summaryrefslogtreecommitdiff
path: root/results/toy_lq
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-03-23 18:21:26 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-03-23 18:21:26 -0500
commit6ed4fa50ddfa4c7957aaa909aaf72f0d7d317712 (patch)
treed7c63adcd19c4f5d46c8a937e5047fece55dea62 /results/toy_lq
Initial implementation: all models, methods, toy and CIFAR experiments
Debug phase. Toy LQ experiments (3 seeds) complete with terminal gradient matching. Credit bridge matches state bridge on linear system (~0.94 cosine). CIFAR experiments in progress.
Diffstat (limited to 'results/toy_lq')
-rw-r--r--results/toy_lq/state_bridge_seed42.ptbin0 -> 150069 bytes
-rw-r--r--results/toy_lq/sweep_results.json1070
-rw-r--r--results/toy_lq/toy_lq_seed42.json335
-rw-r--r--results/toy_lq/toy_lq_v2_seed123_lam0.1_sig0.1_tgw1.0_fm0.0.json330
-rw-r--r--results/toy_lq/toy_lq_v2_seed42_lam0.1_sig0.1_tgw1.0_fm0.0.json458
-rw-r--r--results/toy_lq/toy_lq_v2_seed42_lam0.1_sig0.1_tgw1.0_fm0.1.json330
-rw-r--r--results/toy_lq/toy_lq_v2_seed42_lam1.0_sig0.3_tgw0.0_fm0.0.json282
-rw-r--r--results/toy_lq/toy_lq_v2_seed456_lam0.1_sig0.1_tgw1.0_fm0.0.json330
-rw-r--r--results/toy_lq/value_net_seed42.ptbin0 -> 117515 bytes
9 files changed, 3135 insertions, 0 deletions
diff --git a/results/toy_lq/state_bridge_seed42.pt b/results/toy_lq/state_bridge_seed42.pt
new file mode 100644
index 0000000..a87e99d
--- /dev/null
+++ b/results/toy_lq/state_bridge_seed42.pt
Binary files differ
diff --git a/results/toy_lq/sweep_results.json b/results/toy_lq/sweep_results.json
new file mode 100644
index 0000000..30c3f49
--- /dev/null
+++ b/results/toy_lq/sweep_results.json
@@ -0,0 +1,1070 @@
+{
+ "base": {
+ "best_cos": 0.28987203165888786,
+ "best_step": 500,
+ "final_cos": -0.0006980087685709199,
+ "final_rho": 0.00831739305673788,
+ "final_nudge": 0.0027815375166634717,
+ "history": [
+ {
+ "step": 500,
+ "avg_cos": 0.28987203165888786,
+ "avg_rho": 0.30755721777677536,
+ "avg_nudge": -0.10750458451608817,
+ "loss_term": 0.4910352826118469,
+ "loss_bridge": 0.21142145991325378
+ },
+ {
+ "step": 1000,
+ "avg_cos": 0.17731603110829988,
+ "avg_rho": 0.17737891773382822,
+ "avg_nudge": -0.06381315520654122,
+ "loss_term": 0.1414657086133957,
+ "loss_bridge": 0.16202926635742188
+ },
+ {
+ "step": 1500,
+ "avg_cos": 0.07300025007377069,
+ "avg_rho": 0.07345063022027414,
+ "avg_nudge": -0.02641519942941765,
+ "loss_term": 0.07946588099002838,
+ "loss_bridge": 0.08628662675619125
+ },
+ {
+ "step": 2000,
+ "avg_cos": 0.05074742032835881,
+ "avg_rho": 0.048574333622430764,
+ "avg_nudge": -0.016719758200148743,
+ "loss_term": 0.06007867306470871,
+ "loss_bridge": 0.016275471076369286
+ },
+ {
+ "step": 2500,
+ "avg_cos": 0.045629044994711876,
+ "avg_rho": 0.0567939051737388,
+ "avg_nudge": -0.016934571011612814,
+ "loss_term": 0.04579576849937439,
+ "loss_bridge": 0.008496936410665512
+ },
+ {
+ "step": 3000,
+ "avg_cos": 0.06145744491368532,
+ "avg_rho": 0.05695042138298353,
+ "avg_nudge": -0.020737762407710154,
+ "loss_term": 0.04881729558110237,
+ "loss_bridge": 0.013217507861554623
+ },
+ {
+ "step": 3500,
+ "avg_cos": 0.04631757119204849,
+ "avg_rho": 0.0402289762472113,
+ "avg_nudge": -0.015406294725835323,
+ "loss_term": 0.04255056008696556,
+ "loss_bridge": 0.01808304153382778
+ },
+ {
+ "step": 4000,
+ "avg_cos": 0.07397006265819073,
+ "avg_rho": 0.07162392682706316,
+ "avg_nudge": -0.025235373992472887,
+ "loss_term": 0.05486675351858139,
+ "loss_bridge": 0.02182137593626976
+ },
+ {
+ "step": 4500,
+ "avg_cos": 0.07251314166933298,
+ "avg_rho": 0.07301904633641243,
+ "avg_nudge": -0.027378834628810484,
+ "loss_term": 0.027670202776789665,
+ "loss_bridge": 0.013123266398906708
+ },
+ {
+ "step": 5000,
+ "avg_cos": -0.0006980087685709199,
+ "avg_rho": 0.00831739305673788,
+ "avg_nudge": 0.0027815375166634717,
+ "loss_term": 0.021854262799024582,
+ "loss_bridge": 0.0122066093608737
+ }
+ ]
+ },
+ "noise_0.1": {
+ "best_cos": 0.28885648772120476,
+ "best_step": 500,
+ "final_cos": 0.02330129671220978,
+ "final_rho": 0.03084004654859503,
+ "final_nudge": -0.005932313855737448,
+ "history": [
+ {
+ "step": 500,
+ "avg_cos": 0.28885648772120476,
+ "avg_rho": 0.306567445397377,
+ "avg_nudge": -0.1071426725635926,
+ "loss_term": 0.4925232529640198,
+ "loss_bridge": 0.20981840789318085
+ },
+ {
+ "step": 1000,
+ "avg_cos": 0.17456108083327612,
+ "avg_rho": 0.17607956007122993,
+ "avg_nudge": -0.06276426805804174,
+ "loss_term": 0.1324017345905304,
+ "loss_bridge": 0.1835721731185913
+ },
+ {
+ "step": 1500,
+ "avg_cos": 0.08755840392162402,
+ "avg_rho": 0.08556619860852759,
+ "avg_nudge": -0.03154423305143913,
+ "loss_term": 0.07669232785701752,
+ "loss_bridge": 0.10240059345960617
+ },
+ {
+ "step": 2000,
+ "avg_cos": 0.05209386876473824,
+ "avg_rho": 0.04985952338514229,
+ "avg_nudge": -0.01653688432027896,
+ "loss_term": 0.06218753010034561,
+ "loss_bridge": 0.02190624177455902
+ },
+ {
+ "step": 2500,
+ "avg_cos": 0.038306045811623335,
+ "avg_rho": 0.047700356847296156,
+ "avg_nudge": -0.01320391776971519,
+ "loss_term": 0.06128765642642975,
+ "loss_bridge": 0.01958899199962616
+ },
+ {
+ "step": 3000,
+ "avg_cos": 0.059713449950019516,
+ "avg_rho": 0.054914615117013454,
+ "avg_nudge": -0.01939693869402011,
+ "loss_term": 0.04238733649253845,
+ "loss_bridge": 0.006958359386771917
+ },
+ {
+ "step": 3500,
+ "avg_cos": 0.04283027160757532,
+ "avg_rho": 0.028526597811530035,
+ "avg_nudge": -0.01381517636279265,
+ "loss_term": 0.024001002311706543,
+ "loss_bridge": 0.006152431480586529
+ },
+ {
+ "step": 4000,
+ "avg_cos": 0.0656419579560558,
+ "avg_rho": 0.06320031352030735,
+ "avg_nudge": -0.02216823499960204,
+ "loss_term": 0.04236245155334473,
+ "loss_bridge": 0.01628262549638748
+ },
+ {
+ "step": 4500,
+ "avg_cos": 0.05787398883452018,
+ "avg_rho": 0.0610881638713181,
+ "avg_nudge": -0.02213552314788103,
+ "loss_term": 0.024835661053657532,
+ "loss_bridge": 0.008629711344838142
+ },
+ {
+ "step": 5000,
+ "avg_cos": 0.02330129671220978,
+ "avg_rho": 0.03084004654859503,
+ "avg_nudge": -0.005932313855737448,
+ "loss_term": 0.035377949476242065,
+ "loss_bridge": 0.020307490602135658
+ }
+ ]
+ },
+ "noise_0.3": {
+ "best_cos": 0.28320933257540065,
+ "best_step": 500,
+ "final_cos": -0.007130145425132166,
+ "final_rho": 0.003303757131410142,
+ "final_nudge": 0.004990910800794761,
+ "history": [
+ {
+ "step": 500,
+ "avg_cos": 0.28320933257540065,
+ "avg_rho": 0.30105741570393246,
+ "avg_nudge": -0.10515742873152097,
+ "loss_term": 0.44116002321243286,
+ "loss_bridge": 0.210750013589859
+ },
+ {
+ "step": 1000,
+ "avg_cos": 0.1680816188454628,
+ "avg_rho": 0.1721916707853476,
+ "avg_nudge": -0.060552582144737244,
+ "loss_term": 0.14207889139652252,
+ "loss_bridge": 0.16882070899009705
+ },
+ {
+ "step": 1500,
+ "avg_cos": 0.08877109829336405,
+ "avg_rho": 0.08808179199695587,
+ "avg_nudge": -0.03221472934819758,
+ "loss_term": 0.12282441556453705,
+ "loss_bridge": 0.07336755841970444
+ },
+ {
+ "step": 2000,
+ "avg_cos": 0.04903770827998718,
+ "avg_rho": 0.04795513402981063,
+ "avg_nudge": -0.016069856472313404,
+ "loss_term": 0.06662434339523315,
+ "loss_bridge": 0.02520526573061943
+ },
+ {
+ "step": 2500,
+ "avg_cos": 0.05001032492145896,
+ "avg_rho": 0.053442057532568775,
+ "avg_nudge": -0.01783018947268526,
+ "loss_term": 0.04614880681037903,
+ "loss_bridge": 0.015394347719848156
+ },
+ {
+ "step": 3000,
+ "avg_cos": 0.03979540191357955,
+ "avg_rho": 0.03453826089389622,
+ "avg_nudge": -0.012916556559503078,
+ "loss_term": 0.04155049845576286,
+ "loss_bridge": 0.007860729470849037
+ },
+ {
+ "step": 3500,
+ "avg_cos": 0.06703585013747215,
+ "avg_rho": 0.04949762811884284,
+ "avg_nudge": -0.02297227829694748,
+ "loss_term": 0.059078700840473175,
+ "loss_bridge": 0.030750930309295654
+ },
+ {
+ "step": 4000,
+ "avg_cos": 0.06641693723698457,
+ "avg_rho": 0.06286459214364488,
+ "avg_nudge": -0.021883966866880655,
+ "loss_term": 0.025344880297780037,
+ "loss_bridge": 0.008583566173911095
+ },
+ {
+ "step": 4500,
+ "avg_cos": 0.03687915485352278,
+ "avg_rho": 0.028895257118468482,
+ "avg_nudge": -0.01225966370354096,
+ "loss_term": 0.020479349419474602,
+ "loss_bridge": 0.00925756897777319
+ },
+ {
+ "step": 5000,
+ "avg_cos": -0.007130145425132166,
+ "avg_rho": 0.003303757131410142,
+ "avg_nudge": 0.004990910800794761,
+ "loss_term": 0.03882830590009689,
+ "loss_bridge": 0.022515198215842247
+ }
+ ]
+ },
+ "lam_1.0": {
+ "best_cos": 0.2899630069732666,
+ "best_step": 500,
+ "final_cos": 0.0024576462844076255,
+ "final_rho": 0.010072723651925722,
+ "final_nudge": 0.0017782459035515785,
+ "history": [
+ {
+ "step": 500,
+ "avg_cos": 0.2899630069732666,
+ "avg_rho": 0.3076498980323474,
+ "avg_nudge": -0.10753695170084636,
+ "loss_term": 0.49082812666893005,
+ "loss_bridge": 0.21152979135513306
+ },
+ {
+ "step": 1000,
+ "avg_cos": 0.17747302974263826,
+ "avg_rho": 0.17881879458824793,
+ "avg_nudge": -0.06420790683478117,
+ "loss_term": 0.1407778263092041,
+ "loss_bridge": 0.15578678250312805
+ },
