| {"t": 0, "ts": 1788123232.3791976, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 12832.8828125, "attn_entropy": 1.1551029682159424, "load_balance": 0.0003258686823149522, "g_entropy": 1.1549687385559082, "tau_bias": 0.6566849946975708, "beta": 0.10835317894816399, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788123237.188802, "step": 10, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 7.071310847095447e-06, "advantage": -587.4507446289062, "attn_entropy": 1.110655387242635, "load_balance": 0.00032854297508796054, "g_entropy": 1.1549643675486247, "tau_bias": 0.6658554673194885, "beta": 0.22102038655430079, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788123242.6741729, "step": 20, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.004781411495059729, "advantage": -573.068115234375, "attn_entropy": 0.9017306168874105, "load_balance": 0.0003327992744743824, "g_entropy": 1.154973030090332, "tau_bias": 0.6756224036216736, "beta": 0.2527519352734089, "train_val_corr": 0.0} |
| {"t": 3, "ts": 1788123247.4612484, "step": 30, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.6780183911323547, "advantage": -546.783935546875, "attn_entropy": 0.7481436729431152, "load_balance": 0.0003334786354874571, "g_entropy": 1.1549304326375325, "tau_bias": 0.67994624376297, "beta": 0.2310744859278202, "train_val_corr": 0.0} |
| {"t": 4, "ts": 1788123252.2598903, "step": 40, "action": "PGO_UPDATE", "entropy_pi": 0.003476420184597373, "advantage": -517.9473266601562, "attn_entropy": 0.6541844209035238, "load_balance": 0.00032881022586176795, "g_entropy": 1.1549675464630127, "tau_bias": 0.6816269159317017, "beta": 0.27597904826203984, "train_val_corr": 0.0} |
| {"t": 5, "ts": 1788123257.1605139, "step": 50, "action": "PGO_UPDATE", "entropy_pi": 0.0006053193937987089, "advantage": -494.4080505371094, "attn_entropy": 0.6063317060470581, "load_balance": 0.00032786567074557144, "g_entropy": 1.1549241542816162, "tau_bias": 0.6823055148124695, "beta": 0.29740134999156, "train_val_corr": 0.0} |
| {"t": 6, "ts": 1788123268.6798966, "step": 60, "action": "PGO_UPDATE", "entropy_pi": 0.003176433965563774, "advantage": -470.0270080566406, "attn_entropy": 0.6557672023773193, "load_balance": 0.0003345807393391927, "g_entropy": 1.1549659570058186, "tau_bias": 0.6827506422996521, "beta": 0.2810777711371581, "train_val_corr": 0.0} |
| {"t": 7, "ts": 1788123273.4629374, "step": 70, "action": "PGO_UPDATE", "entropy_pi": 0.10070239752531052, "advantage": -446.7344970703125, "attn_entropy": 0.7486160596211752, "load_balance": 0.0003319638005147378, "g_entropy": 1.1549734274546306, "tau_bias": 0.6825464367866516, "beta": 0.28341985990603763, "train_val_corr": 0.0} |
| {"t": 8, "ts": 1788123278.2771645, "step": 80, "action": "PGO_UPDATE", "entropy_pi": 0.6864379644393921, "advantage": -425.8521423339844, "attn_entropy": 0.6764365832010905, "load_balance": 0.0003247920928212504, "g_entropy": 1.154962380727132, "tau_bias": 0.6821361184120178, "beta": 0.26636930368840694, "train_val_corr": 0.0} |
| {"t": 9, "ts": 1788123283.1606226, "step": 90, "action": "ATTN_META_ONLY", "entropy_pi": 0.03251105546951294, "advantage": -406.2437438964844, "attn_entropy": 0.6970227559407552, "load_balance": 0.0003280730064337452, "g_entropy": 1.154942512512207, "tau_bias": 0.6825621128082275, "beta": 0.31226665154099464, "train_val_corr": 0.0} |
| {"t": 10, "ts": 1788123286.6953292, "step": 100, "action": "ATTN_META_ONLY", "entropy_pi": 0.004839178174734116, "advantage": -378.604736328125, "attn_entropy": 0.7450563907623291, "load_balance": 0.00033152801916003227, "g_entropy": 1.1549358367919922, "tau_bias": 0.6825621128082275, "beta": 0.3085903835793336, "train_val_corr": 0.0} |
| {"t": 11, "ts": 1788123290.1773558, "step": 110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723346949580446e-07, "advantage": -364.6076965332031, "attn_entropy": 0.7687347730000814, "load_balance": 0.0003314387674132983, "g_entropy": 1.1549256642659504, "tau_bias": 0.6825621128082275, "beta": 0.27792889811098576, "train_val_corr": 0.0} |
| {"t": 12, "ts": 1788123300.0782745, "step": 120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072342653036685e-07, "advantage": -346.85736083984375, "attn_entropy": 0.7863913377126058, "load_balance": 0.0003292378581439455, "g_entropy": 1.1549545923868816, "tau_bias": 0.6825621128082275, "beta": 0.3021370011071364, "train_val_corr": 0.0} |
| {"t": 13, "ts": 1788123303.5702984, "step": 130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723550164802873e-07, "advantage": -329.94317626953125, "attn_entropy": 0.7910951773325602, "load_balance": 0.0003294936614111066, "g_entropy": 1.1549348831176758, "tau_bias": 0.6825621128082275, "beta": 0.29860567549864453, "train_val_corr": 0.0} |
| {"t": 14, "ts": 1788123306.9964564, "step": 140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723815907786047e-07, "advantage": -315.177001953125, "attn_entropy": 0.7854828039805094, "load_balance": 0.00033075773778061074, "g_entropy": 1.1549527645111084, "tau_bias": 0.6825621128082275, "beta": 0.2868374188741048, "train_val_corr": 0.0} |
| {"t": 15, "ts": 1788123310.4336946, "step": 150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072430334010278e-07, "advantage": -300.54364013671875, "attn_entropy": 0.806801954905192, "load_balance": 0.0003320779263352354, "g_entropy": 1.154934008916219, "tau_bias": 0.6825621128082275, "beta": 0.2829129522045453, "train_val_corr": 0.0} |
| {"t": 16, "ts": 1788123313.8590446, "step": 160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0724863247778558e-07, "advantage": -282.859375, "attn_entropy": 0.8049591382344564, "load_balance": 0.0003344236562649409, "g_entropy": 1.154828707377116, "tau_bias": 0.6825621128082275, "beta": 0.3094390748689572, "train_val_corr": 0.0} |
| {"t": 17, "ts": 1788123317.259023, "step": 170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0726020011352375e-07, "advantage": -273.0431823730469, "attn_entropy": 0.816098690032959, "load_balance": 0.00033277478845169145, "g_entropy": 1.15491517384847, "tau_bias": 0.6825621128082275, "beta": 0.30594976370533306, "train_val_corr": 0.0} |
| {"t": 18, "ts": 1788123327.1478925, "step": 180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072763152227708e-07, "advantage": -261.8917236328125, "attn_entropy": 0.8266554673512777, "load_balance": 0.0003347119006017844, "g_entropy": 1.154862403869629, "tau_bias": 0.6825621128082275, "beta": 0.3424251476923625, "train_val_corr": 0.0} |
| {"t": 19, "ts": 1788123330.6659534, "step": 190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0729551408749103e-07, "advantage": -244.13601684570312, "attn_entropy": 0.818052609761556, "load_balance": 0.0003300629323348403, "g_entropy": 1.1549814542134602, "tau_bias": 0.6825621128082275, "beta": 0.3231017825504144, "train_val_corr": 1.0} |
| {"t": 20, "ts": 1788123334.272678, "step": 200, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0733752137402917e-07, "advantage": -236.36441040039062, "attn_entropy": 0.8215668996175131, "load_balance": 0.00033043216293056804, "g_entropy": 1.1549723148345947, "tau_bias": 0.6825621128082275, "beta": 0.3305903437236945, "train_val_corr": 1.0} |
| {"t": 21, "ts": 1788123337.7881172, "step": 210, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0738039552270493e-07, "advantage": -226.50099182128906, "attn_entropy": 0.825922966003418, "load_balance": 0.00033078497896591824, "g_entropy": 1.1548945903778076, "tau_bias": 0.6825621128082275, "beta": 0.31367285425464314, "train_val_corr": 1.0} |
| {"t": 22, "ts": 1788123341.592222, "step": 220, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0743024720104586e-07, "advantage": -215.33673095703125, "attn_entropy": 0.8341524600982666, "load_balance": 0.00032877274012813967, "g_entropy": 1.1549522082010906, "tau_bias": 0.6825621128082275, "beta": 0.30157431090871495, "train_val_corr": 1.0} |
| {"t": 23, "ts": 1788123345.137974, "step": 230, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0748788642777072e-07, "advantage": -205.11598205566406, "attn_entropy": 0.8666248321533203, "load_balance": 0.0003315812209621072, "g_entropy": 1.1549619038899739, "tau_bias": 0.6825621128082275, "beta": 0.35245781764388084, "train_val_corr": 1.0} |
| {"t": 24, "ts": 1788123355.1466155, "step": 240, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0754674778800108e-07, "advantage": -195.72412109375, "attn_entropy": 0.8700911204020182, "load_balance": 0.00033078032235304516, "g_entropy": 1.1549568176269531, "tau_bias": 0.6825621128082275, "beta": 0.32509595279892284, "train_val_corr": 1.0} |
| {"t": 25, "ts": 1788123358.6922984, "step": 250, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0763842201176885e-07, "advantage": -186.8941192626953, "attn_entropy": 0.9012970924377441, "load_balance": 0.00033122549454371136, "g_entropy": 1.1549537181854248, "tau_bias": 0.6825621128082275, "beta": 0.356266714942952, "train_val_corr": 1.0} |
| {"t": 26, "ts": 1788123362.6556592, "step": 260, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.07740356472641e-07, "advantage": -176.7180633544922, "attn_entropy": 0.8586797714233398, "load_balance": 0.00032934173941612244, "g_entropy": 1.1549493471781414, "tau_bias": 0.6825621128082275, "beta": 0.3547169864177704, "train_val_corr": 1.0} |
| {"t": 27, "ts": 1788123366.5459092, "step": 270, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0788473875654745e-07, "advantage": -169.86134338378906, "attn_entropy": 0.8861077626546224, "load_balance": 0.0003339961015929778, "g_entropy": 1.1548774242401123, "tau_bias": 0.6825621128082275, "beta": 0.3975948852797349, "train_val_corr": 1.0} |
| {"t": 28, "ts": 1788123369.9703157, "step": 280, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0807196676742024e-07, "advantage": -160.20785522460938, "attn_entropy": 0.8616431554158529, "load_balance": 0.0003307206400980552, "g_entropy": 1.1549482345581055, "tau_bias": 0.6825621128082275, "beta": 0.40018168340126675, "train_val_corr": 0.9999999999999998} |
| {"t": 29, "ts": 1788123389.765345, "step": 290, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723400950828363e-07, "advantage": 9772.640625, "attn_entropy": 1.6032943725585938, "load_balance": 0.0004850582918152213, "g_entropy": 1.732589066028595, "tau_bias": 0.6825621128082275, "beta": 0.4298086650669575, "train_val_corr": 0.9999999999999998} |
| {"t": 30, "ts": 1788123394.144352, "step": 300, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -660.8260498046875, "attn_entropy": 1.6144757270812988, "load_balance": 0.00048595285625196993, "g_entropy": 1.732594609260559, "tau_bias": 0.6825621128082275, "beta": 0.44341884305079776, "train_val_corr": 1.0} |
| {"t": 31, "ts": 1788123399.1420295, "step": 310, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -627.4502563476562, "attn_entropy": 1.6326448321342468, "load_balance": 0.0004826370713999495, "g_entropy": 1.7324487566947937, "tau_bias": 0.6825621128082275, "beta": 0.46108969549338025, "train_val_corr": 1.0} |
| {"t": 32, "ts": 1788123403.7734513, "step": 320, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -593.341796875, "attn_entropy": 1.6058680415153503, "load_balance": 0.0004873054276686162, "g_entropy": 1.7325820326805115, "tau_bias": 0.6825621128082275, "beta": 0.4654461480677128, "train_val_corr": 1.0} |
| {"t": 33, "ts": 1788123408.7596056, "step": 330, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -564.1156616210938, "attn_entropy": 1.600083827972412, "load_balance": 0.0004870330885751173, "g_entropy": 1.7325961589813232, "tau_bias": 0.6825621128082275, "beta": 0.4738068828980128, "train_val_corr": 1.0} |
| {"t": 34, "ts": 1788123413.5856314, "step": 340, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -536.6885375976562, "attn_entropy": 1.6083407998085022, "load_balance": 0.0004855669249081984, "g_entropy": 1.7325507402420044, "tau_bias": 0.6825621128082275, "beta": 0.47891748944918316, "train_val_corr": 1.0} |
| {"t": 35, "ts": 1788123427.7005165, "step": 350, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -510.23553466796875, "attn_entropy": 1.6136450171470642, "load_balance": 0.0004862082132603973, "g_entropy": 1.7325899600982666, "tau_bias": 0.6825621128082275, "beta": 0.48047497992714244, "train_val_corr": 1.0} |
| {"t": 36, "ts": 1788123432.3819606, "step": 360, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -484.1174011230469, "attn_entropy": 1.6175566911697388, "load_balance": 0.0004871479468420148, "g_entropy": 1.7326183319091797, "tau_bias": 0.6825621128082275, "beta": 0.48374314109484357, "train_val_corr": 1.0} |
| {"t": 37, "ts": 1788123437.7028708, "step": 370, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -461.1568298339844, "attn_entropy": 1.6441801190376282, "load_balance": 0.00048355277976952493, "g_entropy": 1.732432782649994, "tau_bias": 0.6825621128082275, "beta": 0.4854518497983615, "train_val_corr": 1.0} |
| {"t": 38, "ts": 1788123442.4343026, "step": 380, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -438.68182373046875, "attn_entropy": 1.634229838848114, "load_balance": 0.0004848124081036076, "g_entropy": 1.7325506806373596, "tau_bias": 0.6825621128082275, "beta": 0.48647210250298184, "train_val_corr": 1.0} |
| {"t": 39, "ts": 1788123446.8809364, "step": 390, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -415.703857421875, "attn_entropy": 1.6223089098930359, "load_balance": 0.00048576516564935446, "g_entropy": 1.7325075268745422, "tau_bias": 0.6825621128082275, "beta": 0.44302606706817943, "train_val_corr": 1.0} |
| {"t": 40, "ts": 1788123451.5779743, "step": 400, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -395.15301513671875, "attn_entropy": 1.6182129383087158, "load_balance": 0.0004849694232689217, "g_entropy": 1.7325542569160461, "tau_bias": 0.6825621128082275, "beta": 0.4548296605547269, "train_val_corr": 0.9999999999999998} |
| {"t": 0, "ts": 1788123541.9785392, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 12832.8828125, "attn_entropy": 1.1551029682159424, "load_balance": 0.0003258686823149522, "g_entropy": 1.1549687385559082, "tau_bias": 0.6566849946975708, "beta": 0.10835317894816399, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788123546.3966537, "step": 10, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 7.071310847095447e-06, "advantage": -587.4507446289062, "attn_entropy": 1.110655387242635, "load_balance": 0.00032854297508796054, "g_entropy": 1.1549643675486247, "tau_bias": 0.6658554673194885, "beta": 0.22102038655430079, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788123551.2294638, "step": 20, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.004781411495059729, "advantage": -573.068115234375, "attn_entropy": 0.9017306168874105, "load_balance": 0.0003327992744743824, "g_entropy": 1.154973030090332, "tau_bias": 0.6756224036216736, "beta": 0.2527519352734089, "train_val_corr": 0.0} |
| {"t": 3, "ts": 1788123555.9621563, "step": 30, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.6780183911323547, "advantage": -546.783935546875, "attn_entropy": 0.7481436729431152, "load_balance": 0.0003334786354874571, "g_entropy": 1.1549304326375325, "tau_bias": 0.67994624376297, "beta": 0.2310744859278202, "train_val_corr": 0.0} |
| {"t": 4, "ts": 1788123560.6857433, "step": 40, "action": "PGO_UPDATE", "entropy_pi": 0.003476420184597373, "advantage": -517.9473266601562, "attn_entropy": 0.6541844209035238, "load_balance": 0.00032881022586176795, "g_entropy": 1.1549675464630127, "tau_bias": 0.6816269159317017, "beta": 0.27597904826203984, "train_val_corr": 0.0} |
| {"t": 5, "ts": 1788123565.372801, "step": 50, "action": "PGO_UPDATE", "entropy_pi": 0.0006053193937987089, "advantage": -494.4080505371094, "attn_entropy": 0.6063317060470581, "load_balance": 0.00032786567074557144, "g_entropy": 1.1549241542816162, "tau_bias": 0.6823055148124695, "beta": 0.29740134999156, "train_val_corr": 0.0} |
| {"t": 6, "ts": 1788123576.6841884, "step": 60, "action": "PGO_UPDATE", "entropy_pi": 0.003176433965563774, "advantage": -470.0270080566406, "attn_entropy": 0.6557672023773193, "load_balance": 0.0003345807393391927, "g_entropy": 1.1549659570058186, "tau_bias": 0.6827506422996521, "beta": 0.2810777711371581, "train_val_corr": 0.0} |
| {"t": 7, "ts": 1788123581.2706726, "step": 70, "action": "PGO_UPDATE", "entropy_pi": 0.10070239752531052, "advantage": -446.7344970703125, "attn_entropy": 0.7486160596211752, "load_balance": 0.0003319638005147378, "g_entropy": 1.1549734274546306, "tau_bias": 0.6825464367866516, "beta": 0.28341985990603763, "train_val_corr": 0.0} |
