Joey Eamigh 67beaede45
quantization + onnx sweeps
Phase 10.8: torchao/bnb quant sweep on iter1-independent. bf16 already
optimal; torchao int8-wo gives -19% VRAM at no F1 cost; all 4-bit
variants collapse (ModernBERT-large too quant-sensitive).

Phase 10.9: ONNX export + ORT eval. Legacy exporter only working path
(dynamo adds 56 Memcpy nodes); ORT fp32 -22% latency vs torch via
kernel fusion but bf16+flash-attn-2 still wins; fp16 broken on rotary;
dynamic int8 silently CPU-fallback + 0.5 F1 collapse.

Driver scripts wired to bun run py:quant / py:onnx; full reports at
results/eval/{quant,onnx}/REPORT.md.
2026-04-07 05:10:38 -04:00

297 lines
6.5 KiB
JSON

{
"GPT-5.4": {
"cat_macro_f1": 0.9336741161693523,
"cat_weighted_f1": 0.9343162998643407,
"cat_macro_precision": 0.93189297179766,
"cat_macro_recall": 0.9377918652022429,
"cat_mcc": 0.9226990724708704,
"cat_auc": 0.9920546854722492,
"cat_ece": 0.05388230005900064,
"cat_confusion_matrix": [
[
225,
0,
3,
0,
2,
0,
0
],
[
0,
85,
0,
0,
2,
1,
0
],
[
2,
0,
144,
1,
3,
0,
0
],
[
0,
0,
3,
131,
0,
2,
0
],
[
6,
1,
5,
19,
164,
1,
2
],
[
0,
3,
1,
8,
2,
207,
0
],
[
0,
0,
0,
0,
12,
0,
165
]
],
"cat_f1_BoardGov": 0.9719222462203023,
"cat_prec_BoardGov": 0.9656652360515021,
"cat_recall_BoardGov": 0.9782608695652174,
"cat_f1_Incident": 0.96045197740113,
"cat_prec_Incident": 0.9550561797752809,
"cat_recall_Incident": 0.9659090909090909,
"cat_f1_Manageme": 0.9411764705882353,
"cat_prec_Manageme": 0.9230769230769231,
"cat_recall_Manageme": 0.96,
"cat_f1_NoneOthe": 0.888135593220339,
"cat_prec_NoneOthe": 0.8238993710691824,
"cat_recall_NoneOthe": 0.9632352941176471,
"cat_f1_RiskMana": 0.856396866840731,
"cat_prec_RiskMana": 0.8864864864864865,
"cat_recall_RiskMana": 0.8282828282828283,
"cat_f1_Strategy": 0.9583333333333334,
"cat_prec_Strategy": 0.981042654028436,
"cat_recall_Strategy": 0.9366515837104072,
"cat_f1_Third-Pa": 0.9593023255813954,
"cat_prec_Third-Pa": 0.9880239520958084,
"cat_recall_Third-Pa": 0.9322033898305084,
"cat_kripp_alpha": 0.9223591517560865,
"spec_macro_f1": 0.8943486525770918,
"spec_weighted_f1": 0.9113685505226937,
"spec_macro_precision": 0.896720845083131,
"spec_macro_recall": 0.8926515273338829,
"spec_mcc": 0.8651595302642376,
"spec_auc": 0.9817804600696421,
"spec_ece": 0.07088303024570146,
"spec_confusion_matrix": [
[
579,
24,
12,
3
],
[
29,
130,
7,
2
],
[
11,
4,
190,
2
],
[
2,
1,
9,
195
]
],
"spec_f1_L1Generi": 0.9346246973365617,
"spec_prec_L1Generi": 0.9323671497584541,
"spec_recall_L1Generi": 0.9368932038834952,
"spec_f1_L2Domain": 0.7951070336391437,
"spec_prec_L2Domain": 0.8176100628930818,
"spec_recall_L2Domain": 0.7738095238095238,
"spec_f1_L3Firm-S": 0.8941176470588236,
"spec_prec_L3Firm-S": 0.8715596330275229,
"spec_recall_L3Firm-S": 0.9178743961352657,
