{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.5612070306424016, "eval_steps": 500, "global_step": 451, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "completion_length": 400.44086837768555, "epoch": 0.002488722974023954, "grad_norm": 0.10229702522786686, "kl": 0.0, "learning_rate": 7.142857142857142e-08, "loss": 0.0, "reward": 0.5412946753203869, "reward_std": 0.5055910516530275, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.5412946753203869, "step": 2 }, { "completion_length": 385.4564914703369, "epoch": 0.004977445948047908, "grad_norm": 0.10059111736111713, "kl": 0.0004247426986694336, "learning_rate": 1.4285714285714285e-07, "loss": 0.0, "reward": 0.47544645331799984, "reward_std": 0.4911654181778431, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.47544645331799984, "step": 4 }, { "completion_length": 389.0725612640381, "epoch": 0.007466168922071862, "grad_norm": 0.11061618345240035, "kl": 0.0004165172576904297, "learning_rate": 2.1428571428571426e-07, "loss": 0.0, "reward": 0.5279018115252256, "reward_std": 0.49625692516565323, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.5279018115252256, "step": 6 }, { "completion_length": 396.0189895629883, "epoch": 0.009954891896095816, "grad_norm": 0.11927608013833589, "kl": 0.00040137767791748047, "learning_rate": 2.857142857142857e-07, "loss": 0.0, "reward": 0.4854910969734192, "reward_std": 0.4980995524674654, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.4854910969734192, "step": 8 }, { "completion_length": 392.9497928619385, "epoch": 0.01244361487011977, "grad_norm": 0.10949296556166527, "kl": 0.0004659891128540039, "learning_rate": 3.5714285714285716e-07, "loss": 0.0, "reward": 0.5334821622818708, "reward_std": 0.483795752748847, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.5334821622818708, "step": 10 }, { "completion_length": 361.7143039703369, "epoch": 0.014932337844143724, "grad_norm": 0.11491431070654654, "kl": 0.0004961490631103516, "learning_rate": 4.285714285714285e-07, "loss": 0.0, "reward": 0.5725446715950966, "reward_std": 0.49694120697677135, "rewards/equation_reward_func": 0.0011160714784637094, "rewards/format_reward_func": 0.5714285969734192, "step": 12 }, { "completion_length": 383.80359077453613, "epoch": 0.017421060818167678, "grad_norm": 0.10217225238845459, "kl": 0.0006783008575439453, "learning_rate": 5e-07, "loss": 0.0, "reward": 0.6261161006987095, "reward_std": 0.47387135215103626, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.6261161006987095, "step": 14 }, { "completion_length": 385.1930961608887, "epoch": 0.019909783792191632, "grad_norm": 0.09079397444986828, "kl": 0.0009381771087646484, "learning_rate": 4.999740409224932e-07, "loss": 0.0, "reward": 0.6529018133878708, "reward_std": 0.46884808875620365, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.6529018133878708, "step": 16 }, { "completion_length": 387.5089473724365, "epoch": 0.022398506766215586, "grad_norm": 0.07789924771682649, "kl": 0.0022106170654296875, "learning_rate": 4.998961690809627e-07, "loss": 0.0, "reward": 0.8169643208384514, "reward_std": 0.35768389888107777, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.8169643208384514, "step": 18 }, { "completion_length": 380.96653938293457, "epoch": 0.02488722974023954, "grad_norm": 0.06315055485645503, "kl": 0.004170417785644531, "learning_rate": 4.997664006472578e-07, "loss": 0.0, "reward": 0.887276828289032, "reward_std": 0.23898791754618287, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.887276828289032, "step": 20 }, { "completion_length": 378.5915355682373, "epoch": 0.027375952714263494, "grad_norm": 0.0566780627533256, "kl": 0.005069732666015625, "learning_rate": 4.995847625707292e-07, "loss": 0.0, "reward": 0.9129464663565159, "reward_std": 0.19532618205994368, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9129464663565159, "step": 22 }, { "completion_length": 385.043550491333, "epoch": 0.029864675688287448, "grad_norm": 0.0507404366996494, "kl": 0.005603790283203125, "learning_rate": 4.993512925726318e-07, "loss": 0.0, "reward": 0.9107143208384514, "reward_std": 0.20043640863150358, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9107143208384514, "step": 24 }, { "completion_length": 374.24667167663574, "epoch": 0.0323533986623114, "grad_norm": 0.03460311969195311, "kl": 0.0071620941162109375, "learning_rate": 4.990660391382923e-07, "loss": 0.0, "reward": 0.9419643171131611, "reward_std": 0.1277988995425403, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9419643171131611, "step": 26 }, { "completion_length": 356.6495723724365, "epoch": 0.034842121636335356, "grad_norm": 0.014238488177721704, "kl": 0.010402679443359375, "learning_rate": 4.987290615070384e-07, "loss": 0.0, "reward": 0.9732143245637417, "reward_std": 0.07358111487701535, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9732143245637417, "step": 28 }, { "completion_length": 356.62501525878906, "epoch": 0.03733084461035931, "grad_norm": 0.016695682547454543, "kl": 0.013233184814453125, "learning_rate": 4.983404296598978e-07, "loss": 0.0, "reward": 0.9799107350409031, "reward_std": 0.0502800983376801, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9799107350409031, "step": 30 }, { "completion_length": 337.0390739440918, "epoch": 0.039819567584383264, "grad_norm": 0.0178363646878267, "kl": 0.019924163818359375, "learning_rate": 4.979002243050646e-07, "loss": 0.0, "reward": 0.9821428917348385, "reward_std": 0.04832730023190379, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9821428917348385, "step": 32 }, { "completion_length": 329.28014945983887, "epoch": 0.042308290558407215, "grad_norm": 0.014714626628216123, "kl": 0.016998291015625, "learning_rate": 4.974085368611381e-07, "loss": 0.0, "reward": 0.9787946827709675, "reward_std": 0.05561715178191662, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9787946827709675, "step": 34 }, { "completion_length": 322.30246925354004, "epoch": 0.04479701353243117, "grad_norm": 0.021040890462160396, "kl": 0.01895904541015625, "learning_rate": 4.968654694381379e-07, "loss": 0.0, "reward": 0.9743303917348385, "reward_std": 0.06606373097747564, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9743303917348385, "step": 36 }, { "completion_length": 305.00335693359375, "epoch": 0.04728573650645512, "grad_norm": 0.01863566038382118, "kl": 0.0214385986328125, "learning_rate": 4.962711348162987e-07, "loss": 0.0, "reward": 0.9910714514553547, "reward_std": 0.0252538132481277, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9910714514553547, "step": 38 }, { "completion_length": 310.13282775878906, "epoch": 0.04977445948047908, "grad_norm": 0.011919224174973252, "kl": 0.0224151611328125, "learning_rate": 4.956256564226487e-07, "loss": 0.0, "reward": 0.9854910969734192, "reward_std": 0.0410374472849071, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9854910969734192, "step": 40 }, { "completion_length": 308.84375953674316, "epoch": 0.05226318245450303, "grad_norm": 0.00934945126695278, "kl": 0.023162841796875, "learning_rate": 4.949291683053768e-07, "loss": 0.0, "reward": 0.9899553768336773, "reward_std": 0.028410539962351322, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9899553768336773, "step": 42 }, { "completion_length": 285.6082706451416, "epoch": 0.05475190542852699, "grad_norm": 