "ts": 1791533043.344692} {"pid": "L3_047", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.2567, "correct": true, "status": "ok", "speedup": 2.2567, "ref_ms": 3.6463, "cand_ms": 1.61575, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 197.4, "calls": 2, "tokens_in": 11198, "tokens_out": 17148, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "9c3be87c9309f45f", "ts": 1791533093.2629075} {"pid": "L3_048", "split": "dev", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.1833, "correct": true, "status": "ok", "speedup": 1.1833, "ref_ms": 15.91128, "cand_ms": 13.44651, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 304.8, "calls": 4, "tokens_in": 560758, "tokens_out": 18577, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2df03a8d3246178d", "ts": 1791533100.2548747} {"pid": "L2_039", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.1488, "correct": true, "status": "ok", "speedup": 4.1488, "ref_ms": 30.1756, "cand_ms": 7.27326, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 193.2, "calls": 3, "tokens_in": 56696, "tokens_out": 16008, "ctx_chars": 26669, "ctx_sha": "3b6d6db80184b500", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "401e47d667ed81cc", "ts": 1791533121.085633} {"pid": "L1_066", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.4597, "correct": true, "status": "ok", "speedup": 3.4597, "ref_ms": 7.7746, "cand_ms": 2.24719, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 126.8, "calls": 2, "tokens_in": 21732, "tokens_out": 6864, "ctx_chars": 15787, "ctx_sha": "304d3d83d624cb50", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1f929bb865f70e50", "ts": 1791533122.353908} {"pid": "L2_040", "split": "dev", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.4156, "correct": true, "status": "ok", "speedup": 4.4156, "ref_ms": 30.40317, "cand_ms": 6.88533, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 122.3, "calls": 2, "tokens_in": 273452, "tokens_out": 4366, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "b7ad61cc045e93ae", "ts": 1791533123.1059918} {"pid": "L2_062", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.6396, "correct": true, "status": "ok", "speedup": 1.6396, "ref_ms": 8.49326, "cand_ms": 5.18012, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 103.6, "calls": 2, "tokens_in": 5489, "tokens_out": 4665, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "8ca2b91ec95bab71", "ts": 1791533135.1403348} {"pid": "L2_062", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 2.0403, "correct": true, "status": "ok", "speedup": 2.0403, "ref_ms": 8.49341, "cand_ms": 4.16286, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 117.5, "calls": 3, "tokens_in": 28568, "tokens_out": 9646, "ctx_chars": 12049, "ctx_sha": "cd92549f2b7fd121", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "8e5910c321563753", "ts": 1791533140.2398396} {"pid": "L1_066", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 1.5921, "correct": true, "status": "ok", "speedup": 1.5921, "ref_ms": 7.75879, "cand_ms": 4.87341, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 133.2, "calls": 2, "tokens_in": 21489, "tokens_out": 6755, "ctx_chars": 15787, "ctx_sha": "304d3d83d624cb50", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0a5c80888bf86e22", "ts": 1791533149.490386} {"pid": "L3_008", "split": "dev", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.4717, "correct": true, "status": "ok", "speedup": 1.4717, "ref_ms": 5.29628, "cand_ms": 3.59884, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 299.6, "calls": 2, "tokens_in": 271793, "tokens_out": 20989, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "300703fec6828f79", "ts": 1791533150.8625107} {"pid": "L3_050", "split": "dev", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 141.4, "calls": 3, "tokens_in": 49498, "tokens_out": 11975, "ctx_chars": 22253, "ctx_sha": "e98f6866890474ec", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "30b14e5d6f492b53", "ts": 1791533155.0506876} {"pid": "L2_073", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 2.3124, "correct": true, "status": "ok", "speedup": 2.3124, "ref_ms": 5.59207, "cand_ms": 2.41828, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 212.8, "calls": 2, "tokens_in": 8321, "tokens_out": 14771, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "186ea92b5c389af6", "ts": 1791533182.5837433} {"pid": "L1_078", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 3.4041, "correct": true, "status": "ok", "speedup": 3.4041, "ref_ms": 35.64315, "cand_ms": 10.47061, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 170.0, "calls": 2, "tokens_in": 7095, "tokens_out": 9991, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "aa4a4092ffe82dae", "ts": 1791533198.6589158} {"pid": "L2_067", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.3622, "correct": true, "status": "ok", "speedup": 1.3622, "ref_ms": 12.82381, "cand_ms": 9.41372, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 94.6, "calls": 2, "tokens_in": 11993, "tokens_out": 6992, "ctx_chars": 7583, "ctx_sha": "5300ffdccc59e7fb", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "1f67da1e07941b39", "ts": 1791533229.715098} {"pid": "L2_073", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.387, "correct": true, "status": "ok", "speedup": 2.387, "ref_ms": 5.71687, "cand_ms": 2.39504, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 214.8, "calls": 2, "tokens_in": 7969, "tokens_out": 14165, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "82dd1f3b329a2ba9", "ts": 1791533249.6795185} {"pid": "L3_008", "split": "dev", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 1, "success": true, "score": 2.7362, "correct": true, "status": "ok", "speedup": 2.7362, "ref_ms": 5.28613, "cand_ms": 1.93193, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 210.1, "calls": 2, "tokens_in": 25821, "tokens_out": 17520, "ctx_chars": 16688, "ctx_sha": "1d0209b1f4f44f83", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "54d166ed12725ff3", "ts": 1791533253.4711313} {"pid": "L2_092", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.7245, "correct": true, "status": "ok", "speedup": 2.7245, "ref_ms": 8.4922, "cand_ms": 3.11703, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 168.1, "calls": 2, "tokens_in": 267216, "tokens_out": 6813, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "368ae0a7f3a195af", "ts": 1791533261.3197565} {"pid": "L2_069", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.6793, "correct": true, "status": "ok", "speedup": 3.6793, "ref_ms": 4.00576, "cand_ms": 1.08873, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 122.5, "calls": 2, "tokens_in": 19927, "tokens_out": 4968, "ctx_chars": 15668, "ctx_sha": "bb1fdfba7b87d1ff", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "fc5f1e03cd6efc2e", "ts": 1791533262.7648022} {"pid": "L2_058", "split": "dev", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 19.2307, "ref_ms": 25.08825, "cand_ms": 1.30459, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 130.8, "calls": 2, "tokens_in": 6777, "tokens_out": 7596, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "62694f69f1e47d5e", "ts": 1791533280.2954032} {"pid": "L2_058", "split": "dev", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 7.0518, "correct": true, "status": "ok", "speedup": 7.0518, "ref_ms": 25.0368, "cand_ms": 3.55041, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 187.7, "calls": 2, "tokens_in": 267605, "tokens_out": 9376, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e85a4afa7ad04e71", "ts": 1791533287.956149} {"pid": "L3_033", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.4329, "correct": true, "status": "ok", "speedup": 1.4329, "ref_ms": 20.67036, "cand_ms": 14.42567, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 177.9, "calls": 2, "tokens_in": 267440, "tokens_out": 8233, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "ffa72545001a9e92", "ts": 1791533300.9714124} {"pid": "L2_058", "split": "dev", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 14.7794, "ref_ms": 25.02596, "cand_ms": 1.6933, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 103.4, "calls": 2, "tokens_in": 6766, "tokens_out": 6932, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "cdf784a3feaf3818", "ts": 1791533302.0675566} {"pid": "L3_050", "split": "dev", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.1777, "correct": true, "status": "ok", "speedup": 2.1777, "ref_ms": 12.69392, "cand_ms": 5.82908, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 73.1, "calls": 2, "tokens_in": 6708, "tokens_out": 3510, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "714bb58a7f7952a7", "ts": 1791533302.817751} {"pid": "L2_058", "split": "dev", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 13.8573, "ref_ms": 25.16042, "cand_ms": 1.81567, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 124.4, "calls": 2, "tokens_in": 