diff --git a/results-loop/PROTOCOL_UNIFIED.md b/results-loop/PROTOCOL_UNIFIED.md index 21cfbf2..2b2ea23 100644 --- a/results-loop/PROTOCOL_UNIFIED.md +++ b/results-loop/PROTOCOL_UNIFIED.md @@ -827,3 +827,24 @@ the 2x2 (verbal/full-state x tape/no-tape). computation-carrying content lives OUTSIDE the verbalizable subspace; if none move, the read-side clamp test (item 29 candidate) decides. Job: scripts/jobs/zzz_sa_rungb_ts.sh. + +--- Outcome, item 28 (scored 2026-07-17 ~06:20). k=0 sanity clean. +Distillation SUCCEEDED geometrically: cos-dist 0.113 -> 0.044 (burst +endpoint lands ~60% closer to the teacher state), with the lowest +output-CE tax of any supervised arm (vals 0.384/0.376). Function did +NOT follow: matched 2:0 = 30.1, ablation (burst off) = 29.7 — burst +contribution nil; hard 34.6 indistinguishable from the pack; and the +state-forcing DAMAGED easy (48.3 vs 62.1 in every other d=1 arm — +the forced endpoint displaces something easy handling needed). +Verdict: null, below reference. The 2x2 (items 25/27/28 + 22 as the +unsupervised corner) is complete and uniform: no state-side +supervision — verbal shadow or full teacher state, tape or burst — +makes the loop compute the deleted step. Combined with items 22-24 +(capacity/time/positions/expressivity all null), the write-side is +exhausted end to end. The one untested link is READ-side: whether the +suffix computation consumes the workspace at all when the right state +is present — the clamp test (write the teacher state into the anchor +at inference via the lens/embedding-basis machinery, no training, and +measure) is item 29's natural content and would assign blame causally. +Nils's morning decision: clamp test vs pivot to the hybrid/A2 line +(where the 57.4 and the drop-bucket reach already live). diff --git a/results-loop/eval_gsm_carrycot_b1_ts50.json b/results-loop/eval_gsm_carrycot_b1_ts50.json new file mode 100644 index 0000000..679f4ee --- /dev/null +++ b/results-loop/eval_gsm_carrycot_b1_ts50.json @@ -0,0 +1,2074 @@ +{ + "tag": "gsm_carrycot_b1_ts50", + "grid": { + "0:0": { + "acc": 0.109375, + "by_label": { + "drop": 0.0, + "easy": 0.9310344827586207, + "hard": 0.007874015748031496 + }, + "per_item": [ + { + "idx": 1092, + "ok": false + }, + { + "idx": 696, + "ok": false + }, + { + "idx": 242, + "ok": false + }, + { + "idx": 1085, + "ok": true + }, + { + "idx": 510, + "ok": false + }, + { + "idx": 334, + "ok": true + }, + { + "idx": 139, + "ok": false + }, + { + "idx": 849, + "ok": false + }, + { + "idx": 593, + "ok": false + }, + { + "idx": 579, + "ok": false + }, + { + "idx": 1064, + "ok": false + }, + { + "idx": 275, + "ok": false + }, + { + "idx": 1175, + "ok": false + }, + { + "idx": 1071, + "ok": false + }, + { + "idx": 1284, + "ok": false + }, + { + "idx": 430, + "ok": false + }, + { + "idx": 1088, + "ok": false + }, + { + "idx": 215, + "ok": false + }, + { + "idx": 841, + "ok": false + }, + { + "idx": 1299, + "ok": false + }, + { + "idx": 1113, + "ok": true + }, + { + "idx": 826, + "ok": false + }, + { + "idx": 570, + "ok": false + }, + { + "idx": 598, + "ok": false + }, + { + "idx": 905, + "ok": false + }, + { + "idx": 761, + "ok": false + }, + { + "idx": 1163, + "ok": false + }, + { + "idx": 1287, + "ok": false + }, + { + "idx": 282, + "ok": false + }, + { + "idx": 321, + "ok": false + }, + { + "idx": 252, + "ok": false + }, + { + "idx": 246, + "ok": false + }, + { + "idx": 781, + "ok": false + }, + { + "idx": 821, + "ok": false + }, + { + "idx": 1210, + "ok": true + }, + { + "idx": 958, + "ok": true + }, + { + "idx": 285, + "ok": false + }, + { + "idx": 1146, + "ok": false + }, + { + "idx": 612, + "ok": false + }, + { + "idx": 725, + "ok": false + }, + { + "idx": 1294, + "ok": false + }, + { + "idx": 968, + "ok": false + }, + { + "idx": 850, + "ok": false + }, + { + "idx": 446, + "ok": false + }, + { + "idx": 976, + "ok": false + }, + { + "idx": 1001, + "ok": false + }, + { + "idx": 1027, + "ok": true + }, + { + "idx": 651, + "ok": false + }, + { + "idx": 1009, + "ok": false + }, + { + "idx": 123, + "ok": false + }, + { + "idx": 909, + "ok": false + }, + { + "idx": 614, + "ok": false + }, + { + "idx": 292, + "ok": false + }, + { + "idx": 1014, + "ok": false + }, + { + "idx": 107, + "ok": false + }, + { + "idx": 1272, + "ok": false + }, + { + "idx": 441, + "ok": false + }, + { + "idx": 52, + "ok": false + }, + { + "idx": 727, + "ok": false + }, + { + "idx": 965, + "ok": false + }, + { + "idx": 800, + "ok": false + }, + { + "idx": 20, + "ok": false + }, + { + "idx": 1078, + "ok": false + }, + { + "idx": 136, + "ok": false + }, + { + "idx": 166, + "ok": true + }, + { + "idx": 809, + "ok": true + }, + { + "idx": 13, + "ok": false + }, + { + "idx": 739, + "ok": false + }, + { + "idx": 84, + "ok": true + }, + { + "idx": 237, + "ok": true + }, + { + "idx": 1271, + "ok": false + }, + { + "idx": 7, + "ok": false + }, + { + "idx": 553, + "ok": false + }, + { + "idx": 1311, + "ok": false + }, + { + "idx": 599, + "ok": false + }, + { + "idx": 464, + "ok": false + }, + { + "idx": 288, + "ok": false + }, + { + "idx": 1173, + "ok": false + }, + { + "idx": 589, + "ok": false + }, + { + "idx": 391, + "ok": false + }, + { + "idx": 888, + "ok": true + }, + { + "idx": 943, + "ok": false + }, + { + "idx": 676, + "ok": false + }, + { + "idx": 786, + "ok": false + }, + { + "idx": 344, + "ok": true + }, + { + "idx": 677, + "ok": false + }, + { + "idx": 863, + "ok": false + }, + { + "idx": 891, + "ok": false + }, + { + "idx": 303, + "ok": false + }, + { + "idx": 916, + "ok": false + }, + { + "idx": 302, + "ok": false + }, + { + "idx": 1073, + "ok": false + }, + { + "idx": 647, + "ok": false + }, + { + "idx": 264, + "ok": false + }, + { + "idx": 427, + "ok": false + }, + { + "idx": 382, + "ok": false + }, + { + "idx": 715, + "ok": false + }, + { + "idx": 796, + "ok": false + }, + { + "idx": 875, + "ok": false + }, + { + "idx": 1007, + "ok": false + }, + { + "idx": 797, + "ok": true + }, + { + "idx": 450, + "ok": false + }, + { + "idx": 401, + "ok": false + }, + { + "idx": 899, + "ok": false + }, + { + "idx": 418, + "ok": false + }, + { + "idx": 1201, + "ok": false + }, + { + "idx": 101, + "ok": false + }, + { + "idx": 795, + "ok": false + }, + { + "idx": 68, + "ok": false + }, + { + "idx": 479, + "ok": false + }, + { + "idx": 1296, + "ok": false + }, + { + "idx": 