+ {
+ "step": 1500,
+ "avg_cos": 0.08065215001503627,
+ "avg_rho": 0.08029377926141024,
+ "avg_nudge": -0.029326035796354216,
+ "loss_term": 0.07120706140995026,
+ "loss_bridge": 0.09130121767520905
+ },
+ {
+ "step": 2000,
+ "avg_cos": 0.0563324602941672,
+ "avg_rho": 0.058026942308060825,
+ "avg_nudge": -0.01875296530003349,
+ "loss_term": 0.06783974170684814,
+ "loss_bridge": 0.01712188683450222
+ },
+ {
+ "step": 2500,
+ "avg_cos": 0.039659525423000254,
+ "avg_rho": 0.04613731553157171,
+ "avg_nudge": -0.013568413676694036,
+ "loss_term": 0.0634445995092392,
+ "loss_bridge": 0.02091756835579872
+ },
+ {
+ "step": 3000,
+ "avg_cos": 0.04386034506993989,
+ "avg_rho": 0.039356538482631244,
+ "avg_nudge": -0.01407914562150836,
+ "loss_term": 0.05031818151473999,
+ "loss_bridge": 0.01259439717978239
+ },
+ {
+ "step": 3500,
+ "avg_cos": 0.0481002099889641,
+ "avg_rho": 0.03689269566287597,
+ "avg_nudge": -0.01590493693947792,
+ "loss_term": 0.03421805799007416,
+ "loss_bridge": 0.014973677694797516
+ },
+ {
+ "step": 4000,
+ "avg_cos": 0.07999587121109168,
+ "avg_rho": 0.07683291751891375,
+ "avg_nudge": -0.02731190746029218,
+ "loss_term": 0.04726963862776756,
+ "loss_bridge": 0.017824556678533554
+ },
+ {
+ "step": 4500,
+ "avg_cos": 0.07246351769814889,
+ "avg_rho": 0.07343382605661948,
+ "avg_nudge": -0.027415843835721414,
+ "loss_term": 0.02768528461456299,
+ "loss_bridge": 0.013396943919360638
+ },
+ {
+ "step": 5000,
+ "avg_cos": 0.0024576462844076255,
+ "avg_rho": 0.010072723651925722,
+ "avg_nudge": 0.0017782459035515785,
+ "loss_term": 0.02114972099661827,
+ "loss_bridge": 0.011466547846794128
+ }
+ ]
+ },
+ "noise_lam": {
+ "best_cos": 0.28980905935168266,
+ "best_step": 500,
+ "final_cos": 0.000333610107190907,
+ "final_rho": 0.009229002442831794,
+ "final_nudge": 0.0020260093733668327,
+ "history": [
+ {
+ "step": 500,
+ "avg_cos": 0.28980905935168266,
+ "avg_rho": 0.30755361666282016,
+ "avg_nudge": -0.10748158146937688,
+ "loss_term": 0.4891643524169922,
+ "loss_bridge": 0.21093463897705078
+ },
+ {
+ "step": 1000,
+ "avg_cos": 0.1692807301878929,
+ "avg_rho": 0.17357065031925836,
+ "avg_nudge": -0.060928904761870704,
+ "loss_term": 0.12851648032665253,
+ "loss_bridge": 0.1991802453994751
+ },
+ {
+ "step": 1500,
+ "avg_cos": 0.08976124723752339,
+ "avg_rho": 0.08664474201699097,
+ "avg_nudge": -0.032548267083863415,
+ "loss_term": 0.08289942145347595,
+ "loss_bridge": 0.08361449092626572
+ },
+ {
+ "step": 2000,
+ "avg_cos": 0.0449219069754084,
+ "avg_rho": 0.03701058775186539,
+ "avg_nudge": -0.013820620176071921,
+ "loss_term": 0.07352523505687714,
+ "loss_bridge": 0.031066572293639183
+ },
+ {
+ "step": 2500,
+ "avg_cos": 0.0341803894067804,
+ "avg_rho": 0.04086895197785149,
+ "avg_nudge": -0.011834259377792478,
+ "loss_term": 0.05221429467201233,
+ "loss_bridge": 0.013445280492305756
+ },
+ {
+ "step": 3000,
+ "avg_cos": 0.043432267770792045,
+ "avg_rho": 0.035848827101290226,
+ "avg_nudge": -0.0138394293996195,
+ "loss_term": 0.08377102017402649,
+ "loss_bridge": 0.02437596395611763
+ },
+ {
+ "step": 3500,
+ "avg_cos": 0.04308730812044814,
+ "avg_rho": 0.02904196917855491,
+ "avg_nudge": -0.013877601828426123,
+ "loss_term": 0.028318829834461212,
+ "loss_bridge": 0.0096125528216362
+ },
+ {
+ "step": 4000,
+ "avg_cos": 0.07217423028002183,
+ "avg_rho": 0.07531639956869185,
+ "avg_nudge": -0.024754961564516027,
+ "loss_term": 0.04526568949222565,
+ "loss_bridge": 0.01877186819911003
+ },
+ {
+ "step": 4500,
+ "avg_cos": 0.041415012208744884,
+ "avg_rho": 0.039630077119606234,
+ "avg_nudge": -0.013629865366965532,
+ "loss_term": 0.0305576603859663,
+ "loss_bridge": 0.011333338916301727
+ },
+ {
+ "step": 5000,
+ "avg_cos": 0.000333610107190907,
+ "avg_rho": 0.009229002442831794,
+ "avg_nudge": 0.0020260093733668327,
+ "loss_term": 0.020293015986680984,
+ "loss_bridge": 0.00792770553380251
+ }
+ ]
+ },
+ "no_ln": {
+ "best_cos": 0.2994285201032956,
+ "best_step": 500,
+ "final_cos": -0.027601251068214577,
+ "final_rho": -0.03011056105606258,
+ "final_nudge": 0.013365049380809069,
+ "history": [
+ {
+ "step": 500,
+ "avg_cos": 0.2994285201032956,
+ "avg_rho": 0.3287110353509585,
+ "avg_nudge": -0.11226618165771167,
+ "loss_term": 0.5378487706184387,
+ "loss_bridge": 0.20209679007530212
+ },
+ {
+ "step": 1000,
+ "avg_cos": 0.23427631705999374,
+ "avg_rho": 0.24483238657315573,
+ "avg_nudge": -0.08577251620590687,
+ "loss_term": 0.14587438106536865,
+ "loss_bridge": 0.17536549270153046
+ },
+ {
+ "step": 1500,
+ "avg_cos": 0.10971186744670074,
+ "avg_rho": 0.1081712432205677,
+ "avg_nudge": -0.039541066934665046,
+ "loss_term": 0.09813931584358215,
+ "loss_bridge": 0.1144137978553772
+ },
+ {
+ "step": 2000,
+ "avg_cos": 0.17568999342620373,
+ "avg_rho": 0.18043102137744427,
+ "avg_nudge": -0.06037815675760309,
+ "loss_term": 0.12119113653898239,
+ "loss_bridge": 0.05170433223247528
+ },
+ {
+ "step": 2500,
+ "avg_cos": 0.1501085925847292,
+ "avg_rho": 0.1694059126699964,
+ "avg_nudge": -0.05651436994473139,
+ "loss_term": 0.07073387503623962,
+ "loss_bridge": 0.015867799520492554
+ },
+ {
+ "step": 3000,
+ "avg_cos": 0.10612630782028039,
+ "avg_rho": 0.09910948442605634,
+ "avg_nudge": -0.034841354160259165,
+ "loss_term": 0.05772688612341881,
+ "loss_bridge": 0.0220709890127182
+ },
+ {
+ "step": 3500,
+ "avg_cos": 0.12348712608218193,
+ "avg_rho": 0.12745930068194866,
+ "avg_nudge": -0.04433920063699285,
+ "loss_term": 0.04150111600756645,
+ "loss_bridge": 0.014408521354198456
+ },
+ {
+ "step": 4000,
+ "avg_cos": 0.012287488003494218,
+ "avg_rho": 0.038615713633286454,
+ "avg_nudge": -0.006448045140132308,
+ "loss_term": 0.04848453402519226,
+ "loss_bridge": 0.026737889274954796
+ },
+ {
+ "step": 4500,
+ "avg_cos": 0.0344570055603981,
+ "avg_rho": 0.043244189505154886,
+ "avg_nudge": -0.012965732564528784,
+ "loss_term": 0.04390523582696915,
+ "loss_bridge": 0.016968518495559692
+ },
+ {
+ "step": 5000,
+ "avg_cos": -0.027601251068214577,
+ "avg_rho": -0.03011056105606258,
+ "avg_nudge": 0.013365049380809069,
+ "loss_term": 0.05419892817735672,
+ "loss_bridge": 0.029718749225139618
+ }
+ ]
+ },
+ "big_vnet": {
+ "best_cos": 0.25947993124524754,
+ "best_step": 500,
+ "final_cos": 0.012725223108039549,
+ "final_rho": -0.0029713623225688934,
+ "final_nudge": -0.0007455882926781973,
+ "history": [
+ {
+ "step": 500,
+ "avg_cos": 0.25947993124524754,
+ "avg_rho": 0.2872927797337373,
+ "avg_nudge": -0.09759780826667945,
+ "loss_term": 0.24058431386947632,
+ "loss_bridge": 0.20110812783241272
+ },
+ {
+ "step": 1000,
+ "avg_cos": 0.11903308952848117,
+ "avg_rho": 0.10757205138603847,
+ "avg_nudge": -0.04069022353117665,
+ "loss_term": 0.1535366326570511,
+ "loss_bridge": 0.10731971263885498
+ },
+ {
+ "step": 1500,
+ "avg_cos": 0.04738504672423005,
+ "avg_rho": 0.04187516961246729,
+ "avg_nudge": -0.01667174060518543,
+ "loss_term": 0.12195796519517899,
+ "loss_bridge": 0.03276967257261276
+ },
+ {
+ "step": 2000,
+ "avg_cos": 0.05584627948701382,
+ "avg_rho": 0.06464844088380535,
+ "avg_nudge": -0.019484267104417086,
+ "loss_term": 0.07039390504360199,
+ "loss_bridge": 0.023653611540794373
+ },
+ {
+ "step": 2500,
+ "avg_cos": 0.11334512817362945,
+ "avg_rho": 0.13342145457863808,
+ "avg_nudge": -0.04256325137491027,
+ "loss_term": 0.09321287274360657,
+ "loss_bridge": 0.03603611886501312
+ },
+ {
+ "step": 3000,
+ "avg_cos": 0.07876436489944656,
+ "avg_rho": 0.08206061793801685,
+ "avg_nudge": -0.02565166230003039,
+ "loss_term": 0.03433217480778694,
+ "loss_bridge": 0.014776414260268211
+ },
+ {
+ "step": 3500,
+ "avg_cos": 0.059695989514390625,
+ "avg_rho": 0.043808821588754654,
+ "avg_nudge": -0.01833860871071617,
+ "loss_term": 0.07867280393838882,
+ "loss_bridge": 0.04651641845703125
+ },
+ {
+ "step": 4000,
+ "avg_cos": 0.008286381295571724,
+ "avg_rho": 0.01973852072842419,
+ "avg_nudge": -0.0019318210737158854,
+ "loss_term": 0.03502834588289261,
+ "loss_bridge": 0.011813998222351074
+ },
+ {
+ "step": 4500,
+ "avg_cos": -0.006770744492920737,
+ "avg_rho": 2.3505534045398235e-05,
+ "avg_nudge": 0.002897862965861956,
+ "loss_term": 0.04147114232182503,
+ "loss_bridge": 0.026934277266263962
+ },
+ {
+ "step": 5000,
+ "avg_cos": 0.012725223108039549,
+ "avg_rho": -0.0029713623225688934,
+ "avg_nudge": -0.0007455882926781973,
+ "loss_term": 0.038749027997255325,
+ "loss_bridge": 0.01941092312335968
+ }
+ ]
+ },
+ "ema_0.999": {
+ "best_cos": 0.10180055970946948,
+ "best_step": 1000,
+ "final_cos": -0.01584776126158734,
+ "final_rho": -0.01703926082700491,
+ "final_nudge": 0.007290713644276063,
+ "history": [
+ {
+ "step": 500,
+ "avg_cos": -0.005628384804974,
+ "avg_rho": 0.010925033983464042,
+ "avg_nudge": 0.0015428058492640655,
+ "loss_term": 0.5920301675796509,
+ "loss_bridge": 1.4890536069869995
+ },
+ {
+ "step": 1000,
+ "avg_cos": 0.10180055970946948,
+ "avg_rho": 0.10515290250380833,
+ "avg_nudge": -0.037424925404290356,
+ "loss_term": 0.5715007185935974,
+ "loss_bridge": 0.4665977954864502
+ },
+ {
+ "step": 1500,
