Record phase-aware telemetry pilot result
This commit is contained in:
@@ -0,0 +1,49 @@
|
||||
{
|
||||
"completed_sessions": 0,
|
||||
"failures": [
|
||||
{
|
||||
"failure": "TimeoutError('client timeout: tp4_mns16 high')",
|
||||
"session": "rep1-mns16"
|
||||
}
|
||||
],
|
||||
"gpu_hours_total": 1.3580546813540988,
|
||||
"hard_cap_h20_hours": 8.0,
|
||||
"schema": "intervention-response-phase-aware-pilot-state-v2",
|
||||
"sessions": {
|
||||
"rep1-mns16": {
|
||||
"burnin": {
|
||||
"elapsed_s": 64.469448031,
|
||||
"feasible": false,
|
||||
"pass_rate": 0.5137254901960784
|
||||
},
|
||||
"failure": "TimeoutError('client timeout: tp4_mns16 high')",
|
||||
"gpu_hours": 1.3580546813540988,
|
||||
"mns": 16,
|
||||
"replicate": 1,
|
||||
"runs": [
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 301.114789132,
|
||||
"feasible": true,
|
||||
"level": "low",
|
||||
"offered_req_s_per_gpu": 1.5,
|
||||
"pass_rate": 1.0,
|
||||
"selected_count": 1800
|
||||
},
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 313.040655133,
|
||||
"feasible": false,
|
||||
"level": "mid",
|
||||
"offered_req_s_per_gpu": 2.125,
|
||||
"pass_rate": 0.5631372549019608,
|
||||
"selected_count": 2550
|
||||
}
|
||||
],
|
||||
"started_at": 1784021277.1191542,
|
||||
"status": "failed"
|
||||
}
|
||||
},
|
||||
"started_at": 1784021276.8224819,
|
||||
"status": "failed"
|
||||
}
|
||||
16451
runs/intervention-response-v2/pilot-audit-v3.json
Normal file
16451
runs/intervention-response-v2/pilot-audit-v3.json
Normal file
File diff suppressed because it is too large
Load Diff
342
runs/intervention-response-v2/pilot-controller-state-v3.json
Normal file
342
runs/intervention-response-v2/pilot-controller-state-v3.json
Normal file
@@ -0,0 +1,342 @@
|
||||
{
|
||||
"completed_at": 1784027453.4005148,
|
||||
"completed_sessions": 6,
|
||||
"failures": [],
|
||||
"gpu_hours_total": 5.092428478929731,
|
||||
"hard_cap_h20_hours": 6.641945318645901,
|
||||
"schema": "intervention-response-phase-aware-pilot-state-v3",
|
||||
"sessions": {
|
||||
"rep1-mns16": {
|
||||
"burnin": {
|
||||
"elapsed_s": 64.194648239,
|
||||
"feasible": false,
|
||||
"pass_rate": 0.5235294117647059
|
||||
},
|
||||
"completed_at": 1784023620.6911042,
|
||||
"gpu_hours": 0.856446467505561,
|
||||
"mns": 16,
|
||||
"replicate": 1,
|
||||
"runs": [
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 301.068878512,
|
||||
"feasible": true,
|
||||
"level": "low",
|
||||
"offered_req_s_per_gpu": 1.5,
|
||||
"pass_rate": 1.0,
|
||||
"selected_count": 1800
|
||||
},
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 313.268231477,
|
||||
"feasible": false,
|
||||
"level": "mid",
|
||||
"offered_req_s_per_gpu": 2.125,
|
||||
"pass_rate": 0.5603921568627451,
|
||||
"selected_count": 2550
|
||||
}
|
||||
],
|
||||
"started_at": 1784022846.257515,
|
||||
"status": "complete",
|
||||
"validation": {
|
||||
"accounting_mode": "graceful-footer",
|
||||
"cell": "tp4_mns16",
|
||||
"invariants": {
|
||||
"anchor_intervals_present": true,
|
||||
"compile_capture_pre_ready": true,
|
||||
"encoded_balanced": true,
|
||||
"footer_sidecar_agrees": true,
|
||||
"last_step_matches": true,
|
||||
"layer1_contiguous": true,
|
||||
"layer1_zero_drops": true,
|
||||
"one_footer_last": true,