173, + "ok": false + }, + { + "idx": 744, + "ok": false + }, + { + "idx": 116, + "ok": true + }, + { + "idx": 1306, + "ok": false + }, + { + "idx": 355, + "ok": false + }, + { + "idx": 477, + "ok": false + }, + { + "idx": 1250, + "ok": false + }, + { + "idx": 609, + "ok": false + }, + { + "idx": 1254, + "ok": true + }, + { + "idx": 177, + "ok": false + }, + { + "idx": 1048, + "ok": false + }, + { + "idx": 582, + "ok": false + }, + { + "idx": 723, + "ok": false + }, + { + "idx": 842, + "ok": false + }, + { + "idx": 938, + "ok": false + }, + { + "idx": 110, + "ok": false + }, + { + "idx": 1057, + "ok": false + }, + { + "idx": 1120, + "ok": false + }, + { + "idx": 881, + "ok": false + }, + { + "idx": 1189, + "ok": false + }, + { + "idx": 931, + "ok": false + }, + { + "idx": 1003, + "ok": false + }, + { + "idx": 521, + "ok": false + }, + { + "idx": 974, + "ok": false + }, + { + "idx": 690, + "ok": false + }, + { + "idx": 544, + "ok": false + }, + { + "idx": 86, + "ok": false + }, + { + "idx": 89, + "ok": false + }, + { + "idx": 333, + "ok": false + }, + { + "idx": 716, + "ok": false + }, + { + "idx": 14, + "ok": false + }, + { + "idx": 287, + "ok": false + }, + { + "idx": 130, + "ok": false + }, + { + "idx": 876, + "ok": false + }, + { + "idx": 454, + "ok": false + }, + { + "idx": 1246, + "ok": true + }, + { + "idx": 812, + "ok": false + }, + { + "idx": 1142, + "ok": false + }, + { + "idx": 452, + "ok": false + }, + { + "idx": 929, + "ok": false + }, + { + "idx": 394, + "ok": false + }, + { + "idx": 695, + "ok": false + }, + { + "idx": 1245, + "ok": false + }, + { + "idx": 209, + "ok": false + }, + { + "idx": 1241, + "ok": false + }, + { + "idx": 175, + "ok": false + }, + { + "idx": 653, + "ok": false + }, + { + "idx": 661, + "ok": false + }, + { + "idx": 1097, + "ok": false + }, + { + "idx": 933, + "ok": false + }, + { + "idx": 665, + "ok": false + }, + { + "idx": 523, + "ok": false + }, + { + "idx": 59, + "ok": false + }, + { + "idx": 1069, + "ok": false + }, + { + "idx": 90, + "ok": false + }, + { + "idx": 389, + "ok": false + }, + { + "idx": 755, + "ok": false + }, + { + "idx": 164, + "ok": false + }, + { + "idx": 429, + "ok": false + }, + { + "idx": 1074, + "ok": false + }, + { + "idx": 708, + "ok": true + }, + { + "idx": 384, + "ok": true + }, + { + "idx": 412, + "ok": false + }, + { + "idx": 514, + "ok": false + }, + { + "idx": 617, + "ok": false + }, + { + "idx": 639, + "ok": false + }, + { + "idx": 1058, + "ok": false + }, + { + "idx": 787, + "ok": false + }, + { + "idx": 987, + "ok": false + }, + { + "idx": 704, + "ok": false + }, + { + "idx": 491, + "ok": false + }, + { + "idx": 91, + "ok": false + }, + { + "idx": 626, + "ok": false + }, + { + "idx": 1130, + "ok": false + }, + { + "idx": 148, + "ok": false + }, + { + "idx": 18, + "ok": false + }, + { + "idx": 897, + "ok": true + }, + { + "idx": 97, + "ok": false + }, + { + "idx": 844, + "ok": false + }, + { + "idx": 1010, + "ok": false + }, + { + "idx": 901, + "ok": false + }, + { + "idx": 241, + "ok": false + }, + { + "idx": 493, + "ok": false + }, + { + "idx": 202, + "ok": true + }, + { + "idx": 314, + "ok": false + }, + { + "idx": 847, + "ok": false + }, + { + "idx": 437, + "ok": false + }, + { + "idx": 902, + "ok": true + }, + { + "idx": 157, + "ok": false + }, + { + "idx": 874, + "ok": true + }, + { + "idx": 1144, + "ok": false + }, + { + "idx": 807, + "ok": false + }, + { + "idx": 80, + "ok": true + }, + { + "idx": 369, + "ok": false + }, + { + "idx": 511, + "ok": false + }, + { + "idx": 262, + "ok": false + }, + { + "idx": 571, + "ok": false + }, + { + "idx": 721, + "ok": false + }, + { + "idx": 654, + "ok": false + }, + { + "idx": 890, + "ok": true + }, + { + "idx": 219, + "ok": false + }, + { + "idx": 1140, + "ok": false + }, + { + "idx": 584, + "ok": false + }, + { + "idx": 1249, + "ok": false + }, + { + "idx": 1108, + "ok": true + }, + { + "idx": 607, + "ok": false + }, + { + "idx": 904, + "ok": false + }, + { + "idx": 1052, + "ok": false + }, + { + "idx": 1238, + "ok": false + }, + { + "idx": 946, + "ok": false + }, + { + "idx": 1098, + "ok": false + }, + { + "idx": 534, + "ok": false + }, + { + "idx": 558, + "ok": false + }, + { + "idx": 474, + "ok": true + }, + { + "idx": 33, + "ok": false + }, + { + "idx": 243, + "ok": false + }, + { + "idx": 1259, + "ok": false + }, + { + "idx": 353, + "ok": false + }, + { + "idx": 509, + "ok": false + }, + { + "idx": 1096, + "ok": false + }, + { + "idx": 1055, + "ok": false + }, + { + "idx": 877, + "ok": false + }, + { + "idx": 249, + "ok": false + }, + { + "idx": 1156, + "ok": false + }, + { + "idx": 735, + "ok": false + }, + { + "idx": 470, + "ok": false + }, + { + "idx": 1119, + "ok": false + }, + { + "idx": 577, + "ok": true + }, + { + "idx": 453, + "ok": false + }, + { + "idx": 132, + "ok": false + }, + { + "idx": 1061, + "ok": false + }, + { + "idx": 629, + "ok": false + }, + { + "idx": 670, + "ok": true + }, + { + "idx": 478, + "ok": false + }, + { + "idx": 764, + "ok": false + }, + { + "idx": 983, + "ok": false + }, + { + "idx": 587, + "ok": false + }, + { + "idx": 1192, + "ok": false + }, + { + "idx": 350, + "ok": false + }, + { + "idx": 281, + "ok": false + }, + { + "idx": 31, + "ok": false + }, + { + "idx": 1132, + "ok": false + }, + { + "idx": 1033, + "ok": false + }, + { + "idx": 671, + "ok": false + }, + { + "idx": 751, + "ok": false + } + ] + }, + "2:0": { + "acc": 0.30078125, + "by_label": { + "drop": 0.19, + "easy": 0.4827586206896552, + "hard": 0.3464566929133858 + }, + "per_item": [ + { + "idx": 1092, + "ok": false + }, + { + "idx": 696, + "ok": false + }, + { + "idx": 242, + "ok": true + }, + { + "idx": 1085, + "ok": true + }, + { + "idx": 510, + "ok": false + }, + { + "idx": 334, + "ok": false + }, + { + "idx": 139, + "ok": false + }, + { + "idx": 849, + "ok": false + }, + { + "idx": 593, + "ok": true + }, + { + "idx": 579, + "ok": true + }, + { + "idx": 1064, + "ok": false + }, + { + "idx": 275, + "ok": false + }, + { + "idx": 1175, + "ok": false + }, + { + "idx": 1071, + "ok": false + }, + { + "idx": 1284, + "ok": false + }, + { + "idx": 430, + "ok": true + }, + { + "idx": 1088, + "ok": false + }, + { + "idx": 215, + "ok": false + }, + { + "idx": 841, + "ok": false + }, + { + "idx": 1299, + "ok": false + }, + { + "idx": 1113, + "ok": true + }, + { + "idx": 826, + "ok": true + }, + { + "idx": 