+ "avg_cos": 0.021814276037427287,
+ "avg_rho": 0.003451728650058309,
+ "avg_nudge": -0.005690907438596089,
+ "loss_term": 0.2616257071495056,
+ "loss_bridge": 0.2758212387561798
+ },
+ {
+ "step": 2000,
+ "avg_cos": 0.03669632730695108,
+ "avg_rho": 0.036930523036668696,
+ "avg_nudge": -0.01006293793519338,
+ "loss_term": 0.11164076626300812,
+ "loss_bridge": 0.1407940685749054
+ },
+ {
+ "step": 2500,
+ "avg_cos": -0.020325756592986483,
+ "avg_rho": -0.027848235641916592,
+ "avg_nudge": 0.011153894321372112,
+ "loss_term": 0.15471391379833221,
+ "loss_bridge": 0.06181420385837555
+ },
+ {
+ "step": 3000,
+ "avg_cos": -0.0060501456415901584,
+ "avg_rho": -0.013405103546877703,
+ "avg_nudge": 0.005228333951284488,
+ "loss_term": 0.07506504654884338,
+ "loss_bridge": 0.08207326382398605
+ },
+ {
+ "step": 3500,
+ "avg_cos": -0.02149865326161186,
+ "avg_rho": -0.023167532014970977,
+ "avg_nudge": 0.010358475303898254,
+ "loss_term": 0.048137497156858444,
+ "loss_bridge": 0.03276998922228813
+ },
+ {
+ "step": 4000,
+ "avg_cos": -0.007104064881180723,
+ "avg_rho": -0.00720199760204802,
+ "avg_nudge": 0.005406570465614398,
+ "loss_term": 0.03773114085197449,
+ "loss_bridge": 0.037960827350616455
+ },
+ {
+ "step": 4500,
+ "avg_cos": -0.0034141440119128674,
+ "avg_rho": -0.003708663280121982,
+ "avg_nudge": 0.002461720102777084,
+ "loss_term": 0.0416095145046711,
+ "loss_bridge": 0.03200625628232956
+ },
+ {
+ "step": 5000,
+ "avg_cos": -0.01584776126158734,
+ "avg_rho": -0.01703926082700491,
+ "avg_nudge": 0.007290713644276063,
+ "loss_term": 0.023291591554880142,
+ "loss_bridge": 0.026996765285730362
+ }
+ ]
+ },
+ "K16": {
+ "best_cos": 0.3187306026617686,
+ "best_step": 500,
+ "final_cos": 0.012039402422184745,
+ "final_rho": -0.002023946028202772,
+ "final_nudge": -0.0010173787983755271,
+ "history": [
+ {
+ "step": 500,
+ "avg_cos": 0.3187306026617686,
+ "avg_rho": 0.3298306291302045,
+ "avg_nudge": -0.12337777391076088,
+ "loss_term": 0.3945310413837433,
+ "loss_bridge": 0.27078020572662354
+ },
+ {
+ "step": 1000,
+ "avg_cos": 0.15608959334592024,
+ "avg_rho": 0.14268888781468073,
+ "avg_nudge": -0.05713697926451763,
+ "loss_term": 0.13724187016487122,
+ "loss_bridge": 0.13912135362625122
+ },
+ {
+ "step": 1500,
+ "avg_cos": 0.07919560000300407,
+ "avg_rho": 0.08190769484887521,
+ "avg_nudge": -0.029933936273058254,
+ "loss_term": 0.08082282543182373,
+ "loss_bridge": 0.07666538655757904
+ },
+ {
+ "step": 2000,
+ "avg_cos": 0.06641554242620866,
+ "avg_rho": 0.055935436549286045,
+ "avg_nudge": -0.020354578581949074,
+ "loss_term": 0.07134468108415604,
+ "loss_bridge": 0.011993557214736938
+ },
+ {
+ "step": 2500,
+ "avg_cos": 0.0844428426741312,
+ "avg_rho": 0.0917752521733443,
+ "avg_nudge": -0.028687965202455718,
+ "loss_term": 0.0323462039232254,
+ "loss_bridge": 0.00667245127260685
+ },
+ {
+ "step": 3000,
+ "avg_cos": 0.0888429010907809,
+ "avg_rho": 0.06338833862294753,
+ "avg_nudge": -0.026075587142258883,
+ "loss_term": 0.04170331731438637,
+ "loss_bridge": 0.010068882256746292
+ },
+ {
+ "step": 3500,
+ "avg_cos": 0.016165781184099615,
+ "avg_rho": 0.014142975055923065,
+ "avg_nudge": -0.003436643397435546,
+ "loss_term": 0.03528498113155365,
+ "loss_bridge": 0.012309195473790169
+ },
+ {
+ "step": 4000,
+ "avg_cos": 0.06803990031282107,
+ "avg_rho": 0.055018783935035266,
+ "avg_nudge": -0.022906929564972717,
+ "loss_term": 0.027342472225427628,
+ "loss_bridge": 0.007336604408919811
+ },
+ {
+ "step": 4500,
+ "avg_cos": 0.024216643689821165,
+ "avg_rho": 0.04094697698019445,
+ "avg_nudge": -0.008364889615525803,
+ "loss_term": 0.027580715715885162,
+ "loss_bridge": 0.016118880361318588
+ },
+ {
+ "step": 5000,
+ "avg_cos": 0.012039402422184745,
+ "avg_rho": -0.002023946028202772,
+ "avg_nudge": -0.0010173787983755271,
+ "loss_term": 0.027855150401592255,
+ "loss_bridge": 0.010500052943825722
+ }
+ ]
+ },
+ "best_combo": {
+ "best_cos": 0.30479515840609867,
+ "best_step": 500,
+ "final_cos": -0.025737087552746136,
+ "final_rho": -0.01576789258979261,
+ "final_nudge": 0.011260819776604572,
+ "history": [
+ {
+ "step": 500,
+ "avg_cos": 0.30479515840609867,
+ "avg_rho": 0.33246727536122006,
+ "avg_nudge": -0.11396304952601592,
+ "loss_term": 0.5129790306091309,
+ "loss_bridge": 0.21324321627616882
+ },
+ {
+ "step": 1000,
+ "avg_cos": 0.24110793943206468,
+ "avg_rho": 0.24976263443628946,
+ "avg_nudge": -0.08793549550076325,
+ "loss_term": 0.14881110191345215,
+ "loss_bridge": 0.1860560178756714
+ },
+ {
+ "step": 1500,
+ "avg_cos": 0.12106851922969024,
+ "avg_rho": 0.11747027436892192,
+ "avg_nudge": -0.042971268917123474,
+ "loss_term": 0.10358402132987976,
+ "loss_bridge": 0.11228226125240326
+ },
+ {
+ "step": 2000,
+ "avg_cos": 0.19137668733795485,
+ "avg_rho": 0.2001398652791977,
+ "avg_nudge": -0.06597264126564066,
+ "loss_term": 0.0836295336484909,
+ "loss_bridge": 0.03368356451392174
+ },
+ {
+ "step": 2500,
+ "avg_cos": 0.1382010855789607,
+ "avg_rho": 0.15255235826286176,
+ "avg_nudge": -0.05140705577408274,
+ "loss_term": 0.058304790407419205,
+ "loss_bridge": 0.014804087579250336
+ },
+ {
+ "step": 3000,
+ "avg_cos": 0.0815443117171526,
+ "avg_rho": 0.07958398557578523,
+ "avg_nudge": -0.026181443439175684,
+ "loss_term": 0.059965550899505615,
+ "loss_bridge": 0.016236742958426476
+ },
+ {
+ "step": 3500,
+ "avg_cos": 0.09519872162491083,
+ "avg_rho": 0.09258671143713097,
+ "avg_nudge": -0.03418003007148703,
+ "loss_term": 0.03956954926252365,
+ "loss_bridge": 0.014235305599868298
+ },
+ {
+ "step": 4000,
+ "avg_cos": -0.011209671385586262,
+ "avg_rho": -0.007080828654579818,
+ "avg_nudge": 0.004587161975602309,
+ "loss_term": 0.03683673217892647,
+ "loss_bridge": 0.018107034265995026
+ },
+ {
+ "step": 4500,
+ "avg_cos": 0.04608155476550261,
+ "avg_rho": 0.05846519426753124,
+ "avg_nudge": -0.017059470837314922,
+ "loss_term": 0.043314699083566666,
+ "loss_bridge": 0.023334285244345665
+ },
+ {
+ "step": 5000,
+ "avg_cos": -0.025737087552746136,
+ "avg_rho": -0.01576789258979261,
+ "avg_nudge": 0.011260819776604572,
+ "loss_term": 0.03279898688197136,
+ "loss_bridge": 0.015516506507992744
+ }
+ ]
+ },
+ "noise_1.0": {
+ "best_cos": 0.2831856335202853,
+ "best_step": 500,
+ "final_cos": 0.010971122809375325,
+ "final_rho": 0.014127362189659229,
+ "final_nudge": -0.002180874968568484,
+ "history": [
+ {
+ "step": 500,
+ "avg_cos": 0.2831856335202853,
+ "avg_rho": 0.30480503539244336,
+ "avg_nudge": -0.1052918794254462,
+ "loss_term": 0.4858350455760956,
+ "loss_bridge": 0.20565161108970642
+ },
+ {
+ "step": 1000,
+ "avg_cos": 0.14922113033632436,
+ "avg_rho": 0.14803783098856607,
+ "avg_nudge": -0.052950371988117695,
+ "loss_term": 0.1246427372097969,
+ "loss_bridge": 0.1951574981212616
+ },
+ {
+ "step": 1500,
+ "avg_cos": 0.032916761857147016,
+ "avg_rho": 0.030339293957998354,
+ "avg_nudge": -0.011420852970331907,
+ "loss_term": 0.059441905468702316,
+ "loss_bridge": 0.09553220868110657
+ },
+ {
+ "step": 2000,
+ "avg_cos": 0.02735897192421059,
+ "avg_rho": 0.019464978327353794,
+ "avg_nudge": -0.008191200438886881,
+ "loss_term": 0.07519456744194031,
+ "loss_bridge": 0.017568862065672874
+ },
+ {
+ "step": 2500,
+ "avg_cos": 0.02141591941472143,
+ "avg_rho": 0.027642763530214626,
+ "avg_nudge": -0.007318320373694102,
+ "loss_term": 0.05027623474597931,
+ "loss_bridge": 0.014622311107814312
+ },
+ {
+ "step": 3000,
+ "avg_cos": 0.048597725903770574,
+ "avg_rho": 0.03585781451935569,
+ "avg_nudge": -0.015588213689625263,
+ "loss_term": 0.06457968056201935,
+ "loss_bridge": 0.01680811122059822
+ },
+ {
+ "step": 3500,
+ "avg_cos": 0.06355043267831206,
+ "avg_rho": 0.04236283013597131,
+ "avg_nudge": -0.021118728754421074,
+ "loss_term": 0.035970453172922134,
+ "loss_bridge": 0.015534179285168648
+ },
+ {
+ "step": 4000,
+ "avg_cos": 0.04567302499587337,
+ "avg_rho": 0.05423017560193936,
+ "avg_nudge": -0.01528523334612449,
+ "loss_term": 0.034011729061603546,
+ "loss_bridge": 0.009947280399501324
+ },
+ {
+ "step": 4500,
+ "avg_cos": 0.024254882785802085,
+ "avg_rho": 0.023739464891453583,
+ "avg_nudge": -0.009648310175786415,
+ "loss_term": 0.04320281371474266,
+ "loss_bridge": 0.01757601648569107
+ },
+ {
+ "step": 5000,
+ "avg_cos": 0.010971122809375325,
+ "avg_rho": 0.014127362189659229,
+ "avg_nudge": -0.002180874968568484,
+ "loss_term": 0.024934478104114532,
+ "loss_bridge": 0.011717695742845535
+ }
+ ]
+ },
+ "lr_3e-4": {
+ "best_cos": 0.6101815849542618,
+ "best_step": 500,
+ "final_cos": -0.008048781737064322,
+ "final_rho": -0.026018392760306597,
+ "final_nudge": 0.007571722225596507,
+ "history": [
+ {
+ "step": 500,
+ "avg_cos": 0.6101815849542618,
+ "avg_rho": 0.620405301451683,
+ "avg_nudge": -0.2231019102036953,
+ "loss_term": 3.107595205307007,
+ "loss_bridge": 2.7781143188476562
+ },
+ {
+ "step": 1000,
+ "avg_cos": 0.39656415830055874,
+ "avg_rho": 0.39799897621075314,
+ "avg_nudge": -0.14455867062012354,
+ "loss_term": 0.29117679595947266,
+ "loss_bridge": 0.13909414410591125
+ },
+ {
+ "step": 1500,
+ "avg_cos": 0.26989879210789997,
