Track simulator fidelity experiment artifacts
This commit is contained in:
@@ -0,0 +1,299 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"anchor_isolation": "fresh_server_per_rate_per_round",
|
||||
"config": {
|
||||
"mbt": 8192,
|
||||
"mns": 64,
|
||||
"moe_ep": 1,
|
||||
"moe_tp": 4,
|
||||
"name": "tp4_mns64_mbt8192",
|
||||
"num_gpu_blocks": 26101,
|
||||
"tp": 4
|
||||
},
|
||||
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
|
||||
"expected_h20_gpu_hours": 3.284259259259259,
|
||||
"expected_wall_seconds": 2955.833333333333,
|
||||
"preregistered_rates": [
|
||||
0.1,
|
||||
1.6,
|
||||
2.4
|
||||
],
|
||||
"rates": [
|
||||
0.1,
|
||||
1.6,
|
||||
2.4,
|
||||
3.2
|
||||
],
|
||||
"requests_per_anchor": 64,
|
||||
"rounds": 2,
|
||||
"target_rate_warmup_requests": {
|
||||
"0.10": 4,
|
||||
"1.60": 32,
|
||||
"2.40": 32
|
||||
}
|
||||
},
|
||||
{
|
||||
"anchor_isolation": "fresh_server_per_rate_per_round",
|
||||
"config": {
|
||||
"mbt": 16384,
|
||||
"mns": 64,
|
||||
"moe_ep": 1,
|
||||
"moe_tp": 4,
|
||||
"name": "tp4_mns64_mbt16384",
|
||||
"num_gpu_blocks": 26101,
|
||||
"tp": 4
|
||||
},
|
||||
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
|
||||
"expected_h20_gpu_hours": 3.284259259259259,
|
||||
"expected_wall_seconds": 2955.833333333333,
|
||||
"preregistered_rates": [
|
||||
0.1,
|
||||
1.6,
|
||||
2.4
|
||||
],
|
||||
"rates": [
|
||||
0.1,
|
||||
1.6,
|
||||
2.4,
|
||||
3.2
|
||||
],
|
||||
"requests_per_anchor": 64,
|
||||
"rounds": 2,
|
||||
"target_rate_warmup_requests": {
|
||||
"0.10": 4,
|
||||
"1.60": 32,
|
||||
"2.40": 32
|
||||
}
|
||||
},
|
||||
{
|
||||
"anchor_isolation": "fresh_server_per_rate_per_round",
|
||||
"config": {
|
||||
"mbt": 8192,
|
||||
"mns": 128,
|
||||
"moe_ep": 1,
|
||||
"moe_tp": 4,
|
||||
"name": "tp4_mns128_mbt8192",
|
||||
"num_gpu_blocks": 26101,
|
||||
"tp": 4
|
||||
},
|
||||
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
|
||||
"expected_h20_gpu_hours": 3.284259259259259,
|
||||
"expected_wall_seconds": 2955.833333333333,
|
||||
"preregistered_rates": [
|
||||
0.1,
|
||||
1.6,
|
||||
2.4
|
||||
],
|
||||
"rates": [
|
||||
0.1,
|
||||
1.6,
|
||||
2.4,
|
||||
3.2
|
||||
],
|
||||
"requests_per_anchor": 64,
|
||||
"rounds": 2,
|
||||
"target_rate_warmup_requests": {
|
||||
"0.10": 4,
|
||||
"1.60": 32,
|
||||
"2.40": 32
|
||||
}
|
||||
},
|
||||
{
|
||||
"anchor_isolation": "fresh_server_per_rate_per_round",
|
||||
"config": {
|
||||
"mbt": 16384,
|
||||
"mns": 128,
|
||||
"moe_ep": 1,
|
||||
"moe_tp": 4,
|
||||
"name": "tp4_mns128_mbt16384",
|
||||
"num_gpu_blocks": 26101,
|
||||
"tp": 4
|
||||
},
|
||||
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
|
||||
"expected_h20_gpu_hours": 3.284259259259259,
|
||||
"expected_wall_seconds": 2955.833333333333,
|
||||
"preregistered_rates": [
|
||||
0.1,
|
||||
1.6,
|
||||
2.4
|
||||
],
|
||||
"rates": [
|
||||
0.1,
|
||||
1.6,
|
||||
2.4,
|
||||
3.2
|
||||
],
|
||||
"requests_per_anchor": 64,
|
||||
"rounds": 2,
|
||||
"target_rate_warmup_requests": {
|
||||
"0.10": 4,
|
||||
"1.60": 32,
|
||||
"2.40": 32
|
||||
}
|
||||
},
|
||||
{
|
||||
"anchor_isolation": "fresh_server_per_rate_per_round",
|
||||
"config": {
|
||||
"mbt": 8192,
|
||||
"mns": 64,
|
||||
"moe_ep": 8,
|
||||
"moe_tp": 1,
|
||||
"name": "tp8_mns64_mbt8192",
|
||||
"num_gpu_blocks": 62351,
|
||||
"tp": 8
|
||||
},
|
||||
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
|
||||
"expected_h20_gpu_hours": 6.712962962962962,
|
||||
"expected_wall_seconds": 3020.833333333333,
|
||||
"preregistered_rates": [
|
||||
0.1,
|
||||
1.2,
|
||||
1.6
|
||||
],
|
||||
"rates": [
|
||||
0.1,
|
||||
1.2,
|
||||
1.6,
|
||||
2.4,
|
||||
3.2
|
||||
],
|
||||
"requests_per_anchor": 64,
|
||||
"rounds": 2,
|
||||
"target_rate_warmup_requests": {
|
||||
"0.10": 4,
|
||||
"1.20": 24,