570, + "ok": false + }, + { + "idx": 598, + "ok": false + }, + { + "idx": 905, + "ok": false + }, + { + "idx": 761, + "ok": false + }, + { + "idx": 1163, + "ok": false + }, + { + "idx": 1287, + "ok": false + }, + { + "idx": 282, + "ok": false + }, + { + "idx": 321, + "ok": true + }, + { + "idx": 252, + "ok": false + }, + { + "idx": 246, + "ok": false + }, + { + "idx": 781, + "ok": false + }, + { + "idx": 821, + "ok": true + }, + { + "idx": 1210, + "ok": true + }, + { + "idx": 958, + "ok": true + }, + { + "idx": 285, + "ok": true + }, + { + "idx": 1146, + "ok": false + }, + { + "idx": 612, + "ok": false + }, + { + "idx": 725, + "ok": true + }, + { + "idx": 1294, + "ok": false + }, + { + "idx": 968, + "ok": false + }, + { + "idx": 850, + "ok": false + }, + { + "idx": 446, + "ok": false + }, + { + "idx": 976, + "ok": false + }, + { + "idx": 1001, + "ok": false + }, + { + "idx": 1027, + "ok": false + }, + { + "idx": 651, + "ok": false + }, + { + "idx": 1009, + "ok": false + }, + { + "idx": 123, + "ok": false + }, + { + "idx": 909, + "ok": false + }, + { + "idx": 614, + "ok": true + }, + { + "idx": 292, + "ok": false + }, + { + "idx": 1014, + "ok": false + }, + { + "idx": 107, + "ok": false + }, + { + "idx": 1272, + "ok": false + }, + { + "idx": 441, + "ok": false + }, + { + "idx": 52, + "ok": false + }, + { + "idx": 727, + "ok": false + }, + { + "idx": 965, + "ok": false + }, + { + "idx": 800, + "ok": false + }, + { + "idx": 20, + "ok": false + }, + { + "idx": 1078, + "ok": true + }, + { + "idx": 136, + "ok": true + }, + { + "idx": 166, + "ok": true + }, + { + "idx": 809, + "ok": false + }, + { + "idx": 13, + "ok": false + }, + { + "idx": 739, + "ok": true + }, + { + "idx": 84, + "ok": false + }, + { + "idx": 237, + "ok": true + }, + { + "idx": 1271, + "ok": false + }, + { + "idx": 7, + "ok": false + }, + { + "idx": 553, + "ok": true + }, + { + "idx": 1311, + "ok": false + }, + { + "idx": 599, + "ok": false + }, + { + "idx": 464, + "ok": false + }, + { + "idx": 288, + "ok": false + }, + { + "idx": 1173, + "ok": false + }, + { + "idx": 589, + "ok": true + }, + { + "idx": 391, + "ok": true + }, + { + "idx": 888, + "ok": true + }, + { + "idx": 943, + "ok": false + }, + { + "idx": 676, + "ok": false + }, + { + "idx": 786, + "ok": false + }, + { + "idx": 344, + "ok": false + }, + { + "idx": 677, + "ok": true + }, + { + "idx": 863, + "ok": true + }, + { + "idx": 891, + "ok": false + }, + { + "idx": 303, + "ok": false + }, + { + "idx": 916, + "ok": false + }, + { + "idx": 302, + "ok": false + }, + { + "idx": 1073, + "ok": false + }, + { + "idx": 647, + "ok": false + }, + { + "idx": 264, + "ok": false + }, + { + "idx": 427, + "ok": false + }, + { + "idx": 382, + "ok": false + }, + { + "idx": 715, + "ok": true + }, + { + "idx": 796, + "ok": false + }, + { + "idx": 875, + "ok": false + }, + { + "idx": 1007, + "ok": false + }, + { + "idx": 797, + "ok": false + }, + { + "idx": 450, + "ok": false + }, + { + "idx": 401, + "ok": false + }, + { + "idx": 899, + "ok": false + }, + { + "idx": 418, + "ok": false + }, + { + "idx": 1201, + "ok": false + }, + { + "idx": 101, + "ok": false + }, + { + "idx": 795, + "ok": true + }, + { + "idx": 68, + "ok": false + }, + { + "idx": 479, + "ok": false + }, + { + "idx": 1296, + "ok": false + }, + { + "idx": 173, + "ok": true + }, + { + "idx": 744, + "ok": false + }, + { + "idx": 116, + "ok": true + }, + { + "idx": 1306, + "ok": false + }, + { + "idx": 355, + "ok": false + }, + { + "idx": 477, + "ok": true + }, + { + "idx": 1250, + "ok": true + }, + { + "idx": 609, + "ok": true + }, + { + "idx": 1254, + "ok": true + }, + { + "idx": 177, + "ok": false + }, + { + "idx": 1048, + "ok": false + }, + { + "idx": 582, + "ok": false + }, + { + "idx": 723, + "ok": true + }, + { + "idx": 842, + "ok": true + }, + { + "idx": 938, + "ok": true + }, + { + "idx": 110, + "ok": false + }, + { + "idx": 1057, + "ok": false + }, + { + "idx": 1120, + "ok": false + }, + { + "idx": 881, + "ok": true + }, + { + "idx": 1189, + "ok": true + }, + { + "idx": 931, + "ok": false + }, + { + "idx": 1003, + "ok": false + }, + { + "idx": 521, + "ok": false + }, + { + "idx": 974, + "ok": true + }, + { + "idx": 690, + "ok": false + }, + { + "idx": 544, + "ok": true + }, + { + "idx": 86, + "ok": false + }, + { + "idx": 89, + "ok": false + }, + { + "idx": 333, + "ok": false + }, + { + "idx": 716, + "ok": false + }, + { + "idx": 14, + "ok": true + }, + { + "idx": 287, + "ok": false + }, + { + "idx": 130, + "ok": true + }, + { + "idx": 876, + "ok": false + }, + { + "idx": 454, + "ok": false + }, + { + "idx": 1246, + "ok": false + }, + { + "idx": 812, + "ok": false + }, + { + "idx": 1142, + "ok": true + }, + { + "idx": 452, + "ok": true + }, + { + "idx": 929, + "ok": true + }, + { + "idx": 394, + "ok": false + }, + { + "idx": 695, + "ok": true + }, + { + "idx": 1245, + "ok": false + }, + { + "idx": 209, + "ok": false + }, + { + "idx": 1241, + "ok": false + }, + { + "idx": 175, + "ok": true + }, + { + "idx": 653, + "ok": true + }, + { + "idx": 661, + "ok": false + }, + { + "idx": 1097, + "ok": true + }, + { + "idx": 933, + "ok": false + }, + { + "idx": 665, + "ok": true + }, + { + "idx": 523, + "ok": false + }, + { + "idx": 59, + "ok": false + }, + { + "idx": 1069, + "ok": false + }, + { + "idx": 90, + "ok": false + }, + { + "idx": 389, + "ok": false + }, + { + "idx": 755, + "ok": false + }, + { + "idx": 164, + "ok": false + }, + { + "idx": 429, + "ok": true + }, + { + "idx": 1074, + "ok": false + }, + { + "idx": 708, + "ok": true + }, + { + "idx": 384, + "ok": false + }, + { + "idx": 412, + "ok": false + }, + { + "idx": 514, + "ok": false + }, + { + "idx": 617, + "ok": true + }, + { + "idx": 639, + "ok": true + }, + { + "idx": 1058, + "ok": true + }, + { + "idx": 787, + "ok": true + }, + { + "idx": 987, + "ok": false + }, + { + "idx": 704, + "ok": false + }, + { + "idx": 491, + "ok": true + }, + { + "idx": 91, + "ok": true + }, + { + "idx": 626, + "ok": false + }, + { + "idx": 1130, + "ok": false + }, + { + "idx": 148, + "ok": false + }, + { + "idx": 18, + "ok": false + }, + { + "idx": 897, + "ok": false + }, + { + "idx": 97, + "ok": false + }, + { + "idx": 844, + "ok": false + }, + { + "idx": 1010, + "ok": true + }, + { + "idx": 901, + "ok": false + }, + { + "idx": 241, + "ok": false + }, + { + "idx": 493, + "ok": false + }, + { + "idx": 