6390, "tokens_out": 6724, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8de8e40a562c6e30", "ts": 1791533306.963834} {"pid": "L1_066", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.371, "correct": true, "status": "ok", "speedup": 2.371, "ref_ms": 7.76294, "cand_ms": 3.2741, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 157.6, "calls": 2, "tokens_in": 21575, "tokens_out": 7121, "ctx_chars": 15787, "ctx_sha": "304d3d83d624cb50", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2ff364447b4876c1", "ts": 1791533308.413239} {"pid": "L2_081", "split": "dev", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.6739, "correct": true, "status": "ok", "speedup": 3.6739, "ref_ms": 8.2069, "cand_ms": 2.23384, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 55.7, "calls": 2, "tokens_in": 18851, "tokens_out": 3405, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "959bbe3b14cd31fd", "ts": 1791533317.0653234} {"pid": "L2_081", "split": "dev", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.034, "correct": true, "status": "ok", "speedup": 1.034, "ref_ms": 8.2139, "cand_ms": 7.94411, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 48.5, "calls": 2, "tokens_in": 4807, "tokens_out": 2264, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "bde2a0f309aab178", "ts": 1791533336.4463613} {"pid": "L2_053", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.1864, "correct": true, "status": "ok", "speedup": 4.1864, "ref_ms": 15.88966, "cand_ms": 3.79551, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 71.8, "calls": 2, "tokens_in": 273528, "tokens_out": 4080, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "e44bca09308424b4", "ts": 1791533352.1240346} {"pid": "L2_053", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.1906, "correct": true, "status": "ok", "speedup": 4.1906, "ref_ms": 15.94369, "cand_ms": 3.80465, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 57.4, "calls": 2, "tokens_in": 18910, "tokens_out": 3560, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "6d3ed964679ccc8a", "ts": 1791533360.1896353} {"pid": "L2_092", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.6507, "correct": true, "status": "ok", "speedup": 2.6507, "ref_ms": 8.5259, "cand_ms": 3.2165, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 99.0, "calls": 2, "tokens_in": 10627, "tokens_out": 4317, "ctx_chars": 5747, "ctx_sha": "169afaa9eeb4d53a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "94cc6db63dfd2680", "ts": 1791533361.745233} {"pid": "L2_067", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.329, "correct": true, "status": "ok", "speedup": 2.329, "ref_ms": 12.85574, "cand_ms": 5.5198, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 213.4, "calls": 3, "tokens_in": 24745, "tokens_out": 13107, "ctx_chars": 7583, "ctx_sha": "5300ffdccc59e7fb", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2426cf9c6cbe0e17", "ts": 1791533368.456619} {"pid": "L3_047", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.4191, "correct": true, "status": "ok", "speedup": 2.4191, "ref_ms": 3.633, "cand_ms": 1.5018, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 128.3, "calls": 2, "tokens_in": 22318, "tokens_out": 9710, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "95d135cfc705fcfc", "ts": 1791533378.0107548} {"pid": "L2_020", "split": "dev", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 6.7239, "correct": true, "status": "ok", "speedup": 6.7239, "ref_ms": 14.20679, "cand_ms": 2.11288, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 358.8, "calls": 2, "tokens_in": 26607, "tokens_out": 10484, "ctx_chars": 20061, "ctx_sha": "a0a8edb8b6ae64a6", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "6869e80373414fe6", "ts": 1791533392.2608147} {"pid": "L3_048", "split": "dev", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.1818, "correct": true, "status": "ok", "speedup": 1.1818, "ref_ms": 15.9997, "cand_ms": 13.53852, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 445.9, "calls": 3, "tokens_in": 418796, "tokens_out": 32988, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "54c9d980e9e2dd54", "ts": 1791533399.9535916} {"pid": "L2_058", "split": "dev", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 16.5696, "ref_ms": 25.17949, "cand_ms": 1.51962, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 292.6, "calls": 3, "tokens_in": 406858, "tokens_out": 12985, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f47a3ebd5e404339", "ts": 1791533414.9523065} {"pid": "L2_052", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.4117, "correct": true, "status": "ok", "speedup": 1.4117, "ref_ms": 11.06357, "cand_ms": 7.83681, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 126.2, "calls": 2, "tokens_in": 12098, "tokens_out": 4419, "ctx_chars": 7687, "ctx_sha": "00b2f6d51bc8c639", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "6e2786d6d0e29194", "ts": 1791533428.2731388} {"pid": "L1_078", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 8.2509, "correct": true, "status": "ok", "speedup": 8.2509, "ref_ms": 35.84782, "cand_ms": 4.3447, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 131.5, "calls": 2, "tokens_in": 25345, "tokens_out": 6650, "ctx_chars": 19130, "ctx_sha": "0551daeb8a590834", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1ac1fcf543290697", "ts": 1791533448.5643744} {"pid": "L2_069", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.2542, "correct": true, "status": "ok", "speedup": 1.2542, "ref_ms": 3.70232, "cand_ms": 2.95183, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 95.3, "calls": 2, "tokens_in": 12428, "tokens_out": 1961, "ctx_chars": 9026, "ctx_sha": "a3512fc398ca432b", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e860b60c37d4853b", "ts": 1791533473.346838} {"pid": "L3_002", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.3533, "correct": true, "status": "ok", "speedup": 2.3533, "ref_ms": 33.85331, "cand_ms": 14.38542, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 130.5, "calls": 2, "tokens_in": 15743, "tokens_out": 4927, "ctx_chars": 10450, "ctx_sha": "b62926c8e92a5539", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3595df2246f3c981", "ts": 1791533482.6169431} {"pid": "L2_029", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.0373, "correct": true, "status": "ok", "speedup": 1.0373, "ref_ms": 8.10903, "cand_ms": 7.81764, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 120.8, "calls": 2, "tokens_in": 265874, "tokens_out": 4761, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "129b8c2ad7cf3107", "ts": 1791533489.2163928} {"pid": "L3_033", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.1727, "correct": true, "status": "ok", "speedup": 3.1727, "ref_ms": 20.46916, "cand_ms": 6.45158, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 194.6, "calls": 2, "tokens_in": 14385, "tokens_out": 14685, "ctx_chars": 7910, "ctx_sha": "434d12593ff4fff3", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "64698c17394f4713", "ts": 1791533501.5314512} {"pid": "L3_002", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.3027, "correct": true, "status": "ok", "speedup": 2.3027, "ref_ms": 33.70598, "cand_ms": 14.63764, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 166.9, "calls": 2, "tokens_in": 274026, "tokens_out": 5412, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "a772d1a20ed1728e", "ts": 1791533503.3747778} {"pid": "L2_037", "split": "dev", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.2838, "correct": true, "status": "ok", "speedup": 1.2838, "ref_ms": 19.6669, "cand_ms": 15.31906, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 103.8, "calls": 2, "tokens_in": 10142, "tokens_out": 2377, "ctx_chars": 6342, "ctx_sha": "c3ce68171bb279a4", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e650232b16d09ce5", "ts": 1791533503.7266922} {"pid": "L2_067", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.4552, "correct": true, "status": "ok", "speedup": 2.4552, "ref_ms": 12.87918, "cand_ms": 5.24572, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 202.9, "calls": 3, "tokens_in": 14985, "tokens_out": 14524, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "828c74814bf5b373", "ts": 1791533503.8263495} {"pid": "L3_047", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.6304, "correct": true, "status": "ok", "speedup": 2.6304, "ref_ms": 3.63671, "cand_ms": 1.38256, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 91.5, "calls": 2, "tokens_in": 13755, "tokens_out": 6250, "ctx_chars": 6833, "ctx_sha": "51e2cdabc27184da", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "a5800f7625e9466e", "ts": 1791533506.4617178} {"pid": "L3_020", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": false, "score": 0.7199, "correct": true, "status": "ok", "speedup": 0.7199, "ref_ms": 7.0549, "cand_ms": 9.80006, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 