| {"t": 8, "ts": 1788123585.8688405, "step": 80, "action": "PGO_UPDATE", "entropy_pi": 0.6864379644393921, "advantage": -425.8521423339844, "attn_entropy": 0.6764365832010905, "load_balance": 0.0003247920928212504, "g_entropy": 1.154962380727132, "tau_bias": 0.6821361184120178, "beta": 0.26636930368840694, "train_val_corr": 0.0} |
| {"t": 9, "ts": 1788123590.0711675, "step": 90, "action": "ATTN_META_ONLY", "entropy_pi": 0.03251105546951294, "advantage": -406.2437438964844, "attn_entropy": 0.6970227559407552, "load_balance": 0.0003280730064337452, "g_entropy": 1.154942512512207, "tau_bias": 0.6825621128082275, "beta": 0.31226665154099464, "train_val_corr": 0.0} |
| {"t": 10, "ts": 1788123593.1590514, "step": 100, "action": "ATTN_META_ONLY", "entropy_pi": 0.004839178174734116, "advantage": -378.604736328125, "attn_entropy": 0.7450563907623291, "load_balance": 0.00033152801916003227, "g_entropy": 1.1549358367919922, "tau_bias": 0.6825621128082275, "beta": 0.3085903835793336, "train_val_corr": 0.0} |
| {"t": 11, "ts": 1788123596.1462967, "step": 110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723346949580446e-07, "advantage": -364.6076965332031, "attn_entropy": 0.7687347730000814, "load_balance": 0.0003314387674132983, "g_entropy": 1.1549256642659504, "tau_bias": 0.6825621128082275, "beta": 0.27792889811098576, "train_val_corr": 0.0} |
| {"t": 12, "ts": 1788123605.648593, "step": 120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072342653036685e-07, "advantage": -346.85736083984375, "attn_entropy": 0.7863913377126058, "load_balance": 0.0003292378581439455, "g_entropy": 1.1549545923868816, "tau_bias": 0.6825621128082275, "beta": 0.3021370011071364, "train_val_corr": 0.0} |
| {"t": 13, "ts": 1788123608.836012, "step": 130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723550164802873e-07, "advantage": -329.94317626953125, "attn_entropy": 0.7910951773325602, "load_balance": 0.0003294936614111066, "g_entropy": 1.1549348831176758, "tau_bias": 0.6825621128082275, "beta": 0.29860567549864453, "train_val_corr": 0.0} |
| {"t": 14, "ts": 1788123611.860091, "step": 140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723815907786047e-07, "advantage": -315.177001953125, "attn_entropy": 0.7854828039805094, "load_balance": 0.00033075773778061074, "g_entropy": 1.1549527645111084, "tau_bias": 0.6825621128082275, "beta": 0.2868374188741048, "train_val_corr": 0.0} |
| {"t": 15, "ts": 1788123614.8538897, "step": 150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072430334010278e-07, "advantage": -300.54364013671875, "attn_entropy": 0.806801954905192, "load_balance": 0.0003320779263352354, "g_entropy": 1.154934008916219, "tau_bias": 0.6825621128082275, "beta": 0.2829129522045453, "train_val_corr": 0.0} |
| {"t": 16, "ts": 1788123617.8897479, "step": 160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0724863247778558e-07, "advantage": -282.859375, "attn_entropy": 0.8049591382344564, "load_balance": 0.0003344236562649409, "g_entropy": 1.154828707377116, "tau_bias": 0.6825621128082275, "beta": 0.3094390748689572, "train_val_corr": 0.0} |
| {"t": 17, "ts": 1788123620.9476707, "step": 170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0726020011352375e-07, "advantage": -273.0431823730469, "attn_entropy": 0.816098690032959, "load_balance": 0.00033277478845169145, "g_entropy": 1.15491517384847, "tau_bias": 0.6825621128082275, "beta": 0.30594976370533306, "train_val_corr": 0.0} |
| {"t": 18, "ts": 1788123630.3594387, "step": 180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072763152227708e-07, "advantage": -261.8917236328125, "attn_entropy": 0.8266554673512777, "load_balance": 0.0003347119006017844, "g_entropy": 1.154862403869629, "tau_bias": 0.6825621128082275, "beta": 0.3424251476923625, "train_val_corr": 0.0} |
| {"t": 19, "ts": 1788123633.3544095, "step": 190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0729551408749103e-07, "advantage": -244.13601684570312, "attn_entropy": 0.818052609761556, "load_balance": 0.0003300629323348403, "g_entropy": 1.1549814542134602, "tau_bias": 0.6825621128082275, "beta": 0.3231017825504144, "train_val_corr": 1.0} |
| {"t": 20, "ts": 1788123636.3629794, "step": 200, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0733752137402917e-07, "advantage": -236.36441040039062, "attn_entropy": 0.8215668996175131, "load_balance": 0.00033043216293056804, "g_entropy": 1.1549723148345947, "tau_bias": 0.6825621128082275, "beta": 0.3305903437236945, "train_val_corr": 1.0} |
| {"t": 21, "ts": 1788123639.3464582, "step": 210, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0738039552270493e-07, "advantage": -226.50099182128906, "attn_entropy": 0.825922966003418, "load_balance": 0.00033078497896591824, "g_entropy": 1.1548945903778076, "tau_bias": 0.6825621128082275, "beta": 0.31367285425464314, "train_val_corr": 1.0} |
| {"t": 22, "ts": 1788123642.344512, "step": 220, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0743024720104586e-07, "advantage": -215.33673095703125, "attn_entropy": 0.8341524600982666, "load_balance": 0.00032877274012813967, "g_entropy": 1.1549522082010906, "tau_bias": 0.6825621128082275, "beta": 0.30157431090871495, "train_val_corr": 1.0} |
| {"t": 23, "ts": 1788123645.347132, "step": 230, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0748788642777072e-07, "advantage": -205.11598205566406, "attn_entropy": 0.8666248321533203, "load_balance": 0.0003315812209621072, "g_entropy": 1.1549619038899739, "tau_bias": 0.6825621128082275, "beta": 0.35245781764388084, "train_val_corr": 1.0} |
| {"t": 24, "ts": 1788123654.8451715, "step": 240, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0754674778800108e-07, "advantage": -195.72412109375, "attn_entropy": 0.8700911204020182, "load_balance": 0.00033078032235304516, "g_entropy": 1.1549568176269531, "tau_bias": 0.6825621128082275, "beta": 0.32509595279892284, "train_val_corr": 1.0} |
| {"t": 25, "ts": 1788123657.8578753, "step": 250, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0763842201176885e-07, "advantage": -186.8941192626953, "attn_entropy": 0.9012970924377441, "load_balance": 0.00033122549454371136, "g_entropy": 1.1549537181854248, "tau_bias": 0.6825621128082275, "beta": 0.356266714942952, "train_val_corr": 1.0} |
| {"t": 26, "ts": 1788123660.850109, "step": 260, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.07740356472641e-07, "advantage": -176.7180633544922, "attn_entropy": 0.8586797714233398, "load_balance": 0.00032934173941612244, "g_entropy": 1.1549493471781414, "tau_bias": 0.6825621128082275, "beta": 0.3547169864177704, "train_val_corr": 1.0} |
| {"t": 27, "ts": 1788123663.844448, "step": 270, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0788473875654745e-07, "advantage": -169.86134338378906, "attn_entropy": 0.8861077626546224, "load_balance": 0.0003339961015929778, "g_entropy": 1.1548774242401123, "tau_bias": 0.6825621128082275, "beta": 0.3975948852797349, "train_val_corr": 1.0} |
| {"t": 28, "ts": 1788123666.8458927, "step": 280, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0807196676742024e-07, "advantage": -160.20785522460938, "attn_entropy": 0.8616431554158529, "load_balance": 0.0003307206400980552, "g_entropy": 1.1549482345581055, "tau_bias": 0.6825621128082275, "beta": 0.40018168340126675, "train_val_corr": 0.9999999999999998} |
| {"t": 29, "ts": 1788123687.1535983, "step": 290, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723400950828363e-07, "advantage": 9772.640625, "attn_entropy": 1.6032943725585938, "load_balance": 0.0004850582918152213, "g_entropy": 1.732589066028595, "tau_bias": 0.6825621128082275, "beta": 0.4298086650669575, "train_val_corr": 0.9999999999999998} |
| {"t": 30, "ts": 1788123691.2324996, "step": 300, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -660.8260498046875, "attn_entropy": 1.6144757270812988, "load_balance": 0.00048595285625196993, "g_entropy": 1.732594609260559, "tau_bias": 0.6825621128082275, "beta": 0.44341884305079776, "train_val_corr": 1.0} |
| {"t": 31, "ts": 1788123695.7337568, "step": 310, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -627.4502563476562, "attn_entropy": 1.6326448321342468, "load_balance": 0.0004826370713999495, "g_entropy": 1.7324487566947937, "tau_bias": 0.6825621128082275, "beta": 0.46108969549338025, "train_val_corr": 1.0} |
| {"t": 32, "ts": 1788123699.8326073, "step": 320, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -593.341796875, "attn_entropy": 1.6058680415153503, "load_balance": 0.0004873054276686162, "g_entropy": 1.7325820326805115, "tau_bias": 0.6825621128082275, "beta": 0.4654461480677128, "train_val_corr": 1.0} |
| {"t": 33, "ts": 1788123703.8381047, "step": 330, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -564.1156616210938, "attn_entropy": 1.600083827972412, "load_balance": 0.0004870330885751173, "g_entropy": 1.7325961589813232, "tau_bias": 0.6825621128082275, "beta": 0.4738068828980128, "train_val_corr": 1.0} |
| {"t": 34, "ts": 1788123707.8701968, "step": 340, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -536.6885375976562, "attn_entropy": 1.6083407998085022, "load_balance": 0.0004855669249081984, "g_entropy": 1.7325507402420044, "tau_bias": 0.6825621128082275, "beta": 0.47891748944918316, "train_val_corr": 1.0} |
| {"t": 35, "ts": 1788123722.3620443, "step": 350, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -510.23553466796875, "attn_entropy": 1.6136450171470642, "load_balance": 0.0004862082132603973, "g_entropy": 1.7325899600982666, "tau_bias": 0.6825621128082275, "beta": 0.48047497992714244, "train_val_corr": 1.0} |
| {"t": 36, "ts": 1788123726.344007, "step": 360, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -484.1174011230469, "attn_entropy": 1.6175566911697388, "load_balance": 0.0004871479468420148, "g_entropy": 1.7326183319091797, "tau_bias": 0.6825621128082275, "beta": 0.48374314109484357, "train_val_corr": 1.0} |
| {"t": 37, "ts": 1788123730.8592224, "step": 370, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -461.1568298339844, "attn_entropy": 1.6441801190376282, "load_balance": 0.00048355277976952493, "g_entropy": 1.732432782649994, "tau_bias": 0.6825621128082275, "beta": 0.4854518497983615, "train_val_corr": 1.0} |
| {"t": 38, "ts": 1788123735.339089, "step": 380, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -438.68182373046875, "attn_entropy": 1.634229838848114, "load_balance": 0.0004848124081036076, "g_entropy": 1.7325506806373596, "tau_bias": 0.6825621128082275, "beta": 0.48647210250298184, "train_val_corr": 1.0} |
| {"t": 39, "ts": 1788123739.2814007, "step": 390, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -415.703857421875, "attn_entropy": 1.6223089098930359, "load_balance": 0.00048576516564935446, "g_entropy": 1.7325075268745422, "tau_bias": 0.6825621128082275, "beta": 0.44302606706817943, "train_val_corr": 1.0} |
| {"t": 40, "ts": 1788123743.4704037, "step": 400, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -395.15301513671875, "attn_entropy": 1.6182129383087158, "load_balance": 0.0004849694232689217, "g_entropy": 1.7325542569160461, "tau_bias": 0.6825621128082275, "beta": 0.4548296605547269, "train_val_corr": 0.9999999999999998} |
| {"t": 41, "ts": 1788123757.8612103, "step": 410, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -376.0028076171875, "attn_entropy": 1.6123040914535522, "load_balance": 0.0004876359162153676, "g_entropy": 1.7325718402862549, "tau_bias": 0.6825621128082275, "beta": 0.46758439143498737, "train_val_corr": 1.0} |
| {"t": 42, "ts": 1788123761.9450712, "step": 420, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -356.8490295410156, "attn_entropy": 1.6140645146369934, "load_balance": 0.00048695525038056076, "g_entropy": 1.732567310333252, "tau_bias": 0.6825621128082275, "beta": 0.4756833116213481, "train_val_corr": 0.9999999999999996} |
| {"t": 43, "ts": 1788123766.2373338, "step": 430, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -339.5235900878906, "attn_entropy": 1.6235848665237427, "load_balance": 0.00048557674745097756, "g_entropy": 1.7325628995895386, "tau_bias": 0.6825621128082275, "beta": 0.48355481028556824, "train_val_corr": 1.0} |
| {"t": 44, "ts": 1788123770.2749033, "step": 440, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -322.7313232421875, "attn_entropy": 1.616319477558136, "load_balance": 0.0004849441029364243, "g_entropy": 1.7325714230537415, "tau_bias": 0.6825621128082275, "beta": 0.4850596363345782, "train_val_corr": 0.9999999999999998} |
| {"t": 45, "ts": 1788123775.1663277, "step": 450, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -305.65460205078125, "attn_entropy": 1.6389607787132263, "load_balance": 0.00048514295485801995, "g_entropy": 1.7325530052185059, "tau_bias": 0.6825621128082275, "beta": 0.4898808499177297, "train_val_corr": 0.9999999999999998} |
| {"t": 46, "ts": 1788123779.1740391, "step": 460, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -288.74853515625, "attn_entropy": 1.6214975714683533, "load_balance": 0.00048458375385962427, "g_entropy": 1.7325217723846436, "tau_bias": 0.6825621128082275, "beta": 0.49146919697523117, "train_val_corr": 0.9999999999999996} |
| {"t": 47, "ts": 1788123793.8613942, "step": 470, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -276.99395751953125, "attn_entropy": 1.6191909909248352, "load_balance": 0.0004847631644224748, "g_entropy": 1.7325488924980164, "tau_bias": 0.6825621128082275, "beta": 0.493382287522157, "train_val_corr": 1.0} |
| {"t": 48, "ts": 1788123797.8622608, "step": 480, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -261.74365234375, "attn_entropy": 1.6289239525794983, "load_balance": 0.0004837842716369778, "g_entropy": 1.7325519919395447, "tau_bias": 0.6825621128082275, "beta": 0.49377255017558735, "train_val_corr": 0.9999999999999998} |
| {"t": 49, "ts": 1788123801.8683276, "step": 490, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -249.047607421875, "attn_entropy": 1.6106890439987183, "load_balance": 0.0004877120954915881, "g_entropy": 1.7325176000595093, "tau_bias": 0.6825621128082275, "beta": 0.4470314246912797, "train_val_corr": 1.0} |
| {"t": 50, "ts": 1788123806.5028965, "step": 500, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -236.6402130126953, "attn_entropy": 1.6172384023666382, "load_balance": 0.0004862587811658159, "g_entropy": 1.7325676083564758, "tau_bias": 0.6825621128082275, "beta": 0.4578147915502389, "train_val_corr": 0.9999999999999999} |
| {"t": 51, "ts": 1788123811.0870423, "step": 510, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -224.488525390625, "attn_entropy": 1.609624445438385, "load_balance": 0.00048750193673186004, "g_entropy": 1.7325673699378967, "tau_bias": 0.6825621128082275, "beta": 0.4707949807246526, "train_val_corr": 0.9999999999999999} |
| {"t": 52, "ts": 1788123815.500918, "step": 520, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -213.23350524902344, "attn_entropy": 1.661973476409912, "load_balance": 0.0004813611594727263, "g_entropy": 1.7322928309440613, "tau_bias": 0.6825621128082275, "beta": 0.483093981941541, "train_val_corr": 0.9999999999999999} |
| {"t": 53, "ts": 1788123830.5761607, "step": 530, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -202.34405517578125, "attn_entropy": 1.6178861856460571, "load_balance": 0.00048653301200829446, "g_entropy": 1.7326090335845947, "tau_bias": 0.6825621128082275, "beta": 0.48385921368996304, "train_val_corr": 0.9999999999999997} |
| {"t": 54, "ts": 1788123834.8804953, "step": 540, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -192.86209106445312, "attn_entropy": 1.6338903903961182, "load_balance": 0.00048408732982352376, "g_entropy": 1.7325540781021118, "tau_bias": 0.6825621128082275, "beta": 0.4856316161652406, "train_val_corr": 1.0} |
| {"t": 55, "ts": 1788123839.2321568, "step": 550, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -183.31748962402344, "attn_entropy": 1.6262450814247131, "load_balance": 0.00048507220344617963, "g_entropy": 1.7326082587242126, "tau_bias": 0.6825621128082275, "beta": 0.48865460976958275, "train_val_corr": 0.9999999999999998} |
| {"t": 56, "ts": 1788123843.3646822, "step": 560, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -174.90304565429688, "attn_entropy": 1.6207201480865479, "load_balance": 0.00048611799138598144, "g_entropy": 1.732525885105133, "tau_bias": 0.6825621128082275, "beta": 0.49009504293402034, "train_val_corr": 0.9999999999999998} |
| {"t": 57, "ts": 1788123848.3910506, "step": 570, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -163.22943115234375, "attn_entropy": 1.6162850856781006, "load_balance": 0.0004862867499468848, "g_entropy": 1.7325520515441895, "tau_bias": 0.6825621128082275, "beta": 0.4907294400036335, "train_val_corr": 1.0} |
