gloamxun/modeling_zhaocui
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Complete standalone final deliverable and unaligned Q2 results

Browse Source
This commit is contained in:
gloamxun
2026-09-25 22:22:37 +08:00
parent c6b018e5d0
commit adc9c2064b
267 changed files with 15479 additions and 7976 deletions
Download Patch File Download Diff File Expand all files Collapse all files
math/Q1/results/unified_adapter/equivalence_report.json
+68
View File
@@ -0,0 +1,68 @@
{
"comparison": "SHA-256 of full float32 feature arrays and boolean masks against frozen old adapter output",
"splits": {
"train": {
"samples": 3395,
"exact_feature_equivalence": {
"text": true,
"audio": true,
"vision": true
},
"exact_mask_equivalence": true,
"old_feature_sha256": {
"text": "7dd4282937b91f5f654ab1aee176df729c0e6bd2499c5c7a3072cff459ce1ae3",
"audio": "44a746e4b03bed665537f124544df8331fe53d33a639f3edcb39cb5bcc2a96e0",
"vision": "516a29f75c4c251c1cb1bcb2eef58d4bfd7b4d27c96badc1023f4a06f15d95b8"
},
"new_feature_sha256": {
"text": "7dd4282937b91f5f654ab1aee176df729c0e6bd2499c5c7a3072cff459ce1ae3",
"audio": "44a746e4b03bed665537f124544df8331fe53d33a639f3edcb39cb5bcc2a96e0",
"vision": "516a29f75c4c251c1cb1bcb2eef58d4bfd7b4d27c96badc1023f4a06f15d95b8"
},
"old_mask_sha256": "8609e08eb50aff524442bef5acfc1a7dfa201819486a64e00cd6d34f2be34f3a",
"new_mask_sha256": "8609e08eb50aff524442bef5acfc1a7dfa201819486a64e00cd6d34f2be34f3a"
},
"valid": {
"samples": 728,
"exact_feature_equivalence": {
"text": true,
"audio": true,
"vision": true
},
"exact_mask_equivalence": true,
"old_feature_sha256": {
"text": "16bdef07347baf00985e7964301eef2272701716220e846c415651806bb5eb0a",
"audio": "b7d6f3092d9ddbcd70afe4b0ecff0490181a83a308a67246613185167cb08e87",
"vision": "fbd9f93e8cae02de59e5d513c4c057d759db626894d298124575bdf18863a024"
},
"new_feature_sha256": {
"text": "16bdef07347baf00985e7964301eef2272701716220e846c415651806bb5eb0a",
"audio": "b7d6f3092d9ddbcd70afe4b0ecff0490181a83a308a67246613185167cb08e87",
"vision": "fbd9f93e8cae02de59e5d513c4c057d759db626894d298124575bdf18863a024"
},
"old_mask_sha256": "adcd9b7bac94c6523b571c7c60eb3e4ad0efc820062bd528b102a4239aaf2325",
"new_mask_sha256": "adcd9b7bac94c6523b571c7c60eb3e4ad0efc820062bd528b102a4239aaf2325"
},
"test": {
"samples": 727,
"exact_feature_equivalence": {
"text": true,
"audio": true,
"vision": true
},
"exact_mask_equivalence": true,
"old_feature_sha256": {
"text": "6cc0c3ee828ab2f322318011b10764aabca2f5d2bcba40abddd714529928a05a",
"audio": "d64dca47fffbbd00a2d8f5628f05efdb9b8743ff51187b1c4cac58ccf3f5a50b",
"vision": "2a8b12d9c3a0d57f8f14bb830dbd2f8acdcfa147f55c50927798692ae6630d6d"
},
"new_feature_sha256": {
"text": "6cc0c3ee828ab2f322318011b10764aabca2f5d2bcba40abddd714529928a05a",
"audio": "d64dca47fffbbd00a2d8f5628f05efdb9b8743ff51187b1c4cac58ccf3f5a50b",
"vision": "2a8b12d9c3a0d57f8f14bb830dbd2f8acdcfa147f55c50927798692ae6630d6d"
},