+ "avg_rho": 0.2640038679043452,
+ "avg_nudge": -0.09908402090271314,
+ "loss_term": 0.1437155306339264,
+ "loss_bridge": 0.06845193356275558
+ },
+ {
+ "step": 2000,
+ "avg_cos": 0.15282577524582544,
+ "avg_rho": 0.1327554533878962,
+ "avg_nudge": -0.05070468131452799,
+ "loss_term": 0.10841675102710724,
+ "loss_bridge": 0.044324424117803574
+ },
+ {
+ "step": 2500,
+ "avg_cos": 0.054395756063361965,
+ "avg_rho": 0.04450509278103709,
+ "avg_nudge": -0.01604464929550886,
+ "loss_term": 0.09302366524934769,
+ "loss_bridge": 0.016296718269586563
+ },
+ {
+ "step": 3000,
+ "avg_cos": 0.041961303912103176,
+ "avg_rho": 0.032989607813457646,
+ "avg_nudge": -0.01202150775740544,
+ "loss_term": 0.06656567752361298,
+ "loss_bridge": 0.0089980224147439
+ },
+ {
+ "step": 3500,
+ "avg_cos": 0.010103868204168975,
+ "avg_rho": -0.01982816867530346,
+ "avg_nudge": 0.0005857348442077637,
+ "loss_term": 0.0479322224855423,
+ "loss_bridge": 0.004413220100104809
+ },
+ {
+ "step": 4000,
+ "avg_cos": 0.028387469239532948,
+ "avg_rho": 0.012580555553237597,
+ "avg_nudge": -0.006568876715997855,
+ "loss_term": 0.06536682695150375,
+ "loss_bridge": 0.005300351418554783
+ },
+ {
+ "step": 4500,
+ "avg_cos": 0.015142000513151288,
+ "avg_rho": 0.019022303090120356,
+ "avg_nudge": -0.004821705476691325,
+ "loss_term": 0.037237197160720825,
+ "loss_bridge": 0.005878066644072533
+ },
+ {
+ "step": 5000,
+ "avg_cos": -0.008048781737064322,
+ "avg_rho": -0.026018392760306597,
+ "avg_nudge": 0.007571722225596507,
+ "loss_term": 0.02460472844541073,
+ "loss_bridge": 0.005403056740760803
+ }
+ ]
+ }
+} \ No newline at end of file
diff --git a/results/toy_lq/toy_lq_seed42.json b/results/toy_lq/toy_lq_seed42.json
new file mode 100644
index 0000000..0a821be
--- /dev/null
+++ b/results/toy_lq/toy_lq_seed42.json
@@ -0,0 +1,335 @@
+{
+ "config": {
+ "d_hidden": 64,
+ "output_dim": 10,
+ "num_layers": 12,
+ "sigma": 0.03,
+ "batch_size": 256,
+ "num_steps": 5000,
+ "lr_fb": 0.001,
+ "lam": 0.1,
+ "K": 8,
+ "ema_momentum": 0.995,
+ "sigma_bridge": 0.03,
+ "eval_every": 500,
+ "seed": 42,
+ "gpu": 0,
+ "output_dir": "results/toy_lq"
+ },
+ "log": {
+ "steps": [
+ 1,
+ 500,
+ 1000,
+ 1500,
+ 2000,
+ 2500,
+ 3000,
+ 3500,
+ 4000,
+ 4500,
+ 5000
+ ],
+ "state_bridge_loss": [
+ 66.01814270019531,
+ 2.058396816253662,
+ 2.191567897796631,
+ 2.1112077236175537,
+ 2.2748100757598877,
+ 2.1154427528381348,
+ 2.0553503036499023,
+ 1.966332197189331,
+ 2.1147494316101074,
+ 2.007577896118164,
+ 2.0389387607574463
+ ],
+ "credit_bridge_loss": [
+ 112.22884368896484,
+ 0.5559965372085571,
+ 0.36617255210876465,
+ 0.22275042533874512,
+ 0.13448813557624817,
+ 0.0859837457537651,
+ 0.06448937207460403,
+ 0.03930438682436943,
+ 0.033317387104034424,
+ 0.03704077750444412,
+ 0.02309737727046013
+ ],
+ "dfa_costate_cos": [
+ 0.0011988391992277824,
+ 0.007705975646296373,
+ -0.0006242827870524847,
+ 0.0037568132393062115,
+ 0.004209253507164808,
+ -0.0012397096635630499,
+ 0.0033803660816584644,
+ 0.003754911944270134,
+ 0.002183924035097544,
+ 0.0057398807973815845,
+ 0.0028941635615550554
+ ],
+ "state_costate_cos": [
+ 0.009303608121207127,
+ 0.9451924241506137,
+ 0.9427064611361577,
+ 0.9456643370481638,
+ 0.947175892499777,
+ 0.9486432488148029,
+ 0.9405259856810937,
+ 0.9429925313362708,
+ 0.9463646090947665,
+ 0.9434385620630704,
+ 0.9468063895518963
+ ],
+ "credit_costate_cos": [
+ 0.03412332414434506,
+ 0.3051199523302225,
+ 0.2641584941974053,
+ 0.17990898627501267,
+ 0.11904546274588658,
+ 0.03094297769264533,
+ 0.022915477577883463,
+ 0.008693795901938127,
+ 0.0027211602920523058,
+ 0.020937439484091904,
+ 0.033342053540624104
+ ],
+ "dfa_rho": [
+ 0.005011526596111556,
+ 0.0020135376447190842,
+ -0.011304221504057447,
+ 0.003935044708972176,
+ 0.0159942601264144,
+ -0.011545649264007807,
+ 0.01096861291443929,
+ 0.0007782066240906715,
+ -0.015019190264865756,
+ 0.007689292387415965,
+ 0.006176682732378443
+ ],
+ "state_rho": [
+ 0.011923154350370169,
+ 0.9337877084811529,
+ 0.9292550335327784,
+ 0.9341330577929815,
+ 0.9364036619663239,
+ 0.9322425921758016,
+ 0.9240961174170176,
+ 0.9329939633607864,
+ 0.9331585764884949,
+ 0.9324665367603302,
+ 0.9281178514162699
+ ],
+ "credit_rho": [
+ 0.031667908265565835,
+ 0.31275976697603863,
+ 0.2433429310719172,
+ 0.1816188059747219,
+ 0.11667139704028766,
+ 0.013198353117331862,
+ 0.022044080891646445,
+ -0.007547003333456814,
+ -0.011566813724736372,
+ -0.003948230994865298,
+ 0.016950203105807304
+ ],
+ "dfa_nudge": [
+ -0.0003799900102118651,
+ -0.0025626374408602715,
+ 0.0017628272374471028,
+ -0.001205168974896272,
+ -0.0011821148606638114,
+ 0.0014717701512078445,
+ -8.787959814071655e-05,
+ -0.0006076549955954155,
+ 0.0005303900688886642,
+ -0.0014991160326947768,
+ -0.0005284918782611688
+ ],
+ "state_nudge": [
+ -0.002327537008871635,
+ -0.34574924657742184,
+ -0.3358767156799634,
+ -0.33698513607184094,
+ -0.3561149264375369,
+ -0.33514803399642307,
+ -0.3557068184018135,
+ -0.3218521823485692,
+ -0.33325668424367905,
+ -0.34358637283245724,
+ -0.34090926001469296
+ ],
+ "credit_nudge": [
+ -0.014598140881086389,
+ -0.11370646270612876,
+ -0.09322128010292847,
+ -0.06459770910441875,
+ -0.04436610918492079,
+ -0.008244700108965239,
+ -0.00636714743450284,
+ 0.0006991980286935965,
+ 0.0036097665627797446,
+ -0.0035287897723416486,
+ -0.007594603579491377
+ ],
+ "bridge_residual": [
+ 0.06566914729773998,
+ 0.37236853316426277,
+ 0.3114783614873886,
+ 0.26258066420753795,
+ 0.20779911428689957,
+ 0.13781529137243828,
+ 0.10999641008675098,
+ 0.07969006771842639,
+ 0.06178054213523865,
+ 0.07378745886186759,
+ 0.0832565538585186
+ ]
+ },
+ "final_per_layer": {
+ "dfa_costate_cos": [
+ -0.039167389273643494,
+ -0.0378018394112587,
+ 0.005690325051546097,
+ -0.023073989897966385,
+ -0.0005057593807578087,
+ -0.014485953375697136,
+ 0.03301015496253967,
+ 0.04401148855686188,
+ 0.054177843034267426,
+ 0.03981431573629379,
+ -0.04246171563863754,
+ -0.0012151142582297325,
+ 0.01963176019489765
+ ],
+ "state_costate_cos": [
+ 0.9444395303726196,
+ 0.9453534483909607,
+ 0.9460644721984863,
+ 0.9466040134429932,
+ 0.9469730257987976,
+ 0.9472954273223877,
+ 0.9476633667945862,
+ 0.9478192925453186,
+ 0.947782576084137,
+ 0.9473406672477722,
+ 0.947346568107605,
+ 0.9471475481987,
+ 0.9466531276702881
+ ],
+ "credit_costate_cos": [
+ 0.04752141237258911,
+ 0.04377397149801254,
+ 0.04051002860069275,
+ 0.03716123104095459,
+ 0.0350164994597435,
+ 0.03194836527109146,
+ 0.02999947965145111,
+ 0.02913709171116352,
+ 0.027683185413479805,
+ 0.0277146864682436,
+ 0.027703404426574707,
+ 0.027434173971414566,
+ 0.027843166142702103
+ ],
+ "dfa_rho": [
+ -0.04803554713726044,
+ 0.001050771214067936,
+ 0.008967258036136627,
+ -0.0271889790892601,
+ 0.02336559258401394,
+ -0.018210411071777344,
+ 0.05891512706875801,
+ 0.040720634162425995,
+ 0.07478035986423492,
+ 0.04802168905735016,
+ -0.06280035525560379,
+ -0.0254659466445446
+ ],
+ "state_rho": [
+ 0.9311305284500122,
+ 0.9222633838653564,
+ 0.9287852644920349,
+ 0.9287664890289307,
+ 0.9245603084564209,
+ 0.928197979927063,
+ 0.9275168180465698,
+ 0.9290561676025391,
+ 0.9267844557762146,
+ 0.927483081817627,
+ 0.9315245151519775,
+ 0.9313452243804932
+ ],
+ "credit_rho": [
+ 0.05740518122911453,
+ 0.035541512072086334,
+ 0.002091987058520317,
+ 0.024556485936045647,
+ -0.006993812508881092,
+ 0.03284040838479996,
+ 0.012268777936697006,
+ -0.004999782890081406,
+ 0.014774687588214874,
+ -0.010628825053572655,
+ 0.05940534919500351,
+ -0.012859531678259373
+ ],
+ "dfa_nudge": [
+ 0.01363457553088665,
+ 0.013758538290858269,
+ -0.0032786596566438675,
+ 0.010209780186414719,
+ -0.0013850200921297073,
+ 0.004463233053684235,
+ -0.012735363095998764,
+ -0.01801125332713127,
+ -0.019914839416742325,
+ -0.012350432574748993,
+ 0.017156170681118965,
+ 0.002111367881298065
+ ],
+ "state_nudge": [
+ -0.34207087755203247,
+ -0.3417494297027588,
+ -0.3413676619529724,
+ -0.3414176106452942,
+ -0.3412688076496124,
+ -0.34025871753692627,
+ -0.340381920337677,
+ -0.34054237604141235,
+ -0.3402785062789917,
+ -0.34061968326568604,
+ -0.34013575315475464,
+ -0.340819776058197
+ ],
+ "credit_nudge": [
+ -0.012597911059856415,
+ -0.011231275275349617,
+ -0.009987404569983482,
+ -0.008699672296643257,
+ -0.007977090775966644,
+ -0.006919408217072487,
+ -0.006156830117106438,
+ -0.005891043692827225,
+ -0.00546320341527462,
+ -0.005353953689336777,
+ -0.005423387512564659,
+ -0.005434062331914902
+ ],
+ "bridge_residual": [
+ 0.10028190910816193,
+ 0.09995798766613007,
+ 0.09832010418176651,
+ 0.09528136253356934,
+ 0.09090456366539001,
+ 0.0843343734741211,
+ 0.07823348790407181,
+ 0.0723348930478096,
+ 0.06821676343679428,
+ 0.06773027032613754,
+ 0.06943590939044952,
+ 0.0740470215678215
+ ]
+ }
+} \ No newline at end of file
diff --git a/results/toy_lq/toy_lq_v2_seed123_lam0.1_sig0.1_tgw1.0_fm0.0.json b/results/toy_lq/toy_lq_v2_seed123_lam0.1_sig0.1_tgw1.0_fm0.0.json
new file mode 100644
index 0000000..56b3336