| {"t": 58, "ts": 1788123879.3307357, "step": 580, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -111.07676696777344, "attn_entropy": 2.1184772491455077, "load_balance": 0.0004762514668982476, "g_entropy": 2.1600786209106446, "tau_bias": 0.6825621128082275, "beta": 0.49381576602657634, "train_val_corr": 0.9999999999999998} |
| {"t": 59, "ts": 1788123884.635483, "step": 590, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -151.12237548828125, "attn_entropy": 2.1231662750244142, "load_balance": 0.0004755671776365489, "g_entropy": 2.1602622985839846, "tau_bias": 0.6825621128082275, "beta": 0.48549926777680713, "train_val_corr": 1.0} |
| {"t": 60, "ts": 1788123889.852645, "step": 600, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -143.07608032226562, "attn_entropy": 2.117449188232422, "load_balance": 0.00047659442643634977, "g_entropy": 2.1601351737976073, "tau_bias": 0.6825621128082275, "beta": 0.49075982471307117, "train_val_corr": 0.9999999999999997} |
| {"t": 61, "ts": 1788123894.8618371, "step": 610, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -137.51858520507812, "attn_entropy": 2.1234819889068604, "load_balance": 0.0004754892841447145, "g_entropy": 2.1601068019866942, "tau_bias": 0.6825621128082275, "beta": 0.4889952205121517, "train_val_corr": 0.9999999999999998} |
| {"t": 62, "ts": 1788123899.8509989, "step": 620, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -129.72665405273438, "attn_entropy": 2.111216688156128, "load_balance": 0.00047790620010346174, "g_entropy": 2.160065460205078, "tau_bias": 0.6825621128082275, "beta": 0.4917351019879182, "train_val_corr": 1.0} |
| {"t": 63, "ts": 1788123904.84527, "step": 630, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -122.90545654296875, "attn_entropy": 2.1211729049682617, "load_balance": 0.00047595406067557633, "g_entropy": 2.1600366592407227, "tau_bias": 0.6825621128082275, "beta": 0.4917837778727214, "train_val_corr": 1.0} |
| {"t": 64, "ts": 1788123923.7466676, "step": 640, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -116.28569793701172, "attn_entropy": 2.1344026565551757, "load_balance": 0.00047427641111426057, "g_entropy": 2.1597102165222166, "tau_bias": 0.6825621128082275, "beta": 0.4928770090142886, "train_val_corr": 1.0} |
| {"t": 65, "ts": 1788123928.7749007, "step": 650, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -111.59024047851562, "attn_entropy": 2.1197393894195558, "load_balance": 0.0004768472339492291, "g_entropy": 2.160223436355591, "tau_bias": 0.6825621128082275, "beta": 0.4938940132657687, "train_val_corr": 0.9999999999999998} |
| {"t": 66, "ts": 1788123933.8727283, "step": 660, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -106.44703674316406, "attn_entropy": 2.1218718528747558, "load_balance": 0.00047538689104840157, "g_entropy": 2.1601235389709474, "tau_bias": 0.6825621128082275, "beta": 0.4941258355975151, "train_val_corr": 1.0} |
| {"t": 67, "ts": 1788123938.8430274, "step": 670, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -99.95701599121094, "attn_entropy": 2.111749458312988, "load_balance": 0.00047750237281434237, "g_entropy": 2.1598252296447753, "tau_bias": 0.6825621128082275, "beta": 0.4939212587972482, "train_val_corr": 0.9999999999999998} |
| {"t": 68, "ts": 1788123944.059375, "step": 680, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -95.36344146728516, "attn_entropy": 2.122874212265015, "load_balance": 0.00047514020116068423, "g_entropy": 2.160086727142334, "tau_bias": 0.6825621128082275, "beta": 0.48150476564963657, "train_val_corr": 0.9999999999999998} |
| {"t": 69, "ts": 1788123949.5781548, "step": 690, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -88.9753646850586, "attn_entropy": 2.116086721420288, "load_balance": 0.0004772925458382815, "g_entropy": 2.1600509166717528, "tau_bias": 0.6825621128082275, "beta": 0.4877573624253273, "train_val_corr": 0.9999999999999998} |
| {"t": 70, "ts": 1788123970.8597703, "step": 700, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -86.511962890625, "attn_entropy": 2.118991661071777, "load_balance": 0.00047580678365193306, "g_entropy": 2.1600395679473876, "tau_bias": 0.6825621128082275, "beta": 0.4896887093782425, "train_val_corr": 1.0} |
| {"t": 71, "ts": 1788123976.432983, "step": 710, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -80.38578033447266, "attn_entropy": 2.1257046699523925, "load_balance": 0.0004749986866954714, "g_entropy": 2.160198783874512, "tau_bias": 0.6825621128082275, "beta": 0.4914555909732978, "train_val_corr": 1.0} |
| {"t": 72, "ts": 1788123982.2943773, "step": 720, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -78.02769470214844, "attn_entropy": 2.1197518348693847, "load_balance": 0.0004753768676891923, "g_entropy": 2.160133647918701, "tau_bias": 0.6825621128082275, "beta": 0.4940040794511636, "train_val_corr": 0.9999999999999997} |
| {"t": 73, "ts": 1788123987.4744911, "step": 730, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -74.27789306640625, "attn_entropy": 2.1116429805755614, "load_balance": 0.0004776368325110525, "g_entropy": 2.1602352619171143, "tau_bias": 0.6825621128082275, "beta": 0.4950043161710103, "train_val_corr": 0.9999999999999998} |
| {"t": 74, "ts": 1788123992.6829665, "step": 740, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -70.31035614013672, "attn_entropy": 2.1278138160705566, "load_balance": 0.0004743919183965772, "g_entropy": 2.16005859375, "tau_bias": 0.6825621128082275, "beta": 0.4960860113302867, "train_val_corr": 1.0} |
| {"t": 75, "ts": 1788123997.891874, "step": 750, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -66.43888854980469, "attn_entropy": 2.120775556564331, "load_balance": 0.0004753792891278863, "g_entropy": 2.1599781990051268, "tau_bias": 0.6825621128082275, "beta": 0.49668751532832783, "train_val_corr": 0.9999999999999997} |
| {"t": 76, "ts": 1788124018.3669877, "step": 760, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -63.807960510253906, "attn_entropy": 2.121780204772949, "load_balance": 0.0004755284811835736, "g_entropy": 2.1597872257232664, "tau_bias": 0.6825621128082275, "beta": 0.497334536164999, "train_val_corr": 1.0} |
| {"t": 77, "ts": 1788124023.6722844, "step": 770, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -59.21980667114258, "attn_entropy": 2.121289110183716, "load_balance": 0.0004752886132337153, "g_entropy": 2.1600587368011475, "tau_bias": 0.6825621128082275, "beta": 0.49746089552839595, "train_val_corr": 1.0} |
| {"t": 78, "ts": 1788124028.7861192, "step": 780, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -56.09053421020508, "attn_entropy": 2.122826671600342, "load_balance": 0.00047556330682709815, "g_entropy": 2.160054636001587, "tau_bias": 0.6825621128082275, "beta": 0.4778650129834811, "train_val_corr": 1.0} |
| {"t": 79, "ts": 1788124034.057653, "step": 790, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -53.929420471191406, "attn_entropy": 2.1165709495544434, "load_balance": 0.00047661769785918296, "g_entropy": 2.1600625991821287, "tau_bias": 0.6825621128082275, "beta": 0.4889161003132661, "train_val_corr": 1.0} |
| {"t": 80, "ts": 1788124039.5571744, "step": 800, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -51.37810516357422, "attn_entropy": 2.119606876373291, "load_balance": 0.0004755357454996556, "g_entropy": 2.159994888305664, "tau_bias": 0.6825621128082275, "beta": 0.4933689050376415, "train_val_corr": 0.9999999999999997} |
| {"t": 81, "ts": 1788124044.88367, "step": 810, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -49.208709716796875, "attn_entropy": 2.1228514194488524, "load_balance": 0.0004761478921864182, "g_entropy": 2.1592533111572267, "tau_bias": 0.6825621128082275, "beta": 0.49477803086241084, "train_val_corr": 1.0} |
| {"t": 0, "ts": 1788124261.0583944, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 12832.8828125, "attn_entropy": 1.1551029682159424, "load_balance": 0.0003258686823149522, "g_entropy": 1.1549687385559082, "tau_bias": 0.6566849946975708, "beta": 0.10835317894816399, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788124265.0690198, "step": 10, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 7.0712876549805515e-06, "advantage": -587.4507446289062, "attn_entropy": 1.110655387242635, "load_balance": 0.00032854297508796054, "g_entropy": 1.1549643675486247, "tau_bias": 0.6658554673194885, "beta": 0.22102038655430079, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788124269.177124, "step": 20, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.004775963723659515, "advantage": -573.068115234375, "attn_entropy": 0.9017306168874105, "load_balance": 0.0003327992744743824, "g_entropy": 1.154973030090332, "tau_bias": 0.6756224036216736, "beta": 0.2527519352734089, "train_val_corr": 0.0} |
| {"t": 3, "ts": 1788124273.2619083, "step": 30, "action": "PGO_UPDATE", "entropy_pi": 0.6780548095703125, "advantage": -546.783935546875, "attn_entropy": 0.7481436729431152, "load_balance": 0.0003334786354874571, "g_entropy": 1.1549304326375325, "tau_bias": 0.67994624376297, "beta": 0.2310744859278202, "train_val_corr": 0.0} |
| {"t": 4, "ts": 1788124277.361251, "step": 40, "action": "PGO_UPDATE", "entropy_pi": 0.6617212295532227, "advantage": -517.9473266601562, "attn_entropy": 0.6541844209035238, "load_balance": 0.00032881022586176795, "g_entropy": 1.1549675464630127, "tau_bias": 0.6816269159317017, "beta": 0.27597904826203984, "train_val_corr": 0.0} |
| {"t": 5, "ts": 1788124281.679165, "step": 50, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.10877113789319992, "advantage": -494.4080505371094, "attn_entropy": 0.6063317060470581, "load_balance": 0.00032786567074557144, "g_entropy": 1.1549241542816162, "tau_bias": 0.6823055148124695, "beta": 0.29740134999156, "train_val_corr": 0.0} |
| {"t": 6, "ts": 1788124292.6681461, "step": 60, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.14552953839302063, "advantage": -470.0270080566406, "attn_entropy": 0.6557672023773193, "load_balance": 0.0003345807393391927, "g_entropy": 1.1549659570058186, "tau_bias": 0.6827506422996521, "beta": 0.2810777711371581, "train_val_corr": 0.0} |
| {"t": 7, "ts": 1788124296.674158, "step": 70, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.6803812980651855, "advantage": -446.7344970703125, "attn_entropy": 0.7486160596211752, "load_balance": 0.0003319638005147378, "g_entropy": 1.1549734274546306, "tau_bias": 0.6825464367866516, "beta": 0.28341985990603763, "train_val_corr": 0.0} |
| {"t": 8, "ts": 1788124300.7660959, "step": 80, "action": "PGO_UPDATE", "entropy_pi": 0.3729284405708313, "advantage": -425.8521423339844, "attn_entropy": 0.6764365832010905, "load_balance": 0.0003247920928212504, "g_entropy": 1.154962380727132, "tau_bias": 0.6821361184120178, "beta": 0.26636930368840694, "train_val_corr": 0.0} |
| {"t": 9, "ts": 1788124304.8625236, "step": 90, "action": "PGO_UPDATE", "entropy_pi": 0.5420128107070923, "advantage": -406.2437438964844, "attn_entropy": 0.6970227559407552, "load_balance": 0.0003280730064337452, "g_entropy": 1.154942512512207, "tau_bias": 0.6825621128082275, "beta": 0.31226665154099464, "train_val_corr": 0.0} |
| {"t": 10, "ts": 1788124309.033539, "step": 100, "action": "ATTN_META_ONLY", "entropy_pi": 0.5260592103004456, "advantage": -378.76788330078125, "attn_entropy": 0.7195657889048258, "load_balance": 0.00033718335907906294, "g_entropy": 1.1549355189005535, "tau_bias": 0.6858869791030884, "beta": 0.26681934855878353, "train_val_corr": 0.0} |
| {"t": 11, "ts": 1788124312.069722, "step": 110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723338423067617e-07, "advantage": -347.23614501953125, "attn_entropy": 0.5069400469462076, "load_balance": 0.00035199266858398914, "g_entropy": 1.1549235184987385, "tau_bias": 0.6858869791030884, "beta": 0.24618053498367468, "train_val_corr": 0.0} |
| {"t": 12, "ts": 1788124322.6720574, "step": 120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723419424939493e-07, "advantage": -337.877197265625, "attn_entropy": 0.5240544478098551, "load_balance": 0.0003486786736175418, "g_entropy": 1.1549527645111084, "tau_bias": 0.6858869791030884, "beta": 0.28050902113318443, "train_val_corr": 0.0} |
| {"t": 13, "ts": 1788124325.6711376, "step": 130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072352032200797e-07, "advantage": -322.0851135253906, "attn_entropy": 0.5410324335098267, "load_balance": 0.00034934406479199726, "g_entropy": 1.1549327373504639, "tau_bias": 0.6858869791030884, "beta": 0.2902587528030078, "train_val_corr": 0.0} |
| {"t": 14, "ts": 1788124328.6726863, "step": 140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072378038064926e-07, "advantage": -308.3538818359375, "attn_entropy": 0.5460982720057169, "load_balance": 0.00034997996408492327, "g_entropy": 1.154950777689616, "tau_bias": 0.6858869791030884, "beta": 0.3038359470665455, "train_val_corr": 0.0} |
| {"t": 15, "ts": 1788124331.6810632, "step": 150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0724394289572956e-07, "advantage": -297.1568603515625, "attn_entropy": 0.5797381003697714, "load_balance": 0.0003493430558592081, "g_entropy": 1.154931863149007, "tau_bias": 0.6858869791030884, "beta": 0.2859800203392903, "train_val_corr": 0.0} |
| {"t": 16, "ts": 1788124334.7721088, "step": 160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072537910180472e-07, "advantage": -276.9546203613281, "attn_entropy": 0.5815096696217855, "load_balance": 0.000354263271826009, "g_entropy": 1.154825766881307, "tau_bias": 0.6858869791030884, "beta": 0.27024551046391326, "train_val_corr": 0.0} |
| {"t": 17, "ts": 1788124337.8681023, "step": 170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072878260150901e-07, "advantage": -269.6792297363281, "attn_entropy": 0.6096884806950887, "load_balance": 0.00034988120508690673, "g_entropy": 1.154912789662679, "tau_bias": 0.6858869791030884, "beta": 0.3069314348200957, "train_val_corr": 0.0} |
| {"t": 18, "ts": 1788124348.0808125, "step": 180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0741082096265018e-07, "advantage": -261.3671569824219, "attn_entropy": 0.641185482343038, "load_balance": 0.00035004694170008105, "g_entropy": 1.1548597017923992, "tau_bias": 0.6858869791030884, "beta": 0.3435237966477871, "train_val_corr": 0.0} |
| {"t": 19, "ts": 1788124351.4976082, "step": 190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.082007597437041e-07, "advantage": -245.57412719726562, "attn_entropy": 0.6446436643600464, "load_balance": 0.00034565734677016735, "g_entropy": 1.1549798647562664, "tau_bias": 0.6858869791030884, "beta": 0.3295938968658447, "train_val_corr": 1.0} |
| {"t": 20, "ts": 1788124354.7464316, "step": 200, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.216125238874156e-07, "advantage": -237.50059509277344, "attn_entropy": 0.6379165252049764, "load_balance": 0.0003462907625362277, "g_entropy": 1.1549704869588215, "tau_bias": 0.6858869791030884, "beta": 0.3172742898265521, "train_val_corr": 1.0} |
| {"t": 21, "ts": 1788124357.9831214, "step": 210, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.6505253458708466e-07, "advantage": -225.76217651367188, "attn_entropy": 0.6465337673823038, "load_balance": 0.00034807727206498384, "g_entropy": 1.154892126719157, "tau_bias": 0.6858869791030884, "beta": 0.3506663416822751, "train_val_corr": 1.0} |
| {"t": 22, "ts": 1788124361.2698205, "step": 220, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.1267188660422107e-07, "advantage": -214.3321075439453, "attn_entropy": 0.6569200754165649, "load_balance": 0.00034462854576607543, "g_entropy": 1.1549503008524578, "tau_bias": 0.6858869791030884, "beta": 0.3367995197574298, "train_val_corr": 1.0} |
| {"t": 23, "ts": 1788124364.5657907, "step": 230, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.3155362189063453e-07, "advantage": -203.81515502929688, "attn_entropy": 0.6984380086263021, "load_balance": 0.0003446880728006363, "g_entropy": 1.1549599170684814, "tau_bias": 0.6858869791030884, "beta": 0.340495773901542, "train_val_corr": 1.0} |
| {"t": 24, "ts": 1788124374.473091, "step": 240, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.2125697657647834e-07, "advantage": -194.96424865722656, "attn_entropy": 0.7062484423319498, "load_balance": 0.000344537819425265, "g_entropy": 1.1549547513326008, "tau_bias": 0.6858869791030884, "beta": 0.3203882115582625, "train_val_corr": 1.0} |
| {"t": 25, "ts": 1788124377.4718754, "step": 250, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.0072101253608707e-07, "advantage": -186.06558227539062, "attn_entropy": 0.764882485071818, "load_balance": 0.00034262895739326876, "g_entropy": 1.1549517313639324, "tau_bias": 0.6858869791030884, "beta": 0.3407290118436019, "train_val_corr": 0.9999999999999999} |