|
||||
"one_ready_marker": true,
|
||||
"sidecar_final": true,
|
||||
"warmup_exact_16": true,
|
||||
"warmup_long": true,
|
||||
"written_matches_records": true
|
||||
},
|
||||
"layer1_records": 60017,
|
||||
"post_ready_capture_events": [],
|
||||
"stream": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/runs/pilot/sessions/rep1-mns16/opprof/opprof-v1-dp0-pid458427-1784022917661752826.jsonl"
|
||||
}
|
||||
},
|
||||
"rep1-mns64": {
|
||||
"burnin": {
|
||||
"elapsed_s": 60.79926316,
|
||||
"feasible": true,
|
||||
"pass_rate": 1.0
|
||||
},
|
||||
"completed_at": 1784024382.2164423,
|
||||
"gpu_hours": 0.8415956518385146,
|
||||
"mns": 64,
|
||||
"replicate": 1,
|
||||
"runs": [
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 301.022700013,
|
||||
"feasible": true,
|
||||
"level": "low",
|
||||
"offered_req_s_per_gpu": 1.5,
|
||||
"pass_rate": 1.0,
|
||||
"selected_count": 1800
|
||||
},
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 301.100993458,
|
||||
"feasible": true,
|
||||
"level": "mid",
|
||||
"offered_req_s_per_gpu": 2.125,
|
||||
"pass_rate": 1.0,
|
||||
"selected_count": 2550
|
||||
}
|
||||
],
|
||||
"started_at": 1784023620.9865165,
|
||||
"status": "complete",
|
||||
"validation": {
|
||||
"accounting_mode": "graceful-footer",
|
||||
"cell": "tp4_mns64",
|
||||
"invariants": {
|
||||
"anchor_intervals_present": true,
|
||||
"compile_capture_pre_ready": true,
|
||||
"encoded_balanced": true,
|
||||
"footer_sidecar_agrees": true,
|
||||
"last_step_matches": true,
|
||||
"layer1_contiguous": true,
|
||||
"layer1_zero_drops": true,
|
||||
"one_footer_last": true,
|
||||
"one_ready_marker": true,
|
||||
"sidecar_final": true,
|
||||
"warmup_exact_16": true,
|
||||
"warmup_long": true,
|
||||
"written_matches_records": true
|
||||
},
|
||||
"layer1_records": 62456,
|
||||
"post_ready_capture_events": [],
|
||||
"stream": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/runs/pilot/sessions/rep1-mns64/opprof/opprof-v1-dp0-pid471212-1784023695315485142.jsonl"
|
||||
}
|
||||
},
|
||||
"rep2-mns16": {
|
||||
"burnin": {
|
||||
"elapsed_s": 63.518994307,
|
||||
"feasible": false,
|
||||
"pass_rate": 0.6647058823529411
|
||||
},
|
||||
"completed_at": 1784025910.710227,
|
||||
"gpu_hours": 0.8481734045346578,
|
||||
"mns": 16,
|
||||
"replicate": 2,
|
||||
"runs": [
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 315.780805484,
|
||||
"feasible": false,
|
||||
"level": "mid",
|
||||
"offered_req_s_per_gpu": 2.125,
|
||||
"pass_rate": 0.31450980392156863,
|
||||
"selected_count": 2550
|
||||
},
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 300.346368314,
|
||||
"feasible": true,
|
||||
"level": "low",
|
||||
"offered_req_s_per_gpu": 1.5,
|
||||
"pass_rate": 1.0,
|
||||
"selected_count": 1800
|
||||
}
|
||||
],
|
||||
"started_at": 1784025143.731658,
|
||||
"status": "complete",
|
||||
"validation": {
|
||||
"accounting_mode": "graceful-footer",
|
||||
"cell": "tp4_mns16",
|
||||
"invariants": {
|
||||
"anchor_intervals_present": true,
|
||||
"compile_capture_pre_ready": true,
|
||||
"encoded_balanced": true,
|
||||
"footer_sidecar_agrees": true,
|
||||
"last_step_matches": true,
|
||||
"layer1_contiguous": true,
|
||||
"layer1_zero_drops": true,
|
||||
"one_footer_last": true,