0.006489996788191869, "kl": 0.0259552001953125, "learning_rate": 4.941818151059955e-07, "loss": 0.0, "reward": 0.9921875149011612, "reward_std": 0.019916759338229895, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9921875149011612, "step": 44 }, { "completion_length": 279.28461265563965, "epoch": 0.05724062840255094, "grad_norm": 0.011058147576593262, "kl": 0.027862548828125, "learning_rate": 4.933837520293017e-07, "loss": 0.0, "reward": 0.993303582072258, "reward_std": 0.01676003262400627, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.993303582072258, "step": 46 }, { "completion_length": 281.8884048461914, "epoch": 0.059729351376574896, "grad_norm": 0.0055576859057008985, "kl": 0.02691650390625, "learning_rate": 4.925351448111454e-07, "loss": 0.0, "reward": 0.9944196566939354, "reward_std": 0.015783633571118116, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9944196566939354, "step": 48 }, { "completion_length": 288.05023765563965, "epoch": 0.06221807435059885, "grad_norm": 0.012749047747490404, "kl": 0.027008056640625, "learning_rate": 4.91636169684011e-07, "loss": 0.0, "reward": 0.994419664144516, "reward_std": 0.015783633571118116, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.994419664144516, "step": 50 }, { "completion_length": 286.1239013671875, "epoch": 0.0647067973246228, "grad_norm": 0.018013792950835963, "kl": 0.03295135498046875, "learning_rate": 4.906870133404186e-07, "loss": 0.0, "reward": 0.9866071566939354, "reward_std": 0.03788072057068348, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9866071566939354, "step": 52 }, { "completion_length": 267.4062604904175, "epoch": 0.06719552029864675, "grad_norm": 0.022259449850372266, "kl": 0.03186798095703125, "learning_rate": 4.896878728941531e-07, "loss": 0.0, "reward": 0.991071455180645, "reward_std": 0.025253813713788986, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.991071455180645, "step": 54 }, { "completion_length": 270.542423248291, "epoch": 0.06968424327267071, "grad_norm": 0.01088790708734008, "kl": 0.03081512451171875, "learning_rate": 4.886389558393284e-07, "loss": 0.0, "reward": 0.9955357313156128, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357313156128, "step": 56 }, { "completion_length": 277.4542579650879, "epoch": 0.07217296624669467, "grad_norm": 0.005367868177232952, "kl": 0.033447265625, "learning_rate": 4.875404800072976e-07, "loss": 0.0, "reward": 0.9955357238650322, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357238650322, "step": 58 }, { "completion_length": 266.13170623779297, "epoch": 0.07466168922071861, "grad_norm": 0.018763444577450522, "kl": 0.0355224609375, "learning_rate": 4.86392673521415e-07, "loss": 0.0, "reward": 0.9921875186264515, "reward_std": 0.022097086533904076, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9921875186264515, "step": 60 }, { "completion_length": 264.5323791503906, "epoch": 0.07715041219474257, "grad_norm": 0.006685649273344385, "kl": 0.032928466796875, "learning_rate": 4.851957747496606e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 62 }, { "completion_length": 269.7288055419922, "epoch": 0.07963913516876653, "grad_norm": 0.005778436612347605, "kl": 0.0353546142578125, "learning_rate": 4.839500322551386e-07, "loss": 0.0, "reward": 0.994419664144516, "reward_std": 0.015783633571118116, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.994419664144516, "step": 64 }, { "completion_length": 259.173002243042, "epoch": 0.08212785814279049, "grad_norm": 0.005211884618410732, "kl": 0.03321075439453125, "learning_rate": 4.826557047444563e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 66 }, { "completion_length": 266.08595275878906, "epoch": 0.08461658111681443, "grad_norm": 0.008193740275267598, "kl": 0.03182220458984375, "learning_rate": 4.813130610139993e-07, "loss": 0.0, "reward": 0.9955357313156128, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357313156128, "step": 68 }, { "completion_length": 264.5357275009155, "epoch": 0.08710530409083839, "grad_norm": 0.005236192803718056, "kl": 0.03408050537109375, "learning_rate": 4.799223798941089e-07, "loss": 0.0, "reward": 0.9944196492433548, "reward_std": 0.015783633571118116, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9944196492433548, "step": 70 }, { "completion_length": 254.89398574829102, "epoch": 0.08959402706486234, "grad_norm": 0.012593840996977298, "kl": 0.03564453125, "learning_rate": 4.78483950191177e-07, "loss": 0.0, "reward": 0.9955357313156128, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357313156128, "step": 72 }, { "completion_length": 258.49219703674316, "epoch": 0.0920827500388863, "grad_norm": 0.008244180466299824, "kl": 0.03539276123046875, "learning_rate": 4.769980706276687e-07, "loss": 0.0, "reward": 0.9955357238650322, "reward_std": 0.010446579195559025, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357238650322, "step": 74 }, { "completion_length": 254.81027793884277, "epoch": 0.09457147301291025, "grad_norm": 0.015490694406396487, "kl": 0.0354461669921875, "learning_rate": 4.7546504978008595e-07, "loss": 0.0, "reward": 0.9910714477300644, "reward_std": 0.025253813713788986, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9910714477300644, "step": 76 }, { "completion_length": 249.98550033569336, "epoch": 0.0970601959869342, "grad_norm": 0.01147964209306704, "kl": 0.036407470703125, "learning_rate": 4.738852060148848e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 78 }, { "completion_length": 253.0022439956665, "epoch": 0.09954891896095816, "grad_norm": 0.007444099420668922, "kl": 0.0356597900390625, "learning_rate": 4.722588674223593e-07, "loss": 0.0, "reward": 0.9944196566939354, "reward_std": 0.015783633571118116, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9944196566939354, "step": 80 }, { "completion_length": 257.6272449493408, "epoch": 0.10203764193498212, "grad_norm": 0.010780487057438663, "kl": 0.03473663330078125, "learning_rate": 4.70586371748506e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 82 }, { "completion_length": 260.4788064956665, "epoch": 0.10452636490900606, "grad_norm": 0.011815984815212375, "kl": 0.0367889404296875, "learning_rate": 4.6886806632488363e-07, "loss": 0.0, "reward": 0.9955357313156128, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357313156128, "step": 84 }, { "completion_length": 251.9944305419922, "epoch": 0.10701508788303002, "grad_norm": 0.008165684742827731, "kl": 0.0371551513671875, "learning_rate": 4.6710430799648143e-07, "loss": 0.0, "reward": 0.9955357313156128, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357313156128, "step": 86 }, { "completion_length": 250.82032203674316, "epoch": 0.10950381085705398, "grad_norm": 0.01157958760624767, "kl": 0.036041259765625, "learning_rate": 4.652954630476127e-07, "loss": 0.0, "reward": 0.9944196566939354, "reward_std": 0.015783633571118116, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9944196566939354, "step": 88 }, { "completion_length": 255.1462163925171, "epoch": 0.11199253383107793, "grad_norm": 0.0014016046187182924, "kl": 0.0375823974609375, "learning_rate": 4.6344190712584713e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 90 }, { "completion_length": 249.1640748977661, "epoch": 0.11448125680510188, "grad_norm": 0.0014472142931128767, "kl": 