| {"t": 26, "ts": 1788124380.4652936, "step": 260, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.7335562435837346e-07, "advantage": -176.5679931640625, "attn_entropy": 0.6980056762695312, "load_balance": 0.00034412458383788663, "g_entropy": 1.154947280883789, "tau_bias": 0.6858869791030884, "beta": 0.3528863949080308, "train_val_corr": 0.9999999999999999} |
| {"t": 27, "ts": 1788124383.7666702, "step": 270, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.57418520277497e-07, "advantage": -170.07618713378906, "attn_entropy": 0.7379186153411865, "load_balance": 0.0003463883961861332, "g_entropy": 1.1548749605814617, "tau_bias": 0.6858869791030884, "beta": 0.3664669804275036, "train_val_corr": 1.0} |
| {"t": 28, "ts": 1788124386.7638974, "step": 280, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.4147925614670385e-07, "advantage": -160.9144744873047, "attn_entropy": 0.6977364222208658, "load_balance": 0.000344944108898441, "g_entropy": 1.154946247736613, "tau_bias": 0.6858869791030884, "beta": 0.35494713112711906, "train_val_corr": 1.0} |
| {"t": 29, "ts": 1788124408.265175, "step": 290, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.1367098668179096e-07, "advantage": 9721.4326171875, "attn_entropy": 1.5881285071372986, "load_balance": 0.0004846553347306326, "g_entropy": 1.7325870394706726, "tau_bias": 0.6858869791030884, "beta": 0.4160541159411271, "train_val_corr": 1.0} |
| {"t": 30, "ts": 1788124412.2355988, "step": 300, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -622.3155517578125, "attn_entropy": 1.6524324417114258, "load_balance": 0.0004860776534769684, "g_entropy": 1.732592761516571, "tau_bias": 0.6858869791030884, "beta": 0.42998138070106506, "train_val_corr": 1.0} |
| {"t": 31, "ts": 1788124416.7361815, "step": 310, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -618.5685424804688, "attn_entropy": 1.6508495807647705, "load_balance": 0.00048290980339515954, "g_entropy": 1.7324458360671997, "tau_bias": 0.6858869791030884, "beta": 0.4564717424412568, "train_val_corr": 1.0} |
| {"t": 32, "ts": 1788124420.7404535, "step": 320, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -594.2369384765625, "attn_entropy": 1.6447937488555908, "load_balance": 0.0004871788405580446, "g_entropy": 1.7325801849365234, "tau_bias": 0.6858869791030884, "beta": 0.44692249471942586, "train_val_corr": 1.0} |
| {"t": 33, "ts": 1788124424.7503288, "step": 330, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -568.0096435546875, "attn_entropy": 1.6505539417266846, "load_balance": 0.0004870098637184128, "g_entropy": 1.7325944304466248, "tau_bias": 0.6858869791030884, "beta": 0.45635670175155, "train_val_corr": 1.0} |
| {"t": 34, "ts": 1788124429.1460357, "step": 340, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -540.8575439453125, "attn_entropy": 1.6664411425590515, "load_balance": 0.0004860205081058666, "g_entropy": 1.7325485348701477, "tau_bias": 0.6858869791030884, "beta": 0.4761435315012932, "train_val_corr": 0.9999999999999998} |
| {"t": 35, "ts": 1788124443.4776602, "step": 350, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -514.1961669921875, "attn_entropy": 1.6660980582237244, "load_balance": 0.00048644450725987554, "g_entropy": 1.7325881719589233, "tau_bias": 0.6858869791030884, "beta": 0.4797222167253494, "train_val_corr": 1.0} |
| {"t": 36, "ts": 1788124447.7610533, "step": 360, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -488.18316650390625, "attn_entropy": 1.6666739583015442, "load_balance": 0.0004871394485235214, "g_entropy": 1.7326167225837708, "tau_bias": 0.6858869791030884, "beta": 0.4833271652460098, "train_val_corr": 1.0} |
| {"t": 37, "ts": 1788124451.7575557, "step": 370, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -464.3638916015625, "attn_entropy": 1.6748652458190918, "load_balance": 0.0004841729678446427, "g_entropy": 1.7324298024177551, "tau_bias": 0.6858869791030884, "beta": 0.48597971101601917, "train_val_corr": 1.0} |
| {"t": 38, "ts": 1788124455.7522204, "step": 380, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -441.2074890136719, "attn_entropy": 1.6739585995674133, "load_balance": 0.00048532993241678923, "g_entropy": 1.732548475265503, "tau_bias": 0.6858869791030884, "beta": 0.48656316349903744, "train_val_corr": 0.9999999999999998} |
| {"t": 39, "ts": 1788124459.7512102, "step": 390, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -419.1637268066406, "attn_entropy": 1.6731659770011902, "load_balance": 0.00048614856495987624, "g_entropy": 1.732504963874817, "tau_bias": 0.6858869791030884, "beta": 0.48829614867766696, "train_val_corr": 0.9999999999999998} |
| {"t": 40, "ts": 1788124463.767644, "step": 400, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -398.2093505859375, "attn_entropy": 1.6745381951332092, "load_balance": 0.00048564080498181283, "g_entropy": 1.7325521111488342, "tau_bias": 0.6858869791030884, "beta": 0.48803526908159256, "train_val_corr": 0.9999999999999998} |
| {"t": 41, "ts": 1788124478.0562284, "step": 410, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -378.1302795410156, "attn_entropy": 1.668882429599762, "load_balance": 0.0004875193117186427, "g_entropy": 1.7325696349143982, "tau_bias": 0.6858869791030884, "beta": 0.4878004727264245, "train_val_corr": 0.9999999999999998} |
| {"t": 42, "ts": 1788124482.2874594, "step": 420, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -359.2438049316406, "attn_entropy": 1.6648924350738525, "load_balance": 0.0004869808763032779, "g_entropy": 1.7325652241706848, "tau_bias": 0.6858869791030884, "beta": 0.48842616751790047, "train_val_corr": 1.0} |
| {"t": 43, "ts": 1788124486.5320423, "step": 430, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -341.5235595703125, "attn_entropy": 1.6719710230827332, "load_balance": 0.0004859988985117525, "g_entropy": 1.7325608730316162, "tau_bias": 0.6858869791030884, "beta": 0.4885176594058673, "train_val_corr": 0.9999999999999996} |
| {"t": 44, "ts": 1788124490.8984883, "step": 440, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -324.4749450683594, "attn_entropy": 1.6790746450424194, "load_balance": 0.00048574653919786215, "g_entropy": 1.7325693368911743, "tau_bias": 0.6858869791030884, "beta": 0.48793965702255565, "train_val_corr": 1.0} |
| {"t": 45, "ts": 1788124495.3933046, "step": 450, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -308.1043701171875, "attn_entropy": 1.6739708185195923, "load_balance": 0.0004855213046539575, "g_entropy": 1.732550859451294, "tau_bias": 0.6858869791030884, "beta": 0.4891777274509271, "train_val_corr": 1.0} |
| {"t": 46, "ts": 1788124499.683269, "step": 460, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -291.8003234863281, "attn_entropy": 1.6772143244743347, "load_balance": 0.000485378346638754, "g_entropy": 1.7325194478034973, "tau_bias": 0.6858869791030884, "beta": 0.488197839508454, "train_val_corr": 1.0} |
| {"t": 47, "ts": 1788124514.7801425, "step": 470, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -278.1778869628906, "attn_entropy": 1.680259644985199, "load_balance": 0.0004856172017753124, "g_entropy": 1.732546627521515, "tau_bias": 0.6858869791030884, "beta": 0.4892190061509609, "train_val_corr": 1.0} |
| {"t": 48, "ts": 1788124518.7393658, "step": 480, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -263.9754333496094, "attn_entropy": 1.6825090646743774, "load_balance": 0.00048491898633074015, "g_entropy": 1.732549786567688, "tau_bias": 0.6858869791030884, "beta": 0.4888780216375987, "train_val_corr": 1.0} |
| {"t": 49, "ts": 1788124522.7514534, "step": 490, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -201.7094268798828, "attn_entropy": 1.6667007207870483, "load_balance": 0.00048756730393506587, "g_entropy": 1.732515275478363, "tau_bias": 0.6858869791030884, "beta": 0.445443303634723, "train_val_corr": 0.9999999999999999} |
| {"t": 50, "ts": 1788124526.7734468, "step": 500, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -204.8629608154297, "attn_entropy": 1.7261027693748474, "load_balance": 0.00048780624638311565, "g_entropy": 1.732565462589264, "tau_bias": 0.6858869791030884, "beta": 0.4694125254948934, "train_val_corr": 0.9999999999999999} |
| {"t": 51, "ts": 1788124530.9698863, "step": 510, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -217.81942749023438, "attn_entropy": 1.7226781249046326, "load_balance": 0.0004880144988419488, "g_entropy": 1.7325652241706848, "tau_bias": 0.6858869791030884, "beta": 0.4661316288014253, "train_val_corr": 1.0} |
| {"t": 52, "ts": 1788124535.163077, "step": 520, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -214.9300537109375, "attn_entropy": 1.7241438031196594, "load_balance": 0.0004859988985117525, "g_entropy": 1.7322887182235718, "tau_bias": 0.6858869791030884, "beta": 0.4712101047237714, "train_val_corr": 1.0} |
| {"t": 53, "ts": 1788124549.9770277, "step": 530, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -206.92893981933594, "attn_entropy": 1.7259352803230286, "load_balance": 0.00048784067621454597, "g_entropy": 1.7326074242591858, "tau_bias": 0.6858869791030884, "beta": 0.46479757502675056, "train_val_corr": 1.0} |
| {"t": 54, "ts": 1788124554.4375312, "step": 540, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -197.0290069580078, "attn_entropy": 1.727387011051178, "load_balance": 0.000487359196995385, "g_entropy": 1.7325519323349, "tau_bias": 0.6858869791030884, "beta": 0.4669773665567239, "train_val_corr": 0.9999999999999999} |
| {"t": 55, "ts": 1788124558.9349935, "step": 550, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -188.17955017089844, "attn_entropy": 1.7268622517585754, "load_balance": 0.0004875415761489421, "g_entropy": 1.7326063513755798, "tau_bias": 0.6858869791030884, "beta": 0.47070271770159405, "train_val_corr": 0.9999999999999999} |
| {"t": 56, "ts": 1788124563.4661057, "step": 560, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -179.3461151123047, "attn_entropy": 1.7277968525886536, "load_balance": 0.0004878996987827122, "g_entropy": 1.7325236797332764, "tau_bias": 0.6858869791030884, "beta": 0.47768790647387505, "train_val_corr": 0.9999999999999998} |
| {"t": 57, "ts": 1788124567.97874, "step": 570, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -168.7914276123047, "attn_entropy": 1.726238191127777, "load_balance": 0.00048783395322971046, "g_entropy": 1.7325498461723328, "tau_bias": 0.6858869791030884, "beta": 0.4670213535428047, "train_val_corr": 1.0} |
| {"t": 58, "ts": 1788124583.9567583, "step": 580, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -160.73892211914062, "attn_entropy": 1.722171664237976, "load_balance": 0.00048721491475589573, "g_entropy": 1.7325059175491333, "tau_bias": 0.6858869791030884, "beta": 0.47173158824443817, "train_val_corr": 0.9999999999999999} |
| {"t": 59, "ts": 1788124588.2578893, "step": 590, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -153.03314208984375, "attn_entropy": 1.7278668880462646, "load_balance": 0.00048795279872138053, "g_entropy": 1.7325857877731323, "tau_bias": 0.6858869791030884, "beta": 0.47939227893948555, "train_val_corr": 1.0} |
| {"t": 60, "ts": 1788124592.7289279, "step": 600, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -144.7894744873047, "attn_entropy": 1.7301654815673828, "load_balance": 0.0004877929750364274, "g_entropy": 1.732554018497467, "tau_bias": 0.6858869791030884, "beta": 0.4819050741692384, "train_val_corr": 0.9999999999999999} |
| {"t": 61, "ts": 1788124597.1341097, "step": 610, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -138.13232421875, "attn_entropy": 1.7228264212608337, "load_balance": 0.000487792378407903, "g_entropy": 1.7325281500816345, "tau_bias": 0.6858869791030884, "beta": 0.4852367180089156, "train_val_corr": 1.0} |
| {"t": 62, "ts": 1788124601.5681095, "step": 620, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -131.56573486328125, "attn_entropy": 1.7273832559585571, "load_balance": 0.00048770359717309475, "g_entropy": 1.7325885891914368, "tau_bias": 0.6858869791030884, "beta": 0.48892194281021756, "train_val_corr": 1.0} |
| {"t": 63, "ts": 1788124606.2712662, "step": 630, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -125.17782592773438, "attn_entropy": 1.7258654832839966, "load_balance": 0.0004883184155914932, "g_entropy": 1.7325623035430908, "tau_bias": 0.6858869791030884, "beta": 0.48849857101837796, "train_val_corr": 1.0} |
| {"t": 64, "ts": 1788124622.3362722, "step": 640, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -118.76419830322266, "attn_entropy": 1.7280497550964355, "load_balance": 0.000487808691104874, "g_entropy": 1.7325714826583862, "tau_bias": 0.6858869791030884, "beta": 0.48979564135273296, "train_val_corr": 0.9999999999999998} |
| {"t": 65, "ts": 1788124626.8444343, "step": 650, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -112.83757781982422, "attn_entropy": 1.7265797853469849, "load_balance": 0.0004883061192231253, "g_entropy": 1.7325857281684875, "tau_bias": 0.6858869791030884, "beta": 0.4906217393775781, "train_val_corr": 0.9999999999999998} |
| {"t": 66, "ts": 1788124631.298164, "step": 660, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -107.02066040039062, "attn_entropy": 1.7257546782493591, "load_balance": 0.00048807632992975414, "g_entropy": 1.732579231262207, "tau_bias": 0.6858869791030884, "beta": 0.4908444707592328, "train_val_corr": 1.0} |
| {"t": 67, "ts": 1788124635.6814637, "step": 670, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -100.48995208740234, "attn_entropy": 1.7264513969421387, "load_balance": 0.0004883151414105669, "g_entropy": 1.7325307130813599, "tau_bias": 0.6858869791030884, "beta": 0.4885313796500365, "train_val_corr": 0.9999999999999999} |
| {"t": 68, "ts": 1788124639.939519, "step": 680, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -96.47933197021484, "attn_entropy": 1.7271618843078613, "load_balance": 0.0004875097656622529, "g_entropy": 1.7325624823570251, "tau_bias": 0.6858869791030884, "beta": 0.4897103024025758, "train_val_corr": 1.0} |
| {"t": 69, "ts": 1788124644.094855, "step": 690, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -52.32509231567383, "attn_entropy": 1.728750467300415, "load_balance": 0.0004878523322986439, "g_entropy": 1.732599675655365, "tau_bias": 0.6858869791030884, "beta": 0.4500890498359998, "train_val_corr": 1.0} |
| {"t": 70, "ts": 1788124660.002825, "step": 700, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -70.06919860839844, "attn_entropy": 1.7253996133804321, "load_balance": 0.0004894861776847392, "g_entropy": 1.7325873374938965, "tau_bias": 0.6858869791030884, "beta": 0.46240758274992305, "train_val_corr": 1.0} |
| {"t": 71, "ts": 1788124664.5324025, "step": 710, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -75.89804077148438, "attn_entropy": 1.7204785346984863, "load_balance": 0.0004905200912617147, "g_entropy": 1.7325413823127747, "tau_bias": 0.6858869791030884, "beta": 0.4587966079513232, "train_val_corr": 0.9999999999999998} |
| {"t": 72, "ts": 1788124669.1399813, "step": 720, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -77.02721405029297, "attn_entropy": 1.7173577547073364, "load_balance": 0.0004909006238449365, "g_entropy": 1.7325013875961304, "tau_bias": 0.6858869791030884, "beta": 0.47556104759375256, "train_val_corr": 0.9999999999999997} |
| {"t": 73, "ts": 1788124673.3904102, "step": 730, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -77.15686798095703, "attn_entropy": 1.715619683265686, "load_balance": 0.0004903437220491469, "g_entropy": 1.7325624823570251, "tau_bias": 0.6858869791030884, "beta": 0.4607866282264392, "train_val_corr": 1.0} |
| {"t": 74, "ts": 1788124677.782983, "step": 740, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -70.80046081542969, "attn_entropy": 1.7127142548561096, "load_balance": 0.0004901515203528106, "g_entropy": 1.7325676083564758, "tau_bias": 0.6858869791030884, "beta": 0.46919166420896846, "train_val_corr": 1.0} |
| {"t": 75, "ts": 1788124682.5026548, "step": 750, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -69.43529510498047, "attn_entropy": 1.7052264213562012, "load_balance": 0.0004906664835289121, "g_entropy": 1.7325361967086792, "tau_bias": 0.6858869791030884, "beta": 0.4794088912506898, "train_val_corr": 1.0} |
| {"t": 76, "ts": 1788124699.263207, "step": 760, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -65.5951156616211, "attn_entropy": 1.7099837064743042, "load_balance": 0.000491680926643312, "g_entropy": 1.7325149774551392, "tau_bias": 0.6858869791030884, "beta": 0.48348159715533257, "train_val_corr": 1.0} |