120.9, "calls": 2, "tokens_in": 19577, "tokens_out": 11530, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "25f968daeec4f48d", "ts": 1791533513.123869} {"pid": "L2_052", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.3682, "correct": true, "status": "ok", "speedup": 1.3682, "ref_ms": 11.08821, "cand_ms": 8.1042, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 158.2, "calls": 2, "tokens_in": 5294, "tokens_out": 4555, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ce6bcde4b94a5420", "ts": 1791533518.4135566} {"pid": "L3_008", "split": "dev", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 2.6762, "correct": true, "status": "ok", "speedup": 2.6762, "ref_ms": 5.31894, "cand_ms": 1.98747, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 216.2, "calls": 2, "tokens_in": 26048, "tokens_out": 18382, "ctx_chars": 16688, "ctx_sha": "1d0209b1f4f44f83", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ce76bd29d0541f60", "ts": 1791533524.5641296} {"pid": "L3_048", "split": "dev", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.2597, "correct": true, "status": "ok", "speedup": 1.2597, "ref_ms": 15.86659, "cand_ms": 12.59549, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 435.9, "calls": 4, "tokens_in": 564169, "tokens_out": 27966, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "7f8a706294170ed4", "ts": 1791533556.9976995} {"pid": "L2_020", "split": "dev", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.4483, "correct": true, "status": "ok", "speedup": 1.4483, "ref_ms": 13.97182, "cand_ms": 9.64732, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 88.9, "calls": 2, "tokens_in": 11084, "tokens_out": 1668, "ctx_chars": 7394, "ctx_sha": "632a38c7eee085c0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2ec948b4378dd1e5", "ts": 1791533562.295094} {"pid": "L2_040", "split": "dev", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0263, "correct": true, "status": "ok", "speedup": 1.0263, "ref_ms": 30.50495, "cand_ms": 29.72338, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 82.5, "calls": 2, "tokens_in": 4451, "tokens_out": 2233, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "274d6827f64ea371", "ts": 1791533585.9182365} {"pid": "L2_040", "split": "dev", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0302, "correct": true, "status": "ok", "speedup": 1.0302, "ref_ms": 30.33148, "cand_ms": 29.44231, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 118.2, "calls": 2, "tokens_in": 4829, "tokens_out": 2727, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "62fd8176b02b3337", "ts": 1791533619.7648263} {"pid": "L2_037", "split": "dev", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.7758, "correct": true, "status": "ok", "speedup": 4.7758, "ref_ms": 19.97644, "cand_ms": 4.18288, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 117.6, "calls": 2, "tokens_in": 19864, "tokens_out": 4393, "ctx_chars": 14516, "ctx_sha": "491a69f435bf3217", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "b40a7a043ba47692", "ts": 1791533630.7717469} {"pid": "L2_020", "split": "dev", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.4306, "correct": true, "status": "ok", "speedup": 1.4306, "ref_ms": 14.07345, "cand_ms": 9.83746, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 124.4, "calls": 2, "tokens_in": 4604, "tokens_out": 2379, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f25c1172bae4b1e4", "ts": 1791533648.9417064} {"pid": "L2_052", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.4058, "correct": true, "status": "ok", "speedup": 1.4058, "ref_ms": 11.16065, "cand_ms": 7.9391, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 175.3, "calls": 2, "tokens_in": 7120, "tokens_out": 8735, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c49b235eaea94f98", "ts": 1791533657.9383385} {"pid": "L3_033", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": false, "score": 0.7864, "correct": true, "status": "ok", "speedup": 0.7864, "ref_ms": 20.64222, "cand_ms": 26.2481, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 178.2, "calls": 2, "tokens_in": 6401, "tokens_out": 6659, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "07b9977f18dde5d9", "ts": 1791533681.9968076} {"pid": "L2_052", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.4114, "correct": true, "status": "ok", "speedup": 1.4114, "ref_ms": 11.05793, "cand_ms": 7.83463, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 178.7, "calls": 2, "tokens_in": 7284, "tokens_out": 9012, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "835c25e6d66ffe0c", "ts": 1791533682.408043} {"pid": "L3_008", "split": "dev", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.1092, "correct": true, "status": "ok", "speedup": 1.1092, "ref_ms": 5.33505, "cand_ms": 4.80967, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 441.0, "calls": 2, "tokens_in": 274531, "tokens_out": 29315, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "19bd9c32259e93c3", "ts": 1791533694.5095828} {"pid": "L1_078", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.2986, "correct": true, "status": "ok", "speedup": 2.2986, "ref_ms": 35.52348, "cand_ms": 15.45445, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 213.7, "calls": 2, "tokens_in": 266180, "tokens_out": 3369, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "68c6156730e38527", "ts": 1791533702.9556587} {"pid": "L2_052", "split": "learn", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.1415, "correct": true, "status": "ok", "speedup": 2.1415, "ref_ms": 11.09376, "cand_ms": 5.18042, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 210.1, "calls": 2, "tokens_in": 28297, "tokens_out": 10641, "ctx_chars": 22084, "ctx_sha": "9cc43a100b1de8c3", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "12bf030d056dda3d", "ts": 1791533716.5602572} {"pid": "L2_052", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.2579, "correct": true, "status": "ok", "speedup": 2.2579, "ref_ms": 11.04802, "cand_ms": 4.89311, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 365.0, "calls": 2, "tokens_in": 28532, "tokens_out": 10725, "ctx_chars": 22084, "ctx_sha": "9cc43a100b1de8c3", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "b22823cbfda0c714", "ts": 1791533726.737221} {"pid": "L2_037", "split": "dev", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.2795, "correct": true, "status": "ok", "speedup": 1.2795, "ref_ms": 19.74088, "cand_ms": 15.42868, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 170.5, "calls": 2, "tokens_in": 4847, "tokens_out": 3073, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ddf257fcd8045337", "ts": 1791533727.4619837} {"pid": "L2_039", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0082, "correct": true, "status": "ok", "speedup": 1.0082, "ref_ms": 30.02644, "cand_ms": 29.78347, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 98.1, "calls": 2, "tokens_in": 12047, "tokens_out": 5415, "ctx_chars": 7281, "ctx_sha": "29172d84bddf7c5a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "7ce11c88fd5304a3", "ts": 1791533747.0038478} {"pid": "L2_053", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": false, "score": 0.8744, "correct": true, "status": "ok", "speedup": 0.8744, "ref_ms": 16.05172, "cand_ms": 18.35812, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 164.8, "calls": 2, "tokens_in": 5782, "tokens_out": 5294, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "2a410fd26eacd0fe", "ts": 1791533750.7470624} {"pid": "L1_066", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.516, "correct": true, "status": "ok", "speedup": 1.516, "ref_ms": 7.77986, "cand_ms": 5.13168, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 204.9, "calls": 3, "tokens_in": 15971, "tokens_out": 11834, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2f5e461549db3959", "ts": 1791533767.197263} {"pid": "L2_029", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.5911, "correct": true, "status": "ok", "speedup": 4.5911, "ref_ms": 7.9851, "cand_ms": 1.73927, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 70.1, "calls": 2, "tokens_in": 273264, "tokens_out": 4531, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "81ecec0dd961c156", "ts": 1791533773.0218837} {"pid": "L2_062", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 119.6, "calls": 3, "tokens_in": 414252, "tokens_out": 8675, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "7bc6b77850a85951", "ts": 1791533814.0805635} {"pid": "L3_048", "split": "dev", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0463, "correct": true, "status": "ok", "speedup": 1.0463, "ref_ms": 15.98615, "cand_ms": 15.27853, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 395.2, "calls": 5, "tokens_in": 32994, "tokens_out": 25304, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f7cee106884dad95", "ts": 1791533823.4358132} {"pid": "L2_081", "split": "dev", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0332, "correct": true, "status": "ok", "speedup": 