Initial pi0.6 minimal validation

This commit is contained in:
seeker
2026-07-11 22:35:54 +08:00
commit 53ef020b46
27 changed files with 3459 additions and 0 deletions
+32
View File
@@ -0,0 +1,32 @@
{
"trajectory_metrics": {
"mixed": 100.86174011230469,
"unconditional": 21.51112937927246,
"positive": 0.061239250004291534,
"negative": 55.823570251464844,
"cfg": 0.24478793144226074,
"negative_to_failure_mse": 48.71984100341797
},
"values": [
{
"source_type": "demo_success",
"target": 0.0,
"prediction": -0.007052943576127291
},
{
"source_type": "autonomous_understeer",
"target": -0.03799404203891754,
"prediction": -0.04714635759592056
},
{
"source_type": "autonomous_stop",
"target": -0.9509902000427246,
"prediction": -0.9405871629714966
},
{
"source_type": "intervention_correction",
"target": -0.0051981499418616295,
"prediction": -0.0118478462100029
}
]
}
Binary file not shown.

After

Width:  |  Height:  |  Size: 87 KiB

+12
View File
@@ -0,0 +1,12 @@
{
"device": "mps",
"experience_samples": 4,
"policy_parameters": 817058,
"value_parameters": 171977,
"sources": [
"demo_success",
"autonomous_understeer",
"autonomous_stop",
"intervention_correction"
]
}
+625
View File
@@ -0,0 +1,625 @@
[
{
"stage": "base",
"step": 1,
"loss": 72.41638946533203,
"text_loss": 68.23114013671875,
"flow_loss": 2.0926246643066406
},
{
"stage": "base",
"step": 20,
"loss": 4.305421829223633,
"text_loss": 1.9023208618164062,
"flow_loss": 1.2015506029129028
},
{
"stage": "base",
"step": 40,
"loss": 2.912196159362793,
"text_loss": 0.8887173533439636,
"flow_loss": 1.0117393732070923
},
{
"stage": "base",
"step": 60,
"loss": 2.184612512588501,
"text_loss": 0.5364341735839844,
"flow_loss": 0.8240891695022583
},
{
"stage": "base",
"step": 80,
"loss": 1.578565239906311,
"text_loss": 0.23946531116962433,
"flow_loss": 0.6695499420166016
},
{
"stage": "base",
"step": 100,
"loss": 1.5856558084487915,
"text_loss": 0.04227600246667862,
"flow_loss": 0.7716898918151855
},
{
"stage": "base",
"step": 120,
"loss": 0.3423895239830017,
"text_loss": 0.0004414900322444737,
"flow_loss": 0.1709740161895752
},
{
"stage": "base",
"step": 140,
"loss": 0.24176472425460815,
"text_loss": 1.8706961782299913e-05,
"flow_loss": 0.12087301164865494
},
{
"stage": "base",
"step": 160,
"loss": 0.3000774383544922,
"text_loss": 7.637506496394053e-05,
"flow_loss": 0.15000052750110626
},
{
"stage": "base",
"step": 180,
"loss": 0.6410971879959106,
"text_loss": 1.6521895304322243e-05,
"flow_loss": 0.32054033875465393
},
{
"stage": "base",
"step": 200,
"loss": 0.6132829189300537,
"text_loss": 9.676185072748922e-06,
"flow_loss": 0.30663663148880005
},
{
"stage": "base",
"step": 220,
"loss": 0.3431224524974823,
"text_loss": 7.356796231761109e-06,
"flow_loss": 0.17155754566192627
},
{
"stage": "base",
"step": 240,
"loss": 0.28047603368759155,
"text_loss": 5.987634267512476e-06,
"flow_loss": 0.1402350217103958
},
{
"stage": "base",
"step": 260,
"loss": 0.13324393332004547,
"text_loss": 4.9011541705112904e-06,
"flow_loss": 0.06661951541900635
},
{
"stage": "base",
"step": 280,
"loss": 0.1635851263999939,
"text_loss": 4.0462705328536686e-06,
"flow_loss": 0.08179053664207458
},
{
"stage": "base",
"step": 300,
"loss": 0.15081387758255005,
"text_loss": 3.4570459774840856e-06,
"flow_loss": 0.07540521025657654
},
{
"stage": "value",
"step": 1,
"loss": 5.427414894104004,
"prediction": -0.5049723982810974,
"target": 0.0
},
{
"stage": "value",
"step": 20,
"loss": 2.24937105178833,
"prediction": -0.3925527334213257,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 40,
"loss": 1.728512167930603,
"prediction": -0.32079368829727173,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 60,
"loss": 1.4823004007339478,
"prediction": -0.3057250678539276,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 80,
"loss": 1.1117331981658936,
"prediction": -0.3553512394428253,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 100,
"loss": 0.2580283582210541,
"prediction": -0.11316870898008347,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 120,
"loss": 0.12432077527046204,
"prediction": -0.054820768535137177,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 140,
"loss": 0.08916354924440384,