"old_mask_sha256": "85706ad6842e8a0642bf5d24642463d0488a6cba55848a2276e397e8592604d6",
"new_mask_sha256": "85706ad6842e8a0642bf5d24642463d0488a6cba55848a2276e397e8592604d6"
}
}
}
math/Q1/results/unified_adapter/full_audit.json
+503
View File
@@ -0,0 +1,503 @@
{
"adapter": "q1-unified-1",
"official_input": "E题数据/附件2-数据集特征文件/unaligned_50.pkl",
"relative": {
"train": {
"samples": 3395,
"coordinate_modes": {
"relative": 3395
},
"feature_shapes": {
"text": {
"[50, 768]": 3395
},
"audio": {
"[50, 74]": 3395
},
"vision": {
"[50, 35]": 3395
}
},
"source_length": {
"text": {
"count": 3395,
"min": 3.0,
"p25": 16.0,
"median": 22.0,
"p75": 32.0,
"max": 50.0,
"mean": 24.645655375552284
},
"audio": {
"count": 3395,
"min": 8.0,
"p25": 86.0,
"median": 127.0,
"p75": 183.0,
"max": 500.0,
"mean": 147.28836524300442
},
"vision": {
"count": 3395,
"min": 1.0,
"p25": 61.0,
"median": 93.0,
"p75": 135.0,
"max": 500.0,
"mean": 107.47304860088366
}
},
"source_length_vs_K": {
"text": {
"L<K": 3142,
"L=K": 253
},
"audio": {
"L>K": 3173,
"L<K": 209,
"L=K": 13
},
"vision": {
"L>K": 2797,
"L<K": 573,
"L=K": 25
}
},
"observed_target_bins_per_sample": {
"text": {
"count": 3395,
"min": 50.0,
"p25": 50.0,
"median": 50.0,
"p75": 50.0,
"max": 50.0,
"mean": 50.0
},
"audio": {
"count": 3395,
"min": 50.0,
"p25": 50.0,
"median": 50.0,
"p75": 50.0,
"max": 50.0,
"mean": 50.0
},
"vision": {
"count": 3395,
"min": 0.0,
"p25": 50.0,
"median": 50.0,
"p75": 50.0,
"max": 50.0,
"mean": 48.10073637702504
}
},
"coverage_per_target_bin": {
"text": {
"count": 169750,
"min": 1.0,
"p25": 1.0,
"median": 1.0,
"p75": 1.0,
"max": 1.0,
"mean": 1.0
},
"audio": {
"count": 169750,
"min": 1.0,
"p25": 1.0,
"median": 1.0,
"p75": 1.0,
"max": 1.0,
"mean": 1.0
},
"vision": {
"count": 169750,
"min": 0.0,
"p25": 1.0,
"median": 1.0,
"p75": 1.0,
"max": 1.0,
"mean": 0.9540337704196024
}
},
"text_nonzero_rows_outside_attention": 86078,
"length_conflict_samples": {
"text": 0,
"audio": 0,
"vision": 618
},
"tail_ambiguous_samples": 618,
"all_missing_target_bins": {
"text": 0,
"audio": 0,
"vision": 6448
},
"all_missing_modality_samples": {
"text": 0,
"audio": 0,
"vision": 30
},
"nonfinite_output_values": 0,
"max_provenance_row_sum_error": 1.1920928955078125e-07,
"sha256": {
"text": "7dd4282937b91f5f654ab1aee176df729c0e6bd2499c5c7a3072cff459ce1ae3",
"audio": "44a746e4b03bed665537f124544df8331fe53d33a639f3edcb39cb5bcc2a96e0",
"vision": "516a29f75c4c251c1cb1bcb2eef58d4bfd7b4d27c96badc1023f4a06f15d95b8"
},
"legacy_sha256": {
"text": "7dd4282937b91f5f654ab1aee176df729c0e6bd2499c5c7a3072cff459ce1ae3",
"audio": "44a746e4b03bed665537f124544df8331fe53d33a639f3edcb39cb5bcc2a96e0",
"vision": "516a29f75c4c251c1cb1bcb2eef58d4bfd7b4d27c96badc1023f4a06f15d95b8"
},
"exact_feature_equivalence": {
"text": true,
"audio": true,
"vision": true
},
"mask_sha256": "8609e08eb50aff524442bef5acfc1a7dfa201819486a64e00cd6d34f2be34f3a",
"exact_mask_equivalence": true
},
"valid": {
"samples": 728,
"coordinate_modes": {