| {"t": 77, "ts": 1788124703.8498473, "step": 770, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -62.98261642456055, "attn_entropy": 1.707980453968048, "load_balance": 0.0004913604352623224, "g_entropy": 1.732504665851593, "tau_bias": 0.6858869791030884, "beta": 0.488824753711621, "train_val_corr": 1.0} |
| {"t": 78, "ts": 1788124708.4487479, "step": 780, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -58.77700424194336, "attn_entropy": 1.7135578393936157, "load_balance": 0.0004905886889901012, "g_entropy": 1.7325653433799744, "tau_bias": 0.6858869791030884, "beta": 0.48786957934498787, "train_val_corr": 0.9999999999999997} |
| {"t": 79, "ts": 1788124713.0548816, "step": 790, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -56.00843048095703, "attn_entropy": 1.7057597041130066, "load_balance": 0.0004913528973702341, "g_entropy": 1.7325591444969177, "tau_bias": 0.6858869791030884, "beta": 0.4898183469971021, "train_val_corr": 1.0} |
| {"t": 80, "ts": 1788124717.6321862, "step": 800, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -49.8045654296875, "attn_entropy": 1.7181665897369385, "load_balance": 0.0004901461361441761, "g_entropy": 1.7325730919837952, "tau_bias": 0.6858869791030884, "beta": 0.4891879769663016, "train_val_corr": 1.0} |
| {"t": 81, "ts": 1788124722.0736988, "step": 810, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -50.467838287353516, "attn_entropy": 1.7106667757034302, "load_balance": 0.0004903259687125683, "g_entropy": 1.732572853565216, "tau_bias": 0.6858869791030884, "beta": 0.49094803755482036, "train_val_corr": 1.0} |
| {"t": 82, "ts": 1788124738.8322847, "step": 820, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -48.986488342285156, "attn_entropy": 1.7152542471885681, "load_balance": 0.000490957812871784, "g_entropy": 1.7325078248977661, "tau_bias": 0.6858869791030884, "beta": 0.4922955073416233, "train_val_corr": 0.9999999999999998} |
| {"t": 83, "ts": 1788124743.0434933, "step": 830, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -45.910030364990234, "attn_entropy": 1.7147006392478943, "load_balance": 0.0004909200069960207, "g_entropy": 1.732499897480011, "tau_bias": 0.6858869791030884, "beta": 0.4920770426591237, "train_val_corr": 0.9999999999999998} |
| {"t": 84, "ts": 1788124747.2724493, "step": 840, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -44.35751724243164, "attn_entropy": 1.7196937799453735, "load_balance": 0.0004899143823422492, "g_entropy": 1.7325312495231628, "tau_bias": 0.6858869791030884, "beta": 0.49280914291739464, "train_val_corr": 0.9999999999999998} |
| {"t": 85, "ts": 1788124751.6386695, "step": 850, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -41.103729248046875, "attn_entropy": 1.708608329296112, "load_balance": 0.0004914606979582459, "g_entropy": 1.732549786567688, "tau_bias": 0.6858869791030884, "beta": 0.49208399653434753, "train_val_corr": 1.0} |
| {"t": 86, "ts": 1788124755.9961329, "step": 860, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -39.97043991088867, "attn_entropy": 1.7122191786766052, "load_balance": 0.0004906736721750349, "g_entropy": 1.7325857877731323, "tau_bias": 0.6858869791030884, "beta": 0.49308499818046886, "train_val_corr": 1.0} |
| {"t": 87, "ts": 1788124786.4678416, "step": 870, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 25.681344985961914, "attn_entropy": 2.1519813537597656, "load_balance": 0.00047892497386783364, "g_entropy": 2.160075378417969, "tau_bias": 0.6858869791030884, "beta": 0.49226335684458417, "train_val_corr": 1.0} |
| {"t": 88, "ts": 1788124791.4566252, "step": 880, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -38.05148696899414, "attn_entropy": 2.154744863510132, "load_balance": 0.00047878685290925205, "g_entropy": 2.160260248184204, "tau_bias": 0.6858869791030884, "beta": 0.4651939123868942, "train_val_corr": 0.9999999999999998} |
| {"t": 89, "ts": 1788124796.889125, "step": 890, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -36.19109344482422, "attn_entropy": 2.153907585144043, "load_balance": 0.0004787041631061584, "g_entropy": 2.16013240814209, "tau_bias": 0.6858869791030884, "beta": 0.4632748154302438, "train_val_corr": 1.0} |
| {"t": 90, "ts": 1788124802.0897303, "step": 900, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -35.70314025878906, "attn_entropy": 2.1523566246032715, "load_balance": 0.0004792106279637665, "g_entropy": 2.1601037979125977, "tau_bias": 0.6858869791030884, "beta": 0.47503282378117245, "train_val_corr": 1.0} |
| {"t": 91, "ts": 1788124807.1643372, "step": 910, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -33.2307014465332, "attn_entropy": 2.154646873474121, "load_balance": 0.00047830480616539717, "g_entropy": 2.1600621700286866, "tau_bias": 0.6858869791030884, "beta": 0.4812828910847505, "train_val_corr": 1.0} |
| {"t": 92, "ts": 1788124812.2291734, "step": 920, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -31.821626663208008, "attn_entropy": 2.153893995285034, "load_balance": 0.00047907487023621795, "g_entropy": 2.1600332736968992, "tau_bias": 0.6858869791030884, "beta": 0.487119114647309, "train_val_corr": 0.9999999999999999} |
| {"t": 93, "ts": 1788124831.8710442, "step": 930, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -29.573589324951172, "attn_entropy": 2.158377170562744, "load_balance": 0.00047924976679496466, "g_entropy": 2.159704494476318, "tau_bias": 0.6858869791030884, "beta": 0.4879647021492322, "train_val_corr": 0.9999999999999999} |
| {"t": 94, "ts": 1788124836.8730357, "step": 940, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -29.302255630493164, "attn_entropy": 2.1553018569946287, "load_balance": 0.0004783784504979849, "g_entropy": 2.1602213382720947, "tau_bias": 0.6858869791030884, "beta": 0.489919938147068, "train_val_corr": 1.0} |
| {"t": 95, "ts": 1788124842.2331085, "step": 950, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -28.161685943603516, "attn_entropy": 2.1540282726287843, "load_balance": 0.00047908847336657344, "g_entropy": 2.1601206779479982, "tau_bias": 0.6858869791030884, "beta": 0.4914902647336324, "train_val_corr": 0.9999999999999998} |
| {"t": 96, "ts": 1788124847.483729, "step": 960, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -25.805139541625977, "attn_entropy": 2.150869369506836, "load_balance": 0.00047874495503492654, "g_entropy": 2.1598202705383303, "tau_bias": 0.6858869791030884, "beta": 0.49162935093045235, "train_val_corr": 1.0} |
| {"t": 0, "ts": 1788125139.2816923, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 6.490824944194173e-07, "advantage": 9542.1015625, "attn_entropy": 1.270505714416504, "load_balance": 0.0003877239068970084, "g_entropy": 1.3860695362091064, "tau_bias": 0.6884288191795349, "beta": 0.4246274071435134, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788125147.1311705, "step": 10, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.5094615264388267e-06, "advantage": -195.01687622070312, "attn_entropy": 1.166415548324585, "load_balance": 0.00038834845181554554, "g_entropy": 1.3860694885253906, "tau_bias": 0.6952975392341614, "beta": 0.3381774028142293, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788125154.4625232, "step": 20, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.0105007959282375e-06, "advantage": -399.8902587890625, "attn_entropy": 1.279242992401123, "load_balance": 0.0003855544957332313, "g_entropy": 1.3859521389007567, "tau_bias": 0.6923446655273438, "beta": 0.3797454908490181, "train_val_corr": 0.0} |
| {"t": 3, "ts": 1788125161.5954826, "step": 30, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.3672993595246226e-05, "advantage": -392.8567199707031, "attn_entropy": 1.2726593494415284, "load_balance": 0.0003893334185704589, "g_entropy": 1.3860649585723877, "tau_bias": 0.6827033162117004, "beta": 0.35708509385585785, "train_val_corr": 0.0} |
| {"t": 4, "ts": 1788125168.8609087, "step": 40, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.006562414113432169, "advantage": -382.0901184082031, "attn_entropy": 1.2691114902496339, "load_balance": 0.0003890277817845345, "g_entropy": 1.3860793113708496, "tau_bias": 0.6767663359642029, "beta": 0.41089556862910587, "train_val_corr": 0.0} |
| {"t": 5, "ts": 1788125175.5010319, "step": 50, "action": "ATTN_META_ONLY", "entropy_pi": 0.716005265712738, "advantage": -355.0482482910156, "attn_entropy": 1.2832530975341796, "load_balance": 0.00038796433946117757, "g_entropy": 1.3860446453094482, "tau_bias": 0.6738803386688232, "beta": 0.3737160563468933, "train_val_corr": 0.0} |
| {"t": 6, "ts": 1788125189.6424944, "step": 60, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.07241825478377e-07, "advantage": -341.54412841796875, "attn_entropy": 1.3818309307098389, "load_balance": 0.00039023988647386433, "g_entropy": 1.3860759735107422, "tau_bias": 0.6738803386688232, "beta": 0.4775547881921132, "train_val_corr": 0.0} |
| {"t": 7, "ts": 1788125193.5816548, "step": 70, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072895028959465e-07, "advantage": -336.008056640625, "attn_entropy": 1.323309564590454, "load_balance": 0.0003940677270293236, "g_entropy": 1.3860984325408936, "tau_bias": 0.6738803386688232, "beta": 0.45802178730567294, "train_val_corr": 0.0} |
| {"t": 8, "ts": 1788125197.4907308, "step": 80, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.613757490304124e-06, "advantage": -340.2835998535156, "attn_entropy": 1.2624247550964356, "load_balance": 0.00039897162932902577, "g_entropy": 1.3859524726867676, "tau_bias": 0.6738803386688232, "beta": 0.428174523015817, "train_val_corr": 0.0} |
| {"t": 9, "ts": 1788125201.3735952, "step": 90, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.027082497254014015, "advantage": -324.3599548339844, "attn_entropy": 1.1906467914581298, "load_balance": 0.00039983333554118874, "g_entropy": 1.3860451698303222, "tau_bias": 0.6738803386688232, "beta": 0.3946264696617921, "train_val_corr": 0.0} |
| {"t": 10, "ts": 1788125205.2621293, "step": 100, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.11121629178524017, "advantage": -311.2347717285156, "attn_entropy": 1.147887372970581, "load_balance": 0.00040122061036527155, "g_entropy": 1.3860110759735107, "tau_bias": 0.6738803386688232, "beta": 0.43031800786654156, "train_val_corr": 0.0} |
| {"t": 11, "ts": 1788125209.1509116, "step": 110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -301.1410217285156, "attn_entropy": 1.1644937992095947, "load_balance": 0.00040011233650147913, "g_entropy": 1.3860479831695556, "tau_bias": 0.6738803386688232, "beta": 0.43374695504705113, "train_val_corr": 0.0} |
| {"t": 12, "ts": 1788125223.2689118, "step": 120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -286.77984619140625, "attn_entropy": 1.1392742156982423, "load_balance": 0.0004001206252723932, "g_entropy": 1.3860615730285644, "tau_bias": 0.6738803386688232, "beta": 0.4423356391489506, "train_val_corr": 0.0} |
| {"t": 13, "ts": 1788125227.477972, "step": 130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -272.51287841796875, "attn_entropy": 1.1481205940246582, "load_balance": 0.0004004205111414194, "g_entropy": 1.386058235168457, "tau_bias": 0.6738803386688232, "beta": 0.4395816350976626, "train_val_corr": 0.0} |
| {"t": 14, "ts": 1788125231.7577827, "step": 140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -258.7662048339844, "attn_entropy": 1.1683048248291015, "load_balance": 0.0004000626504421234, "g_entropy": 1.3860547065734863, "tau_bias": 0.6738803386688232, "beta": 0.4519256092607975, "train_val_corr": 0.0} |
| {"t": 15, "ts": 1788125236.3032188, "step": 150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723302895930829e-07, "advantage": -246.58932495117188, "attn_entropy": 1.1391322612762451, "load_balance": 0.0004000694025307894, "g_entropy": 1.3860613822937011, "tau_bias": 0.6738803386688232, "beta": 0.45591048275430995, "train_val_corr": 0.0} |
| {"t": 16, "ts": 1788125240.5403595, "step": 160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072347200510194e-07, "advantage": -233.6735076904297, "attn_entropy": 1.2016960620880126, "load_balance": 0.0003992679063230753, "g_entropy": 1.3860469341278077, "tau_bias": 0.6738803386688232, "beta": 0.45584550499916077, "train_val_corr": 0.0} |
| {"t": 17, "ts": 1788125244.7798424, "step": 170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0726187699438015e-07, "advantage": -222.4456024169922, "attn_entropy": 1.176374340057373, "load_balance": 0.00040058402810245753, "g_entropy": 1.3860224723815917, "tau_bias": 0.6738803386688232, "beta": 0.4642606774965922, "train_val_corr": 0.0} |
| {"t": 18, "ts": 1788125259.6840618, "step": 180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0943915046700567e-07, "advantage": -211.74729919433594, "attn_entropy": 1.1561166763305664, "load_balance": 0.00040033634286373854, "g_entropy": 1.386043643951416, "tau_bias": 0.6738803386688232, "beta": 0.46289635449647903, "train_val_corr": 0.0} |
| {"t": 19, "ts": 1788125263.7726188, "step": 190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.1881751877117495e-07, "advantage": -201.3402099609375, "attn_entropy": 1.1798153400421143, "load_balance": 0.0003993394551798701, "g_entropy": 1.3860460758209228, "tau_bias": 0.6738803386688232, "beta": 0.45965321237842244, "train_val_corr": 1.0} |
| {"t": 20, "ts": 1788125268.0520132, "step": 200, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0781703824468423e-06, "advantage": -189.22413635253906, "attn_entropy": 1.1684290885925293, "load_balance": 0.00040010216180235146, "g_entropy": 1.3860191345214843, "tau_bias": 0.6738803386688232, "beta": 0.4612926704188188, "train_val_corr": 0.9999999999999999} |
| {"t": 21, "ts": 1788125272.1753557, "step": 210, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.4065415598452091e-05, "advantage": -180.42535400390625, "attn_entropy": 1.1434714794158936, "load_balance": 0.00040058318991214036, "g_entropy": 1.3860584259033204, "tau_bias": 0.6738803386688232, "beta": 0.46709588666756946, "train_val_corr": 1.0} |
| {"t": 22, "ts": 1788125276.3587785, "step": 220, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0002472593623679131, "advantage": -170.21920776367188, "attn_entropy": 1.1248867511749268, "load_balance": 0.0004010834963992238, "g_entropy": 1.386058235168457, "tau_bias": 0.6738803386688232, "beta": 0.46510251984000206, "train_val_corr": 1.0} |
| {"t": 23, "ts": 1788125280.479284, "step": 230, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0016813620459288359, "advantage": -162.7362060546875, "attn_entropy": 1.2136728763580322, "load_balance": 0.0004003636771813035, "g_entropy": 1.3858423233032227, "tau_bias": 0.6738803386688232, "beta": 0.4706132213274638, "train_val_corr": 1.0} |
| {"t": 24, "ts": 1788125295.3645084, "step": 240, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.005559604149311781, "advantage": -154.48529052734375, "attn_entropy": 1.1381769180297852, "load_balance": 0.00039990204386413096, "g_entropy": 1.3860909938812256, "tau_bias": 0.6738803386688232, "beta": 0.478775837769111, "train_val_corr": 0.9999999999999999} |
| {"t": 25, "ts": 1788125299.37998, "step": 250, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.012759986333549023, "advantage": -146.76708984375, "attn_entropy": 1.1809178352355958, "load_balance": 0.0003992422483861446, "g_entropy": 1.3860477447509765, "tau_bias": 0.6738803386688232, "beta": 0.4806722042461236, "train_val_corr": 1.0} |
| {"t": 26, "ts": 1788125303.4757202, "step": 260, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.016578830778598785, "advantage": -139.94540405273438, "attn_entropy": 1.1580220699310302, "load_balance": 0.0003998874453827739, "g_entropy": 1.38609037399292, "tau_bias": 0.6738803386688232, "beta": 0.48915141200025875, "train_val_corr": 1.0} |
| {"t": 27, "ts": 1788125307.6810713, "step": 270, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.013584943488240242, "advantage": -132.7310333251953, "attn_entropy": 1.1573368549346923, "load_balance": 0.00040081872139126063, "g_entropy": 1.386025619506836, "tau_bias": 0.6738803386688232, "beta": 0.4868929112950961, "train_val_corr": 0.9999999999999999} |
| {"t": 28, "ts": 1788125311.954949, "step": 280, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.01030821818858385, "advantage": -125.74127197265625, "attn_entropy": 1.148775339126587, "load_balance": 0.0004011825658380985, "g_entropy": 1.3860462665557862, "tau_bias": 0.6738803386688232, "beta": 0.49747826904058456, "train_val_corr": 1.0} |
| {"t": 29, "ts": 1788125327.350646, "step": 290, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0058175791054964066, "advantage": -119.96617126464844, "attn_entropy": 1.1854559898376464, "load_balance": 0.00040064314380288123, "g_entropy": 1.3860118865966797, "tau_bias": 0.6738803386688232, "beta": 0.502998319764932, "train_val_corr": 0.9999999999999996} |