"prediction": -0.04263461381196976,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 160,
"loss": 0.07165656983852386,
"prediction": -0.034443676471710205,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 180,
"loss": 0.05974685773253441,
"prediction": -0.029927225783467293,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 200,
"loss": 0.05075548216700554,
"prediction": -0.026268303394317627,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 220,
"loss": 0.043695785105228424,
"prediction": -0.023351771757006645,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 240,
"loss": 0.03802856057882309,
"prediction": -0.021020548418164253,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 260,
"loss": 0.03340449184179306,
"prediction": -0.019105376675724983,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 280,
"loss": 0.02958041802048683,
"prediction": -0.017514187842607498,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 300,
"loss": 0.02638067863881588,
"prediction": -0.016178548336029053,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 320,
"loss": 0.023675711825489998,
"prediction": -0.01504577323794365,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 340,
"loss": 0.021368399262428284,
"prediction": -0.014076616615056992,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 360,
"loss": 0.019383536651730537,
"prediction": -0.013240991160273552,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 380,
"loss": 0.017663555219769478,
"prediction": -0.01251534465700388,
"target": -0.0051981499418616295
},
{
"stage": "value",
"step": 400,
"loss": 0.016163267195224762,
"prediction": -0.011881118640303612,
"target": -0.0051981499418616295
},
{
"stage": "mixed",
"step": 1,
"loss": 0.11788154393434525,
"text_loss": 3.4366105410299497e-06,
"flow_loss": 0.05893905460834503
},
{
"stage": "mixed",
"step": 20,
"loss": 4.7238688468933105,
"text_loss": 2.6195578575134277,
"flow_loss": 1.0521554946899414
},
{
"stage": "mixed",
"step": 40,
"loss": 5.051268577575684,
"text_loss": 1.2949998378753662,
"flow_loss": 1.8781343698501587
},
{
"stage": "mixed",
"step": 60,
"loss": 1.6957576274871826,
"text_loss": 0.8319522142410278,
"flow_loss": 0.4319027364253998
},
{
"stage": "mixed",
"step": 80,
"loss": 2.1900432109832764,
"text_loss": 0.8061568140983582,
"flow_loss": 0.6919432282447815
},
{
"stage": "mixed",
"step": 100,
"loss": 2.2935876846313477,
"text_loss": 0.5968648791313171,
"flow_loss": 0.8483614325523376
},
{
"stage": "mixed",
"step": 120,
"loss": 1.4990849494934082,
"text_loss": 0.6506502032279968,
"flow_loss": 0.4242174029350281
},
{
"stage": "mixed",
"step": 140,
"loss": 1.6056029796600342,
"text_loss": 0.5977785587310791,
"flow_loss": 0.5039122104644775
},
{
"stage": "mixed",
"step": 160,
"loss": 1.3810169696807861,
"text_loss": 0.48245665431022644,
"flow_loss": 0.44928014278411865
},
{
"stage": "mixed",
"step": 180,
"loss": 1.1724852323532104,
"text_loss": 0.3958587944507599,
"flow_loss": 0.3883132338523865
},
{
"stage": "mixed",
"step": 200,
"loss": 1.2829020023345947,
"text_loss": 0.18238645792007446,
"flow_loss": 0.5502578020095825
},
{
"stage": "mixed",
"step": 220,
"loss": 0.7328482866287231,
"text_loss": 0.1418272703886032,
"flow_loss": 0.29551050066947937
},
{
"stage": "mixed",
"step": 240,
"loss": 1.196341872215271,
"text_loss": 0.28424081206321716,
"flow_loss": 0.4560505449771881
},
{
"stage": "mixed",
"step": 260,
"loss": 4.298240661621094,
"text_loss": 0.257877379655838,
"flow_loss": 2.020181655883789
},
{
"stage": "mixed",
"step": 280,
"loss": 1.3184027671813965,
"text_loss": 0.07380203157663345,
"flow_loss": 0.622300386428833
},
{
"stage": "mixed",
"step": 300,
"loss": 2.4886393547058105,
"text_loss": 0.30716001987457275,
"flow_loss": 1.0907396078109741
},
{
"stage": "recap",
"step": 1,
"loss": 10.11633586883545,
"text_loss": 9.866013526916504,
"flow_loss": 0.12516121566295624
},
{
"stage": "recap",
"step": 20,
"loss": 3.1665196418762207,
"text_loss": 2.23919415473938,
"flow_loss": 0.4636627733707428
},
{
"stage": "recap",
"step": 40,
"loss": 3.1297008991241455,
"text_loss": 1.4351346492767334,
"flow_loss": 0.847283124923706
},
{
"stage": "recap",
"step": 60,
"loss": 2.608584403991699,
"text_loss": 1.171854853630066,
"flow_loss": 0.7183647751808167