"spec_f1_L4Quanti": 0.9535452322738386,
"spec_prec_L4Quanti": 0.9653465346534653,
"spec_recall_L4Quanti": 0.9420289855072463,
"spec_qwk": 0.9321211092744079,
"spec_mae": 0.11833333333333333,
"spec_kripp_alpha": 0.9170875429859872
},
"Opus-4.6": {
"cat_macro_f1": 0.922684387023173,
"cat_weighted_f1": 0.9216414809666168,
"cat_macro_precision": 0.9177680939029339,
"cat_macro_recall": 0.9316060900094703,
"cat_mcc": 0.909266938399113,
"cat_auc": 0.9939567083286731,
"cat_ece": 0.06541596949100496,
"cat_confusion_matrix": [
[
211,
0,
1,
1,
1,
0,
0
],
[
0,
78,
0,
0,
1,
0,
0
],
[
8,
0,
144,
1,
4,
0,
1
],
[
0,
0,
1,
138,
1,
1,
0
],
[
13,
0,
9,
14,
169,
1,
7
],
[
1,
11,
1,
4,
3,
208,
0
],
[
0,
0,
0,
1,
6,
1,
159
]
],
"cat_f1_BoardGov": 0.9440715883668904,
"cat_prec_BoardGov": 0.9055793991416309,
"cat_recall_BoardGov": 0.985981308411215,
"cat_f1_Incident": 0.9285714285714286,
"cat_prec_Incident": 0.8764044943820225,
"cat_recall_Incident": 0.9873417721518988,
"cat_f1_Manageme": 0.9171974522292994,
"cat_prec_Manageme": 0.9230769230769231,
"cat_recall_Manageme": 0.9113924050632911,
"cat_f1_NoneOthe": 0.92,
"cat_prec_NoneOthe": 0.8679245283018868,
"cat_recall_NoneOthe": 0.9787234042553191,
"cat_f1_RiskMana": 0.8492462311557789,
"cat_prec_RiskMana": 0.9135135135135135,
"cat_recall_RiskMana": 0.7934272300469484,
"cat_f1_Strategy": 0.9476082004555809,
"cat_prec_Strategy": 0.985781990521327,
"cat_recall_Strategy": 0.9122807017543859,
"cat_f1_Third-Pa": 0.9520958083832335,
"cat_prec_Third-Pa": 0.9520958083832335,
"cat_recall_Third-Pa": 0.9520958083832335,
"cat_kripp_alpha": 0.908575631724203,
"spec_macro_f1": 0.8825095464914274,
"spec_weighted_f1": 0.8996514471183623,
"spec_macro_precision": 0.8846890964606792,
"spec_macro_recall": 0.8850552454475074,
"spec_mcc": 0.8488763096810703,
"spec_auc": 0.9736482774372809,
"spec_ece": 0.08238246644536655,
"spec_confusion_matrix": [
[
566,
31,
7,
1
],
[
22,
118,
3,
2
],
[
33,
10,
207,
10
],
[
0,
0,
1,
189
]
],
"spec_f1_L1Generi": 0.9233278955954323,
"spec_prec_L1Generi": 0.9114331723027376,
"spec_recall_L1Generi": 0.9355371900826446,
"spec_f1_L2Domain": 0.7763157894736842,
"spec_prec_L2Domain": 0.7421383647798742,
"spec_recall_L2Domain": 0.8137931034482758,
"spec_f1_L3Firm-S": 0.8661087866108786,
"spec_prec_L3Firm-S": 0.9495412844036697,
"spec_recall_L3Firm-S": 0.7961538461538461,
"spec_f1_L4Quanti": 0.9642857142857143,
"spec_prec_L4Quanti": 0.9356435643564357,
"spec_recall_L4Quanti": 0.9947368421052631,
"spec_qwk": 0.9223702541559166,
"spec_mae": 0.13666666666666666,
"spec_kripp_alpha": 0.9059072309806726
},
"_runtime": {
"encoder_mb": 1579.127296,
"ms_per_sample": 16.293709366727853,
"throughput_per_s": 61.37337898281309,
"peak_vram_mb": 3503.53369140625,
"build_s": 0.6251941699883901
}
}