--- /dev/null
+++ b/results/toy_lq/toy_lq_v2_seed123_lam0.1_sig0.1_tgw1.0_fm0.0.json
@@ -0,0 +1,330 @@
+{
+ "config": {
+ "d_hidden": 64,
+ "output_dim": 10,
+ "num_layers": 12,
+ "sigma": 0.03,
+ "batch_size": 256,
+ "num_steps": 8000,
+ "lr_fb": 0.001,
+ "lam": 0.1,
+ "K": 8,
+ "ema_momentum": 0.995,
+ "sigma_bridge": 0.1,
+ "eval_every": 1000,
+ "seed": 123,
+ "gpu": 0,
+ "output_dir": "results/toy_lq",
+ "vnet_hidden": 256,
+ "vnet_layers": 3,
+ "term_grad_weight": 1.0,
+ "fm_weight": 0.0
+ },
+ "log": {
+ "steps": [
+ 1,
+ 1000,
+ 2000,
+ 3000,
+ 4000,
+ 5000,
+ 6000,
+ 7000,
+ 8000
+ ],
+ "dfa_costate_cos": [
+ 0.0061469420325011015,
+ 0.007492478704079986,
+ 0.006436596314112346,
+ 0.001648913836106658,
+ 0.005657717352733016,
+ 0.010142655577510595,
+ 0.005493079700196783,
+ 0.008208209726338586,
+ 0.002802101274331411
+ ],
+ "state_costate_cos": [
+ 0.04875442975511154,
+ 0.9345830877621969,
+ 0.9331425180037817,
+ 0.9344809154669443,
+ 0.9360056469837824,
+ 0.9349906196196874,
+ 0.9401087015867233,
+ 0.9377894500891367,
+ 0.9381228536367416
+ ],
+ "credit_costate_cos": [
+ 0.005350367398932576,
+ 0.8715064575274786,
+ 0.9082922885815302,
+ 0.9268463253974915,
+ 0.9348577807346979,
+ 0.9338823060194651,
+ 0.9398750513792038,
+ 0.9371217240889868,
+ 0.9403592944145203
+ ],
+ "dfa_rho": [
+ 0.014851124413932363,
+ 0.004832483362406492,
+ 0.005500619454930226,
+ 0.0014784028753638268,
+ 0.0024716570042073727,
+ 0.002679668522129456,
+ 0.004042171291075647,
+ 0.007841781480237842,
+ -0.003731151965136329
+ ],
+ "state_rho": [
+ 0.0525277191773057,
+ 0.9209283490975698,
+ 0.9212760378917059,
+ 0.9215241422255834,
+ 0.9252830098072687,
+ 0.9173514097929001,
+ 0.9268933484951655,
+ 0.9245105236768723,
+ 0.9267788628737131
+ ],
+ "credit_rho": [
+ 8.900166722014546e-05,
+ 0.8210234741369883,
+ 0.8804274102052053,
+ 0.9100336680809656,
+ 0.9228341629107794,
+ 0.9162226617336273,
+ 0.9262114216883978,
+ 0.9239083131154379,
+ 0.9273379941781362
+ ],
+ "dfa_nudge": [
+ -0.0020856610499322414,
+ -0.002391135785728693,
+ -0.0018826122395694256,
+ 0.0002794961134592692,
+ -0.0017084906188150246,
+ -0.0027558018919080496,
+ -0.0014085437481602032,
+ -0.0023310642379025617,
+ -0.0009137461893260479
+ ],
+ "state_nudge": [
+ -0.01762500188002984,
+ -0.31959830472866696,
+ -0.3143775438268979,
+ -0.3134472444653511,
+ -0.33237058420976,
+ -0.3183835695187251,
+ -0.32320864746967953,
+ -0.32294898976882297,
+ -0.31496328860521317
+ ],
+ "credit_nudge": [
+ -0.0004618208234508832,
+ -0.2996478999654452,
+ -0.30627985050280887,
+ -0.3099561383326848,
+ -0.33090290675560635,
+ -0.31673717498779297,
+ -0.3218600004911423,
+ -0.32163529098033905,
+ -0.31442063798507053
+ ],
+ "bridge_residual": [],
+ "state_bridge_loss": [
+ 64.66886901855469,
+ 1.9055249691009521,
+ 1.9802964925765991,
+ 1.9747117757797241,
+ 1.9333608150482178,
+ 2.0244460105895996,
+ 2.235288381576538,
+ 1.8483705520629883,
+ 1.833404541015625
+ ],
+ "credit_bridge_loss": [
+ 129.2601776123047,
+ 8.826760292053223,
+ 8.817267417907715,
+ 9.7413911819458,
+ 8.333325386047363,
+ 8.390682220458984,
+ 8.381990432739258,
+ 9.069635391235352,
+ 8.738546371459961
+ ],
+ "term_loss": [
+ 109.68403625488281,
+ 3.380112648010254,
+ 4.175432205200195,
+ 4.737654685974121,
+ 3.632157802581787,
+ 3.3351938724517822,
+ 3.776655912399292,
+ 4.416824817657471,
+ 4.120006084442139
+ ],
+ "bridge_loss": [
+ 5.943464884694549e-07,
+ 0.2433367669582367,
+ 0.18713834881782532,
+ 0.12417592853307724,
+ 0.13950209319591522,
+ 0.14192476868629456,
+ 0.15276893973350525,
+ 0.10663559287786484,
+ 0.12137635797262192
+ ],
+ "term_grad_loss": [
+ 19.57614517211914,
+ 5.203310966491699,
+ 4.4546966552734375,
+ 4.879560470581055,
+ 4.5616655349731445,
+ 4.9135637283325195,
+ 4.452565670013428,
+ 4.546175003051758,
+ 4.497163772583008
+ ],
+ "fm_loss": [
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0
+ ]
+ },
+ "final_per_layer": {
+ "dfa_costate_cos": [
+ 0.04479089006781578,
+ -0.04426354169845581,
+ 0.008874599821865559,
+ 0.05599997937679291,
+ 0.02961653470993042,
+ -0.022058574482798576,
+ 0.027186769992113113,
+ -0.0337681919336319,
+ -0.020245034247636795,
+ -0.04076787084341049,
+ 0.006424968130886555,
+ 0.021834686398506165
+ ],
+ "state_costate_cos": [
+ 0.9351104497909546,
+ 0.9362065196037292,
+ 0.9370632171630859,
+ 0.9374789595603943,
+ 0.9381210803985596,
+ 0.9385455846786499,
+ 0.9386894702911377,
+ 0.9390624165534973,
+ 0.9393105506896973,
+ 0.9393242597579956,
+ 0.9392982721328735,
+ 0.9392634630203247
+ ],
+ "credit_costate_cos": [
+ 0.9360430240631104,
+ 0.9369803667068481,
+ 0.9380120038986206,
+ 0.9385954141616821,
+ 0.9395070672035217,
+ 0.9403176307678223,
+ 0.9409258961677551,
+ 0.9413450956344604,
+ 0.9420279264450073,
+ 0.9428501725196838,
+ 0.9435971975326538,
+ 0.9441097378730774
+ ],
+ "dfa_rho": [
+ 0.041250549256801605,
+ -0.049739208072423935,
+ 0.00025176629424095154,
+ 0.04237007349729538,
+ 0.040798719972372055,
+ -0.037202395498752594,
+ 0.004211327061057091,
+ 0.0017704367637634277,
+ -0.04704931750893593,
+ -0.02992381900548935,
+ -0.01541070081293583,
+ 0.003898744471371174
+ ],
+ "state_rho": [
+ 0.9230573177337646,
+ 0.9292065501213074,
+ 0.9277745485305786,
+ 0.926990270614624,
+ 0.930223822593689,
+ 0.9262816905975342,
+ 0.9238564968109131,
+ 0.9235492944717407,
+ 0.927101731300354,
+ 0.929185152053833,
+ 0.9233707189559937,
+ 0.9307487607002258
+ ],
+ "credit_rho": [
+ 0.924521803855896,
+ 0.9213208556175232,
+ 0.923781156539917,
+ 0.9222273826599121,
+ 0.9230118989944458,
+ 0.9317750930786133,
+ 0.9238618016242981,
+ 0.9351733326911926,
+ 0.9263075590133667,
+ 0.9302359819412231,
+ 0.9358923435211182,
+ 0.9299467206001282
+ ],
+ "dfa_nudge": [
+ -0.01619502529501915,
+ 0.016632290557026863,
+ -0.004560360684990883,
+ -0.018955951556563377,
+ -0.011058392003178596,
+ 0.007517071440815926,
+ -0.008148249238729477,
+ 0.01091383583843708,
+ 0.006811931729316711,
+ 0.015017258003354073,
+ -0.000978708267211914,
+ -0.00796065479516983
+ ],
+ "state_nudge": [
+ -0.31427979469299316,
+ -0.3147982358932495,
+ -0.3148774206638336,
+ -0.3150269389152527,
+ -0.31536394357681274,
+ -0.3156891465187073,
+ -0.3149397373199463,
+ -0.3145085573196411,
+ -0.3144562840461731,
+ -0.31494998931884766,
+ -0.3152415156364441,
+ -0.31542789936065674
+ ],
+ "credit_nudge": [
+ -0.31250905990600586,
+ -0.3131006360054016,
+ -0.31331712007522583,
+ -0.31366780400276184,
+ -0.3142547011375427,
+ -0.3149237632751465,
+ -0.31442567706108093,
+ -0.314262330532074,
+ -0.31445154547691345,
+ -0.3153681755065918,
+ -0.3161371052265167,
+ -0.3166297376155853
+ ]
+ }
+} \ No newline at end of file
diff --git a/results/toy_lq/toy_lq_v2_seed42_lam0.1_sig0.1_tgw1.0_fm0.0.json b/results/toy_lq/toy_lq_v2_seed42_lam0.1_sig0.1_tgw1.0_fm0.0.json
new file mode 100644
index 0000000..14050eb
--- /dev/null
+++ b/results/toy_lq/toy_lq_v2_seed42_lam0.1_sig0.1_tgw1.0_fm0.0.json
@@ -0,0 +1,458 @@
+{
+ "config": {
+ "d_hidden": 64,
+ "output_dim": 10,
+ "num_layers": 12,
+ "sigma": 0.03,
+ "batch_size": 256,
+ "num_steps": 8000,
+ "lr_fb": 0.001,
+ "lam": 0.1,
+ "K": 8,
+ "ema_momentum": 0.995,
+ "sigma_bridge": 0.1,
+ "eval_every": 500,
+ "seed": 42,
+ "gpu": 0,
+ "output_dir": "results/toy_lq",
+ "vnet_hidden": 256,
+ "vnet_layers": 3,
+ "term_grad_weight": 1.0,
+ "fm_weight": 0.0
+ },
+ "log": {
+ "steps": [
+ 1,
+ 500,
+ 1000,
+ 1500,
+ 2000,
+ 2500,
+ 3000,
+ 3500,
+ 4000,
+ 4500,
+ 5000,
+ 5500,
+ 6000,
+ 6500,
+ 7000,
+ 7500,
+ 8000
+ ],
+ "dfa_costate_cos": [
+ 0.001022340264171362,
+ 0.00324871806272616,
+ 0.003955680275491129,
+ -6.335701133745412e-05,
+ 0.0009047117297692845,
+ -0.0015635235855976741,
+ 0.0050255006256823736,
+ 0.003974012487257521,
+ -0.0024126653637116155,
+ 0.0010036304011009634,
+ -0.0006338046708454689,
+ 0.00017608713824301958,
+ -9.714129070440929e-05,
+ -0.0011926805212472875,
+ -0.0026168684319903455,
+ -0.003671417556082209,
+ 0.0016770829679444432
+ ],
+ "state_costate_cos": [
+ 0.009337988216429949,
+ 0.943408285578092,
+ 0.9517824550469717,
+ 0.9448912839094797,
+ 0.9432462950547537,
+ 0.9444176405668259,
+ 0.9435405482848486,
+ 0.9443136354287466,
+ 0.9458288550376892,
+ 0.9465046127637228,
+ 0.9465998113155365,
+ 0.9461832990248998,
+ 0.9424780905246735,
+ 0.9474884221951166,
+ 0.9449383119742075,
+ 0.9425351719061533,
+ 0.9405365288257599
+ ],
+ "credit_costate_cos": [
+ 0.024892715892444055,
+ 0.8234576731920242,
+ 0.8861371924479803,
+ 0.8940252065658569,
+ 0.9119344304005305,
+ 0.928387979666392,
+ 0.9261951943238577,
+ 0.9374307443698248,
+ 0.939670259753863,
+ 0.9423713783423106,
+ 0.9447299987077713,
+ 0.944857731461525,
+ 0.9409955541292826,
+ 0.9459459533294042,
+ 0.9439971546332041,
+ 0.9420813073714575,
+ 0.9400773843129476
+ ],
+ "dfa_rho": [
+ 0.015879416760678094,
+ 0.004265802912414074,
+ 0.008714484671751658,
+ 0.001407407767449816,
+ 0.007156838779337704,
+ -0.0010706717148423195,
+ -0.00500367038572828,
+ 0.00037602245962868136,
+ 0.00797194141584138,
+ 0.012475600582547486,