|
||||
"one_ready_marker": true,
|
||||
"sidecar_final": true,
|
||||
"warmup_exact_16": true,
|
||||
"warmup_long": true,
|
||||
"written_matches_records": true
|
||||
},
|
||||
"layer1_records": 58465,
|
||||
"post_ready_capture_events": [],
|
||||
"stream": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/runs/pilot/sessions/rep2-mns16/opprof/opprof-v1-dp0-pid496100-1784025206790752505.jsonl"
|
||||
}
|
||||
},
|
||||
"rep2-mns64": {
|
||||
"burnin": {
|
||||
"elapsed_s": 60.803771161,
|
||||
"feasible": true,
|
||||
"pass_rate": 1.0
|
||||
},
|
||||
"completed_at": 1784025143.4362338,
|
||||
"gpu_hours": 0.8412917502721151,
|
||||
"mns": 64,
|
||||
"replicate": 2,
|
||||
"runs": [
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 300.605515019,
|
||||
"feasible": true,
|
||||
"level": "mid",
|
||||
"offered_req_s_per_gpu": 2.125,
|
||||
"pass_rate": 1.0,
|
||||
"selected_count": 2550
|
||||
},
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 300.354084826,
|
||||
"feasible": true,
|
||||
"level": "low",
|
||||
"offered_req_s_per_gpu": 1.5,
|
||||
"pass_rate": 1.0,
|
||||
"selected_count": 1800
|
||||
}
|
||||
],
|
||||
"started_at": 1784024382.5080929,
|
||||
"status": "complete",
|
||||
"validation": {
|
||||
"accounting_mode": "graceful-footer",
|
||||
"cell": "tp4_mns64",
|
||||
"invariants": {
|
||||
"anchor_intervals_present": true,
|
||||
"compile_capture_pre_ready": true,
|
||||
"encoded_balanced": true,
|
||||
"footer_sidecar_agrees": true,
|
||||
"last_step_matches": true,
|
||||
"layer1_contiguous": true,
|
||||
"layer1_zero_drops": true,
|
||||
"one_footer_last": true,
|
||||
"one_ready_marker": true,
|
||||
"sidecar_final": true,
|
||||
"warmup_exact_16": true,
|
||||
"warmup_long": true,
|
||||
"written_matches_records": true
|
||||
},
|
||||
"layer1_records": 61696,
|
||||
"post_ready_capture_events": [],
|
||||
"stream": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/runs/pilot/sessions/rep2-mns64/opprof/opprof-v1-dp0-pid483758-1784024456752184540.jsonl"
|
||||
}
|
||||
},
|
||||
"rep3-mns16": {
|
||||
"burnin": {
|
||||
"elapsed_s": 64.324514503,
|
||||
"feasible": false,
|
||||
"pass_rate": 0.5588235294117647
|
||||
},
|
||||
"completed_at": 1784026691.6293187,
|
||||
"gpu_hours": 0.8631463612450494,
|
||||
"mns": 16,
|
||||
"replicate": 3,
|
||||
"runs": [
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 300.711109876,
|
||||
"feasible": true,
|
||||
"level": "low",
|
||||
"offered_req_s_per_gpu": 1.5,
|
||||
"pass_rate": 1.0,
|
||||
"selected_count": 1800
|
||||
},
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 317.011840655,
|
||||
"feasible": false,
|
||||
"level": "mid",
|
||||
"offered_req_s_per_gpu": 2.125,
|
||||
"pass_rate": 0.2635294117647059,
|
||||
"selected_count": 2550
|
||||
}
|
||||
],
|
||||
"started_at": 1784025911.00421,
|
||||
"status": "complete",
|
||||
"validation": {
|
||||
"accounting_mode": "graceful-footer",
|
||||
"cell": "tp4_mns16",
|
||||
"invariants": {
|
||||
"anchor_intervals_present": true,
|
||||
"compile_capture_pre_ready": true,
|
||||
"encoded_balanced": true,
|
||||
"footer_sidecar_agrees": true,
|
||||
"last_step_matches": true,
|
||||
"layer1_contiguous": true,
|
||||
"layer1_zero_drops": true,
|
||||
"one_footer_last": true,