0.0380706787109375, "learning_rate": 4.615440251639995e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 92 }, { "completion_length": 256.1071557998657, "epoch": 0.11696997977912583, "grad_norm": 0.005854394163673583, "kl": 0.0372772216796875, "learning_rate": 4.596022113001894e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 94 }, { "completion_length": 239.82813549041748, "epoch": 0.11945870275314979, "grad_norm": 0.0014814527335160008, "kl": 0.03824615478515625, "learning_rate": 4.576168687959895e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 96 }, { "completion_length": 245.9185380935669, "epoch": 0.12194742572717375, "grad_norm": 0.009993182099046437, "kl": 0.03774261474609375, "learning_rate": 4.555884099526793e-07, "loss": 0.0, "reward": 0.994419664144516, "reward_std": 0.015783633571118116, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.994419664144516, "step": 98 }, { "completion_length": 243.829252243042, "epoch": 0.1244361487011977, "grad_norm": 0.0012629113621896403, "kl": 0.037689208984375, "learning_rate": 4.5351725602562174e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 100 }, { "completion_length": 240.93304634094238, "epoch": 0.12692487167522165, "grad_norm": 0.008888933685989486, "kl": 0.04000091552734375, "learning_rate": 4.514038371367791e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 102 }, { "completion_length": 250.9430913925171, "epoch": 0.1294135946492456, "grad_norm": 0.007935174731567693, "kl": 0.03668212890625, "learning_rate": 4.4924859218538936e-07, "loss": 0.0, "reward": 0.996651791036129, "reward_std": 0.0072898524813354015, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.996651791036129, "step": 104 }, { "completion_length": 253.6439847946167, "epoch": 0.13190231762326957, "grad_norm": 0.007207650723410012, "kl": 0.059051513671875, "learning_rate": 4.470519687568185e-07, "loss": 0.0001, "reward": 0.993303582072258, "reward_std": 0.01894036028534174, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.993303582072258, "step": 106 }, { "completion_length": 246.56920719146729, "epoch": 0.1343910405972935, "grad_norm": 0.006148168480495231, "kl": 0.036407470703125, "learning_rate": 4.4481442302960923e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 108 }, { "completion_length": 238.95313549041748, "epoch": 0.13687976357131748, "grad_norm": 0.009431097188708973, "kl": 0.035797119140625, "learning_rate": 4.4253641968074505e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 110 }, { "completion_length": 246.18081378936768, "epoch": 0.13936848654534142, "grad_norm": 0.005876057759970698, "kl": 0.037750244140625, "learning_rate": 4.402184317891501e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 112 }, { "completion_length": 248.73215198516846, "epoch": 0.14185720951936537, "grad_norm": 0.0077199360865173455, "kl": 0.0368499755859375, "learning_rate": 4.37860940737443e-07, "loss": 0.0, "reward": 0.9955357313156128, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357313156128, "step": 114 }, { "completion_length": 243.86273765563965, "epoch": 0.14434593249338934, "grad_norm": 0.0054189642531993635, "kl": 0.03558349609375, "learning_rate": 4.354644361119671e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 116 }, { "completion_length": 251.38617134094238, "epoch": 0.14683465546741328, "grad_norm": 0.006117742951139463, "kl": 0.0378570556640625, "learning_rate": 4.3302941560111716e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 118 }, { "completion_length": 250.118314743042, "epoch": 0.14932337844143723, "grad_norm": 0.008141566580477025, "kl": 0.0386962890625, "learning_rate": 4.3055638489198236e-07, "loss": 0.0, "reward": 0.9977678582072258, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678582072258, "step": 120 }, { "completion_length": 248.11273288726807, "epoch": 0.1518121014154612, "grad_norm": 0.0036890211568659974, "kl": 0.04131317138671875, "learning_rate": 4.280458575653296e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 122 }, { "completion_length": 248.6015739440918, "epoch": 0.15430082438948514, "grad_norm": 0.009172809538520958, "kl": 0.0360565185546875, "learning_rate": 4.2549835498894665e-07, "loss": 0.0, "reward": 0.994419664144516, "reward_std": 0.015783633571118116, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.994419664144516, "step": 124 }, { "completion_length": 242.13393878936768, "epoch": 0.1567895473635091, "grad_norm": 0.021937162250364135, "kl": 0.03790283203125, "learning_rate": 4.229144062093679e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 126 }, { "completion_length": 244.00000953674316, "epoch": 0.15927827033753306, "grad_norm": 0.013265008355772755, "kl": 0.037567138671875, "learning_rate": 4.2029454784200675e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 128 }, { "completion_length": 241.54353713989258, "epoch": 0.161766993311557, "grad_norm": 0.013941850356785124, "kl": 0.038330078125, "learning_rate": 4.1763932395971433e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 130 }, { "completion_length": 237.6663064956665, "epoch": 0.16425571628558097, "grad_norm": 0.009267818117271523, "kl": 0.0396575927734375, "learning_rate": 4.1494928597979117e-07, "loss": 0.0, "reward": 0.994419664144516, "reward_std": 0.015783633571118116, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.994419664144516, "step": 132 }, { "completion_length": 240.70090103149414, "epoch": 0.16674443925960492, "grad_norm": 0.012119765907156485, "kl": 0.0418548583984375, "learning_rate": 4.122249925494726e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 134 }, { "completion_length": 235.82367038726807, "epoch": 0.16923316223362886, "grad_norm": 0.0013331935396181439, "kl": 0.0379486083984375, "learning_rate": 4.094670094299131e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 136 }, { "completion_length": 233.64621543884277, "epoch": 0.17172188520765283, "grad_norm": 0.005329870298582281, "kl": 0.0389251708984375, "learning_rate": 4.066759093786931e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 138 }, { "completion_length": 244.22546005249023, "epoch": 0.17421060818167677, "grad_norm": 0.005619989780456964, "kl": 0.0381927490234375, "learning_rate": 4.038522720308732e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 140 }, { "completion_length": 242.11719799041748, "epoch": 0.17669933115570072, "grad_norm": 0.006376477165794642, "kl": 0.0377197265625, "learning_rate": 4.009966837786194e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 142 }, { "completion_length": 238.0703248977661, "epoch": 0.1791880541297247, "grad_norm": 0.028370327898306225, "kl": 0.03790283203125, "learning_rate": 3.981097376494259e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 144 }, { "completion_length": 244.7712163925171, "epoch": 0.18167677710374863, "grad_norm": 0.0015509057376277774, "kl": 0.0378265380859375, "learning_rate": 3.951920331829592e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 146 }, { "completion_length": 247.24666213989258, "epoch": 0.1841655000777726, "grad_norm": 0.0012690449195768786, "kl": 0.0364837646484375, "learning_rate": 3.922441763065506e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 148 }, { "completion_length": 240.0212163925171, "epoch": 0.18665422305179655, "grad_norm": 0.013797136486153857, "kl": 0.03704833984375, "learning_rate": 