1.0332, "ref_ms": 8.2479, "cand_ms": 7.98301, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 51.2, "calls": 2, "tokens_in": 4529, "tokens_out": 2260, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2ce4d36b84047595", "ts": 1791533824.1735024} {"pid": "L1_066", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.5708, "correct": true, "status": "ok", "speedup": 1.5708, "ref_ms": 7.78992, "cand_ms": 4.95936, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 412.5, "calls": 3, "tokens_in": 409631, "tokens_out": 21474, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "5ac381d57a4d10db", "ts": 1791533861.0669975} {"pid": "L3_008", "split": "dev", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.5614, "correct": true, "status": "ok", "speedup": 1.5614, "ref_ms": 5.25012, "cand_ms": 3.36238, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 256.3, "calls": 2, "tokens_in": 11377, "tokens_out": 23256, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "fc6e9d64b0daa17a", "ts": 1791533876.047116} {"pid": "L2_020", "split": "dev", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.434, "correct": true, "status": "ok", "speedup": 1.434, "ref_ms": 14.12049, "cand_ms": 9.8472, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 140.4, "calls": 2, "tokens_in": 5157, "tokens_out": 3313, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "da34a185874a19fe", "ts": 1791533887.3750618} {"pid": "L3_050", "split": "dev", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 2.7859, "correct": true, "status": "ok", "speedup": 2.7859, "ref_ms": 12.77722, "cand_ms": 4.58636, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 177.8, "calls": 3, "tokens_in": 30165, "tokens_out": 13320, "ctx_chars": 10330, "ctx_sha": "4725ef765672a6e6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "c40f06ce3d5f68f4", "ts": 1791533894.3590055} {"pid": "L3_008", "split": "dev", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.5111, "correct": true, "status": "ok", "speedup": 1.5111, "ref_ms": 5.24365, "cand_ms": 3.47004, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 275.4, "calls": 2, "tokens_in": 272547, "tokens_out": 20815, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e2479c685639170c", "ts": 1791533906.1495392} {"pid": "L3_020", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.0092, "correct": true, "status": "ok", "speedup": 2.0092, "ref_ms": 6.74634, "cand_ms": 3.35771, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 243.6, "calls": 2, "tokens_in": 272724, "tokens_out": 17281, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "a5b5e37ed57b82af", "ts": 1791533926.005769} {"pid": "L3_050", "split": "dev", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.1029, "correct": true, "status": "ok", "speedup": 2.1029, "ref_ms": 12.67123, "cand_ms": 6.02571, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 108.6, "calls": 2, "tokens_in": 9643, "tokens_out": 5569, "ctx_chars": 3184, "ctx_sha": "e64357aa997958f6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "7c67d36b59b912e6", "ts": 1791533931.9884062} {"pid": "L2_088", "split": "dev", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0618, "correct": true, "status": "ok", "speedup": 1.0618, "ref_ms": 8.59504, "cand_ms": 8.0951, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 99.9, "calls": 2, "tokens_in": 4993, "tokens_out": 2725, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "9dd2fabf1ba36132", "ts": 1791535412.180929} {"pid": "L2_040", "split": "dev", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0391, "correct": true, "status": "ok", "speedup": 1.0391, "ref_ms": 30.53867, "cand_ms": 29.38943, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 121.3, "calls": 2, "tokens_in": 9085, "tokens_out": 2194, "ctx_chars": 5438, "ctx_sha": "5bb43e4b3db56789", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "95042a40e1236705", "ts": 1791535433.5854952} {"pid": "L1_078", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 1, "success": true, "score": 2.252, "correct": true, "status": "ok", "speedup": 2.252, "ref_ms": 35.57866, "cand_ms": 15.79842, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 129.7, "calls": 2, "tokens_in": 12244, "tokens_out": 2735, "ctx_chars": 7879, "ctx_sha": "f7c7999053853d91", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "dfc38f43c0cf6540", "ts": 1791535441.9487448} {"pid": "L2_088", "split": "dev", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0525, "correct": true, "status": "ok", "speedup": 1.0525, "ref_ms": 8.55435, "cand_ms": 8.12779, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 143.3, "calls": 2, "tokens_in": 10233, "tokens_out": 2163, "ctx_chars": 6231, "ctx_sha": "4e345ad7f535c321", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8b0cfc9a9738410c", "ts": 1791535455.5665705} {"pid": "L2_039", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0043, "correct": true, "status": "ok", "speedup": 1.0043, "ref_ms": 30.18337, "cand_ms": 30.05282, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 153.1, "calls": 2, "tokens_in": 6077, "tokens_out": 6830, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e6a9c66ad2e101b7", "ts": 1791535465.3938003} {"pid": "L2_037", "split": "dev", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.7219, "correct": true, "status": "ok", "speedup": 4.7219, "ref_ms": 19.80811, "cand_ms": 4.19494, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 150.4, "calls": 2, "tokens_in": 24415, "tokens_out": 4293, "ctx_chars": 19121, "ctx_sha": "d421a9dea165588e", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "8bcef0c022a15d34", "ts": 1791535583.951061} {"pid": "L2_073", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 1, "success": true, "score": 3.0203, "correct": true, "status": "ok", "speedup": 3.0203, "ref_ms": 5.64848, "cand_ms": 1.87019, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 287.6, "calls": 2, "tokens_in": 29384, "tokens_out": 12099, "ctx_chars": 22975, "ctx_sha": "4e003dc4030b57a1", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f4b29a4d3a7ed2cb", "ts": 1791535599.8587668} {"pid": "L2_058", "split": "dev", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 9.5369, "correct": true, "status": "ok", "speedup": 9.5369, "ref_ms": 25.25886, "cand_ms": 2.64854, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 315.3, "calls": 2, "tokens_in": 267690, "tokens_out": 8598, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "45dc8fe558c6fc5b", "ts": 1791535627.5900176} {"pid": "L2_039", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "outputs produced during timing do not match the reference (output mismatch beyond atol=rtol=0.0001); results must not be cached or skipped", "wall_s": 232.5, "calls": 2, "tokens_in": 275702, "tokens_out": 11838, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "2d409b132b15d827", "ts": 1791535644.6732357} {"pid": "L1_078", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.2854, "correct": true, "status": "ok", "speedup": 2.2854, "ref_ms": 35.62089, "cand_ms": 15.58659, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 343.5, "calls": 2, "tokens_in": 266383, "tokens_out": 3482, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "776d478b0831f0c7", "ts": 1791535655.8116438} {"pid": "L3_033", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.323, "correct": true, "status": "ok", "speedup": 1.323, "ref_ms": 20.63252, "cand_ms": 15.59546, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 235.4, "calls": 2, "tokens_in": 267022, "tokens_out": 7109, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "ddd38a5d56133e70", "ts": 1791535677.3555455} {"pid": "L3_044", "split": "dev", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 4.5201, "correct": true, "status": "ok", "speedup": 4.5201, "ref_ms": 75.55502, "cand_ms": 16.71535, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 220.9, "calls": 2, "tokens_in": 26632, "tokens_out": 14312, "ctx_chars": 15252, "ctx_sha": "575b4fa0082f404b", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "a4fa432703dd6a4b", "ts": 1791535686.2635398} {"pid": "L3_047", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.9318, "correct": true, "status": "ok", "speedup": 1.9318, "ref_ms": 3.65317, "cand_ms": 1.89111, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 396.0, "calls": 2, "tokens_in": 270094, "tokens_out": 14491, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "bc401eea368f3bb9", "ts": 1791535708.2270591} {"pid": "L2_073", "split": "learn", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 2.7066, "correct": true, "status": "ok", "speedup": 2.7066, "ref_ms": 5.64379, "cand_ms": 2.08522, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 418.9, "calls": 2, "tokens_in": 9193, "tokens_out": 24195, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d85a842c2c40a72b", "ts": 