Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_350000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_400000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_450000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_500000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_550000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_600000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_650000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_700000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_750000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_800000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/env.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/env_sv.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/eval.csv
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
avg_gripper_contact_length,num_gripper_contacts,prev_qpos,prev_qvel,qpos,qvel,control,time,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
|
| 2 |
+
0.0,0.0,-0.12294212273145795,0.03123370676221134,-0.1201740117216519,0.05236926337646817,21.572539073370592,22.783999999997413,0.14,11509.44,-1.38,-750.38,453.68,1.2918314933776855,350000
|
| 3 |
+
0.0,0.0,-0.10439949449624131,0.021370889744436683,-0.10170666840401399,0.027558137173595277,26.834251254766464,15.529999999998374,0.5,31124.28,-0.7,-464.28,308.6,0.9271091270446777,400000
|
| 4 |
+
0.0,0.0,-0.11113898058998958,0.03395067975167628,-0.10778232631931668,0.02197510528761741,27.804653336699527,11.607999999998835,0.66,45643.86,-0.44,-315.04,230.16,0.6732655954360962,450000
|
| 5 |
+
0.0,0.0,-0.07821390074540031,0.05312713030417753,-0.07353739400823782,0.051328818874468864,29.60568480297476,10.098999999999025,0.7,57311.78,-0.46,-312.8,199.98,0.5827190542221069,500000
|
| 6 |
+
0.0,0.0,-0.08705438538137966,0.037094911525992896,-0.08259609696517899,0.05043453788184153,32.85618081389617,5.892999999999518,0.88,64909.2,-0.2,-181.66,115.86,0.35923210144042966,550000
|
| 7 |
+
0.0,0.0,-0.07293349423320093,0.021861675661118036,-0.07046127691247825,0.0312426031051787,29.13055356367509,8.516999999999156,0.74,72707.98,-0.34,-233.9,168.34,0.49684685230255127,600000
|
| 8 |
+
0.0,0.0,-0.05611056905805985,0.07480868663544035,-0.04998123139060258,0.061221654456794894,34.01213388874553,3.579999999999808,0.96,78560.06,-0.06,-103.98,69.6,0.2253513240814209,650000
|
| 9 |
+
0.0,0.0,-0.08190186876855078,0.08710486755558111,-0.07662310184069353,0.02226635562339968,32.51111390060739,5.731999999999673,0.9,83498.8,-0.18,-176.88,112.64,0.3399758720397949,700000
|
| 10 |
+
0.0,0.0,-0.0815717228025153,0.056101232019872244,-0.07764970419575518,0.03430422690167995,32.78742000800917,4.5949999999997155,0.92,88904.56,-0.1,-125.62,89.9,0.27464373588562013,750000
|
| 11 |
+
0.0,0.0,-0.07183822996491951,0.04106823076458341,-0.06667342686573315,0.05031643458889304,35.13448298329891,2.864999999999896,0.98,92620.74,-0.02,-77.52,55.3,0.1806633996963501,800000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/eval_sv.csv
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
avg_gripper_contact_length,num_gripper_contacts,prev_qpos,prev_qvel,qpos,qvel,control,time,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
|
| 2 |
+
0.0,0.0,-0.12294212273145795,0.03123370676221134,-0.1201740117216519,0.05236926337646817,21.572539073370592,22.783999999997413,0.14,11509.44,-1.38,-750.38,453.68,1.2918314933776855,350000
|
| 3 |
+
0.0,0.0,-0.10439949449624131,0.021370889744436683,-0.10170666840401399,0.027558137173595277,26.834251254766464,15.529999999998374,0.5,31124.28,-0.7,-464.28,308.6,0.9271091270446777,400000
|
| 4 |
+
