{ "generated": "2026-08-20 11:17:21", "rule": "macro and corporate are carried side by side as separate columns and are NEVER averaged", "note": "Ranges over a handful of seeds. No significance test, no p-value.", "seeds": [ 42, 1, 2 ], "tolerance": 0.01, "precision": { "fp16": true, "bf16": false, "reason": "NVIDIA GeForce GTX 1660 Ti sm_75 no native bf16" }, "metrics": { "macro_f1": { "name": "macro real held-out F1", "units": "pts", "scale": 100.0 }, "corp_f1": { "name": "corporate F1", "units": "pts", "scale": 100.0 }, "probe_acc": { "name": "probe accuracy", "units": "pts", "scale": 100.0 }, "pairs_solved": { "name": "minimal pairs solved", "units": "pairs", "scale": 1.0 }, "agree_acc": { "name": "polarity-agreeing probe acc", "units": "pts", "scale": 100.0 }, "pb_f1": { "name": "PhraseBank F1", "units": "pts", "scale": 100.0 } }, "configs": [ { "name": "u4@20k", "macro_share": 0.65, "unfreeze": 4, "total": 20000, "epochs": 16, "criterion": "macro_floored", "mix_policy": "fixed_total" }, { "name": "u6@32k", "macro_share": 0.65, "unfreeze": 6, "total": 32000, "epochs": 16, "criterion": "macro_floored", "mix_policy": "fixed_total" } ], "per_seed": [ { "config": "u4@20k", "seed": 42, "status": "LOADED", "dir": "models/mix65_unfreeze4_macro_floored_s42", "how": "run.json match in mix65_unfreeze4_macro_floored_s42", "metrics": { "macro_f1": 67.59165949395553, "corp_f1": 81.38670066473745, "probe_acc": 79.16666666666666, "pairs_solved": 12.0, "agree_acc": 57.14285714285714, "pb_f1": 86.91964125668869 } }, { "config": "u4@20k", "seed": 1, "status": "TRAINED", "dir": "models/rep_u4_20k_s1", "how": "trained by this script, 102.94 min", "metrics": { "macro_f1": 67.28569186992823, "corp_f1": 82.06353062408495, "probe_acc": 70.83333333333334, "pairs_solved": 7.0, "agree_acc": 50.0, "pb_f1": 85.065296617682 } }, { "config": "u4@20k", "seed": 2, "status": "TRAINED", "dir": "models/rep_u4_20k_s2", "how": "trained by this script, 136.91 min", "metrics": { "macro_f1": 67.41373179920018, "corp_f1": 82.31776419246067, "probe_acc": 64.58333333333334, "pairs_solved": 5.0, "agree_acc": 57.14285714285714, "pb_f1": 73.63131856850693 } }, { "config": "u6@32k", "seed": 42, "status": "LOADED", "dir": "models/mix65_unfreeze6_full32k", "how": "run.json match in mix65_unfreeze6_full32k", "metrics": { "macro_f1": 68.81987346760383, "corp_f1": 83.97251903033337, "probe_acc": 77.08333333333334, "pairs_solved": 8.0, "agree_acc": 64.28571428571429, "pb_f1": 73.07008355119325 } }, { "config": "u6@32k", "seed": 1, "status": "TRAINED", "dir": "models/rep_u6_32k_s1", "how": "trained by this script, 205.69 min", "metrics": { "macro_f1": 69.3386664919747, "corp_f1": 82.66029840632898, "probe_acc": 81.25, "pairs_solved": 11.0, "agree_acc": 57.14285714285714, "pb_f1": 65.74260663190499 } }, { "config": "u6@32k", "seed": 2, "status": "TRAINED", "dir": "models/rep_u6_32k_s2", "how": "trained by this script, 246.78 min", "metrics": { "macro_f1": 69.728009428257, "corp_f1": 84.15625933222256, "probe_acc": 81.25, "pairs_solved": 10.0, "agree_acc": 64.28571428571429, "pb_f1": 69.87313438147625 } } ], "vanilla": { "macro_f1": 39.03300821786394, "corp_f1": 70.23790161183014, "probe_acc": 41.66666666666667, "pairs_solved": 6.0, "agree_acc": 71.42857142857143, "pb_f1": 96.24820403323632 }, "aggregate": { "u4@20k": { "macro_f1": { "n": 3, "mean": 67.43036105436131, "std": 0.15366016345702269, "min": 67.28569186992823, "max": 67.59165949395553, "range": 0.3059676240273035 }, "corp_f1": { "n": 3, "mean": 81.9226651604277, "std": 0.4812505920023736, "min": 81.38670066473745, "max": 82.31776419246067, "range": 