"relative": 728
},
"feature_shapes": {
"text": {
"[50, 768]": 728
},
"audio": {
"[50, 74]": 728
},
"vision": {
"[50, 35]": 728
}
},
"source_length": {
"text": {
"count": 728,
"min": 3.0,
"p25": 17.0,
"median": 23.5,
"p75": 33.0,
"max": 50.0,
"mean": 25.587912087912088
},
"audio": {
"count": 728,
"min": 12.0,
"p25": 98.75,
"median": 138.0,
"p75": 189.25,
"max": 500.0,
"mean": 154.11263736263737
},
"vision": {
"count": 728,
"min": 1.0,
"p25": 72.75,
"median": 102.0,
"p75": 141.25,
"max": 500.0,
"mean": 114.28846153846153
}
},
"source_length_vs_K": {
"text": {
"L<K": 681,
"L=K": 47
},
"audio": {
"L>K": 697,
"L<K": 27,
"L=K": 4
},
"vision": {
"L>K": 645,
"L<K": 77,
"L=K": 6
}
},
"observed_target_bins_per_sample": {
"text": {
"count": 728,
"min": 50.0,
"p25": 50.0,
"median": 50.0,
"p75": 50.0,
"max": 50.0,
"mean": 50.0
},
"audio": {
"count": 728,
"min": 50.0,
"p25": 50.0,
"median": 50.0,
"p75": 50.0,
"max": 50.0,
"mean": 50.0
},
"vision": {
"count": 728,
"min": 2.0,
"p25": 50.0,
"median": 50.0,
"p75": 50.0,
"max": 50.0,
"mean": 48.50961538461539
}
},
"coverage_per_target_bin": {
"text": {
"count": 36400,
"min": 1.0,
"p25": 1.0,
"median": 1.0,
"p75": 1.0,
"max": 1.0,
"mean": 1.0
},
"audio": {
"count": 36400,
"min": 1.0,
"p25": 1.0,
"median": 1.0,
"p75": 1.0,
"max": 1.0,
"mean": 1.0
},
"vision": {
"count": 36400,
"min": 0.0,
"p25": 1.0,
"median": 1.0,
"p75": 1.0,
"max": 1.0,
"mean": 0.9609031476994342
}
},
"text_nonzero_rows_outside_attention": 17772,
"length_conflict_samples": {
"text": 0,
"audio": 0,
"vision": 141
},
"tail_ambiguous_samples": 141,
"all_missing_target_bins": {
"text": 0,
"audio": 0,
"vision": 1085
},
"all_missing_modality_samples": {
"text": 0,
"audio": 0,
"vision": 0
},
"nonfinite_output_values": 0,
"max_provenance_row_sum_error": 1.1920928955078125e-07,
"sha256": {
"text": "16bdef07347baf00985e7964301eef2272701716220e846c415651806bb5eb0a",
"audio": "b7d6f3092d9ddbcd70afe4b0ecff0490181a83a308a67246613185167cb08e87",
"vision": "fbd9f93e8cae02de59e5d513c4c057d759db626894d298124575bdf18863a024"
},
"legacy_sha256": {
"text": "16bdef07347baf00985e7964301eef2272701716220e846c415651806bb5eb0a",
"audio": "b7d6f3092d9ddbcd70afe4b0ecff0490181a83a308a67246613185167cb08e87",
"vision": "fbd9f93e8cae02de59e5d513c4c057d759db626894d298124575bdf18863a024"
},
"exact_feature_equivalence": {
"text": true,
"audio": true,
"vision": true
},
"mask_sha256": "adcd9b7bac94c6523b571c7c60eb3e4ad0efc820062bd528b102a4239aaf2325",
"exact_mask_equivalence": true
},
"test": {
"samples": 727,
"coordinate_modes": {
"relative": 727
},
"feature_shapes": {
"text": {
"[50, 768]": 727
},
"audio": {
"[50, 74]": 727
},
"vision": {
"[50, 35]": 727
}
},
"source_length": {
"text": {
"count": 727,
"min": 4.0,
"p25": 16.0,
"median": 23.0,
"p75": 32.0,
"max": 50.0,
"mean": 25.184319119669876
},
"audio": {
"count": 727,
"min": 23.0,
"p25": 91.0,
"median": 135.0,
"p75": 190.0,
"max": 500.0,
"mean": 155.87757909215955