1791535731.1165972} {"pid": "L3_008", "split": "dev", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.5179, "correct": true, "status": "ok", "speedup": 1.5179, "ref_ms": 5.32049, "cand_ms": 3.50513, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 439.5, "calls": 2, "tokens_in": 20267, "tokens_out": 21814, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c7fc3831d40e61bc", "ts": 1791535751.7325773} {"pid": "L2_039", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 1, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "outputs produced during timing do not match the reference (output mismatch beyond atol=rtol=0.0001); results must not be cached or skipped", "wall_s": 298.9, "calls": 2, "tokens_in": 26190, "tokens_out": 13732, "ctx_chars": 19597, "ctx_sha": "e31c3ee202e0b25a", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "7dcd98208cf622e9", "ts": 1791535754.4580297} {"pid": "L3_047", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.3966, "correct": true, "status": "ok", "speedup": 2.3966, "ref_ms": 3.70322, "cand_ms": 1.54522, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 444.9, "calls": 3, "tokens_in": 20996, "tokens_out": 18054, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "fc817b0356f4da28", "ts": 1791535757.2133348} {"pid": "L2_067", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 2.8262, "correct": true, "status": "ok", "speedup": 2.8262, "ref_ms": 12.85269, "cand_ms": 4.54771, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 111.5, "calls": 2, "tokens_in": 18605, "tokens_out": 7162, "ctx_chars": 14070, "ctx_sha": "3d6ada40588e7cb1", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "65952635fc71cb44", "ts": 1791535797.737535} {"pid": "L2_063", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 1, "success": true, "score": 1.0956, "correct": true, "status": "ok", "speedup": 1.0956, "ref_ms": 7.9962, "cand_ms": 7.2987, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 205.2, "calls": 2, "tokens_in": 265623, "tokens_out": 4298, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "5bc9058ed26e9251", "ts": 1791535805.104582} {"pid": "L3_047", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 2.637, "correct": true, "status": "ok", "speedup": 2.637, "ref_ms": 3.69832, "cand_ms": 1.40245, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 227.5, "calls": 2, "tokens_in": 8332, "tokens_out": 8986, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0df401c2267a8b68", "ts": 1791535872.140303} {"pid": "L2_020", "split": "dev", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.4241, "correct": true, "status": "ok", "speedup": 1.4241, "ref_ms": 14.021, "cand_ms": 9.84548, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 197.7, "calls": 2, "tokens_in": 11058, "tokens_out": 2086, "ctx_chars": 7394, "ctx_sha": "632a38c7eee085c0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0066f4002d8e3de9", "ts": 1791535905.9003313} {"pid": "L3_044", "split": "dev", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.2557, "correct": true, "status": "ok", "speedup": 1.2557, "ref_ms": 75.63961, "cand_ms": 60.23563, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 368.6, "calls": 2, "tokens_in": 270744, "tokens_out": 14696, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "aeca9400318165a2", "ts": 1791535996.1652143} {"pid": "L2_020", "split": "dev", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 6.6027, "correct": true, "status": "ok", "speedup": 6.6027, "ref_ms": 13.98287, "cand_ms": 2.11776, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 345.2, "calls": 2, "tokens_in": 26626, "tokens_out": 10567, "ctx_chars": 20061, "ctx_sha": "a0a8edb8b6ae64a6", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "1a5fdbf97322b9e4", "ts": 1791536000.9961038} {"pid": "L1_066", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 1, "success": true, "score": 1.7548, "correct": true, "status": "ok", "speedup": 1.7548, "ref_ms": 7.8961, "cand_ms": 4.49971, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 431.4, "calls": 3, "tokens_in": 27734, "tokens_out": 15488, "ctx_chars": 8854, "ctx_sha": "420ebf050379abd1", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c264987b59df1703", "ts": 1791536015.4001803} {"pid": "L2_073", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.7278, "correct": true, "status": "ok", "speedup": 1.7278, "ref_ms": 5.62661, "cand_ms": 3.25644, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 405.0, "calls": 2, "tokens_in": 267139, "tokens_out": 7589, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "8b8ec223dbaabf04", "ts": 1791536082.3982608} {"pid": "L2_073", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.61, "correct": true, "status": "ok", "speedup": 1.61, "ref_ms": 5.63939, "cand_ms": 3.50271, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 303.9, "calls": 3, "tokens_in": 18890, "tokens_out": 5666, "ctx_chars": 6744, "ctx_sha": "b92173e1465ccf4d", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "9023bacb00214ab8", "ts": 1791536101.6533492} {"pid": "L2_052", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.3567, "correct": true, "status": "ok", "speedup": 1.3567, "ref_ms": 11.0487, "cand_ms": 8.14362, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 362.1, "calls": 2, "tokens_in": 5906, "tokens_out": 6203, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e1599fafa7dd3edd", "ts": 1791536113.8451736} {"pid": "L2_053", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.0135, "correct": true, "status": "ok", "speedup": 1.0135, "ref_ms": 16.02927, "cand_ms": 15.81574, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 254.3, "calls": 2, "tokens_in": 4325, "tokens_out": 2037, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4a027533c4aaf555", "ts": 1791536126.4365706} {"pid": "L2_067", "split": "learn", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": false, "score": 0.0747, "correct": true, "status": "ok", "speedup": 0.0747, "ref_ms": 13.10652, "cand_ms": 175.54574, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 152.9, "calls": 2, "tokens_in": 12038, "tokens_out": 5875, "ctx_chars": 7583, "ctx_sha": "5300ffdccc59e7fb", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "808ed97d5f87fb60", "ts": 1791536153.8755753} {"pid": "L2_073", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 1, "success": true, "score": 1.7221, "correct": true, "status": "ok", "speedup": 1.7221, "ref_ms": 5.64248, "cand_ms": 3.27652, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 399.8, "calls": 2, "tokens_in": 267630, "tokens_out": 8156, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "20ad21c7c78cefbe", "ts": 1791536156.9940686} {"pid": "L3_050", "split": "dev", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.8155, "correct": true, "status": "ok", "speedup": 2.8155, "ref_ms": 12.69659, "cand_ms": 4.50961, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 429.2, "calls": 3, "tokens_in": 417795, "tokens_out": 14253, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "57e3c53255a5c3a0", "ts": 1791536160.2903326} {"pid": "L3_050", "split": "dev", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.4392, "correct": true, "status": "ok", "speedup": 3.4392, "ref_ms": 12.74017, "cand_ms": 3.70444, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 257.9, "calls": 3, "tokens_in": 38100, "tokens_out": 12140, "ctx_chars": 15252, "ctx_sha": "575b4fa0082f404b", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "e448d96fbb453755", "ts": 1791536163.8110347} {"pid": "L2_058", "split": "dev", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 24.6471, "ref_ms": 25.14383, "cand_ms": 1.02016, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 424.0, "calls": 3, "tokens_in": 45114, "tokens_out": 13963, "ctx_chars": 20061, "ctx_sha": "a0a8edb8b6ae64a6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c01908bc6eb21b16", "ts": 1791536229.076306} {"pid": "L1_066", "split": "learn", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.1383, "correct": true, "status": "ok", "speedup": 3.1383, "ref_ms": 7.77999, "cand_ms": 2.47902, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 262.9, "calls": 2, "tokens_in": 21352, "tokens_out": 5937, "ctx_chars": 15787, "ctx_sha": "304d3d83d624cb50", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2b920ade2cb79f3c", "ts": 1791536259.0546355} {"pid": "L2_088", "split": "dev", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.8893, "correct": true, "status": "ok", "speedup": 4.8893, "ref_ms": 8.539, "cand_ms": 1.74648, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 164.1, "calls": 2, "tokens_in": 274229, "tokens_out": 5560, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "b9837ff88fe65543", "ts": 1791536277.9831707} {"pid": "L2_062", "split": "learn", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0826, "correct": true, "status": "ok", "speedup": 