| {"t": 30, "ts": 1788125331.6571925, "step": 300, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.006492504384368658, "advantage": -114.3309326171875, "attn_entropy": 1.151627540588379, "load_balance": 0.0003999004838988185, "g_entropy": 1.3860742568969726, "tau_bias": 0.6738803386688232, "beta": 0.5036054328083992, "train_val_corr": 0.9999999999999998} |
| {"t": 31, "ts": 1788125336.5304706, "step": 310, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0033297298941761255, "advantage": -108.36418151855469, "attn_entropy": 1.1721509456634522, "load_balance": 0.00039949347265064714, "g_entropy": 1.3860493183135987, "tau_bias": 0.6738803386688232, "beta": 0.5072503114740053, "train_val_corr": 1.0} |
| {"t": 32, "ts": 1788125340.7771022, "step": 320, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.010149714536964893, "advantage": -103.09806823730469, "attn_entropy": 1.1592730045318604, "load_balance": 0.000400595529936254, "g_entropy": 1.3860292434692383, "tau_bias": 0.6738803386688232, "beta": 0.5100527405738831, "train_val_corr": 1.0} |
| {"t": 33, "ts": 1788125344.976405, "step": 330, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.004982486367225647, "advantage": -98.12397766113281, "attn_entropy": 1.1777015209197998, "load_balance": 0.00039942751172930004, "g_entropy": 1.3860764503479004, "tau_bias": 0.6738803386688232, "beta": 0.5116011699040731, "train_val_corr": 1.0} |
| {"t": 34, "ts": 1788125349.0832233, "step": 340, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.003196484176442027, "advantage": -93.45796203613281, "attn_entropy": 1.1608904361724854, "load_balance": 0.00039953291416168214, "g_entropy": 1.3860557556152344, "tau_bias": 0.6738803386688232, "beta": 0.5091929112871488, "train_val_corr": 0.9999999999999998} |
| {"t": 35, "ts": 1788125364.632737, "step": 350, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.004064985550940037, "advantage": -88.75334167480469, "attn_entropy": 1.1884860515594482, "load_balance": 0.0003990248311311007, "g_entropy": 1.3860629558563233, "tau_bias": 0.6738803386688232, "beta": 0.5124903693795204, "train_val_corr": 1.0} |
| {"t": 36, "ts": 1788125369.144133, "step": 360, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.00239217234775424, "advantage": -84.46669006347656, "attn_entropy": 1.171740436553955, "load_balance": 0.0003985615447163582, "g_entropy": 1.3860741138458252, "tau_bias": 0.6738803386688232, "beta": 0.508305182059606, "train_val_corr": 1.0} |
| {"t": 37, "ts": 1788125373.6589594, "step": 370, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.004973315168172121, "advantage": -80.03627014160156, "attn_entropy": 1.1596295356750488, "load_balance": 0.000399786327034235, "g_entropy": 1.3860690593719482, "tau_bias": 0.6738803386688232, "beta": 0.5095507850249609, "train_val_corr": 1.0} |
| {"t": 38, "ts": 1788125377.67428, "step": 380, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.003127150237560272, "advantage": -75.1961898803711, "attn_entropy": 1.149003028869629, "load_balance": 0.0004005014430731535, "g_entropy": 1.386031150817871, "tau_bias": 0.6738803386688232, "beta": 0.5087985148032507, "train_val_corr": 1.0} |
| {"t": 39, "ts": 1788125381.9842942, "step": 390, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0022004754282534122, "advantage": -72.4137954711914, "attn_entropy": 1.1888943672180177, "load_balance": 0.0003998229978606105, "g_entropy": 1.3860560417175294, "tau_bias": 0.6738803386688232, "beta": 0.5056421235203743, "train_val_corr": 1.0} |
| {"t": 40, "ts": 1788125386.4466147, "step": 400, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.08486604690551758, "advantage": -65.63363647460938, "attn_entropy": 1.1943612098693848, "load_balance": 0.000398473278619349, "g_entropy": 1.386085081100464, "tau_bias": 0.6738803386688232, "beta": 0.5119305923581123, "train_val_corr": 1.0} |
| {"t": 41, "ts": 1788125403.832303, "step": 410, "action": "ATTN_META_ONLY", "entropy_pi": 0.6631171107292175, "advantage": -60.48951721191406, "attn_entropy": 1.1544793605804444, "load_balance": 0.00039966171607375145, "g_entropy": 1.3860754489898681, "tau_bias": 0.6738803386688232, "beta": 0.5132955387234688, "train_val_corr": 1.0} |
| {"t": 42, "ts": 1788125408.5468493, "step": 420, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.693095862865448, "advantage": -58.16092300415039, "attn_entropy": 1.1790603160858155, "load_balance": 0.0003998546162620187, "g_entropy": 1.3860394477844238, "tau_bias": 0.6738803386688232, "beta": 0.5115591237942377, "train_val_corr": 1.0} |
| {"t": 43, "ts": 1788125413.5888684, "step": 430, "action": "ATTN_META_ONLY", "entropy_pi": 0.5941907167434692, "advantage": -55.47230911254883, "attn_entropy": 1.1804873466491699, "load_balance": 0.0004005348077043891, "g_entropy": 1.386008358001709, "tau_bias": 0.6738803386688232, "beta": 0.5078148295482, "train_val_corr": 1.0} |
| {"t": 44, "ts": 1788125418.2839391, "step": 440, "action": "ATTN_META_ONLY", "entropy_pi": 0.05659782513976097, "advantage": -53.86839294433594, "attn_entropy": 1.1586002826690673, "load_balance": 0.00040055604185909035, "g_entropy": 1.3860560417175294, "tau_bias": 0.6738803386688232, "beta": 0.5065790464480718, "train_val_corr": 0.9999999999999999} |
| {"t": 45, "ts": 1788125423.0025222, "step": 450, "action": "ATTN_META_ONLY", "entropy_pi": 0.012302313931286335, "advantage": -49.95772933959961, "attn_entropy": 1.1470095634460449, "load_balance": 0.00040034539997577665, "g_entropy": 1.3860599994659424, "tau_bias": 0.6738803386688232, "beta": 0.5054244250059128, "train_val_corr": 0.9999999999999998} |
| {"t": 46, "ts": 1788125427.6768768, "step": 460, "action": "ATTN_META_ONLY", "entropy_pi": 0.007580969948321581, "advantage": -48.707237243652344, "attn_entropy": 1.1388647079467773, "load_balance": 0.0004011595854535699, "g_entropy": 1.386035442352295, "tau_bias": 0.6738803386688232, "beta": 0.5055311347047488, "train_val_corr": 1.0} |
| {"t": 47, "ts": 1788125444.7828453, "step": 470, "action": "ATTN_META_ONLY", "entropy_pi": 0.00584577489644289, "advantage": -46.050987243652344, "attn_entropy": 1.1739228248596192, "load_balance": 0.00040066533256322145, "g_entropy": 1.3860188961029052, "tau_bias": 0.6738803386688232, "beta": 0.5032903651396433, "train_val_corr": 0.9999999999999999} |
| {"t": 48, "ts": 1788125449.5648654, "step": 480, "action": "ATTN_META_ONLY", "entropy_pi": 0.0013820494059473276, "advantage": -43.83534240722656, "attn_entropy": 1.1464832305908204, "load_balance": 0.00040202457457780836, "g_entropy": 1.3860108375549316, "tau_bias": 0.6738803386688232, "beta": 0.5037118097146353, "train_val_corr": 1.0} |
| {"t": 49, "ts": 1788125454.0700765, "step": 490, "action": "ATTN_META_ONLY", "entropy_pi": 0.0016845820937305689, "advantage": -41.46880340576172, "attn_entropy": 1.1686693668365478, "load_balance": 0.0003995756385847926, "g_entropy": 1.386058235168457, "tau_bias": 0.6738803386688232, "beta": 0.5031059806545576, "train_val_corr": 1.0} |
| {"t": 50, "ts": 1788125458.3622084, "step": 500, "action": "ATTN_META_ONLY", "entropy_pi": 0.0012539781164377928, "advantage": -39.777381896972656, "attn_entropy": 1.1610835552215577, "load_balance": 0.0003996460698544979, "g_entropy": 1.3860533714294434, "tau_bias": 0.6738803386688232, "beta": 0.5025716622670492, "train_val_corr": 1.0} |
| {"t": 51, "ts": 1788125462.6564548, "step": 510, "action": "ATTN_META_ONLY", "entropy_pi": 0.000341119448421523, "advantage": -36.02648162841797, "attn_entropy": 1.1421716690063477, "load_balance": 0.0004006815375760198, "g_entropy": 1.3860642910003662, "tau_bias": 0.6738803386688232, "beta": 0.5033115819096565, "train_val_corr": 0.9999999999999998} |
| {"t": 52, "ts": 1788125466.7834368, "step": 520, "action": "ATTN_META_ONLY", "entropy_pi": 0.0026952505577355623, "advantage": -35.93657302856445, "attn_entropy": 1.1427021026611328, "load_balance": 0.0004004070069640875, "g_entropy": 1.386064052581787, "tau_bias": 0.6738803386688232, "beta": 0.502916527291139, "train_val_corr": 1.0} |
| {"t": 53, "ts": 1788125482.4423475, "step": 530, "action": "ATTN_META_ONLY", "entropy_pi": 0.003353739622980356, "advantage": -34.37860870361328, "attn_entropy": 1.1584591388702392, "load_balance": 0.00040169430430978534, "g_entropy": 1.3860135078430176, "tau_bias": 0.6738803386688232, "beta": 0.5030516137679418, "train_val_corr": 1.0} |
| {"t": 54, "ts": 1788125486.9377055, "step": 540, "action": "ATTN_META_ONLY", "entropy_pi": 0.00030476294341497123, "advantage": -32.38759994506836, "attn_entropy": 1.1563827037811278, "load_balance": 0.0004010135307908058, "g_entropy": 1.3860071182250977, "tau_bias": 0.6738803386688232, "beta": 0.5027062445878983, "train_val_corr": 1.0} |
| {"t": 55, "ts": 1788125491.6435204, "step": 550, "action": "ATTN_META_ONLY", "entropy_pi": 0.0014754078583791852, "advantage": -30.753459930419922, "attn_entropy": 1.1418019771575927, "load_balance": 0.0004011933226138353, "g_entropy": 1.386031723022461, "tau_bias": 0.6738803386688232, "beta": 0.5026311328013738, "train_val_corr": 1.0} |
| {"t": 56, "ts": 1788125496.3603463, "step": 560, "action": "ATTN_META_ONLY", "entropy_pi": 0.0014734064461663365, "advantage": -29.400184631347656, "attn_entropy": 1.1662140369415284, "load_balance": 0.0003998730331659317, "g_entropy": 1.3860460281372071, "tau_bias": 0.6738803386688232, "beta": 0.5027426530917486, "train_val_corr": 0.9999999999999996} |
| {"t": 57, "ts": 1788125500.959332, "step": 570, "action": "ATTN_META_ONLY", "entropy_pi": 0.0002389978471910581, "advantage": -27.678998947143555, "attn_entropy": 1.1532794952392578, "load_balance": 0.0004003167385235429, "g_entropy": 1.3860742568969726, "tau_bias": 0.6738803386688232, "beta": 0.5025671720504761, "train_val_corr": 1.0} |
| {"t": 0, "ts": 1788125554.4469495, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 6.490824944194173e-07, "advantage": 9542.1015625, "attn_entropy": 1.270505714416504, "load_balance": 0.0003877239068970084, "g_entropy": 1.3860695362091064, "tau_bias": 0.6884288191795349, "beta": 0.4246274071435134, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788125560.8298154, "step": 10, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.5094615264388267e-06, "advantage": -195.01687622070312, "attn_entropy": 1.166415548324585, "load_balance": 0.00038834845181554554, "g_entropy": 1.3860694885253906, "tau_bias": 0.6952975392341614, "beta": 0.3381774028142293, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788125567.2966046, "step": 20, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.0105007959282375e-06, "advantage": -399.8902587890625, "attn_entropy": 1.279242992401123, "load_balance": 0.0003855544957332313, "g_entropy": 1.3859521389007567, "tau_bias": 0.6923446655273438, "beta": 0.3797454908490181, "train_val_corr": 0.0} |
| {"t": 3, "ts": 1788125573.9960964, "step": 30, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.3672993595246226e-05, "advantage": -392.8567199707031, "attn_entropy": 1.2726593494415284, "load_balance": 0.0003893334185704589, "g_entropy": 1.3860649585723877, "tau_bias": 0.6827033162117004, "beta": 0.35708509385585785, "train_val_corr": 0.0} |
| {"t": 4, "ts": 1788125580.9576807, "step": 40, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.006562414113432169, "advantage": -382.0901184082031, "attn_entropy": 1.2691114902496339, "load_balance": 0.0003890277817845345, "g_entropy": 1.3860793113708496, "tau_bias": 0.6767663359642029, "beta": 0.41089556862910587, "train_val_corr": 0.0} |
| {"t": 5, "ts": 1788125587.6289973, "step": 50, "action": "ATTN_META_ONLY", "entropy_pi": 0.716005265712738, "advantage": -355.0482482910156, "attn_entropy": 1.2832530975341796, "load_balance": 0.00038796433946117757, "g_entropy": 1.3860446453094482, "tau_bias": 0.6738803386688232, "beta": 0.3737160563468933, "train_val_corr": 0.0} |
| {"t": 6, "ts": 1788125602.1542387, "step": 60, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.07241825478377e-07, "advantage": -341.54412841796875, "attn_entropy": 1.3818309307098389, "load_balance": 0.00039023988647386433, "g_entropy": 1.3860759735107422, "tau_bias": 0.6738803386688232, "beta": 0.4775547881921132, "train_val_corr": 0.0} |
| {"t": 7, "ts": 1788125606.1297348, "step": 70, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072895028959465e-07, "advantage": -336.008056640625, "attn_entropy": 1.323309564590454, "load_balance": 0.0003940677270293236, "g_entropy": 1.3860984325408936, "tau_bias": 0.6738803386688232, "beta": 0.45802178730567294, "train_val_corr": 0.0} |
| {"t": 8, "ts": 1788125610.1443117, "step": 80, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.613757490304124e-06, "advantage": -340.2835998535156, "attn_entropy": 1.2624247550964356, "load_balance": 0.00039897162932902577, "g_entropy": 1.3859524726867676, "tau_bias": 0.6738803386688232, "beta": 0.428174523015817, "train_val_corr": 0.0} |
| {"t": 9, "ts": 1788125614.7298768, "step": 90, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.027082497254014015, "advantage": -324.3599548339844, "attn_entropy": 1.1906467914581298, "load_balance": 0.00039983333554118874, "g_entropy": 1.3860451698303222, "tau_bias": 0.6738803386688232, "beta": 0.3946264696617921, "train_val_corr": 0.0} |
| {"t": 10, "ts": 1788125619.1872222, "step": 100, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.11121629178524017, "advantage": -311.2347717285156, "attn_entropy": 1.147887372970581, "load_balance": 0.00040122061036527155, "g_entropy": 1.3860110759735107, "tau_bias": 0.6738803386688232, "beta": 0.43031800786654156, "train_val_corr": 0.0} |
| {"t": 11, "ts": 1788125623.3698685, "step": 110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -301.1410217285156, "attn_entropy": 1.1644937992095947, "load_balance": 0.00040011233650147913, "g_entropy": 1.3860479831695556, "tau_bias": 0.6738803386688232, "beta": 0.43374695504705113, "train_val_corr": 0.0} |
| {"t": 12, "ts": 1788125638.0718012, "step": 120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -286.77984619140625, "attn_entropy": 1.1392742156982423, "load_balance": 0.0004001206252723932, "g_entropy": 1.3860615730285644, "tau_bias": 0.6738803386688232, "beta": 0.4423356391489506, "train_val_corr": 0.0} |
| {"t": 13, "ts": 1788125642.2731109, "step": 130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -272.51287841796875, "attn_entropy": 1.1481205940246582, "load_balance": 0.0004004205111414194, "g_entropy": 1.386058235168457, "tau_bias": 0.6738803386688232, "beta": 0.4395816350976626, "train_val_corr": 0.0} |
| {"t": 14, "ts": 1788125646.2959356, "step": 140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -258.7662048339844, "attn_entropy": 1.1683048248291015, "load_balance": 0.0004000626504421234, "g_entropy": 1.3860547065734863, "tau_bias": 0.6738803386688232, "beta": 0.4519256092607975, "train_val_corr": 0.0} |
| {"t": 15, "ts": 1788125650.484103, "step": 150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723302895930829e-07, "advantage": -246.58932495117188, "attn_entropy": 1.1391322612762451, "load_balance": 0.0004000694025307894, "g_entropy": 1.3860613822937011, "tau_bias": 0.6738803386688232, "beta": 0.45591048275430995, "train_val_corr": 0.0} |
| {"t": 16, "ts": 1788125654.6833446, "step": 160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072347200510194e-07, "advantage": -233.6735076904297, "attn_entropy": 1.2016960620880126, "load_balance": 0.0003992679063230753, "g_entropy": 1.3860469341278077, "tau_bias": 0.6738803386688232, "beta": 0.45584550499916077, "train_val_corr": 0.0} |
| {"t": 17, "ts": 1788125658.8944757, "step": 170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0726187699438015e-07, "advantage": -222.4456024169922, "attn_entropy": 1.176374340057373, "load_balance": 0.00040058402810245753, "g_entropy": 1.3860224723815917, "tau_bias": 0.6738803386688232, "beta": 0.4642606774965922, "train_val_corr": 0.0} |
| {"t": 18, "ts": 1788125673.7755167, "step": 180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0943915046700567e-07, "advantage": -211.74729919433594, "attn_entropy": 1.1561166763305664, "load_balance": 0.00040033634286373854, "g_entropy": 1.386043643951416, "tau_bias": 0.6738803386688232, "beta": 0.46289635449647903, "train_val_corr": 0.0} |
| {"t": 19, "ts": 1788125677.9743133, "step": 190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.1881751877117495e-07, "advantage": -201.3402099609375, "attn_entropy": 1.1798153400421143, "load_balance": 0.0003993394551798701, "g_entropy": 1.3860460758209228, "tau_bias": 0.6738803386688232, "beta": 0.45965321237842244, "train_val_corr": 1.0} |