},
{
"stage": "recap",
"step": 80,
"loss": 3.5118634700775146,
"text_loss": 0.9280703067779541,
"flow_loss": 1.2918965816497803
},
{
"stage": "recap",
"step": 100,
"loss": 2.7196712493896484,
"text_loss": 0.8991937041282654,
"flow_loss": 0.9102387428283691
},
{
"stage": "recap",
"step": 120,
"loss": 1.1335762739181519,
"text_loss": 0.7848832011222839,
"flow_loss": 0.17434655129909515
},
{
"stage": "recap",
"step": 140,
"loss": 2.5729737281799316,
"text_loss": 0.5885628461837769,
"flow_loss": 0.9922055006027222
},
{
"stage": "recap",
"step": 160,
"loss": 1.9800522327423096,
"text_loss": 0.6485287547111511,
"flow_loss": 0.6657617688179016
},
{
"stage": "recap",
"step": 180,
"loss": 1.5937684774398804,
"text_loss": 0.6764931678771973,
"flow_loss": 0.45863765478134155
},
{
"stage": "recap",
"step": 200,
"loss": 1.588905692100525,
"text_loss": 1.1673603057861328,
"flow_loss": 0.21077267825603485
},
{
"stage": "recap",
"step": 220,
"loss": 1.1653995513916016,
"text_loss": 0.5840165019035339,
"flow_loss": 0.2906915545463562
},
{
"stage": "recap",
"step": 240,
"loss": 2.6636130809783936,
"text_loss": 1.3158458471298218,
"flow_loss": 0.6738836169242859
},
{
"stage": "recap",
"step": 260,
"loss": 0.5980206727981567,
"text_loss": 0.42834123969078064,
"flow_loss": 0.08483970910310745
},
{
"stage": "recap",
"step": 280,
"loss": 1.0666983127593994,
"text_loss": 0.47541406750679016,
"flow_loss": 0.2956421375274658
},
{
"stage": "recap",
"step": 300,
"loss": 0.8535268306732178,
"text_loss": 0.4074874520301819,
"flow_loss": 0.22301967442035675
},
{
"stage": "recap",
"step": 320,
"loss": 5.488016605377197,
"text_loss": 0.851451575756073,
"flow_loss": 2.3182826042175293
},
{
"stage": "recap",
"step": 340,
"loss": 0.7862600088119507,
"text_loss": 0.37299302220344543,
"flow_loss": 0.20663349330425262
},
{
"stage": "recap",
"step": 360,
"loss": 1.3418667316436768,
"text_loss": 0.7838777899742126,
"flow_loss": 0.27899447083473206
},
{
"stage": "recap",
"step": 380,
"loss": 0.7067349553108215,
"text_loss": 0.15938280522823334,
"flow_loss": 0.2736760675907135
},
{
"stage": "recap",
"step": 400,
"loss": 0.4985463619232178,
"text_loss": 0.2566893398761749,
"flow_loss": 0.12092851102352142
},
{
"stage": "recap",
"step": 420,
"loss": 0.5810034871101379,
"text_loss": 0.24579037725925446,
"flow_loss": 0.16760656237602234
},
{
"stage": "recap",
"step": 440,
"loss": 0.40272825956344604,
"text_loss": 0.19410930573940277,
"flow_loss": 0.10430946946144104
},
{
"stage": "recap",
"step": 460,
"loss": 0.7170483469963074,
"text_loss": 0.32609468698501587,
"flow_loss": 0.19547683000564575
},
{
"stage": "recap",
"step": 480,
"loss": 0.3233756422996521,
"text_loss": 0.08512496948242188,
"flow_loss": 0.11912534385919571
},
{
"stage": "recap",
"step": 500,
"loss": 0.625529408454895,
"text_loss": 0.23650097846984863,
"flow_loss": 0.1945142149925232
},
{
"stage": "recap",
"step": 520,
"loss": 1.645598292350769,
"text_loss": 0.874957263469696,
"flow_loss": 0.3853205144405365
},
{
"stage": "recap",
"step": 540,
"loss": 0.8086838722229004,
"text_loss": 0.31192541122436523,
"flow_loss": 0.24837924540042877
},
{
"stage": "recap",
"step": 560,
"loss": 1.9226100444793701,
"text_loss": 0.8500325083732605,
"flow_loss": 0.5362887382507324
},
{
"stage": "recap",
"step": 580,
"loss": 2.138998031616211,
"text_loss": 0.7942134141921997,
"flow_loss": 0.6723923683166504
},
{
"stage": "recap",
"step": 600,
"loss": 0.504305362701416,
"text_loss": 0.13201656937599182,
"flow_loss": 0.1861443817615509
},
{
"stage": "recap",
"step": 620,
"loss": 0.5794067978858948,
"text_loss": 0.26564836502075195,
"flow_loss": 0.1568792164325714
},
{
"stage": "recap",
"step": 640,
"loss": 0.8541183471679688,
"text_loss": 0.154631569981575,
"flow_loss": 0.34974339604377747
},
{
"stage": "recap",
"step": 660,
"loss": 0.16945119202136993,
"text_loss": 0.056921038776636124,
"flow_loss": 0.056265074759721756
},
{
"stage": "recap",
"step": 680,
"loss": 0.47458726167678833,
"text_loss": 0.04364287480711937,
"flow_loss": 0.21547219157218933
},
{
"stage": "recap",
"step": 700,
"loss": 0.18534913659095764,
"text_loss": 0.05316398665308952,
"flow_loss": 0.06609257310628891
}
]
Binary file not shown.

After

Width:  |  Height:  |  Size: 46 KiB