0.0,0.0,-0.11113898058998958,0.03395067975167628,-0.10778232631931668,0.02197510528761741,27.804653336699527,11.607999999998835,0.66,45643.86,-0.44,-315.04,230.16,0.6732655954360962,450000
|
| 5 |
+
0.0,0.0,-0.07821390074540031,0.05312713030417753,-0.07353739400823782,0.051328818874468864,29.60568480297476,10.098999999999025,0.7,57311.78,-0.46,-312.8,199.98,0.5827190542221069,500000
|
| 6 |
+
0.0,0.0,-0.08705438538137966,0.037094911525992896,-0.08259609696517899,0.05043453788184153,32.85618081389617,5.892999999999518,0.88,64909.2,-0.2,-181.66,115.86,0.35923210144042966,550000
|
| 7 |
+
0.0,0.0,-0.07293349423320093,0.021861675661118036,-0.07046127691247825,0.0312426031051787,29.13055356367509,8.516999999999156,0.74,72707.98,-0.34,-233.9,168.34,0.49684685230255127,600000
|
| 8 |
+
0.0,0.0,-0.05611056905805985,0.07480868663544035,-0.04998123139060258,0.061221654456794894,34.01213388874553,3.579999999999808,0.96,78560.06,-0.06,-103.98,69.6,0.2253513240814209,650000
|
| 9 |
+
0.0,0.0,-0.08190186876855078,0.08710486755558111,-0.07662310184069353,0.02226635562339968,32.51111390060739,5.731999999999673,0.9,83498.8,-0.18,-176.88,112.64,0.3399758720397949,700000
|
| 10 |
+
0.0,0.0,-0.0815717228025153,0.056101232019872244,-0.07764970419575518,0.03430422690167995,32.78742000800917,4.5949999999997155,0.92,88904.56,-0.1,-125.62,89.9,0.27464373588562013,750000
|
| 11 |
+
0.0,0.0,-0.07183822996491951,0.04106823076458341,-0.06667342686573315,0.05031643458889304,35.13448298329891,2.864999999999896,0.98,92620.74,-0.02,-77.52,55.3,0.1806633996963501,800000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/online_agent.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/actor_loss,actor/bc_flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
445.7115,0.7067522,0.65377146,-12.352527,-52.435505,-78.84434,0.6081508,-0.520904,30.517178,305000
|
| 3 |
+
540.9462,0.8347899,0.8316962,-11.381289,-61.580788,-109.09413,3.1441615,-3.1623406,92.36945,310000
|
| 4 |
+
616.64087,0.86508167,0.8254259,-17.779192,-68.31887,-114.497505,0.8703755,-1.3486322,48.367,315000
|
| 5 |
+
609.3012,0.9165865,1.5153502,-5.3626113,-67.824036,-146.58945,3.83913,-3.104559,83.89997,320000
|
| 6 |
+
601.0441,0.9483128,0.6209473,-21.71055,-67.12059,-124.15658,2.6138494,-1.7375144,69.066,325000
|
| 7 |
+
602.47906,0.7481787,0.9520208,-11.879025,-67.272575,-145.70853,1.0734226,-0.7574681,48.044014,330000
|
| 8 |
+
648.5374,1.0723513,0.91962475,-12.086072,-71.68345,-155.9749,5.3180294,-8.626411,201.65736,335000
|
| 9 |
+
662.57806,0.7133709,1.2167645,-23.779255,-72.92409,-145.53572,12.044887,-11.081339,119.708534,340000
|
| 10 |
+
669.28455,0.89016306,1.1195942,-17.29771,-73.96504,-140.08261,0.9281524,-1.7528518,52.101227,345000
|
| 11 |
+
665.0903,0.767177,1.5255989,-18.08008,-73.74904,-153.7963,0.60282147,-0.7558749,57.740284,350000
|
| 12 |
+
668.0568,0.80877686,1.7845745,-17.178873,-73.72634,-154.21588,1.3326921,-1.1995299,64.82351,355000
|
| 13 |
+
686.2513,0.8313422,1.41268,-16.989653,-75.43462,-152.15828,0.92451566,-1.3505316,58.180954,360000
|
| 14 |
+
707.42053,0.81933033,1.5041503,-17.248562,-77.08352,-154.41106,1.2795796,-1.322609,54.508305,365000
|
| 15 |
+
677.9205,0.833178,1.3231558,-7.459535,-74.40679,-149.41524,6.0711603,-5.5830116,231.49094,370000
|
| 16 |
+
708.14154,0.87533677,2.7791488,-20.8209,-77.69152,-165.98422,2.4237638,-2.4950507,124.903465,375000
|
| 17 |
+
775.4923,0.8390852,2.4848251,-14.617637,-84.278755,-170.78738,1.0647764,-1.1413312,73.378395,380000
|
| 18 |
+
769.2057,0.91490114,1.6568139,-23.268904,-83.2633,-172.68602,52.806942,-50.153557,966.85596,385000
|
| 19 |
+
747.43646,1.2103626,1.7273043,-15.154629,-81.38075,-172.86072,3.4175205,-3.5559297,90.181366,390000