| {"t": 20, "ts": 1788125682.1452987, "step": 200, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0781703824468423e-06, "advantage": -189.22413635253906, "attn_entropy": 1.1684290885925293, "load_balance": 0.00040010216180235146, "g_entropy": 1.3860191345214843, "tau_bias": 0.6738803386688232, "beta": 0.4612926704188188, "train_val_corr": 0.9999999999999999} |
| {"t": 21, "ts": 1788125686.4502761, "step": 210, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.4065415598452091e-05, "advantage": -180.42535400390625, "attn_entropy": 1.1434714794158936, "load_balance": 0.00040058318991214036, "g_entropy": 1.3860584259033204, "tau_bias": 0.6738803386688232, "beta": 0.46709588666756946, "train_val_corr": 1.0} |
| {"t": 22, "ts": 1788125690.6796925, "step": 220, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0002472593623679131, "advantage": -170.21920776367188, "attn_entropy": 1.1248867511749268, "load_balance": 0.0004010834963992238, "g_entropy": 1.386058235168457, "tau_bias": 0.6738803386688232, "beta": 0.46510251984000206, "train_val_corr": 1.0} |
| {"t": 23, "ts": 1788125694.940372, "step": 230, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0016813620459288359, "advantage": -162.7362060546875, "attn_entropy": 1.2136728763580322, "load_balance": 0.0004003636771813035, "g_entropy": 1.3858423233032227, "tau_bias": 0.6738803386688232, "beta": 0.4706132213274638, "train_val_corr": 1.0} |
| {"t": 24, "ts": 1788125710.9321415, "step": 240, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.005559604149311781, "advantage": -154.48529052734375, "attn_entropy": 1.1381769180297852, "load_balance": 0.00039990204386413096, "g_entropy": 1.3860909938812256, "tau_bias": 0.6738803386688232, "beta": 0.478775837769111, "train_val_corr": 0.9999999999999999} |
| {"t": 25, "ts": 1788125715.1858358, "step": 250, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.012759986333549023, "advantage": -146.76708984375, "attn_entropy": 1.1809178352355958, "load_balance": 0.0003992422483861446, "g_entropy": 1.3860477447509765, "tau_bias": 0.6738803386688232, "beta": 0.4806722042461236, "train_val_corr": 1.0} |
| {"t": 26, "ts": 1788125719.4594076, "step": 260, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.016578830778598785, "advantage": -139.94540405273438, "attn_entropy": 1.1580220699310302, "load_balance": 0.0003998874453827739, "g_entropy": 1.38609037399292, "tau_bias": 0.6738803386688232, "beta": 0.48915141200025875, "train_val_corr": 1.0} |
| {"t": 27, "ts": 1788125723.701219, "step": 270, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.013584943488240242, "advantage": -132.7310333251953, "attn_entropy": 1.1573368549346923, "load_balance": 0.00040081872139126063, "g_entropy": 1.386025619506836, "tau_bias": 0.6738803386688232, "beta": 0.4868929112950961, "train_val_corr": 0.9999999999999999} |
| {"t": 28, "ts": 1788125728.07211, "step": 280, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.01030821818858385, "advantage": -125.74127197265625, "attn_entropy": 1.148775339126587, "load_balance": 0.0004011825658380985, "g_entropy": 1.3860462665557862, "tau_bias": 0.6738803386688232, "beta": 0.49747826904058456, "train_val_corr": 1.0} |
| {"t": 29, "ts": 1788125743.8523388, "step": 290, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0058175791054964066, "advantage": -119.96617126464844, "attn_entropy": 1.1854559898376464, "load_balance": 0.00040064314380288123, "g_entropy": 1.3860118865966797, "tau_bias": 0.6738803386688232, "beta": 0.502998319764932, "train_val_corr": 0.9999999999999996} |
| {"t": 30, "ts": 1788125748.0655637, "step": 300, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.006492504384368658, "advantage": -114.3309326171875, "attn_entropy": 1.151627540588379, "load_balance": 0.0003999004838988185, "g_entropy": 1.3860742568969726, "tau_bias": 0.6738803386688232, "beta": 0.5036054328083992, "train_val_corr": 0.9999999999999998} |
| {"t": 31, "ts": 1788125752.972728, "step": 310, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0033297298941761255, "advantage": -108.36418151855469, "attn_entropy": 1.1721509456634522, "load_balance": 0.00039949347265064714, "g_entropy": 1.3860493183135987, "tau_bias": 0.6738803386688232, "beta": 0.5072503114740053, "train_val_corr": 1.0} |
| {"t": 32, "ts": 1788125757.3883684, "step": 320, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.010149714536964893, "advantage": -103.09806823730469, "attn_entropy": 1.1592730045318604, "load_balance": 0.000400595529936254, "g_entropy": 1.3860292434692383, "tau_bias": 0.6738803386688232, "beta": 0.5100527405738831, "train_val_corr": 1.0} |
| {"t": 33, "ts": 1788125761.8362126, "step": 330, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.004982486367225647, "advantage": -98.12397766113281, "attn_entropy": 1.1777015209197998, "load_balance": 0.00039942751172930004, "g_entropy": 1.3860764503479004, "tau_bias": 0.6738803386688232, "beta": 0.5116011699040731, "train_val_corr": 1.0} |
| {"t": 34, "ts": 1788125766.3468633, "step": 340, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.003196484176442027, "advantage": -93.45796203613281, "attn_entropy": 1.1608904361724854, "load_balance": 0.00039953291416168214, "g_entropy": 1.3860557556152344, "tau_bias": 0.6738803386688232, "beta": 0.5091929112871488, "train_val_corr": 0.9999999999999998} |
| {"t": 35, "ts": 1788125782.2590024, "step": 350, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.004064985550940037, "advantage": -88.75334167480469, "attn_entropy": 1.1884860515594482, "load_balance": 0.0003990248311311007, "g_entropy": 1.3860629558563233, "tau_bias": 0.6738803386688232, "beta": 0.5124903693795204, "train_val_corr": 1.0} |
| {"t": 36, "ts": 1788125786.3709393, "step": 360, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.00239217234775424, "advantage": -84.46669006347656, "attn_entropy": 1.171740436553955, "load_balance": 0.0003985615447163582, "g_entropy": 1.3860741138458252, "tau_bias": 0.6738803386688232, "beta": 0.508305182059606, "train_val_corr": 1.0} |
| {"t": 37, "ts": 1788125790.473693, "step": 370, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.004973315168172121, "advantage": -80.03627014160156, "attn_entropy": 1.1596295356750488, "load_balance": 0.000399786327034235, "g_entropy": 1.3860690593719482, "tau_bias": 0.6738803386688232, "beta": 0.5095507850249609, "train_val_corr": 1.0} |
| {"t": 38, "ts": 1788125794.5692034, "step": 380, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.003127150237560272, "advantage": -75.1961898803711, "attn_entropy": 1.149003028869629, "load_balance": 0.0004005014430731535, "g_entropy": 1.386031150817871, "tau_bias": 0.6738803386688232, "beta": 0.5087985148032507, "train_val_corr": 1.0} |
| {"t": 39, "ts": 1788125798.5753767, "step": 390, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0022004754282534122, "advantage": -72.4137954711914, "attn_entropy": 1.1888943672180177, "load_balance": 0.0003998229978606105, "g_entropy": 1.3860560417175294, "tau_bias": 0.6738803386688232, "beta": 0.5056421235203743, "train_val_corr": 1.0} |
| {"t": 40, "ts": 1788125802.7413995, "step": 400, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.08486604690551758, "advantage": -65.63363647460938, "attn_entropy": 1.1943612098693848, "load_balance": 0.000398473278619349, "g_entropy": 1.386085081100464, "tau_bias": 0.6738803386688232, "beta": 0.5119305923581123, "train_val_corr": 1.0} |
| {"t": 41, "ts": 1788125820.0657184, "step": 410, "action": "ATTN_META_ONLY", "entropy_pi": 0.6631171107292175, "advantage": -60.48951721191406, "attn_entropy": 1.1544793605804444, "load_balance": 0.00039966171607375145, "g_entropy": 1.3860754489898681, "tau_bias": 0.6738803386688232, "beta": 0.5132955387234688, "train_val_corr": 1.0} |
| {"t": 42, "ts": 1788125825.0487247, "step": 420, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.693095862865448, "advantage": -58.16092300415039, "attn_entropy": 1.1790603160858155, "load_balance": 0.0003998546162620187, "g_entropy": 1.3860394477844238, "tau_bias": 0.6738803386688232, "beta": 0.5115591237942377, "train_val_corr": 1.0} |
| {"t": 43, "ts": 1788125829.5943537, "step": 430, "action": "ATTN_META_ONLY", "entropy_pi": 0.5941907167434692, "advantage": -55.47230911254883, "attn_entropy": 1.1804873466491699, "load_balance": 0.0004005348077043891, "g_entropy": 1.386008358001709, "tau_bias": 0.6738803386688232, "beta": 0.5078148295482, "train_val_corr": 1.0} |
| {"t": 44, "ts": 1788125833.8803716, "step": 440, "action": "ATTN_META_ONLY", "entropy_pi": 0.05659782513976097, "advantage": -53.86839294433594, "attn_entropy": 1.1586002826690673, "load_balance": 0.00040055604185909035, "g_entropy": 1.3860560417175294, "tau_bias": 0.6738803386688232, "beta": 0.5065790464480718, "train_val_corr": 0.9999999999999999} |
| {"t": 45, "ts": 1788125839.0999238, "step": 450, "action": "ATTN_META_ONLY", "entropy_pi": 0.012302313931286335, "advantage": -49.95772933959961, "attn_entropy": 1.1470095634460449, "load_balance": 0.00040034539997577665, "g_entropy": 1.3860599994659424, "tau_bias": 0.6738803386688232, "beta": 0.5054244250059128, "train_val_corr": 0.9999999999999998} |
| {"t": 46, "ts": 1788125843.4960096, "step": 460, "action": "ATTN_META_ONLY", "entropy_pi": 0.007580969948321581, "advantage": -48.707237243652344, "attn_entropy": 1.1388647079467773, "load_balance": 0.0004011595854535699, "g_entropy": 1.386035442352295, "tau_bias": 0.6738803386688232, "beta": 0.5055311347047488, "train_val_corr": 1.0} |
| {"t": 47, "ts": 1788125859.84968, "step": 470, "action": "ATTN_META_ONLY", "entropy_pi": 0.00584577489644289, "advantage": -46.050987243652344, "attn_entropy": 1.1739228248596192, "load_balance": 0.00040066533256322145, "g_entropy": 1.3860188961029052, "tau_bias": 0.6738803386688232, "beta": 0.5032903651396433, "train_val_corr": 0.9999999999999999} |
| {"t": 48, "ts": 1788125864.3968432, "step": 480, "action": "ATTN_META_ONLY", "entropy_pi": 0.0013820494059473276, "advantage": -43.83534240722656, "attn_entropy": 1.1464832305908204, "load_balance": 0.00040202457457780836, "g_entropy": 1.3860108375549316, "tau_bias": 0.6738803386688232, "beta": 0.5037118097146353, "train_val_corr": 1.0} |
| {"t": 49, "ts": 1788125869.0819223, "step": 490, "action": "ATTN_META_ONLY", "entropy_pi": 0.0016845820937305689, "advantage": -41.46880340576172, "attn_entropy": 1.1686693668365478, "load_balance": 0.0003995756385847926, "g_entropy": 1.386058235168457, "tau_bias": 0.6738803386688232, "beta": 0.5031059806545576, "train_val_corr": 1.0} |
| {"t": 50, "ts": 1788125873.7323415, "step": 500, "action": "ATTN_META_ONLY", "entropy_pi": 0.0012539781164377928, "advantage": -39.777381896972656, "attn_entropy": 1.1610835552215577, "load_balance": 0.0003996460698544979, "g_entropy": 1.3860533714294434, "tau_bias": 0.6738803386688232, "beta": 0.5025716622670492, "train_val_corr": 1.0} |
| {"t": 51, "ts": 1788125878.6319995, "step": 510, "action": "ATTN_META_ONLY", "entropy_pi": 0.000341119448421523, "advantage": -36.02648162841797, "attn_entropy": 1.1421716690063477, "load_balance": 0.0004006815375760198, "g_entropy": 1.3860642910003662, "tau_bias": 0.6738803386688232, "beta": 0.5033115819096565, "train_val_corr": 0.9999999999999998} |
| {"t": 52, "ts": 1788125883.6392472, "step": 520, "action": "ATTN_META_ONLY", "entropy_pi": 0.0026952505577355623, "advantage": -35.93657302856445, "attn_entropy": 1.1427021026611328, "load_balance": 0.0004004070069640875, "g_entropy": 1.386064052581787, "tau_bias": 0.6738803386688232, "beta": 0.502916527291139, "train_val_corr": 1.0} |
| {"t": 53, "ts": 1788125899.5843985, "step": 530, "action": "ATTN_META_ONLY", "entropy_pi": 0.003353739622980356, "advantage": -34.37860870361328, "attn_entropy": 1.1584591388702392, "load_balance": 0.00040169430430978534, "g_entropy": 1.3860135078430176, "tau_bias": 0.6738803386688232, "beta": 0.5030516137679418, "train_val_corr": 1.0} |
| {"t": 54, "ts": 1788125903.9688394, "step": 540, "action": "ATTN_META_ONLY", "entropy_pi": 0.00030476294341497123, "advantage": -32.38759994506836, "attn_entropy": 1.1563827037811278, "load_balance": 0.0004010135307908058, "g_entropy": 1.3860071182250977, "tau_bias": 0.6738803386688232, "beta": 0.5027062445878983, "train_val_corr": 1.0} |
| {"t": 55, "ts": 1788125909.3924553, "step": 550, "action": "ATTN_META_ONLY", "entropy_pi": 0.0014754078583791852, "advantage": -30.753459930419922, "attn_entropy": 1.1418019771575927, "load_balance": 0.0004011933226138353, "g_entropy": 1.386031723022461, "tau_bias": 0.6738803386688232, "beta": 0.5026311328013738, "train_val_corr": 1.0} |
| {"t": 56, "ts": 1788125914.1810246, "step": 560, "action": "ATTN_META_ONLY", "entropy_pi": 0.0014734064461663365, "advantage": -29.400184631347656, "attn_entropy": 1.1662140369415284, "load_balance": 0.0003998730331659317, "g_entropy": 1.3860460281372071, "tau_bias": 0.6738803386688232, "beta": 0.5027426530917486, "train_val_corr": 0.9999999999999996} |
| {"t": 57, "ts": 1788125918.8835998, "step": 570, "action": "ATTN_META_ONLY", "entropy_pi": 0.0002389978471910581, "advantage": -27.678998947143555, "attn_entropy": 1.1532794952392578, "load_balance": 0.0004003167385235429, "g_entropy": 1.3860742568969726, "tau_bias": 0.6738803386688232, "beta": 0.5025671720504761, "train_val_corr": 1.0} |
| {"t": 58, "ts": 1788125951.1689117, "step": 580, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.3698834180831909, "advantage": 58.3387565612793, "attn_entropy": 2.035511779785156, "load_balance": 0.00048379715881310406, "g_entropy": 2.160086679458618, "tau_bias": 0.6738803386688232, "beta": 0.5158383150895437, "train_val_corr": 0.9999999999999998} |
| {"t": 59, "ts": 1788125956.3365867, "step": 590, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0010952134616672993, "advantage": -27.053817749023438, "attn_entropy": 2.0174367427825928, "load_balance": 0.0004844999813940376, "g_entropy": 2.1602671146392822, "tau_bias": 0.6738803386688232, "beta": 0.5228293389081955, "train_val_corr": 1.0} |
| {"t": 60, "ts": 1788125961.4977508, "step": 600, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0003517061995808035, "advantage": -29.461488723754883, "attn_entropy": 2.015485668182373, "load_balance": 0.0004847450938541442, "g_entropy": 2.1601423740386965, "tau_bias": 0.6738803386688232, "beta": 0.5151345357298851, "train_val_corr": 1.0} |
| {"t": 61, "ts": 1788125966.686876, "step": 610, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0009571269620209932, "advantage": -28.6281795501709, "attn_entropy": 2.0259146213531496, "load_balance": 0.00048448871239088477, "g_entropy": 2.160114288330078, "tau_bias": 0.6738803386688232, "beta": 0.5106113702058792, "train_val_corr": 1.0} |
| {"t": 62, "ts": 1788125972.09133, "step": 620, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0019330652430653572, "advantage": -26.12168312072754, "attn_entropy": 2.0080596446990966, "load_balance": 0.0004841358691919595, "g_entropy": 2.160073757171631, "tau_bias": 0.6738803386688232, "beta": 0.5100613956650099, "train_val_corr": 1.0} |
| {"t": 63, "ts": 1788125977.587503, "step": 630, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0010432025883346796, "advantage": -25.726634979248047, "attn_entropy": 2.012330484390259, "load_balance": 0.0004860997723881155, "g_entropy": 2.160045623779297, "tau_bias": 0.6738803386688232, "beta": 0.5070616751909256, "train_val_corr": 1.0} |
| {"t": 64, "ts": 1788125998.365598, "step": 640, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0021449089981615543, "advantage": -23.389938354492188, "attn_entropy": 2.029577875137329, "load_balance": 0.00048810883308760824, "g_entropy": 2.1597250938415526, "tau_bias": 0.6738803386688232, "beta": 0.506904661655426, "train_val_corr": 1.0} |
| {"t": 65, "ts": 1788126003.7797225, "step": 650, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.002176842885091901, "advantage": -23.213642120361328, "attn_entropy": 2.015138292312622, "load_balance": 0.0004838344466406852, "g_entropy": 2.160228967666626, "tau_bias": 0.6738803386688232, "beta": 0.5048491830627123, "train_val_corr": 0.9999999999999998} |
| {"t": 66, "ts": 1788126008.8774388, "step": 660, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.003656059270724654, "advantage": -22.041627883911133, "attn_entropy": 2.029644775390625, "load_balance": 0.0004849683493375778, "g_entropy": 2.160130834579468, "tau_bias": 0.6738803386688232, "beta": 0.5043178324898084, "train_val_corr": 1.0} |
| {"t": 67, "ts": 1788126013.861006, "step": 670, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0012289525475353003, "advantage": -20.791349411010742, "attn_entropy": 2.0216003894805907, "load_balance": 0.00048384200199507176, "g_entropy": 2.1598379135131838, "tau_bias": 0.6738803386688232, "beta": 0.504519502321879, "train_val_corr": 1.0} |
