| {"t": 0, "ts": 1788056007.1375484, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.3746508359909058, "advantage": NaN, "attn_entropy": 3.4977147579193115, "load_balance": 0.0009509647497907281, "g_entropy": 3.3737047910690308, "tau_bias": NaN, "beta": 0.49884337559342384, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788056011.633347, "step": 10, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": NaN, "train_val_corr": 0.0} |
| {"t": 0, "ts": 1788056034.0219119, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.3746508359909058, "advantage": NaN, "attn_entropy": 3.4977147579193115, "load_balance": 0.0009509647497907281, "g_entropy": 3.3737047910690308, "tau_bias": NaN, "beta": 0.49884337559342384, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788056038.6241837, "step": 10, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": NaN, "train_val_corr": 0.0} |
| {"t": 0, "ts": 1788056102.227451, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.3746508359909058, "advantage": NaN, "attn_entropy": 3.4977147579193115, "load_balance": 0.0009509647497907281, "g_entropy": 3.3737047910690308, "tau_bias": NaN, "beta": 0.49884337559342384, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788056106.4479978, "step": 10, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": NaN, "train_val_corr": 0.0} |
| {"t": 0, "ts": 1788056131.6138318, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.3746508359909058, "advantage": NaN, "attn_entropy": 3.4977147579193115, "load_balance": 0.0009509647497907281, "g_entropy": 3.3737047910690308, "tau_bias": NaN, "beta": 0.49884337559342384, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788056135.9755397, "step": 10, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": NaN, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788056140.2311304, "step": 20, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": 1.0, "train_val_corr": 0.0} |
| {"t": 0, "ts": 1788056160.9383981, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.3746508359909058, "advantage": NaN, "attn_entropy": 3.4977147579193115, "load_balance": 0.0009509647497907281, "g_entropy": 3.3737047910690308, "tau_bias": NaN, "beta": 0.49884337559342384, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788056165.1638763, "step": 10, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": NaN, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788056169.3292696, "step": 20, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": 1.0, "train_val_corr": 0.0} |
| {"t": 0, "ts": 1788056194.348417, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.3746508359909058, "advantage": NaN, "attn_entropy": 3.4977147579193115, "load_balance": 0.0009509647497907281, "g_entropy": 3.3737047910690308, "tau_bias": NaN, "beta": 0.49884337559342384, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788056198.473998, "step": 10, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": NaN, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788056202.5434074, "step": 20, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": 1.0, "train_val_corr": 0.0} |
| {"t": 0, "ts": 1788056225.4160354, "step": 0, "action": "ATTN_HYBRID_FULL", "entropy_pi": 1.315382719039917, "advantage": 109.59370422363281, "attn_entropy": 3.309232473373413, "load_balance": 0.0014783814549446106, "g_entropy": 3.1536834239959717, "tau_bias": 0.702392578125, "beta": 0.4987971931695938, "train_val_corr": 0.0} |
| {"t": 0, "ts": 1788056277.4576707, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.3746508359909058, "advantage": NaN, "attn_entropy": 3.4977147579193115, "load_balance": 0.0009509647497907281, "g_entropy": 3.3737047910690308, "tau_bias": NaN, "beta": 0.49884337559342384, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788056281.7400432, "step": 10, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": NaN, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788056285.9288547, "step": 20, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": 1.0, "train_val_corr": 0.0} |
| {"t": 0, "ts": 1788056312.5701947, "step": 0, "action": "SHRINK", "entropy_pi": 1.4201205968856812, "advantage": 96.9046859741211, "attn_entropy": 3.571521282196045, "load_balance": 0.0009180156339425594, "g_entropy": 3.4834388494491577, "tau_bias": 0.7023934125900269, "beta": 0.49887706339359283, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788056317.2208955, "step": 10, "action": "ATTN_HYBRID_FULL", "entropy_pi": 0.4387620687484741, "advantage": 147.26792907714844, "attn_entropy": 3.5394179821014404, "load_balance": 0.0009498308936599642, "g_entropy": 3.435598373413086, "tau_bias": 0.6840249300003052, "beta": 0.49214625731110573, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788056321.8554132, "step": 20, "action": "SHRINK", "entropy_pi": 0.1811761111021042, "advantage": 59.2436637878418, "attn_entropy": 3.5404351949691772, "load_balance": 0.0009542845364194363, "g_entropy": 3.3646485805511475, "tau_bias": 0.667445182800293, "beta": 0.4830969199538231, "train_val_corr": 0.0} |
| {"t": 0, "ts": 1788056349.7419574, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.3746508359909058, "advantage": NaN, "attn_entropy": 3.4977147579193115, "load_balance": 0.0009509647497907281, "g_entropy": 3.3737047910690308, "tau_bias": NaN, "beta": 0.49884337559342384, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788056354.5151277, "step": 10, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": NaN, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788056359.083536, "step": 20, "action": "CONCAT", "entropy_pi": NaN, "advantage": NaN, "attn_entropy": NaN, "load_balance": NaN, "g_entropy": NaN, "tau_bias": NaN, "beta": 1.0, "train_val_corr": 0.0} |
| {"t": 0, "ts": 1788056386.7635508, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.3746508359909058, "advantage": NaN, "attn_entropy": 3.4977147579193115, "load_balance": 0.0009509647497907281, "g_entropy": 3.3737047910690308, "tau_bias": NaN, "beta": 0.49884337559342384, "train_val_corr": 0.0} |
| {"t": 0, "ts": 1788056488.0259535, "step": 0, "action": "ATTN_META_ONLY", "entropy_pi": 1.443568468093872, "advantage": 93.41775512695312, "attn_entropy": 3.4977147579193115, "load_balance": 0.0009509647497907281, "g_entropy": 3.3737047910690308, "tau_bias": 0.7023932933807373, "beta": 0.4989074803888798, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788056490.3224974, "step": 10, "action": "RECURSE", "entropy_pi": 0.31905433535575867, "advantage": 255.9584503173828, "attn_entropy": 3.3608778715133667, "load_balance": 0.0012983513588551432, "g_entropy": 3.143410801887512, "tau_bias": 0.7023932933807373, "beta": 0.48602383956313133, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788056492.5256395, "step": 20, "action": "ATTN_META_ONLY", "entropy_pi": 0.5152419209480286, "advantage": 96.30131530761719, "attn_entropy": 3.4192309379577637, "load_balance": 0.0010744767496362329, "g_entropy": 3.2595118284225464, "tau_bias": 0.7023932933807373, "beta": 0.0, "train_val_corr": 0.0} |
| {"t": 0, "ts": 1788061752.3799934, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.4314768314361572, "advantage": 12.196395874023438, "attn_entropy": 3.465693950653076, "load_balance": 0.0009766783332452178, "g_entropy": 3.465651035308838, "tau_bias": 0.6998578906059265, "beta": 0.4996812012977898, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788061760.6249628, "step": 10, "action": "ATTN_META_ONLY", "entropy_pi": 0.37726789712905884, "advantage": 4.059122085571289, "attn_entropy": 3.465688467025757, "load_balance": 0.0009766449220478535, "g_entropy": 3.465660572052002, "tau_bias": 0.6825059652328491, "beta": 0.48645601887255907, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788061765.4370427, "step": 20, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.3489358723163605, "advantage": 4.684025764465332, "attn_entropy": 3.465716600418091, "load_balance": 0.0009765742579475045, "g_entropy": 3.4657235145568848, "tau_bias": 0.6825059652328491, "beta": 0.4460525941103697, "train_val_corr": 0.0} |
| {"t": 3, "ts": 1788061770.062885, "step": 30, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.18095572292804718, "advantage": 4.670926570892334, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765630820766091, "g_entropy": 3.465735673904419, "tau_bias": 0.6825059652328491, "beta": 0.4161718189716339, "train_val_corr": 0.0} |
| {"t": 4, "ts": 1788061774.736584, "step": 40, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.06657496094703674, "advantage": 1.5985686779022217, "attn_entropy": 3.4656989574432373, "load_balance": 0.0009766235016286373, "g_entropy": 3.4656782150268555, "tau_bias": 0.6825059652328491, "beta": 0.41371983382850885, "train_val_corr": 0.0} |
| {"t": 5, "ts": 1788061779.5201325, "step": 50, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.017713041976094246, "advantage": 0.9894397258758545, "attn_entropy": 3.465726613998413, "load_balance": 0.0009765656432136893, "g_entropy": 3.4657323360443115, "tau_bias": 0.6825059652328491, "beta": 0.41069499566219747, "train_val_corr": 0.0} |
| {"t": 6, "ts": 1788061784.170581, "step": 60, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.00536221731454134, "advantage": 0.20533403754234314, "attn_entropy": 3.4656949043273926, "load_balance": 0.0009766197763383389, "g_entropy": 3.4656858444213867, "tau_bias": 0.6825059652328491, "beta": 0.4118864182382822, "train_val_corr": 0.0} |
| {"t": 7, "ts": 1788061789.1425362, "step": 70, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.002073008334264159, "advantage": 0.16651062667369843, "attn_entropy": 3.465721845626831, "load_balance": 0.000976587412878871, "g_entropy": 3.4657132625579834, "tau_bias": 0.6825059652328491, "beta": 0.41206342563964427, "train_val_corr": 0.0} |
| {"t": 8, "ts": 1788061793.9544754, "step": 80, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.000960617559030652, "advantage": 1.8434627056121826, "attn_entropy": 3.4657318592071533, "load_balance": 0.0009765645954757929, "g_entropy": 3.4657342433929443, "tau_bias": 0.6825059652328491, "beta": 0.4030056339688599, "train_val_corr": 0.0} |
| {"t": 9, "ts": 1788061798.8138664, "step": 90, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.00047436877503059804, "advantage": 0.1334790587425232, "attn_entropy": 3.4657280445098877, "load_balance": 0.0009765650611370802, "g_entropy": 3.4657325744628906, "tau_bias": 0.6825059652328491, "beta": 0.40750716254115105, "train_val_corr": 0.0} |
| {"t": 10, "ts": 1788061803.532684, "step": 100, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.00023796736786607653, "advantage": 0.5758548378944397, "attn_entropy": 3.4657347202301025, "load_balance": 0.0009765641298145056, "g_entropy": 3.4657347202301025, "tau_bias": 0.6825059652328491, "beta": 0.3980432965327054, "train_val_corr": 0.0} |
| {"t": 11, "ts": 1788061808.355102, "step": 110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0725063620830042e-07, "advantage": -0.11289187520742416, "attn_entropy": 3.4657299518585205, "load_balance": 0.0009765642462298274, "g_entropy": 3.465733528137207, "tau_bias": 0.6825059652328491, "beta": 0.38803647994063795, "train_val_corr": 0.0} |
| {"t": 12, "ts": 1788061813.0253348, "step": 120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.07235089533242e-07, "advantage": 1.5969810485839844, "attn_entropy": 3.4657347202301025, "load_balance": 0.000976565177552402, "g_entropy": 3.465733766555786, "tau_bias": 0.6825059652328491, "beta": 0.37650668912101537, "train_val_corr": 0.0} |
| {"t": 13, "ts": 1788061817.8631094, "step": 130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723308580272715e-07, "advantage": 0.20267429947853088, "attn_entropy": 3.465730905532837, "load_balance": 0.0009765649447217584, "g_entropy": 3.4657344818115234, "tau_bias": 0.6825059652328491, "beta": 0.3635533689521253, "train_val_corr": 0.0} |
| {"t": 14, "ts": 1788061822.6531694, "step": 140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723273053135927e-07, "advantage": -1.0899327993392944, "attn_entropy": 3.465726613998413, "load_balance": 0.0009765655267983675, "g_entropy": 3.4657325744628906, "tau_bias": 0.6825059652328491, "beta": 0.38892226945608854, "train_val_corr": 0.0} |
| {"t": 15, "ts": 1788061827.7544544, "step": 150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072326594770857e-07, "advantage": -0.7170608043670654, "attn_entropy": 3.46565580368042, "load_balance": 0.0009766313014551997, "g_entropy": 3.4656620025634766, "tau_bias": 0.6825059652328491, "beta": 0.3803178849630058, "train_val_corr": 0.0} |
| {"t": 16, "ts": 1788061832.8613849, "step": 160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.311659038066864, "attn_entropy": 3.4655568599700928, "load_balance": 0.0009767910232767463, "g_entropy": 3.465520143508911, "tau_bias": 0.6825059652328491, "beta": 0.36774669867008924, "train_val_corr": 0.0} |
| {"t": 17, "ts": 1788061837.8350918, "step": 170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.5659658908843994, "attn_entropy": 3.465723991394043, "load_balance": 0.000976571231149137, "g_entropy": 3.4657247066497803, "tau_bias": 0.6825059652328491, "beta": 0.3801291912095621, "train_val_corr": 0.0} |
| {"t": 18, "ts": 1788061842.6467907, "step": 180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.40437066555023193, "attn_entropy": 3.4654507637023926, "load_balance": 0.0009769166354089975, "g_entropy": 3.465397357940674, "tau_bias": 0.6825059652328491, "beta": 0.35899304307531565, "train_val_corr": 0.0} |
| {"t": 19, "ts": 1788061847.474397, "step": 190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.8632622957229614, "attn_entropy": 3.465704917907715, "load_balance": 0.000976585317403078, "g_entropy": 3.4657142162323, "tau_bias": 0.6825059652328491, "beta": 0.37313824286684394, "train_val_corr": 1.0} |
| {"t": 20, "ts": 1788061852.3496954, "step": 200, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.09683369100093842, "attn_entropy": 3.4657273292541504, "load_balance": 0.0009765669237822294, "g_entropy": 3.4657325744628906, "tau_bias": 0.6825059652328491, "beta": 0.3780269909184426, "train_val_corr": 1.0} |
| {"t": 21, "ts": 1788061857.276045, "step": 210, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.028799787163734436, "attn_entropy": 3.4657275676727295, "load_balance": 0.0009765666909515858, "g_entropy": 3.4657297134399414, "tau_bias": 0.6825059652328491, "beta": 0.3418491252232343, "train_val_corr": 1.0} |
| {"t": 22, "ts": 1788061862.1676314, "step": 220, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.9800748825073242, "attn_entropy": 3.4657132625579834, "load_balance": 0.0009765776339918375, "g_entropy": 3.4657208919525146, "tau_bias": 0.6825059652328491, "beta": 0.3502060023602098, "train_val_corr": 0.9999999999999998} |
| {"t": 23, "ts": 1788061867.2826009, "step": 230, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.8731364607810974, "attn_entropy": 3.4657294750213623, "load_balance": 0.0009765748400241137, "g_entropy": 3.4657254219055176, "tau_bias": 0.6825059652328491, "beta": 0.3606975325383246, "train_val_corr": 1.0} |
| {"t": 24, "ts": 1788061872.0538595, "step": 240, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.4596744775772095, "attn_entropy": 3.465730905532837, "load_balance": 0.000976563896983862, "g_entropy": 3.4657347202301025, "tau_bias": 0.6825059652328491, "beta": 0.33628414501436055, "train_val_corr": 1.0} |
| {"t": 25, "ts": 1788061876.8581295, "step": 250, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.82267165184021, "attn_entropy": 3.465726852416992, "load_balance": 0.000976567156612873, "g_entropy": 3.4657318592071533, "tau_bias": 0.6825059652328491, "beta": 0.3743814944755286, "train_val_corr": 1.0} |
| {"t": 26, "ts": 1788061881.665303, "step": 260, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.7187963128089905, "attn_entropy": 3.4657182693481445, "load_balance": 0.000976590788923204, "g_entropy": 3.465712070465088, "tau_bias": 0.6825059652328491, "beta": 0.3503865608945489, "train_val_corr": 1.0} |
| {"t": 27, "ts": 1788061886.3553238, "step": 270, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.8268409371376038, "attn_entropy": 3.4656879901885986, "load_balance": 0.000976602896116674, "g_entropy": 3.4656882286071777, "tau_bias": 0.6825059652328491, "beta": 0.3589870510622859, "train_val_corr": 1.0} |
| {"t": 28, "ts": 1788061891.2720065, "step": 280, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.0717150866985321, "attn_entropy": 3.46570086479187, "load_balance": 0.0009765906725078821, "g_entropy": 3.465707778930664, "tau_bias": 0.6825059652328491, "beta": 0.3634747745236382, "train_val_corr": 0.9999999999999996} |
| {"t": 29, "ts": 1788061895.9467983, "step": 290, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.5949488282203674, "attn_entropy": 3.4657347202301025, "load_balance": 0.0009765647118911147, "g_entropy": 3.4657347202301025, "tau_bias": 0.6825059652328491, "beta": 0.332804745528847, "train_val_corr": 1.0} |
| {"t": 30, "ts": 1788061900.6356084, "step": 300, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.5853696465492249, "attn_entropy": 3.465578556060791, "load_balance": 0.0009767620358616114, "g_entropy": 3.465543508529663, "tau_bias": 0.6825059652328491, "beta": 0.35700433142483234, "train_val_corr": 1.0} |
| {"t": 31, "ts": 1788061905.9689317, "step": 310, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.48080888390541077, "attn_entropy": 3.4657347202301025, "load_balance": 0.0009765654103830457, "g_entropy": 3.4657342433929443, "tau_bias": 0.6825059652328491, "beta": 0.3535890739876777, "train_val_corr": 1.0} |
| {"t": 32, "ts": 1788061910.9749823, "step": 320, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.5996444225311279, "attn_entropy": 3.4657275676727295, "load_balance": 0.0009765668073669076, "g_entropy": 3.465730667114258, "tau_bias": 0.6825059652328491, "beta": 0.36899717547930777, "train_val_corr": 1.0} |
| {"t": 33, "ts": 1788061915.9576216, "step": 330, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.5113747715950012, "attn_entropy": 3.4657280445098877, "load_balance": 0.000976565177552402, "g_entropy": 3.4657325744628906, "tau_bias": 0.6825059652328491, "beta": 0.360649683047086, "train_val_corr": 0.9999999999999999} |
| {"t": 34, "ts": 1788061920.8607903, "step": 340, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.5356424450874329, "attn_entropy": 3.4657344818115234, "load_balance": 0.000976564479060471, "g_entropy": 3.4657342433929443, "tau_bias": 0.6825059652328491, "beta": 0.37861975375562906, "train_val_corr": 1.0} |
| {"t": 35, "ts": 1788061925.5565891, "step": 350, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3122017979621887, "attn_entropy": 3.4657299518585205, "load_balance": 0.0009765747236087918, "g_entropy": 3.465726137161255, "tau_bias": 0.6825059652328491, "beta": 0.3623075825162232, "train_val_corr": 1.0} |
| {"t": 36, "ts": 1788061930.3840034, "step": 360, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.38994187116622925, "attn_entropy": 3.4657015800476074, "load_balance": 0.0009766161674633622, "g_entropy": 3.465686798095703, "tau_bias": 0.6825059652328491, "beta": 0.37385495752096176, "train_val_corr": 0.9999999999999997} |
| {"t": 37, "ts": 1788061935.3576949, "step": 370, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.39430344104766846, "attn_entropy": 3.465726852416992, "load_balance": 0.0009765669237822294, "g_entropy": 3.465731382369995, "tau_bias": 0.6825059652328491, "beta": 0.37253871373832226, "train_val_corr": 1.0} |
| {"t": 38, "ts": 1788061940.1239405, "step": 380, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3766990602016449, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765635477378964, "g_entropy": 3.4657349586486816, "tau_bias": 0.6825059652328491, "beta": 0.3839623623061925, "train_val_corr": 0.9999999999999998} |
| {"t": 39, "ts": 1788061945.135741, "step": 390, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.36100950837135315, "attn_entropy": 3.465670585632324, "load_balance": 0.0009766194270923734, "g_entropy": 3.4656777381896973, "tau_bias": 0.6825059652328491, "beta": 0.3860988817177713, "train_val_corr": 1.0} |
| {"t": 40, "ts": 1788061949.767824, "step": 400, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2372560203075409, "attn_entropy": 3.4657206535339355, "load_balance": 0.0009765737922862172, "g_entropy": 3.465723752975464, "tau_bias": 0.6825059652328491, "beta": 0.3748259039130062, "train_val_corr": 1.0} |
| {"t": 41, "ts": 1788061954.5375507, "step": 410, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.5207928419113159, "attn_entropy": 3.465733051300049, "load_balance": 0.000976564479060471, "g_entropy": 3.4657340049743652, "tau_bias": 0.6825059652328491, "beta": 0.38147839717566967, "train_val_corr": 1.0} |
| {"t": 42, "ts": 1788061959.179991, "step": 420, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.16010957956314087, "attn_entropy": 3.4656693935394287, "load_balance": 0.0009766193106770515, "g_entropy": 3.465675115585327, "tau_bias": 0.6825059652328491, "beta": 0.3901851892005652, "train_val_corr": 1.0} |
| {"t": 43, "ts": 1788061963.8276691, "step": 430, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.27382799983024597, "attn_entropy": 3.4655873775482178, "load_balance": 0.000976750859990716, "g_entropy": 3.4655635356903076, "tau_bias": 0.6825059652328491, "beta": 0.39055967098101974, "train_val_corr": 0.9999999999999999} |
| {"t": 44, "ts": 1788061968.6311266, "step": 440, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.4852777123451233, "attn_entropy": 3.4654500484466553, "load_balance": 0.000976916286163032, "g_entropy": 3.465397357940674, "tau_bias": 0.6825059652328491, "beta": 0.4003439722582698, "train_val_corr": 0.9999999999999999} |
| {"t": 45, "ts": 1788061973.3525758, "step": 450, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.27782967686653137, "attn_entropy": 3.465686559677124, "load_balance": 0.0009766322327777743, "g_entropy": 3.465669870376587, "tau_bias": 0.6825059652328491, "beta": 0.3949335226789117, "train_val_corr": 1.0} |
| {"t": 46, "ts": 1788061978.1790345, "step": 460, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.21530485153198242, "attn_entropy": 3.46571946144104, "load_balance": 0.0009765926515683532, "g_entropy": 3.4657087326049805, "tau_bias": 0.6825059652328491, "beta": 0.39156086277216673, "train_val_corr": 0.9999999999999998} |
| {"t": 47, "ts": 1788061982.9818034, "step": 470, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.37716585397720337, "attn_entropy": 3.4657130241394043, "load_balance": 0.00097659754101187, "g_entropy": 3.4657068252563477, "tau_bias": 0.6825059652328491, "beta": 0.4293024865910411, "train_val_corr": 0.9999999999999999} |
| {"t": 48, "ts": 1788061987.838538, "step": 480, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.4202137589454651, "attn_entropy": 3.465729236602783, "load_balance": 0.0009765761205926538, "g_entropy": 3.465724229812622, "tau_bias": 0.6825059652328491, "beta": 0.41247075190767646, "train_val_corr": 1.0} |