|
||||
"one_ready_marker": true,
|
||||
"sidecar_final": true,
|
||||
"warmup_exact_16": true,
|
||||
"warmup_long": true,
|
||||
"written_matches_records": true
|
||||
},
|
||||
"layer1_records": 61438,
|
||||
"post_ready_capture_events": [],
|
||||
"stream": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/runs/pilot/sessions/rep3-mns16/opprof/opprof-v1-dp0-pid508913-1784025983046041167.jsonl"
|
||||
}
|
||||
},
|
||||
"rep3-mns64": {
|
||||
"burnin": {
|
||||
"elapsed_s": 60.850091109,
|
||||
"feasible": true,
|
||||
"pass_rate": 1.0
|
||||
},
|
||||
"completed_at": 1784027453.3790896,
|
||||
"gpu_hours": 0.8417748435338338,
|
||||
"mns": 64,
|
||||
"replicate": 3,
|
||||
"runs": [
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 300.710505069,
|
||||
"feasible": true,
|
||||
"level": "low",
|
||||
"offered_req_s_per_gpu": 1.5,
|
||||
"pass_rate": 1.0,
|
||||
"selected_count": 1800
|
||||
},
|
||||
{
|
||||
"early_stopped": false,
|
||||
"elapsed_s": 300.869326418,
|
||||
"feasible": true,
|
||||
"level": "mid",
|
||||
"offered_req_s_per_gpu": 2.125,
|
||||
"pass_rate": 1.0,
|
||||
"selected_count": 2550
|
||||
}
|
||||
],
|
||||
"started_at": 1784026691.96421,
|
||||
"status": "complete",
|
||||
"validation": {
|
||||
"accounting_mode": "graceful-footer",
|
||||
"cell": "tp4_mns64",
|
||||
"invariants": {
|
||||
"anchor_intervals_present": true,
|
||||
"compile_capture_pre_ready": true,
|
||||
"encoded_balanced": true,
|
||||
"footer_sidecar_agrees": true,
|
||||
"last_step_matches": true,
|
||||
"layer1_contiguous": true,
|
||||
"layer1_zero_drops": true,
|
||||
"one_footer_last": true,
|
||||
"one_ready_marker": true,
|
||||
"sidecar_final": true,
|
||||
"warmup_exact_16": true,
|
||||
"warmup_long": true,
|
||||
"written_matches_records": true
|
||||
},
|
||||
"layer1_records": 64776,
|
||||
"post_ready_capture_events": [],
|
||||
"stream": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/runs/pilot/sessions/rep3-mns64/opprof/opprof-v1-dp0-pid521797-1784026767359409666.jsonl"
|
||||
}
|
||||
}
|
||||
},
|
||||
"started_at": 1784022845.964628,
|
||||
"status": "complete"
|
||||
}
|
||||
324
runs/intervention-response-v2/pilot-manifest-v3.json
Normal file
324
runs/intervention-response-v2/pilot-manifest-v3.json
Normal file
@@ -0,0 +1,324 @@
|
||||
{
|
||||
"budget": {
|
||||
"expected_h20_hours": [
|
||||
4.8,
|
||||
6.641945318645901
|
||||
],
|
||||
"expected_wall_minutes": [
|
||||
75,
|
||||
95
|
||||
],
|
||||
"global_hard_cap_h20_hours": 8.0,
|
||||
"hard_cap_h20_hours": 6.641945318645901,
|
||||
"prior_attempt_h20_hours": 1.3580546813540988,
|
||||
"session_estimate_h20_hours": 1.0
|
||||
},
|
||||
"burnin": {
|
||||
"anchor": 0.18919793755240089,
|
||||
"arrival_order_sha256": "6c0ac4cb9a30ef501eeeacc8e6cc631c345e976db5ccf530ea5a1ec706d62a24",
|
||||
"input_length_order_sha256": "7939cc20e1a00d1031d27d71508789f38decbbbb6ea59a1df18b2ec342fd2ef8",
|
||||
"offered_req_s": 8.5,
|
||||
"offered_req_s_per_gpu": 2.125,
|
||||
"request_id_order_sha256": "84f4809acbc8acd3b1d14dfa357134a1dc0b9287341624b33f598dafeef54dc7",
|
||||
"selected_count": 510,
|
||||
"study": "/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/studies/burnin-tp4.json",
|
||||