|
| 20 |
+
752.12695,0.7634815,2.495509,-13.142955,-81.83032,-167.7289,3.1348517,-3.1964853,104.54646,395000
|
| 21 |
+
759.2383,0.9173783,1.3310732,-16.531017,-82.0801,-174.62259,11.38324,-10.722104,129.5972,400000
|
| 22 |
+
743.1406,0.68061996,2.0100157,-14.602492,-80.87149,-166.5832,2.2343507,-1.8132733,76.825264,405000
|
| 23 |
+
746.9345,0.8274262,3.782421,-7.19479,-81.37439,-169.2571,1.9872674,-1.78309,75.53299,410000
|
| 24 |
+
750.5191,0.7723874,1.543495,0.8388382,-81.45662,-175.28888,1.1554648,-1.2087846,58.415115,415000
|
| 25 |
+
778.0577,0.97244775,1.7165412,-10.761151,-84.174614,-173.57988,36.9573,-36.84243,902.6307,420000
|
| 26 |
+
781.3694,0.9713011,2.0240152,-5.035806,-84.40839,-173.2682,2.637841,-2.159695,127.93145,425000
|
| 27 |
+
758.7815,0.7949314,1.5561113,-14.528761,-81.97677,-173.46764,8.697059,-7.253913,133.22995,430000
|
| 28 |
+
735.12274,0.7623388,2.0105586,2.270846,-80.466515,-158.94768,1.2659122,-1.2246403,68.58373,435000
|
| 29 |
+
732.07465,1.0426729,3.2365913,-14.439586,-80.204506,-172.13814,2.8134086,-2.991327,112.67689,440000
|
| 30 |
+
762.48474,0.7440357,3.478644,-11.833263,-83.07718,-173.18018,2.3919027,-3.2427492,121.02144,445000
|
| 31 |
+
742.8799,1.064743,2.2775369,-16.384031,-80.40606,-164.09546,1.066736,-1.0172443,62.304688,450000
|
| 32 |
+
787.2357,0.8748975,2.1341562,-14.89056,-85.49163,-172.87286,2.3575764,-2.5423062,84.75143,455000
|
| 33 |
+
766.108,0.7674749,3.1847131,-5.929598,-83.108505,-174.02693,6.9600515,-6.649285,110.24331,460000
|
| 34 |
+
764.6128,0.9792771,1.9070653,-1.4096687,-82.49771,-164.27406,2.3908875,-2.3956656,75.37895,465000
|
| 35 |
+
768.27985,0.8667493,1.9766972,-0.184668,-83.3609,-170.03607,23.68221,-23.664942,267.78964,470000
|
| 36 |
+
797.2321,1.1415435,1.7666928,-20.70811,-86.35821,-174.70876,1.5116276,-1.4736242,61.285385,475000
|
| 37 |
+
791.9427,1.0564243,3.176107,0.096508384,-85.31713,-163.06784,1.9919732,-1.8961915,111.25355,480000
|
| 38 |
+
775.21234,0.8257254,1.4294792,-0.21109492,-84.02596,-174.27373,2.1052728,-2.1030724,67.24888,485000
|
| 39 |
+
804.4284,1.0296396,2.6542854,3.7111926,-86.20194,-169.03952,1.387049,-1.5705668,82.297165,490000
|
| 40 |
+
786.58124,2.1084867,1.7179979,-11.258596,-84.61236,-176.95967,2.8257248,-1.8964311,74.42772,495000
|
| 41 |
+
772.3121,0.96355855,2.2649553,-9.051461,-83.763145,-174.66594,2.851241,-2.7885053,78.50817,500000
|
| 42 |
+
762.72156,0.9661943,2.5731435,-14.538089,-82.59147,-176.02652,2.0492787,-1.8421787,82.672386,505000
|
| 43 |
+
793.00635,1.0129051,2.9449737,-13.474467,-85.09369,-173.79967,2.907948,-2.7646234,84.89687,510000
|
| 44 |
+
764.46246,0.7681531,10.620972,-10.667935,-82.988846,-169.3138,3.0367548,-2.8539276,240.08377,515000
|
| 45 |
+
785.77295,1.0973715,2.5735788,-16.532927,-84.8267,-176.24716,4.1926265,-2.3414068,83.00844,520000
|
| 46 |
+
774.31335,0.92759156,2.8527231,-2.9606376,-83.33984,-176.90286,1.7836312,-2.036624,105.26757,525000
|
| 47 |
+
804.3937,1.132477,2.0732124,-8.804147,-86.8793,-168.53128,17.369062,-15.127992,168.76201,530000
|
| 48 |
+
803.14105,1.4882967,3.8520706,-6.5309706,-85.128716,-175.34886,57.06677,-29.42813,497.08215,535000
|
| 49 |
+
794.6374,1.3967235,3.2766836,2.9274538,-85.54815,-173.90913,2.6659544,-3.0292783,145.1177,540000
|
| 50 |
+
757.95184,0.85211813,2.323631,-5.6617417,-81.89776,-170.5356,3.6532433,-3.4411225,90.62291,545000
|
| 51 |
+
797.204,1.395182,2.9096801,-11.654829,-85.379684,-173.55327,2.074678,-1.6246101,92.78856,550000
|
| 52 |
+
803.08795,0.9311178,2.0466588,-24.597004,-86.70263,-174.4755,14.803878,-16.312965,460.04968,555000
|
| 53 |
+