},
"vision": {
"count": 727,
"min": 1.0,
"p25": 65.0,
"median": 101.0,
"p75": 141.5,
"max": 500.0,
"mean": 114.78404401650619
}
},
"source_length_vs_K": {
"text": {
"L=K": 52,
"L<K": 675
},
"audio": {
"L>K": 681,
"L<K": 43,
"L=K": 3
},
"vision": {
"L>K": 615,
"L<K": 109,
"L=K": 3
}
},
"observed_target_bins_per_sample": {
"text": {
"count": 727,
"min": 50.0,
"p25": 50.0,
"median": 50.0,
"p75": 50.0,
"max": 50.0,
"mean": 50.0
},
"audio": {
"count": 727,
"min": 50.0,
"p25": 50.0,
"median": 50.0,
"p75": 50.0,
"max": 50.0,
"mean": 50.0
},
"vision": {
"count": 727,
"min": 0.0,
"p25": 50.0,
"median": 50.0,
"p75": 50.0,
"max": 50.0,
"mean": 48.189821182943604
}
},
"coverage_per_target_bin": {
"text": {
"count": 36350,
"min": 1.0,
"p25": 1.0,
"median": 1.0,
"p75": 1.0,
"max": 1.0,
"mean": 1.0
},
"audio": {
"count": 36350,
"min": 1.0,
"p25": 1.0,
"median": 1.0,
"p75": 1.0,
"max": 1.0,
"mean": 1.0
},
"vision": {
"count": 36350,
"min": 0.0,
"p25": 1.0,
"median": 1.0,
"p75": 1.0,
"max": 1.0,
"mean": 0.9549938173243645
}
},
"text_nonzero_rows_outside_attention": 18041,
"length_conflict_samples": {
"text": 0,
"audio": 0,
"vision": 131
},
"tail_ambiguous_samples": 131,
"all_missing_target_bins": {
"text": 0,
"audio": 0,
"vision": 1316
},
"all_missing_modality_samples": {
"text": 0,
"audio": 0,
"vision": 8
},
"nonfinite_output_values": 0,
"max_provenance_row_sum_error": 1.1920928955078125e-07,
"sha256": {
"text": "6cc0c3ee828ab2f322318011b10764aabca2f5d2bcba40abddd714529928a05a",
"audio": "d64dca47fffbbd00a2d8f5628f05efdb9b8743ff51187b1c4cac58ccf3f5a50b",
"vision": "2a8b12d9c3a0d57f8f14bb830dbd2f8acdcfa147f55c50927798692ae6630d6d"
},
"legacy_sha256": {
"text": "6cc0c3ee828ab2f322318011b10764aabca2f5d2bcba40abddd714529928a05a",
"audio": "d64dca47fffbbd00a2d8f5628f05efdb9b8743ff51187b1c4cac58ccf3f5a50b",
"vision": "2a8b12d9c3a0d57f8f14bb830dbd2f8acdcfa147f55c50927798692ae6630d6d"
},
"exact_feature_equivalence": {
"text": true,
"audio": true,
"vision": true
},
"mask_sha256": "85706ad6842e8a0642bf5d24642463d0488a6cba55848a2276e397e8592604d6",
"exact_mask_equivalence": true
}
},
"physical": {
"samples": 100,
"coordinate_modes": {
"physical": 100
},
"feature_shapes": {
"text": {
"[50, 768]": 100
},
"audio": {
"[50, 74]": 100
},
"vision": {
"[50, 35]": 100
}
},
"duration_s": {
"count": 100,
"min": 2.256999969482422,
"p25": 5.084147214889526,
"median": 6.722493410110474,
"p75": 8.725488424301147,
"max": 29.288021087646484,
"mean": 7.874980225563049
},
"nonfinite_output_values": 0,
"max_provenance_row_sum_error": 2.384185791015625e-07,
"stored_dense_0_1_s_views_untouched": true
}
}
math/Q1/results/unified_adapter/legacy_relative_baseline.json
+86
View File
@@ -0,0 +1,86 @@
{
"train": {
"sha256": {
"text": "7dd4282937b91f5f654ab1aee176df729c0e6bd2499c5c7a3072cff459ce1ae3",
"audio": "44a746e4b03bed665537f124544df8331fe53d33a639f3edcb39cb5bcc2a96e0",
"vision": "516a29f75c4c251c1cb1bcb2eef58d4bfd7b4d27c96badc1023f4a06f15d95b8"