3.8926677920936093e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 150 }, { "completion_length": 246.80692958831787, "epoch": 0.1891429460258205, "grad_norm": 0.008542886544667705, "kl": 0.0371246337890625, "learning_rate": 3.862604602152464e-07, "loss": 0.0, "reward": 0.9944196566939354, "reward_std": 0.015783633571118116, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9944196566939354, "step": 152 }, { "completion_length": 237.7500123977661, "epoch": 0.19163166899984446, "grad_norm": 0.00848780488153459, "kl": 0.0372467041015625, "learning_rate": 3.8322584365434934e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 154 }, { "completion_length": 235.2388505935669, "epoch": 0.1941203919738684, "grad_norm": 0.0014224607179590997, "kl": 0.0376434326171875, "learning_rate": 3.8016355973344173e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 156 }, { "completion_length": 242.0346097946167, "epoch": 0.19660911494789235, "grad_norm": 0.007810868977196938, "kl": 0.0355224609375, "learning_rate": 3.7707424440504863e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 158 }, { "completion_length": 244.3404130935669, "epoch": 0.19909783792191632, "grad_norm": 0.006684946104716033, "kl": 0.035614013671875, "learning_rate": 3.739585392353787e-07, "loss": 0.0, "reward": 0.9955357313156128, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357313156128, "step": 160 }, { "completion_length": 246.79577159881592, "epoch": 0.20158656089594026, "grad_norm": 0.005256302746271805, "kl": 0.035919189453125, "learning_rate": 3.7081709127108767e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 162 }, { "completion_length": 240.33483219146729, "epoch": 0.20407528386996424, "grad_norm": 0.005275884352682047, "kl": 0.0363922119140625, "learning_rate": 3.6765055290490513e-07, "loss": 0.0, "reward": 0.994419664144516, "reward_std": 0.015783633571118116, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.994419664144516, "step": 164 }, { "completion_length": 244.2767972946167, "epoch": 0.20656400684398818, "grad_norm": 0.00905429835962999, "kl": 0.0367431640625, "learning_rate": 3.644595817401501e-07, "loss": 0.0, "reward": 0.9955357313156128, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357313156128, "step": 166 }, { "completion_length": 239.8694314956665, "epoch": 0.20905272981801212, "grad_norm": 0.001515588287808503, "kl": 0.0360565185546875, "learning_rate": 3.6124484045416483e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 168 }, { "completion_length": 245.84041213989258, "epoch": 0.2115414527920361, "grad_norm": 0.01143986411870428, "kl": 0.035736083984375, "learning_rate": 3.580069966606949e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 170 }, { "completion_length": 234.6406373977661, "epoch": 0.21403017576606004, "grad_norm": 0.012227399752466542, "kl": 0.0365753173828125, "learning_rate": 3.547467227712444e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 172 }, { "completion_length": 239.46206378936768, "epoch": 0.21651889874008398, "grad_norm": 0.0013708158434779418, "kl": 0.0361328125, "learning_rate": 3.5146469585543386e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 174 }, { "completion_length": 242.0636281967163, "epoch": 0.21900762171410795, "grad_norm": 0.005985792387537067, "kl": 0.03522491455078125, "learning_rate": 3.481615975003922e-07, "loss": 0.0, "reward": 0.9955357238650322, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357238650322, "step": 176 }, { "completion_length": 236.69867134094238, "epoch": 0.2214963446881319, "grad_norm": 0.005543063900031294, "kl": 0.0347747802734375, "learning_rate": 3.448381136692089e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 178 }, { "completion_length": 232.74442958831787, "epoch": 0.22398506766215587, "grad_norm": 0.016458488651150318, "kl": 0.0449371337890625, "learning_rate": 3.4149493455847897e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 180 }, { "completion_length": 239.68750953674316, "epoch": 0.2264737906361798, "grad_norm": 0.008616008287002855, "kl": 0.035369873046875, "learning_rate": 3.3813275445496766e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 182 }, { "completion_length": 237.28572463989258, "epoch": 0.22896251361020376, "grad_norm": 0.0012520075655868543, "kl": 0.0345611572265625, "learning_rate": 3.347522715914262e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 184 }, { "completion_length": 239.86608219146729, "epoch": 0.23145123658422773, "grad_norm": 0.006149863991426027, "kl": 0.035400390625, "learning_rate": 3.313541880015877e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 186 }, { "completion_length": 235.6138515472412, "epoch": 0.23393995955825167, "grad_norm": 0.006501865958706451, "kl": 0.0355377197265625, "learning_rate": 3.279392093743747e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 188 }, { "completion_length": 244.5089406967163, "epoch": 0.2364286825322756, "grad_norm": 0.008690843209276718, "kl": 0.03710174560546875, "learning_rate": 3.245080449073459e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 190 }, { "completion_length": 236.89286994934082, "epoch": 0.23891740550629958, "grad_norm": 0.010695035904088867, "kl": 0.0343170166015625, "learning_rate": 3.210614071594162e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 192 }, { "completion_length": 237.45425128936768, "epoch": 0.24140612848032353, "grad_norm": 0.008876854007516248, "kl": 0.0358428955078125, "learning_rate": 3.1760001190287695e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 194 }, { "completion_length": 232.3035831451416, "epoch": 0.2438948514543475, "grad_norm": 0.0012580700152787947, "kl": 0.0338134765625, "learning_rate": 3.141245779747502e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 196 }, { "completion_length": 236.17523384094238, "epoch": 0.24638357442837144, "grad_norm": 0.0013888134732519966, "kl": 0.03568267822265625, "learning_rate": 3.106358271275056e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 198 }, { "completion_length": 232.61384868621826, "epoch": 0.2488722974023954, "grad_norm": 0.0013082596723838322, "kl": 0.0361175537109375, "learning_rate": 3.0713448387917227e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 200 }, { "completion_length": 234.1596097946167, "epoch": 0.25136102037641933, "grad_norm": 0.005619002043642409, "kl": 0.035064697265625, "learning_rate": 3.0362127536287636e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 202 }, { "completion_length": 240.12724590301514, "epoch": 0.2538497433504433, "grad_norm": 0.001215418276843526, "kl": 0.032501220703125, "learning_rate": 3.0009693117583523e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 204 }, { "completion_length": 240.5993413925171, "epoch": 0.2563384663244673, "grad_norm": 0.0012980749880742157, "kl": 0.03325653076171875, "learning_rate": 2.965621832278401e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 206 }, { "completion_length": 238.35157299041748, "epoch": 0.2588271892984912, "grad_norm": 0.012326143240222623, "kl": 0.03427886962890625, "learning_rate": 2.9301776558925875e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 208 }, { "completion_length": 239.8359498977661, "epoch": 0.26131591227251516, "grad_norm": 0.00486814033751187, "kl": 0.03197479248046875, "learning_rate": 