202, + "ok": false + }, + { + "idx": 314, + "ok": false + }, + { + "idx": 847, + "ok": false + }, + { + "idx": 437, + "ok": false + }, + { + "idx": 902, + "ok": false + }, + { + "idx": 157, + "ok": false + }, + { + "idx": 874, + "ok": true + }, + { + "idx": 1144, + "ok": false + }, + { + "idx": 807, + "ok": false + }, + { + "idx": 80, + "ok": false + }, + { + "idx": 369, + "ok": false + }, + { + "idx": 511, + "ok": false + }, + { + "idx": 262, + "ok": true + }, + { + "idx": 571, + "ok": false + }, + { + "idx": 721, + "ok": false + }, + { + "idx": 654, + "ok": false + }, + { + "idx": 890, + "ok": true + }, + { + "idx": 219, + "ok": false + }, + { + "idx": 1140, + "ok": false + }, + { + "idx": 584, + "ok": false + }, + { + "idx": 1249, + "ok": false + }, + { + "idx": 1108, + "ok": true + }, + { + "idx": 607, + "ok": false + }, + { + "idx": 904, + "ok": true + }, + { + "idx": 1052, + "ok": false + }, + { + "idx": 1238, + "ok": false + }, + { + "idx": 946, + "ok": false + }, + { + "idx": 1098, + "ok": true + }, + { + "idx": 534, + "ok": false + }, + { + "idx": 558, + "ok": true + }, + { + "idx": 474, + "ok": false + }, + { + "idx": 33, + "ok": true + }, + { + "idx": 243, + "ok": true + }, + { + "idx": 1259, + "ok": false + }, + { + "idx": 353, + "ok": false + }, + { + "idx": 509, + "ok": true + }, + { + "idx": 1096, + "ok": false + }, + { + "idx": 1055, + "ok": true + }, + { + "idx": 877, + "ok": false + }, + { + "idx": 249, + "ok": true + }, + { + "idx": 1156, + "ok": false + }, + { + "idx": 735, + "ok": false + }, + { + "idx": 470, + "ok": false + }, + { + "idx": 1119, + "ok": false + }, + { + "idx": 577, + "ok": false + }, + { + "idx": 453, + "ok": false + }, + { + "idx": 132, + "ok": false + }, + { + "idx": 1061, + "ok": true + }, + { + "idx": 629, + "ok": false + }, + { + "idx": 670, + "ok": true + }, + { + "idx": 478, + "ok": false + }, + { + "idx": 764, + "ok": false + }, + { + "idx": 983, + "ok": false + }, + { + "idx": 587, + "ok": false + }, + { + "idx": 1192, + "ok": true + }, + { + "idx": 350, + "ok": true + }, + { + "idx": 281, + "ok": false + }, + { + "idx": 31, + "ok": true + }, + { + "idx": 1132, + "ok": false + }, + { + "idx": 1033, + "ok": false + }, + { + "idx": 671, + "ok": true + }, + { + "idx": 751, + "ok": false + } + ] + } + }, + "n": 256 +} \ No newline at end of file diff --git a/results-loop/eval_gsm_carrycot_b1_ts50_ablate.json b/results-loop/eval_gsm_carrycot_b1_ts50_ablate.json new file mode 100644 index 0000000..923a767 --- /dev/null +++ b/results-loop/eval_gsm_carrycot_b1_ts50_ablate.json @@ -0,0 +1,1040 @@ +{ + "tag": "gsm_carrycot_b1_ts50_ablate", + "grid": { + "2:0": { + "acc": 0.296875, + "by_label": { + "drop": 0.18, + "easy": 0.4827586206896552, + "hard": 0.3464566929133858 + }, + "per_item": [ + { + "idx": 1092, + "ok": false + }, + { + "idx": 696, + "ok": false + }, + { + "idx": 242, + "ok": true + }, + { + "idx": 1085, + "ok": true + }, + { + "idx": 510, + "ok": false + }, + { + "idx": 334, + "ok": false + }, + { + "idx": 139, + "ok": false + }, + { + "idx": 849, + "ok": false + }, + { + "idx": 593, + "ok": false + }, + { + "idx": 579, + "ok": true + }, + { + "idx": 1064, + "ok": false + }, + { + "idx": 275, + "ok": false + }, + { + "idx": 1175, + "ok": false + }, + { + "idx": 1071, + "ok": false + }, + { + "idx": 1284, + "ok": false + }, + { + "idx": 430, + "ok": true + }, + { + "idx": 1088, + "ok": false + }, + { + "idx": 215, + "ok": false + }, + { + "idx": 841, + "ok": false + }, + { + "idx": 1299, + "ok": false + }, + { + "idx": 1113, + "ok": true + }, + { + "idx": 826, + "ok": true + }, + { + "idx": 570, + "ok": false + }, + { + "idx": 598, + "ok": false + }, + { + "idx": 905, + "ok": false + }, + { + "idx": 761, + "ok": false + }, + { + "idx": 1163, + "ok": false + }, + { + "idx": 1287, + "ok": false + }, + { + "idx": 282, + "ok": false + }, + { + "idx": 321, + "ok": true + }, + { + "idx": 252, + "ok": false + }, + { + "idx": 246, + "ok": false + }, + { + "idx": 781, + "ok": false + }, + { + "idx": 821, + "ok": true + }, + { + "idx": 1210, + "ok": true + }, + { + "idx": 958, + "ok": true + }, + { + "idx": 285, + "ok": true + }, + { + "idx": 1146, + "ok": false + }, + { + "idx": 612, + "ok": false + }, + { + "idx": 725, + "ok": true + }, + { + "idx": 1294, + "ok": false + }, + { + "idx": 968, + "ok": false + }, + { + "idx": 850, + "ok": false + }, + { + "idx": 446, + "ok": true + }, + { + "idx": 976, + "ok": false + }, + { + "idx": 1001, + "ok": false + }, + { + "idx": 1027, + "ok": false + }, + { + "idx": 651, + "ok": false + }, + { + "idx": 1009, + "ok": false + }, + { + "idx": 123, + "ok": false + }, + { + "idx": 909, + "ok": false + }, + { + "idx": 614, + "ok": true + }, + { + "idx": 292, + "ok": false + }, + { + "idx": 1014, + "ok": false + }, + { + "idx": 107, + "ok": false + }, + { + "idx": 1272, + "ok": false + }, + { + "idx": 441, + "ok": false + }, + { + "idx": 52, + "ok": false + }, + { + "idx": 727, + "ok": false + }, + { + "idx": 965, + "ok": false + }, + { + "idx": 800, + "ok": false + }, + { + "idx": 20, + "ok": false + }, + { + "idx": 1078, + "ok": true + }, + { + "idx": 136, + "ok": true + }, + { + "idx": 166, + "ok": true + }, + { + "idx": 809, + "ok": false + }, + { + "idx": 13, + "ok": false + }, + { + "idx": 739, + "ok": true + }, + { + "idx": 84, + "ok": false + }, + { + "idx": 237, + "ok": true + }, + { + "idx": 1271, + "ok": false + }, + { + "idx": 7, + "ok": false + }, + { + "idx": 553, + "ok": true + }, + { + "idx": 1311, + "ok": false + }, + { + "idx": 599, + "ok": false + }, + { + "idx": 464, + "ok": false + }, + { + "idx": 288, + "ok": false + }, + { + "idx": 1173, + "ok": false + }, + { + "idx": 589, + "ok": true + }, + { + "idx": 391, + "ok": true + }, + { + "idx": 888, + "ok": true + }, + { + "idx": 943, + "ok": false + }, + { + "idx": 676, + "ok": false + }, + { + "idx": 786, + "ok": false + }, + { + "idx": 344, + "ok": false + }, + { + "idx": 677, + "ok": true + }, + { + "idx": 863, + "ok": true + }, + { + "idx": 891, + "ok": false + }, + { + "idx": 303, + "ok": false + }, + { + "idx": 916, + "ok": false + }, + { + "idx": 302, + "ok": false + }, + { + "idx": 1073, + "ok": false + }, + { + "idx": 647, + "ok": false + }, + { + "idx": 264, + "ok": false + }, + { + "idx": 427, + "ok": false + }, + { + "idx": 382, + "ok": false + }, + { + "idx": 