752.2199,0.9442888,2.632631,2.4421306,-81.47011,-175.86276,4.584734,-3.2361383,136.05646,560000
|
| 54 |
+
766.3031,1.2555871,3.3333383,-6.6597457,-82.95369,-168.72765,3.7065883,-3.4906888,97.70839,565000
|
| 55 |
+
794.64935,1.2057395,3.730072,-12.307201,-85.65021,-177.45009,3.522656,-5.2406306,122.726685,570000
|
| 56 |
+
793.63586,1.172966,2.7419572,-6.265837,-85.156746,-175.84364,2.5144324,-2.7212806,90.27865,575000
|
| 57 |
+
786.3652,1.2119699,2.3650258,-11.777868,-84.69754,-164.05388,3.1694105,-3.3200488,76.25548,580000
|
| 58 |
+
799.79486,1.0494143,5.4708204,-6.1812377,-85.48999,-174.44789,1.325226,-1.882567,135.23236,585000
|
| 59 |
+
775.6564,1.3542421,2.8076637,-3.441286,-83.750854,-178.82812,1.8704932,-2.4562473,81.913704,590000
|
| 60 |
+
750.96497,1.1345422,3.2515957,1.1290846,-81.19744,-178.57076,1.8631359,-1.7144275,99.14474,595000
|
| 61 |
+
767.51483,0.9448624,2.1504982,-6.5295167,-82.60241,-171.99377,3.0315926,-2.6483727,115.30594,600000
|
| 62 |
+
779.5913,0.88519406,2.4766946,-2.1794984,-84.19848,-160.03574,5.0879574,-5.541548,106.40292,605000
|
| 63 |
+
737.22723,1.1187298,2.8533242,-3.6369731,-80.2213,-168.16307,103.195854,-73.214874,2002.8071,610000
|
| 64 |
+
738.0061,0.9001357,3.6137562,-4.03646,-79.739944,-160.34088,6.90032,-6.270361,142.53078,615000
|
| 65 |
+
742.6438,0.9189588,3.3265824,-4.1122527,-80.47425,-156.62767,3.0442863,-2.7793715,107.66594,620000
|
| 66 |
+
761.2071,0.82523656,2.4533162,-8.560383,-82.10732,-161.27226,11.7015085,-11.748071,131.48909,625000
|
| 67 |
+
788.7787,1.1402719,3.8665054,-6.8959923,-84.30932,-180.80365,20.331932,-24.965939,241.03583,630000
|
| 68 |
+
739.129,0.93275607,11.155135,-8.994619,-80.42977,-159.0004,7.3336573,-6.392983,154.87224,635000
|
| 69 |
+
744.95776,1.1765379,2.3001025,-3.9059694,-80.72818,-172.14642,8.035266,-8.610076,109.17848,640000
|
| 70 |
+
786.9014,0.7947228,2.5631788,-1.8253506,-85.220375,-167.13829,3.8914545,-1.8001872,95.176346,645000
|
| 71 |
+
750.7606,1.8344504,3.1115065,-4.698361,-80.670105,-168.24486,3.7681146,-3.6617184,106.9008,650000
|
| 72 |
+
808.23083,1.5310676,3.1454313,-6.9085016,-86.80552,-176.76411,5.665899,-6.650193,203.544,655000
|
| 73 |
+
790.30005,1.1866757,2.276695,-6.3205256,-85.067856,-180.02774,5.2066903,-4.642188,99.069984,660000
|
| 74 |
+
767.0398,0.88042593,2.5593526,-8.933398,-82.65102,-171.28865,2.6147673,-2.7512605,90.849236,665000
|
| 75 |
+
748.65967,0.9095199,2.8696182,-4.8519382,-80.732216,-175.58203,4.0907574,-3.909927,100.668274,670000
|
| 76 |
+
738.4146,1.0282882,3.783757,0.50874865,-79.58459,-162.1042,8.883556,-9.0076,149.64507,675000
|
| 77 |
+
756.971,1.0486386,6.7505426,-4.941852,-81.55868,-166.354,14.543388,-14.509989,383.6606,680000
|
| 78 |
+
738.79065,0.9815539,2.3061986,-1.7204304,-80.00114,-176.50647,9.952954,-9.457936,139.6656,685000
|
| 79 |
+
760.50464,1.248038,1.7455435,-6.2076626,-82.01316,-171.12253,2.149419,-2.2062604,92.03039,690000
|
| 80 |
+
737.76215,1.0977467,2.6454215,-0.6030441,-80.23732,-156.75607,5.0341344,-5.410624,113.32216,695000
|
| 81 |
+
752.0907,1.6926332,3.3107746,-5.047271,-81.02194,-176.30309,12.000195,-10.256998,141.981,700000
|
| 82 |
+
763.84845,0.9437394,4.8092866,-1.2320012,-81.98423,-181.23242,9.104534,-9.51656,273.75873,705000
|
| 83 |
+
780.9561,1.2711927,2.0201383,-5.5420613,-83.82884,-167.80536,5.006038,-4.70293,143.26604,710000
|
| 84 |
+
753.0308,1.352349,3.0836215,-0.2849102,-81.21197,-178.02702,8.028269,-10.1541605,116.665306,715000
|
| 85 |
+
743.6613,1.1420364,3.1947298,-8.212874,-80.79064,-162.41757,18.054663,-10.024042,367.05566,720000
|
| 86 |
+
749.5941,1.0439986,4.68707,5.2620053,-80.99566,-174.84041,3.6034036,-6.263559,152.08559,725000
|