"study_sha256": "5d6c2098042909a863efd3112818fbee9bafe96f22898ac98b66846dbe1fef0f"
|
||||
},
|
||||
"checkpoints": {
|
||||
"fractions": [
|
||||
0.1,
|
||||
0.25,
|
||||
0.5,
|
||||
0.75,
|
||||
1.0
|
||||
],
|
||||
"seconds": [
|
||||
30.0,
|
||||
75.0,
|
||||
150.0,
|
||||
225.0,
|
||||
300.0
|
||||
]
|
||||
},
|
||||
"engine": {
|
||||
"disable_slo_early_stop": true,
|
||||
"duration_s": 300.0,
|
||||
"mns_endpoints": [
|
||||
16,
|
||||
64
|
||||
],
|
||||
"replay_time_scale": 0.5,
|
||||
"safety_deadline_s": 360.0,
|
||||
"tp": 4
|
||||
},
|
||||
"private": {
|
||||
"merged_traces": {
|
||||
"1": {
|
||||
"bytes": 337429767,
|
||||
"path": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/private/traces/rep1.jsonl",
|
||||
"request_id_scheme": "sha256(source_sha256:line_number:original_id)",
|
||||
"rows": 9420,
|
||||
"sha256": "68983266aa0e66aa589562f7c08edbd966f9ba4405e20c105adb43777d2dfbf5",
|
||||
"source_sha256": [
|
||||
"b242d1d9086df3accab57b4c92445d5edd581e12f47e12cea227aa63964c6930",
|
||||
"d23b549f7b69af3647308677bbf76f818a3c226a1c98f9a9f93f09ceee46be87"
|
||||
],
|
||||
"sources": [
|
||||
"/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/traces/low1.jsonl",
|
||||
"/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/traces/high1.jsonl"
|
||||
]
|
||||
},
|
||||
"2": {
|
||||
"bytes": 337509330,
|
||||
"path": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/private/traces/rep2.jsonl",
|
||||
"request_id_scheme": "sha256(source_sha256:line_number:original_id)",
|
||||
"rows": 9457,
|
||||
"sha256": "f38e8938f6a481fc6725b71b21aa04ff7eaf79783cdfd6e41aa2f074156f00c2",
|
||||
"source_sha256": [
|
||||
"4cbb0baac082bd54af562ce2f39104c5c23b4671672da365a67b1e8c146adf9f",
|
||||
"bb0bcd2564a88000f435f12feb21c7c902eafc9ea5fe916adfe9d1eae47f3f9a"
|
||||
],
|
||||
"sources": [
|
||||
"/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/traces/low2.jsonl",
|
||||
"/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/traces/high2.jsonl"
|
||||
]
|
||||
},
|
||||
"3": {
|
||||
"bytes": 337450256,
|
||||
"path": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/private/traces/rep3.jsonl",
|
||||
"request_id_scheme": "sha256(source_sha256:line_number:original_id)",
|
||||
"rows": 9431,
|
||||
"sha256": "3094084b0bb20cc02eecf465091a5c919b4e5b112f704cdc36a563d1efdcee46",
|
||||
"source_sha256": [
|
||||
"1f7ececb142f9a363d2d1ca25eb7b8488b2cc319a51b55faa384f2a3d51f2142",
|
||||
"6f326234791e1cff4ff866bface0d097d0d6e3844eebb1c97653d8e9c35e9397"
|
||||
],
|
||||
"sources": [
|
||||
"/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/traces/low3.jsonl",
|
||||
"/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/traces/high3.jsonl"
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"repetitions": {
|
||||
"1": {
|
||||
"duration_s": 300.0,
|
||||
"load_order": [
|
||||
"low",
|
||||
"mid"
|
||||
],
|
||||
"merged_trace": {
|
||||
"bytes": 337429767,
|
||||
"path": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/private/traces/rep1.jsonl",
|
||||
"request_id_scheme": "sha256(source_sha256:line_number:original_id)",
|
||||
"rows": 9420,
|
||||
"sha256": "68983266aa0e66aa589562f7c08edbd966f9ba4405e20c105adb43777d2dfbf5",
|
||||
"source_sha256": [
|
||||
"b242d1d9086df3accab57b4c92445d5edd581e12f47e12cea227aa63964c6930",