1.0826, "ref_ms": 8.6371, "cand_ms": 7.97809, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 118.3, "calls": 2, "tokens_in": 9248, "tokens_out": 1941, "ctx_chars": 5389, "ctx_sha": "be81589e9761e178", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "92fb728d9a6d0e61", "ts": 1791536282.068009} {"pid": "L2_067", "split": "learn", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.1526, "correct": true, "status": "ok", "speedup": 1.1526, "ref_ms": 12.94787, "cand_ms": 11.23396, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 151.3, "calls": 2, "tokens_in": 11074, "tokens_out": 2414, "ctx_chars": 7583, "ctx_sha": "5300ffdccc59e7fb", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f53a56657e5447f0", "ts": 1791536305.2008963} {"pid": "L2_073", "split": "learn", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 2.1984, "correct": true, "status": "ok", "speedup": 2.1984, "ref_ms": 5.62046, "cand_ms": 2.55665, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 292.3, "calls": 2, "tokens_in": 7140, "tokens_out": 13343, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "55aee0b44fab2310", "ts": 1791536307.6874886} {"pid": "L2_081", "split": "dev", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.198, "correct": true, "status": "ok", "speedup": 1.198, "ref_ms": 8.22562, "cand_ms": 6.86637, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 209.6, "calls": 2, "tokens_in": 266391, "tokens_out": 4946, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "76f302a20501ca95", "ts": 1791536311.2098255} {"pid": "L3_044", "split": "dev", "rep": 2, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 4.911, "correct": true, "status": "ok", "speedup": 4.911, "ref_ms": 75.52786, "cand_ms": 15.37927, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 259.7, "calls": 2, "tokens_in": 22602, "tokens_out": 18161, "ctx_chars": 10330, "ctx_sha": "4725ef765672a6e6", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "37a7854113c63daf", "ts": 1791536386.0978339} {"pid": "L2_037", "split": "dev", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 4.7252, "correct": true, "status": "ok", "speedup": 4.7252, "ref_ms": 19.82283, "cand_ms": 4.19515, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 267.3, "calls": 2, "tokens_in": 16929, "tokens_out": 4563, "ctx_chars": 12049, "ctx_sha": "cd92549f2b7fd121", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "f32b89b5b1184d02", "ts": 1791536427.5880125} {"pid": "L2_052", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 1, "success": true, "score": 1.3507, "correct": true, "status": "ok", "speedup": 1.3507, "ref_ms": 10.996, "cand_ms": 8.14099, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 373.6, "calls": 2, "tokens_in": 268468, "tokens_out": 10056, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "33f19c2a4fd91fb9", "ts": 1791536456.047011} {"pid": "L3_048", "split": "dev", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 8.5369, "correct": true, "status": "ok", "speedup": 8.5369, "ref_ms": 16.21543, "cand_ms": 1.89946, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 722.4, "calls": 3, "tokens_in": 415155, "tokens_out": 33732, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f2663a21bf1d2688", "ts": 1791536476.852766} {"pid": "L1_066", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 2.2989, "correct": true, "status": "ok", "speedup": 2.2989, "ref_ms": 7.78537, "cand_ms": 3.38658, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 258.0, "calls": 2, "tokens_in": 267885, "tokens_out": 8391, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "1d108b3f69ef293c", "ts": 1791536517.031775} {"pid": "L3_020", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 1, "success": true, "score": 1.5665, "correct": true, "status": "ok", "speedup": 1.5665, "ref_ms": 8.30859, "cand_ms": 5.3038, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 294.8, "calls": 2, "tokens_in": 12805, "tokens_out": 21670, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "d09ec676c08fdc4e", "ts": 1791536572.8179164} {"pid": "L2_058", "split": "dev", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 13.0286, "ref_ms": 25.16099, "cand_ms": 1.93121, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 98.1, "calls": 2, "tokens_in": 25068, "tokens_out": 5752, "ctx_chars": 20061, "ctx_sha": "a0a8edb8b6ae64a6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "498c57beebb4ba39", "ts": 1791536574.9742098} {"pid": "L3_008", "split": "dev", "rep": 1, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.397, "correct": true, "status": "ok", "speedup": 1.397, "ref_ms": 5.27854, "cand_ms": 3.77838, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 358.1, "calls": 2, "tokens_in": 12202, "tokens_out": 22219, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "36adc02d708a6908", "ts": 1791536587.1762779} {"pid": "L3_008", "split": "dev", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 1.687, "correct": true, "status": "ok", "speedup": 1.687, "ref_ms": 5.29295, "cand_ms": 3.13757, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 336.2, "calls": 2, "tokens_in": 25395, "tokens_out": 15776, "ctx_chars": 16688, "ctx_sha": "1d0209b1f4f44f83", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3efc7336872fb145", "ts": 1791536641.4096024} {"pid": "L3_008", "split": "dev", "rep": 2, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 1.0237, "correct": true, "status": "ok", "speedup": 1.0237, "ref_ms": 5.30491, "cand_ms": 5.18203, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 207.4, "calls": 2, "tokens_in": 8875, "tokens_out": 14165, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "a6143014e0445f52", "ts": 1791536663.409556} {"pid": "L1_078", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 1, "success": true, "score": 2.3023, "correct": true, "status": "ok", "speedup": 2.3023, "ref_ms": 36.13506, "cand_ms": 15.69525, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 273.1, "calls": 2, "tokens_in": 266509, "tokens_out": 3781, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "651493d37c725e3c", "ts": 1791536700.6913297} {"pid": "L2_052", "split": "learn", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 1, "success": true, "score": 1.4276, "correct": true, "status": "ok", "speedup": 1.4276, "ref_ms": 11.16703, "cand_ms": 7.8222, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 438.8, "calls": 2, "tokens_in": 267887, "tokens_out": 9480, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "0f2ff21a56675b41", "ts": 1791536720.8983188} {"pid": "L2_063", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.5511, "correct": true, "status": "ok", "speedup": 3.5511, "ref_ms": 8.10057, "cand_ms": 2.28111, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 161.5, "calls": 2, "tokens_in": 15618, "tokens_out": 4223, "ctx_chars": 11583, "ctx_sha": "bb093721f8760f3d", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "c487f287863bcc65", "ts": 1791536736.4981003} {"pid": "L1_066", "split": "learn", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.5495, "correct": true, "status": "ok", "speedup": 1.5495, "ref_ms": 7.80045, "cand_ms": 5.0341, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 454.1, "calls": 3, "tokens_in": 29775, "tokens_out": 15398, "ctx_chars": 8854, "ctx_sha": "420ebf050379abd1", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "20bf4df7418160c1", "ts": 1791536761.7865067} {"pid": "L3_020", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 1, "success": true, "score": 1.9561, "correct": true, "status": "ok", "speedup": 1.9561, "ref_ms": 7.77198, "cand_ms": 3.97319, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 381.1, "calls": 2, "tokens_in": 273248, "tokens_out": 23109, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ca7d99e2ede587fc", "ts": 1791536767.1497161} {"pid": "L2_062", "split": "learn", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 3.1498, "correct": true, "status": "ok", "speedup": 3.1498, "ref_ms": 8.64571, "cand_ms": 2.74485, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 202.4, "calls": 3, "tokens_in": 39906, "tokens_out": 10428, "ctx_chars": 19121, "ctx_sha": "d421a9dea165588e", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "62f8d92483f73640", "ts": 1791536775.2069607} {"pid": "L2_039", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 1, "success": true, "score": 1.2299, "correct": true, "status": "ok", "speedup": 1.2299, "ref_ms": 30.2105, "cand_ms": 24.5625, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 267.5, "calls": 2, "tokens_in": 268024, "tokens_out": 11497, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "5d040eb793abed06", "ts": 1791536784.5730577} {"pid": "L3_048", "split": "dev", "rep": 0, "arm": "livKF", "attempt": 0, "restart": 0, "success": false, "score": 0.0, "correct": false, "status": "incorrect", "speedup": 0.0, "ref_ms": null, "cand_ms": null, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 