| 87 |
+
747.8231,1.0826979,2.391407,-1.7218308,-80.71792,-168.11119,4.4369617,-3.8833907,136.83281,730000
|
| 88 |
+
718.9636,1.4775288,2.794027,-5.5998144,-78.056404,-163.30861,6.482394,-7.002937,100.06658,735000
|
| 89 |
+
725.54663,0.96460533,2.5259855,-1.6908525,-78.952065,-173.9765,2.9157948,-3.5310402,93.73268,740000
|
| 90 |
+
754.3702,1.1783581,1.8194555,-3.484763,-81.157104,-165.44067,5.988167,-10.77407,203.29507,745000
|
| 91 |
+
749.14154,1.2969267,3.8388326,-4.6701317,-80.76187,-166.4654,13.456177,-15.453715,152.8089,750000
|
| 92 |
+
757.0184,1.5768065,2.8882232,-3.8268995,-81.1002,-165.22676,4.545012,-3.9273949,161.39761,755000
|
| 93 |
+
730.8891,1.2322688,2.8605525,-5.809835,-78.92743,-172.28262,3.0652173,-3.0786448,108.601616,760000
|
| 94 |
+
734.0105,0.9886557,2.2588508,-3.3347857,-79.49747,-178.43976,3.7906306,-3.7033021,94.730606,765000
|
| 95 |
+
732.5965,1.2802167,2.1851826,-1.5475245,-79.12591,-164.63258,7.7178874,-6.7318554,130.58243,770000
|
| 96 |
+
744.4439,1.0170586,2.0408473,-1.0134212,-80.44061,-175.82146,4.594987,-5.429667,91.422516,775000
|
| 97 |
+
689.60657,1.0607388,2.0958357,2.3110409,-75.28622,-165.88174,2.3652515,-2.943553,99.57483,780000
|
| 98 |
+
683.8931,1.1364448,3.1574738,-3.4482079,-74.48487,-156.06206,6.0995092,-11.228961,196.29413,785000
|
| 99 |
+
724.72815,1.4664173,2.1594098,-4.7242427,-78.2048,-167.63239,4.6017094,-4.0982294,110.577194,790000
|
| 100 |
+
698.12646,1.0609691,2.767758,0.39704955,-75.79394,-168.02867,2.912955,-1.9018892,111.22442,795000
|
| 101 |
+
708.2269,1.1827989,3.0044873,-4.0008106,-76.82312,-158.24232,29.176046,-23.688541,283.74982,800000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/online_agent_sv.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/actor_loss,actor/bc_flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
445.7115,0.7067522,0.65377146,-12.352527,-52.435505,-78.84434,0.6081508,-0.520904,30.517178,305000
|
| 3 |
+
540.9462,0.8347899,0.8316962,-11.381289,-61.580788,-109.09413,3.1441615,-3.1623406,92.36945,310000
|
| 4 |
+
616.64087,0.86508167,0.8254259,-17.779192,-68.31887,-114.497505,0.8703755,-1.3486322,48.367,315000
|
| 5 |
+
609.3012,0.9165865,1.5153502,-5.3626113,-67.824036,-146.58945,3.83913,-3.104559,83.89997,320000
|
| 6 |
+
601.0441,0.9483128,0.6209473,-21.71055,-67.12059,-124.15658,2.6138494,-1.7375144,69.066,325000
|
| 7 |
+
602.47906,0.7481787,0.9520208,-11.879025,-67.272575,-145.70853,1.0734226,-0.7574681,48.044014,330000
|
| 8 |
+
648.5374,1.0723513,0.91962475,-12.086072,-71.68345,-155.9749,5.3180294,-8.626411,201.65736,335000
|
| 9 |
+
662.57806,0.7133709,1.2167645,-23.779255,-72.92409,-145.53572,12.044887,-11.081339,119.708534,340000
|
| 10 |
+
669.28455,0.89016306,1.1195942,-17.29771,-73.96504,-140.08261,0.9281524,-1.7528518,52.101227,345000
|
| 11 |
+
665.0903,0.767177,1.5255989,-18.08008,-73.74904,-153.7963,0.60282147,-0.7558749,57.740284,350000
|
| 12 |
+
668.0568,0.80877686,1.7845745,-17.178873,-73.72634,-154.21588,1.3326921,-1.1995299,64.82351,355000
|
| 13 |
+
686.2513,0.8313422,1.41268,-16.989653,-75.43462,-152.15828,0.92451566,-1.3505316,58.180954,360000
|
| 14 |
+
707.42053,0.81933033,1.5041503,-17.248562,-77.08352,-154.41106,1.2795796,-1.322609,54.508305,365000
|
| 15 |
+
677.9205,0.833178,1.3231558,-7.459535,-74.40679,-149.41524,6.0711603,-5.5830116,231.49094,370000
|
| 16 |
+
708.14154,0.87533677,2.7791488,-20.8209,-77.69152,-165.98422,2.4237638,-2.4950507,124.903465,375000
|
| 17 |
+
775.4923,0.8390852,2.4848251,-14.617637,-84.278755,-170.78738,1.0647764,-1.1413312,73.378395,380000
|
| 18 |
+
769.2057,0.91490114,1.6568139,-23.268904,-83.2633,-172.68602,52.806942,-50.153557,966.85596,385000