|
||||
"d23b549f7b69af3647308677bbf76f818a3c226a1c98f9a9f93f09ceee46be87"
|
||||
],
|
||||
"sources": [
|
||||
"/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/traces/low1.jsonl",
|
||||
"/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/traces/high1.jsonl"
|
||||
]
|
||||
},
|
||||
"selections": {
|
||||
"low": {
|
||||
"anchor": 0.34815061842962747,
|
||||
"arrival_order_sha256": "0b9473052a28b2eb98bb4bda59c726d6c74cd42656c00046f0559cefd38e0c42",
|
||||
"input_length_order_sha256": "0172aa1fd7d994e9d95857c32293e25f6c537616b40e01034308a0d57cd94139",
|
||||
"offered_req_s": 6.0,
|
||||
"offered_req_s_per_gpu": 1.5,
|
||||
"request_id_order_sha256": "af50f0c3edfc6f9fb74734b2501378fc8ba6fdd3dd3fe84f2bb1d68540eee69b",
|
||||
"selected_count": 1800,
|
||||
"target_count": 1800,
|
||||
"target_req_s_per_gpu": 1.5
|
||||
},
|
||||
"mid": {
|
||||
"anchor": 0.48686986110831465,
|
||||
"arrival_order_sha256": "c2ad99986ce558da5901a9c5ec0a00bd69f198c981d8779235f2773a5c87f1c0",
|
||||
"input_length_order_sha256": "9442bfebdc3fab5062dc1f4d688dc28c02afe3fd806c56dd8159f0ac7e6d0b94",
|
||||
"offered_req_s": 8.5,
|
||||
"offered_req_s_per_gpu": 2.125,
|
||||
"request_id_order_sha256": "0bb61dbc9c26875e991d0d4f984134910d37463e5063f86ee960cf4f8aafb771",
|
||||
"selected_count": 2550,
|
||||
"target_count": 2550,
|
||||
"target_req_s_per_gpu": 2.125
|
||||
}
|
||||
},
|
||||
"source_roles": [
|
||||
"low1",
|
||||
"high1"
|
||||
],
|
||||
"study": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/private/studies/rep1-tp4.json",
|
||||
"study_sha256": "ecfff96e33d458eb1e3b9a6d24386f00cc6f1b19ff926e2ec6320b3f671a7ae3"
|
||||
},
|
||||
"2": {
|
||||
"duration_s": 300.0,
|
||||
"load_order": [
|
||||
"mid",
|
||||
"low"
|
||||
],
|
||||
"merged_trace": {
|
||||
"bytes": 337509330,
|
||||
"path": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/private/traces/rep2.jsonl",
|
||||
"request_id_scheme": "sha256(source_sha256:line_number:original_id)",
|
||||
"rows": 9457,
|
||||
"sha256": "f38e8938f6a481fc6725b71b21aa04ff7eaf79783cdfd6e41aa2f074156f00c2",
|
||||
"source_sha256": [
|
||||
"4cbb0baac082bd54af562ce2f39104c5c23b4671672da365a67b1e8c146adf9f",
|
||||
"bb0bcd2564a88000f435f12feb21c7c902eafc9ea5fe916adfe9d1eae47f3f9a"
|
||||
],
|
||||
"sources": [
|
||||
"/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/traces/low2.jsonl",
|
||||
"/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/traces/high2.jsonl"
|
||||
]
|
||||
},
|
||||
"selections": {
|
||||
"low": {
|
||||
"anchor": 0.3411190868318572,
|
||||
"arrival_order_sha256": "f4eafbdf7420e8a97e38d46fff1aec5fdbc2a049133862a793b4635b51061b7f",
|
||||
"input_length_order_sha256": "cdf82cfc546651f1859c53348eace72348572f09e6e1879ad77d51b489a998fe",
|
||||
"offered_req_s": 6.0,
|
||||
"offered_req_s_per_gpu": 1.5,
|
||||
"request_id_order_sha256": "adc728f189a1ce0301609cdbae7d1dc2318609b13eafb94bcb90903bb7998eb1",
|
||||
"selected_count": 1800,
|
||||
"target_count": 1800,
|
||||
"target_req_s_per_gpu": 1.5
|
||||
},
|
||||
"mid": {
|
||||
"anchor": 0.4825698948735577,
|
||||
"arrival_order_sha256": "b9fc12cf3f86bc8a79bee65296e65aa2b8bf2aeca46b2887094c669adcbb9a00",
|
||||
"input_length_order_sha256": "d8d4bd6fc8ba852a45605b673b6b3e4f33b58f459e69f2a032d226ee175b074e",