715, + "ok": true + }, + { + "idx": 796, + "ok": false + }, + { + "idx": 875, + "ok": false + }, + { + "idx": 1007, + "ok": false + }, + { + "idx": 797, + "ok": false + }, + { + "idx": 450, + "ok": false + }, + { + "idx": 401, + "ok": false + }, + { + "idx": 899, + "ok": false + }, + { + "idx": 418, + "ok": false + }, + { + "idx": 1201, + "ok": false + }, + { + "idx": 101, + "ok": false + }, + { + "idx": 795, + "ok": true + }, + { + "idx": 68, + "ok": false + }, + { + "idx": 479, + "ok": false + }, + { + "idx": 1296, + "ok": false + }, + { + "idx": 173, + "ok": true + }, + { + "idx": 744, + "ok": false + }, + { + "idx": 116, + "ok": true + }, + { + "idx": 1306, + "ok": false + }, + { + "idx": 355, + "ok": false + }, + { + "idx": 477, + "ok": true + }, + { + "idx": 1250, + "ok": true + }, + { + "idx": 609, + "ok": true + }, + { + "idx": 1254, + "ok": true + }, + { + "idx": 177, + "ok": false + }, + { + "idx": 1048, + "ok": false + }, + { + "idx": 582, + "ok": false + }, + { + "idx": 723, + "ok": true + }, + { + "idx": 842, + "ok": true + }, + { + "idx": 938, + "ok": true + }, + { + "idx": 110, + "ok": false + }, + { + "idx": 1057, + "ok": false + }, + { + "idx": 1120, + "ok": false + }, + { + "idx": 881, + "ok": true + }, + { + "idx": 1189, + "ok": true + }, + { + "idx": 931, + "ok": false + }, + { + "idx": 1003, + "ok": false + }, + { + "idx": 521, + "ok": false + }, + { + "idx": 974, + "ok": true + }, + { + "idx": 690, + "ok": false + }, + { + "idx": 544, + "ok": true + }, + { + "idx": 86, + "ok": false + }, + { + "idx": 89, + "ok": false + }, + { + "idx": 333, + "ok": false + }, + { + "idx": 716, + "ok": false + }, + { + "idx": 14, + "ok": true + }, + { + "idx": 287, + "ok": false + }, + { + "idx": 130, + "ok": true + }, + { + "idx": 876, + "ok": false + }, + { + "idx": 454, + "ok": false + }, + { + "idx": 1246, + "ok": false + }, + { + "idx": 812, + "ok": false + }, + { + "idx": 1142, + "ok": true + }, + { + "idx": 452, + "ok": true + }, + { + "idx": 929, + "ok": true + }, + { + "idx": 394, + "ok": false + }, + { + "idx": 695, + "ok": true + }, + { + "idx": 1245, + "ok": true + }, + { + "idx": 209, + "ok": false + }, + { + "idx": 1241, + "ok": false + }, + { + "idx": 175, + "ok": true + }, + { + "idx": 653, + "ok": true + }, + { + "idx": 661, + "ok": false + }, + { + "idx": 1097, + "ok": true + }, + { + "idx": 933, + "ok": false + }, + { + "idx": 665, + "ok": true + }, + { + "idx": 523, + "ok": false + }, + { + "idx": 59, + "ok": false + }, + { + "idx": 1069, + "ok": true + }, + { + "idx": 90, + "ok": false + }, + { + "idx": 389, + "ok": false + }, + { + "idx": 755, + "ok": false + }, + { + "idx": 164, + "ok": false + }, + { + "idx": 429, + "ok": false + }, + { + "idx": 1074, + "ok": false + }, + { + "idx": 708, + "ok": true + }, + { + "idx": 384, + "ok": false + }, + { + "idx": 412, + "ok": false + }, + { + "idx": 514, + "ok": false + }, + { + "idx": 617, + "ok": true + }, + { + "idx": 639, + "ok": false + }, + { + "idx": 1058, + "ok": false + }, + { + "idx": 787, + "ok": true + }, + { + "idx": 987, + "ok": false + }, + { + "idx": 704, + "ok": false + }, + { + "idx": 491, + "ok": true + }, + { + "idx": 91, + "ok": true + }, + { + "idx": 626, + "ok": false + }, + { + "idx": 1130, + "ok": false + }, + { + "idx": 148, + "ok": true + }, + { + "idx": 18, + "ok": false + }, + { + "idx": 897, + "ok": false + }, + { + "idx": 97, + "ok": false + }, + { + "idx": 844, + "ok": false + }, + { + "idx": 1010, + "ok": true + }, + { + "idx": 901, + "ok": false + }, + { + "idx": 241, + "ok": false + }, + { + "idx": 493, + "ok": false + }, + { + "idx": 202, + "ok": false + }, + { + "idx": 314, + "ok": false + }, + { + "idx": 847, + "ok": false + }, + { + "idx": 437, + "ok": false + }, + { + "idx": 902, + "ok": false + }, + { + "idx": 157, + "ok": false + }, + { + "idx": 874, + "ok": true + }, + { + "idx": 1144, + "ok": false + }, + { + "idx": 807, + "ok": false + }, + { + "idx": 80, + "ok": false + }, + { + "idx": 369, + "ok": false + }, + { + "idx": 511, + "ok": false + }, + { + "idx": 262, + "ok": true + }, + { + "idx": 571, + "ok": false + }, + { + "idx": 721, + "ok": false + }, + { + "idx": 654, + "ok": false + }, + { + "idx": 890, + "ok": true + }, + { + "idx": 219, + "ok": false + }, + { + "idx": 1140, + "ok": false + }, + { + "idx": 584, + "ok": false + }, + { + "idx": 1249, + "ok": false + }, + { + "idx": 1108, + "ok": true + }, + { + "idx": 607, + "ok": false + }, + { + "idx": 904, + "ok": true + }, + { + "idx": 1052, + "ok": false + }, + { + "idx": 1238, + "ok": false + }, + { + "idx": 946, + "ok": false + }, + { + "idx": 1098, + "ok": true + }, + { + "idx": 534, + "ok": false + }, + { + "idx": 558, + "ok": true + }, + { + "idx": 474, + "ok": false + }, + { + "idx": 33, + "ok": true + }, + { + "idx": 243, + "ok": true + }, + { + "idx": 1259, + "ok": false + }, + { + "idx": 353, + "ok": false + }, + { + "idx": 509, + "ok": true + }, + { + "idx": 1096, + "ok": false + }, + { + "idx": 1055, + "ok": true + }, + { + "idx": 877, + "ok": false + }, + { + "idx": 249, + "ok": false + }, + { + "idx": 1156, + "ok": false + }, + { + "idx": 735, + "ok": false + }, + { + "idx": 470, + "ok": false + }, + { + "idx": 1119, + "ok": false + }, + { + "idx": 577, + "ok": false + }, + { + "idx": 453, + "ok": false + }, + { + "idx": 132, + "ok": false + }, + { + "idx": 1061, + "ok": true + }, + { + "idx": 629, + "ok": false + }, + { + "idx": 670, + "ok": true + }, + { + "idx": 478, + "ok": false + }, + { + "idx": 764, + "ok": false + }, + { + "idx": 983, + "ok": false + }, + { + "idx": 587, + "ok": false + }, + { + "idx": 1192, + "ok": true + }, + { + "idx": 350, + "ok": true + }, + { + "idx": 281, + "ok": false + }, + { + "idx": 31, + "ok": true + }, + { + "idx": 1132, + "ok": false + }, + { + "idx": 1033, + "ok": false + }, + { + "idx": 671, + "ok": true + }, + { + "idx": 751, + "ok": false + } + ] + } + }, + "n": 256 +} \ No newline at end of file diff --git a/results-loop/train_carrycot_b1_ii10_ts50_p0_log.json b/results-loop/train_carrycot_b1_ii10_ts50_p0_log.json new file mode 100644 index 0000000..192c6a8 --- /dev/null +++ b/results-loop/train_carrycot_b1_ii10_ts50_p0_log.json @@ -0,0 +1 @@ +[{"step": 0, "loss": 1.5047228336334229, "lce": 0.0, "lgen": 0.0, "lts": 0.11272062361240387}, {"step": 1, "loss": 1.4074137210845947, "lce": 0.0, "lgen": 