657.6, "calls": 5, "tokens_in": 57596, "tokens_out": 17873, "ctx_chars": 10330, "ctx_sha": "4725ef765672a6e6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "6b968cae2bc41ada", "ts": 1791536814.5686483} {"pid": "L1_078", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 3.0342, "correct": true, "status": "ok", "speedup": 3.0342, "ref_ms": 35.84719, "cand_ms": 11.81453, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 290.8, "calls": 2, "tokens_in": 7842, "tokens_out": 11240, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f0241b45f2d109e9", "ts": 1791536877.9636219} {"pid": "L3_047", "split": "learn", "rep": 0, "arm": "ace", "attempt": 0, "restart": 2, "success": false, "score": 0.2493, "correct": true, "status": "ok", "speedup": 0.2493, "ref_ms": 3.64415, "cand_ms": 14.61887, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 278.0, "calls": 2, "tokens_in": 270708, "tokens_out": 17250, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "8c33c62702f7cf05", "ts": 1791536919.4271452} {"pid": "L1_078", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 2.2852, "correct": true, "status": "ok", "speedup": 2.2852, "ref_ms": 35.9582, "cand_ms": 15.73509, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 205.0, "calls": 2, "tokens_in": 12121, "tokens_out": 2696, "ctx_chars": 7879, "ctx_sha": "f7c7999053853d91", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f181c33fa05d5a8c", "ts": 1791536972.1705835} {"pid": "L2_029", "split": "learn", "rep": 1, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0087, "correct": true, "status": "ok", "speedup": 1.0087, "ref_ms": 8.00604, "cand_ms": 7.93707, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 61.0, "calls": 2, "tokens_in": 8549, "tokens_out": 1905, "ctx_chars": 5477, "ctx_sha": "8765bd9517445b21", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "49e9ff7a9a994b5b", "ts": 1791536980.425902} {"pid": "L3_044", "split": "dev", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 3.7388, "correct": true, "status": "ok", "speedup": 3.7388, "ref_ms": 75.54968, "cand_ms": 20.20686, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 296.2, "calls": 2, "tokens_in": 281145, "tokens_out": 21110, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "f4a14a176a363607", "ts": 1791536996.8674238} {"pid": "L2_073", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 1, "success": true, "score": 1.7151, "correct": true, "status": "ok", "speedup": 1.7151, "ref_ms": 5.63152, "cand_ms": 3.28355, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 373.7, "calls": 2, "tokens_in": 268028, "tokens_out": 9314, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "309f244307a9a77a", "ts": 1791537037.1544838} {"pid": "L3_033", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 1, "success": true, "score": 1.5146, "correct": true, "status": "ok", "speedup": 1.5146, "ref_ms": 20.50143, "cand_ms": 13.53579, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 241.3, "calls": 2, "tokens_in": 6440, "tokens_out": 7007, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "71f339fe4e466c91", "ts": 1791537055.880757} {"pid": "L2_092", "split": "learn", "rep": 0, "arm": "prior", "attempt": 0, "restart": 0, "success": true, "score": 2.7919, "correct": true, "status": "ok", "speedup": 2.7919, "ref_ms": 8.53776, "cand_ms": 3.05801, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 277.6, "calls": 2, "tokens_in": 5963, "tokens_out": 6691, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "6b5e7380e5c78e10", "ts": 1791537062.2217712} {"pid": "L3_050", "split": "dev", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 3.1921, "correct": true, "status": "ok", "speedup": 3.1921, "ref_ms": 12.65397, "cand_ms": 3.96416, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 325.8, "calls": 3, "tokens_in": 417806, "tokens_out": 15605, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "322e65534dd9b617", "ts": 1791537062.2823534} {"pid": "L2_039", "split": "learn", "rep": 2, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 3.3147, "correct": true, "status": "ok", "speedup": 3.3147, "ref_ms": 30.20187, "cand_ms": 9.11157, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 331.1, "calls": 3, "tokens_in": 419053, "tokens_out": 16155, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "b1a2068c4a77ad83", "ts": 1791537092.8616722} {"pid": "L3_050", "split": "dev", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 1, "success": true, "score": 3.1652, "correct": true, "status": "ok", "speedup": 3.1652, "ref_ms": 12.91974, "cand_ms": 4.08175, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 274.6, "calls": 3, "tokens_in": 37362, "tokens_out": 11321, "ctx_chars": 15252, "ctx_sha": "575b4fa0082f404b", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ca0bc03dc0a72e84", "ts": 1791537152.5487492} {"pid": "L3_044", "split": "dev", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.7614, "correct": true, "status": "ok", "speedup": 4.7614, "ref_ms": 75.6062, "cand_ms": 15.87905, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 387.9, "calls": 2, "tokens_in": 280858, "tokens_out": 19532, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "c0c779f5ea5e2307", "ts": 1791537163.108915} {"pid": "L3_048", "split": "dev", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 1, "success": true, "score": 5.0246, "correct": true, "status": "ok", "speedup": 5.0246, "ref_ms": 15.91517, "cand_ms": 3.16743, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 877.5, "calls": 5, "tokens_in": 59990, "tokens_out": 37143, "ctx_chars": 10330, "ctx_sha": "4725ef765672a6e6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "914fdd56e037c830", "ts": 1791537188.7216065} {"pid": "L2_040", "split": "dev", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0402, "correct": true, "status": "ok", "speedup": 1.0402, "ref_ms": 30.49996, "cand_ms": 29.3223, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 204.0, "calls": 2, "tokens_in": 8847, "tokens_out": 2031, "ctx_chars": 5438, "ctx_sha": "5bb43e4b3db56789", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3284a2a056626e8a", "ts": 1791537259.8841324} {"pid": "L1_078", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.3037, "correct": true, "status": "ok", "speedup": 2.3037, "ref_ms": 35.75874, "cand_ms": 15.52239, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 302.6, "calls": 2, "tokens_in": 266359, "tokens_out": 3492, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3b8644518a9563f3", "ts": 1791537274.7894886} {"pid": "L2_088", "split": "dev", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 3.7643, "correct": true, "status": "ok", "speedup": 3.7643, "ref_ms": 8.53661, "cand_ms": 2.26779, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 127.5, "calls": 2, "tokens_in": 19403, "tokens_out": 5440, "ctx_chars": 14050, "ctx_sha": "200638981b1d7614", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "b575b2666d372a00", "ts": 1791537316.1885316} {"pid": "L3_048", "split": "dev", "rep": 1, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 1.0572, "correct": true, "status": "ok", "speedup": 1.0572, "ref_ms": 15.88607, "cand_ms": 15.02698, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 640.2, "calls": 5, "tokens_in": 59511, "tokens_out": 21891, "ctx_chars": 10330, "ctx_sha": "4725ef765672a6e6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "e083831842abb194", "ts": 1791537361.0999465} {"pid": "L1_078", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 1, "success": true, "score": 8.0067, "correct": true, "status": "ok", "speedup": 8.0067, "ref_ms": 36.29955, "cand_ms": 4.53363, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 321.0, "calls": 2, "tokens_in": 25497, "tokens_out": 7065, "ctx_chars": 19130, "ctx_sha": "0551daeb8a590834", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2909bcda7b401760", "ts": 1791537383.3062184} {"pid": "L2_039", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 1, "success": true, "score": 1.1321, "correct": true, "status": "ok", "speedup": 1.1321, "ref_ms": 30.18151, "cand_ms": 26.65915, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 362.3, "calls": 2, "tokens_in": 268429, "tokens_out": 12212, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "d01b62eb2a643a86", "ts": 1791537424.4754627} {"pid": "L2_073", "split": "learn", "rep": 1, "arm": "prior", "attempt": 0, "restart": 1, "success": true, "score": 2.3638, "correct": true, "status": "ok", "speedup": 2.3638, "ref_ms": 5.64824, "cand_ms": 2.3895, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 398.5, "calls": 2, "tokens_in": 9107, "tokens_out": 19323, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "c9c3fb74ee4737f9", "ts": 1791537435.6457198} {"pid": "L2_040", "split": "dev", "rep": 2, "arm": "livKF", "attempt": 0, "restart": 0, "success": true, "score": 