0.9310635277232251 }, "probe_acc": { "n": 3, "mean": 71.52777777777779, "std": 7.316426217258837, "min": 64.58333333333334, "max": 79.16666666666666, "range": 14.583333333333314 }, "pairs_solved": { "n": 3, "mean": 8.0, "std": 3.605551275463989, "min": 5.0, "max": 12.0, "range": 7.0 }, "agree_acc": { "n": 3, "mean": 54.76190476190476, "std": 4.12393049421161, "min": 50.0, "max": 57.14285714285714, "range": 7.142857142857139 }, "pb_f1": { "n": 3, "mean": 81.8720854809592, "std": 7.196688682239868, "min": 73.63131856850693, "max": 86.91964125668869, "range": 13.288322688181765 } }, "u6@32k": { "macro_f1": { "n": 3, "mean": 69.29551646261184, "std": 0.4556030888101787, "min": 68.81987346760383, "max": 69.728009428257, "range": 0.9081359606531691 }, "corp_f1": { "n": 3, "mean": 83.59635892296164, "std": 0.815841340417078, "min": 82.66029840632898, "max": 84.15625933222256, "range": 1.4959609258935842 }, "probe_acc": { "n": 3, "mean": 79.86111111111111, "std": 2.405626121623435, "min": 77.08333333333334, "max": 81.25, "range": 4.166666666666657 }, "pairs_solved": { "n": 3, "mean": 9.666666666666666, "std": 1.5275252316519468, "min": 8.0, "max": 11.0, "range": 3.0 }, "agree_acc": { "n": 3, "mean": 61.904761904761905, "std": 4.123930494211619, "min": 57.14285714285714, "max": 64.28571428571429, "range": 7.142857142857153 }, "pb_f1": { "n": 3, "mean": 69.56194152152483, "std": 3.673637195986982, "min": 65.74260663190499, "max": 73.07008355119325, "range": 7.327476919288259 } } }, "comparisons": [ { "a": "u4@20k", "b": "u6@32k", "metric": "macro_f1", "units": "pts", "gap": 1.86515540825053, "spread": 0.9081359606531691, "half_spread": 0.4540679803265846, "n_seeds": 3, "leader": "u6@32k", "ranges_overlap": false, "verdict": "RESOLVED", "a_min": 67.28569186992823, "a_max": 67.59165949395553, "b_min": 68.81987346760383, "b_max": 69.728009428257 }, { "a": "u4@20k", "b": "u6@32k", "metric": "corp_f1", "units": "pts", "gap": 1.6736937625339436, "spread": 1.4959609258935842, "half_spread": 0.7479804629467921, "n_seeds": 3, "leader": "u6@32k", "ranges_overlap": false, "verdict": "RESOLVED", "a_min": 81.38670066473745, "a_max": 82.31776419246067, "b_min": 82.66029840632898, "b_max": 84.15625933222256 }, { "a": "u4@20k", "b": "u6@32k", "metric": "probe_acc", "units": "pts", "gap": 8.333333333333329, "spread": 14.583333333333314, "half_spread": 7.291666666666657, "n_seeds": 3, "leader": null, "ranges_overlap": true, "verdict": "NOT resolved", "a_min": 64.58333333333334, "a_max": 79.16666666666666, "b_min": 77.08333333333334, "b_max": 81.25 }, { "a": "u4@20k", "b": "u6@32k", "metric": "pairs_solved", "units": "pairs", "gap": 1.666666666666666, "spread": 7.0, "half_spread": 3.5, "n_seeds": 3, "leader": null, "ranges_overlap": true, "verdict": "NOT resolved", "a_min": 5.0, "a_max": 12.0, "b_min": 8.0, "b_max": 11.0 }, { "a": "u4@20k", "b": "u6@32k", "metric": "agree_acc", "units": "pts", "gap": 7.142857142857146, "spread": 7.142857142857153, "half_spread": 3.5714285714285765, "n_seeds": 3, "leader": null, "ranges_overlap": true, "verdict": "NOT resolved", "a_min": 50.0, "a_max": 57.14285714285714, "b_min": 57.14285714285714, "b_max": 64.28571428571429 }, { "a": "u4@20k", "b": "u6@32k", "metric": "pb_f1", "units": "pts", "gap": 12.31014395943437, "spread": 13.288322688181765, "half_spread": 6.644161344090882, "n_seeds": 3, "leader": null, "ranges_overlap": false, "verdict": "NOT resolved", "a_min": 73.63131856850693, "a_max": 86.91964125668869, "b_min": 65.74260663190499, "b_max": 73.07008355119325 } ], "unrankable_metrics": [ "probe_acc", "pairs_solved", "agree_acc", "pb_f1" ] }