2.894644143385885e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 210 }, { "completion_length": 236.45759963989258, "epoch": 0.26380463524653913, "grad_norm": 0.00850905620683849, "kl": 0.0343170166015625, "learning_rate": 2.859028674095937e-07, "loss": 0.0, "reward": 0.996651791036129, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.996651791036129, "step": 212 }, { "completion_length": 234.11273288726807, "epoch": 0.26629335822056305, "grad_norm": 0.0011776757140757428, "kl": 0.0316925048828125, "learning_rate": 2.823338644380566e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 214 }, { "completion_length": 241.9665298461914, "epoch": 0.268782081194587, "grad_norm": 0.005375269654956656, "kl": 0.03156280517578125, "learning_rate": 2.7875814660817504e-07, "loss": 0.0, "reward": 0.9955357313156128, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357313156128, "step": 216 }, { "completion_length": 237.3906364440918, "epoch": 0.271270804168611, "grad_norm": 0.0045854327854698935, "kl": 0.03202056884765625, "learning_rate": 2.751764564986396e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 218 }, { "completion_length": 230.79688358306885, "epoch": 0.27375952714263496, "grad_norm": 0.008443268042406577, "kl": 0.031982421875, "learning_rate": 2.715895379284194e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 220 }, { "completion_length": 237.45759963989258, "epoch": 0.2762482501166589, "grad_norm": 0.0013591790273522189, "kl": 0.03302001953125, "learning_rate": 2.6799813580229174e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 222 }, { "completion_length": 241.00559043884277, "epoch": 0.27873697309068285, "grad_norm": 0.006856945865958338, "kl": 0.031402587890625, "learning_rate": 2.6440299595614606e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 224 }, { "completion_length": 242.82032585144043, "epoch": 0.2812256960647068, "grad_norm": 0.011147423978654824, "kl": 0.03250885009765625, "learning_rate": 2.6080486500209347e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 226 }, { "completion_length": 245.30581665039062, "epoch": 0.28371441903873074, "grad_norm": 0.008917482676403654, "kl": 0.03244781494140625, "learning_rate": 2.572044901734166e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 228 }, { "completion_length": 239.4486722946167, "epoch": 0.2862031420127547, "grad_norm": 0.0012479917659233364, "kl": 0.0322265625, "learning_rate": 2.536026191693893e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 230 }, { "completion_length": 240.26452255249023, "epoch": 0.2886918649867787, "grad_norm": 0.007817347570993229, "kl": 0.03277587890625, "learning_rate": 2.5e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 232 }, { "completion_length": 242.38840198516846, "epoch": 0.2911805879608026, "grad_norm": 0.004794984024963255, "kl": 0.03249359130859375, "learning_rate": 2.4639738083061073e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 234 }, { "completion_length": 234.61161708831787, "epoch": 0.29366931093482657, "grad_norm": 0.001402625251204755, "kl": 0.03316497802734375, "learning_rate": 2.4279550982658345e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 236 }, { "completion_length": 231.462064743042, "epoch": 0.29615803390885054, "grad_norm": 0.01673664168050879, "kl": 0.03163909912109375, "learning_rate": 2.3919513499790646e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 238 }, { "completion_length": 241.8259038925171, "epoch": 0.29864675688287445, "grad_norm": 0.0021634188282300413, "kl": 0.034698486328125, "learning_rate": 2.3559700404385394e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 240 }, { "completion_length": 240.47992134094238, "epoch": 0.3011354798568984, "grad_norm": 0.008658887288561594, "kl": 0.03231048583984375, "learning_rate": 2.3200186419770823e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 242 }, { "completion_length": 239.5848331451416, "epoch": 0.3036242028309224, "grad_norm": 0.0011648905322271979, "kl": 0.03226470947265625, "learning_rate": 2.284104620715807e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 244 }, { "completion_length": 230.66853523254395, "epoch": 0.3061129258049463, "grad_norm": 0.00123117657873765, "kl": 0.03214263916015625, "learning_rate": 2.2482354350136043e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 246 }, { "completion_length": 231.6562623977661, "epoch": 0.3086016487789703, "grad_norm": 0.0011476508674390896, "kl": 0.0305328369140625, "learning_rate": 2.2124185339182496e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 248 }, { "completion_length": 239.59152603149414, "epoch": 0.31109037175299425, "grad_norm": 0.001092011224535122, "kl": 0.02968597412109375, "learning_rate": 2.1766613556194344e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 250 }, { "completion_length": 233.17523384094238, "epoch": 0.3135790947270182, "grad_norm": 0.0011917811528517187, "kl": 0.0297393798828125, "learning_rate": 2.1409713259040628e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 252 }, { "completion_length": 240.12166118621826, "epoch": 0.31606781770104214, "grad_norm": 0.005939716498084994, "kl": 0.03424072265625, "learning_rate": 2.105355856614115e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 254 }, { "completion_length": 237.22322368621826, "epoch": 0.3185565406750661, "grad_norm": 0.007985852144002343, "kl": 0.03028106689453125, "learning_rate": 2.069822344107413e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 256 }, { "completion_length": 230.8951005935669, "epoch": 0.3210452636490901, "grad_norm": 0.0012251477176528757, "kl": 0.03383636474609375, "learning_rate": 2.034378167721599e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 258 }, { "completion_length": 241.6506814956665, "epoch": 0.323533986623114, "grad_norm": 0.005073098129706296, "kl": 0.0304107666015625, "learning_rate": 1.9990306882416485e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 260 }, { "completion_length": 237.0290288925171, "epoch": 0.32602270959713797, "grad_norm": 0.0011250188792632052, "kl": 0.0294952392578125, "learning_rate": 1.9637872463712362e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 262 }, { "completion_length": 241.60603618621826, "epoch": 0.32851143257116194, "grad_norm": 0.001159198174006997, "kl": 0.03064727783203125, "learning_rate": 1.9286551612082773e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 264 }, { "completion_length": 233.5770206451416, "epoch": 0.33100015554518586, "grad_norm": 0.008148989229574561, "kl": 0.02930450439453125, "learning_rate": 1.8936417287249446e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 266 }, { "completion_length": 246.89398384094238, "epoch": 0.33348887851920983, "grad_norm": 0.016173200021972613, "kl": 0.02889251708984375, "learning_rate": 1.8587542202524985e-07, "loss": 0.0, "reward": 0.9944196566939354, "reward_std": 0.015783633571118116, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9944196566939354, "step": 268 }, { "completion_length": 241.57701873779297, "epoch": 0.3359776014932338, "grad_norm": 0.007919979972576274, "kl": 0.0288543701171875, "learning_rate": 1.82399988097123e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 270 }, { "completion_length": 231.98438358306885, "epoch": 0.3384663244672577, "grad_norm": 0.005824865666987302, "kl": 