|
||||
"offered_req_s": 8.5,
|
||||
"offered_req_s_per_gpu": 2.125,
|
||||
"request_id_order_sha256": "56a0616b6b54abafd37875c7cb25f8639afef2706ccc55dfbe568f45859ea382",
|
||||
"selected_count": 2550,
|
||||
"target_count": 2550,
|
||||
"target_req_s_per_gpu": 2.125
|
||||
}
|
||||
},
|
||||
"source_roles": [
|
||||
"low2",
|
||||
"high2"
|
||||
],
|
||||
"study": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/private/studies/rep2-tp4.json",
|
||||
"study_sha256": "d92a576db031db24bb58f354ea725d7f7567cb76699d387117ac5a6c9317bbb9"
|
||||
},
|
||||
"3": {
|
||||
"duration_s": 300.0,
|
||||
"load_order": [
|
||||
"low",
|
||||
"mid"
|
||||
],
|
||||
"merged_trace": {
|
||||
"bytes": 337450256,
|
||||
"path": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/private/traces/rep3.jsonl",
|
||||
"request_id_scheme": "sha256(source_sha256:line_number:original_id)",
|
||||
"rows": 9431,
|
||||
"sha256": "3094084b0bb20cc02eecf465091a5c919b4e5b112f704cdc36a563d1efdcee46",
|
||||
"source_sha256": [
|
||||
"1f7ececb142f9a363d2d1ca25eb7b8488b2cc319a51b55faa384f2a3d51f2142",
|
||||
"6f326234791e1cff4ff866bface0d097d0d6e3844eebb1c97653d8e9c35e9397"
|
||||
],
|
||||
"sources": [
|
||||
"/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/traces/low3.jsonl",
|
||||
"/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/private/traces/high3.jsonl"
|
||||
]
|
||||
},
|
||||
"selections": {
|
||||
"low": {
|
||||
"anchor": 0.3459572828521402,
|
||||
"arrival_order_sha256": "68de977e2ea7396ffe9406675a3d2c5ebecd1b9ea5afc8116c836cc53cfca188",
|
||||
"input_length_order_sha256": "dffa79545e738b899bec2e9d282764a3388fe38b162982fb2d26928e17ef6016",
|
||||
"offered_req_s": 6.0,
|
||||
"offered_req_s_per_gpu": 1.5,
|
||||
"request_id_order_sha256": "4993c26442fc6b5a4c09b6f576fd8b3cb1be7ce83b7a771e4a57ee7600de688d",
|
||||
"selected_count": 1800,
|
||||
"target_count": 1800,
|
||||
"target_req_s_per_gpu": 1.5
|
||||
},
|
||||
"mid": {
|
||||
"anchor": 0.48664343020532463,
|
||||
"arrival_order_sha256": "efce7339e22d3618cb4d55e6b55bfddb2c563c18faba2a992d5829c13e3f55e9",
|
||||
"input_length_order_sha256": "0792b05fff6729fbd92ab2bb4cb6d31bea7799e232ad42772936bc06efbafb54",
|
||||
"offered_req_s": 8.5,
|
||||
"offered_req_s_per_gpu": 2.125,
|
||||
"request_id_order_sha256": "2a2fabe2c4cf176aeb7e0d32fb8e7dbb1f27429a2e7a0cd18d7d186f23096f19",
|
||||
"selected_count": 2550,
|
||||
"target_count": 2550,
|
||||
"target_req_s_per_gpu": 2.125
|
||||
}
|
||||
},
|
||||
"source_roles": [
|
||||
"low3",
|
||||
"high3"
|
||||
],
|
||||
"study": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/private/studies/rep3-tp4.json",
|
||||
"study_sha256": "fb8ffe256dace32f4ca8a8d49b662d98c3b69b94ecc8fa826e43068b238884ab"
|
||||
}
|
||||
},
|
||||
"sanity": {
|
||||
"distinct_selected_sets": 6,
|
||||
"invariants": {
|
||||
"all_counts_positive": true,
|
||||
"load_levels_two": true,
|
||||
"selection_hashes_unique": true,
|
||||
"selection_sets_disjoint_across_repetitions": true,
|
||||
"six_sessions": true,
|
||||
"three_repetitions": true
|
||||
},
|
||||
"red_flags": [],
|
||||
"selected_sets": 6
|
||||
},
|
||||
"schema": "intervention-response-phase-aware-pilot-manifest-v3",
|
||||
"sessions": [
|
||||
{
|
||||
"mns": 16,
|
||||
"replicate": 1,