+ 0.006475616673318048,
+ 0.006899521841357152,
+ 0.008204833992446462,
+ -0.0002780493038396041,
+ -0.009471656677002708,
+ -0.00781721225939691,
+ 0.025706250220537186
+ ],
+ "state_rho": [
+ 0.0029325426245729127,
+ 0.9265175064404806,
+ 0.938806007305781,
+ 0.9280826350053152,
+ 0.9287765026092529,
+ 0.9266663392384847,
+ 0.9301863809426626,
+ 0.9323704888423284,
+ 0.9297124246756235,
+ 0.9302101731300354,
+ 0.9340693553288778,
+ 0.9324037134647369,
+ 0.9265123655398687,
+ 0.9321505973736445,
+ 0.927787164847056,
+ 0.9323761165142059,
+ 0.9224280416965485
+ ],
+ "credit_rho": [
+ 0.02234963719577839,
+ 0.7719902147849401,
+ 0.8432890474796295,
+ 0.8447659462690353,
+ 0.877406562368075,
+ 0.8958166440327963,
+ 0.9122767845789591,
+ 0.9254603485266367,
+ 0.9236042300860087,
+ 0.9263056516647339,
+ 0.9323819329341253,
+ 0.9314924577871958,
+ 0.9266939163208008,
+ 0.929329847296079,
+ 0.9257104198137919,
+ 0.9289217789967855,
+ 0.9269137680530548
+ ],
+ "dfa_nudge": [
+ -0.0003799900102118651,
+ -0.0009698765352368355,
+ -0.0013957968913018703,
+ 0.00035563452790180844,
+ -0.0003614289841304223,
+ 0.0008372832089662552,
+ -0.0013908503266672294,
+ -0.0013163429684937,
+ 0.0005854369762043158,
+ -0.000560786963130037,
+ 0.00015371766251822314,
+ -1.0695696497956911e-05,
+ 2.807355485856533e-05,
+ 5.036763225992521e-05,
+ 0.0008217894161740938,
+ 0.0017250357971837123,
+ -0.0004334271264572938
+ ],
+ "state_nudge": [
+ -0.002327537008871635,
+ -0.34193428109089535,
+ -0.340603639682134,
+ -0.35042013972997665,
+ -0.3389856591820717,
+ -0.34554000198841095,
+ -0.3481511374314626,
+ -0.3558509051799774,
+ -0.3337947155038516,
+ -0.33715616663297016,
+ -0.33583804468313855,
+ -0.35106155276298523,
+ -0.34434546530246735,
+ -0.34641525397698086,
+ -0.3329972525437673,
+ -0.34870391835769016,
+ -0.3395152688026428
+ ],
+ "credit_nudge": [
+ -0.0079942528779308,
+ -0.30343081553777057,
+ -0.31936119496822357,
+ -0.33327333877484006,
+ -0.3284662067890167,
+ -0.3394550507267316,
+ -0.3424832498033841,
+ -0.3524467721581459,
+ -0.33071904132763547,
+ -0.3346964443723361,
+ -0.3337800477941831,
+ -0.34932391593853634,
+ -0.34230031818151474,
+ -0.3444634775320689,
+ -0.3310972551504771,
+ -0.34694332132736844,
+ -0.3377286195755005
+ ],
+ "bridge_residual": [],
+ "state_bridge_loss": [
+ 66.01814270019531,
+ 2.0012869834899902,
+ 2.1027088165283203,
+ 2.1019272804260254,
+ 2.0727572441101074,
+ 1.9770110845565796,
+ 2.1761908531188965,
+ 2.094480514526367,
+ 1.9725749492645264,
+ 2.0142102241516113,
+ 2.0340821743011475,
+ 1.9380583763122559,
+ 1.989743947982788,
+ 2.4057328701019287,
+ 2.19437575340271,
+ 2.1816155910491943,
+ 2.0803794860839844
+ ],
+ "credit_bridge_loss": [
+ 132.09298706054688,
+ 11.307573318481445,
+ 9.575517654418945,
+ 8.768391609191895,
+ 8.752981185913086,
+ 9.271968841552734,
+ 8.606213569641113,
+ 8.753968238830566,
+ 8.223488807678223,
+ 9.935165405273438,
+ 9.02967357635498,
+ 8.346063613891602,
+ 9.022041320800781,
+ 8.36446762084961,
+ 8.635725021362305,
+ 8.760185241699219,
+ 8.503408432006836
+ ],
+ "term_loss": [
+ 111.63633728027344,
+ 4.978545188903809,
+ 3.8962953090667725,
+ 3.81073260307312,
+ 4.386394500732422,
+ 4.507748603820801,
+ 3.6740365028381348,
+ 3.7450127601623535,
+ 3.5060954093933105,
+ 4.545898914337158,
+ 4.322302341461182,
+ 3.594371795654297,
+ 4.038668632507324,
+ 4.025404453277588,
+ 3.9016177654266357,
+ 3.7638583183288574,
+ 3.807260036468506
+ ],
+ "bridge_loss": [
+ 6.45359421014291e-07,
+ 0.432157039642334,
+ 0.20619139075279236,
+ 0.24715952575206757,
+ 0.1523856669664383,
+ 0.12624874711036682,
+ 0.13425695896148682,
+ 0.16367560625076294,
+ 0.14530189335346222,
+ 0.18452416360378265,
+ 0.11599670350551605,
+ 0.11983858048915863,
+ 0.11901542544364929,
+ 0.16489851474761963,
+ 0.16058529913425446,
+ 0.09414370357990265,
+ 0.12402483820915222
+ ],
+ "term_grad_loss": [
+ 20.456655502319336,
+ 5.8968706130981445,
+ 5.4730305671691895,
+ 4.710499286651611,
+ 4.214200496673584,
+ 4.637970924377441,
+ 4.797920227050781,
+ 4.845280170440674,
+ 4.572091579437256,
+ 5.204742908477783,
+ 4.591374397277832,
+ 4.631853103637695,
+ 4.864356994628906,
+ 4.174164772033691,
+ 4.573522090911865,
+ 4.9021830558776855,
+ 4.5721235275268555
+ ],
+ "fm_loss": [
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0
+ ]
+ },
+ "final_per_layer": {
+ "dfa_costate_cos": [
+ -0.03974368795752525,
+ -0.03234883397817612,
+ -0.01280729565769434,
+ -0.03282422572374344,
+ 0.005050511099398136,
+ -0.01393066719174385,
+ 0.036346256732940674,
+ 0.04377925395965576,
+ 0.06324614584445953,
+ 0.05324942618608475,
+ -0.04297419637441635,
+ -0.006917691323906183
+ ],
+ "state_costate_cos": [
+ 0.9383341073989868,
+ 0.9390445947647095,
+ 0.9393846988677979,
+ 0.9396730661392212,
+ 0.9402315616607666,
+ 0.940619707107544,
+ 0.9413514137268066,
+ 0.9420933723449707,
+ 0.941848874092102,
+ 0.9416857957839966,
+ 0.9411274194717407,
+ 0.9410437345504761
+ ],
+ "credit_costate_cos": [
+ 0.937440037727356,
+ 0.9379364252090454,
+ 0.9384041428565979,
+ 0.9385387897491455,
+ 0.9392049312591553,
+ 0.9398118257522583,
+ 0.9403334259986877,
+ 0.9412999153137207,
+ 0.94156414270401,
+ 0.9419326186180115,
+ 0.9419490098953247,
+ 0.9425133466720581
+ ],
+ "dfa_rho": [
+ -0.023802103474736214,
+ -0.039411380887031555,
+ -0.008970402181148529,
+ -0.0021191751584410667,
+ 0.04573667049407959,
+ 0.010564171709120274,
+ 0.04995737224817276,
+ 0.10094872862100601,
+ 0.07801118493080139,
+ 0.07188688963651657,
+ -0.02006501331925392,
+ 0.045738060027360916
+ ],
+ "state_rho": [
+ 0.9204449653625488,
+ 0.917449951171875,
+ 0.9193954467773438,
+ 0.9267550706863403,
+ 0.9280773401260376,
+ 0.9225738048553467,
+ 0.9190236926078796,
+ 0.924782931804657,
+ 0.9248216152191162,
+ 0.9217315912246704,
+ 0.9215092658996582,
+ 0.9225708246231079
+ ],
+ "credit_rho": [
+ 0.9222818613052368,
+ 0.923028826713562,
+ 0.924055814743042,
+ 0.9263180494308472,
+ 0.9288915991783142,
+ 0.922785758972168,
+ 0.9231191873550415,
+ 0.9254114627838135,
+ 0.9321990013122559,
+ 0.9311563372612,
+ 0.934211015701294,
+ 0.9295063018798828
+ ],
+ "dfa_nudge": [
+ 0.014356113970279694,
+ 0.013086749240756035,
+ 0.004036703146994114,
+ 0.011657552793622017,
+ -0.0023863790556788445,
+ 0.006091207265853882,
+ -0.013204541988670826,
+ -0.016102034598588943,
+ -0.022989045828580856,
+ -0.018843289464712143,
+ 0.015521062538027763,
+ 0.0035747764632105827
+ ],
+ "state_nudge": [
+ -0.34063079953193665,
+ -0.34022200107574463,
+ -0.33977580070495605,
+ -0.3401387929916382,
+ -0.34019535779953003,
+ -0.33964985609054565,
+ -0.3392874002456665,
+ -0.33898109197616577,
+ -0.3392573297023773,
+ -0.3390581011772156,
+ -0.33809930086135864,
+ -0.33888739347457886
+ ],
+ "credit_nudge": [
+ -0.3375471234321594,
+ -0.33736705780029297,
+ -0.33710652589797974,
+ -0.33756691217422485,
+ -0.3378610908985138,
+ -0.33758991956710815,
+ -0.33741605281829834,
+ -0.3374325633049011,
+ -0.33806926012039185,
+ -0.33822208642959595,
+ -0.33765909075737,
+ -0.3389057517051697
+ ]
+ }
+} \ No newline at end of file
diff --git a/results/toy_lq/toy_lq_v2_seed42_lam0.1_sig0.1_tgw1.0_fm0.1.json b/results/toy_lq/toy_lq_v2_seed42_lam0.1_sig0.1_tgw1.0_fm0.1.json
new file mode 100644
index 0000000..2977e98
--- /dev/null
+++ b/results/toy_lq/toy_lq_v2_seed42_lam0.1_sig0.1_tgw1.0_fm0.1.json
@@ -0,0 +1,330 @@
+{
+ "config": {
+ "d_hidden": 64,
+ "output_dim": 10,
+ "num_layers": 12,
+ "sigma": 0.03,
+ "batch_size": 256,
+ "num_steps": 8000,
+ "lr_fb": 0.001,
+ "lam": 0.1,
+ "K": 8,
+ "ema_momentum": 0.995,
+ "sigma_bridge": 0.1,
+ "eval_every": 1000,
+ "seed": 42,
+ "gpu": 0,
+ "output_dir": "results/toy_lq",
+ "vnet_hidden": 256,
+ "vnet_layers": 3,
+ "term_grad_weight": 1.0,
+ "fm_weight": 0.1
+ },
+ "log": {
+ "steps": [
+ 1,
+ 1000,
+ 2000,
+ 3000,
+ 4000,
+ 5000,
+ 6000,
+ 7000,
+ 8000
+ ],
+ "dfa_costate_cos": [
+ -0.003210080186060319,
+ 0.006517285481095314,
+ 0.002081584728633364,
+ 0.002482607301014165,
+ 0.0003743169557613631,
+ -0.0018058015266433358,
+ 0.005970992535973589,
+ 0.0013112322388527293,
+ -0.00010686229992037018
+ ],
+ "state_costate_cos": [
+ -0.008148168989767631,
+ 0.942050834496816,
+ 0.9447367936372757,
+ 0.9457606921593348,
+ 0.9468860725561777,
+ 0.9432125687599182,
+ 0.9417577485243479,
+ 0.945394163330396,
+ 0.9473433345556259
+ ],
+ "credit_costate_cos": [
+ -0.011870964197441936,
+ 0.8804089923699697,
+ 0.9169842700163523,
+ 0.9352772484223048,
+ 0.9427581528822581,
+ 0.9391989062229792,
+ 0.9398341725269953,
+ 0.9456242968638738,
+ 0.9460541109244028
+ ],
+ "dfa_rho": [
+ -0.012772266054525971,
+ 0.015942092907304566,
+ 0.008943260026474794,
+ 0.004492536109561722,
+ -0.007791806012392044,
+ -0.007830069400370121,
+ 0.014392409706488252,
+ 0.0063066319562494755,
+ -0.001311147507900993
+ ],
+ "state_rho": [
+ -0.0018634579222028453,
+ 0.9263874938090643,
+ 0.9358506997426351,
+ 0.9348766555388769,
+ 0.9348586251338323,
+ 0.9323162386814753,
+ 0.9287882298231125,
+ 0.9243461688359579,