| {"t": 49, "ts": 1788061992.4751558, "step": 490, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.25070682168006897, "attn_entropy": 3.4657275676727295, "load_balance": 0.0009765669237822294, "g_entropy": 3.4657323360443115, "tau_bias": 0.6825059652328491, "beta": 0.4098122329451144, "train_val_corr": 1.0} |
| {"t": 50, "ts": 1788061997.2321436, "step": 500, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3505333364009857, "attn_entropy": 3.46553897857666, "load_balance": 0.0009768109302967787, "g_entropy": 3.4655001163482666, "tau_bias": 0.6825059652328491, "beta": 0.41911696130409837, "train_val_corr": 0.9999999999999998} |
| {"t": 51, "ts": 1788062001.7678668, "step": 510, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3719431757926941, "attn_entropy": 3.465701103210449, "load_balance": 0.0009765906725078821, "g_entropy": 3.465707778930664, "tau_bias": 0.6825059652328491, "beta": 0.4378633978776634, "train_val_corr": 0.9999999999999998} |
| {"t": 52, "ts": 1788062006.2725759, "step": 520, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.6557691693305969, "attn_entropy": 3.4657299518585205, "load_balance": 0.0009765748400241137, "g_entropy": 3.4657254219055176, "tau_bias": 0.6825059652328491, "beta": 0.4210786079056561, "train_val_corr": 1.0} |
| {"t": 53, "ts": 1788062010.8320568, "step": 530, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.15072107315063477, "attn_entropy": 3.465625286102295, "load_balance": 0.0009767032461240888, "g_entropy": 3.465606212615967, "tau_bias": 0.6825059652328491, "beta": 0.43314575031399727, "train_val_corr": 1.0} |
| {"t": 54, "ts": 1788062015.350769, "step": 540, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.08121585845947266, "attn_entropy": 3.4655003547668457, "load_balance": 0.0009768601739779115, "g_entropy": 3.465444564819336, "tau_bias": 0.6825059652328491, "beta": 0.43476943066343665, "train_val_corr": 1.0} |
| {"t": 55, "ts": 1788062019.8676417, "step": 550, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.03759681060910225, "attn_entropy": 3.4657299518585205, "load_balance": 0.0009765643626451492, "g_entropy": 3.465733528137207, "tau_bias": 0.6825059652328491, "beta": 0.4377800994552672, "train_val_corr": 1.0} |
| {"t": 56, "ts": 1788062024.4806743, "step": 560, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.05827708914875984, "attn_entropy": 3.4657342433929443, "load_balance": 0.0009765629656612873, "g_entropy": 3.465735673904419, "tau_bias": 0.6825059652328491, "beta": 0.4386471416801214, "train_val_corr": 1.0} |
| {"t": 57, "ts": 1788062029.1335294, "step": 570, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.4158880412578583, "attn_entropy": 3.4657185077667236, "load_balance": 0.0009765910217538476, "g_entropy": 3.465711832046509, "tau_bias": 0.6825059652328491, "beta": 0.45018703304231167, "train_val_corr": 0.9999999999999998} |
| {"t": 58, "ts": 1788062033.9142175, "step": 580, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3458681106567383, "attn_entropy": 3.4657182693481445, "load_balance": 0.0009765902068465948, "g_entropy": 3.465712785720825, "tau_bias": 0.6825059652328491, "beta": 0.43727845419198275, "train_val_corr": 0.9999999999999998} |
| {"t": 59, "ts": 1788062038.5797672, "step": 590, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.16523149609565735, "attn_entropy": 3.4657115936279297, "load_balance": 0.0009765785653144121, "g_entropy": 3.4657199382781982, "tau_bias": 0.6825059652328491, "beta": 0.4331219708546996, "train_val_corr": 1.0} |
| {"t": 60, "ts": 1788062043.3887863, "step": 600, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3132249712944031, "attn_entropy": 3.46572208404541, "load_balance": 0.0009765706490725279, "g_entropy": 3.4657275676727295, "tau_bias": 0.6825059652328491, "beta": 0.4369978350587189, "train_val_corr": 1.0} |
| {"t": 61, "ts": 1788062047.9600813, "step": 610, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.20995070040225983, "attn_entropy": 3.4657022953033447, "load_balance": 0.0009766148868948221, "g_entropy": 3.4656882286071777, "tau_bias": 0.6825059652328491, "beta": 0.4297758638858795, "train_val_corr": 1.0} |
| {"t": 62, "ts": 1788062052.4854233, "step": 620, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.14897634088993073, "attn_entropy": 3.4657020568847656, "load_balance": 0.0009765876457095146, "g_entropy": 3.4657089710235596, "tau_bias": 0.6825059652328491, "beta": 0.45090480661019683, "train_val_corr": 1.0} |
| {"t": 63, "ts": 1788062057.0796378, "step": 630, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.18352802097797394, "attn_entropy": 3.4657042026519775, "load_balance": 0.0009765863651409745, "g_entropy": 3.465712308883667, "tau_bias": 0.6825059652328491, "beta": 0.4338137558661401, "train_val_corr": 1.0} |
| {"t": 64, "ts": 1788062061.9296575, "step": 640, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.03494615852832794, "attn_entropy": 3.465707540512085, "load_balance": 0.0009765824070200324, "g_entropy": 3.4657156467437744, "tau_bias": 0.6825059652328491, "beta": 0.4385287705808878, "train_val_corr": 1.0} |
| {"t": 65, "ts": 1788062066.6803756, "step": 650, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.23712845146656036, "attn_entropy": 3.465721607208252, "load_balance": 0.000976571231149137, "g_entropy": 3.4657270908355713, "tau_bias": 0.6825059652328491, "beta": 0.42577739944681525, "train_val_corr": 1.0} |
| {"t": 66, "ts": 1788062071.5687642, "step": 660, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.04593503847718239, "attn_entropy": 3.465705156326294, "load_balance": 0.000976604875177145, "g_entropy": 3.4656968116760254, "tau_bias": 0.6825059652328491, "beta": 0.4073777236044407, "train_val_corr": 1.0} |
| {"t": 67, "ts": 1788062076.5578842, "step": 670, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1608942151069641, "attn_entropy": 3.4657175540924072, "load_balance": 0.0009765743743628263, "g_entropy": 3.4657235145568848, "tau_bias": 0.6825059652328491, "beta": 0.4287472602445632, "train_val_corr": 0.9999999999999998} |
| {"t": 68, "ts": 1788062081.04565, "step": 680, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.09706144034862518, "attn_entropy": 3.465693712234497, "load_balance": 0.0009765978902578354, "g_entropy": 3.4657034873962402, "tau_bias": 0.6825059652328491, "beta": 0.3984413262223825, "train_val_corr": 1.0} |
| {"t": 69, "ts": 1788062085.5389407, "step": 690, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.26969870924949646, "attn_entropy": 3.4657037258148193, "load_balance": 0.0009766097646206617, "g_entropy": 3.4656949043273926, "tau_bias": 0.6825059652328491, "beta": 0.4076503908727318, "train_val_corr": 0.9999999999999997} |
| {"t": 70, "ts": 1788062090.0160663, "step": 700, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.17486456036567688, "attn_entropy": 3.4657301902770996, "load_balance": 0.0009765755385160446, "g_entropy": 3.465723991394043, "tau_bias": 0.6825059652328491, "beta": 0.41692282259464264, "train_val_corr": 0.9999999999999999} |
| {"t": 71, "ts": 1788062094.6184256, "step": 710, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1804960072040558, "attn_entropy": 3.465728521347046, "load_balance": 0.0009765654103830457, "g_entropy": 3.4657325744628906, "tau_bias": 0.6825059652328491, "beta": 0.4175487032625824, "train_val_corr": 1.0} |
| {"t": 72, "ts": 1788062099.2415168, "step": 720, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.09638193249702454, "attn_entropy": 3.4657328128814697, "load_balance": 0.0009765628492459655, "g_entropy": 3.4657347202301025, "tau_bias": 0.6825059652328491, "beta": 0.42982566379942, "train_val_corr": 1.0} |
| {"t": 73, "ts": 1788062103.9828553, "step": 730, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.10520675778388977, "attn_entropy": 3.4657058715820312, "load_balance": 0.0009766094153746963, "g_entropy": 3.4656972885131836, "tau_bias": 0.6825059652328491, "beta": 0.43367593782022595, "train_val_corr": 0.9999999999999998} |
| {"t": 74, "ts": 1788062108.9253192, "step": 740, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2834641635417938, "attn_entropy": 3.4657175540924072, "load_balance": 0.0009765924187377095, "g_entropy": 3.465710401535034, "tau_bias": 0.6825059652328491, "beta": 0.43896513478830457, "train_val_corr": 0.9999999999999998} |
| {"t": 75, "ts": 1788062113.9345171, "step": 750, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.05847368761897087, "attn_entropy": 3.4657046794891357, "load_balance": 0.0009765862487256527, "g_entropy": 3.465712308883667, "tau_bias": 0.6825059652328491, "beta": 0.42995735816657543, "train_val_corr": 1.0} |
| {"t": 76, "ts": 1788062118.8516912, "step": 760, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.15852400660514832, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765643626451492, "g_entropy": 3.4657344818115234, "tau_bias": 0.6825059652328491, "beta": 0.423198611009866, "train_val_corr": 1.0} |
| {"t": 77, "ts": 1788062123.7509527, "step": 770, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.06558346003293991, "attn_entropy": 3.4657320976257324, "load_balance": 0.000976563198491931, "g_entropy": 3.465735673904419, "tau_bias": 0.6825059652328491, "beta": 0.43145650113001466, "train_val_corr": 1.0} |
| {"t": 78, "ts": 1788062128.6429603, "step": 780, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.09751679748296738, "attn_entropy": 3.4656829833984375, "load_balance": 0.0009766381699591875, "g_entropy": 3.465670347213745, "tau_bias": 0.6825059652328491, "beta": 0.419617674080655, "train_val_corr": 1.0} |
| {"t": 79, "ts": 1788062133.3686795, "step": 790, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.149979829788208, "attn_entropy": 3.4657278060913086, "load_balance": 0.0009765669237822294, "g_entropy": 3.4657323360443115, "tau_bias": 0.6825059652328491, "beta": 0.42412071069702506, "train_val_corr": 1.0} |
| {"t": 80, "ts": 1788062138.1716626, "step": 800, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.014015568420290947, "attn_entropy": 3.4657018184661865, "load_balance": 0.0009766145376488566, "g_entropy": 3.4656898975372314, "tau_bias": 0.6825059652328491, "beta": 0.4265689901076257, "train_val_corr": 1.0} |
| {"t": 81, "ts": 1788062142.9255428, "step": 810, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.16042226552963257, "attn_entropy": 3.46571683883667, "load_balance": 0.0009765923023223877, "g_entropy": 3.465710401535034, "tau_bias": 0.6825059652328491, "beta": 0.4066472896374762, "train_val_corr": 1.0} |
| {"t": 82, "ts": 1788062147.9182954, "step": 820, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.05789411440491676, "attn_entropy": 3.465714931488037, "load_balance": 0.0009765764698386192, "g_entropy": 3.4657208919525146, "tau_bias": 0.6825059652328491, "beta": 0.4259752379730344, "train_val_corr": 1.0} |
| {"t": 83, "ts": 1788062152.916212, "step": 830, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1283777356147766, "attn_entropy": 3.4654674530029297, "load_balance": 0.0009768964955583215, "g_entropy": 3.4654226303100586, "tau_bias": 0.6825059652328491, "beta": 0.42254856741055846, "train_val_corr": 1.0} |
| {"t": 84, "ts": 1788062157.738928, "step": 840, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.026185745373368263, "attn_entropy": 3.465717315673828, "load_balance": 0.0009765749564394355, "g_entropy": 3.4657235145568848, "tau_bias": 0.6825059652328491, "beta": 0.4349383800290525, "train_val_corr": 1.0} |
| {"t": 85, "ts": 1788062162.373664, "step": 850, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.31131675839424133, "attn_entropy": 3.4657135009765625, "load_balance": 0.0009766012663021684, "g_entropy": 3.46570086479187, "tau_bias": 0.6825059652328491, "beta": 0.4414253714494407, "train_val_corr": 1.0} |
| {"t": 86, "ts": 1788062167.1369255, "step": 860, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.07277030497789383, "attn_entropy": 3.465723991394043, "load_balance": 0.0009765700669959188, "g_entropy": 3.4657299518585205, "tau_bias": 0.6825059652328491, "beta": 0.4380032094195485, "train_val_corr": 1.0} |
| {"t": 87, "ts": 1788062171.736606, "step": 870, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.04978436604142189, "attn_entropy": 3.465729236602783, "load_balance": 0.0009765648283064365, "g_entropy": 3.4657340049743652, "tau_bias": 0.6825059652328491, "beta": 0.43766275187954307, "train_val_corr": 1.0} |
| {"t": 88, "ts": 1788062176.5428045, "step": 880, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.13919132947921753, "attn_entropy": 3.465712785720825, "load_balance": 0.000976598123088479, "g_entropy": 3.4657044410705566, "tau_bias": 0.6825059652328491, "beta": 0.45945316506549716, "train_val_corr": 1.0} |
| {"t": 89, "ts": 1788062181.578475, "step": 890, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.11017447710037231, "attn_entropy": 3.4656982421875, "load_balance": 0.0009766187286004424, "g_entropy": 3.4656872749328613, "tau_bias": 0.6825059652328491, "beta": 0.4541251575574279, "train_val_corr": 1.0} |
| {"t": 90, "ts": 1788062186.7184339, "step": 900, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.004344100598245859, "attn_entropy": 3.4657063484191895, "load_balance": 0.0009765854338184, "g_entropy": 3.465714454650879, "tau_bias": 0.6825059652328491, "beta": 0.46599459322169423, "train_val_corr": 1.0} |
| {"t": 91, "ts": 1788062191.664392, "step": 910, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.07181119173765182, "attn_entropy": 3.4657299518585205, "load_balance": 0.0009765648283064365, "g_entropy": 3.4657344818115234, "tau_bias": 0.6825059652328491, "beta": 0.46914348378777504, "train_val_corr": 1.0} |
| {"t": 92, "ts": 1788062196.6267855, "step": 920, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.15061204135417938, "attn_entropy": 3.465623140335083, "load_balance": 0.0009766682051122189, "g_entropy": 3.465627670288086, "tau_bias": 0.6825059652328491, "beta": 0.4753662389703095, "train_val_corr": 1.0} |
| {"t": 93, "ts": 1788062201.7342005, "step": 930, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.15720675885677338, "attn_entropy": 3.4657206535339355, "load_balance": 0.0009765718132257462, "g_entropy": 3.4657254219055176, "tau_bias": 0.6825059652328491, "beta": 0.476740853395313, "train_val_corr": 0.9999999999999998} |
| {"t": 94, "ts": 1788062206.572346, "step": 940, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.17518970370292664, "attn_entropy": 3.465714693069458, "load_balance": 0.0009765774011611938, "g_entropy": 3.46572208404541, "tau_bias": 0.6825059652328491, "beta": 0.47577057126909494, "train_val_corr": 0.9999999999999999} |
| {"t": 95, "ts": 1788062211.539931, "step": 950, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.07870855182409286, "attn_entropy": 3.465695381164551, "load_balance": 0.0009765939321368933, "g_entropy": 3.465705633163452, "tau_bias": 0.6825059652328491, "beta": 0.478028055280447, "train_val_corr": 0.9999999999999999} |
| {"t": 96, "ts": 1788062216.3320303, "step": 960, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.015386868268251419, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765662252902985, "g_entropy": 3.465733289718628, "tau_bias": 0.6825059652328491, "beta": 0.4800280714407563, "train_val_corr": 0.9999999999999999} |
| {"t": 97, "ts": 1788062221.1845837, "step": 970, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.24403010308742523, "attn_entropy": 3.4657223224639893, "load_balance": 0.000976570532657206, "g_entropy": 3.4657275676727295, "tau_bias": 0.6825059652328491, "beta": 0.48234995221719146, "train_val_corr": 1.0} |
| {"t": 98, "ts": 1788062226.1366785, "step": 980, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.11278492957353592, "attn_entropy": 3.4655721187591553, "load_balance": 0.0009767694864422083, "g_entropy": 3.465545654296875, "tau_bias": 0.6825059652328491, "beta": 0.48226652992889285, "train_val_corr": 0.9999999999999998} |
| {"t": 99, "ts": 1788062230.9343596, "step": 990, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.026140404865145683, "attn_entropy": 3.4653897285461426, "load_balance": 0.0009769832249730825, "g_entropy": 3.465336561203003, "tau_bias": 0.6825059652328491, "beta": 0.48442417941987514, "train_val_corr": 0.9999999999999998} |
| {"t": 100, "ts": 1788062235.877721, "step": 1000, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.06556063890457153, "attn_entropy": 3.4656898975372314, "load_balance": 0.0009766313014551997, "g_entropy": 3.4656732082366943, "tau_bias": 0.6825059652328491, "beta": 0.48690478364005685, "train_val_corr": 0.9999999999999998} |
| {"t": 101, "ts": 1788062240.734156, "step": 1010, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.09029306471347809, "attn_entropy": 3.4657304286956787, "load_balance": 0.00097656378056854, "g_entropy": 3.4657347202301025, "tau_bias": 0.6825059652328491, "beta": 0.48741635819897056, "train_val_corr": 0.9999999999999998} |
| {"t": 102, "ts": 1788062245.852924, "step": 1020, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.0002491181658115238, "attn_entropy": 3.465716600418091, "load_balance": 0.0009765949798747897, "g_entropy": 3.465707302093506, "tau_bias": 0.6825059652328491, "beta": 0.47784342616796494, "train_val_corr": 1.0} |
| {"t": 103, "ts": 1788062250.8450568, "step": 1030, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.3825323283672333, "attn_entropy": 3.465726852416992, "load_balance": 0.0009765791473910213, "g_entropy": 3.46572208404541, "tau_bias": 0.6825059652328491, "beta": 0.473401983268559, "train_val_corr": 1.0} |
| {"t": 104, "ts": 1788062255.4218023, "step": 1040, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.09458405524492264, "attn_entropy": 3.465717077255249, "load_balance": 0.0009765763534232974, "g_entropy": 3.4657227993011475, "tau_bias": 0.6825059652328491, "beta": 0.4731494444422424, "train_val_corr": 1.0} |
| {"t": 105, "ts": 1788062259.8567698, "step": 1050, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.10663579404354095, "attn_entropy": 3.4656128883361816, "load_balance": 0.0009767231531441212, "g_entropy": 3.4655871391296387, "tau_bias": 0.6825059652328491, "beta": 0.4748772461898625, "train_val_corr": 1.0} |
| {"t": 106, "ts": 1788062264.454527, "step": 1060, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1308841109275818, "attn_entropy": 3.4657182693481445, "load_balance": 0.0009765723953023553, "g_entropy": 3.4657256603240967, "tau_bias": 0.6825059652328491, "beta": 0.47549182130023837, "train_val_corr": 1.0} |
| {"t": 0, "ts": 1788064142.9768403, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.3965106010437012, "advantage": 6.150230884552002, "attn_entropy": 3.465726137161255, "load_balance": 0.0009765895083546638, "g_entropy": 3.4657163619995117, "tau_bias": 0.6999524235725403, "beta": 0.4997497859100501, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788064147.7439024, "step": 10, "action": "ATTN_META_ONLY", "entropy_pi": 0.43277978897094727, "advantage": 3.986206293106079, "attn_entropy": 3.465681552886963, "load_balance": 0.0009766446892172098, "g_entropy": 3.4656660556793213, "tau_bias": 0.6827874183654785, "beta": 0.48796860004464787, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788064150.9610531, "step": 20, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.42900341749191284, "advantage": 2.667457103729248, "attn_entropy": 3.4657349586486816, "load_balance": 0.000976563896983862, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.45504378403226536, "train_val_corr": 0.0} |
| {"t": 3, "ts": 1788064154.2298422, "step": 30, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.23094631731510162, "advantage": 2.4395856857299805, "attn_entropy": 3.465686321258545, "load_balance": 0.0009766557486727834, "g_entropy": 3.46565318107605, "tau_bias": 0.6827874183654785, "beta": 0.4218534504373868, "train_val_corr": 0.0} |
| {"t": 4, "ts": 1788064157.4720805, "step": 40, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.08378235250711441, "advantage": 3.4406511783599854, "attn_entropy": 3.465696334838867, "load_balance": 0.000976639916189015, "g_entropy": 3.4656686782836914, "tau_bias": 0.6827874183654785, "beta": 0.41006101481616497, "train_val_corr": 0.0} |
| {"t": 5, "ts": 1788064160.8784344, "step": 50, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.024425746873021126, "advantage": 1.53561532497406, "attn_entropy": 3.465733766555786, "load_balance": 0.000976563198491931, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.4412246240923802, "train_val_corr": 0.0} |
| {"t": 6, "ts": 1788064164.081837, "step": 60, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.00788771640509367, "advantage": 0.8819096684455872, "attn_entropy": 3.465564727783203, "load_balance": 0.0009768615709617734, "g_entropy": 3.465465784072876, "tau_bias": 0.6827874183654785, "beta": 0.42499463135997456, "train_val_corr": 0.0} |
| {"t": 7, "ts": 1788064167.3341906, "step": 70, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0030015152879059315, "advantage": -0.13336920738220215, "attn_entropy": 3.465731143951416, "load_balance": 0.0009765659924596548, "g_entropy": 3.4657325744628906, "tau_bias": 0.6827874183654785, "beta": 0.4174178938070933, "train_val_corr": 0.0} |
| {"t": 8, "ts": 1788064170.657961, "step": 80, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0013734034728258848, "advantage": 1.7500206232070923, "attn_entropy": 3.4657249450683594, "load_balance": 0.0009765754221007228, "g_entropy": 3.4657225608825684, "tau_bias": 0.6827874183654785, "beta": 0.40271858498454094, "train_val_corr": 0.0} |
| {"t": 9, "ts": 1788064173.94547, "step": 90, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0007402171031571925, "advantage": -0.5032905340194702, "attn_entropy": 3.4657347202301025, "load_balance": 0.0009765629656612873, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.40244941785931587, "train_val_corr": 0.0} |
| {"t": 10, "ts": 1788064177.2608497, "step": 100, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0004036571190226823, "advantage": 0.5129812359809875, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765662252902985, "g_entropy": 3.465733051300049, "tau_bias": 0.6827874183654785, "beta": 0.3971490344653527, "train_val_corr": 0.0} |
| {"t": 11, "ts": 1788064180.6516466, "step": 110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723591376281547e-07, "advantage": 5.339087009429932, "attn_entropy": 3.465714454650879, "load_balance": 0.0009765875292941928, "g_entropy": 3.465714931488037, "tau_bias": 0.6827874183654785, "beta": 0.36107198397318524, "train_val_corr": 0.0} |
| {"t": 12, "ts": 1788064184.045402, "step": 120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.07233043170163e-07, "advantage": 0.357145220041275, "attn_entropy": 3.4657349586486816, "load_balance": 0.000976563896983862, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.370147039492925, "train_val_corr": 0.0} |