|
| 19 |
+
747.43646,1.2103626,1.7273043,-15.154629,-81.38075,-172.86072,3.4175205,-3.5559297,90.181366,390000
|
| 20 |
+
752.12695,0.7634815,2.495509,-13.142955,-81.83032,-167.7289,3.1348517,-3.1964853,104.54646,395000
|
| 21 |
+
759.2383,0.9173783,1.3310732,-16.531017,-82.0801,-174.62259,11.38324,-10.722104,129.5972,400000
|
| 22 |
+
743.1406,0.68061996,2.0100157,-14.602492,-80.87149,-166.5832,2.2343507,-1.8132733,76.825264,405000
|
| 23 |
+
746.9345,0.8274262,3.782421,-7.19479,-81.37439,-169.2571,1.9872674,-1.78309,75.53299,410000
|
| 24 |
+
750.5191,0.7723874,1.543495,0.8388382,-81.45662,-175.28888,1.1554648,-1.2087846,58.415115,415000
|
| 25 |
+
778.0577,0.97244775,1.7165412,-10.761151,-84.174614,-173.57988,36.9573,-36.84243,902.6307,420000
|
| 26 |
+
781.3694,0.9713011,2.0240152,-5.035806,-84.40839,-173.2682,2.637841,-2.159695,127.93145,425000
|
| 27 |
+
758.7815,0.7949314,1.5561113,-14.528761,-81.97677,-173.46764,8.697059,-7.253913,133.22995,430000
|
| 28 |
+
735.12274,0.7623388,2.0105586,2.270846,-80.466515,-158.94768,1.2659122,-1.2246403,68.58373,435000
|
| 29 |
+
732.07465,1.0426729,3.2365913,-14.439586,-80.204506,-172.13814,2.8134086,-2.991327,112.67689,440000
|
| 30 |
+
762.48474,0.7440357,3.478644,-11.833263,-83.07718,-173.18018,2.3919027,-3.2427492,121.02144,445000
|
| 31 |
+
742.8799,1.064743,2.2775369,-16.384031,-80.40606,-164.09546,1.066736,-1.0172443,62.304688,450000
|
| 32 |
+
787.2357,0.8748975,2.1341562,-14.89056,-85.49163,-172.87286,2.3575764,-2.5423062,84.75143,455000
|
| 33 |
+
766.108,0.7674749,3.1847131,-5.929598,-83.108505,-174.02693,6.9600515,-6.649285,110.24331,460000
|
| 34 |
+
764.6128,0.9792771,1.9070653,-1.4096687,-82.49771,-164.27406,2.3908875,-2.3956656,75.37895,465000
|
| 35 |
+
768.27985,0.8667493,1.9766972,-0.184668,-83.3609,-170.03607,23.68221,-23.664942,267.78964,470000
|
| 36 |
+
797.2321,1.1415435,1.7666928,-20.70811,-86.35821,-174.70876,1.5116276,-1.4736242,61.285385,475000
|
| 37 |
+
791.9427,1.0564243,3.176107,0.096508384,-85.31713,-163.06784,1.9919732,-1.8961915,111.25355,480000
|
| 38 |
+
775.21234,0.8257254,1.4294792,-0.21109492,-84.02596,-174.27373,2.1052728,-2.1030724,67.24888,485000
|
| 39 |
+
804.4284,1.0296396,2.6542854,3.7111926,-86.20194,-169.03952,1.387049,-1.5705668,82.297165,490000
|
| 40 |
+
786.58124,2.1084867,1.7179979,-11.258596,-84.61236,-176.95967,2.8257248,-1.8964311,74.42772,495000
|
| 41 |
+
772.3121,0.96355855,2.2649553,-9.051461,-83.763145,-174.66594,2.851241,-2.7885053,78.50817,500000
|
| 42 |
+
762.72156,0.9661943,2.5731435,-14.538089,-82.59147,-176.02652,2.0492787,-1.8421787,82.672386,505000
|
| 43 |
+
793.00635,1.0129051,2.9449737,-13.474467,-85.09369,-173.79967,2.907948,-2.7646234,84.89687,510000
|
| 44 |
+
764.46246,0.7681531,10.620972,-10.667935,-82.988846,-169.3138,3.0367548,-2.8539276,240.08377,515000
|
| 45 |
+
785.77295,1.0973715,2.5735788,-16.532927,-84.8267,-176.24716,4.1926265,-2.3414068,83.00844,520000
|
| 46 |
+
774.31335,0.92759156,2.8527231,-2.9606376,-83.33984,-176.90286,1.7836312,-2.036624,105.26757,525000
|
| 47 |
+
804.3937,1.132477,2.0732124,-8.804147,-86.8793,-168.53128,17.369062,-15.127992,168.76201,530000
|
| 48 |
+
803.14105,1.4882967,3.8520706,-6.5309706,-85.128716,-175.34886,57.06677,-29.42813,497.08215,535000
|
| 49 |
+
794.6374,1.3967235,3.2766836,2.9274538,-85.54815,-173.90913,2.6659544,-3.0292783,145.1177,540000
|
| 50 |
+
757.95184,0.85211813,2.323631,-5.6617417,-81.89776,-170.5356,3.6532433,-3.4411225,90.62291,545000
|
| 51 |
+
797.204,1.395182,2.9096801,-11.654829,-85.379684,-173.55327,2.074678,-1.6246101,92.78856,550000
|
| 52 |
+