+ 0.9346484492222468
+ ],
+ "credit_rho": [
+ -0.023325924955618877,
+ 0.8106876164674759,
+ 0.8797721316417059,
+ 0.9208102275927862,
+ 0.9290666033824285,
+ 0.9226995905240377,
+ 0.9258128056923548,
+ 0.9266915867726008,
+ 0.9364602218071619
+ ],
+ "dfa_nudge": [
+ 0.0015840742271393538,
+ -0.0023392424918711185,
+ -0.0002702907659113407,
+ -0.0010186488119264443,
+ -0.0001735797462364038,
+ 0.000983052421361208,
+ -0.0020705487113445997,
+ -0.0009097627674539884,
+ 0.0002721068449318409
+ ],
+ "state_nudge": [
+ 0.0024757004963854947,
+ -0.33942782630523044,
+ -0.35110870252052945,
+ -0.35064691056807834,
+ -0.3403419057528178,
+ -0.3532385254899661,
+ -0.33996084084113437,
+ -0.35185040285189945,
+ -0.3480343023935954
+ ],
+ "credit_nudge": [
+ 0.006069206205817561,
+ -0.31947339574495953,
+ -0.3404841795563698,
+ -0.3458903282880783,
+ -0.3376796667774518,
+ -0.3504715636372566,
+ -0.3379351521531741,
+ -0.3500200683871905,
+ -0.3462969238559405
+ ],
+ "bridge_residual": [],
+ "state_bridge_loss": [
+ 66.01814270019531,
+ 2.341611623764038,
+ 1.9537389278411865,
+ 1.9830116033554077,
+ 2.0491604804992676,
+ 2.0490386486053467,
+ 2.1182405948638916,
+ 2.373213291168213,
+ 1.9122812747955322
+ ],
+ "credit_bridge_loss": [
+ 132.09298706054688,
+ 9.123503684997559,
+ 8.516526222229004,
+ 8.634014129638672,
+ 8.720410346984863,
+ 8.43734359741211,
+ 10.247673034667969,
+ 8.351385116577148,
+ 8.474419593811035
+ ],
+ "term_loss": [
+ 111.63633728027344,
+ 4.155745029449463,
+ 3.8754897117614746,
+ 4.040826320648193,
+ 4.010752201080322,
+ 4.2646074295043945,
+ 5.391899108886719,
+ 3.27858829498291,
+ 3.74959135055542
+ ],
+ "bridge_loss": [
+ 6.45359421014291e-07,
+ 0.22446846961975098,
+ 0.18948684632778168,
+ 0.14564603567123413,
+ 0.1301368772983551,
+ 0.1614246517419815,
+ 0.19166265428066254,
+ 0.19554881751537323,
+ 0.15442883968353271
+ ],
+ "term_grad_loss": [
+ 20.456655502319336,
+ 4.743132591247559,
+ 4.45129919052124,
+ 4.447327136993408,
+ 4.579296112060547,
+ 4.011109352111816,
+ 4.663890838623047,
+ 4.877087593078613,
+ 4.57021427154541
+ ],
+ "fm_loss": [
+ 1.4957863925246784e-07,
+ 0.001574160298332572,
+ 0.0025115222670137882,
+ 0.002142899436876178,
+ 0.0022483705542981625,
+ 0.0020201210863888264,
+ 0.00219835271127522,
+ 0.0016042720526456833,
+ 0.0018535356502979994
+ ]
+ },
+ "final_per_layer": {
+ "dfa_costate_cos": [
+ -0.04993891716003418,
+ -0.03484980762004852,
+ 0.008264334872364998,
+ -0.018589604645967484,
+ -0.019490346312522888,
+ 0.0018934037070721388,
+ 0.025425557047128677,
+ 0.046417269855737686,
+ 0.06304077804088593,
+ 0.03301604464650154,
+ -0.06211906671524048,
+ 0.005648006685078144
+ ],
+ "state_costate_cos": [
+ 0.9454483985900879,
+ 0.946227490901947,
+ 0.9468960165977478,
+ 0.9470230340957642,
+ 0.9475629925727844,
+ 0.9478208422660828,
+ 0.9478966593742371,
+ 0.9480605125427246,
+ 0.9479074478149414,
+ 0.9478251934051514,
+ 0.9478766918182373,
+ 0.9475747346878052
+ ],
+ "credit_costate_cos": [
+ 0.9432812333106995,
+ 0.9438751935958862,
+ 0.9443729519844055,
+ 0.9447157382965088,
+ 0.9455237984657288,
+ 0.9461240768432617,
+ 0.9463104009628296,
+ 0.9467931985855103,
+ 0.9471821784973145,
+ 0.9476308226585388,
+ 0.9481172561645508,
+ 0.9487224817276001
+ ],
+ "dfa_rho": [
+ -0.0704549178481102,
+ 0.031227122992277145,
+ 0.009932642802596092,
+ -0.015737976878881454,
+ -0.045219600200653076,
+ 0.013525029644370079,
+ 0.03365146368741989,
+ 0.04508150368928909,
+ 0.05846859887242317,
+ 7.291417568922043e-05,
+ -0.06866942346096039,
+ -0.007611127570271492
+ ],
+ "state_rho": [
+ 0.935008704662323,
+ 0.9310771822929382,
+ 0.9295646548271179,
+ 0.938683032989502,
+ 0.9329910278320312,
+ 0.9313007593154907,
+ 0.9357653260231018,
+ 0.9376221895217896,
+ 0.9326146841049194,
+ 0.9372754693031311,
+ 0.9379282593727112,
+ 0.9359501004219055
+ ],
+ "credit_rho": [
+ 0.9306489825248718,
+ 0.9282867312431335,
+ 0.9364583492279053,
+ 0.9361423850059509,
+ 0.9323122501373291,
+ 0.9380875825881958,
+ 0.93974369764328,
+ 0.9351372122764587,
+ 0.941116213798523,
+ 0.9382349252700806,
+ 0.9381735324859619,
+ 0.9431807994842529
+ ],
+ "dfa_nudge": [
+ 0.020365234464406967,
+ 0.014575351029634476,
+ -0.002057630568742752,
+ 0.006316322833299637,
+ 0.007856002077460289,
+ 0.0004078727215528488,
+ -0.010462434962391853,
+ -0.017474167048931122,
+ -0.02493620105087757,
+ -0.011619189754128456,
+ 0.022399690002202988,
+ -0.00210556760430336
+ ],
+ "state_nudge": [
+ -0.34937936067581177,
+ -0.3488026261329651,
+ -0.3481972813606262,
+ -0.34827157855033875,
+ -0.3484804630279541,
+ -0.3478168845176697,
+ -0.34806668758392334,
+ -0.3481366038322449,
+ -0.3481329381465912,
+ -0.3476967513561249,
+ -0.3463967740535736,
+ -0.34703367948532104
+ ],
+ "credit_nudge": [
+ -0.34637150168418884,
+ -0.345956414937973,
+ -0.3455013632774353,
+ -0.34578341245651245,
+ -0.3462638854980469,
+ -0.3458409905433655,
+ -0.3462728261947632,
+ -0.3466273546218872,
+ -0.3469495475292206,
+ -0.34689074754714966,
+ -0.3459630608558655,
+ -0.34714198112487793
+ ]
+ }
+} \ No newline at end of file
diff --git a/results/toy_lq/toy_lq_v2_seed42_lam1.0_sig0.3_tgw0.0_fm0.0.json b/results/toy_lq/toy_lq_v2_seed42_lam1.0_sig0.3_tgw0.0_fm0.0.json
new file mode 100644
index 0000000..78451b9
--- /dev/null
+++ b/results/toy_lq/toy_lq_v2_seed42_lam1.0_sig0.3_tgw0.0_fm0.0.json
@@ -0,0 +1,282 @@
+{
+ "config": {
+ "d_hidden": 64,
+ "output_dim": 10,
+ "num_layers": 12,
+ "sigma": 0.03,
+ "batch_size": 256,
+ "num_steps": 5000,
+ "lr_fb": 0.001,
+ "lam": 1.0,
+ "K": 8,
+ "ema_momentum": 0.995,
+ "sigma_bridge": 0.3,
+ "eval_every": 1000,
+ "seed": 42,
+ "gpu": 0,
+ "output_dir": "results/toy_lq",
+ "vnet_hidden": 256,
+ "vnet_layers": 3,
+ "term_grad_weight": 0.0,
+ "fm_weight": 0.0
+ },
+ "log": {
+ "steps": [
+ 1,
+ 1000,
+ 2000,
+ 3000,
+ 4000,
+ 5000
+ ],
+ "dfa_costate_cos": [
+ 0.001022340264171362,
+ 0.0024294707691296935,
+ 0.000613357910575966,
+ 0.002641987521201372,
+ 0.0019003628791930776,
+ 0.004648004221962765
+ ],
+ "state_costate_cos": [
+ 0.009337988216429949,
+ 0.9437081764141718,
+ 0.9386202742656072,
+ 0.9438605606555939,
+ 0.9475679496924082,
+ 0.9496726940075556
+ ],
+ "credit_costate_cos": [
+ 0.023481125943362713,
+ 0.0021192015459140143,
+ 0.05908452393487096,
+ 0.11570050132771333,
+ 0.09644180163741112,
+ 0.06304322431484859
+ ],
+ "dfa_rho": [
+ 0.015879416760678094,
+ 0.009290086299491426,
+ 0.0009949249991526206,
+ -0.004670841522359599,
+ -0.0029721508423487344,
+ 0.0010571565168599288
+ ],
+ "state_rho": [
+ 0.0029325426245729127,
+ 0.9371241927146912,
+ 0.9219773809115092,
+ 0.9298903445402781,
+ 0.9345368842283884,
+ 0.9332165767749151
+ ],
+ "credit_rho": [
+ 0.02086908878603329,
+ -0.014479975526531538,
+ 0.04267269264285763,
+ 0.10674913817395766,
+ 0.091526560485363,
+ 0.04765695089008659
+ ],
+ "dfa_nudge": [
+ -0.0003799900102118651,
+ -0.0008909914953013262,
+ 0.00031573620314399403,
+ -0.0008827850688248873,
+ -0.0003006396194299062,
+ -0.0016971436173965533
+ ],
+ "state_nudge": [
+ -0.002327537008871635,
+ -0.33619146794080734,
+ -0.3439306889971097,
+ -0.32351043323675793,
+ -0.33487510432799655,
+ -0.35304194688796997
+ ],
+ "credit_nudge": [
+ -0.007470574385176103,
+ 0.002750888311614593,
+ -0.017584003585701186,
+ -0.037241545505821705,
+ -0.03454847944279512,
+ -0.02138534157226483
+ ],
+ "bridge_residual": [],
+ "state_bridge_loss": [
+ 66.01814270019531,
+ 2.143366813659668,
+ 1.9674744606018066,
+ 2.152421712875366,
+ 2.0728020668029785,
+ 2.0048255920410156
+ ],
+ "credit_bridge_loss": [
+ 111.63633728027344,
+ 0.35802197456359863,
+ 0.10368431359529495,
+ 0.12013768404722214,
+ 0.07032017409801483,
+ 0.051539346575737
+ ],
+ "term_loss": [
+ 111.63633728027344,
+ 0.2640027403831482,
+ 0.05911973863840103,
+ 0.06323631852865219,
+ 0.03984691575169563,
+ 0.03099522553384304
+ ],
+ "bridge_loss": [
+ 3.0909704946679994e-06,
+ 0.09401924908161163,
+ 0.04456457495689392,
+ 0.056901365518569946,
+ 0.030473260208964348,
+ 0.02054412104189396
+ ],
+ "term_grad_loss": [
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0
+ ],
+ "fm_loss": [
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0
+ ]
+ },
+ "final_per_layer": {
+ "dfa_costate_cos": [
+ -0.025100916624069214,
+ -0.025588383898139,
+ 0.0002230944810435176,
+ -0.012649456970393658,
+ -0.003438096959143877,
+ -0.008626529946923256,
+ 0.04746557027101517,
+ 0.0495537593960762,
+ 0.05357586592435837,
+ 0.039518602192401886,
+ -0.06593793630599976,
+ 0.0067804791033267975
+ ],
+ "state_costate_cos": [
+ 0.94776451587677,
+ 0.9486032724380493,
+ 0.9489368200302124,
+ 0.9489387273788452,
+ 0.9493762850761414,
+ 0.9498711228370667,
+ 0.9505667686462402,
+ 0.9509860277175903,
+ 0.9503088593482971,
+ 0.9503939151763916,
+ 0.9501732587814331,
+ 0.9501527547836304
+ ],
+ "credit_costate_cos": [
+ 0.06872019171714783,
+ 0.0653301253914833,
+ 0.06267654895782471,
+ 0.060872238129377365,
+ 0.059321627020835876,
+ 0.05934217572212219,
+ 0.06014599651098251,
+ 0.05938819795846939,