| {"t": 13, "ts": 1788064187.4500463, "step": 130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723270210964984e-07, "advantage": 0.8049210906028748, "attn_entropy": 3.4657068252563477, "load_balance": 0.0009766024304553866, "g_entropy": 3.465696334838867, "tau_bias": 0.6827874183654785, "beta": 0.366573844725887, "train_val_corr": 0.0} |
| {"t": 14, "ts": 1788064190.9136994, "step": 140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072326594770857e-07, "advantage": 3.3919293880462646, "attn_entropy": 3.4656827449798584, "load_balance": 0.0009766630828380585, "g_entropy": 3.465646743774414, "tau_bias": 0.6827874183654785, "beta": 0.3621972535426418, "train_val_corr": 0.0} |
| {"t": 15, "ts": 1788064194.3696837, "step": 150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 2.8862380981445312, "attn_entropy": 3.46571946144104, "load_balance": 0.0009765962604433298, "g_entropy": 3.465708017349243, "tau_bias": 0.6827874183654785, "beta": 0.33662276932348806, "train_val_corr": 0.0} |
| {"t": 16, "ts": 1788064197.7591145, "step": 160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -1.0972247123718262, "attn_entropy": 3.465714454650879, "load_balance": 0.0009766047587618232, "g_entropy": 3.4657013416290283, "tau_bias": 0.6827874183654785, "beta": 0.3453244051585595, "train_val_corr": 0.0} |
| {"t": 17, "ts": 1788064201.1332207, "step": 170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.6433818936347961, "attn_entropy": 3.4657349586486816, "load_balance": 0.000976563896983862, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.333378910087049, "train_val_corr": 0.0} |
| {"t": 18, "ts": 1788064204.5856376, "step": 180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.7547290921211243, "attn_entropy": 3.465559482574463, "load_balance": 0.0009768652962520719, "g_entropy": 3.465468168258667, "tau_bias": 0.6827874183654785, "beta": 0.3511454105998079, "train_val_corr": 0.0} |
| {"t": 19, "ts": 1788064208.0325737, "step": 190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.8870226740837097, "attn_entropy": 3.465705156326294, "load_balance": 0.0009766275761649013, "g_entropy": 3.4656784534454346, "tau_bias": 0.6827874183654785, "beta": 0.36920825329919654, "train_val_corr": 1.0} |
| {"t": 0, "ts": 1788064272.6446154, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.3965106010437012, "advantage": 6.150230884552002, "attn_entropy": 3.465726137161255, "load_balance": 0.0009765895083546638, "g_entropy": 3.4657163619995117, "tau_bias": 0.6999524235725403, "beta": 0.4997497859100501, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788064277.4829707, "step": 10, "action": "ATTN_META_ONLY", "entropy_pi": 0.43277978897094727, "advantage": 3.986206293106079, "attn_entropy": 3.465681552886963, "load_balance": 0.0009766446892172098, "g_entropy": 3.4656660556793213, "tau_bias": 0.6827874183654785, "beta": 0.48796860004464787, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788064280.8233538, "step": 20, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.42900341749191284, "advantage": 2.667457103729248, "attn_entropy": 3.4657349586486816, "load_balance": 0.000976563896983862, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.45504378403226536, "train_val_corr": 0.0} |
| {"t": 3, "ts": 1788064284.1560636, "step": 30, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.23094631731510162, "advantage": 2.4395856857299805, "attn_entropy": 3.465686321258545, "load_balance": 0.0009766557486727834, "g_entropy": 3.46565318107605, "tau_bias": 0.6827874183654785, "beta": 0.4218534504373868, "train_val_corr": 0.0} |
| {"t": 4, "ts": 1788064287.4641597, "step": 40, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.08378235250711441, "advantage": 3.4406511783599854, "attn_entropy": 3.465696334838867, "load_balance": 0.000976639916189015, "g_entropy": 3.4656686782836914, "tau_bias": 0.6827874183654785, "beta": 0.41006101481616497, "train_val_corr": 0.0} |
| {"t": 5, "ts": 1788064290.8458934, "step": 50, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.024425746873021126, "advantage": 1.53561532497406, "attn_entropy": 3.465733766555786, "load_balance": 0.000976563198491931, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.4412246240923802, "train_val_corr": 0.0} |
| {"t": 6, "ts": 1788064294.5324466, "step": 60, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.00788771640509367, "advantage": 0.8819096684455872, "attn_entropy": 3.465564727783203, "load_balance": 0.0009768615709617734, "g_entropy": 3.465465784072876, "tau_bias": 0.6827874183654785, "beta": 0.42499463135997456, "train_val_corr": 0.0} |
| {"t": 7, "ts": 1788064297.9369285, "step": 70, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0030015152879059315, "advantage": -0.13336920738220215, "attn_entropy": 3.465731143951416, "load_balance": 0.0009765659924596548, "g_entropy": 3.4657325744628906, "tau_bias": 0.6827874183654785, "beta": 0.4174178938070933, "train_val_corr": 0.0} |
| {"t": 8, "ts": 1788064301.3195128, "step": 80, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0013734034728258848, "advantage": 1.7500206232070923, "attn_entropy": 3.4657249450683594, "load_balance": 0.0009765754221007228, "g_entropy": 3.4657225608825684, "tau_bias": 0.6827874183654785, "beta": 0.40271858498454094, "train_val_corr": 0.0} |
| {"t": 9, "ts": 1788064304.663954, "step": 90, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0007402171031571925, "advantage": -0.5032905340194702, "attn_entropy": 3.4657347202301025, "load_balance": 0.0009765629656612873, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.40244941785931587, "train_val_corr": 0.0} |
| {"t": 10, "ts": 1788064308.036013, "step": 100, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 0.0004036571190226823, "advantage": 0.5129812359809875, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765662252902985, "g_entropy": 3.465733051300049, "tau_bias": 0.6827874183654785, "beta": 0.3971490344653527, "train_val_corr": 0.0} |
| {"t": 11, "ts": 1788064311.425271, "step": 110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723591376281547e-07, "advantage": 5.339087009429932, "attn_entropy": 3.465714454650879, "load_balance": 0.0009765875292941928, "g_entropy": 3.465714931488037, "tau_bias": 0.6827874183654785, "beta": 0.36107198397318524, "train_val_corr": 0.0} |
| {"t": 12, "ts": 1788064314.8217025, "step": 120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.07233043170163e-07, "advantage": 0.357145220041275, "attn_entropy": 3.4657349586486816, "load_balance": 0.000976563896983862, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.370147039492925, "train_val_corr": 0.0} |
| {"t": 13, "ts": 1788064318.2553504, "step": 130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723270210964984e-07, "advantage": 0.8049210906028748, "attn_entropy": 3.4657068252563477, "load_balance": 0.0009766024304553866, "g_entropy": 3.465696334838867, "tau_bias": 0.6827874183654785, "beta": 0.366573844725887, "train_val_corr": 0.0} |
| {"t": 14, "ts": 1788064321.5706663, "step": 140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072326594770857e-07, "advantage": 3.3919293880462646, "attn_entropy": 3.4656827449798584, "load_balance": 0.0009766630828380585, "g_entropy": 3.465646743774414, "tau_bias": 0.6827874183654785, "beta": 0.3621972535426418, "train_val_corr": 0.0} |
| {"t": 15, "ts": 1788064324.9841073, "step": 150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 2.8862380981445312, "attn_entropy": 3.46571946144104, "load_balance": 0.0009765962604433298, "g_entropy": 3.465708017349243, "tau_bias": 0.6827874183654785, "beta": 0.33662276932348806, "train_val_corr": 0.0} |
| {"t": 16, "ts": 1788064328.380048, "step": 160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -1.0972247123718262, "attn_entropy": 3.465714454650879, "load_balance": 0.0009766047587618232, "g_entropy": 3.4657013416290283, "tau_bias": 0.6827874183654785, "beta": 0.3453244051585595, "train_val_corr": 0.0} |
| {"t": 17, "ts": 1788064331.7334223, "step": 170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.6433818936347961, "attn_entropy": 3.4657349586486816, "load_balance": 0.000976563896983862, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.333378910087049, "train_val_corr": 0.0} |
| {"t": 18, "ts": 1788064335.1291394, "step": 180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.7547290921211243, "attn_entropy": 3.465559482574463, "load_balance": 0.0009768652962520719, "g_entropy": 3.465468168258667, "tau_bias": 0.6827874183654785, "beta": 0.3511454105998079, "train_val_corr": 0.0} |
| {"t": 19, "ts": 1788064338.4556794, "step": 190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.8870226740837097, "attn_entropy": 3.465705156326294, "load_balance": 0.0009766275761649013, "g_entropy": 3.4656784534454346, "tau_bias": 0.6827874183654785, "beta": 0.36920825329919654, "train_val_corr": 1.0} |
| {"t": 20, "ts": 1788064341.8267, "step": 200, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.7385338544845581, "attn_entropy": 3.465719223022461, "load_balance": 0.0009765817085281014, "g_entropy": 3.465718984603882, "tau_bias": 0.6827874183654785, "beta": 0.33207590505480766, "train_val_corr": 0.9999999999999996} |
| {"t": 21, "ts": 1788064345.0533624, "step": 210, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.9935973286628723, "attn_entropy": 3.4657340049743652, "load_balance": 0.00097656378056854, "g_entropy": 3.4657347202301025, "tau_bias": 0.6827874183654785, "beta": 0.3140322680895527, "train_val_corr": 1.0} |
| {"t": 22, "ts": 1788064348.2516894, "step": 220, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.9393198490142822, "attn_entropy": 3.4657058715820312, "load_balance": 0.0009766229195520282, "g_entropy": 3.4656827449798584, "tau_bias": 0.6827874183654785, "beta": 0.3133082911372185, "train_val_corr": 0.9999999999999998} |
| {"t": 23, "ts": 1788064351.53637, "step": 230, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.9193313717842102, "attn_entropy": 3.465684413909912, "load_balance": 0.0009766543516889215, "g_entropy": 3.4656553268432617, "tau_bias": 0.6827874183654785, "beta": 0.3284319043159485, "train_val_corr": 0.9999999999999999} |
| {"t": 24, "ts": 1788064354.7817256, "step": 240, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -1.195479393005371, "attn_entropy": 3.4657301902770996, "load_balance": 0.000976565876044333, "g_entropy": 3.4657320976257324, "tau_bias": 0.6827874183654785, "beta": 0.35506764737268287, "train_val_corr": 0.9999999999999998} |
| {"t": 25, "ts": 1788064358.034604, "step": 250, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.9781172275543213, "attn_entropy": 3.4656853675842285, "load_balance": 0.0009766536531969905, "g_entropy": 3.4656577110290527, "tau_bias": 0.6827874183654785, "beta": 0.34901463985443115, "train_val_corr": 0.9999999999999999} |
| {"t": 26, "ts": 1788064361.514351, "step": 260, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.9799543023109436, "attn_entropy": 3.465719699859619, "load_balance": 0.0009765955619513988, "g_entropy": 3.465707540512085, "tau_bias": 0.6827874183654785, "beta": 0.3714653110752503, "train_val_corr": 1.0} |
| {"t": 27, "ts": 1788064364.9201949, "step": 270, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.5776582360267639, "attn_entropy": 3.4657139778137207, "load_balance": 0.0009766052244231105, "g_entropy": 3.4656999111175537, "tau_bias": 0.6827874183654785, "beta": 0.345436276247104, "train_val_corr": 1.0} |
| {"t": 28, "ts": 1788064368.3390787, "step": 280, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.9507522583007812, "attn_entropy": 3.465668201446533, "load_balance": 0.0009766604052856565, "g_entropy": 3.4656424522399902, "tau_bias": 0.6827874183654785, "beta": 0.34194946226974327, "train_val_corr": 0.9999999999999999} |
| {"t": 29, "ts": 1788064371.6485767, "step": 290, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.6442179083824158, "attn_entropy": 3.4657278060913086, "load_balance": 0.000976573210209608, "g_entropy": 3.465724229812622, "tau_bias": 0.6827874183654785, "beta": 0.35318853333592415, "train_val_corr": 0.9999999999999998} |
| {"t": 30, "ts": 1788064374.9672031, "step": 300, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.5109460949897766, "attn_entropy": 3.4655842781066895, "load_balance": 0.0009768240852281451, "g_entropy": 3.4655039310455322, "tau_bias": 0.6827874183654785, "beta": 0.32971538230776787, "train_val_corr": 0.9999999999999999} |
| {"t": 31, "ts": 1788064379.051154, "step": 310, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.6130321025848389, "attn_entropy": 3.465731143951416, "load_balance": 0.0009765655267983675, "g_entropy": 3.4657323360443115, "tau_bias": 0.6827874183654785, "beta": 0.36919306591153145, "train_val_corr": 1.0} |
| {"t": 32, "ts": 1788064382.4756463, "step": 320, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 1.007981538772583, "attn_entropy": 3.4657132625579834, "load_balance": 0.0009766054572537541, "g_entropy": 3.465700149536133, "tau_bias": 0.6827874183654785, "beta": 0.32431560195982456, "train_val_corr": 1.0} |
| {"t": 33, "ts": 1788064385.9671574, "step": 330, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.496245414018631, "attn_entropy": 3.4657206535339355, "load_balance": 0.0009765789145603776, "g_entropy": 3.465721368789673, "tau_bias": 0.6827874183654785, "beta": 0.34092362225055695, "train_val_corr": 0.9999999999999994} |
| {"t": 34, "ts": 1788064389.425484, "step": 340, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.7375359535217285, "attn_entropy": 3.465684413909912, "load_balance": 0.0009766565635800362, "g_entropy": 3.4656548500061035, "tau_bias": 0.6827874183654785, "beta": 0.3776192981749773, "train_val_corr": 0.9999999999999998} |
| {"t": 35, "ts": 1788064392.8660567, "step": 350, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.7117959260940552, "attn_entropy": 3.4654903411865234, "load_balance": 0.0009769854368641973, "g_entropy": 3.465355157852173, "tau_bias": 0.6827874183654785, "beta": 0.36338008629779023, "train_val_corr": 1.0} |
| {"t": 36, "ts": 1788064396.3140268, "step": 360, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.7805131077766418, "attn_entropy": 3.4657320976257324, "load_balance": 0.0009765645954757929, "g_entropy": 3.465733289718628, "tau_bias": 0.6827874183654785, "beta": 0.3682893179357052, "train_val_corr": 1.0} |
| {"t": 37, "ts": 1788064399.7256587, "step": 370, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.7485364079475403, "attn_entropy": 3.4657065868377686, "load_balance": 0.0009765999857336283, "g_entropy": 3.4656975269317627, "tau_bias": 0.6827874183654785, "beta": 0.40214986602465314, "train_val_corr": 0.9999999999999998} |
| {"t": 38, "ts": 1788064403.1440017, "step": 380, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.32728293538093567, "attn_entropy": 3.465728521347046, "load_balance": 0.0009765694849193096, "g_entropy": 3.4657301902770996, "tau_bias": 0.6827874183654785, "beta": 0.35593203889826935, "train_val_corr": 1.0} |
| {"t": 39, "ts": 1788064406.6152146, "step": 390, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2903577983379364, "attn_entropy": 3.4657342433929443, "load_balance": 0.000976563896983862, "g_entropy": 3.4657349586486816, "tau_bias": 0.6827874183654785, "beta": 0.35119115995864075, "train_val_corr": 1.0} |
| {"t": 40, "ts": 1788064410.227623, "step": 400, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.7349421977996826, "attn_entropy": 3.4657297134399414, "load_balance": 0.0009765680879354477, "g_entropy": 3.4657304286956787, "tau_bias": 0.6827874183654785, "beta": 0.3984898713727792, "train_val_corr": 0.9999999999999999} |
| {"t": 41, "ts": 1788064413.6311257, "step": 410, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2386416494846344, "attn_entropy": 3.4656946659088135, "load_balance": 0.0009766480652615428, "g_entropy": 3.465660333633423, "tau_bias": 0.6827874183654785, "beta": 0.3828007411211729, "train_val_corr": 1.0} |
| {"t": 42, "ts": 1788064416.9658942, "step": 420, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.18966588377952576, "attn_entropy": 3.4656927585601807, "load_balance": 0.0009766204748302698, "g_entropy": 3.4656789302825928, "tau_bias": 0.6827874183654785, "beta": 0.3616393767297268, "train_val_corr": 1.0} |
| {"t": 43, "ts": 1788064420.357888, "step": 430, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.6056281924247742, "attn_entropy": 3.465733051300049, "load_balance": 0.000976569252088666, "g_entropy": 3.4657301902770996, "tau_bias": 0.6827874183654785, "beta": 0.38901051009694737, "train_val_corr": 1.0} |
| {"t": 44, "ts": 1788064423.7557223, "step": 440, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3426635265350342, "attn_entropy": 3.465731620788574, "load_balance": 0.0009765648283064365, "g_entropy": 3.465733289718628, "tau_bias": 0.6827874183654785, "beta": 0.3756866604089737, "train_val_corr": 0.9999999999999999} |
| {"t": 45, "ts": 1788064427.1510894, "step": 450, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.38312458992004395, "attn_entropy": 3.465719223022461, "load_balance": 0.0009765997529029846, "g_entropy": 3.465703010559082, "tau_bias": 0.6827874183654785, "beta": 0.40426554158329964, "train_val_corr": 1.0} |
| {"t": 46, "ts": 1788064430.5461602, "step": 460, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.25971969962120056, "attn_entropy": 3.4656591415405273, "load_balance": 0.000976701732724905, "g_entropy": 3.4656126499176025, "tau_bias": 0.6827874183654785, "beta": 0.3682354961832364, "train_val_corr": 1.0} |
| {"t": 47, "ts": 1788064434.026201, "step": 470, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.5266053676605225, "attn_entropy": 3.465721607208252, "load_balance": 0.0009765801951289177, "g_entropy": 3.465719699859619, "tau_bias": 0.6827874183654785, "beta": 0.39809969440102577, "train_val_corr": 1.0} |
| {"t": 48, "ts": 1788064437.5749788, "step": 480, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.03914675489068031, "attn_entropy": 3.465708017349243, "load_balance": 0.0009766191942617297, "g_entropy": 3.465686798095703, "tau_bias": 0.6827874183654785, "beta": 0.39972827148934204, "train_val_corr": 1.0} |
| {"t": 49, "ts": 1788064441.07369, "step": 490, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.34376174211502075, "attn_entropy": 3.4656782150268555, "load_balance": 0.0009766671573743224, "g_entropy": 3.4656472206115723, "tau_bias": 0.6827874183654785, "beta": 0.4144493502875169, "train_val_corr": 1.0} |
| {"t": 50, "ts": 1788064444.6455555, "step": 500, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1928202509880066, "attn_entropy": 3.4657139778137207, "load_balance": 0.000976588111370802, "g_entropy": 3.465712308883667, "tau_bias": 0.6827874183654785, "beta": 0.4087384467323621, "train_val_corr": 1.0} |
| {"t": 51, "ts": 1788064448.1140504, "step": 510, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.14315280318260193, "attn_entropy": 3.4657063484191895, "load_balance": 0.0009766194270923734, "g_entropy": 3.4656877517700195, "tau_bias": 0.6827874183654785, "beta": 0.40398559098442394, "train_val_corr": 1.0} |
| {"t": 52, "ts": 1788064451.5587156, "step": 520, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3601071238517761, "attn_entropy": 3.4657256603240967, "load_balance": 0.0009765728609636426, "g_entropy": 3.4657254219055176, "tau_bias": 0.6827874183654785, "beta": 0.4053203960259755, "train_val_corr": 0.9999999999999999} |
| {"t": 53, "ts": 1788064455.0834465, "step": 530, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.18293601274490356, "attn_entropy": 3.465686082839966, "load_balance": 0.0009766274597495794, "g_entropy": 3.465672731399536, "tau_bias": 0.6827874183654785, "beta": 0.3897963557392359, "train_val_corr": 1.0} |
| {"t": 54, "ts": 1788064458.61463, "step": 540, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.4649839699268341, "attn_entropy": 3.4656941890716553, "load_balance": 0.0009766179136931896, "g_entropy": 3.4656829833984375, "tau_bias": 0.6827874183654785, "beta": 0.4091953883568446, "train_val_corr": 1.0} |
| {"t": 55, "ts": 1788064462.130069, "step": 550, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.29352858662605286, "attn_entropy": 3.4657256603240967, "load_balance": 0.0009765729773789644, "g_entropy": 3.4657254219055176, "tau_bias": 0.6827874183654785, "beta": 0.4157894589006901, "train_val_corr": 0.9999999999999999} |
| {"t": 56, "ts": 1788064465.6280622, "step": 560, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2960616946220398, "attn_entropy": 3.465730905532837, "load_balance": 0.0009765664581209421, "g_entropy": 3.465733051300049, "tau_bias": 0.6827874183654785, "beta": 0.40395809275408584, "train_val_corr": 0.9999999999999997} |
| {"t": 57, "ts": 1788064469.120896, "step": 570, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.008964287117123604, "attn_entropy": 3.4657275676727295, "load_balance": 0.0009765838040038943, "g_entropy": 3.465717315673828, "tau_bias": 0.6827874183654785, "beta": 0.40184684842824936, "train_val_corr": 1.0} |
| {"t": 58, "ts": 1788064472.6643505, "step": 580, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.21685856580734253, "attn_entropy": 3.4654626846313477, "load_balance": 0.0009770211763679981, "g_entropy": 3.465327024459839, "tau_bias": 0.6827874183654785, "beta": 0.41539520273605984, "train_val_corr": 1.0} |
| {"t": 59, "ts": 1788064476.1256175, "step": 590, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.34286561608314514, "attn_entropy": 3.465721368789673, "load_balance": 0.0009765782160684466, "g_entropy": 3.46572208404541, "tau_bias": 0.6827874183654785, "beta": 0.40106676146388054, "train_val_corr": 1.0} |
| {"t": 60, "ts": 1788064479.5835273, "step": 600, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2689277231693268, "attn_entropy": 3.4657204151153564, "load_balance": 0.000976594164967537, "g_entropy": 3.465710163116455, "tau_bias": 0.6827874183654785, "beta": 0.4296191098789374, "train_val_corr": 0.9999999999999999} |
| {"t": 61, "ts": 1788064483.0825946, "step": 610, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.21701475977897644, "attn_entropy": 3.4657273292541504, "load_balance": 0.0009765704162418842, "g_entropy": 3.465728759765625, "tau_bias": 0.6827874183654785, "beta": 0.4187115083138148, "train_val_corr": 1.0} |
| {"t": 62, "ts": 1788064486.54519, "step": 620, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3902035355567932, "attn_entropy": 3.4656643867492676, "load_balance": 0.00097669439855963, "g_entropy": 3.4656176567077637, "tau_bias": 0.6827874183654785, "beta": 0.42633839324116707, "train_val_corr": 1.0} |
| {"t": 63, "ts": 1788064490.0148473, "step": 630, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.32502198219299316, "attn_entropy": 3.4657042026519775, "load_balance": 0.0009766246657818556, "g_entropy": 3.4656851291656494, "tau_bias": 0.6827874183654785, "beta": 0.43753335004051525, "train_val_corr": 1.0} |
| {"t": 64, "ts": 1788064493.45351, "step": 640, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.005130372941493988, "attn_entropy": 3.4656057357788086, "load_balance": 0.000976795214228332, "g_entropy": 3.465533494949341, "tau_bias": 0.6827874183654785, "beta": 0.43148451422651607, "train_val_corr": 0.9999999999999999} |
| {"t": 65, "ts": 1788064496.9257991, "step": 650, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.28411269187927246, "attn_entropy": 3.4657278060913086, "load_balance": 0.0009765798458829522, "g_entropy": 3.465721845626831, "tau_bias": 0.6827874183654785, "beta": 0.44427646075685817, "train_val_corr": 1.0} |
| {"t": 66, "ts": 1788064500.4173236, "step": 660, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2553403377532959, "attn_entropy": 3.465730667114258, "load_balance": 0.0009765661088749766, "g_entropy": 3.4657323360443115, "tau_bias": 0.6827874183654785, "beta": 0.44645915056268376, "train_val_corr": 1.0} |
| {"t": 67, "ts": 1788064503.8451514, "step": 670, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.19228415191173553, "attn_entropy": 3.465686082839966, "load_balance": 0.0009766274597495794, "g_entropy": 3.465672731399536, "tau_bias": 0.6827874183654785, "beta": 0.4416886406640212, "train_val_corr": 1.0} |
| {"t": 68, "ts": 1788064507.3186274, "step": 680, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.19054992496967316, "attn_entropy": 3.4657301902770996, "load_balance": 0.0009765664581209421, "g_entropy": 3.465731382369995, "tau_bias": 0.6827874183654785, "beta": 0.4517577104270458, "train_val_corr": 1.0} |
| {"t": 69, "ts": 1788064510.7807271, "step": 690, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.31130528450012207, "attn_entropy": 3.465733289718628, "load_balance": 0.000976569950580597, "g_entropy": 3.4657299518585205, "tau_bias": 0.6827874183654785, "beta": 0.45001745720704395, "train_val_corr": 1.0} |
| {"t": 70, "ts": 1788064514.274979, "step": 700, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3287065029144287, "attn_entropy": 3.465733766555786, "load_balance": 0.0009765634313225746, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.44254425416390103, "train_val_corr": 0.9999999999999999} |
| {"t": 71, "ts": 1788064517.7542408, "step": 710, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.14191296696662903, "attn_entropy": 3.4656898975372314, "load_balance": 0.0009766496950760484, "g_entropy": 3.4656596183776855, "tau_bias": 0.6827874183654785, "beta": 0.4242607293029626, "train_val_corr": 0.9999999999999998} |
| {"t": 72, "ts": 1788064521.2437031, "step": 720, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.20020729303359985, "attn_entropy": 3.4656591415405273, "load_balance": 0.000976705108769238, "g_entropy": 3.4656083583831787, "tau_bias": 0.6827874183654785, "beta": 0.4268517481784026, "train_val_corr": 1.0} |
| {"t": 73, "ts": 1788064524.6617696, "step": 730, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.0430157370865345, "attn_entropy": 3.465688943862915, "load_balance": 0.0009766471339389682, "g_entropy": 3.4656643867492676, "tau_bias": 0.6827874183654785, "beta": 0.42372234786550206, "train_val_corr": 1.0} |
| {"t": 74, "ts": 1788064528.170578, "step": 740, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.010195963084697723, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765628492459655, "g_entropy": 3.465735912322998, "tau_bias": 0.6827874183654785, "beta": 0.43124905849496525, "train_val_corr": 1.0} |
| {"t": 75, "ts": 1788064531.680828, "step": 750, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.02018607407808304, "attn_entropy": 3.465686082839966, "load_balance": 0.0009766316507011652, "g_entropy": 3.465670585632324, "tau_bias": 0.6827874183654785, "beta": 0.4359078072011471, "train_val_corr": 1.0} |
| {"t": 76, "ts": 1788064535.1249433, "step": 760, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.19807560741901398, "attn_entropy": 3.4656901359558105, "load_balance": 0.0009766246657818556, "g_entropy": 3.465675115585327, "tau_bias": 0.6827874183654785, "beta": 0.439842422803243, "train_val_corr": 0.9999999999999998} |
| {"t": 77, "ts": 1788064538.5341275, "step": 770, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.04305761680006981, "attn_entropy": 3.4655537605285645, "load_balance": 0.0009768800809979439, "g_entropy": 3.4654510021209717, "tau_bias": 0.6827874183654785, "beta": 0.42814817527929944, "train_val_corr": 0.9999999999999998} |
| {"t": 78, "ts": 1788064541.9709914, "step": 780, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.12640869617462158, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765642462298274, "g_entropy": 3.4657347202301025, "tau_bias": 0.6827874183654785, "beta": 0.443157147616148, "train_val_corr": 1.0} |
| {"t": 79, "ts": 1788064545.5634701, "step": 790, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.11914430558681488, "attn_entropy": 3.4656896591186523, "load_balance": 0.0009766246657818556, "g_entropy": 3.465675115585327, "tau_bias": 0.6827874183654785, "beta": 0.4285976017514865, "train_val_corr": 1.0} |
| {"t": 80, "ts": 1788064549.029303, "step": 800, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.04266534745693207, "attn_entropy": 3.4657094478607178, "load_balance": 0.0009766148868948221, "g_entropy": 3.4656922817230225, "tau_bias": 0.6827874183654785, "beta": 0.43423860520124435, "train_val_corr": 1.0} |
| {"t": 81, "ts": 1788064552.4451993, "step": 810, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.16138535737991333, "attn_entropy": 3.465700387954712, "load_balance": 0.0009766113944351673, "g_entropy": 3.4656877517700195, "tau_bias": 0.6827874183654785, "beta": 0.4413350783288479, "train_val_corr": 0.9999999999999998} |
| {"t": 82, "ts": 1788064555.9206395, "step": 820, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.23217721283435822, "attn_entropy": 3.4657299518585205, "load_balance": 0.0009765673894435167, "g_entropy": 3.465731620788574, "tau_bias": 0.6827874183654785, "beta": 0.43135741849740344, "train_val_corr": 1.0} |
| {"t": 83, "ts": 1788064559.3204598, "step": 830, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.22197739779949188, "attn_entropy": 3.465731382369995, "load_balance": 0.0009765737922862172, "g_entropy": 3.465726852416992, "tau_bias": 0.6827874183654785, "beta": 0.4255206994712353, "train_val_corr": 1.0} |
| {"t": 84, "ts": 1788064562.7237928, "step": 840, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.43526673316955566, "attn_entropy": 3.465726375579834, "load_balance": 0.0009765704162418842, "g_entropy": 3.465728282928467, "tau_bias": 0.6827874183654785, "beta": 0.4283125214278698, "train_val_corr": 1.0} |
| {"t": 85, "ts": 1788064566.2513165, "step": 850, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.08031424134969711, "attn_entropy": 3.465601682662964, "load_balance": 0.0009767977753654122, "g_entropy": 3.4655280113220215, "tau_bias": 0.6827874183654785, "beta": 0.4398307551940282, "train_val_corr": 1.0} |
| {"t": 86, "ts": 1788064569.6416912, "step": 860, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.28272026777267456, "attn_entropy": 3.4657158851623535, "load_balance": 0.0009765842696651816, "g_entropy": 3.4657139778137207, "tau_bias": 0.6827874183654785, "beta": 0.43850549558798474, "train_val_corr": 0.9999999999999999} |
| {"t": 87, "ts": 1788064573.041927, "step": 870, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3408834934234619, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765629656612873, "g_entropy": 3.465735673904419, "tau_bias": 0.6827874183654785, "beta": 0.4569965936243534, "train_val_corr": 0.9999999999999999} |
| {"t": 88, "ts": 1788064576.463983, "step": 880, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.25710901618003845, "attn_entropy": 3.4657230377197266, "load_balance": 0.0009765906725078821, "g_entropy": 3.4657115936279297, "tau_bias": 0.6827874183654785, "beta": 0.46122919271389645, "train_val_corr": 1.0} |
| {"t": 89, "ts": 1788064579.8435428, "step": 890, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.2513127028942108, "attn_entropy": 3.4657020568847656, "load_balance": 0.0009766074363142252, "g_entropy": 3.465691089630127, "tau_bias": 0.6827874183654785, "beta": 0.4536662350098292, "train_val_corr": 1.0} |
| {"t": 90, "ts": 1788064583.2405124, "step": 900, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.09088271111249924, "attn_entropy": 3.465681552886963, "load_balance": 0.0009766359580680728, "g_entropy": 3.465665578842163, "tau_bias": 0.6827874183654785, "beta": 0.4632485881447792, "train_val_corr": 1.0} |
| {"t": 91, "ts": 1788064586.6194003, "step": 910, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.061410970985889435, "attn_entropy": 3.4656717777252197, "load_balance": 0.0009766570292413235, "g_entropy": 3.4656436443328857, "tau_bias": 0.6827874183654785, "beta": 0.4637119223674138, "train_val_corr": 1.0} |
| {"t": 92, "ts": 1788064590.025078, "step": 920, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.4150483012199402, "attn_entropy": 3.4657256603240967, "load_balance": 0.0009765845024958253, "g_entropy": 3.46571683883667, "tau_bias": 0.6827874183654785, "beta": 0.4571143177648385, "train_val_corr": 0.9999999999999998} |
| {"t": 93, "ts": 1788064593.469152, "step": 930, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.03283070772886276, "attn_entropy": 3.465731143951416, "load_balance": 0.0009765662252902985, "g_entropy": 3.465733051300049, "tau_bias": 0.6827874183654785, "beta": 0.4618874875207742, "train_val_corr": 1.0} |
| {"t": 94, "ts": 1788064596.9205492, "step": 940, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.07049116492271423, "attn_entropy": 3.4657206535339355, "load_balance": 0.0009765933500602841, "g_entropy": 3.4657106399536133, "tau_bias": 0.6827874183654785, "beta": 0.4601097454627355, "train_val_corr": 1.0} |
| {"t": 95, "ts": 1788064600.3451347, "step": 950, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1847286969423294, "attn_entropy": 3.4657082557678223, "load_balance": 0.0009766191942617297, "g_entropy": 3.465686798095703, "tau_bias": 0.6827874183654785, "beta": 0.46868743126591045, "train_val_corr": 1.0} |
| {"t": 96, "ts": 1788064603.8566542, "step": 960, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.0021949680522084236, "attn_entropy": 3.465733051300049, "load_balance": 0.0009765711147338152, "g_entropy": 3.465729236602783, "tau_bias": 0.6827874183654785, "beta": 0.47090208778778714, "train_val_corr": 1.0} |
| {"t": 97, "ts": 1788064607.338607, "step": 970, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.03603089973330498, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765627328306437, "g_entropy": 3.465735673904419, "tau_bias": 0.6827874183654785, "beta": 0.46313028906782466, "train_val_corr": 1.0} |
| {"t": 98, "ts": 1788064610.7463663, "step": 980, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.09213776886463165, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765654103830457, "g_entropy": 3.4657340049743652, "tau_bias": 0.6827874183654785, "beta": 0.4731232039630413, "train_val_corr": 1.0} |
| {"t": 99, "ts": 1788064614.328097, "step": 990, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.29084476828575134, "attn_entropy": 3.4656357765197754, "load_balance": 0.0009767403826117516, "g_entropy": 3.465578079223633, "tau_bias": 0.6827874183654785, "beta": 0.4731818065047264, "train_val_corr": 1.0} |
| {"t": 100, "ts": 1788064618.1849563, "step": 1000, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.0017990003107115626, "attn_entropy": 3.4656968116760254, "load_balance": 0.0009766373550519347, "g_entropy": 3.4656710624694824, "tau_bias": 0.6827874183654785, "beta": 0.4729238400856654, "train_val_corr": 1.0} |
| {"t": 101, "ts": 1788064621.737037, "step": 1010, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.08796868473291397, "attn_entropy": 3.4656777381896973, "load_balance": 0.0009766435250639915, "g_entropy": 3.4656543731689453, "tau_bias": 0.6827874183654785, "beta": 0.4743075097600619, "train_val_corr": 1.0} |
| {"t": 102, "ts": 1788064625.225169, "step": 1020, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1792883425951004, "attn_entropy": 3.4657180309295654, "load_balance": 0.0009765999857336283, "g_entropy": 3.4657037258148193, "tau_bias": 0.6827874183654785, "beta": 0.46158957357207936, "train_val_corr": 0.9999999999999998} |
| {"t": 103, "ts": 1788064628.7283475, "step": 1030, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.002586444141343236, "attn_entropy": 3.4656829833984375, "load_balance": 0.0009766590083017945, "g_entropy": 3.465653896331787, "tau_bias": 0.6827874183654785, "beta": 0.44676563516259193, "train_val_corr": 1.0} |
| {"t": 104, "ts": 1788064632.2197914, "step": 1040, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.16220812499523163, "attn_entropy": 3.4657251834869385, "load_balance": 0.0009765850845724344, "g_entropy": 3.46571683883667, "tau_bias": 0.6827874183654785, "beta": 0.4569696995119254, "train_val_corr": 0.9999999999999997} |
| {"t": 105, "ts": 1788064635.6834588, "step": 1050, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.0027884466107934713, "attn_entropy": 3.465729236602783, "load_balance": 0.0009765777504071593, "g_entropy": 3.4657227993011475, "tau_bias": 0.6827874183654785, "beta": 0.433777816593647, "train_val_corr": 0.9999999999999997} |
| {"t": 106, "ts": 1788064639.1599953, "step": 1060, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.09212933480739594, "attn_entropy": 3.4657108783721924, "load_balance": 0.0009765924187377095, "g_entropy": 3.4657068252563477, "tau_bias": 0.6827874183654785, "beta": 0.4293055248757203, "train_val_corr": 1.0} |
| {"t": 107, "ts": 1788064642.584492, "step": 1070, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.24079665541648865, "attn_entropy": 3.4657344818115234, "load_balance": 0.000976563896983862, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.4549347795546055, "train_val_corr": 0.9999999999999999} |
| {"t": 108, "ts": 1788064646.0750911, "step": 1080, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.981768012046814, "attn_entropy": 3.465724468231201, "load_balance": 0.0009765858994796872, "g_entropy": 3.465717077255249, "tau_bias": 0.6827874183654785, "beta": 0.42322382144629955, "train_val_corr": 0.9999999999999998} |
| {"t": 109, "ts": 1788064649.7673268, "step": 1090, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.22462353110313416, "attn_entropy": 3.4657299518585205, "load_balance": 0.0009765680879354477, "g_entropy": 3.4657304286956787, "tau_bias": 0.6827874183654785, "beta": 0.4437238598863284, "train_val_corr": 0.9999999999999998} |
| {"t": 110, "ts": 1788064653.440584, "step": 1100, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.18058530986309052, "attn_entropy": 3.4657351970672607, "load_balance": 0.0009765630820766091, "g_entropy": 3.465735673904419, "tau_bias": 0.6827874183654785, "beta": 0.45659111191829044, "train_val_corr": 1.0} |
| {"t": 111, "ts": 1788064656.9565012, "step": 1110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.2724873125553131, "attn_entropy": 3.465733051300049, "load_balance": 0.000976563896983862, "g_entropy": 3.4657344818115234, "tau_bias": 0.6827874183654785, "beta": 0.45024702077110607, "train_val_corr": 0.9999999999999998} |
| {"t": 112, "ts": 1788064660.5141015, "step": 1120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.4495542347431183, "attn_entropy": 3.4657347202301025, "load_balance": 0.0009765628492459655, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.4576938934624195, "train_val_corr": 1.0} |
| {"t": 113, "ts": 1788064664.08336, "step": 1130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.26367491483688354, "attn_entropy": 3.4657280445098877, "load_balance": 0.0009765702998265624, "g_entropy": 3.465728759765625, "tau_bias": 0.6827874183654785, "beta": 0.4551788965861003, "train_val_corr": 1.0} |
| {"t": 114, "ts": 1788064667.7127898, "step": 1140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.13339047133922577, "attn_entropy": 3.4656968116760254, "load_balance": 0.0009766340954229236, "g_entropy": 3.4656758308410645, "tau_bias": 0.6827874183654785, "beta": 0.46304934844374657, "train_val_corr": 1.0} |
| {"t": 115, "ts": 1788064671.5386665, "step": 1150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.13025689125061035, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765657596290112, "g_entropy": 3.465733528137207, "tau_bias": 0.6827874183654785, "beta": 0.46860069284836453, "train_val_corr": 1.0} |
| {"t": 116, "ts": 1788064675.2345073, "step": 1160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.1253555566072464, "attn_entropy": 3.465731620788574, "load_balance": 0.0009765649447217584, "g_entropy": 3.465733528137207, "tau_bias": 0.6827874183654785, "beta": 0.46532202512025833, "train_val_corr": 1.0} |
| {"t": 117, "ts": 1788064679.0263803, "step": 1170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.06404183059930801, "attn_entropy": 3.4656825065612793, "load_balance": 0.0009766636649146676, "g_entropy": 3.4656484127044678, "tau_bias": 0.6827874183654785, "beta": 0.4643540717661381, "train_val_corr": 0.9999999999999998} |
| {"t": 118, "ts": 1788064682.5811374, "step": 1180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.18419507145881653, "attn_entropy": 3.4657089710235596, "load_balance": 0.0009766140719875693, "g_entropy": 3.4656927585601807, "tau_bias": 0.6827874183654785, "beta": 0.45395489657918614, "train_val_corr": 0.9999999999999998} |
| {"t": 119, "ts": 1788064686.1437132, "step": 1190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1115054115653038, "attn_entropy": 3.465700149536133, "load_balance": 0.0009766300208866596, "g_entropy": 3.465679168701172, "tau_bias": 0.6827874183654785, "beta": 0.4473685162762801, "train_val_corr": 1.0} |
| {"t": 120, "ts": 1788064689.723727, "step": 1200, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.0827554389834404, "attn_entropy": 3.4656734466552734, "load_balance": 0.0009766784496605396, "g_entropy": 3.4656338691711426, "tau_bias": 0.6827874183654785, "beta": 0.4510260100166003, "train_val_corr": 1.0} |
| {"t": 121, "ts": 1788064693.3187027, "step": 1210, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.38932088017463684, "attn_entropy": 3.4657347202301025, "load_balance": 0.0009765657596290112, "g_entropy": 3.465733528137207, "tau_bias": 0.6827874183654785, "beta": 0.43855890010794, "train_val_corr": 1.0} |
| {"t": 122, "ts": 1788064696.9282598, "step": 1220, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.10248168557882309, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765633149072528, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.4572278435031573, "train_val_corr": 1.0} |
| {"t": 123, "ts": 1788064700.6291351, "step": 1230, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.03721442446112633, "attn_entropy": 3.465714454650879, "load_balance": 0.0009765883442014456, "g_entropy": 3.465712785720825, "tau_bias": 0.6827874183654785, "beta": 0.43120413770278293, "train_val_corr": 0.9999999999999997} |
| {"t": 124, "ts": 1788064704.2316167, "step": 1240, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.1696757823228836, "attn_entropy": 3.465589761734009, "load_balance": 0.000976813375018537, "g_entropy": 3.465512752532959, "tau_bias": 0.6827874183654785, "beta": 0.4437260602911313, "train_val_corr": 1.0} |
| {"t": 125, "ts": 1788064707.823951, "step": 1250, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2420753836631775, "attn_entropy": 3.4657227993011475, "load_balance": 0.0009765906725078821, "g_entropy": 3.4657115936279297, "tau_bias": 0.6827874183654785, "beta": 0.4351732445259889, "train_val_corr": 0.9999999999999998} |
| {"t": 126, "ts": 1788064711.3718882, "step": 1260, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.01733282394707203, "attn_entropy": 3.465724468231201, "load_balance": 0.0009765855502337217, "g_entropy": 3.465717315673828, "tau_bias": 0.6827874183654785, "beta": 0.451769075045983, "train_val_corr": 0.9999999999999997} |
| {"t": 127, "ts": 1788064714.9381046, "step": 1270, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.08763353526592255, "attn_entropy": 3.465729236602783, "load_balance": 0.0009765789145603776, "g_entropy": 3.46572208404541, "tau_bias": 0.6827874183654785, "beta": 0.42666035890579224, "train_val_corr": 0.9999999999999998} |
| {"t": 128, "ts": 1788064718.6327038, "step": 1280, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2469296157360077, "attn_entropy": 3.4656496047973633, "load_balance": 0.000976720592007041, "g_entropy": 3.4655942916870117, "tau_bias": 0.6827874183654785, "beta": 0.450008787214756, "train_val_corr": 0.9999999999999999} |
| {"t": 129, "ts": 1788064722.2280502, "step": 1290, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.5952051877975464, "attn_entropy": 3.465715169906616, "load_balance": 0.0009765870636329055, "g_entropy": 3.4657139778137207, "tau_bias": 0.6827874183654785, "beta": 0.45210429405172664, "train_val_corr": 1.0} |
| {"t": 130, "ts": 1788064725.7734487, "step": 1300, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1085255816578865, "attn_entropy": 3.4657294750213623, "load_balance": 0.0009765768190845847, "g_entropy": 3.465724468231201, "tau_bias": 0.6827874183654785, "beta": 0.4523769145210584, "train_val_corr": 0.9999999999999999} |
| {"t": 131, "ts": 1788064729.3163724, "step": 1310, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.41254910826683044, "attn_entropy": 3.4655303955078125, "load_balance": 0.0009769182652235031, "g_entropy": 3.465418577194214, "tau_bias": 0.6827874183654785, "beta": 0.4516809744139512, "train_val_corr": 0.9999999999999998} |
| {"t": 132, "ts": 1788064732.8513844, "step": 1320, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.009833362884819508, "attn_entropy": 3.465735673904419, "load_balance": 0.0009765634313225746, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.46056991443037987, "train_val_corr": 0.9999999999999999} |
| {"t": 133, "ts": 1788064736.516638, "step": 1330, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.1179906502366066, "attn_entropy": 3.4657235145568848, "load_balance": 0.0009765775175765157, "g_entropy": 3.4657225608825684, "tau_bias": 0.6827874183654785, "beta": 0.4521276814242204, "train_val_corr": 1.0} |
| {"t": 134, "ts": 1788064740.128959, "step": 1340, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2830069065093994, "attn_entropy": 3.465730905532837, "load_balance": 0.0009765751892700791, "g_entropy": 3.4657256603240967, "tau_bias": 0.6827874183654785, "beta": 0.46260349949200946, "train_val_corr": 0.9999999999999998} |
| {"t": 135, "ts": 1788064743.8314342, "step": 1350, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2685953676700592, "attn_entropy": 3.465552806854248, "load_balance": 0.0009768878808245063, "g_entropy": 3.465444564819336, "tau_bias": 0.6827874183654785, "beta": 0.46758022035161656, "train_val_corr": 1.0} |
| {"t": 136, "ts": 1788064747.4162996, "step": 1360, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1978834867477417, "attn_entropy": 3.4657256603240967, "load_balance": 0.0009765845024958253, "g_entropy": 3.46571683883667, "tau_bias": 0.6827874183654785, "beta": 0.4751618653535843, "train_val_corr": 1.0} |
| {"t": 137, "ts": 1788064750.9640617, "step": 1370, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.19222767651081085, "attn_entropy": 3.4657182693481445, "load_balance": 0.0009765834547579288, "g_entropy": 3.4657185077667236, "tau_bias": 0.6827874183654785, "beta": 0.4726291758318742, "train_val_corr": 0.9999999999999999} |
| {"t": 138, "ts": 1788064754.569064, "step": 1380, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.7475152015686035, "attn_entropy": 3.4657022953033447, "load_balance": 0.0009766252478584647, "g_entropy": 3.4656827449798584, "tau_bias": 0.6827874183654785, "beta": 0.4702263188858827, "train_val_corr": 1.0} |
| {"t": 139, "ts": 1788064758.2388039, "step": 1390, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.04111356660723686, "attn_entropy": 3.4657163619995117, "load_balance": 0.0009765898576006293, "g_entropy": 3.4657084941864014, "tau_bias": 0.6827874183654785, "beta": 0.4755131055911382, "train_val_corr": 1.0} |
| {"t": 140, "ts": 1788064761.882431, "step": 1400, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.16696111857891083, "attn_entropy": 3.465725898742676, "load_balance": 0.0009765736758708954, "g_entropy": 3.4657254219055176, "tau_bias": 0.6827874183654785, "beta": 0.47744617611169815, "train_val_corr": 1.0} |
| {"t": 141, "ts": 1788064765.6574223, "step": 1410, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.26772138476371765, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765627328306437, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.4728454140325387, "train_val_corr": 1.0} |
| {"t": 142, "ts": 1788064769.6539845, "step": 1420, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.27696692943573, "attn_entropy": 3.465719699859619, "load_balance": 0.000976581941358745, "g_entropy": 3.4657161235809326, "tau_bias": 0.6827874183654785, "beta": 0.47450151666998863, "train_val_corr": 1.0} |
| {"t": 143, "ts": 1788064773.6305795, "step": 1430, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.002909902948886156, "attn_entropy": 3.4657251834869385, "load_balance": 0.0009765868308022618, "g_entropy": 3.465714454650879, "tau_bias": 0.6827874183654785, "beta": 0.4658218075831731, "train_val_corr": 1.0} |
| {"t": 144, "ts": 1788064777.4596765, "step": 1440, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.6299518942832947, "attn_entropy": 3.465704917907715, "load_balance": 0.0009766221046447754, "g_entropy": 3.4656853675842285, "tau_bias": 0.6827874183654785, "beta": 0.4372681565582752, "train_val_corr": 1.0} |
| {"t": 145, "ts": 1788064781.4586098, "step": 1450, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.01938677579164505, "attn_entropy": 3.4654440879821777, "load_balance": 0.0009770620381459594, "g_entropy": 3.4652886390686035, "tau_bias": 0.6827874183654785, "beta": 0.45259423926472664, "train_val_corr": 1.0} |
| {"t": 146, "ts": 1788064785.2378285, "step": 1460, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.14373712241649628, "attn_entropy": 3.4657156467437744, "load_balance": 0.0009766020812094212, "g_entropy": 3.465703248977661, "tau_bias": 0.6827874183654785, "beta": 0.45231224969029427, "train_val_corr": 1.0} |
| {"t": 147, "ts": 1788064789.1413627, "step": 1470, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.16635338962078094, "attn_entropy": 3.4657351970672607, "load_balance": 0.0009765636641532183, "g_entropy": 3.4657344818115234, "tau_bias": 0.6827874183654785, "beta": 0.46614690000812214, "train_val_corr": 0.9999999999999998} |
| {"t": 148, "ts": 1788064793.1460128, "step": 1480, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.19940975308418274, "attn_entropy": 3.4657108783721924, "load_balance": 0.000976594164967537, "g_entropy": 3.4657044410705566, "tau_bias": 0.6827874183654785, "beta": 0.47083714976906776, "train_val_corr": 1.0} |
| {"t": 149, "ts": 1788064797.1368868, "step": 1490, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.03137271851301193, "attn_entropy": 3.465733766555786, "load_balance": 0.0009765636641532183, "g_entropy": 3.4657347202301025, "tau_bias": 0.6827874183654785, "beta": 0.4498376784225305, "train_val_corr": 0.9999999999999998} |
| {"t": 150, "ts": 1788064801.0533652, "step": 1500, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.2429044544696808, "attn_entropy": 3.4656717777252197, "load_balance": 0.0009766832226887345, "g_entropy": 3.465630054473877, "tau_bias": 0.6827874183654785, "beta": 0.44441615293423337, "train_val_corr": 0.9999999999999997} |
| {"t": 151, "ts": 1788064804.4468558, "step": 1510, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.18713197112083435, "attn_entropy": 3.465679883956909, "load_balance": 0.0009766394505277276, "g_entropy": 3.4656624794006348, "tau_bias": 0.6827874183654785, "beta": 0.4533064352969329, "train_val_corr": 1.0} |
| {"t": 152, "ts": 1788064807.8703434, "step": 1520, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.32566213607788086, "attn_entropy": 3.4657158851623535, "load_balance": 0.000976601499132812, "g_entropy": 3.4657034873962402, "tau_bias": 0.6827874183654785, "beta": 0.45284699896971387, "train_val_corr": 1.0} |
| {"t": 153, "ts": 1788064811.4310784, "step": 1530, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.13038130104541779, "attn_entropy": 3.4657294750213623, "load_balance": 0.0009765679715201259, "g_entropy": 3.465731382369995, "tau_bias": 0.6827874183654785, "beta": 0.43049737190206844, "train_val_corr": 1.0} |
| {"t": 154, "ts": 1788064814.9237032, "step": 1540, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.04242474213242531, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765627328306437, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.41618626688917476, "train_val_corr": 0.9999999999999997} |
| {"t": 155, "ts": 1788064818.3818758, "step": 1550, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.001020467490889132, "attn_entropy": 3.4657254219055176, "load_balance": 0.0009765858994796872, "g_entropy": 3.465716600418091, "tau_bias": 0.6827874183654785, "beta": 0.411369688808918, "train_val_corr": 1.0} |
| {"t": 156, "ts": 1788064821.8394551, "step": 1560, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.09717503935098648, "attn_entropy": 3.465723991394043, "load_balance": 0.0009765750728547573, "g_entropy": 3.4657249450683594, "tau_bias": 0.6827874183654785, "beta": 0.43607570479313534, "train_val_corr": 1.0} |
| {"t": 157, "ts": 1788064825.355063, "step": 1570, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.04631917178630829, "attn_entropy": 3.4656946659088135, "load_balance": 0.0009766407310962677, "g_entropy": 3.465670108795166, "tau_bias": 0.6827874183654785, "beta": 0.4301300955315431, "train_val_corr": 0.9999999999999998} |
| {"t": 158, "ts": 1788064829.014836, "step": 1580, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2924998104572296, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765634313225746, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.437656960139672, "train_val_corr": 1.0} |
| {"t": 159, "ts": 1788064832.6431599, "step": 1590, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.4301561117172241, "attn_entropy": 3.4656572341918945, "load_balance": 0.0009767155861482024, "g_entropy": 3.46559739112854, "tau_bias": 0.6827874183654785, "beta": 0.42447201162576675, "train_val_corr": 1.0} |
| {"t": 160, "ts": 1788064836.2356434, "step": 1600, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.21383610367774963, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765642462298274, "g_entropy": 3.4657342433929443, "tau_bias": 0.6827874183654785, "beta": 0.4409516056378682, "train_val_corr": 0.9999999999999998} |
| {"t": 161, "ts": 1788064839.8395066, "step": 1610, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.16552139818668365, "attn_entropy": 3.4655628204345703, "load_balance": 0.0009768666932359338, "g_entropy": 3.4654664993286133, "tau_bias": 0.6827874183654785, "beta": 0.4321834382911523, "train_val_corr": 0.9999999999999998} |
| {"t": 162, "ts": 1788064843.4510965, "step": 1620, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.570837676525116, "attn_entropy": 3.4657347202301025, "load_balance": 0.0009765627328306437, "g_entropy": 3.465735912322998, "tau_bias": 0.6827874183654785, "beta": 0.4398215102652709, "train_val_corr": 0.9999999999999998} |
| {"t": 163, "ts": 1788064847.122278, "step": 1630, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1485716551542282, "attn_entropy": 3.4657232761383057, "load_balance": 0.0009765761205926538, "g_entropy": 3.465723752975464, "tau_bias": 0.6827874183654785, "beta": 0.4475727279980977, "train_val_corr": 1.0} |
| {"t": 164, "ts": 1788064850.7367022, "step": 1640, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.01737542264163494, "attn_entropy": 3.4657351970672607, "load_balance": 0.0009765640133991838, "g_entropy": 3.4657347202301025, "tau_bias": 0.6827874183654785, "beta": 0.4572400314112504, "train_val_corr": 1.0} |
| {"t": 165, "ts": 1788064854.3674183, "step": 1650, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.026719549670815468, "attn_entropy": 3.4657344818115234, "load_balance": 0.000976563198491931, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.4644009744127591, "train_val_corr": 1.0} |
| {"t": 166, "ts": 1788064857.9602396, "step": 1660, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.04951103404164314, "attn_entropy": 3.465714693069458, "load_balance": 0.0009765883442014456, "g_entropy": 3.465712785720825, "tau_bias": 0.6827874183654785, "beta": 0.4611584072311719, "train_val_corr": 1.0} |
| {"t": 167, "ts": 1788064861.6156423, "step": 1670, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.0819038450717926, "attn_entropy": 3.465700149536133, "load_balance": 0.0009766131406649947, "g_entropy": 3.4656870365142822, "tau_bias": 0.6827874183654785, "beta": 0.455714621891578, "train_val_corr": 0.9999999999999999} |
| {"t": 168, "ts": 1788064865.2458954, "step": 1680, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.23699703812599182, "attn_entropy": 3.465733528137207, "load_balance": 0.0009765687864273787, "g_entropy": 3.465731143951416, "tau_bias": 0.6827874183654785, "beta": 0.46558379506071407, "train_val_corr": 0.9999999999999999} |
| {"t": 169, "ts": 1788064868.8534048, "step": 1690, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.26975172758102417, "attn_entropy": 3.4657347202301025, "load_balance": 0.0009765628492459655, "g_entropy": 3.465735912322998, "tau_bias": 0.6827874183654785, "beta": 0.46201281001170474, "train_val_corr": 0.9999999999999998} |
| {"t": 170, "ts": 1788064872.461249, "step": 1700, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.2662128806114197, "attn_entropy": 3.4656217098236084, "load_balance": 0.000976764364168048, "g_entropy": 3.4655587673187256, "tau_bias": 0.6827874183654785, "beta": 0.4521857847770055, "train_val_corr": 1.0} |
| {"t": 171, "ts": 1788064876.06468, "step": 1710, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723766169794544e-07, "advantage": -0.024124829098582268, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765628492459655, "g_entropy": 3.465735912322998, "tau_bias": 0.6827874183654785, "beta": 0.4489150382578373, "train_val_corr": 0.9999999999999999} |
| {"t": 172, "ts": 1788064879.6393626, "step": 1720, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.07237533800253e-07, "advantage": -0.251202791929245, "attn_entropy": 3.465712785720825, "load_balance": 0.0009765905560925603, "g_entropy": 3.4657089710235596, "tau_bias": 0.6827874183654785, "beta": 0.4487219676375389, "train_val_corr": 1.0} |
| {"t": 173, "ts": 1788064883.2742496, "step": 1730, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723835802982649e-07, "advantage": 0.2158113718032837, "attn_entropy": 3.4657273292541504, "load_balance": 0.0009765718132257462, "g_entropy": 3.4657278060913086, "tau_bias": 0.6827874183654785, "beta": 0.4156984823445479, "train_val_corr": 1.0} |
| {"t": 174, "ts": 1788064886.9387643, "step": 1740, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723750537854357e-07, "advantage": -0.10978222638368607, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765642462298274, "g_entropy": 3.4657347202301025, "tau_bias": 0.6827874183654785, "beta": 0.4466785242160161, "train_val_corr": 1.0} |
| {"t": 175, "ts": 1788064890.5598242, "step": 1750, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723813065615104e-07, "advantage": 0.8380187153816223, "attn_entropy": 3.465717077255249, "load_balance": 0.000976603478193283, "g_entropy": 3.46570086479187, "tau_bias": 0.6827874183654785, "beta": 0.4204261153936386, "train_val_corr": 0.9999999999999998} |
| {"t": 176, "ts": 1788064894.1776848, "step": 1760, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723805960187747e-07, "advantage": 0.052201468497514725, "attn_entropy": 3.465698719024658, "load_balance": 0.0009766132570803165, "g_entropy": 3.4656858444213867, "tau_bias": 0.6827874183654785, "beta": 0.43053710584839183, "train_val_corr": 1.0} |
| {"t": 177, "ts": 1788064897.7369814, "step": 1770, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723769011965487e-07, "advantage": -0.2041945457458496, "attn_entropy": 3.465561628341675, "load_balance": 0.0009768693707883358, "g_entropy": 3.465460777282715, "tau_bias": 0.6827874183654785, "beta": 0.4470687136054039, "train_val_corr": 1.0} |
| {"t": 178, "ts": 1788064901.3289554, "step": 1780, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723786064991145e-07, "advantage": 0.5694143176078796, "attn_entropy": 3.4657320976257324, "load_balance": 0.0009765670401975513, "g_entropy": 3.465731382369995, "tau_bias": 0.6827874183654785, "beta": 0.4336218535900116, "train_val_corr": 0.9999999999999998} |
| {"t": 179, "ts": 1788064904.8259768, "step": 1790, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723759064367187e-07, "advantage": -0.022628189995884895, "attn_entropy": 3.4657347202301025, "load_balance": 0.0009765630820766091, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.4394732241829236, "train_val_corr": 1.0} |
| {"t": 180, "ts": 1788064908.452915, "step": 1800, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723773275221902e-07, "advantage": -0.29891064763069153, "attn_entropy": 3.4657323360443115, "load_balance": 0.0009765714639797807, "g_entropy": 3.465728759765625, "tau_bias": 0.6827874183654785, "beta": 0.4413501185675462, "train_val_corr": 1.0} |
| {"t": 181, "ts": 1788064912.0426776, "step": 1810, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723740590256057e-07, "advantage": -0.18555401265621185, "attn_entropy": 3.4657349586486816, "load_balance": 0.000976563896983862, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.46091554934779805, "train_val_corr": 1.0} |
| {"t": 182, "ts": 1788064915.5443184, "step": 1820, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723831539726234e-07, "advantage": 0.2225903421640396, "attn_entropy": 3.4657111167907715, "load_balance": 0.0009765925351530313, "g_entropy": 3.4657068252563477, "tau_bias": 0.6827874183654785, "beta": 0.43802693113684654, "train_val_corr": 0.9999999999999998} |
| {"t": 183, "ts": 1788064919.1545858, "step": 1830, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.072382869755529e-07, "advantage": 0.12254434823989868, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765643626451492, "g_entropy": 3.4657347202301025, "tau_bias": 0.6827874183654785, "beta": 0.43870412434140843, "train_val_corr": 1.0} |
| {"t": 184, "ts": 1788064922.6553469, "step": 1840, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723764748709073e-07, "advantage": -0.06636510044336319, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765629656612873, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.45380424087246257, "train_val_corr": 1.0} |
| {"t": 185, "ts": 1788064926.175033, "step": 1850, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723759064367187e-07, "advantage": -0.035329077392816544, "attn_entropy": 3.4656991958618164, "load_balance": 0.0009766099974513054, "g_entropy": 3.4656929969787598, "tau_bias": 0.6827874183654785, "beta": 0.45396818220615387, "train_val_corr": 0.9999999999999998} |
| {"t": 186, "ts": 1788064929.6836116, "step": 1860, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723760485452658e-07, "advantage": -0.2204180359840393, "attn_entropy": 3.4657270908355713, "load_balance": 0.000976582057774067, "g_entropy": 3.4657199382781982, "tau_bias": 0.6827874183654785, "beta": 0.4617518099645774, "train_val_corr": 0.9999999999999997} |
| {"t": 187, "ts": 1788064933.2311614, "step": 1870, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723786064991145e-07, "advantage": -0.17154984176158905, "attn_entropy": 3.465731143951416, "load_balance": 0.0009765659924596548, "g_entropy": 3.4657325744628906, "tau_bias": 0.6827874183654785, "beta": 0.45718080177903175, "train_val_corr": 1.0} |
| {"t": 188, "ts": 1788064936.7774565, "step": 1880, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723776117392845e-07, "advantage": -0.10730176419019699, "attn_entropy": 3.465733528137207, "load_balance": 0.0009765640133991838, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.4611852963765462, "train_val_corr": 1.0} |
| {"t": 189, "ts": 1788064940.2653565, "step": 1890, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723749116768886e-07, "advantage": -0.06558559089899063, "attn_entropy": 3.465679168701172, "load_balance": 0.0009766428265720606, "g_entropy": 3.4656615257263184, "tau_bias": 0.6827874183654785, "beta": 0.46821553880969685, "train_val_corr": 0.9999999999999998} |
| {"t": 190, "ts": 1788064943.7518756, "step": 1900, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723815907786047e-07, "advantage": 0.031573861837387085, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765643626451492, "g_entropy": 3.4657347202301025, "tau_bias": 0.6827874183654785, "beta": 0.4509202030797799, "train_val_corr": 1.0} |
| {"t": 191, "ts": 1788064947.2384322, "step": 1910, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.1002141181725165e-07, "advantage": -0.21992740035057068, "attn_entropy": 3.465675115585327, "load_balance": 0.0009766765870153904, "g_entropy": 3.4656362533569336, "tau_bias": 0.6827874183654785, "beta": 0.4437060331304868, "train_val_corr": 1.0} |
| {"t": 192, "ts": 1788064950.7733588, "step": 1920, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0963439339993784e-07, "advantage": 0.22060483694076538, "attn_entropy": 3.4657211303710938, "load_balance": 0.0009765790309756994, "g_entropy": 3.465721368789673, "tau_bias": 0.6827874183654785, "beta": 0.4548121566573779, "train_val_corr": 1.0} |
| {"t": 193, "ts": 1788064954.4387124, "step": 1930, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0957868684945424e-07, "advantage": 0.0035962562542408705, "attn_entropy": 3.4657351970672607, "load_balance": 0.0009765627328306437, "g_entropy": 3.465735912322998, "tau_bias": 0.6827874183654785, "beta": 0.4534476076563199, "train_val_corr": 1.0} |
| {"t": 194, "ts": 1788064957.9561145, "step": 1940, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0956028379259806e-07, "advantage": -0.2507789433002472, "attn_entropy": 3.4657344818115234, "load_balance": 0.000976563896983862, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.4673336495955785, "train_val_corr": 0.9999999999999998} |
| {"t": 195, "ts": 1788064961.5385795, "step": 1950, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0980105830403772e-07, "advantage": -0.28040406107902527, "attn_entropy": 3.4657182693481445, "load_balance": 0.0009765994036570191, "g_entropy": 3.465705156326294, "tau_bias": 0.6827874183654785, "beta": 0.46189265449841815, "train_val_corr": 1.0} |
| {"t": 196, "ts": 1788064965.0517106, "step": 1960, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.099190083981739e-07, "advantage": 0.07957780361175537, "attn_entropy": 3.465616464614868, "load_balance": 0.0009767774026840925, "g_entropy": 3.465543270111084, "tau_bias": 0.6827874183654785, "beta": 0.4550172972182433, "train_val_corr": 1.0} |
| {"t": 197, "ts": 1788064968.8637328, "step": 1970, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0964620262020617e-07, "advantage": -0.2623690366744995, "attn_entropy": 3.4657278060913086, "load_balance": 0.0009765700669959188, "g_entropy": 3.465728998184204, "tau_bias": 0.6827874183654785, "beta": 0.47118186329801875, "train_val_corr": 1.0} |
| {"t": 198, "ts": 1788064972.4565926, "step": 1980, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0961326185897633e-07, "advantage": -0.17350280284881592, "attn_entropy": 3.4657135009765625, "load_balance": 0.0009766072034835815, "g_entropy": 3.4656994342803955, "tau_bias": 0.6827874183654785, "beta": 0.47294242804249126, "train_val_corr": 0.9999999999999998} |
| {"t": 199, "ts": 1788064976.1270564, "step": 1990, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0978228576495894e-07, "advantage": 0.027073033154010773, "attn_entropy": 3.4657297134399414, "load_balance": 0.0009765769354999065, "g_entropy": 3.465724468231201, "tau_bias": 0.6827874183654785, "beta": 0.4661207174261411, "train_val_corr": 1.0} |
| {"t": 200, "ts": 1788064980.0181532, "step": 2000, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0975693360014702e-07, "advantage": 0.04879835993051529, "attn_entropy": 3.465733051300049, "load_balance": 0.00097656378056854, "g_entropy": 3.4657349586486816, "tau_bias": 0.6827874183654785, "beta": 0.47077441588044167, "train_val_corr": 1.0} |
| {"t": 201, "ts": 1788064983.6830652, "step": 2010, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.2165873758694943e-07, "advantage": 0.03135708346962929, "attn_entropy": 3.465724229812622, "load_balance": 0.0009765872964635491, "g_entropy": 3.4657154083251953, "tau_bias": 0.6827874183654785, "beta": 0.46359503890077275, "train_val_corr": 0.9999999999999998} |
| {"t": 202, "ts": 1788064987.2183127, "step": 2020, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.205796789667147e-07, "advantage": 0.04282089322805405, "attn_entropy": 3.465731143951416, "load_balance": 0.000976565876044333, "g_entropy": 3.4657325744628906, "tau_bias": 0.6827874183654785, "beta": 0.4680071858068307, "train_val_corr": 1.0} |
| {"t": 203, "ts": 1788064990.7579565, "step": 2030, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.2243473551952775e-07, "advantage": 0.01627657376229763, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765645954757929, "g_entropy": 3.4657340049743652, "tau_bias": 0.6827874183654785, "beta": 0.4621809385716915, "train_val_corr": 0.9999999999999998} |
| {"t": 204, "ts": 1788064994.5714014, "step": 2040, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.217409615923316e-07, "advantage": -0.08395959436893463, "attn_entropy": 3.4657092094421387, "load_balance": 0.0009765997529029846, "g_entropy": 3.465701103210449, "tau_bias": 0.6827874183654785, "beta": 0.4559035549561183, "train_val_corr": 0.9999999999999998} |
| {"t": 205, "ts": 1788064998.4867294, "step": 2050, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.2377221853275842e-07, "advantage": 0.07966841757297516, "attn_entropy": 3.4654951095581055, "load_balance": 0.0009769764728844166, "g_entropy": 3.46536922454834, "tau_bias": 0.6827874183654785, "beta": 0.447163850069046, "train_val_corr": 1.0} |
| {"t": 206, "ts": 1788065001.8806243, "step": 2060, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.2310473468678538e-07, "advantage": -0.04563966393470764, "attn_entropy": 3.46572208404541, "load_balance": 0.0009765905560925603, "g_entropy": 3.465712785720825, "tau_bias": 0.6827874183654785, "beta": 0.4457642783721288, "train_val_corr": 1.0} |
| {"t": 207, "ts": 1788065005.6400566, "step": 2070, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.2156520174121397e-07, "advantage": -0.08771983534097672, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765634313225746, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.4647180065512657, "train_val_corr": 1.0} |
| {"t": 208, "ts": 1788065009.085396, "step": 2080, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.2185160730714415e-07, "advantage": -0.1213865801692009, "attn_entropy": 3.4657182693481445, "load_balance": 0.0009765996364876628, "g_entropy": 3.465705156326294, "tau_bias": 0.6827874183654785, "beta": 0.46480708569288254, "train_val_corr": 1.0} |
| {"t": 209, "ts": 1788065012.5771995, "step": 2090, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.2121648157735763e-07, "advantage": -0.2508995831012726, "attn_entropy": 3.4657278060913086, "load_balance": 0.0009765706490725279, "g_entropy": 3.4657280445098877, "tau_bias": 0.6827874183654785, "beta": 0.47202831382552785, "train_val_corr": 0.9999999999999996} |
| {"t": 210, "ts": 1788065016.0359204, "step": 2100, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.2178615211032593e-07, "advantage": 0.1718491166830063, "attn_entropy": 3.465728998184204, "load_balance": 0.0009765776339918375, "g_entropy": 3.465724229812622, "tau_bias": 0.6827874183654785, "beta": 0.4641746406753858, "train_val_corr": 1.0} |
| {"t": 211, "ts": 1788065019.5240052, "step": 2110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.3986839892131684e-07, "advantage": 0.016598721966147423, "attn_entropy": 3.4656460285186768, "load_balance": 0.000976723269559443, "g_entropy": 3.465595006942749, "tau_bias": 0.6827874183654785, "beta": 0.4669988974928856, "train_val_corr": 1.0} |
| {"t": 212, "ts": 1788065023.0271292, "step": 2120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.408761474725907e-07, "advantage": -0.07396677881479263, "attn_entropy": 3.4657201766967773, "load_balance": 0.000976582057774067, "g_entropy": 3.4657163619995117, "tau_bias": 0.6827874183654785, "beta": 0.4694293874005477, "train_val_corr": 1.0} |
| {"t": 213, "ts": 1788065026.6193595, "step": 2130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.3569991469685192e-07, "advantage": -0.12291886657476425, "attn_entropy": 3.4657201766967773, "load_balance": 0.000976579380221665, "g_entropy": 3.4657208919525146, "tau_bias": 0.6827874183654785, "beta": 0.4733496842284997, "train_val_corr": 0.9999999999999998} |
| {"t": 214, "ts": 1788065029.9515798, "step": 2140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.389730013874214e-07, "advantage": -0.1592530906200409, "attn_entropy": 3.465707302093506, "load_balance": 0.000976618379354477, "g_entropy": 3.4656877517700195, "tau_bias": 0.6827874183654785, "beta": 0.4801686530311902, "train_val_corr": 0.9999999999999998} |
| {"t": 215, "ts": 1788065033.388353, "step": 2150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.411433399629459e-07, "advantage": 0.4314922094345093, "attn_entropy": 3.465729236602783, "load_balance": 0.0009765701834112406, "g_entropy": 3.4657275676727295, "tau_bias": 0.6827874183654785, "beta": 0.4794842451810837, "train_val_corr": 1.0} |
| {"t": 216, "ts": 1788065036.9184225, "step": 2160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.3651250558032189e-07, "advantage": -0.13573433458805084, "attn_entropy": 3.4656291007995605, "load_balance": 0.0009767516748979688, "g_entropy": 3.4655697345733643, "tau_bias": 0.6827874183654785, "beta": 0.4813782771428426, "train_val_corr": 1.0} |
| {"t": 217, "ts": 1788065040.6453483, "step": 2170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.4150244826159906e-07, "advantage": 0.09427055716514587, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765652939677238, "g_entropy": 3.4657340049743652, "tau_bias": 0.6827874183654785, "beta": 0.4838824160397053, "train_val_corr": 1.0} |
| {"t": 218, "ts": 1788065044.2559032, "step": 2180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.3787184488810453e-07, "advantage": -0.04417243227362633, "attn_entropy": 3.465664863586426, "load_balance": 0.000976693001575768, "g_entropy": 3.4656190872192383, "tau_bias": 0.6827874183654785, "beta": 0.48702559247612953, "train_val_corr": 1.0} |
| {"t": 219, "ts": 1788065047.8670282, "step": 2190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.3608143351339095e-07, "advantage": -0.0071738893166184425, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765627328306437, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.4858642655114333, "train_val_corr": 0.9999999999999998} |
| {"t": 220, "ts": 1788065051.5661054, "step": 2200, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.377537526854212e-07, "advantage": -0.14669758081436157, "attn_entropy": 3.465698719024658, "load_balance": 0.0009766314178705215, "g_entropy": 3.465679407119751, "tau_bias": 0.6827874183654785, "beta": 0.4874942973256111, "train_val_corr": 1.0} |
| {"t": 221, "ts": 1788065055.28024, "step": 2210, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.343407032867617e-07, "advantage": 0.12264572829008102, "attn_entropy": 3.4657304286956787, "load_balance": 0.0009765673894435167, "g_entropy": 3.465731143951416, "tau_bias": 0.6827874183654785, "beta": 0.49061331152915955, "train_val_corr": 0.9999999999999998} |
| {"t": 222, "ts": 1788065058.954282, "step": 2220, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.3711588426067465e-07, "advantage": -0.012763550505042076, "attn_entropy": 3.4657251834869385, "load_balance": 0.0009765854338184, "g_entropy": 3.465717315673828, "tau_bias": 0.6827874183654785, "beta": 0.4877839982509613, "train_val_corr": 1.0} |
| {"t": 223, "ts": 1788065062.3634176, "step": 2230, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.3713833741112467e-07, "advantage": 0.09768354892730713, "attn_entropy": 3.4656894207000732, "load_balance": 0.000976627692580223, "g_entropy": 3.4656736850738525, "tau_bias": 0.6827874183654785, "beta": 0.48727546632289886, "train_val_corr": 1.0} |
| {"t": 224, "ts": 1788065065.8498547, "step": 2240, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.397230787209992e-07, "advantage": 0.1906396746635437, "attn_entropy": 3.465733289718628, "load_balance": 0.000976564479060471, "g_entropy": 3.4657347202301025, "tau_bias": 0.6827874183654785, "beta": 0.4709380231797695, "train_val_corr": 1.0} |
| {"t": 225, "ts": 1788065069.3313391, "step": 2250, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.3682918026679545e-07, "advantage": -0.17518702149391174, "attn_entropy": 3.4656121730804443, "load_balance": 0.0009767877636477351, "g_entropy": 3.465538740158081, "tau_bias": 0.6827874183654785, "beta": 0.4669017605483532, "train_val_corr": 0.9999999999999998} |
| {"t": 226, "ts": 1788065072.927025, "step": 2260, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.375725927095118e-07, "advantage": -0.14378708600997925, "attn_entropy": 3.4657299518585205, "load_balance": 0.000976567156612873, "g_entropy": 3.4657301902770996, "tau_bias": 0.6827874183654785, "beta": 0.46558861061930656, "train_val_corr": 1.0} |
| {"t": 227, "ts": 1788065076.365205, "step": 2270, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.3968829054865637e-07, "advantage": -0.23518787324428558, "attn_entropy": 3.465636968612671, "load_balance": 0.0009767408482730389, "g_entropy": 3.465578079223633, "tau_bias": 0.6827874183654785, "beta": 0.45059310893217724, "train_val_corr": 0.9999999999999999} |
| {"t": 228, "ts": 1788065079.8259494, "step": 2280, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.3649873526210285e-07, "advantage": -0.04208465293049812, "attn_entropy": 3.4656882286071777, "load_balance": 0.0009766517905518413, "g_entropy": 3.4656567573547363, "tau_bias": 0.6827874183654785, "beta": 0.45410003885626793, "train_val_corr": 0.9999999999999997} |
| {"t": 229, "ts": 1788065083.3366098, "step": 2290, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.3756409461839212e-07, "advantage": 0.10417430847883224, "attn_entropy": 3.4653446674346924, "load_balance": 0.0009772273479029536, "g_entropy": 3.4651360511779785, "tau_bias": 0.6827874183654785, "beta": 0.4616142436861992, "train_val_corr": 0.9999999999999998} |
| {"t": 230, "ts": 1788065086.9538236, "step": 2300, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.3570693485908123e-07, "advantage": -0.20490293204784393, "attn_entropy": 3.4656906127929688, "load_balance": 0.0009766500443220139, "g_entropy": 3.4656596183776855, "tau_bias": 0.6827874183654785, "beta": 0.46686989565690357, "train_val_corr": 0.9999999999999998} |
| {"t": 231, "ts": 1788065090.7459776, "step": 2310, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5722710006448324e-07, "advantage": 0.21343465149402618, "attn_entropy": 3.465710401535034, "load_balance": 0.000976593466475606, "g_entropy": 3.465707302093506, "tau_bias": 0.6827874183654785, "beta": 0.4613804332911968, "train_val_corr": 1.0} |
| {"t": 232, "ts": 1788065094.3135545, "step": 2320, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5882738441396214e-07, "advantage": 0.28820520639419556, "attn_entropy": 3.465728521347046, "load_balance": 0.0009765804279595613, "g_entropy": 3.4657204151153564, "tau_bias": 0.6827874183654785, "beta": 0.461506233861049, "train_val_corr": 0.9999999999999999} |
| {"t": 233, "ts": 1788065097.9182212, "step": 2330, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.504670248981711e-07, "advantage": 0.2561437487602234, "attn_entropy": 3.465730667114258, "load_balance": 0.0009765757713466883, "g_entropy": 3.465726137161255, "tau_bias": 0.6827874183654785, "beta": 0.46651827171444893, "train_val_corr": 1.0} |
| {"t": 234, "ts": 1788065101.432391, "step": 2340, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.505593954538199e-07, "advantage": -0.2804209291934967, "attn_entropy": 3.465733528137207, "load_balance": 0.0009765640133991838, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.47348035126924515, "train_val_corr": 0.9999999999999997} |
| {"t": 235, "ts": 1788065104.9838512, "step": 2350, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.523347575333901e-07, "advantage": -0.005635123699903488, "attn_entropy": 3.4657325744628906, "load_balance": 0.000976564479060471, "g_entropy": 3.4657340049743652, "tau_bias": 0.6827874183654785, "beta": 0.4679368461171786, "train_val_corr": 0.9999999999999999} |
| {"t": 236, "ts": 1788065108.5275865, "step": 2360, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.518482915547793e-07, "advantage": 0.06928130239248276, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765662252902985, "g_entropy": 3.465733289718628, "tau_bias": 0.6827874183654785, "beta": 0.47848551099499065, "train_val_corr": 1.0} |
| {"t": 237, "ts": 1788065112.2449584, "step": 2370, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.500435130059486e-07, "advantage": 0.0871732234954834, "attn_entropy": 3.465707302093506, "load_balance": 0.0009766184957697988, "g_entropy": 3.4656877517700195, "tau_bias": 0.6827874183654785, "beta": 0.47809973731637, "train_val_corr": 0.9999999999999999} |
| {"t": 238, "ts": 1788065115.9410305, "step": 2380, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5486122012807755e-07, "advantage": -0.02457631751894951, "attn_entropy": 3.465717315673828, "load_balance": 0.0009766005678102374, "g_entropy": 3.4657039642333984, "tau_bias": 0.6827874183654785, "beta": 0.4717074930667877, "train_val_corr": 1.0} |
| {"t": 239, "ts": 1788065119.9420624, "step": 2390, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5211224397025944e-07, "advantage": -0.07012975960969925, "attn_entropy": 3.4657249450683594, "load_balance": 0.0009765855502337217, "g_entropy": 3.46571683883667, "tau_bias": 0.6827874183654785, "beta": 0.475323145588239, "train_val_corr": 1.0} |
| {"t": 240, "ts": 1788065123.4357417, "step": 2400, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.568103525391052e-07, "advantage": 0.3465483784675598, "attn_entropy": 3.4657278060913086, "load_balance": 0.0009765704162418842, "g_entropy": 3.465728759765625, "tau_bias": 0.6827874183654785, "beta": 0.4682985916733742, "train_val_corr": 0.9999999999999999} |
| {"t": 241, "ts": 1788065127.124565, "step": 2410, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5854927798718563e-07, "advantage": -0.26340508460998535, "attn_entropy": 3.465726852416992, "load_balance": 0.0009765714639797807, "g_entropy": 3.465726852416992, "tau_bias": 0.6827874183654785, "beta": 0.4618107092877229, "train_val_corr": 1.0} |
| {"t": 242, "ts": 1788065130.770106, "step": 2420, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.532565872570558e-07, "advantage": 0.012026093900203705, "attn_entropy": 3.4657256603240967, "load_balance": 0.0009765729773789644, "g_entropy": 3.4657254219055176, "tau_bias": 0.6827874183654785, "beta": 0.46628232921163243, "train_val_corr": 1.0} |
| {"t": 243, "ts": 1788065134.2809227, "step": 2430, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.6261923835591006e-07, "advantage": 0.031846415251493454, "attn_entropy": 3.4655330181121826, "load_balance": 0.0009769175667315722, "g_entropy": 3.465421199798584, "tau_bias": 0.6827874183654785, "beta": 0.4676028365890185, "train_val_corr": 1.0} |
| {"t": 244, "ts": 1788065137.7306244, "step": 2440, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.589601990621304e-07, "advantage": -0.06660982966423035, "attn_entropy": 3.4657235145568848, "load_balance": 0.0009765750728547573, "g_entropy": 3.4657249450683594, "tau_bias": 0.6827874183654785, "beta": 0.4570357029636701, "train_val_corr": 1.0} |
| {"t": 245, "ts": 1788065141.1762962, "step": 2450, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.581319336059096e-07, "advantage": -0.12560750544071198, "attn_entropy": 3.4657163619995117, "load_balance": 0.0009765843860805035, "g_entropy": 3.4657139778137207, "tau_bias": 0.6827874183654785, "beta": 0.4563496137658755, "train_val_corr": 1.0} |
| {"t": 246, "ts": 1788065144.7168293, "step": 2460, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5570489015080966e-07, "advantage": -0.07777968049049377, "attn_entropy": 3.465599775314331, "load_balance": 0.0009768069721758366, "g_entropy": 3.465519905090332, "tau_bias": 0.6827874183654785, "beta": 0.4606131973365943, "train_val_corr": 1.0} |
| {"t": 247, "ts": 1788065148.1247647, "step": 2470, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.596883916794468e-07, "advantage": -0.07886029034852982, "attn_entropy": 3.465721607208252, "load_balance": 0.0009765918366611004, "g_entropy": 3.465712547302246, "tau_bias": 0.6827874183654785, "beta": 0.4713559001684189, "train_val_corr": 0.9999999999999999} |
| {"t": 248, "ts": 1788065151.6269922, "step": 2480, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.554914431129873e-07, "advantage": -0.21665455400943756, "attn_entropy": 3.4656448364257812, "load_balance": 0.000976724666543305, "g_entropy": 3.4655942916870117, "tau_bias": 0.6827874183654785, "beta": 0.47214797139167786, "train_val_corr": 1.0} |
| {"t": 249, "ts": 1788065155.1261218, "step": 2490, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5766937028492976e-07, "advantage": -0.10327299684286118, "attn_entropy": 3.4657180309295654, "load_balance": 0.0009765984723344445, "g_entropy": 3.4657061100006104, "tau_bias": 0.6827874183654785, "beta": 0.46820178379615146, "train_val_corr": 0.9999999999999999} |
| {"t": 250, "ts": 1788065158.861873, "step": 2500, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5333739017696644e-07, "advantage": -0.25494882464408875, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765649447217584, "g_entropy": 3.4657344818115234, "tau_bias": 0.6827874183654785, "beta": 0.4802144678930442, "train_val_corr": 1.0} |
| {"t": 251, "ts": 1788065162.530587, "step": 2510, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5936361680578557e-07, "advantage": -0.19527089595794678, "attn_entropy": 3.465726613998413, "load_balance": 0.000976570532657206, "g_entropy": 3.465728282928467, "tau_bias": 0.6827874183654785, "beta": 0.46841754019260406, "train_val_corr": 1.0} |
| {"t": 252, "ts": 1788065166.238182, "step": 2520, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5635196720941167e-07, "advantage": -0.05599379166960716, "attn_entropy": 3.4657301902770996, "load_balance": 0.000976567273028195, "g_entropy": 3.4657325744628906, "tau_bias": 0.6827874183654785, "beta": 0.4768282324075699, "train_val_corr": 0.9999999999999999} |
| {"t": 253, "ts": 1788065169.9380145, "step": 2530, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5446141194152005e-07, "advantage": -0.0907755196094513, "attn_entropy": 3.4657092094421387, "load_balance": 0.0009766125585883856, "g_entropy": 3.4656944274902344, "tau_bias": 0.6827874183654785, "beta": 0.4807229960958163, "train_val_corr": 0.9999999999999998} |
| {"t": 254, "ts": 1788065173.5726674, "step": 2540, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.6271263209309836e-07, "advantage": 0.09038802981376648, "attn_entropy": 3.4654743671417236, "load_balance": 0.000977012445218861, "g_entropy": 3.4653358459472656, "tau_bias": 0.6827874183654785, "beta": 0.4770178149143855, "train_val_corr": 1.0} |
| {"t": 255, "ts": 1788065177.2340894, "step": 2550, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5435502948312205e-07, "advantage": -0.13908356428146362, "attn_entropy": 3.4657351970672607, "load_balance": 0.0009765626164153218, "g_entropy": 3.465735673904419, "tau_bias": 0.6827874183654785, "beta": 0.4804920442402363, "train_val_corr": 1.0} |
| {"t": 256, "ts": 1788065180.8762531, "step": 2560, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5702723860376864e-07, "advantage": 0.009330769069492817, "attn_entropy": 3.465665578842163, "load_balance": 0.000976698356680572, "g_entropy": 3.4656126499176025, "tau_bias": 0.6827874183654785, "beta": 0.47903449833393097, "train_val_corr": 0.9999999999999997} |
| {"t": 257, "ts": 1788065184.4668996, "step": 2570, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.602616859803675e-07, "advantage": -0.1436482071876526, "attn_entropy": 3.465733528137207, "load_balance": 0.0009765640133991838, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.4812890328466892, "train_val_corr": 1.0} |
| {"t": 258, "ts": 1788065188.1211722, "step": 2580, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.598702337763825e-07, "advantage": 0.02204107865691185, "attn_entropy": 3.4657130241394043, "load_balance": 0.0009765906725078821, "g_entropy": 3.4657089710235596, "tau_bias": 0.6827874183654785, "beta": 0.4760408004124959, "train_val_corr": 0.9999999999999998} |
| {"t": 259, "ts": 1788065191.8139827, "step": 2590, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.6419081677886425e-07, "advantage": 0.011911604553461075, "attn_entropy": 3.4657163619995117, "load_balance": 0.000976603594608605, "g_entropy": 3.465700387954712, "tau_bias": 0.6827874183654785, "beta": 0.474395003169775, "train_val_corr": 1.0} |
| {"t": 260, "ts": 1788065195.5499556, "step": 2600, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.5496984790152055e-07, "advantage": 0.09398873895406723, "attn_entropy": 3.4656686782836914, "load_balance": 0.0009766577277332544, "g_entropy": 3.4656481742858887, "tau_bias": 0.6827874183654785, "beta": 0.480871790399154, "train_val_corr": 1.0} |
| {"t": 261, "ts": 1788065199.1578798, "step": 2610, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.826237732733716e-07, "advantage": 0.28739434480667114, "attn_entropy": 3.4653897285461426, "load_balance": 0.0009771540062502027, "g_entropy": 3.4652152061462402, "tau_bias": 0.6827874183654785, "beta": 0.4763408787548542, "train_val_corr": 1.0} |
| {"t": 262, "ts": 1788065202.7842066, "step": 2620, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.8044320288245217e-07, "advantage": -0.031399186700582504, "attn_entropy": 3.4656853675842285, "load_balance": 0.000976658659055829, "g_entropy": 3.4656543731689453, "tau_bias": 0.6827874183654785, "beta": 0.47688569128513336, "train_val_corr": 0.9999999999999998} |
| {"t": 263, "ts": 1788065206.4406576, "step": 2630, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.854970659882383e-07, "advantage": -0.05376177281141281, "attn_entropy": 3.4657280445098877, "load_balance": 0.0009765702998265624, "g_entropy": 3.465728759765625, "tau_bias": 0.6827874183654785, "beta": 0.47196753198901814, "train_val_corr": 1.0} |
| {"t": 264, "ts": 1788065210.0879896, "step": 2640, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.8099967153139005e-07, "advantage": -0.13561220467090607, "attn_entropy": 3.4657323360443115, "load_balance": 0.000976573210209608, "g_entropy": 3.4657270908355713, "tau_bias": 0.6827874183654785, "beta": 0.4766352002819379, "train_val_corr": 1.0} |
| {"t": 265, "ts": 1788065213.860511, "step": 2650, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.7607478614299907e-07, "advantage": 0.14305824041366577, "attn_entropy": 3.4656009674072266, "load_balance": 0.000976803246885538, "g_entropy": 3.4655237197875977, "tau_bias": 0.6827874183654785, "beta": 0.47408221041162807, "train_val_corr": 0.9999999999999999} |
| {"t": 266, "ts": 1788065217.5278869, "step": 2660, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.8092722459405195e-07, "advantage": 0.019777420908212662, "attn_entropy": 3.4656810760498047, "load_balance": 0.000976663432084024, "g_entropy": 3.4656455516815186, "tau_bias": 0.6827874183654785, "beta": 0.4733673284451167, "train_val_corr": 1.0} |
| {"t": 267, "ts": 1788065221.1470973, "step": 2670, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.7759062959376024e-07, "advantage": 0.06965241581201553, "attn_entropy": 3.46573543548584, "load_balance": 0.000976563198491931, "g_entropy": 3.465735912322998, "tau_bias": 0.6827874183654785, "beta": 0.4786001183092594, "train_val_corr": 1.0} |
| {"t": 268, "ts": 1788065224.7442706, "step": 2680, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.809011050430854e-07, "advantage": -0.0739205852150917, "attn_entropy": 3.46573543548584, "load_balance": 0.000976563198491931, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.47343215843041736, "train_val_corr": 1.0} |
| {"t": 269, "ts": 1788065228.4342473, "step": 2690, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.837169290614838e-07, "advantage": 0.25415700674057007, "attn_entropy": 3.465733051300049, "load_balance": 0.0009765711147338152, "g_entropy": 3.465729236602783, "tau_bias": 0.6827874183654785, "beta": 0.46981297185023624, "train_val_corr": 0.9999999999999998} |
| {"t": 270, "ts": 1788065232.135055, "step": 2700, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.849530176263215e-07, "advantage": -0.06884058564901352, "attn_entropy": 3.465731620788574, "load_balance": 0.0009765670401975513, "g_entropy": 3.4657318592071533, "tau_bias": 0.6827874183654785, "beta": 0.466513279825449, "train_val_corr": 0.9999999999999998} |
| {"t": 271, "ts": 1788065235.8575003, "step": 2710, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.8303156796027906e-07, "advantage": -0.15914101898670197, "attn_entropy": 3.465649127960205, "load_balance": 0.0009767244337126613, "g_entropy": 3.465592622756958, "tau_bias": 0.6827874183654785, "beta": 0.4664857437213262, "train_val_corr": 1.0} |
| {"t": 272, "ts": 1788065239.3715737, "step": 2720, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.782081196528452e-07, "advantage": 0.6081835627555847, "attn_entropy": 3.465728998184204, "load_balance": 0.0009765683207660913, "g_entropy": 3.4657304286956787, "tau_bias": 0.6827874183654785, "beta": 0.46424250677227974, "train_val_corr": 1.0} |
| {"t": 273, "ts": 1788065242.955324, "step": 2730, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.8122627782067866e-07, "advantage": 0.16348177194595337, "attn_entropy": 3.4656765460968018, "load_balance": 0.0009766469011083245, "g_entropy": 3.4656577110290527, "tau_bias": 0.6827874183654785, "beta": 0.4720236286520958, "train_val_corr": 1.0} |
| {"t": 274, "ts": 1788065246.526158, "step": 2740, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.73315180265854e-07, "advantage": -0.07675337046384811, "attn_entropy": 3.4657351970672607, "load_balance": 0.000976563198491931, "g_entropy": 3.465735912322998, "tau_bias": 0.6827874183654785, "beta": 0.47634782269597054, "train_val_corr": 1.0} |
| {"t": 275, "ts": 1788065250.1150398, "step": 2750, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.7535853064364346e-07, "advantage": -0.11710375547409058, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765634313225746, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.47373737022280693, "train_val_corr": 0.9999999999999999} |
| {"t": 276, "ts": 1788065253.6612432, "step": 2760, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.8256422979211493e-07, "advantage": 0.17101888358592987, "attn_entropy": 3.4657108783721924, "load_balance": 0.0009766144212335348, "g_entropy": 3.465691328048706, "tau_bias": 0.6827874183654785, "beta": 0.46438589816292125, "train_val_corr": 1.0} |
| {"t": 277, "ts": 1788065257.263786, "step": 2770, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.787298569728591e-07, "advantage": 0.002128107938915491, "attn_entropy": 3.465726613998413, "load_balance": 0.0009765720460563898, "g_entropy": 3.4657270908355713, "tau_bias": 0.6827874183654785, "beta": 0.47494164605935413, "train_val_corr": 1.0} |
| {"t": 278, "ts": 1788065260.8701832, "step": 2780, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.787739674658951e-07, "advantage": -0.08707451820373535, "attn_entropy": 3.4657280445098877, "load_balance": 0.000976569950580597, "g_entropy": 3.465729236602783, "tau_bias": 0.6827874183654785, "beta": 0.46964546541372937, "train_val_corr": 1.0} |
| {"t": 279, "ts": 1788065264.524958, "step": 2790, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.8774013571819523e-07, "advantage": 0.24637430906295776, "attn_entropy": 3.465432643890381, "load_balance": 0.0009770875331014395, "g_entropy": 3.465268135070801, "tau_bias": 0.6827874183654785, "beta": 0.4688282509644826, "train_val_corr": 0.9999999999999999} |
| {"t": 280, "ts": 1788065268.0602047, "step": 2800, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.8442835287023627e-07, "advantage": -0.301301509141922, "attn_entropy": 3.4656500816345215, "load_balance": 0.0009767181472852826, "g_entropy": 3.465599536895752, "tau_bias": 0.6827874183654785, "beta": 0.46708786363403004, "train_val_corr": 1.0} |
| {"t": 281, "ts": 1788065271.6260448, "step": 2810, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.879755811591167e-07, "advantage": 0.8682606220245361, "attn_entropy": 3.4657323360443115, "load_balance": 0.0009765715803951025, "g_entropy": 3.465728759765625, "tau_bias": 0.6827874183654785, "beta": 0.4679129545887311, "train_val_corr": 1.0} |
| {"t": 282, "ts": 1788065275.119839, "step": 2820, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.892407167109923e-07, "advantage": -0.2172641158103943, "attn_entropy": 3.4657092094421387, "load_balance": 0.000976615585386753, "g_entropy": 3.4656927585601807, "tau_bias": 0.6827874183654785, "beta": 0.473941121250391, "train_val_corr": 0.9999999999999998} |
| {"t": 283, "ts": 1788065278.656304, "step": 2830, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.028625599199586e-07, "advantage": -0.06997527182102203, "attn_entropy": 3.4657301902770996, "load_balance": 0.0009765661088749766, "g_entropy": 3.4657318592071533, "tau_bias": 0.6827874183654785, "beta": 0.4598637521266937, "train_val_corr": 1.0} |
| {"t": 284, "ts": 1788065282.240632, "step": 2840, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.0137084650050383e-07, "advantage": 0.5867351293563843, "attn_entropy": 3.46572208404541, "load_balance": 0.0009765780996531248, "g_entropy": 3.4657206535339355, "tau_bias": 0.6827874183654785, "beta": 0.455441369364659, "train_val_corr": 1.0} |
| {"t": 285, "ts": 1788065285.8184388, "step": 2850, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.9851449312445766e-07, "advantage": -0.16504038870334625, "attn_entropy": 3.465731143951416, "load_balance": 0.000976565876044333, "g_entropy": 3.4657325744628906, "tau_bias": 0.6827874183654785, "beta": 0.4586895840863387, "train_val_corr": 1.0} |
| {"t": 286, "ts": 1788065289.2173235, "step": 2860, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.9952724389659124e-07, "advantage": 0.379830539226532, "attn_entropy": 3.4655075073242188, "load_balance": 0.0009769643656909466, "g_entropy": 3.4653773307800293, "tau_bias": 0.6827874183654785, "beta": 0.46277448038260144, "train_val_corr": 1.0} |
| {"t": 287, "ts": 1788065292.5846796, "step": 2870, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.942310004527826e-07, "advantage": 0.11819262057542801, "attn_entropy": 3.4657297134399414, "load_balance": 0.0009765675058588386, "g_entropy": 3.465730667114258, "tau_bias": 0.6827874183654785, "beta": 0.46391208097338676, "train_val_corr": 1.0} |
| {"t": 288, "ts": 1788065296.1169362, "step": 2880, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.917724657436338e-07, "advantage": -0.037398044019937515, "attn_entropy": 3.465670585632324, "load_balance": 0.0009766594739630818, "g_entropy": 3.4656436443328857, "tau_bias": 0.6827874183654785, "beta": 0.4651237676541011, "train_val_corr": 1.0} |
| {"t": 289, "ts": 1788065299.8450167, "step": 2890, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.945049573099823e-07, "advantage": -0.1773173063993454, "attn_entropy": 3.4657278060913086, "load_balance": 0.0009765706490725279, "g_entropy": 3.4657280445098877, "tau_bias": 0.6827874183654785, "beta": 0.47054769843816757, "train_val_corr": 1.0} |
| {"t": 290, "ts": 1788065303.281959, "step": 2900, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.931986102794326e-07, "advantage": -0.24148111045360565, "attn_entropy": 3.4657275676727295, "load_balance": 0.0009765708819031715, "g_entropy": 3.4657278060913086, "tau_bias": 0.6827874183654785, "beta": 0.4748867948849996, "train_val_corr": 1.0} |
| {"t": 291, "ts": 1788065306.7374637, "step": 2910, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.98098626672072e-07, "advantage": 0.2162833958864212, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765627328306437, "g_entropy": 3.465735673904419, "tau_bias": 0.6827874183654785, "beta": 0.46639365206162137, "train_val_corr": 0.9999999999999998} |
| {"t": 292, "ts": 1788065310.257829, "step": 2920, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.9121321176717174e-07, "advantage": 0.10197971016168594, "attn_entropy": 3.4656834602355957, "load_balance": 0.0009766638977453113, "g_entropy": 3.4656484127044678, "tau_bias": 0.6827874183654785, "beta": 0.47756504515806836, "train_val_corr": 0.9999999999999998} |
| {"t": 293, "ts": 1788065313.849587, "step": 2930, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.959660037049616e-07, "advantage": -0.08889443427324295, "attn_entropy": 3.4657349586486816, "load_balance": 0.0009765629656612873, "g_entropy": 3.465735912322998, "tau_bias": 0.6827874183654785, "beta": 0.4786757255593936, "train_val_corr": 0.9999999999999997} |
| {"t": 294, "ts": 1788065317.325575, "step": 2940, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.868778494757862e-07, "advantage": -0.14486458897590637, "attn_entropy": 3.465733766555786, "load_balance": 0.0009765635477378964, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.48194579655925435, "train_val_corr": 1.0} |
| {"t": 295, "ts": 1788065320.8367398, "step": 2950, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.9880868623877177e-07, "advantage": 0.09738022834062576, "attn_entropy": 3.465653896331787, "load_balance": 0.000976685550995171, "g_entropy": 3.4656224250793457, "tau_bias": 0.6827874183654785, "beta": 0.47658223658800125, "train_val_corr": 1.0} |
| {"t": 296, "ts": 1788065324.3592794, "step": 2960, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.880769329749455e-07, "advantage": 0.05600021407008171, "attn_entropy": 3.4657301902770996, "load_balance": 0.0009765767026692629, "g_entropy": 3.465724468231201, "tau_bias": 0.6827874183654785, "beta": 0.48262923831741017, "train_val_corr": 1.0} |
| {"t": 297, "ts": 1788065327.837382, "step": 2970, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.9166528747737175e-07, "advantage": -0.17829500138759613, "attn_entropy": 3.4656546115875244, "load_balance": 0.0009767103474587202, "g_entropy": 3.465609312057495, "tau_bias": 0.6827874183654785, "beta": 0.4845187266667684, "train_val_corr": 0.9999999999999998} |
| {"t": 298, "ts": 1788065331.3331878, "step": 2980, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.868542026135401e-07, "advantage": -0.24440866708755493, "attn_entropy": 3.465660572052002, "load_balance": 0.0009767056908458471, "g_entropy": 3.4656083583831787, "tau_bias": 0.6827874183654785, "beta": 0.4835605248808861, "train_val_corr": 0.9999999999999998} |
| {"t": 299, "ts": 1788065334.8151987, "step": 2990, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.9227831532807613e-07, "advantage": -0.11569783836603165, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765662252902985, "g_entropy": 3.465733051300049, "tau_bias": 0.6827874183654785, "beta": 0.4849612129231294, "train_val_corr": 1.0} |
| {"t": 300, "ts": 1788065338.4538555, "step": 3000, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.91474066216324e-07, "advantage": -0.32254427671432495, "attn_entropy": 3.4657132625579834, "load_balance": 0.000976590788923204, "g_entropy": 3.4657089710235596, "tau_bias": 0.6827874183654785, "beta": 0.4884628765285015, "train_val_corr": 1.0} |
| {"t": 301, "ts": 1788065341.9377847, "step": 3010, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.011646185768768e-07, "advantage": -0.14478227496147156, "attn_entropy": 3.4657087326049805, "load_balance": 0.0009766194270923734, "g_entropy": 3.465686798095703, "tau_bias": 0.6827874183654785, "beta": 0.4869709573686123, "train_val_corr": 1.0} |
| {"t": 302, "ts": 1788065345.4495335, "step": 3020, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.0389483640647086e-07, "advantage": 0.13042493164539337, "attn_entropy": 3.4657342433929443, "load_balance": 0.000976563198491931, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.4816287544866403, "train_val_corr": 1.0} |
| {"t": 303, "ts": 1788065348.9320004, "step": 3030, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.9769614684482804e-07, "advantage": -0.2325238436460495, "attn_entropy": 3.4657304286956787, "load_balance": 0.0009765664581209421, "g_entropy": 3.465731382369995, "tau_bias": 0.6827874183654785, "beta": 0.48975130294760066, "train_val_corr": 0.9999999999999999} |
| {"t": 304, "ts": 1788065352.3859417, "step": 3040, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.998643822138547e-07, "advantage": 0.015368456020951271, "attn_entropy": 3.465726137161255, "load_balance": 0.0009765846189111471, "g_entropy": 3.4657177925109863, "tau_bias": 0.6827874183654785, "beta": 0.48513374974330264, "train_val_corr": 1.0} |
| {"t": 305, "ts": 1788065355.915141, "step": 3050, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.017932783677679e-07, "advantage": -0.07363183051347733, "attn_entropy": 3.4657318592071533, "load_balance": 0.0009765649447217584, "g_entropy": 3.465733289718628, "tau_bias": 0.6827874183654785, "beta": 0.47609132900834084, "train_val_corr": 1.0} |
| {"t": 306, "ts": 1788065359.4239783, "step": 3060, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.012719105299766e-07, "advantage": -0.21719025075435638, "attn_entropy": 3.465557098388672, "load_balance": 0.0009768815943971276, "g_entropy": 3.4654510021209717, "tau_bias": 0.6827874183654785, "beta": 0.47547250986099243, "train_val_corr": 1.0} |
| {"t": 307, "ts": 1788065362.9208586, "step": 3070, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.044663401396974e-07, "advantage": -0.016123464331030846, "attn_entropy": 3.465733051300049, "load_balance": 0.0009765640133991838, "g_entropy": 3.4657344818115234, "tau_bias": 0.6827874183654785, "beta": 0.46930860603849095, "train_val_corr": 1.0} |
| {"t": 308, "ts": 1788065366.4162767, "step": 3080, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.0322709676511295e-07, "advantage": 0.06891706585884094, "attn_entropy": 3.4657223224639893, "load_balance": 0.0009765912545844913, "g_entropy": 3.465712070465088, "tau_bias": 0.6827874183654785, "beta": 0.480303352077802, "train_val_corr": 1.0} |
| {"t": 309, "ts": 1788065369.8437314, "step": 3090, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.0839382247904723e-07, "advantage": 0.020318666473031044, "attn_entropy": 3.4656481742858887, "load_balance": 0.0009767247829586267, "g_entropy": 3.4655911922454834, "tau_bias": 0.6827874183654785, "beta": 0.4681539324422677, "train_val_corr": 1.0} |
| {"t": 310, "ts": 1788065373.4150343, "step": 3100, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.0172975584719097e-07, "advantage": -0.13271380960941315, "attn_entropy": 3.4657325744628906, "load_balance": 0.00097656378056854, "g_entropy": 3.4657349586486816, "tau_bias": 0.6827874183654785, "beta": 0.47393831238150597, "train_val_corr": 1.0} |
| {"t": 311, "ts": 1788065376.8614204, "step": 3110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.010695479588321e-07, "advantage": 0.012865696102380753, "attn_entropy": 3.465715169906616, "load_balance": 0.000976606272161007, "g_entropy": 3.4656996726989746, "tau_bias": 0.6827874183654785, "beta": 0.4814940293629964, "train_val_corr": 0.9999999999999996} |
| {"t": 312, "ts": 1788065380.3758996, "step": 3120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.045678624857828e-07, "advantage": -0.07131144404411316, "attn_entropy": 3.4657344818115234, "load_balance": 0.0009765627328306437, "g_entropy": 3.465735912322998, "tau_bias": 0.6827874183654785, "beta": 0.47452976554632187, "train_val_corr": 1.0} |
| {"t": 313, "ts": 1788065383.842928, "step": 3130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.0044719778743456e-07, "advantage": -0.04366002231836319, "attn_entropy": 3.4657280445098877, "load_balance": 0.000976570532657206, "g_entropy": 3.465728759765625, "tau_bias": 0.6827874183654785, "beta": 0.47800490881005925, "train_val_corr": 0.9999999999999999} |
| {"t": 314, "ts": 1788065387.2223203, "step": 3140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.0677148288305034e-07, "advantage": 0.09603435546159744, "attn_entropy": 3.4656856060028076, "load_balance": 0.0009766570292413235, "g_entropy": 3.4656548500061035, "tau_bias": 0.6827874183654785, "beta": 0.4681437549491723, "train_val_corr": 0.9999999999999998} |
| {"t": 315, "ts": 1788065390.686061, "step": 3150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.009314468727098e-07, "advantage": -0.17398317158222198, "attn_entropy": 3.4657351970672607, "load_balance": 0.000976563198491931, "g_entropy": 3.46573543548584, "tau_bias": 0.6827874183654785, "beta": 0.4809168167412281, "train_val_corr": 1.0} |
| {"t": 316, "ts": 1788065394.1606205, "step": 3160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.0727639455108147e-07, "advantage": 0.1754216104745865, "attn_entropy": 3.4657351970672607, "load_balance": 0.0009765633149072528, "g_entropy": 3.4657351970672607, "tau_bias": 0.6827874183654785, "beta": 0.4744939903418223, "train_val_corr": 1.0} |
| {"t": 317, "ts": 1788065397.5688407, "step": 3170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.055734225654305e-07, "advantage": -0.08232268691062927, "attn_entropy": 3.465707302093506, "load_balance": 0.0009766020812094212, "g_entropy": 3.4656965732574463, "tau_bias": 0.6827874183654785, "beta": 0.4741557960708936, "train_val_corr": 1.0} |
| {"t": 318, "ts": 1788065401.0306497, "step": 3180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.040695162326301e-07, "advantage": 0.1354457288980484, "attn_entropy": 3.465714931488037, "load_balance": 0.0009765884606167674, "g_entropy": 3.465712785720825, "tau_bias": 0.6827874183654785, "beta": 0.47217389817039174, "train_val_corr": 1.0} |
| {"t": 319, "ts": 1788065404.479593, "step": 3190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.098919023614144e-07, "advantage": -0.12311404198408127, "attn_entropy": 3.4655699729919434, "load_balance": 0.0009768566815182567, "g_entropy": 3.465477466583252, "tau_bias": 0.6827874183654785, "beta": 0.47789863124489784, "train_val_corr": 1.0} |
| {"t": 320, "ts": 1788065408.0383341, "step": 3200, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.038155114154506e-07, "advantage": -0.1093050166964531, "attn_entropy": 3.465700149536133, "load_balance": 0.0009766101138666272, "g_entropy": 3.4656929969787598, "tau_bias": 0.6827874183654785, "beta": 0.4741924914220969, "train_val_corr": 1.0} |
| {"t": 321, "ts": 1788065411.5374837, "step": 3210, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.272098467732576e-07, "advantage": 0.19969353079795837, "attn_entropy": 3.465683698654175, "load_balance": 0.0009766636649146676, "g_entropy": 3.465646743774414, "tau_bias": 0.6827874183654785, "beta": 0.4719187120596568, "train_val_corr": 1.0} |
| {"t": 322, "ts": 1788065415.045644, "step": 3220, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.261736196691345e-07, "advantage": -0.08641387522220612, "attn_entropy": 3.4656949043273926, "load_balance": 0.0009766406146809459, "g_entropy": 3.465669870376587, "tau_bias": 0.6827874183654785, "beta": 0.4706205489734809, "train_val_corr": 0.9999999999999999} |
| {"t": 323, "ts": 1788065418.6852763, "step": 3230, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.359990330409346e-07, "advantage": 0.2816021144390106, "attn_entropy": 3.465688467025757, "load_balance": 0.000976630486547947, "g_entropy": 3.4656736850738525, "tau_bias": 0.6827874183654785, "beta": 0.47871874272823334, "train_val_corr": 0.9999999999999996} |
| {"t": 324, "ts": 1788065422.2756984, "step": 3240, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.2828276630425535e-07, "advantage": 0.41422179341316223, "attn_entropy": 3.465733766555786, "load_balance": 0.0009765682043507695, "g_entropy": 3.465731620788574, "tau_bias": 0.6827874183654785, "beta": 0.4649204860130946, "train_val_corr": 1.0} |
| {"t": 0, "ts": 1788066479.8216395, "step": 0, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 3.5206634493079036e-05, "advantage": 0.9454452395439148, "attn_entropy": 3.6684612035751343, "load_balance": 0.0007053087028907612, "g_entropy": 3.6684547662734985, "tau_bias": 0.6802318096160889, "beta": 0.48403943205873173, "train_val_corr": 0.0} |
| {"t": 1, "ts": 1788066491.0349884, "step": 10, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 1.4831667840553564e-06, "advantage": 4.6396918296813965, "attn_entropy": 3.6684433221817017, "load_balance": 0.0007053526205709204, "g_entropy": 3.668413758277893, "tau_bias": 0.6841914057731628, "beta": 0.47622835636138916, "train_val_corr": 0.0} |
| {"t": 2, "ts": 1788066502.2139, "step": 20, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.684687956389098e-07, "advantage": 1.3636293411254883, "attn_entropy": 3.6684335470199585, "load_balance": 0.0007053589797578752, "g_entropy": 3.6683952808380127, "tau_bias": 0.6835595965385437, "beta": 0.4858490290741126, "train_val_corr": 0.0} |
| {"t": 3, "ts": 1788066513.4778757, "step": 30, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.1233927327557467e-07, "advantage": 1.9659438133239746, "attn_entropy": 3.668455481529236, "load_balance": 0.0007053215085761622, "g_entropy": 3.6684412956237793, "tau_bias": 0.6817525029182434, "beta": 0.4790104553103447, "train_val_corr": 0.0} |
| {"t": 4, "ts": 1788066524.3824208, "step": 40, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.077912171216667e-07, "advantage": 2.835692882537842, "attn_entropy": 3.668433427810669, "load_balance": 0.0007053697481751442, "g_entropy": 3.668395757675171, "tau_bias": 0.6812742352485657, "beta": 0.4811113712688287, "train_val_corr": 0.0} |
| {"t": 5, "ts": 1788066535.5213156, "step": 50, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0732348104957055e-07, "advantage": 2.111607074737549, "attn_entropy": 3.668461561203003, "load_balance": 0.0007053043955238536, "g_entropy": 3.66845440864563, "tau_bias": 0.6815788745880127, "beta": 0.47518303121129674, "train_val_corr": 0.0} |
| {"t": 6, "ts": 1788066546.5694547, "step": 60, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0724945670735906e-07, "advantage": 1.9290306568145752, "attn_entropy": 3.668452262878418, "load_balance": 0.0007053347217151895, "g_entropy": 3.668432593345642, "tau_bias": 0.6826574802398682, "beta": 0.48127953708171844, "train_val_corr": 0.0} |
| {"t": 7, "ts": 1788066557.64479, "step": 70, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723666693811538e-07, "advantage": 1.8052716255187988, "attn_entropy": 3.668463110923767, "load_balance": 0.0007053045410430059, "g_entropy": 3.6684569120407104, "tau_bias": 0.6831184029579163, "beta": 0.4850631356239319, "train_val_corr": 0.0} |
| {"t": 8, "ts": 1788066568.5212734, "step": 80, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723366844777047e-07, "advantage": 1.8425261974334717, "attn_entropy": 3.668458104133606, "load_balance": 0.0007053156732581556, "g_entropy": 3.6684463024139404, "tau_bias": 0.6833832859992981, "beta": 0.4775386303663254, "train_val_corr": 0.0} |
| {"t": 9, "ts": 1788066579.3610454, "step": 90, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723300053759885e-07, "advantage": 0.12656369805335999, "attn_entropy": 3.668395757675171, "load_balance": 0.0007054543093545362, "g_entropy": 3.6683130264282227, "tau_bias": 0.683688223361969, "beta": 0.48446593309442204, "train_val_corr": 0.0} |
| {"t": 10, "ts": 1788066590.212835, "step": 100, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723274474221398e-07, "advantage": 0.7926420569419861, "attn_entropy": 3.668431282043457, "load_balance": 0.000705361322616227, "g_entropy": 3.6683905124664307, "tau_bias": 0.6836584806442261, "beta": 0.4784329372147719, "train_val_corr": 0.0} |
| {"t": 11, "ts": 1788066601.3758328, "step": 110, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.5956395268440247, "attn_entropy": 3.668448805809021, "load_balance": 0.0007053405424812809, "g_entropy": 3.668427348136902, "tau_bias": 0.6838372945785522, "beta": 0.4787932187318802, "train_val_corr": 0.0} |
| {"t": 12, "ts": 1788066612.4243655, "step": 120, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.315799355506897, "attn_entropy": 3.6684337854385376, "load_balance": 0.0007053569861454889, "g_entropy": 3.668392539024353, "tau_bias": 0.6837651133537292, "beta": 0.4787758526702722, "train_val_corr": 0.0} |
| {"t": 13, "ts": 1788066623.1357775, "step": 130, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.4512214958667755, "attn_entropy": 3.6684621572494507, "load_balance": 0.0007053036824800074, "g_entropy": 3.66845440864563, "tau_bias": 0.6839790940284729, "beta": 0.483419278015693, "train_val_corr": 0.0} |
| {"t": 14, "ts": 1788066633.7679214, "step": 140, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.0900285542011261, "attn_entropy": 3.6684247255325317, "load_balance": 0.0007054073357721791, "g_entropy": 3.6683733463287354, "tau_bias": 0.684233546257019, "beta": 0.482182494054238, "train_val_corr": 0.0} |
| {"t": 15, "ts": 1788066644.0112607, "event": "pgo_update", "design": 1.0, "theta_gp_l": 0.6, "theta_gp_sf": 0.6, "theta_gp_sn": 0.5} |
| {"t": 16, "ts": 1788066645.037937, "step": 150, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.6331067085266113, "attn_entropy": 3.668460965156555, "load_balance": 0.0007053049193928018, "g_entropy": 3.668452501296997, "tau_bias": 0.6842595338821411, "beta": 0.4844466025630633, "train_val_corr": 0.0} |
| {"t": 17, "ts": 1788066656.324494, "step": 160, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.7678735852241516, "attn_entropy": 3.6684359312057495, "load_balance": 0.0007053434528643265, "g_entropy": 3.668397903442383, "tau_bias": 0.684265673160553, "beta": 0.48549673582116765, "train_val_corr": 0.0} |
| {"t": 18, "ts": 1788066667.3410301, "step": 170, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.15948930382728577, "attn_entropy": 3.668454170227051, "load_balance": 0.0007053199806250632, "g_entropy": 3.6684376001358032, "tau_bias": 0.6841767430305481, "beta": 0.48156025260686874, "train_val_corr": 0.0} |
| {"t": 19, "ts": 1788066678.4733763, "step": 180, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.4330444931983948, "attn_entropy": 3.6684614419937134, "load_balance": 0.0007053049193928018, "g_entropy": 3.6684532165527344, "tau_bias": 0.6840287446975708, "beta": 0.4639933668076992, "train_val_corr": 0.0} |
| {"t": 20, "ts": 1788066689.6209748, "step": 190, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 1.7540299892425537, "attn_entropy": 3.668440341949463, "load_balance": 0.0007053667068248615, "g_entropy": 3.668406367301941, "tau_bias": 0.6845646500587463, "beta": 0.4593263516823451, "train_val_corr": 1.0} |
| {"t": 21, "ts": 1788066700.933211, "step": 200, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.6977701187133789, "attn_entropy": 3.6684610843658447, "load_balance": 0.0007053046865621582, "g_entropy": 3.6684526205062866, "tau_bias": 0.6855381727218628, "beta": 0.4761141190926234, "train_val_corr": 1.0} |
| {"t": 22, "ts": 1788066712.2333114, "step": 210, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.6593194007873535, "attn_entropy": 3.6684303283691406, "load_balance": 0.0007053863955661654, "g_entropy": 3.668389320373535, "tau_bias": 0.6859238743782043, "beta": 0.46639324103792507, "train_val_corr": 1.0} |
| {"t": 23, "ts": 1788066723.4400394, "step": 220, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2703312635421753, "attn_entropy": 3.6684410572052, "load_balance": 0.0007053335284581408, "g_entropy": 3.6684112548828125, "tau_bias": 0.686248242855072, "beta": 0.47620297223329544, "train_val_corr": 0.9999999999999999} |
| {"t": 24, "ts": 1788066734.4862463, "step": 230, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.898449718952179, "attn_entropy": 3.6684319972991943, "load_balance": 0.0007053542794892564, "g_entropy": 3.6683932542800903, "tau_bias": 0.6864221692085266, "beta": 0.48268355801701546, "train_val_corr": 1.0} |
| {"t": 25, "ts": 1788066746.2235174, "step": 240, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.8051705360412598, "attn_entropy": 3.6684244871139526, "load_balance": 0.0007053649314912036, "g_entropy": 3.668372869491577, "tau_bias": 0.6861872673034668, "beta": 0.47845853492617607, "train_val_corr": 1.0} |
| {"t": 26, "ts": 1788066758.0440955, "step": 250, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.711195707321167, "attn_entropy": 3.6684556007385254, "load_balance": 0.000705315382219851, "g_entropy": 3.6684406995773315, "tau_bias": 0.6861929893493652, "beta": 0.4793113283813, "train_val_corr": 1.0} |
| {"t": 27, "ts": 1788066769.5595105, "step": 260, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.5875639915466309, "attn_entropy": 3.6684017181396484, "load_balance": 0.0007054688903735951, "g_entropy": 3.668330430984497, "tau_bias": 0.6862627863883972, "beta": 0.4811618501941363, "train_val_corr": 1.0} |
| {"t": 28, "ts": 1788066780.5817063, "step": 270, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.6849701404571533, "attn_entropy": 3.6684592962265015, "load_balance": 0.0007053115987218916, "g_entropy": 3.6684490442276, "tau_bias": 0.6862375736236572, "beta": 0.4822976378103097, "train_val_corr": 1.0} |
| {"t": 29, "ts": 1788066791.2265983, "step": 280, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.4371486306190491, "attn_entropy": 3.668458938598633, "load_balance": 0.0007053124136291444, "g_entropy": 3.668448328971863, "tau_bias": 0.6861386299133301, "beta": 0.4747037924826145, "train_val_corr": 0.9999999999999999} |
| {"t": 30, "ts": 1788066802.7835348, "step": 290, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.4233397841453552, "attn_entropy": 3.66846239566803, "load_balance": 0.0007053028093650937, "g_entropy": 3.668455958366394, "tau_bias": 0.6857851147651672, "beta": 0.4839010921617349, "train_val_corr": 0.9999999999999996} |
| {"t": 31, "ts": 1788066813.213528, "event": "pgo_update", "design": 2.0, "theta_gp_l": 0.6, "theta_gp_sf": 0.6, "theta_gp_sn": 0.5} |
| {"t": 32, "ts": 1788066814.1685283, "step": 300, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.45876985788345337, "attn_entropy": 3.668432593345642, "load_balance": 0.0007053631125018001, "g_entropy": 3.668389678001404, "tau_bias": 0.6832864284515381, "beta": 0.4758089544872443, "train_val_corr": 0.9999999999999999} |
| {"t": 33, "ts": 1788066825.1506345, "step": 310, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.40741539001464844, "attn_entropy": 3.6684377193450928, "load_balance": 0.0007053461158648133, "g_entropy": 3.668403148651123, "tau_bias": 0.6852775812149048, "beta": 0.4729018732905388, "train_val_corr": 1.0} |
| {"t": 34, "ts": 1788066836.0819507, "step": 320, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.24334199726581573, "attn_entropy": 3.6684322357177734, "load_balance": 0.0007053416920825839, "g_entropy": 3.6683907508850098, "tau_bias": 0.6833176016807556, "beta": 0.4823558144271374, "train_val_corr": 0.9999999999999999} |
| {"t": 35, "ts": 1788066846.868169, "step": 330, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.6800429821014404, "attn_entropy": 3.6684505939483643, "load_balance": 0.0007053249719319865, "g_entropy": 3.6684306859970093, "tau_bias": 0.6825512051582336, "beta": 0.48007506380478543, "train_val_corr": 1.0} |
| {"t": 36, "ts": 1788066858.0141208, "step": 340, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.440685898065567, "attn_entropy": 3.6684404611587524, "load_balance": 0.0007053317240206525, "g_entropy": 3.668407917022705, "tau_bias": 0.6816686987876892, "beta": 0.48383088534077007, "train_val_corr": 1.0} |
| {"t": 37, "ts": 1788066869.1752152, "step": 350, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.27554652094841003, "attn_entropy": 3.6684377193450928, "load_balance": 0.0007053590816212818, "g_entropy": 3.668407440185547, "tau_bias": 0.6804227232933044, "beta": 0.4823990787069003, "train_val_corr": 1.0} |
| {"t": 38, "ts": 1788066880.6393585, "step": 360, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3906957805156708, "attn_entropy": 3.6684643030166626, "load_balance": 0.0007053000153973699, "g_entropy": 3.6684603691101074, "tau_bias": 0.6794785261154175, "beta": 0.4804467149078846, "train_val_corr": 1.0} |
| {"t": 39, "ts": 1788066892.2313838, "step": 370, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3726836144924164, "attn_entropy": 3.6684439182281494, "load_balance": 0.0007053429580992088, "g_entropy": 3.6684181690216064, "tau_bias": 0.6796945929527283, "beta": 0.47917761529485386, "train_val_corr": 1.0} |
| {"t": 40, "ts": 1788066903.625397, "step": 380, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.6205267906188965, "attn_entropy": 3.668460965156555, "load_balance": 0.0007053098961478099, "g_entropy": 3.668452501296997, "tau_bias": 0.6791942715644836, "beta": 0.47458356122175854, "train_val_corr": 1.0} |
| {"t": 41, "ts": 1788066915.1353853, "step": 390, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1305583119392395, "attn_entropy": 3.668444037437439, "load_balance": 0.0007053520384943113, "g_entropy": 3.668415665626526, "tau_bias": 0.6784675121307373, "beta": 0.4798006129761537, "train_val_corr": 1.0} |
| {"t": 42, "ts": 1788066926.7794192, "step": 400, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.20112697780132294, "attn_entropy": 3.6684638261795044, "load_balance": 0.0007053021545289084, "g_entropy": 3.668458342552185, "tau_bias": 0.6790205836296082, "beta": 0.47703033313155174, "train_val_corr": 1.0} |
| {"t": 43, "ts": 1788066938.3441424, "step": 410, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.5432929992675781, "attn_entropy": 3.668413996696472, "load_balance": 0.0007054239540593699, "g_entropy": 3.6683460474014282, "tau_bias": 0.6762887835502625, "beta": 0.4780069130162398, "train_val_corr": 0.9999999999999999} |
| {"t": 44, "ts": 1788066949.7603097, "step": 420, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.03362882509827614, "attn_entropy": 3.6684343814849854, "load_balance": 0.0007053544832160696, "g_entropy": 3.6683908700942993, "tau_bias": 0.6736059188842773, "beta": 0.4831029971440633, "train_val_corr": 1.0} |
| {"t": 45, "ts": 1788066961.6344566, "step": 430, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.4855019152164459, "attn_entropy": 3.668378472328186, "load_balance": 0.0007055334717733786, "g_entropy": 3.6682697534561157, "tau_bias": 0.672545313835144, "beta": 0.4831637466947238, "train_val_corr": 1.0} |
| {"t": 46, "ts": 1788066973.2232456, "step": 440, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.16926045715808868, "attn_entropy": 3.6684463024139404, "load_balance": 0.0007053523295326158, "g_entropy": 3.6684199571609497, "tau_bias": 0.6721946597099304, "beta": 0.486588799705108, "train_val_corr": 1.0} |
| {"t": 47, "ts": 1788066983.8469224, "event": "pgo_update", "design": 4.0, "theta_gp_l": 0.6, "theta_gp_sf": 0.6, "theta_gp_sn": 0.5} |
| {"t": 48, "ts": 1788066984.8443334, "step": 450, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3062012195587158, "attn_entropy": 3.668455958366394, "load_balance": 0.000705321945133619, "g_entropy": 3.668440818786621, "tau_bias": 0.6715911030769348, "beta": 0.4853380285203457, "train_val_corr": 0.9999999999999996} |
| {"t": 49, "ts": 1788066996.1196613, "step": 460, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.3614934980869293, "attn_entropy": 3.668441414833069, "load_balance": 0.0007053669687593356, "g_entropy": 3.6684086322784424, "tau_bias": 0.6734089851379395, "beta": 0.4881207247575124, "train_val_corr": 1.0} |
| {"t": 50, "ts": 1788067007.4143586, "step": 470, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1449953019618988, "attn_entropy": 3.668435573577881, "load_balance": 0.0007053430163068697, "g_entropy": 3.668394684791565, "tau_bias": 0.6719743013381958, "beta": 0.4847046708067258, "train_val_corr": 1.0} |
| {"t": 51, "ts": 1788067019.07023, "step": 480, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.26725539565086365, "attn_entropy": 3.668439745903015, "load_balance": 0.000705345650203526, "g_entropy": 3.668403148651123, "tau_bias": 0.6680817604064941, "beta": 0.48165032640099525, "train_val_corr": 1.0} |
| {"t": 52, "ts": 1788067030.5411274, "step": 490, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.05076686292886734, "attn_entropy": 3.6684600114822388, "load_balance": 0.0007053138106130064, "g_entropy": 3.668449282646179, "tau_bias": 0.6640639305114746, "beta": 0.4829866836468379, "train_val_corr": 1.0} |
| {"t": 53, "ts": 1788067042.346294, "step": 500, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.24415816366672516, "attn_entropy": 3.6684658527374268, "load_balance": 0.000705299957189709, "g_entropy": 3.668461799621582, "tau_bias": 0.6637139320373535, "beta": 0.48523958399891853, "train_val_corr": 0.9999999999999998} |
| {"t": 54, "ts": 1788067053.6619265, "step": 510, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.23852792382240295, "attn_entropy": 3.668459177017212, "load_balance": 0.0007053075678413734, "g_entropy": 3.6684471368789673, "tau_bias": 0.6629581451416016, "beta": 0.487367940445741, "train_val_corr": 0.9999999999999996} |
| {"t": 55, "ts": 1788067065.3374696, "step": 520, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2067384570837021, "attn_entropy": 3.668459892272949, "load_balance": 0.0007053068693494424, "g_entropy": 3.6684491634368896, "tau_bias": 0.6623247265815735, "beta": 0.48684730380773544, "train_val_corr": 1.0} |
| {"t": 56, "ts": 1788067076.9847672, "step": 530, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.32243841886520386, "attn_entropy": 3.668436288833618, "load_balance": 0.0007053758745314553, "g_entropy": 3.668395757675171, "tau_bias": 0.6621003150939941, "beta": 0.4757155602176984, "train_val_corr": 0.9999999999999996} |
| {"t": 57, "ts": 1788067088.2253387, "step": 540, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.19990164041519165, "attn_entropy": 3.668450951576233, "load_balance": 0.0007053183653624728, "g_entropy": 3.668428063392639, "tau_bias": 0.6614701151847839, "beta": 0.4851752606530984, "train_val_corr": 0.9999999999999998} |
| {"t": 58, "ts": 1788067099.4145842, "step": 550, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.24102263152599335, "attn_entropy": 3.668461799621582, "load_balance": 0.0007053061126498505, "g_entropy": 3.668453097343445, "tau_bias": 0.6613015532493591, "beta": 0.4877706952393055, "train_val_corr": 1.0} |
| {"t": 59, "ts": 1788067110.4529705, "step": 560, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.046832505613565445, "attn_entropy": 3.668431043624878, "load_balance": 0.0007053883891785517, "g_entropy": 3.668383836746216, "tau_bias": 0.6611025929450989, "beta": 0.4830683159331481, "train_val_corr": 1.0} |
| {"t": 60, "ts": 1788067121.5849712, "step": 570, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.38949713110923767, "attn_entropy": 3.6684435606002808, "load_balance": 0.0007053595036268234, "g_entropy": 3.6684120893478394, "tau_bias": 0.6604306697845459, "beta": 0.48503293966253597, "train_val_corr": 1.0} |
| {"t": 61, "ts": 1788067133.8843446, "step": 580, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.33279240131378174, "attn_entropy": 3.668465495109558, "load_balance": 0.00070529906952288, "g_entropy": 3.668461322784424, "tau_bias": 0.6594482660293579, "beta": 0.4910058056314786, "train_val_corr": 1.0} |
| {"t": 62, "ts": 1788067145.3364775, "step": 590, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.21688508987426758, "attn_entropy": 3.6684333086013794, "load_balance": 0.0007053855224512517, "g_entropy": 3.6683878898620605, "tau_bias": 0.659489095211029, "beta": 0.48646218578020733, "train_val_corr": 0.9999999999999999} |
| {"t": 63, "ts": 1788067155.2412221, "event": "pgo_update", "design": 5.0, "theta_gp_l": 0.6, "theta_gp_sf": 0.6, "theta_gp_sn": 0.5} |
| {"t": 64, "ts": 1788067156.166522, "step": 600, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.24581140279769897, "attn_entropy": 3.6684552431106567, "load_balance": 0.0007053180161165074, "g_entropy": 3.6684389114379883, "tau_bias": 0.6611983776092529, "beta": 0.49015723913908005, "train_val_corr": 1.0} |
| {"t": 65, "ts": 1788067168.359636, "step": 610, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.06303665041923523, "attn_entropy": 3.668425440788269, "load_balance": 0.0007053690933389589, "g_entropy": 3.668410539627075, "tau_bias": 0.6564289927482605, "beta": 0.48758360122640926, "train_val_corr": 0.9999999999999999} |
| {"t": 66, "ts": 1788067179.1822321, "step": 620, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.050063520669937134, "attn_entropy": 3.6684550046920776, "load_balance": 0.0007053243461996317, "g_entropy": 3.6684404611587524, "tau_bias": 0.6555282473564148, "beta": 0.48524434119462967, "train_val_corr": 0.9999999999999999} |
| {"t": 67, "ts": 1788067190.7149777, "step": 630, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.1459260731935501, "attn_entropy": 3.6684340238571167, "load_balance": 0.0007053565350361168, "g_entropy": 3.6683937311172485, "tau_bias": 0.655155599117279, "beta": 0.4890332358578841, "train_val_corr": 1.0} |
| {"t": 68, "ts": 1788067202.267645, "step": 640, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.07314702868461609, "attn_entropy": 3.6684335470199585, "load_balance": 0.000705376747646369, "g_entropy": 3.6683982610702515, "tau_bias": 0.655581533908844, "beta": 0.490194429953893, "train_val_corr": 1.0} |
| {"t": 69, "ts": 1788067213.3755746, "step": 650, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.08220133930444717, "attn_entropy": 3.6683638095855713, "load_balance": 0.0007055583409965038, "g_entropy": 3.668269157409668, "tau_bias": 0.6554046273231506, "beta": 0.48768868669867516, "train_val_corr": 1.0} |
| {"t": 70, "ts": 1788067224.8256092, "step": 660, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.148427352309227, "attn_entropy": 3.6684350967407227, "load_balance": 0.00070534176484216, "g_entropy": 3.668392062187195, "tau_bias": 0.6556360125541687, "beta": 0.4877605053285758, "train_val_corr": 1.0} |
| {"t": 71, "ts": 1788067236.369302, "step": 670, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.15100610256195068, "attn_entropy": 3.6684231758117676, "load_balance": 0.000705390761140734, "g_entropy": 3.668367028236389, "tau_bias": 0.655384361743927, "beta": 0.49003410960237187, "train_val_corr": 1.0} |
| {"t": 72, "ts": 1788067247.4364161, "step": 680, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.5385120511054993, "attn_entropy": 3.6683777570724487, "load_balance": 0.0007055175228742883, "g_entropy": 3.668278932571411, "tau_bias": 0.6553956270217896, "beta": 0.4882822670042515, "train_val_corr": 1.0} |
| {"t": 73, "ts": 1788067258.2590728, "step": 690, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.08413854241371155, "attn_entropy": 3.6684590578079224, "load_balance": 0.000705307800672017, "g_entropy": 3.66844642162323, "tau_bias": 0.6550443172454834, "beta": 0.49325010056296986, "train_val_corr": 1.0} |
| {"t": 74, "ts": 1788067268.9700308, "step": 700, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.0003142365603707731, "attn_entropy": 3.6684619188308716, "load_balance": 0.0007053068693494424, "g_entropy": 3.66845440864563, "tau_bias": 0.655267059803009, "beta": 0.4921794372300307, "train_val_corr": 1.0} |
| {"t": 75, "ts": 1788067279.9737785, "step": 710, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.05690828338265419, "attn_entropy": 3.6684590578079224, "load_balance": 0.00070531626988668, "g_entropy": 3.6684484481811523, "tau_bias": 0.6551838517189026, "beta": 0.49490249653657276, "train_val_corr": 0.9999999999999998} |
| {"t": 76, "ts": 1788067291.522189, "step": 720, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.2730717957019806, "attn_entropy": 3.668443441390991, "load_balance": 0.0007053355366224423, "g_entropy": 3.668411135673523, "tau_bias": 0.6546598076820374, "beta": 0.49344727769494057, "train_val_corr": 1.0} |
| {"t": 77, "ts": 1788067302.913541, "step": 730, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.16817627847194672, "attn_entropy": 3.6684322357177734, "load_balance": 0.0007053648732835427, "g_entropy": 3.6683837175369263, "tau_bias": 0.6548746824264526, "beta": 0.4948183136681716, "train_val_corr": 1.0} |
| {"t": 78, "ts": 1788067314.0860825, "step": 740, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.2762778699398041, "attn_entropy": 3.6684521436691284, "load_balance": 0.0007053170847939327, "g_entropy": 3.66843044757843, "tau_bias": 0.6546237468719482, "beta": 0.495056327432394, "train_val_corr": 1.0} |
| {"t": 79, "ts": 1788067324.4879138, "event": "pgo_update", "design": 7.0, "theta_gp_l": 0.6, "theta_gp_sf": 0.6, "theta_gp_sn": -0.613298811407241} |
| {"t": 80, "ts": 1788067325.4799204, "step": 750, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.21889090538024902, "attn_entropy": 3.6684606075286865, "load_balance": 0.0007053086446831003, "g_entropy": 3.6684513092041016, "tau_bias": 0.6546695828437805, "beta": 0.4954443189005057, "train_val_corr": 0.9999999999999998} |
| {"t": 81, "ts": 1788067336.846196, "step": 760, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": 0.005587427876889706, "attn_entropy": 3.668458580970764, "load_balance": 0.0007053083827486262, "g_entropy": 3.6684459447860718, "tau_bias": 0.6547521948814392, "beta": 0.4922633282840252, "train_val_corr": 1.0} |
| {"t": 82, "ts": 1788067347.9869757, "step": 770, "action": "ATTN_HYBRID_SPARSE", "entropy_pi": 2.0723264526623097e-07, "advantage": -0.29261350631713867, "attn_entropy": 3.6684411764144897, "load_balance": 0.0007053454173728824, "g_entropy": 3.668405055999756, "tau_bias": 0.6545678377151489, "beta": 0.49312543372313183, "train_val_corr": 0.9999999999999996} |
|
|