0.0, "lts": 0.11771547794342041}, {"step": 2, "loss": 1.64420485496521, "lce": 0.0, "lgen": 0.0, "lts": 0.14652204513549805}, {"step": 3, "loss": 1.4635393619537354, "lce": 0.0, "lgen": 0.0, "lts": 0.10492360591888428}, {"step": 4, "loss": 1.1991362571716309, "lce": 0.0, "lgen": 0.0, "lts": 0.1314617246389389}, {"step": 5, "loss": 1.041207194328308, "lce": 0.0, "lgen": 0.0, "lts": 0.11454488337039948}, {"step": 6, "loss": 1.4601948261260986, "lce": 0.0, "lgen": 0.0, "lts": 0.11645461618900299}, {"step": 7, "loss": 1.1655343770980835, "lce": 0.0, "lgen": 0.0, "lts": 0.10517677664756775}, {"step": 8, "loss": 0.9329603910446167, "lce": 0.0, "lgen": 0.0, "lts": 0.10646587610244751}, {"step": 9, "loss": 0.9955830574035645, "lce": 0.0, "lgen": 0.0, "lts": 0.09236153960227966}, {"step": 10, "loss": 1.283742904663086, "lce": 0.0, "lgen": 0.0, "lts": 0.11528995633125305}, {"step": 11, "loss": 1.1502629518508911, "lce": 0.0, "lgen": 0.0, "lts": 0.10781833529472351}, {"step": 12, "loss": 1.0663058757781982, "lce": 0.0, "lgen": 0.0, "lts": 0.11895358562469482}, {"step": 13, "loss": 0.7363285422325134, "lce": 0.0, "lgen": 0.0, "lts": 0.09728878736495972}, {"step": 14, "loss": 0.7942532300949097, "lce": 0.0, "lgen": 0.0, "lts": 0.10655149072408676}, {"step": 15, "loss": 0.9720652103424072, "lce": 0.0, "lgen": 0.0, "lts": 0.10463134944438934}, {"step": 16, "loss": 0.7289019823074341, "lce": 0.0, "lgen": 0.0, "lts": 0.08909517526626587}, {"step": 17, "loss": 1.1486961841583252, "lce": 0.0, "lgen": 0.0, "lts": 0.11482714116573334}, {"step": 18, "loss": 0.8102765083312988, "lce": 0.0, "lgen": 0.0, "lts": 0.09318946301937103}, {"step": 19, "loss": 1.0046491622924805, "lce": 0.0, "lgen": 0.0, "lts": 0.09032142162322998}, {"step": 20, "loss": 0.7477749586105347, "lce": 0.0, "lgen": 0.0, "lts": 0.08069650828838348}, {"step": 21, "loss": 0.8178378343582153, "lce": 0.0, "lgen": 0.0, "lts": 0.0872267484664917}, {"step": 22, "loss": 0.875950813293457, "lce": 0.0, "lgen": 0.0, "lts": 0.0924345850944519}, {"step": 23, "loss": 1.359808087348938, "lce": 0.0, "lgen": 0.0, "lts": 0.09794123470783234}, {"step": 24, "loss": 0.7898613214492798, "lce": 0.0, "lgen": 0.0, "lts": 0.07725772261619568}, {"step": 25, "loss": 1.054410457611084, "lce": 0.0, "lgen": 0.0, "lts": 0.09328921139240265}, {"step": 26, "loss": 0.7385439872741699, "lce": 0.0, "lgen": 0.0, "lts": 0.10627532005310059}, {"step": 27, "loss": 0.8392857313156128, "lce": 0.0, "lgen": 0.0, "lts": 0.0773458331823349}, {"step": 28, "loss": 0.844818115234375, "lce": 0.0, "lgen": 0.0, "lts": 0.08942341804504395}, {"step": 29, "loss": 0.8340024352073669, "lce": 0.0, "lgen": 0.0, "lts": 0.0916968435049057}, {"step": 30, "loss": 0.8130306005477905, "lce": 0.0, "lgen": 0.0, "lts": 0.08542439341545105}, {"step": 31, "loss": 0.9481423497200012, "lce": 0.0, "lgen": 0.0, "lts": 0.08650924265384674}, {"step": 32, "loss": 0.4792209267616272, "lce": 0.0, "lgen": 0.0, "lts": 0.06848591566085815}, {"step": 33, "loss": 0.8799536228179932, "lce": 0.0, "lgen": 0.0, "lts": 0.08254629373550415}, {"step": 34, "loss": 0.8195165395736694, "lce": 0.0, "lgen": 0.0, "lts": 0.08632358908653259}, {"step": 35, "loss": 0.510076105594635, "lce": 0.0, "lgen": 0.0, "lts": 0.0702170729637146}, {"step": 36, "loss": 0.8218207359313965, "lce": 0.0, "lgen": 0.0, "lts": 0.08573532104492188}, {"step": 37, "loss": 0.5782496333122253, "lce": 0.0, "lgen": 0.0, "lts": 0.0750507116317749}, {"step": 38, "loss": 0.6318389177322388, "lce": 0.0, "lgen": 0.0, "lts": 0.0683220624923706}, {"step": 39, "loss": 0.6006115674972534, "lce": 0.0, "lgen": 0.0, "lts": 0.07094329595565796}, {"step": 40, "loss": 0.5838391780853271, "lce": 0.0, "lgen": 0.0, "lts": 0.07995140552520752}, {"step": 41, "loss": 0.9609639644622803, "lce": 0.0, "lgen": 0.0, "lts": 0.07215943932533264}, {"step": 42, "loss": 0.5835752487182617, "lce": 0.0, "lgen": 0.0, "lts": 0.06734469532966614}, {"step": 43, "loss": 0.8881217837333679, "lce": 0.0, "lgen": 0.0, "lts": 0.08270855247974396}, {"step": 44, "loss": 0.47441112995147705, "lce": 0.0, "lgen": 0.0, "lts": 0.0676625669002533}, {"step": 45, "loss": 0.9230786561965942, "lce": 0.0, "lgen": 0.0, "lts": 0.07088080048561096}, {"step": 46, "loss": 0.5272029638290405, "lce": 0.0, "lgen": 0.0, "lts": 0.07333371043205261}, {"step": 47, "loss": 0.7075742483139038, "lce": 0.0, "lgen": 0.0, "lts": 0.06955571472644806}, {"step": 48, "loss": 0.49771833419799805, "lce": 0.0, "lgen": 0.0, "lts": 0.06653985381126404}, {"step": 49, "loss": 0.7246980667114258, "lce": 0.0, "lgen": 0.0, "lts": 0.07076196372509003}, {"step": 50, "loss": 0.40368977189064026, "lce": 0.0, "lgen": 0.0, "lts": 0.06189800798892975}, {"step": 51, "loss": 0.7207615971565247, "lce": 0.0, "lgen": 0.0, "lts": 0.06802281737327576}, {"step": 52, "loss": 0.4485570192337036, "lce": 0.0, "lgen": 0.0, "lts": 0.06309817731380463}, {"step": 53, "loss": 0.835166871547699, "lce": 0.0, "lgen": 0.0, "lts": 0.08319586515426636}, {"step": 54, "loss": 0.5566937923431396, "lce": 0.0, "lgen": 0.0, "lts": 0.0737466961145401}, {"step": 55, "loss": 0.8655577898025513, "lce": 0.0, "lgen": 0.0, "lts": 0.06491121649742126}, {"step": 56, "loss": 0.5289262533187866, "lce": 0.0, "lgen": 0.0, "lts": 0.07986433804035187}, {"step": 57, "loss": 0.592563807964325, "lce": 0.0, "lgen": 0.0, "lts": 0.06364572048187256}, {"step": 58, "loss": 0.5113296508789062, "lce": 0.0, "lgen": 0.0, "lts": 0.06858019530773163}, {"step": 59, "loss": 0.45800715684890747, "lce": 0.0, "lgen": 0.0, "lts": 0.059395015239715576}, {"step": 60, "loss": 0.49579915404319763, "lce": 0.0, "lgen": 0.0, "lts": 0.06774207949638367}, {"step": 61, "loss": 0.7773079872131348, "lce": 0.0, "lgen": 0.0, "lts": 0.06714797019958496}, {"step": 62, "loss": 0.5377289056777954, "lce": 0.0, "lgen": 0.0, "lts": 0.06636747717857361}, {"step": 63, "loss": 0.6924800872802734, "lce": 0.0, "lgen": 0.0, "lts": 0.06660693883895874}, {"step": 64, "loss": 0.6767141819000244, "lce": 0.0, "lgen": 0.0, "lts": 0.06374552845954895}, {"step": 65, "loss": 0.6920298337936401, "lce": 0.0, "lgen": 0.0, "lts": 0.06207479536533356}, {"step": 66, "loss": 0.37985748052597046, "lce": 0.0, "lgen": 0.0, "lts": 0.05174155533313751}, {"step": 67, "loss": 0.8556783199310303, "lce": 0.0, "lgen": 0.0, "lts": 0.07018914818763733}, {"step": 68, "loss": 0.4960007071495056, "lce": 