+ 0.06065107509493828,
+ 0.06321083009243011,
+ 0.07017489522695541,
+ 0.066684789955616
+ ],
+ "dfa_rho": [
+ -0.039396628737449646,
+ -0.062005721032619476,
+ 0.005523890256881714,
+ 0.014756813645362854,
+ -0.029910940676927567,
+ 0.016373179852962494,
+ 0.06027424708008766,
+ 0.07274787873029709,
+ 0.04506715014576912,
+ 0.02043943479657173,
+ -0.07323547452688217,
+ -0.017947951331734657
+ ],
+ "state_rho": [
+ 0.9350653886795044,
+ 0.9352835416793823,
+ 0.9357374310493469,
+ 0.934054434299469,
+ 0.9226828813552856,
+ 0.930233359336853,
+ 0.9396862983703613,
+ 0.9324671030044556,
+ 0.9295884966850281,
+ 0.9347179532051086,
+ 0.9344969987869263,
+ 0.9345850348472595
+ ],
+ "credit_rho": [
+ 0.07084883749485016,
+ 0.0004139472730457783,
+ 0.08371011912822723,
+ 0.010933063924312592,
+ 0.07074157148599625,
+ 0.02977888286113739,
+ 0.06011004000902176,
+ 0.020937703549861908,
+ 0.067134790122509,
+ 0.04539356008172035,
+ 0.06114630401134491,
+ 0.050734590739011765
+ ],
+ "dfa_nudge": [
+ 0.010068551637232304,
+ 0.009215200319886208,
+ -0.002217007800936699,
+ 0.007142472080886364,
+ 0.0020765019580721855,
+ 0.004165132530033588,
+ -0.019989464432001114,
+ -0.018945707008242607,
+ -0.01947549544274807,
+ -0.014030318707227707,
+ 0.023684613406658173,
+ -0.0020602019503712654
+ ],
+ "state_nudge": [
+ -0.3548189401626587,
+ -0.3539973497390747,
+ -0.3535424768924713,
+ -0.35353928804397583,
+ -0.35366636514663696,
+ -0.35295385122299194,
+ -0.35282424092292786,
+ -0.35278239846229553,
+ -0.3528212308883667,
+ -0.3526480793952942,
+ -0.35135188698768616,
+ -0.35155725479125977
+ ],
+ "credit_nudge": [
+ -0.024559948593378067,
+ -0.023154649883508682,
+ -0.02181980386376381,
+ -0.020881079137325287,
+ -0.02010848931968212,
+ -0.019884146749973297,
+ -0.020017635077238083,
+ -0.01966693066060543,
+ -0.020179908722639084,
+ -0.02114756405353546,
+ -0.023488853126764297,
+ -0.021715089678764343
+ ]
+ }
+} \ No newline at end of file
diff --git a/results/toy_lq/toy_lq_v2_seed456_lam0.1_sig0.1_tgw1.0_fm0.0.json b/results/toy_lq/toy_lq_v2_seed456_lam0.1_sig0.1_tgw1.0_fm0.0.json
new file mode 100644
index 0000000..8e7c7b0
--- /dev/null
+++ b/results/toy_lq/toy_lq_v2_seed456_lam0.1_sig0.1_tgw1.0_fm0.0.json
@@ -0,0 +1,330 @@
+{
+ "config": {
+ "d_hidden": 64,
+ "output_dim": 10,
+ "num_layers": 12,
+ "sigma": 0.03,
+ "batch_size": 256,
+ "num_steps": 8000,
+ "lr_fb": 0.001,
+ "lam": 0.1,
+ "K": 8,
+ "ema_momentum": 0.995,
+ "sigma_bridge": 0.1,
+ "eval_every": 1000,
+ "seed": 456,
+ "gpu": 0,
+ "output_dir": "results/toy_lq",
+ "vnet_hidden": 256,
+ "vnet_layers": 3,
+ "term_grad_weight": 1.0,
+ "fm_weight": 0.0
+ },
+ "log": {
+ "steps": [
+ 1,
+ 1000,
+ 2000,
+ 3000,
+ 4000,
+ 5000,
+ 6000,
+ 7000,
+ 8000
+ ],
+ "dfa_costate_cos": [
+ -0.008305357536301017,
+ -0.0011448257913192113,
+ -0.011490714969113469,
+ -0.005118173896335065,
+ -0.0028971168600643673,
+ -0.007146042305976152,
+ -0.005135039333254099,
+ -0.006408803591815134,
+ 0.0030692683843274913
+ ],
+ "state_costate_cos": [
+ 0.010766413528472185,
+ 0.9454400340716044,
+ 0.9422353406747183,
+ 0.945327232281367,
+ 0.9411078443129858,
+ 0.9500264773766199,
+ 0.947187085946401,
+ 0.9483370830615362,
+ 0.9451590329408646
+ ],
+ "credit_costate_cos": [
+ 0.010942678588132063,
+ 0.8771380881468455,
+ 0.9226242254177729,
+ 0.9362819741169611,
+ 0.9372822741667429,
+ 0.9464249561230341,
+ 0.9468309829632441,
+ 0.9452949613332748,
+ 0.9439582029978434
+ ],
+ "dfa_rho": [
+ -0.0028248391657446823,
+ -0.001316564545656244,
+ -0.00823917348558704,
+ -0.008288809360237792,
+ -0.009200356512640914,
+ -0.02464000484906137,
+ 0.006656331475824118,
+ -0.014378171879798174,
+ 0.00816792449525868
+ ],
+ "state_rho": [
+ 0.02655455912463367,
+ 0.9340365380048752,
+ 0.930340642730395,
+ 0.9328931520382563,
+ 0.9261527856191,
+ 0.9353549828131994,
+ 0.9365303913752238,
+ 0.930912658572197,
+ 0.9325708796580633
+ ],
+ "credit_rho": [
+ 0.015292729716748,
+ 0.8341556191444397,
+ 0.884218767285347,
+ 0.9175956894954046,
+ 0.9214809189240137,
+ 0.9294924139976501,
+ 0.9364803830782572,
+ 0.9272431135177612,
+ 0.9332626809676489
+ ],
+ "dfa_nudge": [
+ 0.004384364855165283,
+ 0.0014555706487347682,
+ 0.005660574107120435,
+ 0.003231095770994822,
+ 0.0024609332904219627,
+ 0.0033611954810718694,
+ 0.0025722047624488673,
+ 0.003350513521581888,
+ -0.00046457063096265
+ ],
+ "state_nudge": [
+ -0.005116054400180777,
+ -0.36389906456073123,
+ -0.37967536846796673,
+ -0.3594902977347374,
+ -0.3901909242073695,
+ -0.3562925284107526,
+ -0.34591514120499295,
+ -0.3550695503751437,
+ -0.3515613650282224
+ ],
+ "credit_nudge": [
+ -0.003232262640570601,
+ -0.34101804345846176,
+ -0.37139702836672467,
+ -0.355108546713988,
+ -0.38709117472171783,
+ -0.3536044582724571,
+ -0.34420712540547055,
+ -0.35209985077381134,
+ -0.3494671831528346
+ ],
+ "bridge_residual": [],
+ "state_bridge_loss": [
+ 66.31975555419922,
+ 2.3091068267822266,
+ 2.0314407348632812,
+ 2.110802412033081,
+ 1.9804980754852295,
+ 1.8128150701522827,
+ 2.0147881507873535,
+ 2.169416904449463,
+ 2.0117833614349365
+ ],
+ "credit_bridge_loss": [
+ 158.73072814941406,
+ 11.18570613861084,
+ 9.38658332824707,
+ 9.429727554321289,
+ 10.842954635620117,
+ 10.344818115234375,
+ 10.250753402709961,
+ 10.136574745178223,
+ 9.871820449829102
+ ],
+ "term_loss": [
+ 132.93673706054688,
+ 4.870186805725098,
+ 3.9316887855529785,
+ 4.335302829742432,
+ 5.871437072753906,
+ 4.5994768142700195,
+ 5.077899932861328,
+ 4.8271284103393555,
+ 4.638625621795654
+ ],
+ "bridge_loss": [
+ 7.166463547036983e-07,
+ 0.3530547022819519,
+ 0.20790576934814453,
+ 0.15763649344444275,
+ 0.18163490295410156,
+ 0.154127299785614,
+ 0.1578863561153412,
+ 0.13594242930412292,
+ 0.12283627688884735
+ ],
+ "term_grad_loss": [
+ 25.793991088867188,
+ 5.962464809417725,
+ 5.246988296508789,
+ 4.936788082122803,
+ 4.789882183074951,
+ 5.591214656829834,
+ 5.0149664878845215,
+ 5.173503875732422,
+ 5.110358238220215
+ ],
+ "fm_loss": [
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0,
+ 0.0
+ ]
+ },
+ "final_per_layer": {
+ "dfa_costate_cos": [
+ 0.0057477825321257114,
+ -0.05385865271091461,
+ 0.031865090131759644,
+ -0.0450170561671257,
+ 0.01222146674990654,
+ 0.048112209886312485,
+ -0.0029807062819600105,
+ 0.02491983398795128,
+ -0.03023526817560196,
+ -0.0383906215429306,
+ 0.005803969223052263,
+ 0.07864317297935486
+ ],
+ "state_costate_cos": [
+ 0.9431054592132568,
+ 0.9437580108642578,
+ 0.9442368149757385,
+ 0.9451977014541626,
+ 0.9453786611557007,
+ 0.9453213214874268,
+ 0.9453005790710449,
+ 0.945610761642456,
+ 0.9459618330001831,
+ 0.946029007434845,
+ 0.9460264444351196,
+ 0.9459818005561829
+ ],
+ "credit_costate_cos": [
+ 0.9404189586639404,
+ 0.9415367841720581,
+ 0.9419513940811157,
+ 0.9428710341453552,
+ 0.943200409412384,
+ 0.9437626004219055,
+ 0.9443795680999756,
+ 0.9448325037956238,
+ 0.945106029510498,
+ 0.9459753036499023,
+ 0.9465078115463257,
+ 0.9469560384750366
+ ],
+ "dfa_rho": [
+ 0.04672882705926895,
+ -0.030157513916492462,
+ 0.03139471262693405,
+ -0.02426629513502121,
+ -0.003147948533296585,
+ 0.06672847270965576,
+ -0.0028628872241824865,
+ -0.0006099608726799488,
+ -0.06767985224723816,
+ -0.07952223718166351,
+ 0.023338939994573593,
+ 0.13807083666324615
+ ],
+ "state_rho": [
+ 0.9322999715805054,
+ 0.9332318902015686,
+ 0.933842658996582,
+ 0.9367775917053223,
+ 0.9355518221855164,
+ 0.9306066036224365,
+ 0.9324768781661987,
+ 0.9316605925559998,
+ 0.9233090281486511,
+ 0.9335967302322388,
+ 0.9341922998428345,
+ 0.933304488658905
+ ],
+ "credit_rho": [
+ 0.929013192653656,
+ 0.925915002822876,
+ 0.9249007701873779,
+ 0.9293269515037537,
+ 0.9353340268135071,
+ 0.9355732202529907,
+ 0.9336704611778259,
+ 0.9395359754562378,
+ 0.934350848197937,
+ 0.9350711107254028,
+ 0.9423503279685974,
+ 0.9341102838516235
+ ],
+ "dfa_nudge": [
+ -0.0025230227038264275,
+ 0.01772259920835495,
+ -0.011610012501478195,
+ 0.01727830246090889,
+ -0.002929902635514736,
+ -0.01679525338113308,
+ 0.0033558662980794907,
+ -0.007272847928106785,
+ 0.013050400651991367,
+ 0.014434966258704662,
+ -0.0013312064111232758,
+ -0.02895473688840866
+ ],
+ "state_nudge": [
+ -0.3518102467060089,
+ -0.3520665764808655,
+ -0.35131847858428955,
+ -0.35165226459503174,
+ -0.35131698846817017,
+ -0.35155874490737915,
+ -0.3516783118247986,
+ -0.3522875905036926,
+ -0.35148167610168457,
+ -0.3511171340942383,
+ -0.35132837295532227,
+ -0.3511199951171875
+ ],
+ "credit_nudge": [
+ -0.34800052642822266,
+ -0.3485172390937805,
+ -0.3479737639427185,
+ -0.3486989140510559,
+ -0.3486787676811218,
+ -0.3492557406425476,
+ -0.3497552275657654,
+ -0.35073035955429077,
+ -0.35016047954559326,
+ -0.3501723110675812,
+ -0.3507159650325775,
+ -0.35094690322875977
+ ]
+ }
+} \ No newline at end of file
diff --git a/results/toy_lq/value_net_seed42.pt b/results/toy_lq/value_net_seed42.pt
new file mode 100644
index 0000000..0cb6683
--- /dev/null
+++ b/results/toy_lq/value_net_seed42.pt
Binary files differ