},
"mask_sha256": "8609e08eb50aff524442bef5acfc1a7dfa201819486a64e00cd6d34f2be34f3a",
"audit": {
"method": "index_cell_overlap_on_independent_normalized_progress_axes",
"physical_time_alignment": false,
"samples": 3395,
"vision_length_conflict_samples": 618,
"vision_tail_ambiguous_samples": 618,
"nonzero_text_rows_outside_attention": 86078,
"observed_target_rows": {
"text": 169750,
"audio": 169750,
"vision": 163302
},
"mean_target_coverage": {
"text": 1.0,
"audio": 1.0,
"vision": 0.9540337701314328
},
"quality_fields_available": false,
"word_or_frame_timestamps_available": false
}
},
"valid": {
"sha256": {
"text": "16bdef07347baf00985e7964301eef2272701716220e846c415651806bb5eb0a",
"audio": "b7d6f3092d9ddbcd70afe4b0ecff0490181a83a308a67246613185167cb08e87",
"vision": "fbd9f93e8cae02de59e5d513c4c057d759db626894d298124575bdf18863a024"
},
"mask_sha256": "adcd9b7bac94c6523b571c7c60eb3e4ad0efc820062bd528b102a4239aaf2325",
"audit": {
"method": "index_cell_overlap_on_independent_normalized_progress_axes",
"physical_time_alignment": false,
"samples": 728,
"vision_length_conflict_samples": 141,
"vision_tail_ambiguous_samples": 141,
"nonzero_text_rows_outside_attention": 17772,
"observed_target_rows": {
"text": 36400,
"audio": 36400,
"vision": 35315
},
"mean_target_coverage": {
"text": 1.0,
"audio": 1.0,
"vision": 0.96090314748523
},
"quality_fields_available": false,
"word_or_frame_timestamps_available": false
}
},
"test": {
"sha256": {
"text": "6cc0c3ee828ab2f322318011b10764aabca2f5d2bcba40abddd714529928a05a",
"audio": "d64dca47fffbbd00a2d8f5628f05efdb9b8743ff51187b1c4cac58ccf3f5a50b",
"vision": "2a8b12d9c3a0d57f8f14bb830dbd2f8acdcfa147f55c50927798692ae6630d6d"
},
"mask_sha256": "85706ad6842e8a0642bf5d24642463d0488a6cba55848a2276e397e8592604d6",
"audit": {
"method": "index_cell_overlap_on_independent_normalized_progress_axes",
"physical_time_alignment": false,
"samples": 727,
"vision_length_conflict_samples": 131,
"vision_tail_ambiguous_samples": 131,
"nonzero_text_rows_outside_attention": 18041,
"observed_target_rows": {
"text": 36350,
"audio": 36350,
"vision": 35034
},
"mean_target_coverage": {
"text": 1.0,
"audio": 1.0,
"vision": 0.9549938172651288
},
"quality_fields_available": false,
"word_or_frame_timestamps_available": false
}
}
}
math/Q1/results/unified_adapter/q2_smoke.json
+80
View File
@@ -0,0 +1,80 @@
{
"train": {
"samples": 3395,
"feature_shapes": {
"text": [
3395,
50,
768
],
"audio": [
3395,
50,
74
],
"vision": [
3395,
50,
35
]
},
"mask_shape": [
3395,
50,
3
],
"labels_preserved": true
},
"valid": {
"samples": 728,
"feature_shapes": {
"text": [
728,
50,
768
],
"audio": [
728,
50,
74
],
"vision": [
728,
50,
35
]
},
"mask_shape": [
728,
50,
3
],
"labels_preserved": true
},
"test": {
"samples": 727,
"feature_shapes": {
"text": [
727,
50,
768
],
"audio": [
727,
50,
74
],
"vision": [
727,
50,
35
]
},
"mask_shape": [
727,
50,
3
],
"labels_preserved": true
}
}