|
||||
"session": "rep1-mns16"
|
||||
},
|
||||
{
|
||||
"mns": 64,
|
||||
"replicate": 1,
|
||||
"session": "rep1-mns64"
|
||||
},
|
||||
{
|
||||
"mns": 64,
|
||||
"replicate": 2,
|
||||
"session": "rep2-mns64"
|
||||
},
|
||||
{
|
||||
"mns": 16,
|
||||
"replicate": 2,
|
||||
"session": "rep2-mns16"
|
||||
},
|
||||
{
|
||||
"mns": 16,
|
||||
"replicate": 3,
|
||||
"session": "rep3-mns16"
|
||||
},
|
||||
{
|
||||
"mns": 64,
|
||||
"replicate": 3,
|
||||
"session": "rep3-mns64"
|
||||
}
|
||||
],
|
||||
"source": {
|
||||
"base_manifest": "/home/admin/cpfs/wjh/fidelity-prefix-pilot-20260714/runs/p1b/pilot-manifest.json",
|
||||
"base_manifest_sha256": "86b249a087ab1bcd51cd8de3d1da6bf34afd41af977eb58c93229b941dbf5c8a",
|
||||
"prior_attempt_failure": [
|
||||
{
|
||||
"failure": "TimeoutError('client timeout: tp4_mns16 high')",
|
||||
"session": "rep1-mns16"
|
||||
}
|
||||
],
|
||||
"prior_attempt_h20_hours": 1.3580546813540988,
|
||||
"prior_attempt_state": "/home/admin/cpfs/wjh/intervention-response-v2-20260714/runs/pilot/controller-state.json",
|
||||
"prior_attempt_state_sha256": "c88030ae36862abfc643a855eb3630fb18cd74a58b388514aa31ec1ab485a431",
|
||||
"source_trace": "/home/admin/cpfs/wjh/aituner/aituner/trace_windows/traces/chat_w20260312_1000.jsonl",
|
||||
"source_trace_sha256": "875ba869775deb78086477919f03b322da14e2673c7d070e26528c4190912757",
|
||||
"window_id": "chat_w20260312_1000"
|
||||
},
|
||||
"status": "PASS"
|
||||
}
|
||||
46
runs/intervention-response-v2/platform-v3.json
Normal file
46
runs/intervention-response-v2/platform-v3.json
Normal file
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"schema": "intervention-response-platform-v3",
|
||||
"host_alias": "dash0",
|
||||
"hostname": "ds-07429c65-1-6c5fd97778-9vhkr",
|
||||
"os": "Ubuntu 24.04.2 LTS",
|
||||
"kernel": "Linux 5.10.134-013.8.2.kangaroo.al8.x86_64 x86_64 GNU/Linux",
|
||||
"cpu": {
|
||||
"logical_cpus": 160,
|
||||
"model": "Intel(R) Xeon(R) Processor"
|
||||
},
|
||||
"gpu": {
|
||||
"count": 8,
|
||||
"experiment_ids": [
|
||||
0,
|
||||
1,
|
||||
2,
|
||||
3
|
||||
],
|
||||
"memory_mib_each": 97871,
|
||||
"model": "NVIDIA H20"
|
||||
},
|
||||
"runtime": {
|
||||
"driver": "580.95.05",
|
||||
"python": "3.12.3",
|
||||
"torch": "2.11.0+cu130",
|
||||
"torch_cuda": "13.0",
|
||||
"vllm_editable_source": "/home/admin/cpfs/wjh/opprof-phase2-dash0-20260711/vllm-v0.24.0",
|
||||
"vllm_git_head": "4b253fd8619764b6971a7f2e3a3aa7545f6ace05",
|
||||
"vllm_git_status_clean": true,
|
||||
"vllm_import_path": "/home/admin/cpfs/wjh/opprof-phase2-dash0-20260711/vllm-v0.24.0/vllm/__init__.py",
|
||||
"vllm_reported_version": "0.24.1.dev3+g668cfb7e2"
|
||||
},
|
||||
"model": {
|
||||
"bytes": 61084188040,
|
||||
"path": "/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B"
|
||||
},
|
||||
"aituner_commit": "7fd956355072399b1b56946ecd8007da8f9d2fb0",
|
||||
"experiment": {
|
||||
"completed_at": "2026-07-14T19:10:53+08:00",
|
||||
"incremental_h20_hours": 5.092428478929731,
|
||||
"prior_invalid_attempt_h20_hours": 1.3580546813540988,
|
||||
"started_at": "2026-07-14T17:54:05+08:00",
|
||||
"total_h20_hours": 6.45048316028383,
|
||||
"wall_minutes": 76.79059811433156
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user