4.3576, "correct": true, "status": "ok", "speedup": 4.3576, "ref_ms": 30.53583, "cand_ms": 7.00751, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 284.4, "calls": 2, "tokens_in": 23971, "tokens_out": 3618, "ctx_chars": 19121, "ctx_sha": "d421a9dea165588e", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "bf4cf734cb7223bd", "ts": 1791537436.989674} {"pid": "L2_058", "split": "dev", "rep": 0, "arm": "livP1", "attempt": 0, "restart": 0, "success": true, "score": 10.0, "correct": true, "status": "ok", "speedup": 22.1039, "ref_ms": 25.23403, "cand_ms": 1.14161, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 305.9, "calls": 2, "tokens_in": 14089, "tokens_out": 10158, "ctx_chars": 8031, "ctx_sha": "8e7ee93b3140d14f", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "a250bdf6ab832321", "ts": 1791537468.9677062} {"pid": "L2_029", "split": "learn", "rep": 2, "arm": "bare", "attempt": 0, "restart": 0, "success": false, "score": 1.0008, "correct": true, "status": "ok", "speedup": 1.0008, "ref_ms": 8.09829, "cand_ms": 8.09184, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 199.8, "calls": 2, "tokens_in": 4108, "tokens_out": 2269, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "44835516446806bd", "ts": 1791537474.6304193} {"pid": "L2_029", "split": "learn", "rep": 2, "arm": "ace", "attempt": 0, "restart": 0, "success": false, "score": 0.9744, "correct": true, "status": "ok", "speedup": 0.9744, "ref_ms": 8.07576, "cand_ms": 8.2879, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 133.5, "calls": 2, "tokens_in": 265826, "tokens_out": 4730, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "c3b13571f8cb5a23", "ts": 1791537494.5704675} {"pid": "L3_048", "split": "dev", "rep": 1, "arm": "livKF", "attempt": 0, "restart": 0, "success": false, "score": 0.9538, "correct": true, "status": "ok", "speedup": 0.9538, "ref_ms": 15.89614, "cand_ms": 16.66665, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 516.4, "calls": 5, "tokens_in": 57122, "tokens_out": 20647, "ctx_chars": 10330, "ctx_sha": "4725ef765672a6e6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "f482f02f081d1769", "ts": 1791537496.790703} {"pid": "L2_029", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.5856, "correct": true, "status": "ok", "speedup": 4.5856, "ref_ms": 8.00451, "cand_ms": 1.74559, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 90.7, "calls": 2, "tokens_in": 273202, "tokens_out": 4192, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "2dcce2d8bb855114", "ts": 1791537526.3682897} {"pid": "L2_039", "split": "learn", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.0028, "correct": true, "status": "ok", "speedup": 1.0028, "ref_ms": 30.13638, "cand_ms": 30.05096, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 168.7, "calls": 2, "tokens_in": 12032, "tokens_out": 5615, "ctx_chars": 7281, "ctx_sha": "29172d84bddf7c5a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "4d3b5b70444c9543", "ts": 1791537552.0465593} {"pid": "L2_063", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.5595, "correct": true, "status": "ok", "speedup": 3.5595, "ref_ms": 7.98874, "cand_ms": 2.24437, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 151.9, "calls": 2, "tokens_in": 15704, "tokens_out": 4919, "ctx_chars": 11583, "ctx_sha": "bb093721f8760f3d", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "e441f1f20a66cf11", "ts": 1791537576.4140089} {"pid": "L3_008", "split": "dev", "rep": 2, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.2929, "correct": true, "status": "ok", "speedup": 1.2929, "ref_ms": 5.29629, "cand_ms": 4.09632, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 274.1, "calls": 2, "tokens_in": 18917, "tokens_out": 20072, "ctx_chars": 10959, "ctx_sha": "e7f81f5bab9cda55", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ae7c63b91abd11e3", "ts": 1791537590.2820904} {"pid": "L2_040", "split": "dev", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 4.44, "correct": true, "status": "ok", "speedup": 4.44, "ref_ms": 30.49444, "cand_ms": 6.86814, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 236.0, "calls": 2, "tokens_in": 273574, "tokens_out": 5503, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": true, "uses_tf32x3": false, "src_sha": "6e88a552ff538952", "ts": 1791537672.9786155} {"pid": "L3_048", "split": "dev", "rep": 0, "arm": "stock", "attempt": 0, "restart": 0, "success": true, "score": 1.1806, "correct": true, "status": "ok", "speedup": 1.1806, "ref_ms": 15.91624, "cand_ms": 13.48107, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 598.7, "calls": 5, "tokens_in": 38858, "tokens_out": 22202, "ctx_chars": 3184, "ctx_sha": "e64357aa997958f6", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "2d8d14121b721519", "ts": 1791537691.609612} {"pid": "L2_020", "split": "dev", "rep": 1, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 1.4347, "correct": true, "status": "ok", "speedup": 1.4347, "ref_ms": 14.1308, "cand_ms": 9.8492, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 459.0, "calls": 2, "tokens_in": 266507, "tokens_out": 4764, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "547201fff79b7e41", "ts": 1791537718.888614} {"pid": "L3_002", "split": "learn", "rep": 0, "arm": "aceseed", "attempt": 0, "restart": 0, "success": true, "score": 2.2876, "correct": true, "status": "ok", "speedup": 2.2876, "ref_ms": 33.72788, "cand_ms": 14.74358, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 264.5, "calls": 2, "tokens_in": 273821, "tokens_out": 5121, "ctx_chars": 312455, "ctx_sha": "25bfa9af595ca101", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "3be7c8dae19bd392", "ts": 1791537739.0927477} {"pid": "L2_063", "split": "learn", "rep": 1, "arm": "ace", "attempt": 0, "restart": 0, "success": true, "score": 1.115, "correct": true, "status": "ok", "speedup": 1.115, "ref_ms": 8.05674, "cand_ms": 7.2259, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 265.1, "calls": 2, "tokens_in": 265668, "tokens_out": 4302, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": true, "src_sha": "bef825f177cf39ce", "ts": 1791537759.6439946} {"pid": "L3_048", "split": "dev", "rep": 2, "arm": "ace", "attempt": 0, "restart": 1, "success": true, "score": 1.0587, "correct": true, "status": "ok", "speedup": 1.0587, "ref_ms": 15.90467, "cand_ms": 15.02287, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 797.4, "calls": 3, "tokens_in": 408278, "tokens_out": 51976, "ctx_chars": 305234, "ctx_sha": "4a0a8e7a95364a4a", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "ce85fad98c6897d1", "ts": 1791537794.235476} {"pid": "L2_069", "split": "learn", "rep": 1, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 4.3906, "correct": true, "status": "ok", "speedup": 4.3906, "ref_ms": 4.00523, "cand_ms": 0.91222, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 285.7, "calls": 2, "tokens_in": 20040, "tokens_out": 5180, "ctx_chars": 15668, "ctx_sha": "bb1fdfba7b87d1ff", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "02bf039d2d63b942", "ts": 1791537862.0985956} {"pid": "L1_066", "split": "learn", "rep": 0, "arm": "bare", "attempt": 0, "restart": 0, "success": true, "score": 1.5996, "correct": true, "status": "ok", "speedup": 1.5996, "ref_ms": 7.89637, "cand_ms": 4.93656, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 398.7, "calls": 3, "tokens_in": 16095, "tokens_out": 13896, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "71df035d8d2c641f", "ts": 1791537867.6674094} {"pid": "L2_069", "split": "learn", "rep": 0, "arm": "livEng", "attempt": 0, "restart": 0, "success": true, "score": 3.7978, "correct": true, "status": "ok", "speedup": 3.7978, "ref_ms": 4.02126, "cand_ms": 1.05884, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 329.8, "calls": 2, "tokens_in": 20212, "tokens_out": 5775, "ctx_chars": 15668, "ctx_sha": "bb1fdfba7b87d1ff", "uses_bf16": true, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "6f1f5fa0e8179a8b", "ts": 1791537881.8781266} {"pid": "L3_008", "split": "dev", "rep": 1, "arm": "prior", "attempt": 0, "restart": 1, "success": true, "score": 1.4512, "correct": true, "status": "ok", "speedup": 1.4512, "ref_ms": 5.28304, "cand_ms": 3.64044, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "", "wall_s": 400.4, "calls": 2, "tokens_in": 12241, "tokens_out": 29170, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "241497d1ce9228b7", "ts": 1791537897.2113583} {"pid": "L3_020", "split": "learn", "rep": 2, "arm": "livEng", "attempt": 0, "restart": 0, "success": false, "score": 0.7855, "correct": true, "status": "ok", "speedup": 0.7855, "ref_ms": 6.54102, "cand_ms": 8.32719, "evaluator": "fa88aae56eab8b0e", "infra": false, "error": "ok", "wall_s": 441.4, "calls": 3, "tokens_in": 61566, "tokens_out": 34379, "ctx_chars": 21293, "ctx_sha": "c37e861435b5bbc4", "uses_bf16": false, "uses_out_dtype": false, "uses_tf32x3": false, "src_sha": "bd90e1f57699ed9c", "ts": 1791537967.7673435}