|
||||
"1.60": 32
|
||||
}
|
||||
},
|
||||
{
|
||||
"anchor_isolation": "fresh_server_per_rate_per_round",
|
||||
"config": {
|
||||
"mbt": 16384,
|
||||
"mns": 64,
|
||||
"moe_ep": 8,
|
||||
"moe_tp": 1,
|
||||
"name": "tp8_mns64_mbt16384",
|
||||
"num_gpu_blocks": 62351,
|
||||
"tp": 8
|
||||
},
|
||||
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
|
||||
"expected_h20_gpu_hours": 6.712962962962962,
|
||||
"expected_wall_seconds": 3020.833333333333,
|
||||
"preregistered_rates": [
|
||||
0.1,
|
||||
1.2,
|
||||
1.6
|
||||
],
|
||||
"rates": [
|
||||
0.1,
|
||||
1.2,
|
||||
1.6,
|
||||
2.4
|
||||
],
|
||||
"requests_per_anchor": 64,
|
||||
"rounds": 2,
|
||||
"target_rate_warmup_requests": {
|
||||
"0.10": 4,
|
||||
"1.20": 24,
|
||||
"1.60": 32
|
||||
}
|
||||
},
|
||||
{
|
||||
"anchor_isolation": "fresh_server_per_rate_per_round",
|
||||
"config": {
|
||||
"mbt": 8192,
|
||||
"mns": 128,
|
||||
"moe_ep": 8,
|
||||
"moe_tp": 1,
|
||||
"name": "tp8_mns128_mbt8192",
|
||||
"num_gpu_blocks": 62351,
|
||||
"tp": 8
|
||||
},
|
||||
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
|
||||
"expected_h20_gpu_hours": 6.712962962962962,
|
||||
"expected_wall_seconds": 3020.833333333333,
|
||||
"preregistered_rates": [
|
||||
0.1,
|
||||
1.2,
|
||||
1.6
|
||||
],
|
||||
"rates": [
|
||||
0.1,
|
||||
1.2,
|
||||
1.6,
|
||||
2.4
|
||||
],
|
||||
"requests_per_anchor": 64,
|
||||
"rounds": 2,
|
||||
"target_rate_warmup_requests": {
|
||||
"0.10": 4,
|
||||
"1.20": 24,
|
||||
"1.60": 32
|
||||
}
|
||||
},
|
||||
{
|
||||
"anchor_isolation": "fresh_server_per_rate_per_round",
|
||||
"config": {
|
||||
"mbt": 16384,
|
||||
"mns": 128,
|
||||
"moe_ep": 8,
|
||||
"moe_tp": 1,
|
||||
"name": "tp8_mns128_mbt16384",
|
||||
"num_gpu_blocks": 62351,
|
||||
"tp": 8
|
||||
},
|
||||
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
|
||||
"expected_h20_gpu_hours": 6.712962962962962,
|
||||
"expected_wall_seconds": 3020.833333333333,
|
||||
"preregistered_rates": [
|
||||
0.1,
|
||||
1.2,
|
||||
1.6
|
||||
],
|
||||
"rates": [
|
||||
0.1,
|
||||
1.2,
|
||||
1.6,
|
||||
2.4,
|
||||
3.2
|
||||
],
|
||||
"requests_per_anchor": 64,
|
||||
"rounds": 2,
|
||||
"target_rate_warmup_requests": {
|
||||
"0.10": 4,
|
||||
"1.20": 24,
|
||||
"1.60": 32
|
||||
}
|
||||
}
|
||||
],
|
||||
"execution_protocol_amendment": {
|
||||
"contract": "fresh server and target-rate warmup for every config-rate-round",
|
||||
"reason": "observed cross-anchor GPU/kernel/batch warm-state leakage",
|
||||
"timing": "after excluded multi-rate-per-server diagnostic and before any accepted real surface cell"
|
||||
},
|
||||
"expansion_artifact_roots": [
|
||||
"artifacts/t0-real-expansion-r2p40-v1",
|
||||
"artifacts/t0-real-expansion-r3p20-v1"
|
||||
],
|
||||
"expected_total_h20_gpu_hours": 39.98888888888888,
|
||||
"frontier_freeze": {
|
||||
"path": "/home/gahow/phd/aituner/runs/frontier-multicase-sufficiency-v1/artifacts/frontier-t0-surface-v1/frontier_surface_frozen.json",
|
||||
"sha256": "801aa36451c8647f71cc87011144622d2203786e82f189ed1375d964399b106a"
|
||||
},
|
||||
"hard_timeout_hours_per_cell": 2.0,
|
||||
"post_pilot_sensitivities": [
|
||||
"tpot_120ms",
|
||||
"tpot_150ms",
|
||||
"tpot_180ms"
|
||||
],
|
||||
"preregistered_plan": {
|
||||
"path": "/home/gahow/phd/aituner/runs/frontier-multicase-sufficiency-v1/artifacts/t0-real-surface-v1/real-plan.json",
|
||||
"sha256": "f7acb45d1183a6026dba4bbf9bc2d7578452b815b8de0035ca732512f3d9d47a"
|
||||
},
|
||||
"schema": "qwen235b-t0-real-executed-plan-v1",
|
||||
"selection_slo": "tpot_150ms",
|
||||
"selection_timing": "rate anchors frozen after complete simulator surface and before any accepted real surface cell",
|
||||
"status": "complete",
|
||||
"strict_preregistered_slo": "tpot_40ms"
|
||||
}
|
||||
Reference in New Issue
Block a user