803.08795,0.9311178,2.0466588,-24.597004,-86.70263,-174.4755,14.803878,-16.312965,460.04968,555000
|
| 53 |
+
752.2199,0.9442888,2.632631,2.4421306,-81.47011,-175.86276,4.584734,-3.2361383,136.05646,560000
|
| 54 |
+
766.3031,1.2555871,3.3333383,-6.6597457,-82.95369,-168.72765,3.7065883,-3.4906888,97.70839,565000
|
| 55 |
+
794.64935,1.2057395,3.730072,-12.307201,-85.65021,-177.45009,3.522656,-5.2406306,122.726685,570000
|
| 56 |
+
793.63586,1.172966,2.7419572,-6.265837,-85.156746,-175.84364,2.5144324,-2.7212806,90.27865,575000
|
| 57 |
+
786.3652,1.2119699,2.3650258,-11.777868,-84.69754,-164.05388,3.1694105,-3.3200488,76.25548,580000
|
| 58 |
+
799.79486,1.0494143,5.4708204,-6.1812377,-85.48999,-174.44789,1.325226,-1.882567,135.23236,585000
|
| 59 |
+
775.6564,1.3542421,2.8076637,-3.441286,-83.750854,-178.82812,1.8704932,-2.4562473,81.913704,590000
|
| 60 |
+
750.96497,1.1345422,3.2515957,1.1290846,-81.19744,-178.57076,1.8631359,-1.7144275,99.14474,595000
|
| 61 |
+
767.51483,0.9448624,2.1504982,-6.5295167,-82.60241,-171.99377,3.0315926,-2.6483727,115.30594,600000
|
| 62 |
+
779.5913,0.88519406,2.4766946,-2.1794984,-84.19848,-160.03574,5.0879574,-5.541548,106.40292,605000
|
| 63 |
+
737.22723,1.1187298,2.8533242,-3.6369731,-80.2213,-168.16307,103.195854,-73.214874,2002.8071,610000
|
| 64 |
+
738.0061,0.9001357,3.6137562,-4.03646,-79.739944,-160.34088,6.90032,-6.270361,142.53078,615000
|
| 65 |
+
742.6438,0.9189588,3.3265824,-4.1122527,-80.47425,-156.62767,3.0442863,-2.7793715,107.66594,620000
|
| 66 |
+
761.2071,0.82523656,2.4533162,-8.560383,-82.10732,-161.27226,11.7015085,-11.748071,131.48909,625000
|
| 67 |
+
788.7787,1.1402719,3.8665054,-6.8959923,-84.30932,-180.80365,20.331932,-24.965939,241.03583,630000
|
| 68 |
+
739.129,0.93275607,11.155135,-8.994619,-80.42977,-159.0004,7.3336573,-6.392983,154.87224,635000
|
| 69 |
+
744.95776,1.1765379,2.3001025,-3.9059694,-80.72818,-172.14642,8.035266,-8.610076,109.17848,640000
|
| 70 |
+
786.9014,0.7947228,2.5631788,-1.8253506,-85.220375,-167.13829,3.8914545,-1.8001872,95.176346,645000
|
| 71 |
+
750.7606,1.8344504,3.1115065,-4.698361,-80.670105,-168.24486,3.7681146,-3.6617184,106.9008,650000
|
| 72 |
+
808.23083,1.5310676,3.1454313,-6.9085016,-86.80552,-176.76411,5.665899,-6.650193,203.544,655000
|
| 73 |
+
790.30005,1.1866757,2.276695,-6.3205256,-85.067856,-180.02774,5.2066903,-4.642188,99.069984,660000
|
| 74 |
+
767.0398,0.88042593,2.5593526,-8.933398,-82.65102,-171.28865,2.6147673,-2.7512605,90.849236,665000
|
| 75 |
+
748.65967,0.9095199,2.8696182,-4.8519382,-80.732216,-175.58203,4.0907574,-3.909927,100.668274,670000
|
| 76 |
+
738.4146,1.0282882,3.783757,0.50874865,-79.58459,-162.1042,8.883556,-9.0076,149.64507,675000
|
| 77 |
+
756.971,1.0486386,6.7505426,-4.941852,-81.55868,-166.354,14.543388,-14.509989,383.6606,680000
|
| 78 |
+
738.79065,0.9815539,2.3061986,-1.7204304,-80.00114,-176.50647,9.952954,-9.457936,139.6656,685000
|
| 79 |
+
760.50464,1.248038,1.7455435,-6.2076626,-82.01316,-171.12253,2.149419,-2.2062604,92.03039,690000
|
| 80 |
+
737.76215,1.0977467,2.6454215,-0.6030441,-80.23732,-156.75607,5.0341344,-5.410624,113.32216,695000
|
| 81 |
+
752.0907,1.6926332,3.3107746,-5.047271,-81.02194,-176.30309,12.000195,-10.256998,141.981,700000
|
| 82 |
+
763.84845,0.9437394,4.8092866,-1.2320012,-81.98423,-181.23242,9.104534,-9.51656,273.75873,705000
|
| 83 |
+
780.9561,1.2711927,2.0201383,-5.5420613,-83.82884,-167.80536,5.006038,-4.70293,143.26604,710000
|
| 84 |
+
753.0308,1.352349,3.0836215,-0.2849102,-81.21197,-178.02702,8.028269,-10.1541605,116.665306,715000
|
| 85 |
+
743.6613,1.1420364,3.1947298,-8.212874,-80.79064,-162.41757,18.054663,-10.024042,367.05566,720000