0.0288848876953125, "learning_rate": 1.7893859284058378e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 272 }, { "completion_length": 240.15403079986572, "epoch": 0.3409550474412817, "grad_norm": 0.005849415216135437, "kl": 0.02838134765625, "learning_rate": 1.7549195509265407e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 274 }, { "completion_length": 236.81586074829102, "epoch": 0.34344377041530566, "grad_norm": 0.014300393698816647, "kl": 0.02855682373046875, "learning_rate": 1.7206079062562536e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 276 }, { "completion_length": 237.93304824829102, "epoch": 0.3459324933893296, "grad_norm": 0.006324763215032033, "kl": 0.02925872802734375, "learning_rate": 1.6864581199841226e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 278 }, { "completion_length": 235.18527793884277, "epoch": 0.34842121636335355, "grad_norm": 0.0011361122835219525, "kl": 0.04534149169921875, "learning_rate": 1.6524772840857388e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 280 }, { "completion_length": 236.23884868621826, "epoch": 0.3509099393373775, "grad_norm": 0.006624613315554435, "kl": 0.02925872802734375, "learning_rate": 1.6186724554503237e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 282 }, { "completion_length": 233.81363010406494, "epoch": 0.35339866231140143, "grad_norm": 0.0010583585640121704, "kl": 0.02803802490234375, "learning_rate": 1.5850506544152103e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 284 }, { "completion_length": 235.45648288726807, "epoch": 0.3558873852854254, "grad_norm": 0.006945667793827179, "kl": 0.03301239013671875, "learning_rate": 1.5516188633079107e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 286 }, { "completion_length": 232.47210884094238, "epoch": 0.3583761082594494, "grad_norm": 0.0058822702186793144, "kl": 0.03041839599609375, "learning_rate": 1.5183840249960784e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 288 }, { "completion_length": 233.774564743042, "epoch": 0.36086483123347335, "grad_norm": 0.0010805626564454967, "kl": 0.028167724609375, "learning_rate": 1.4853530414456612e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 290 }, { "completion_length": 237.87054824829102, "epoch": 0.36335355420749726, "grad_norm": 0.005734105971756099, "kl": 0.02758026123046875, "learning_rate": 1.4525327722875568e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 292 }, { "completion_length": 237.0993413925171, "epoch": 0.36584227718152124, "grad_norm": 0.017115197738888723, "kl": 0.0272064208984375, "learning_rate": 1.4199300333930515e-07, "loss": 0.0, "reward": 0.9955357238650322, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357238650322, "step": 294 }, { "completion_length": 232.11942958831787, "epoch": 0.3683310001555452, "grad_norm": 0.001178682970890626, "kl": 0.02896881103515625, "learning_rate": 1.3875515954583523e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 296 }, { "completion_length": 241.54911708831787, "epoch": 0.3708197231295691, "grad_norm": 0.01055702171846327, "kl": 0.02869415283203125, "learning_rate": 1.3554041825985e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 298 }, { "completion_length": 235.68304824829102, "epoch": 0.3733084461035931, "grad_norm": 0.006778222288303374, "kl": 0.0286407470703125, "learning_rate": 1.323494470950949e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 300 }, { "completion_length": 238.79130935668945, "epoch": 0.37579716907761707, "grad_norm": 0.008015757124174978, "kl": 0.02869415283203125, "learning_rate": 1.2918290872891236e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 302 }, { "completion_length": 233.8794755935669, "epoch": 0.378285892051641, "grad_norm": 0.0009938073180528301, "kl": 0.02816009521484375, "learning_rate": 1.260414607646213e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 304 }, { "completion_length": 242.52456665039062, "epoch": 0.38077461502566495, "grad_norm": 0.007613603270829063, "kl": 0.02838897705078125, "learning_rate": 1.2292575559495143e-07, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 306 }, { "completion_length": 236.0591630935669, "epoch": 0.3832633379996889, "grad_norm": 0.007171730472972239, "kl": 0.028594970703125, "learning_rate": 1.1983644026655835e-07, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 308 }, { "completion_length": 241.35604000091553, "epoch": 0.38575206097371284, "grad_norm": 0.0011600397120661158, "kl": 0.02840423583984375, "learning_rate": 1.1677415634565066e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 310 }, { "completion_length": 233.03907203674316, "epoch": 0.3882407839477368, "grad_norm": 0.0010814554021977632, "kl": 0.02860260009765625, "learning_rate": 1.1373953978475353e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 312 }, { "completion_length": 237.86831760406494, "epoch": 0.3907295069217608, "grad_norm": 0.0010944470027230678, "kl": 0.02793121337890625, "learning_rate": 1.1073322079063913e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 314 }, { "completion_length": 237.2890748977661, "epoch": 0.3932182298957847, "grad_norm": 0.01903527238338617, "kl": 0.02887725830078125, "learning_rate": 1.0775582369344946e-07, "loss": 0.0, "reward": 0.9955357201397419, "reward_std": 0.012626906391233206, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357201397419, "step": 316 }, { "completion_length": 241.7209939956665, "epoch": 0.39570695286980867, "grad_norm": 0.006903717479599212, "kl": 0.02970123291015625, "learning_rate": 1.0480796681704077e-07, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 318 }, { "completion_length": 236.0134038925171, "epoch": 0.39819567584383264, "grad_norm": 0.0011547787615559003, "kl": 0.02854156494140625, "learning_rate": 1.018902623505741e-07, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 320 }, { "completion_length": 241.60826969146729, "epoch": 0.4006843988178566, "grad_norm": 0.0010017599761343319, "kl": 0.02718353271484375, "learning_rate": 9.900331622138063e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 322 }, { "completion_length": 233.4330472946167, "epoch": 0.40317312179188053, "grad_norm": 0.0013114923906156683, "kl": 0.02910614013671875, "learning_rate": 9.614772796912681e-08, "loss": 0.0, "reward": 0.996651791036129, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.996651791036129, "step": 324 }, { "completion_length": 229.5357255935669, "epoch": 0.4056618447659045, "grad_norm": 0.0011343461889418145, "kl": 0.0290069580078125, "learning_rate": 9.332409062130686e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 326 }, { "completion_length": 241.87501335144043, "epoch": 0.40815056773992847, "grad_norm": 0.0066577720593599425, "kl": 0.0284423828125, "learning_rate": 9.053299057008699e-08, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 328 }, { "completion_length": 229.70648288726807, "epoch": 0.4106392907139524, "grad_norm": 0.0010762623483081323, "kl": 0.02895355224609375, "learning_rate": 8.777500745052743e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 330 }, { "completion_length": 229.516752243042, "epoch": 0.41312801368797636, "grad_norm": 0.001064089704651314, "kl": 0.02860260009765625, "learning_rate": 8.505071402020892e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 332 }, { "completion_length": 238.25670719146729, "epoch": 