0.0, "lgen": 0.0, "lts": 0.06554390490055084}, {"step": 69, "loss": 0.7220816612243652, "lce": 0.0, "lgen": 0.0, "lts": 0.07959900796413422}, {"step": 70, "loss": 0.49491822719573975, "lce": 0.0, "lgen": 0.0, "lts": 0.06134328246116638}, {"step": 71, "loss": 0.639042854309082, "lce": 0.0, "lgen": 0.0, "lts": 0.06271153688430786}, {"step": 72, "loss": 0.526469349861145, "lce": 0.0, "lgen": 0.0, "lts": 0.054178278893232346}, {"step": 73, "loss": 0.6549123525619507, "lce": 0.0, "lgen": 0.0, "lts": 0.055060699582099915}, {"step": 74, "loss": 0.5522487163543701, "lce": 0.0, "lgen": 0.0, "lts": 0.05334275960922241}, {"step": 75, "loss": 0.5931364297866821, "lce": 0.0, "lgen": 0.0, "lts": 0.06812028586864471}, {"step": 76, "loss": 0.5620400309562683, "lce": 0.0, "lgen": 0.0, "lts": 0.07079604268074036}, {"step": 77, "loss": 0.44757866859436035, "lce": 0.0, "lgen": 0.0, "lts": 0.05672474205493927}, {"step": 78, "loss": 0.4550245404243469, "lce": 0.0, "lgen": 0.0, "lts": 0.06587843596935272}, {"step": 79, "loss": 0.5709511041641235, "lce": 0.0, "lgen": 0.0, "lts": 0.06395985186100006}, {"step": 80, "loss": 0.5650538802146912, "lce": 0.0, "lgen": 0.0, "lts": 0.06734609603881836}, {"step": 81, "loss": 0.7398033142089844, "lce": 0.0, "lgen": 0.0, "lts": 0.059707507491111755}, {"step": 82, "loss": 0.4566003978252411, "lce": 0.0, "lgen": 0.0, "lts": 0.05285918712615967}, {"step": 83, "loss": 0.5599358677864075, "lce": 0.0, "lgen": 0.0, "lts": 0.06986699998378754}, {"step": 84, "loss": 0.3926864266395569, "lce": 0.0, "lgen": 0.0, "lts": 0.055703967809677124}, {"step": 85, "loss": 0.7212618589401245, "lce": 0.0, "lgen": 0.0, "lts": 0.06356105208396912}, {"step": 86, "loss": 0.4503684639930725, "lce": 0.0, "lgen": 0.0, "lts": 0.052130818367004395}, {"step": 87, "loss": 0.5692128539085388, "lce": 0.0, "lgen": 0.0, "lts": 0.05414474010467529}, {"step": 88, "loss": 0.3799988627433777, "lce": 0.0, "lgen": 0.0, "lts": 0.05068647861480713}, {"step": 89, "loss": 0.5780673623085022, "lce": 0.0, "lgen": 0.0, "lts": 0.053919658064842224}, {"step": 90, "loss": 0.4778730869293213, "lce": 0.0, "lgen": 0.0, "lts": 0.06292031705379486}, {"step": 91, "loss": 0.5826357007026672, "lce": 0.0, "lgen": 0.0, "lts": 0.06102384626865387}, {"step": 92, "loss": 0.4076835811138153, "lce": 0.0, "lgen": 0.0, "lts": 0.05219927430152893}, {"step": 93, "loss": 0.710052490234375, "lce": 0.0, "lgen": 0.0, "lts": 0.06814366579055786}, {"step": 94, "loss": 0.42970800399780273, "lce": 0.0, "lgen": 0.0, "lts": 0.05678112804889679}, {"step": 95, "loss": 0.5518535375595093, "lce": 0.0, "lgen": 0.0, "lts": 0.06150232255458832}, {"step": 96, "loss": 0.46910446882247925, "lce": 0.0, "lgen": 0.0, "lts": 0.07051008939743042}, {"step": 97, "loss": 0.4896562695503235, "lce": 0.0, "lgen": 0.0, "lts": 0.06222691386938095}, {"step": 98, "loss": 0.41837549209594727, "lce": 0.0, "lgen": 0.0, "lts": 0.05446963012218475}, {"step": 99, "loss": 0.5855940580368042, "lce": 0.0, "lgen": 0.0, "lts": 0.06204374134540558}, {"step": 100, "loss": 0.40192848443984985, "lce": 0.0, "lgen": 0.0, "lts": 0.06000266969203949}, {"step": 101, "loss": 0.5414867997169495, "lce": 0.0, "lgen": 0.0, "lts": 0.049822911620140076}, {"step": 102, "loss": 0.5365982055664062, "lce": 0.0, "lgen": 0.0, "lts": 0.06114336848258972}, {"step": 103, "loss": 0.4613693058490753, "lce": 0.0, "lgen": 0.0, "lts": 0.05533319711685181}, {"step": 104, "loss": 0.387119323015213, "lce": 0.0, "lgen": 0.0, "lts": 0.05416133999824524}, {"step": 105, "loss": 0.47459250688552856, "lce": 0.0, "lgen": 0.0, "lts": 0.04919438064098358}, {"step": 106, "loss": 0.3361128568649292, "lce": 0.0, "lgen": 0.0, "lts": 0.04895985126495361}, {"step": 107, "loss": 0.6543912887573242, "lce": 0.0, "lgen": 0.0, "lts": 0.06340011954307556}, {"step": 108, "loss": 0.3880237936973572, "lce": 0.0, "lgen": 0.0, "lts": 0.05161389708518982}, {"step": 109, "loss": 0.8290464878082275, "lce": 0.0, "lgen": 0.0, "lts": 0.05762180685997009}, {"step": 110, "loss": 0.43987101316452026, "lce": 0.0, "lgen": 0.0, "lts": 0.05176873505115509}, {"step": 111, "loss": 0.47317010164260864, "lce": 0.0, "lgen": 0.0, "lts": 0.04835920035839081}, {"step": 112, "loss": 0.5779678225517273, "lce": 0.0, "lgen": 0.0, "lts": 0.04898761212825775}, {"step": 113, "loss": 0.6500906944274902, "lce": 0.0, "lgen": 0.0, "lts": 0.05857664346694946}, {"step": 114, "loss": 0.4360724985599518, "lce": 0.0, "lgen": 0.0, "lts": 0.055417582392692566}, {"step": 115, "loss": 0.5127462148666382, "lce": 0.0, "lgen": 0.0, "lts": 0.05071067810058594}, {"step": 116, "loss": 0.4021334648132324, "lce": 0.0, "lgen": 0.0, "lts": 0.053552232682704926}, {"step": 117, "loss": 0.7351061105728149, "lce": 0.0, "lgen": 0.0, "lts": 0.05314977467060089}, {"step": 118, "loss": 0.4148310720920563, "lce": 0.0, "lgen": 0.0, "lts": 0.04898636043071747}, {"step": 119, "loss": 0.49637556076049805, "lce": 0.0, "lgen": 0.0, "lts": 0.05784359574317932}, {"step": 120, "loss": 0.4586293697357178, "lce": 0.0, "lgen": 0.0, "lts": 0.043360888957977295}, {"step": 121, "loss": 0.5751935839653015, "lce": 0.0, "lgen": 0.0, "lts": 0.05199781060218811}, {"step": 122, "loss": 0.472608745098114, "lce": 0.0, "lgen": 0.0, "lts": 0.0527472198009491}, {"step": 123, "loss": 0.7508822679519653, "lce": 0.0, "lgen": 0.0, "lts": 0.05906376242637634}, {"step": 124, "loss": 0.41243356466293335, "lce": 0.0, "lgen": 0.0, "lts": 0.050460562109947205}, {"step": 125, "loss": 0.5559567213058472, "lce": 0.0, "lgen": 0.0, "lts": 0.060850225389003754}, {"step": 126, "loss": 0.45334184169769287, "lce": 0.0, "lgen": 0.0, "lts": 0.048067763447761536}, {"step": 127, "loss": 0.46283453702926636, "lce": 0.0, "lgen": 0.0, "lts": 0.05528248846530914}, {"step": 128, "loss": 0.517735481262207, "lce": 0.0, "lgen": 0.0, "lts": 0.04811982810497284}, {"step": 129, "loss": 0.5172321796417236, "lce": 0.0, "lgen": 0.0, "lts": 0.05170898139476776}, {"step": 130, "loss": 0.31836754083633423, "lce": 0.0, "lgen": 0.0, "lts": 0.043254777789115906}, {"step": 131, "loss": 0.3874337673187256, "lce": 0.0, "lgen": 0.0, "lts": 0.045563023537397385}, {"step": 132, "loss": 0.4427737593650818, "lce": 0.0, "lgen": 0.0, "lts": 0.04866158962249756}, {"step": 133, "loss": 0.5631333589553833, "lce": 0.0, "lgen": 0.0, "lts": 0.04458041489124298}, {"step": 134, "loss": 0.4342558979988098, "lce": 0.0, "lgen": 