|
| 86 |
+
749.5941,1.0439986,4.68707,5.2620053,-80.99566,-174.84041,3.6034036,-6.263559,152.08559,725000
|
| 87 |
+
747.8231,1.0826979,2.391407,-1.7218308,-80.71792,-168.11119,4.4369617,-3.8833907,136.83281,730000
|
| 88 |
+
718.9636,1.4775288,2.794027,-5.5998144,-78.056404,-163.30861,6.482394,-7.002937,100.06658,735000
|
| 89 |
+
725.54663,0.96460533,2.5259855,-1.6908525,-78.952065,-173.9765,2.9157948,-3.5310402,93.73268,740000
|
| 90 |
+
754.3702,1.1783581,1.8194555,-3.484763,-81.157104,-165.44067,5.988167,-10.77407,203.29507,745000
|
| 91 |
+
749.14154,1.2969267,3.8388326,-4.6701317,-80.76187,-166.4654,13.456177,-15.453715,152.8089,750000
|
| 92 |
+
757.0184,1.5768065,2.8882232,-3.8268995,-81.1002,-165.22676,4.545012,-3.9273949,161.39761,755000
|
| 93 |
+
730.8891,1.2322688,2.8605525,-5.809835,-78.92743,-172.28262,3.0652173,-3.0786448,108.601616,760000
|
| 94 |
+
734.0105,0.9886557,2.2588508,-3.3347857,-79.49747,-178.43976,3.7906306,-3.7033021,94.730606,765000
|
| 95 |
+
732.5965,1.2802167,2.1851826,-1.5475245,-79.12591,-164.63258,7.7178874,-6.7318554,130.58243,770000
|
| 96 |
+
744.4439,1.0170586,2.0408473,-1.0134212,-80.44061,-175.82146,4.594987,-5.429667,91.422516,775000
|
| 97 |
+
689.60657,1.0607388,2.0958357,2.3110409,-75.28622,-165.88174,2.3652515,-2.943553,99.57483,780000
|
| 98 |
+
683.8931,1.1364448,3.1574738,-3.4482079,-74.48487,-156.06206,6.0995092,-11.228961,196.29413,785000
|
| 99 |
+
724.72815,1.4664173,2.1594098,-4.7242427,-78.2048,-167.63239,4.6017094,-4.0982294,110.577194,790000
|
| 100 |
+
698.12646,1.0609691,2.767758,0.39704955,-75.79394,-168.02867,2.912955,-1.9018892,111.22442,795000
|
| 101 |
+
708.2269,1.1827989,3.0044873,-4.0008106,-76.82312,-158.24232,29.176046,-23.688541,283.74982,800000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_350000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97df409d4f4df5c0ecf62dfb18c9128c04e6ecab4bb2137f9e5b93522410471a
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_400000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f5500254be5c558bb709259ad3cb861f2e4ae04f470f70e9f24951bbd85a7de
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_450000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a761c36aea4cc9aae64110010f0a16423d7c395d98b9c20ae4d2cdd9908c90f7
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_500000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcd4aa74ce987554c2bfafbb4c6a5e067203e7e007d06c7e7f425bec7c5056a9
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_550000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6d1fad6d15131e1c1f95e0500cd3148d05cb594fe59fd2a1be864e52f11a0fd
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_600000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c734c949d0b9a20c55dd341954a73a897b656a1670b581b9a84c770d9a241c3f
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_650000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e8a78cfebd39404c16225dec9d2feaf5856aa109dac33fb125c4b2f4ecceafc
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_700000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1a357401830d89795b29be7d13358693cf08c6cd629021eec5b39d8759693da
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_750000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa3f913da2ccd8d4d01890d070f83ae3d324b1848823f8cd6ccf5d38a2182b96
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/params_800000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2bfee00da7649a1937358dcd15c7d198d608549a931d85db15e8ee0e021401c
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_125821/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/ttfa3xd8
|