diff options
Diffstat (limited to 'results/oral_a_v3_calibration_gate.json')
| -rw-r--r-- | results/oral_a_v3_calibration_gate.json | 115 |
1 files changed, 115 insertions, 0 deletions
diff --git a/results/oral_a_v3_calibration_gate.json b/results/oral_a_v3_calibration_gate.json new file mode 100644 index 0000000..c0364bc --- /dev/null +++ b/results/oral_a_v3_calibration_gate.json @@ -0,0 +1,115 @@ +{ + "checks": { + "all_four_records_finite": true, + "v3_all_layer_at_least_0.05": true, + "v3_candidate_selected": true, + "v3_early_gain_over_v2_at_least_0.01": false, + "v3_early_third_at_least_0.01": false, + "v3_reaches_60pct_of_family_oracle": false + }, + "confirmation_test_seeds_touched": false, + "family_oracle_early_third": 0.02396580002561188, + "matched_v2_reference": { + "calibration_mode": "channel_subspace", + "eta_A": 0.01, + "finite": true, + "metric_space": "channel_basis_moments", + "metrics": { + "all_layer_alignment": 0.052739956808325494, + "early_third_alignment": 0.007209058462952574, + "mean_calibration_mse": 0.2708950854477958, + "mean_parameter_update_rms": 0.011981565658686305, + "mean_prediction_target_cosine": 0.00018159585958168355, + "mean_target_power": 0.2708926473589623 + }, + "path": "results/oral_a_v3_calibration/channel_subspace_etaA0.01.json", + "source_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1" + }, + "protocol": "oral_a_v3_vectorizer_causal_capture_v1", + "review_score_after": 5, + "review_score_before": 5, + "rows": [ + { + "calibration_mode": "channel_subspace", + "eta_A": 0.01, + "finite": true, + "metric_space": "channel_basis_moments", + "metrics": { + "all_layer_alignment": 0.052739956808325494, + "early_third_alignment": 0.007209058462952574, + "mean_calibration_mse": 0.2708950854477958, + "mean_parameter_update_rms": 0.011981565658686305, + "mean_prediction_target_cosine": 0.00018159585958168355, + "mean_target_power": 0.2708926473589623 + }, + "path": "results/oral_a_v3_calibration/channel_subspace_etaA0.01.json", + "source_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1" + }, + { + "calibration_mode": "vectorizer_subspace", + "eta_A": 0.01, + "finite": true, + "metric_space": "vectorizer_parameter_gradients", + "metrics": { + "all_layer_alignment": 0.0625791079364717, + "early_third_alignment": 0.007139206010227402, + "mean_calibration_mse": 0.00019177845804523746, + "mean_parameter_update_rms": 0.010982968905010668, + "mean_prediction_target_cosine": 0.0018218688400943384, + "mean_target_power": 0.00019176158875808158 + }, + "path": "results/oral_a_v3_calibration/vectorizer_subspace_etaA0.01.json", + "source_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1" + }, + { + "calibration_mode": "vectorizer_subspace", + "eta_A": 0.1, + "finite": true, + "metric_space": "vectorizer_parameter_gradients", + "metrics": { + "all_layer_alignment": 0.0309489116587333, + "early_third_alignment": 0.004803654310914378, + "mean_calibration_mse": 0.0001923398035258008, + "mean_parameter_update_rms": 0.011050459120615532, + "mean_prediction_target_cosine": 0.0014602501420039524, + "mean_target_power": 0.00019176158875808158 + }, + "path": "results/oral_a_v3_calibration/vectorizer_subspace_etaA0.1.json", + "source_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1" + }, + { + "calibration_mode": "vectorizer_subspace", + "eta_A": 1.0, + "finite": true, + "metric_space": "vectorizer_parameter_gradients", + "metrics": { + "all_layer_alignment": 0.006801062087393611, + "early_third_alignment": 0.002233794856389674, + "mean_calibration_mse": 0.00019906028706469792, + "mean_parameter_update_rms": 0.01158272062540019, + "mean_prediction_target_cosine": -0.0001920852658946125, + "mean_target_power": 0.00019176158875808158 + }, + "path": "results/oral_a_v3_calibration/vectorizer_subspace_etaA1.0.json", + "source_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1" + } + ], + "score_change_rule": "mechanics/calibration alone cannot raise score", + "selected_v3": { + "calibration_mode": "vectorizer_subspace", + "eta_A": 0.01, + "finite": true, + "metric_space": "vectorizer_parameter_gradients", + "metrics": { + "all_layer_alignment": 0.0625791079364717, + "early_third_alignment": 0.007139206010227402, + "mean_calibration_mse": 0.00019177845804523746, + "mean_parameter_update_rms": 0.010982968905010668, + "mean_prediction_target_cosine": 0.0018218688400943384, + "mean_target_power": 0.00019176158875808158 + }, + "path": "results/oral_a_v3_calibration/vectorizer_subspace_etaA0.01.json", + "source_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1" + }, + "status": "failed" +} |