| {"t": 68, "ts": 1788126019.0497837, "step": 680, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.002925821579992771, "advantage": -19.810102462768555, "attn_entropy": 2.0379168510437013, "load_balance": 0.00048407462309114636, "g_entropy": 2.160094690322876, "tau_bias": 0.6738803386688232, "beta": 0.5031283150116602, "train_val_corr": 1.0} |
| {"t": 69, "ts": 1788126024.3776062, "step": 690, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0011354057351127267, "advantage": -17.626693725585938, "attn_entropy": 2.015362501144409, "load_balance": 0.00048416260979138314, "g_entropy": 2.1600595474243165, "tau_bias": 0.6738803386688232, "beta": 0.5033149793744087, "train_val_corr": 0.9999999999999998} |
| {"t": 70, "ts": 1788126044.1358967, "step": 700, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0037583813536912203, "advantage": -18.355289459228516, "attn_entropy": 2.025461292266846, "load_balance": 0.000484961672918871, "g_entropy": 2.160048484802246, "tau_bias": 0.6738803386688232, "beta": 0.5027885561188062, "train_val_corr": 1.0} |
| {"t": 71, "ts": 1788126049.4430094, "step": 710, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0029137402307242155, "advantage": -15.977474212646484, "attn_entropy": 2.0312567710876466, "load_balance": 0.0004848775512073189, "g_entropy": 2.160204792022705, "tau_bias": 0.6738803386688232, "beta": 0.5028743371367455, "train_val_corr": 1.0} |
| {"t": 72, "ts": 1788126054.5722058, "step": 720, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.003976082429289818, "advantage": -16.12769317626953, "attn_entropy": 2.0338630199432375, "load_balance": 0.0004845506104175001, "g_entropy": 2.160140800476074, "tau_bias": 0.6738803386688232, "beta": 0.502639522155126, "train_val_corr": 1.0} |
| {"t": 73, "ts": 1788126059.6871564, "step": 730, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.005663752555847168, "advantage": -15.918889045715332, "attn_entropy": 2.014795255661011, "load_balance": 0.000483749556588009, "g_entropy": 2.1602406978607176, "tau_bias": 0.6738803386688232, "beta": 0.5025673732161522, "train_val_corr": 1.0} |
| {"t": 74, "ts": 1788126064.7710528, "step": 740, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0026043164543807507, "advantage": -15.543977737426758, "attn_entropy": 2.045548152923584, "load_balance": 0.000484482484171167, "g_entropy": 2.1600672245025634, "tau_bias": 0.6738803386688232, "beta": 0.5026168848077456, "train_val_corr": 1.0} |
| {"t": 75, "ts": 1788126070.174759, "step": 750, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.004636361263692379, "advantage": -13.764791488647461, "attn_entropy": 2.03689923286438, "load_balance": 0.00048429148155264555, "g_entropy": 2.159988260269165, "tau_bias": 0.6738803386688232, "beta": 0.5025705645481745, "train_val_corr": 0.9999999999999998} |
| {"t": 76, "ts": 1788126089.9575613, "step": 760, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.004357007797807455, "advantage": -13.626601219177246, "attn_entropy": 2.0326388835906983, "load_balance": 0.00048450299073010683, "g_entropy": 2.159800672531128, "tau_bias": 0.6738803386688232, "beta": 0.5024241631229719, "train_val_corr": 0.9999999999999997} |
| {"t": 77, "ts": 1788126095.3735824, "step": 770, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0012720718514174223, "advantage": -12.803934097290039, "attn_entropy": 2.0385677814483643, "load_balance": 0.0004841759393457323, "g_entropy": 2.1600671768188477, "tau_bias": 0.6738803386688232, "beta": 0.5025465935468674, "train_val_corr": 0.9999999999999998} |
| {"t": 78, "ts": 1788126100.6986978, "step": 780, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.005337185226380825, "advantage": 5.066944599151611, "attn_entropy": 2.033849859237671, "load_balance": 0.0004839429340790957, "g_entropy": 2.1600632190704347, "tau_bias": 0.6738803386688232, "beta": 0.5190336580077807, "train_val_corr": 1.0} |
| {"t": 79, "ts": 1788126106.1417582, "step": 790, "action": "ATTN_META_ONLY", "entropy_pi": 0.440406858921051, "advantage": -4.5910820960998535, "attn_entropy": 1.9574323177337647, "load_balance": 0.000485663436120376, "g_entropy": 2.160071039199829, "tau_bias": 0.6738803386688232, "beta": 0.5156374201178551, "train_val_corr": 1.0} |
| {"t": 80, "ts": 1788126111.6312559, "step": 800, "action": "ATTN_META_ONLY", "entropy_pi": 0.01578938402235508, "advantage": -6.138219356536865, "attn_entropy": 1.9511978149414062, "load_balance": 0.0004867528041359037, "g_entropy": 2.1600045680999758, "tau_bias": 0.6738803386688232, "beta": 0.5154327203830084, "train_val_corr": 1.0} |
| {"t": 81, "ts": 1788126117.2018661, "step": 810, "action": "ATTN_META_ONLY", "entropy_pi": 0.003746215719729662, "advantage": -8.559961318969727, "attn_entropy": 1.953460121154785, "load_balance": 0.00048711950075812637, "g_entropy": 2.1592759132385253, "tau_bias": 0.6738803386688232, "beta": 0.5126730799674988, "train_val_corr": 1.0} |
| {"t": 82, "ts": 1788126138.142058, "step": 820, "action": "ATTN_META_ONLY", "entropy_pi": 0.006806425750255585, "advantage": -7.999255657196045, "attn_entropy": 1.93467116355896, "load_balance": 0.00048671564436517654, "g_entropy": 2.1600085735321044, "tau_bias": 0.6738803386688232, "beta": 0.5111171454191208, "train_val_corr": 1.0} |
| {"t": 0, "ts": 1788126192.6363294, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.00017917381774168462, "advantage": 227.32652282714844, "attn_entropy": 2.0355122566223143, "load_balance": 0.0004837971180677414, "g_entropy": 2.1600866317749023, "tau_bias": 0.6714344024658203, "beta": 0.5067430411775907, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788126201.5428398, "step": 10, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0725235572172096e-07, "advantage": 18.085060119628906, "attn_entropy": 2.054842710494995, "load_balance": 0.0004830253834370524, "g_entropy": 2.1602674961090087, "tau_bias": 0.6735682487487793, "beta": 0.5176717936992645, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788126210.4582593, "step": 20, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723271632050455e-07, "advantage": 27.350732803344727, "attn_entropy": 2.0247424602508546, "load_balance": 0.00048366966657340524, "g_entropy": 2.1601426124572756, "tau_bias": 0.673219621181488, "beta": 0.5359030763308207, "train_val_corr": 0.0} |
| {"t": 3, "ts": 1788126219.145798, "step": 30, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 15.786223411560059, "attn_entropy": 1.964686346054077, "load_balance": 0.000484890298685059, "g_entropy": 2.160111331939697, "tau_bias": 0.6769165992736816, "beta": 0.5596063261230787, "train_val_corr": 0.0} |
| {"t": 4, "ts": 1788126228.4763732, "step": 40, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 25.207059860229492, "attn_entropy": 1.7985050678253174, "load_balance": 0.00048381361993961037, "g_entropy": 2.1600728034973145, "tau_bias": 0.6755410432815552, "beta": 0.5541981185475985, "train_val_corr": 0.0} |
| {"t": 5, "ts": 1788126237.4453683, "step": 50, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 1.1103157997131348, "attn_entropy": 1.7330020427703858, "load_balance": 0.0004895870166365057, "g_entropy": 2.1600465297698976, "tau_bias": 0.6724205017089844, "beta": 0.5298878873387972, "train_val_corr": 0.0} |
| {"t": 6, "ts": 1788126260.2468543, "step": 60, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 590.5339965820312, "attn_entropy": 1.6874082565307618, "load_balance": 0.0004925359913613647, "g_entropy": 2.159713792800903, "tau_bias": 0.6817032098770142, "beta": 0.5903124089042345, "train_val_corr": 0.0} |
| {"t": 7, "ts": 1788126269.1997154, "step": 70, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -16.591445922851562, "attn_entropy": 1.5545526027679444, "load_balance": 0.00048126386827789246, "g_entropy": 2.160224676132202, "tau_bias": 0.6797938346862793, "beta": 0.507224311431249, "train_val_corr": 0.0} |
| {"t": 8, "ts": 1788126278.1574042, "step": 80, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -9.766301155090332, "attn_entropy": 1.522092628479004, "load_balance": 0.0004836282168980688, "g_entropy": 2.1601266384124758, "tau_bias": 0.6793375611305237, "beta": 0.5377323428789774, "train_val_corr": 0.0} |
| {"t": 9, "ts": 1788126287.036668, "step": 90, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -29.583782196044922, "attn_entropy": 1.5034541606903076, "load_balance": 0.0004839279921725392, "g_entropy": 2.1598302364349364, "tau_bias": 0.6787957549095154, "beta": 0.5123314062754313, "train_val_corr": 0.0} |
| {"t": 10, "ts": 1788126295.7636447, "step": 100, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -8.132418632507324, "attn_entropy": 1.0929081916809082, "load_balance": 0.00048706847592256964, "g_entropy": 2.1600954055786135, "tau_bias": 0.6723408102989197, "beta": 0.5203984354933103, "train_val_corr": 0.0} |
| {"t": 11, "ts": 1788126304.481036, "step": 110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 18.97127342224121, "attn_entropy": 0.83097403049469, "load_balance": 0.00048486777814105153, "g_entropy": 2.1600653171539306, "tau_bias": 0.6678800582885742, "beta": 0.47113435342907906, "train_val_corr": 0.0} |
| {"t": 12, "ts": 1788126327.4540505, "step": 120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 21.623130798339844, "attn_entropy": 0.7216166138648987, "load_balance": 0.0004889722273219377, "g_entropy": 2.16005539894104, "tau_bias": 0.6670333743095398, "beta": 0.49963652715086937, "train_val_corr": 0.0} |
| {"t": 13, "ts": 1788126336.2741098, "step": 130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -29.69931983947754, "attn_entropy": 0.585305392742157, "load_balance": 0.0004934844328090549, "g_entropy": 2.1602096557617188, "tau_bias": 0.66675865650177, "beta": 0.5205062652627627, "train_val_corr": 0.0} |
| {"t": 14, "ts": 1788126345.1378076, "step": 140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -24.825214385986328, "attn_entropy": 0.5763588845729828, "load_balance": 0.0004915100114885717, "g_entropy": 2.1601463317871095, "tau_bias": 0.6671183705329895, "beta": 0.5117040375868479, "train_val_corr": 0.0} |
| {"t": 15, "ts": 1788126354.0680416, "step": 150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -9.196451187133789, "attn_entropy": 0.4660482912789803, "load_balance": 0.0004863198846578598, "g_entropy": 2.160244417190552, "tau_bias": 0.6674085855484009, "beta": 0.5042916635672251, "train_val_corr": 0.0} |
| {"t": 16, "ts": 1788126363.2929258, "step": 160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 5.171746253967285, "attn_entropy": 0.473962278484305, "load_balance": 0.0004917469108477235, "g_entropy": 2.1600740432739256, "tau_bias": 0.666881799697876, "beta": 0.495130921403567, "train_val_corr": 0.0} |
| {"t": 17, "ts": 1788126372.7411726, "step": 170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -12.970258712768555, "attn_entropy": 0.4467926608296239, "load_balance": 0.0004883096262346953, "g_entropy": 2.159991979598999, "tau_bias": 0.6716200113296509, "beta": 0.49583973238865536, "train_val_corr": 0.0} |
| {"t": 18, "ts": 1788126395.7470055, "step": 180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -25.125844955444336, "attn_entropy": 0.4066826919304276, "load_balance": 0.0004913410113658756, "g_entropy": 2.159798526763916, "tau_bias": 0.6755051612854004, "beta": 0.5125463530421257, "train_val_corr": 0.0} |
| {"t": 19, "ts": 1788126404.638361, "step": 190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -30.421192169189453, "attn_entropy": 0.430326719417053, "load_balance": 0.0004892115481197834, "g_entropy": 2.1600648880004885, "tau_bias": 0.6767040491104126, "beta": 0.5158374806245168, "train_val_corr": 1.0} |
| {"t": 20, "ts": 1788126413.6649938, "step": 200, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 7.939769744873047, "attn_entropy": 0.35784093434861575, "load_balance": 0.0004894376441370695, "g_entropy": 2.1600598335266112, "tau_bias": 0.674694836139679, "beta": 0.5074347828825315, "train_val_corr": 1.0} |
| {"t": 21, "ts": 1788126422.7769647, "step": 210, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -17.49796485900879, "attn_entropy": 0.3460727847194036, "load_balance": 0.0004881194268818945, "g_entropy": 2.160063457489014, "tau_bias": 0.6826353073120117, "beta": 0.5279871647556623, "train_val_corr": 1.0} |
| {"t": 22, "ts": 1788126431.964756, "step": 220, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -21.042387008666992, "attn_entropy": 0.3589412679194339, "load_balance": 0.0004908104601781815, "g_entropy": 2.15998911857605, "tau_bias": 0.6877725124359131, "beta": 0.5319088200728098, "train_val_corr": 0.9999999999999998} |
| {"t": 23, "ts": 1788126440.9320936, "step": 230, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -22.887676239013672, "attn_entropy": 0.3755609211309633, "load_balance": 0.0004914941440802067, "g_entropy": 2.1592233657836912, "tau_bias": 0.6951130628585815, "beta": 0.5318169916669527, "train_val_corr": 0.9999999999999998} |
| {"t": 24, "ts": 1788126466.3578506, "step": 240, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -24.331802368164062, "attn_entropy": 0.40531937450120237, "load_balance": 0.00048616206622682513, "g_entropy": 2.159971237182617, "tau_bias": 0.7105238437652588, "beta": 0.5353185087442398, "train_val_corr": 1.0} |
| {"t": 25, "ts": 1788126477.4683964, "step": 250, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -22.909597396850586, "attn_entropy": 0.3774760658370731, "load_balance": 0.0004889726580586285, "g_entropy": 2.1602219104766847, "tau_bias": 0.7252944707870483, "beta": 0.5303623676300049, "train_val_corr": 0.9999999999999998} |
| {"t": 26, "ts": 1788126487.1753337, "step": 260, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -22.02788543701172, "attn_entropy": 0.3736056953128193, "load_balance": 0.0004898030776530505, "g_entropy": 2.160190963745117, "tau_bias": 0.7309679388999939, "beta": 0.5255451301733652, "train_val_corr": 1.0} |
| {"t": 27, "ts": 1788126496.5354962, "step": 270, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -21.07895851135254, "attn_entropy": 0.3956847702965547, "load_balance": 0.0004937016114126891, "g_entropy": 2.159998559951782, "tau_bias": 0.7323011755943298, "beta": 0.5255791495243708, "train_val_corr": 0.9999999999999998} |
| {"t": 28, "ts": 1788126505.557187, "step": 280, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -18.771472930908203, "attn_entropy": 0.3733940075614746, "load_balance": 0.000488863093778491, "g_entropy": 2.1599738597869873, "tau_bias": 0.7322610020637512, "beta": 0.5179417232672373, "train_val_corr": 1.0} |
| {"t": 29, "ts": 1788126529.5430217, "step": 290, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -18.7200870513916, "attn_entropy": 0.3843183451279522, "load_balance": 0.00048516308888792994, "g_entropy": 2.1591451168060303, "tau_bias": 0.7320997714996338, "beta": 0.5189330577850342, "train_val_corr": 0.9999999999999998} |
| {"t": 30, "ts": 1788126538.9556677, "step": 300, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -18.891111373901367, "attn_entropy": 0.3910404942644462, "load_balance": 0.0004904203990008682, "g_entropy": 2.160218858718872, "tau_bias": 0.7331053614616394, "beta": 0.5145035733779272, "train_val_corr": 0.9999999999999996} |
| {"t": 31, "ts": 1788126549.3887286, "step": 310, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -17.62580680847168, "attn_entropy": 0.39861026379510633, "load_balance": 0.0004920470761135221, "g_entropy": 2.1597146511077883, "tau_bias": 0.7346453070640564, "beta": 0.5142688155174255, "train_val_corr": 1.0} |
| {"t": 32, "ts": 1788126558.9010973, "step": 320, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -15.903139114379883, "attn_entropy": 0.38717344043564167, "load_balance": 0.0004875882470514625, "g_entropy": 2.1600770473480226, "tau_bias": 0.7362115383148193, "beta": 0.5136745274066925, "train_val_corr": 1.0} |
| {"t": 33, "ts": 1788126568.091787, "step": 330, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -14.828242301940918, "attn_entropy": 0.3987285131874586, "load_balance": 0.0004913592536468058, "g_entropy": 2.1601103782653808, "tau_bias": 0.7360255718231201, "beta": 0.5084644084175428, "train_val_corr": 1.0} |
| {"t": 34, "ts": 1788126577.5000668, "step": 340, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -15.03446102142334, "attn_entropy": 0.391869539438143, "load_balance": 0.0004897781473118812, "g_entropy": 2.1599307537078856, "tau_bias": 0.7351741194725037, "beta": 0.5063914259274801, "train_val_corr": 0.9999999999999994} |
|
|