0.0, "lts": 0.04943951964378357}, {"step": 135, "loss": 0.5783673524856567, "lce": 0.0, "lgen": 0.0, "lts": 0.05392685532569885}, {"step": 136, "loss": 0.3874635696411133, "lce": 0.0, "lgen": 0.0, "lts": 0.044099174439907074}, {"step": 137, "loss": 0.6051167845726013, "lce": 0.0, "lgen": 0.0, "lts": 0.058689504861831665}, {"step": 138, "loss": 0.39138907194137573, "lce": 0.0, "lgen": 0.0, "lts": 0.04729408025741577}, {"step": 139, "loss": 0.5797715187072754, "lce": 0.0, "lgen": 0.0, "lts": 0.05744433403015137}, {"step": 140, "loss": 0.3090330958366394, "lce": 0.0, "lgen": 0.0, "lts": 0.04800431430339813}, {"step": 141, "loss": 0.4287537932395935, "lce": 0.0, "lgen": 0.0, "lts": 0.04722754657268524}, {"step": 142, "loss": 0.4301179051399231, "lce": 0.0, "lgen": 0.0, "lts": 0.048840537667274475}, {"step": 143, "loss": 0.3531453013420105, "lce": 0.0, "lgen": 0.0, "lts": 0.04024568200111389}, {"step": 144, "loss": 0.4418158531188965, "lce": 0.0, "lgen": 0.0, "lts": 0.04943254590034485}, {"step": 145, "loss": 0.7443171143531799, "lce": 0.0, "lgen": 0.0, "lts": 0.05471500754356384}, {"step": 146, "loss": 0.3620806336402893, "lce": 0.0, "lgen": 0.0, "lts": 0.05227801203727722}, {"step": 147, "loss": 0.5641224384307861, "lce": 0.0, "lgen": 0.0, "lts": 0.06353966891765594}, {"step": 148, "loss": 0.33531343936920166, "lce": 0.0, "lgen": 0.0, "lts": 0.04033063352108002}, {"step": 149, "loss": 0.33499860763549805, "lce": 0.0, "lgen": 0.0, "lts": 0.03434966504573822}, {"step": 150, "loss": 0.36534860730171204, "lce": 0.0, "lgen": 0.0, "lts": 0.04821683466434479}, {"step": 151, "loss": 0.5310852527618408, "lce": 0.0, "lgen": 0.0, "lts": 0.04752962291240692}, {"step": 152, "loss": 0.3817670941352844, "lce": 0.0, "lgen": 0.0, "lts": 0.04738278687000275}, {"step": 153, "loss": 0.649752140045166, "lce": 0.0, "lgen": 0.0, "lts": 0.055062681436538696}, {"step": 154, "loss": 0.26364290714263916, "lce": 0.0, "lgen": 0.0, "lts": 0.038594990968704224}, {"step": 155, "loss": 0.5131887793540955, "lce": 0.0, "lgen": 0.0, "lts": 0.04880562424659729}, {"step": 156, "loss": 0.3895303010940552, "lce": 0.0, "lgen": 0.0, "lts": 0.05665573477745056}, {"step": 157, "loss": 0.4593570828437805, "lce": 0.0, "lgen": 0.0, "lts": 0.04226626455783844}, {"step": 158, "loss": 0.2717948257923126, "lce": 0.0, "lgen": 0.0, "lts": 0.043872177600860596}, {"step": 159, "loss": 0.5956176519393921, "lce": 0.0, "lgen": 0.0, "lts": 0.04625299572944641}, {"step": 160, "loss": 0.4153735339641571, "lce": 0.0, "lgen": 0.0, "lts": 0.04441314935684204}, {"step": 161, "loss": 0.46592557430267334, "lce": 0.0, "lgen": 0.0, "lts": 0.04376760125160217}, {"step": 162, "loss": 0.2900693118572235, "lce": 0.0, "lgen": 0.0, "lts": 0.035647034645080566}, {"step": 163, "loss": 0.5923764705657959, "lce": 0.0, "lgen": 0.0, "lts": 0.04938891530036926}, {"step": 164, "loss": 0.4054659903049469, "lce": 0.0, "lgen": 0.0, "lts": 0.05224040150642395}, {"step": 165, "loss": 0.7396280765533447, "lce": 0.0, "lgen": 0.0, "lts": 0.05416722595691681}, {"step": 166, "loss": 0.43460899591445923, "lce": 0.0, "lgen": 0.0, "lts": 0.050557270646095276}, {"step": 167, "loss": 0.6247192025184631, "lce": 0.0, "lgen": 0.0, "lts": 0.04853050410747528}, {"step": 168, "loss": 0.3287210464477539, "lce": 0.0, "lgen": 0.0, "lts": 0.045322299003601074}, {"step": 169, "loss": 0.5996208190917969, "lce": 0.0, "lgen": 0.0, "lts": 0.05817493796348572}, {"step": 170, "loss": 0.3202337324619293, "lce": 0.0, "lgen": 0.0, "lts": 0.043233513832092285}, {"step": 171, "loss": 0.6401004195213318, "lce": 0.0, "lgen": 0.0, "lts": 0.05729542672634125}, {"step": 172, "loss": 0.32129281759262085, "lce": 0.0, "lgen": 0.0, "lts": 0.04986700415611267}, {"step": 173, "loss": 0.6127773523330688, "lce": 0.0, "lgen": 0.0, "lts": 0.055774226784706116}, {"step": 174, "loss": 0.35884952545166016, "lce": 0.0, "lgen": 0.0, "lts": 0.050218671560287476}, {"step": 175, "loss": 0.534093976020813, "lce": 0.0, "lgen": 0.0, "lts": 0.05866095423698425}, {"step": 176, "loss": 0.32738956809043884, "lce": 0.0, "lgen": 0.0, "lts": 0.040567100048065186}, {"step": 177, "loss": 0.5521131753921509, "lce": 0.0, "lgen": 0.0, "lts": 0.0495319589972496}, {"step": 178, "loss": 0.26264530420303345, "lce": 0.0, "lgen": 0.0, "lts": 0.03346695005893707}, {"step": 179, "loss": 0.38471049070358276, "lce": 0.0, "lgen": 0.0, "lts": 0.03990732133388519}, {"step": 180, "loss": 0.3611783981323242, "lce": 0.0, "lgen": 0.0, "lts": 0.05048392713069916}, {"step": 181, "loss": 0.44967877864837646, "lce": 0.0, "lgen": 0.0, "lts": 0.045359402894973755}, {"step": 182, "loss": 0.4338880479335785, "lce": 0.0, "lgen": 0.0, "lts": 0.05133374035358429}, {"step": 183, "loss": 0.5102113485336304, "lce": 0.0, "lgen": 0.0, "lts": 0.050054505467414856}, {"step": 184, "loss": 0.3939969539642334, "lce": 0.0, "lgen": 0.0, "lts": 0.044341474771499634}, {"step": 185, "loss": 0.41801196336746216, "lce": 0.0, "lgen": 0.0, "lts": 0.05020807683467865}, {"step": 186, "loss": 0.3069412112236023, "lce": 0.0, "lgen": 0.0, "lts": 0.047896042466163635}, {"step": 187, "loss": 0.4692491292953491, "lce": 0.0, "lgen": 0.0, "lts": 0.047530874609947205}, {"step": 188, "loss": 0.3570277690887451, "lce": 0.0, "lgen": 0.0, "lts": 0.04704795405268669}, {"step": 189, "loss": 0.3496771454811096, "lce": 0.0, "lgen": 0.0, "lts": 0.035211384296417236}, {"step": 190, "loss": 0.3694356083869934, "lce": 0.0, "lgen": 0.0, "lts": 0.04070194065570831}, {"step": 191, "loss": 0.4659930467605591, "lce": 0.0, "lgen": 0.0, "lts": 0.04384883493185043}, {"step": 192, "loss": 0.33064132928848267, "lce": 0.0, "lgen": 0.0, "lts": 0.038689568638801575}, {"step": 193, "loss": 0.48109015822410583, "lce": 0.0, "lgen": 0.0, "lts": 0.049077242612838745}, {"step": 194, "loss": 0.2720203697681427, "lce": 0.0, "lgen": 0.0, "lts": 0.04312078282237053}, {"step": 195, "loss": 0.4144325852394104, "lce": 0.0, "lgen": 0.0, "lts": 0.04180857539176941}, {"step": 196, "loss": 0.3911369740962982, "lce": 0.0, "lgen": 0.0, "lts": 0.054920926690101624}, {"step": 197, "loss": 0.4906545877456665, "lce": 0.0, "lgen": 0.0, "lts": 0.0495048463344574}, {"step": 198, "loss": 0.28382593393325806, "lce": 0.0, "lgen": 0.0, "lts": 0.04691864550113678}, {"step": 199, "loss": 0.6900931000709534, "lce": 0.0, "lgen": 0.0, "lts": 0.05205075442790985}] \ No newline at end of file