0.41561673666200033, "grad_norm": 0.00645868519135834, "kl": 0.03199005126953125, "learning_rate": 8.236067604028562e-08, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 334 }, { "completion_length": 233.23773574829102, "epoch": 0.41810545963602425, "grad_norm": 0.0015168370588455773, "kl": 0.02906036376953125, "learning_rate": 7.970545215799327e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 336 }, { "completion_length": 233.602689743042, "epoch": 0.4205941826100482, "grad_norm": 0.0010219844895423763, "kl": 0.02813720703125, "learning_rate": 7.708559379063204e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 338 }, { "completion_length": 231.45759773254395, "epoch": 0.4230829055840722, "grad_norm": 0.0013665815983744528, "kl": 0.030242919921875, "learning_rate": 7.45016450110534e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 340 }, { "completion_length": 238.58929824829102, "epoch": 0.4255716285580961, "grad_norm": 0.0009993803897500766, "kl": 0.02672576904296875, "learning_rate": 7.195414243467029e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 342 }, { "completion_length": 227.868314743042, "epoch": 0.4280603515321201, "grad_norm": 0.015796748341056373, "kl": 0.0280303955078125, "learning_rate": 6.944361510801763e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 344 }, { "completion_length": 236.65626049041748, "epoch": 0.43054907450614405, "grad_norm": 0.0010452832449649905, "kl": 0.02677154541015625, "learning_rate": 6.697058439888283e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 346 }, { "completion_length": 230.65514469146729, "epoch": 0.43303779748016796, "grad_norm": 0.001002506595208053, "kl": 0.02809906005859375, "learning_rate": 6.453556388803288e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 348 }, { "completion_length": 242.3861722946167, "epoch": 0.43552652045419193, "grad_norm": 0.008545847497911966, "kl": 0.02759552001953125, "learning_rate": 6.213905926255697e-08, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 350 }, { "completion_length": 232.85268878936768, "epoch": 0.4380152434282159, "grad_norm": 0.0011257932930819766, "kl": 0.029296875, "learning_rate": 5.978156821084987e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 352 }, { "completion_length": 233.83483219146729, "epoch": 0.4405039664022399, "grad_norm": 0.0012045288926858105, "kl": 0.0295257568359375, "learning_rate": 5.7463580319254853e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 354 }, { "completion_length": 242.27233219146729, "epoch": 0.4429926893762638, "grad_norm": 0.004569960372352263, "kl": 0.02753448486328125, "learning_rate": 5.518557697039081e-08, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 356 }, { "completion_length": 234.8716630935669, "epoch": 0.44548141235028776, "grad_norm": 0.0010851206277206634, "kl": 0.027191162109375, "learning_rate": 5.294803124318145e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 358 }, { "completion_length": 238.5435380935669, "epoch": 0.44797013532431174, "grad_norm": 0.005569266348540911, "kl": 0.0275421142578125, "learning_rate": 5.07514078146106e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 360 }, { "completion_length": 236.9576015472412, "epoch": 0.45045885829833565, "grad_norm": 0.020665916015112376, "kl": 0.02768707275390625, "learning_rate": 4.859616286322094e-08, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 362 }, { "completion_length": 239.62054634094238, "epoch": 0.4529475812723596, "grad_norm": 0.006716636201154639, "kl": 0.0279541015625, "learning_rate": 4.648274397437829e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 364 }, { "completion_length": 243.7142972946167, "epoch": 0.4554363042463836, "grad_norm": 0.008375247072193117, "kl": 0.02677154541015625, "learning_rate": 4.4411590047320617e-08, "loss": 0.0, "reward": 0.9955357313156128, "reward_std": 0.012626906856894493, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9955357313156128, "step": 366 }, { "completion_length": 231.89956378936768, "epoch": 0.4579250272204075, "grad_norm": 0.006050299420520613, "kl": 0.02796173095703125, "learning_rate": 4.2383131204010494e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 368 }, { "completion_length": 233.9709930419922, "epoch": 0.4604137501944315, "grad_norm": 0.005614903622972587, "kl": 0.02776336669921875, "learning_rate": 4.039778869981064e-08, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 370 }, { "completion_length": 237.66853618621826, "epoch": 0.46290247316845545, "grad_norm": 0.005600721897853672, "kl": 0.02752685546875, "learning_rate": 3.845597483600049e-08, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 372 }, { "completion_length": 233.05358123779297, "epoch": 0.46539119614247937, "grad_norm": 0.0050807254989125574, "kl": 0.02738189697265625, "learning_rate": 3.655809287415284e-08, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 374 }, { "completion_length": 231.516752243042, "epoch": 0.46787991911650334, "grad_norm": 0.005810047125219509, "kl": 0.0279083251953125, "learning_rate": 3.4704536952387285e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 376 }, { "completion_length": 238.53126049041748, "epoch": 0.4703686420905273, "grad_norm": 0.0010598227537549207, "kl": 0.028472900390625, "learning_rate": 3.2895692003518575e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 378 }, { "completion_length": 233.06139469146729, "epoch": 0.4728573650645512, "grad_norm": 0.0009997280997362191, "kl": 0.02701568603515625, "learning_rate": 3.113193367511635e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 380 }, { "completion_length": 238.0580472946167, "epoch": 0.4753460880385752, "grad_norm": 0.004960102294910648, "kl": 0.02744293212890625, "learning_rate": 2.9413628251493934e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 382 }, { "completion_length": 233.74108123779297, "epoch": 0.47783481101259917, "grad_norm": 0.0010633611406857888, "kl": 0.02855682373046875, "learning_rate": 2.774113257764066e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 384 }, { "completion_length": 240.4765739440918, "epoch": 0.48032353398662314, "grad_norm": 0.005811110894816115, "kl": 0.0283355712890625, "learning_rate": 2.611479398511518e-08, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 386 }, { "completion_length": 233.49889278411865, "epoch": 0.48281225696064706, "grad_norm": 0.0010872044363361894, "kl": 0.02774810791015625, "learning_rate": 2.4534950219914057e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 388 }, { "completion_length": 234.7712173461914, "epoch": 0.48530097993467103, "grad_norm": 0.00647383989173491, "kl": 0.02785491943359375, "learning_rate": 2.300192937233128e-08, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 390 }, { "completion_length": 237.8906373977661, "epoch": 0.487789702908695, "grad_norm": 0.0060801580997462655, "kl": 0.026580810546875, "learning_rate": 2.1516049808822935e-08, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 392 }, { "completion_length": 238.05916023254395, "epoch": 0.4902784258827189, "grad_norm": 0.0043540174002808405, "kl": 0.02710723876953125, "learning_rate": 2.007762010589098e-08, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 394 }, { "completion_length": 236.493314743042, "epoch": 0.4927671488567429, "grad_norm": 0.0009850409330263736, "kl": 0.0270843505859375, "learning_rate": 1.8686938986000627e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 396 }, { "completion_length": 238.78795623779297, "epoch": 0.49525587183076686, "grad_norm": 0.0009346164946872228, "kl": 0.0274200439453125, "learning_rate": 1.734429525554365e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 398 }, { "completion_length": 242.94197273254395, "epoch": 0.4977445948047908, "grad_norm": 0.0010475326616489664, "kl": 0.0272369384765625, "learning_rate": 1.604996774486145e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 400 }, { "completion_length": 232.65179538726807, "epoch": 0.5002333177788147, "grad_norm": 0.0015104224923932832, "kl": 0.03054046630859375, "learning_rate": 1.4804225250339281e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 402 }, { "completion_length": 234.68192958831787, "epoch": 0.5027220407528387, "grad_norm": 0.0010144168231863183, "kl": 0.02809906005859375, "learning_rate": 1.360732647858498e-08, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 404 }, { "completion_length": 240.7020206451416, "epoch": 0.5052107637268627, "grad_norm": 0.011133122318443774, "kl": 0.02752685546875, "learning_rate": 1.2459519992702311e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 406 }, { "completion_length": 237.8292531967163, "epoch": 0.5076994867008866, "grad_norm": 0.0011848309164625682, "kl": 0.027618408203125, "learning_rate": 1.1361044160671629e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 408 }, { "completion_length": 233.75670528411865, "epoch": 0.5101882096749105, "grad_norm": 0.0010625408361392933, "kl": 0.0267333984375, "learning_rate": 1.0312127105846947e-08, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 410 }, { "completion_length": 237.33817958831787, "epoch": 0.5126769326489345, "grad_norm": 0.007793581686460402, "kl": 0.0284576416015625, "learning_rate": 9.312986659581301e-09, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 412 }, { "completion_length": 233.3125114440918, "epoch": 0.5151656556229585, "grad_norm": 0.0010496450844472917, "kl": 0.02787017822265625, "learning_rate": 8.363830315988945e-09, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 414 }, { "completion_length": 230.6584939956665, "epoch": 0.5176543785969824, "grad_norm": 0.0011012715920442739, "kl": 0.02850341796875, "learning_rate": 7.46485518885462e-09, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 416 }, { "completion_length": 234.76675128936768, "epoch": 0.5201431015710064, "grad_norm": 0.0010189132878744552, "kl": 0.0274200439453125, "learning_rate": 6.616247970698319e-09, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 418 }, { "completion_length": 235.1004581451416, "epoch": 0.5226318245450303, "grad_norm": 0.0012076086244090446, "kl": 0.02881622314453125, "learning_rate": 5.8181848940044855e-09, "loss": 0.0, "reward": 0.996651791036129, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.996651791036129, "step": 420 }, { "completion_length": 242.5714406967163, "epoch": 0.5251205475190542, "grad_norm": 0.0009532448128675256, "kl": 0.026458740234375, "learning_rate": 5.070831694623135e-09, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 422 }, { "completion_length": 235.7656364440918, "epoch": 0.5276092704930783, "grad_norm": 0.0011084492135268256, "kl": 0.02764129638671875, "learning_rate": 4.374343577351336e-09, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 424 }, { "completion_length": 236.34710884094238, "epoch": 0.5300979934671022, "grad_norm": 0.0010636945299241864, "kl": 0.02762603759765625, "learning_rate": 3.7288651837012745e-09, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 426 }, { "completion_length": 232.45090007781982, "epoch": 0.5325867164411261, "grad_norm": 0.0010014166929854047, "kl": 0.02701568603515625, "learning_rate": 3.134530561862081e-09, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 428 }, { "completion_length": 229.3448781967163, "epoch": 0.5350754394151501, "grad_norm": 0.001004048594531098, "kl": 0.02599334716796875, "learning_rate": 2.5914631388619103e-09, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 430 }, { "completion_length": 234.39733123779297, "epoch": 0.537564162389174, "grad_norm": 0.001044397349569461, "kl": 0.02791595458984375, "learning_rate": 2.0997756949353297e-09, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 432 }, { "completion_length": 230.9609498977661, "epoch": 0.540052885363198, "grad_norm": 0.0010577923618969485, "kl": 0.02771759033203125, "learning_rate": 1.6595703401020844e-09, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 434 }, { "completion_length": 232.87054538726807, "epoch": 0.542541608337222, "grad_norm": 0.00624001051094032, "kl": 0.03231048583984375, "learning_rate": 1.2709384929615596e-09, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 436 }, { "completion_length": 230.40849113464355, "epoch": 0.5450303313112459, "grad_norm": 0.0058621450206555745, "kl": 0.02861785888671875, "learning_rate": 9.339608617077165e-10, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 438 }, { "completion_length": 240.4866180419922, "epoch": 0.5475190542852699, "grad_norm": 0.0011255089792763164, "kl": 0.027740478515625, "learning_rate": 6.487074273681114e-10, "loss": 0.0, "reward": 1.0, "reward_std": 0.0, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 1.0, "step": 440 }, { "completion_length": 235.4363956451416, "epoch": 0.5500077772592938, "grad_norm": 0.0011407272911082328, "kl": 0.029541015625, "learning_rate": 4.152374292708538e-10, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 442 }, { "completion_length": 236.4843873977661, "epoch": 0.5524965002333178, "grad_norm": 0.006496529221920559, "kl": 0.0265655517578125, "learning_rate": 2.3359935274214204e-10, "loss": 0.0, "reward": 0.9988839328289032, "reward_std": 0.0031567267142236233, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9988839328289032, "step": 444 }, { "completion_length": 238.70090293884277, "epoch": 0.5549852232073418, "grad_norm": 0.005033970606058095, "kl": 0.0269317626953125, "learning_rate": 1.0383091903720665e-10, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 446 }, { "completion_length": 235.43974113464355, "epoch": 0.5574739461813657, "grad_norm": 0.001040213545098924, "kl": 0.0272979736328125, "learning_rate": 2.595907750671533e-11, "loss": 0.0, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 448 }, { "completion_length": 235.83706188201904, "epoch": 0.5599626691553896, "grad_norm": 0.006177204331510563, "kl": 0.02693939208984375, "learning_rate": 0.0, "loss": 0.0, "reward": 0.9966517984867096, "reward_std": 0.00947018014267087, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9966517984867096, "step": 450 }, { "completion_length": 238.5446491241455, "epoch": 0.5612070306424016, "kl": 0.0272674560546875, "reward": 0.9977678656578064, "reward_std": 0.0063134534284472466, "rewards/equation_reward_func": 0.0, "rewards/format_reward_func": 0.9977678656578064, "step": 451, "total_flos": 0.0, "train_loss": 6.298603717921231e-08, "train_runtime": 66.8559, "train_samples_per_second": 376.93, "train_steps_per_second": 6.731 } ], "logging_steps": 2, "max_steps": 450, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 25, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }