{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.08, "eval_steps": 500, "global_step": 450, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "completion_length": 558.21875, "epoch": 0.00035555555555555557, "grad_norm": 0.16319611465157086, "kl": 0.0, "learning_rate": 7.142857142857142e-08, "loss": -0.0, "reward": 0.28125, "reward_std": 0.4586672969162464, "rewards/equation_reward_func": 0.015625, "rewards/format_reward_func": 0.265625, "step": 2 }, { "completion_length": 516.21875, "epoch": 0.0007111111111111111, "grad_norm": 0.17418126905911543, "kl": 0.00036662817001342773, "learning_rate": 1.4285714285714285e-07, "loss": 0.0, "reward": 0.3125, "reward_std": 0.4291788823902607, "rewards/equation_reward_func": 0.0703125, "rewards/format_reward_func": 0.2421875, "step": 4 }, { "completion_length": 511.15625, "epoch": 0.0010666666666666667, "grad_norm": 0.18686057402139436, "kl": 0.0004163980484008789, "learning_rate": 2.1428571428571426e-07, "loss": 0.0, "reward": 0.2578125, "reward_std": 0.4385656677186489, "rewards/equation_reward_func": 0.0625, "rewards/format_reward_func": 0.1953125, "step": 6 }, { "completion_length": 477.4609375, "epoch": 0.0014222222222222223, "grad_norm": 0.1777894589379156, "kl": 0.00041472911834716797, "learning_rate": 2.857142857142857e-07, "loss": 0.0, "reward": 0.3203125, "reward_std": 0.446503184735775, "rewards/equation_reward_func": 0.046875, "rewards/format_reward_func": 0.2734375, "step": 8 }, { "completion_length": 506.890625, "epoch": 0.0017777777777777779, "grad_norm": 0.2354010939066695, "kl": 0.0004538297653198242, "learning_rate": 3.5714285714285716e-07, "loss": 0.0, "reward": 0.3828125, "reward_std": 0.4801974333822727, "rewards/equation_reward_func": 0.0703125, "rewards/format_reward_func": 0.3125, "step": 10 }, { "completion_length": 475.9765625, "epoch": 0.0021333333333333334, "grad_norm": 0.17183303573120517, "kl": 0.0004565715789794922, "learning_rate": 4.285714285714285e-07, "loss": 0.0, "reward": 0.2578125, "reward_std": 0.4146980494260788, "rewards/equation_reward_func": 0.015625, "rewards/format_reward_func": 0.2421875, "step": 12 }, { "completion_length": 522.140625, "epoch": 0.002488888888888889, "grad_norm": 0.19584841533297276, "kl": 0.0005878210067749023, "learning_rate": 5e-07, "loss": 0.0, "reward": 0.3984375, "reward_std": 0.5455609019845724, "rewards/equation_reward_func": 0.0625, "rewards/format_reward_func": 0.3359375, "step": 14 }, { "completion_length": 504.8359375, "epoch": 0.0028444444444444446, "grad_norm": 0.1963897788415132, "kl": 0.0007581710815429688, "learning_rate": 4.999740409224932e-07, "loss": 0.0, "reward": 0.4453125, "reward_std": 0.507007647305727, "rewards/equation_reward_func": 0.0390625, "rewards/format_reward_func": 0.40625, "step": 16 }, { "completion_length": 439.265625, "epoch": 0.0032, "grad_norm": 0.17301487165752755, "kl": 0.0015461444854736328, "learning_rate": 4.998961690809627e-07, "loss": 0.0, "reward": 0.6015625, "reward_std": 0.5544095803052187, "rewards/equation_reward_func": 0.078125, "rewards/format_reward_func": 0.5234375, "step": 18 }, { "completion_length": 440.75, "epoch": 0.0035555555555555557, "grad_norm": 0.1656037102176249, "kl": 0.004067420959472656, "learning_rate": 4.997664006472578e-07, "loss": 0.0, "reward": 0.734375, "reward_std": 0.5903380792587996, "rewards/equation_reward_func": 0.125, "rewards/format_reward_func": 0.609375, "step": 20 }, { "completion_length": 411.96875, "epoch": 0.003911111111111111, "grad_norm": 0.1908015876481413, "kl": 0.00445556640625, "learning_rate": 4.995847625707292e-07, "loss": 0.0, "reward": 0.765625, "reward_std": 0.5255697090178728, "rewards/equation_reward_func": 0.0859375, "rewards/format_reward_func": 0.6796875, "step": 22 }, { "completion_length": 445.640625, "epoch": 0.004266666666666667, "grad_norm": 0.19251232902264467, "kl": 0.005351066589355469, "learning_rate": 4.993512925726318e-07, "loss": 0.0, "reward": 0.8203125, "reward_std": 0.4650081805884838, "rewards/equation_reward_func": 0.0625, "rewards/format_reward_func": 0.7578125, "step": 24 }, { "completion_length": 450.7890625, "epoch": 0.004622222222222222, "grad_norm": 0.1362690788735505, "kl": 0.0061969757080078125, "learning_rate": 4.990660391382923e-07, "loss": 0.0, "reward": 0.8828125, "reward_std": 0.49951413460075855, "rewards/equation_reward_func": 0.1015625, "rewards/format_reward_func": 0.78125, "step": 26 }, { "completion_length": 427.34375, "epoch": 0.004977777777777778, "grad_norm": 0.1397441605336418, "kl": 0.0075531005859375, "learning_rate": 4.987290615070384e-07, "loss": 0.0, "reward": 1.03125, "reward_std": 0.3855034988373518, "rewards/equation_reward_func": 0.140625, "rewards/format_reward_func": 0.890625, "step": 28 }, { "completion_length": 449.6953125, "epoch": 0.005333333333333333, "grad_norm": 0.13266541127233653, "kl": 0.008485794067382812, "learning_rate": 4.983404296598978e-07, "loss": 0.0, "reward": 0.90625, "reward_std": 0.42431665025651455, "rewards/equation_reward_func": 0.109375, "rewards/format_reward_func": 0.796875, "step": 30 }, { "completion_length": 449.546875, "epoch": 0.005688888888888889, "grad_norm": 0.17828848506675551, "kl": 0.009744644165039062, "learning_rate": 4.979002243050646e-07, "loss": 0.0, "reward": 0.9765625, "reward_std": 0.4631799254566431, "rewards/equation_reward_func": 0.1171875, "rewards/format_reward_func": 0.859375, "step": 32 }, { "completion_length": 513.921875, "epoch": 0.006044444444444444, "grad_norm": 0.14516749872112322, "kl": 0.009546279907226562, "learning_rate": 4.974085368611381e-07, "loss": 0.0, "reward": 0.9453125, "reward_std": 0.37294892966747284, "rewards/equation_reward_func": 0.0625, "rewards/format_reward_func": 0.8828125, "step": 34 }, { "completion_length": 471.6796875, "epoch": 0.0064, "grad_norm": 0.1472615847955791, "kl": 0.010135650634765625, "learning_rate": 4.968654694381379e-07, "loss": 0.0, "reward": 1.0078125, "reward_std": 0.36952908150851727, "rewards/equation_reward_func": 0.109375, "rewards/format_reward_func": 0.8984375, "step": 36 }, { "completion_length": 502.9921875, "epoch": 0.0067555555555555554, "grad_norm": 0.11856505582596304, "kl": 0.016201019287109375, "learning_rate": 4.962711348162987e-07, "loss": 0.0, "reward": 0.9453125, "reward_std": 0.33866361156105995, "rewards/equation_reward_func": 0.078125, "rewards/format_reward_func": 0.8671875, "step": 38 }, { "completion_length": 438.1875, "epoch": 0.0071111111111111115, "grad_norm": 0.1491753865500343, "kl": 0.01209259033203125, "learning_rate": 4.956256564226487e-07, "loss": 0.0, "reward": 1.0234375, "reward_std": 0.29591915011405945, "rewards/equation_reward_func": 0.09375, "rewards/format_reward_func": 0.9296875, "step": 40 }, { "completion_length": 428.75, "epoch": 0.007466666666666667, "grad_norm": 0.10965524897254234, "kl": 0.01348876953125, "learning_rate": 4.949291683053768e-07, "loss": 0.0, "reward": 1.0703125, "reward_std": 0.3557952530682087, "rewards/equation_reward_func": 0.1328125, "rewards/format_reward_func": 0.9375, "step": 42 }, { "completion_length": 483.65625, "epoch": 0.007822222222222222, "grad_norm": 0.07034266397094524, "kl": 0.019378662109375, "learning_rate": 4.941818151059955e-07, "loss": 0.0, "reward": 0.9921875, "reward_std": 0.182886628434062, "rewards/equation_reward_func": 0.0390625, "rewards/format_reward_func": 0.953125, "step": 44 }, { "completion_length": 425.375, "epoch": 0.008177777777777779, "grad_norm": 0.14631602871481755, "kl": 0.01434326171875, "learning_rate": 4.933837520293017e-07, "loss": 0.0, "reward": 1.0625, "reward_std": 0.35122798942029476, "rewards/equation_reward_func": 0.1328125, "rewards/format_reward_func": 0.9296875, "step": 46 }, { "completion_length": 435.6328125, "epoch": 0.008533333333333334, "grad_norm": 0.16370041909573974, "kl": 0.01432037353515625, "learning_rate": 4.925351448111454e-07, "loss": 0.0, "reward": 1.109375, "reward_std": 0.3174794539809227, "rewards/equation_reward_func": 0.1640625, "rewards/format_reward_func": 0.9453125, "step": 48 }, { "completion_length": 442.1171875, "epoch": 0.008888888888888889, "grad_norm": 0.1311062256072383, "kl": 0.014678955078125, "learning_rate": 4.91636169684011e-07, "loss": 0.0, "reward": 1.0703125, "reward_std": 0.30886387825012207, "rewards/equation_reward_func": 0.125, "rewards/format_reward_func": 0.9453125, "step": 50 }, { "completion_length": 430.7578125, "epoch": 0.009244444444444444, "grad_norm": 0.13267168261468218, "kl": 0.01804351806640625, "learning_rate": 4.906870133404186e-07, "loss": 0.0, "reward": 1.0703125, "reward_std": 0.2635674234479666, "rewards/equation_reward_func": 0.109375, "rewards/format_reward_func": 0.9609375, "step": 52 }, { "completion_length": 411.578125, "epoch": 0.0096, "grad_norm": 0.17179126795155464, "kl": 0.01618194580078125, "learning_rate": 4.896878728941531e-07, "loss": 0.0, "reward": 1.140625, "reward_std": 0.29143064096570015, "rewards/equation_reward_func": 0.15625, "rewards/format_reward_func": 0.984375, "step": 54 }, { "completion_length": 398.4453125, "epoch": 0.009955555555555556, "grad_norm": 0.14196611468000556, "kl": 0.016681671142578125, "learning_rate": 4.886389558393284e-07, "loss": 0.0, "reward": 1.109375, "reward_std": 0.26196980848908424, "rewards/equation_reward_func": 0.125, "rewards/format_reward_func": 0.984375, "step": 56 }, { "completion_length": 389.7890625, "epoch": 0.010311111111111111, "grad_norm": 0.1476241924443653, "kl": 0.019023895263671875, "learning_rate": 4.875404800072976e-07, "loss": 0.0, "reward": 1.1484375, "reward_std": 0.3381521496921778, "rewards/equation_reward_func": 0.171875, "rewards/format_reward_func": 0.9765625, "step": 58 }, { "completion_length": 388.6015625, "epoch": 0.010666666666666666, "grad_norm": 0.11394197670203084, "kl": 0.0216827392578125, "learning_rate": 4.86392673521415e-07, "loss": 0.0, "reward": 1.0703125, "reward_std": 0.22548809088766575, "rewards/equation_reward_func": 0.09375, "rewards/format_reward_func": 0.9765625, "step": 60 }, { "completion_length": 368.5625, "epoch": 0.011022222222222221, "grad_norm": 0.13423259129208498, "kl": 0.018878936767578125, "learning_rate": 4.851957747496606e-07, "loss": 0.0, "reward": 1.140625, "reward_std": 0.30397036112844944, "rewards/equation_reward_func": 0.1640625, "rewards/format_reward_func": 0.9765625, "step": 62 }, { "completion_length": 400.7734375, "epoch": 0.011377777777777778, "grad_norm": 0.08843954217928876, "kl": 0.0186004638671875, "learning_rate": 4.839500322551386e-07, "loss": 0.0, "reward": 1.0625, "reward_std": 0.25172007270157337, "rewards/equation_reward_func": 0.1015625, "rewards/format_reward_func": 0.9609375, "step": 64 }, { "completion_length": 393.4296875, "epoch": 0.011733333333333333, "grad_norm": 0.11714237597674881, "kl": 0.02496337890625, "learning_rate": 4.826557047444563e-07, "loss": 0.0, "reward": 1.1640625, "reward_std": 0.27939521707594395, "rewards/equation_reward_func": 0.1953125, "rewards/format_reward_func": 0.96875, "step": 66 }, { "completion_length": 417.25, "epoch": 0.012088888888888889, "grad_norm": 0.1544015474537589, "kl": 0.020420074462890625, "learning_rate": 4.813130610139993e-07, "loss": 0.0, "reward": 1.109375, "reward_std": 0.33851570822298527, "rewards/equation_reward_func": 0.1484375, "rewards/format_reward_func": 0.9609375, "step": 68 }, { "completion_length": 432.0703125, "epoch": 0.012444444444444444, "grad_norm": 0.12342065446113715, "kl": 0.023410797119140625, "learning_rate": 4.799223798941089e-07, "loss": 0.0, "reward": 1.09375, "reward_std": 0.36288236267864704, "rewards/equation_reward_func": 0.1484375, "rewards/format_reward_func": 0.9453125, "step": 70 }, { "completion_length": 389.6640625, "epoch": 0.0128, "grad_norm": 0.14656284486731108, "kl": 0.0208740234375, "learning_rate": 4.78483950191177e-07, "loss": 0.0, "reward": 1.125, "reward_std": 0.2977413833141327, "rewards/equation_reward_func": 0.140625, "rewards/format_reward_func": 0.984375, "step": 72 }, { "completion_length": 386.0234375, "epoch": 0.013155555555555556, "grad_norm": 0.1322785515012084, "kl": 0.0208892822265625, "learning_rate": 4.769980706276687e-07, "loss": 0.0, "reward": 1.1875, "reward_std": 0.23033758997917175, "rewards/equation_reward_func": 0.1953125, "rewards/format_reward_func": 0.9921875, "step": 74 }, { "completion_length": 391.1171875, "epoch": 0.013511111111111111, "grad_norm": 0.137897578511538, "kl": 0.02099609375, "learning_rate": 4.7546504978008595e-07, "loss": 0.0, "reward": 1.1640625, "reward_std": 0.3311441335827112, "rewards/equation_reward_func": 0.1953125, "rewards/format_reward_func": 0.96875, "step": 76 }, { "completion_length": 418.8125, "epoch": 0.013866666666666666, "grad_norm": 0.10892568772438567, "kl": 0.021595001220703125, "learning_rate": 4.738852060148848e-07, "loss": 0.0, "reward": 1.09375, "reward_std": 0.2359209954738617, "rewards/equation_reward_func": 0.1328125, "rewards/format_reward_func": 0.9609375, "step": 78 }, { "completion_length": 369.0, "epoch": 0.014222222222222223, "grad_norm": 0.12919106909292583, "kl": 0.02898406982421875, "learning_rate": 4.722588674223593e-07, "loss": 0.0, "reward": 1.1484375, "reward_std": 0.21382390893995762, "rewards/equation_reward_func": 0.1484375, "rewards/format_reward_func": 1.0, "step": 80 }, { "completion_length": 370.3515625, "epoch": 0.014577777777777778, "grad_norm": 0.15310962735407482, "kl": 0.02521514892578125, "learning_rate": 4.70586371748506e-07, "loss": 0.0, "reward": 1.1484375, "reward_std": 0.36273445934057236, "rewards/equation_reward_func": 0.1875, "rewards/format_reward_func": 0.9609375, "step": 82 }, { "completion_length": 396.390625, "epoch": 0.014933333333333333, "grad_norm": 0.13989921599508573, "kl": 0.0299530029296875, "learning_rate": 4.6886806632488363e-07, "loss": 0.0, "reward": 1.1171875, "reward_std": 0.3056321032345295, "rewards/equation_reward_func": 0.140625, "rewards/format_reward_func": 0.9765625, "step": 84 }, { "completion_length": 400.7734375, "epoch": 0.015288888888888888, "grad_norm": 0.16427882618928974, "kl": 0.0267181396484375, "learning_rate": 4.6710430799648143e-07, "loss": 0.0, "reward": 1.21875, "reward_std": 0.3713865801692009, "rewards/equation_reward_func": 0.2421875, "rewards/format_reward_func": 0.9765625, "step": 86 }, { "completion_length": 395.515625, "epoch": 0.015644444444444443, "grad_norm": 0.15324522374897853, "kl": 0.030181884765625, "learning_rate": 4.652954630476127e-07, "loss": 0.0, "reward": 1.1484375, "reward_std": 0.25547589734196663, "rewards/equation_reward_func": 0.171875, "rewards/format_reward_func": 0.9765625, "step": 88 }, { "completion_length": 425.8984375, "epoch": 0.016, "grad_norm": 0.1254448594399879, "kl": 0.0306243896484375, "learning_rate": 4.6344190712584713e-07, "loss": 0.0, "reward": 1.046875, "reward_std": 0.23911622539162636, "rewards/equation_reward_func": 0.078125, "rewards/format_reward_func": 0.96875, "step": 90 }, { "completion_length": 392.8828125, "epoch": 0.016355555555555557, "grad_norm": 0.11207079919662942, "kl": 0.03009033203125, "learning_rate": 4.615440251639995e-07, "loss": 0.0, "reward": 1.1484375, "reward_std": 0.2369818277657032, "rewards/equation_reward_func": 0.15625, "rewards/format_reward_func": 0.9921875, "step": 92 }, { "completion_length": 384.5546875, "epoch": 0.01671111111111111, "grad_norm": 0.14199339358701857, "kl": 0.04071044921875, "learning_rate": 4.596022113001894e-07, "loss": 0.0, "reward": 1.25, "reward_std": 0.3733201716095209, "rewards/equation_reward_func": 0.28125, "rewards/format_reward_func": 0.96875, "step": 94 }, { "completion_length": 437.5625, "epoch": 0.017066666666666667, "grad_norm": 0.12806187866277957, "kl": 0.041961669921875, "learning_rate": 4.576168687959895e-07, "loss": 0.0, "reward": 1.1015625, "reward_std": 0.20016413368284702, "rewards/equation_reward_func": 0.109375, "rewards/format_reward_func": 0.9921875, "step": 96 }, { "completion_length": 384.7734375, "epoch": 0.01742222222222222, "grad_norm": 0.16560343482417905, "kl": 0.0358428955078125, "learning_rate": 4.555884099526793e-07, "loss": 0.0, "reward": 1.2109375, "reward_std": 0.3128028716892004, "rewards/equation_reward_func": 0.21875, "rewards/format_reward_func": 0.9921875, "step": 98 }, { "completion_length": 377.8046875, "epoch": 0.017777777777777778, "grad_norm": 0.06544152830497535, "kl": 0.0405426025390625, "learning_rate": 4.5351725602562174e-07, "loss": 0.0, "reward": 1.109375, "reward_std": 0.14123954437673092, "rewards/equation_reward_func": 0.1171875, "rewards/format_reward_func": 0.9921875, "step": 100 }, { "completion_length": 360.8828125, "epoch": 0.018133333333333335, "grad_norm": 0.11192315546197115, "kl": 0.037384033203125, "learning_rate": 4.514038371367791e-07, "loss": 0.0, "reward": 1.15625, "reward_std": 0.2957183439284563, "rewards/equation_reward_func": 0.1796875, "rewards/format_reward_func": 0.9765625, "step": 102 }, { "completion_length": 355.203125, "epoch": 0.018488888888888888, "grad_norm": 0.12420501860194036, "kl": 0.06029510498046875, "learning_rate": 4.4924859218538936e-07, "loss": 0.0001, "reward": 1.15625, "reward_std": 0.25118329003453255, "rewards/equation_reward_func": 0.171875, "rewards/format_reward_func": 0.984375, "step": 104 }, { "completion_length": 378.75, "epoch": 0.018844444444444445, "grad_norm": 0.12758866020524365, "kl": 0.0380859375, "learning_rate": 4.470519687568185e-07, "loss": 0.0, "reward": 1.1015625, "reward_std": 0.2606765292584896, "rewards/equation_reward_func": 0.1171875, "rewards/format_reward_func": 0.984375, "step": 106 }, { "completion_length": 380.8203125, "epoch": 0.0192, "grad_norm": 0.16123721776657848, "kl": 0.04666900634765625, "learning_rate": 4.4481442302960923e-07, "loss": 0.0, "reward": 1.1171875, "reward_std": 0.2664504889398813, "rewards/equation_reward_func": 0.1328125, "rewards/format_reward_func": 0.984375, "step": 108 }, { "completion_length": 384.2578125, "epoch": 0.019555555555555555, "grad_norm": 0.1514840733121254, "kl": 0.0447998046875, "learning_rate": 4.4253641968074505e-07, "loss": 0.0, "reward": 1.2265625, "reward_std": 0.30851516872644424, "rewards/equation_reward_func": 0.2265625, "rewards/format_reward_func": 1.0, "step": 110 }, { "completion_length": 374.7578125, "epoch": 0.019911111111111112, "grad_norm": 0.13918628422029689, "kl": 0.0448150634765625, "learning_rate": 4.402184317891501e-07, "loss": 0.0, "reward": 1.2109375, "reward_std": 0.32930916734039783, "rewards/equation_reward_func": 0.234375, "rewards/format_reward_func": 0.9765625, "step": 112 }, { "completion_length": 365.015625, "epoch": 0.020266666666666665, "grad_norm": 0.1357853470773616, "kl": 0.0449066162109375, "learning_rate": 4.37860940737443e-07, "loss": 0.0, "reward": 1.3125, "reward_std": 0.3374421428889036, "rewards/equation_reward_func": 0.3203125, "rewards/format_reward_func": 0.9921875, "step": 114 }, { "completion_length": 373.3671875, "epoch": 0.020622222222222222, "grad_norm": 0.14960512254555802, "kl": 0.0490875244140625, "learning_rate": 4.354644361119671e-07, "loss": 0.0, "reward": 1.1796875, "reward_std": 0.21382390893995762, "rewards/equation_reward_func": 0.1875, "rewards/format_reward_func": 0.9921875, "step": 116 }, { "completion_length": 378.625, "epoch": 0.02097777777777778, "grad_norm": 0.1510812591190034, "kl": 0.0518798828125, "learning_rate": 4.3302941560111716e-07, "loss": 0.0001, "reward": 1.2734375, "reward_std": 0.31605015881359577, "rewards/equation_reward_func": 0.28125, "rewards/format_reward_func": 0.9921875, "step": 118 }, { "completion_length": 380.46875, "epoch": 0.021333333333333333, "grad_norm": 0.14734857757565625, "kl": 0.0499420166015625, "learning_rate": 4.3055638489198236e-07, "loss": 0.0, "reward": 1.1484375, "reward_std": 0.28012007288634777, "rewards/equation_reward_func": 0.171875, "rewards/format_reward_func": 0.9765625, "step": 120 }, { "completion_length": 378.453125, "epoch": 0.02168888888888889, "grad_norm": 0.1541652488299738, "kl": 0.0516815185546875, "learning_rate": 4.280458575653296e-07, "loss": 0.0001, "reward": 1.21875, "reward_std": 0.30403448827564716, "rewards/equation_reward_func": 0.234375, "rewards/format_reward_func": 0.984375, "step": 122 }, { "completion_length": 331.6953125, "epoch": 0.022044444444444443, "grad_norm": 0.1800491418335961, "kl": 0.0565338134765625, "learning_rate": 4.2549835498894665e-07, "loss": 0.0001, "reward": 1.34375, "reward_std": 0.34010059013962746, "rewards/equation_reward_func": 0.3515625, "rewards/format_reward_func": 0.9921875, "step": 124 }, { "completion_length": 348.4140625, "epoch": 0.0224, "grad_norm": 0.1794948955818512, "kl": 0.057586669921875, "learning_rate": 4.229144062093679e-07, "loss": 0.0001, "reward": 1.296875, "reward_std": 0.3322049658745527, "rewards/equation_reward_func": 0.3046875, "rewards/format_reward_func": 0.9921875, "step": 126 }, { "completion_length": 388.171875, "epoch": 0.022755555555555557, "grad_norm": 0.143172951066265, "kl": 0.0540313720703125, "learning_rate": 4.2029454784200675e-07, "loss": 0.0001, "reward": 1.1875, "reward_std": 0.31116871163249016, "rewards/equation_reward_func": 0.203125, "rewards/format_reward_func": 0.984375, "step": 128 }, { "completion_length": 328.7578125, "epoch": 0.02311111111111111, "grad_norm": 0.15975290384389043, "kl": 0.073944091796875, "learning_rate": 4.1763932395971433e-07, "loss": 0.0001, "reward": 1.3359375, "reward_std": 0.35031135752797127, "rewards/equation_reward_func": 0.3515625, "rewards/format_reward_func": 0.984375, "step": 130 }, { "completion_length": 392.6953125, "epoch": 0.023466666666666667, "grad_norm": 0.15405003814264823, "kl": 0.0763092041015625, "learning_rate": 4.1494928597979117e-07, "loss": 0.0001, "reward": 1.203125, "reward_std": 0.3124668952077627, "rewards/equation_reward_func": 0.2421875, "rewards/format_reward_func": 0.9609375, "step": 132 }, { "completion_length": 353.1484375, "epoch": 0.023822222222222224, "grad_norm": 0.19135038627848672, "kl": 0.0674285888671875, "learning_rate": 4.122249925494726e-07, "loss": 0.0001, "reward": 1.203125, "reward_std": 0.2993340939283371, "rewards/equation_reward_func": 0.203125, "rewards/format_reward_func": 1.0, "step": 134 }, { "completion_length": 381.6796875, "epoch": 0.024177777777777777, "grad_norm": 0.15650361206530433, "kl": 0.065765380859375, "learning_rate": 4.094670094299131e-07, "loss": 0.0001, "reward": 1.2734375, "reward_std": 0.34999459609389305, "rewards/equation_reward_func": 0.3125, "rewards/format_reward_func": 0.9609375, "step": 136 }, { "completion_length": 408.96875, "epoch": 0.024533333333333334, "grad_norm": 0.1551337440537955, "kl": 0.0649566650390625, "learning_rate": 4.066759093786931e-07, "loss": 0.0001, "reward": 1.2734375, "reward_std": 0.3595039639621973, "rewards/equation_reward_func": 0.3125, "rewards/format_reward_func": 0.9609375, "step": 138 }, { "completion_length": 365.265625, "epoch": 0.024888888888888887, "grad_norm": 0.14349181297141309, "kl": 0.0655364990234375, "learning_rate": 4.038522720308732e-07, "loss": 0.0001, "reward": 1.34375, "reward_std": 0.28242738731205463, "rewards/equation_reward_func": 0.359375, "rewards/format_reward_func": 0.984375, "step": 140 }, { "completion_length": 417.859375, "epoch": 0.025244444444444444, "grad_norm": 0.12417767012343875, "kl": 0.0717010498046875, "learning_rate": 4.009966837786194e-07, "loss": 0.0001, "reward": 1.1484375, "reward_std": 0.2211486864835024, "rewards/equation_reward_func": 0.15625, "rewards/format_reward_func": 0.9921875, "step": 142 }, { "completion_length": 413.171875, "epoch": 0.0256, "grad_norm": 0.15012499276377514, "kl": 0.0660858154296875, "learning_rate": 3.981097376494259e-07, "loss": 0.0001, "reward": 1.2734375, "reward_std": 0.33003650419414043, "rewards/equation_reward_func": 0.2890625, "rewards/format_reward_func": 0.984375, "step": 144 }, { "completion_length": 359.765625, "epoch": 0.025955555555555555, "grad_norm": 0.15995574283554995, "kl": 0.0708770751953125, "learning_rate": 3.951920331829592e-07, "loss": 0.0001, "reward": 1.2421875, "reward_std": 0.277237007394433, "rewards/equation_reward_func": 0.2734375, "rewards/format_reward_func": 0.96875, "step": 146 }, { "completion_length": 417.5078125, "epoch": 0.02631111111111111, "grad_norm": 0.17208499354721293, "kl": 0.0723419189453125, "learning_rate": 3.922441763065506e-07, "loss": 0.0001, "reward": 1.234375, "reward_std": 0.3679391499608755, "rewards/equation_reward_func": 0.2734375, "rewards/format_reward_func": 0.9609375, "step": 148 }, { "completion_length": 417.3671875, "epoch": 0.02666666666666667, "grad_norm": 0.17080855226672484, "kl": 0.0657806396484375, "learning_rate": 3.8926677920936093e-07, "loss": 0.0001, "reward": 1.2109375, "reward_std": 0.37137173116207123, "rewards/equation_reward_func": 0.2578125, "rewards/format_reward_func": 0.953125, "step": 150 }, { "completion_length": 452.265625, "epoch": 0.027022222222222222, "grad_norm": 0.13098468802735794, "kl": 0.062225341796875, "learning_rate": 3.862604602152464e-07, "loss": 0.0001, "reward": 1.3046875, "reward_std": 0.3546949904412031, "rewards/equation_reward_func": 0.3515625, "rewards/format_reward_func": 0.953125, "step": 152 }, { "completion_length": 456.4609375, "epoch": 0.02737777777777778, "grad_norm": 0.13309465770298312, "kl": 0.0681304931640625, "learning_rate": 3.8322584365434934e-07, "loss": 0.0001, "reward": 1.25, "reward_std": 0.3172913808375597, "rewards/equation_reward_func": 0.3046875, "rewards/format_reward_func": 0.9453125, "step": 154 }, { "completion_length": 414.6875, "epoch": 0.027733333333333332, "grad_norm": 0.1765554041111672, "kl": 0.0706787109375, "learning_rate": 3.8016355973344173e-07, "loss": 0.0001, "reward": 1.2578125, "reward_std": 0.3864140044897795, "rewards/equation_reward_func": 0.296875, "rewards/format_reward_func": 0.9609375, "step": 156 }, { "completion_length": 419.3203125, "epoch": 0.02808888888888889, "grad_norm": 0.1525317919499253, "kl": 0.0763397216796875, "learning_rate": 3.7707424440504863e-07, "loss": 0.0001, "reward": 1.21875, "reward_std": 0.32123037427663803, "rewards/equation_reward_func": 0.2578125, "rewards/format_reward_func": 0.9609375, "step": 158 }, { "completion_length": 458.296875, "epoch": 0.028444444444444446, "grad_norm": 0.13661366975115602, "kl": 0.0710906982421875, "learning_rate": 3.739585392353787e-07, "loss": 0.0001, "reward": 1.171875, "reward_std": 0.3388565890491009, "rewards/equation_reward_func": 0.25, "rewards/format_reward_func": 0.921875, "step": 160 }, { "completion_length": 407.5234375, "epoch": 0.0288, "grad_norm": 0.14265288581900928, "kl": 0.090179443359375, "learning_rate": 3.7081709127108767e-07, "loss": 0.0001, "reward": 1.34375, "reward_std": 0.4125017859041691, "rewards/equation_reward_func": 0.3671875, "rewards/format_reward_func": 0.9765625, "step": 162 }, { "completion_length": 457.34375, "epoch": 0.029155555555555556, "grad_norm": 0.14147277763916563, "kl": 0.079864501953125, "learning_rate": 3.6765055290490513e-07, "loss": 0.0001, "reward": 1.1015625, "reward_std": 0.26880460046231747, "rewards/equation_reward_func": 0.1328125, "rewards/format_reward_func": 0.96875, "step": 164 }, { "completion_length": 357.3515625, "epoch": 0.02951111111111111, "grad_norm": 0.1715828805345642, "kl": 0.0870819091796875, "learning_rate": 3.644595817401501e-07, "loss": 0.0001, "reward": 1.3515625, "reward_std": 0.35194794088602066, "rewards/equation_reward_func": 0.3828125, "rewards/format_reward_func": 0.96875, "step": 166 }, { "completion_length": 425.90625, "epoch": 0.029866666666666666, "grad_norm": 0.14100531969548477, "kl": 0.07891845703125, "learning_rate": 3.6124484045416483e-07, "loss": 0.0001, "reward": 1.2890625, "reward_std": 0.28513263165950775, "rewards/equation_reward_func": 0.3203125, "rewards/format_reward_func": 0.96875, "step": 168 }, { "completion_length": 366.703125, "epoch": 0.030222222222222223, "grad_norm": 0.16622145587450843, "kl": 0.0851593017578125, "learning_rate": 3.580069966606949e-07, "loss": 0.0001, "reward": 1.4296875, "reward_std": 0.31588183902204037, "rewards/equation_reward_func": 0.4296875, "rewards/format_reward_func": 1.0, "step": 170 }, { "completion_length": 371.0234375, "epoch": 0.030577777777777777, "grad_norm": 0.137987763899706, "kl": 0.1009979248046875, "learning_rate": 3.547467227712444e-07, "loss": 0.0001, "reward": 1.4375, "reward_std": 0.2630355451256037, "rewards/equation_reward_func": 0.453125, "rewards/format_reward_func": 0.984375, "step": 172 }, { "completion_length": 389.546875, "epoch": 0.030933333333333334, "grad_norm": 0.1711519127577815, "kl": 0.0822601318359375, "learning_rate": 3.5146469585543386e-07, "loss": 0.0001, "reward": 1.3125, "reward_std": 0.3842947632074356, "rewards/equation_reward_func": 0.359375, "rewards/format_reward_func": 0.953125, "step": 174 }, { "completion_length": 438.453125, "epoch": 0.03128888888888889, "grad_norm": 0.12051965947246142, "kl": 0.0817413330078125, "learning_rate": 3.481615975003922e-07, "loss": 0.0001, "reward": 1.2421875, "reward_std": 0.31843096762895584, "rewards/equation_reward_func": 0.2890625, "rewards/format_reward_func": 0.953125, "step": 176 }, { "completion_length": 381.703125, "epoch": 0.03164444444444445, "grad_norm": 0.15318076967674452, "kl": 0.0802001953125, "learning_rate": 3.448381136692089e-07, "loss": 0.0001, "reward": 1.4375, "reward_std": 0.23410366661846638, "rewards/equation_reward_func": 0.4453125, "rewards/format_reward_func": 0.9921875, "step": 178 }, { "completion_length": 404.2109375, "epoch": 0.032, "grad_norm": 0.18128262823423888, "kl": 0.078521728515625, "learning_rate": 3.4149493455847897e-07, "loss": 0.0001, "reward": 1.3046875, "reward_std": 0.2657256331294775, "rewards/equation_reward_func": 0.3515625, "rewards/format_reward_func": 0.953125, "step": 180 }, { "completion_length": 424.4609375, "epoch": 0.032355555555555554, "grad_norm": 0.14981419450826716, "kl": 0.083251953125, "learning_rate": 3.3813275445496766e-07, "loss": 0.0001, "reward": 1.15625, "reward_std": 0.33486341312527657, "rewards/equation_reward_func": 0.203125, "rewards/format_reward_func": 0.953125, "step": 182 }, { "completion_length": 345.890625, "epoch": 0.032711111111111114, "grad_norm": 0.15455090626242537, "kl": 0.0913238525390625, "learning_rate": 3.347522715914262e-07, "loss": 0.0001, "reward": 1.4765625, "reward_std": 0.3798140827566385, "rewards/equation_reward_func": 0.5, "rewards/format_reward_func": 0.9765625, "step": 184 }, { "completion_length": 330.0859375, "epoch": 0.03306666666666667, "grad_norm": 0.17923333714255735, "kl": 0.0919342041015625, "learning_rate": 3.313541880015877e-07, "loss": 0.0001, "reward": 1.4609375, "reward_std": 0.28012007288634777, "rewards/equation_reward_func": 0.4765625, "rewards/format_reward_func": 0.984375, "step": 186 }, { "completion_length": 419.8828125, "epoch": 0.03342222222222222, "grad_norm": 0.2229598300520282, "kl": 0.089447021484375, "learning_rate": 3.279392093743747e-07, "loss": 0.0001, "reward": 1.265625, "reward_std": 0.3122788220643997, "rewards/equation_reward_func": 0.328125, "rewards/format_reward_func": 0.9375, "step": 188 }, { "completion_length": 400.140625, "epoch": 0.033777777777777775, "grad_norm": 0.12889272306222627, "kl": 0.085418701171875, "learning_rate": 3.245080449073459e-07, "loss": 0.0001, "reward": 1.25, "reward_std": 0.24054957926273346, "rewards/equation_reward_func": 0.2734375, "rewards/format_reward_func": 0.9765625, "step": 190 }, { "completion_length": 363.1171875, "epoch": 0.034133333333333335, "grad_norm": 0.16266797929879878, "kl": 0.09893798828125, "learning_rate": 3.210614071594162e-07, "loss": 0.0001, "reward": 1.484375, "reward_std": 0.24435340240597725, "rewards/equation_reward_func": 0.4921875, "rewards/format_reward_func": 0.9921875, "step": 192 }, { "completion_length": 385.84375, "epoch": 0.03448888888888889, "grad_norm": 0.1286538346420234, "kl": 0.0966796875, "learning_rate": 3.1760001190287695e-07, "loss": 0.0001, "reward": 1.296875, "reward_std": 0.29644319973886013, "rewards/equation_reward_func": 0.3359375, "rewards/format_reward_func": 0.9609375, "step": 194 }, { "completion_length": 491.7578125, "epoch": 0.03484444444444444, "grad_norm": 0.13692671785492067, "kl": 0.082366943359375, "learning_rate": 3.141245779747502e-07, "loss": 0.0001, "reward": 1.1875, "reward_std": 0.39936898462474346, "rewards/equation_reward_func": 0.28125, "rewards/format_reward_func": 0.90625, "step": 196 }, { "completion_length": 385.8515625, "epoch": 0.0352, "grad_norm": 0.15906297032986566, "kl": 0.0865325927734375, "learning_rate": 3.106358271275056e-07, "loss": 0.0001, "reward": 1.3203125, "reward_std": 0.23891541920602322, "rewards/equation_reward_func": 0.3359375, "rewards/format_reward_func": 0.984375, "step": 198 }, { "completion_length": 345.7734375, "epoch": 0.035555555555555556, "grad_norm": 0.10916438327428707, "kl": 0.10546875, "learning_rate": 3.0713448387917227e-07, "loss": 0.0001, "reward": 1.484375, "reward_std": 0.21754318848252296, "rewards/equation_reward_func": 0.5078125, "rewards/format_reward_func": 0.9765625, "step": 200 }, { "completion_length": 469.6328125, "epoch": 0.03591111111111111, "grad_norm": 0.13427396937511493, "kl": 0.1422882080078125, "learning_rate": 3.0362127536287636e-07, "loss": 0.0001, "reward": 1.296875, "reward_std": 0.4032180178910494, "rewards/equation_reward_func": 0.359375, "rewards/format_reward_func": 0.9375, "step": 202 }, { "completion_length": 462.484375, "epoch": 0.03626666666666667, "grad_norm": 0.14175335721131654, "kl": 0.084930419921875, "learning_rate": 3.0009693117583523e-07, "loss": 0.0001, "reward": 1.2109375, "reward_std": 0.3685295097529888, "rewards/equation_reward_func": 0.2734375, "rewards/format_reward_func": 0.9375, "step": 204 }, { "completion_length": 442.421875, "epoch": 0.03662222222222222, "grad_norm": 0.1605545110922793, "kl": 0.092681884765625, "learning_rate": 2.965621832278401e-07, "loss": 0.0001, "reward": 1.2265625, "reward_std": 0.36273445934057236, "rewards/equation_reward_func": 0.3125, "rewards/format_reward_func": 0.9140625, "step": 206 }, { "completion_length": 487.59375, "epoch": 0.036977777777777776, "grad_norm": 0.17241738987093455, "kl": 0.083953857421875, "learning_rate": 2.9301776558925875e-07, "loss": 0.0001, "reward": 1.2421875, "reward_std": 0.3413938693702221, "rewards/equation_reward_func": 0.2890625, "rewards/format_reward_func": 0.953125, "step": 208 }, { "completion_length": 385.3359375, "epoch": 0.037333333333333336, "grad_norm": 0.18550539158073817, "kl": 0.099517822265625, "learning_rate": 2.894644143385885e-07, "loss": 0.0001, "reward": 1.46875, "reward_std": 0.40134032256901264, "rewards/equation_reward_func": 0.5, "rewards/format_reward_func": 0.96875, "step": 210 }, { "completion_length": 407.0703125, "epoch": 0.03768888888888889, "grad_norm": 0.10848019065658879, "kl": 0.1204833984375, "learning_rate": 2.859028674095937e-07, "loss": 0.0001, "reward": 1.375, "reward_std": 0.311705494299531, "rewards/equation_reward_func": 0.421875, "rewards/format_reward_func": 0.953125, "step": 212 }, { "completion_length": 430.4921875, "epoch": 0.03804444444444444, "grad_norm": 0.09779461620640097, "kl": 0.1276397705078125, "learning_rate": 2.823338644380566e-07, "loss": 0.0001, "reward": 1.28125, "reward_std": 0.24435340240597725, "rewards/equation_reward_func": 0.359375, "rewards/format_reward_func": 0.921875, "step": 214 }, { "completion_length": 337.546875, "epoch": 0.0384, "grad_norm": 0.11632584351646018, "kl": 0.169647216796875, "learning_rate": 2.7875814660817504e-07, "loss": 0.0002, "reward": 1.5625, "reward_std": 0.20069601200520992, "rewards/equation_reward_func": 0.578125, "rewards/format_reward_func": 0.984375, "step": 216 }, { "completion_length": 452.1171875, "epoch": 0.03875555555555556, "grad_norm": 0.12440617923159014, "kl": 0.1014556884765625, "learning_rate": 2.751764564986396e-07, "loss": 0.0001, "reward": 1.234375, "reward_std": 0.28065195120871067, "rewards/equation_reward_func": 0.28125, "rewards/format_reward_func": 0.953125, "step": 218 }, { "completion_length": 456.3359375, "epoch": 0.03911111111111111, "grad_norm": 0.19414546978036584, "kl": 0.1228485107421875, "learning_rate": 2.715895379284194e-07, "loss": 0.0001, "reward": 1.265625, "reward_std": 0.27309720776975155, "rewards/equation_reward_func": 0.3046875, "rewards/format_reward_func": 0.9609375, "step": 220 }, { "completion_length": 422.109375, "epoch": 0.039466666666666664, "grad_norm": 0.18691301250047884, "kl": 0.1074981689453125, "learning_rate": 2.6799813580229174e-07, "loss": 0.0001, "reward": 1.3125, "reward_std": 0.31189604848623276, "rewards/equation_reward_func": 0.3828125, "rewards/format_reward_func": 0.9296875, "step": 222 }, { "completion_length": 375.328125, "epoch": 0.039822222222222224, "grad_norm": 0.1870312456814116, "kl": 0.12664794921875, "learning_rate": 2.6440299595614606e-07, "loss": 0.0001, "reward": 1.484375, "reward_std": 0.271799024194479, "rewards/equation_reward_func": 0.5078125, "rewards/format_reward_func": 0.9765625, "step": 224 }, { "completion_length": 441.59375, "epoch": 0.04017777777777778, "grad_norm": 0.1395588541862425, "kl": 0.099700927734375, "learning_rate": 2.6080486500209347e-07, "loss": 0.0001, "reward": 1.34375, "reward_std": 0.3171109911054373, "rewards/equation_reward_func": 0.40625, "rewards/format_reward_func": 0.9375, "step": 226 }, { "completion_length": 412.484375, "epoch": 0.04053333333333333, "grad_norm": 0.17905219731684363, "kl": 0.1191253662109375, "learning_rate": 2.572044901734166e-07, "loss": 0.0001, "reward": 1.2890625, "reward_std": 0.28012007288634777, "rewards/equation_reward_func": 0.3515625, "rewards/format_reward_func": 0.9375, "step": 228 }, { "completion_length": 476.296875, "epoch": 0.04088888888888889, "grad_norm": 0.1304738846155797, "kl": 0.1032562255859375, "learning_rate": 2.536026191693893e-07, "loss": 0.0001, "reward": 1.25, "reward_std": 0.23391559347510338, "rewards/equation_reward_func": 0.296875, "rewards/format_reward_func": 0.953125, "step": 230 }, { "completion_length": 382.609375, "epoch": 0.041244444444444445, "grad_norm": 0.14335342765956446, "kl": 0.172271728515625, "learning_rate": 2.5e-07, "loss": 0.0002, "reward": 1.4140625, "reward_std": 0.23068872280418873, "rewards/equation_reward_func": 0.46875, "rewards/format_reward_func": 0.9453125, "step": 232 }, { "completion_length": 413.921875, "epoch": 0.0416, "grad_norm": 0.11409022946228915, "kl": 0.150146484375, "learning_rate": 2.4639738083061073e-07, "loss": 0.0002, "reward": 1.3828125, "reward_std": 0.14966704696416855, "rewards/equation_reward_func": 0.4140625, "rewards/format_reward_func": 0.96875, "step": 234 }, { "completion_length": 435.7265625, "epoch": 0.04195555555555556, "grad_norm": 0.19382477904173945, "kl": 0.108245849609375, "learning_rate": 2.4279550982658345e-07, "loss": 0.0001, "reward": 1.296875, "reward_std": 0.4299037382006645, "rewards/equation_reward_func": 0.3671875, "rewards/format_reward_func": 0.9296875, "step": 236 }, { "completion_length": 422.359375, "epoch": 0.04231111111111111, "grad_norm": 0.07742598896983852, "kl": 0.134552001953125, "learning_rate": 2.3919513499790646e-07, "loss": 0.0001, "reward": 1.2734375, "reward_std": 0.28402500227093697, "rewards/equation_reward_func": 0.3359375, "rewards/format_reward_func": 0.9375, "step": 238 }, { "completion_length": 446.703125, "epoch": 0.042666666666666665, "grad_norm": 0.13048074165206625, "kl": 0.10418701171875, "learning_rate": 2.3559700404385394e-07, "loss": 0.0001, "reward": 1.2734375, "reward_std": 0.20680594816803932, "rewards/equation_reward_func": 0.34375, "rewards/format_reward_func": 0.9296875, "step": 240 }, { "completion_length": 380.8671875, "epoch": 0.043022222222222226, "grad_norm": 0.15195815320180947, "kl": 0.134918212890625, "learning_rate": 2.3200186419770823e-07, "loss": 0.0001, "reward": 1.4375, "reward_std": 0.17176413349807262, "rewards/equation_reward_func": 0.453125, "rewards/format_reward_func": 0.984375, "step": 242 }, { "completion_length": 317.765625, "epoch": 0.04337777777777778, "grad_norm": 0.20510319394941706, "kl": 0.139068603515625, "learning_rate": 2.284104620715807e-07, "loss": 0.0001, "reward": 1.6015625, "reward_std": 0.2688144091516733, "rewards/equation_reward_func": 0.609375, "rewards/format_reward_func": 0.9921875, "step": 244 }, { "completion_length": 401.015625, "epoch": 0.04373333333333333, "grad_norm": 0.17580532584141528, "kl": 0.115447998046875, "learning_rate": 2.2482354350136043e-07, "loss": 0.0001, "reward": 1.3359375, "reward_std": 0.2896084077656269, "rewards/equation_reward_func": 0.3828125, "rewards/format_reward_func": 0.953125, "step": 246 }, { "completion_length": 374.3828125, "epoch": 0.044088888888888886, "grad_norm": 0.13703363908634722, "kl": 0.13311767578125, "learning_rate": 2.2124185339182496e-07, "loss": 0.0001, "reward": 1.453125, "reward_std": 0.19958838261663914, "rewards/equation_reward_func": 0.484375, "rewards/format_reward_func": 0.96875, "step": 248 }, { "completion_length": 410.9921875, "epoch": 0.044444444444444446, "grad_norm": 0.12840967985250826, "kl": 0.124114990234375, "learning_rate": 2.1766613556194344e-07, "loss": 0.0001, "reward": 1.265625, "reward_std": 0.29555559158325195, "rewards/equation_reward_func": 0.328125, "rewards/format_reward_func": 0.9375, "step": 250 }, { "completion_length": 370.46875, "epoch": 0.0448, "grad_norm": 0.14200419109331727, "kl": 0.12237548828125, "learning_rate": 2.1409713259040628e-07, "loss": 0.0001, "reward": 1.40625, "reward_std": 0.17965975776314735, "rewards/equation_reward_func": 0.421875, "rewards/format_reward_func": 0.984375, "step": 252 }, { "completion_length": 372.2265625, "epoch": 0.04515555555555555, "grad_norm": 0.23225534396386804, "kl": 0.143218994140625, "learning_rate": 2.105355856614115e-07, "loss": 0.0001, "reward": 1.3046875, "reward_std": 0.20411095581948757, "rewards/equation_reward_func": 0.34375, "rewards/format_reward_func": 0.9609375, "step": 254 }, { "completion_length": 285.4921875, "epoch": 0.04551111111111111, "grad_norm": 0.24766446564024155, "kl": 0.151763916015625, "learning_rate": 2.069822344107413e-07, "loss": 0.0002, "reward": 1.59375, "reward_std": 0.25689312256872654, "rewards/equation_reward_func": 0.609375, "rewards/format_reward_func": 0.984375, "step": 256 }, { "completion_length": 313.8203125, "epoch": 0.04586666666666667, "grad_norm": 0.16165568014293, "kl": 0.146575927734375, "learning_rate": 2.034378167721599e-07, "loss": 0.0001, "reward": 1.59375, "reward_std": 0.13781969621777534, "rewards/equation_reward_func": 0.6015625, "rewards/format_reward_func": 0.9921875, "step": 258 }, { "completion_length": 415.359375, "epoch": 0.04622222222222222, "grad_norm": 0.09688841854391178, "kl": 0.12677001953125, "learning_rate": 1.9990306882416485e-07, "loss": 0.0001, "reward": 1.2890625, "reward_std": 0.15756267122924328, "rewards/equation_reward_func": 0.328125, "rewards/format_reward_func": 0.9609375, "step": 260 }, { "completion_length": 373.765625, "epoch": 0.04657777777777778, "grad_norm": 0.11053378420987946, "kl": 0.12457275390625, "learning_rate": 1.9637872463712362e-07, "loss": 0.0001, "reward": 1.4140625, "reward_std": 0.17859892547130585, "rewards/equation_reward_func": 0.4453125, "rewards/format_reward_func": 0.96875, "step": 262 }, { "completion_length": 399.046875, "epoch": 0.046933333333333334, "grad_norm": 0.09951068355965577, "kl": 0.12164306640625, "learning_rate": 1.9286551612082773e-07, "loss": 0.0001, "reward": 1.3828125, "reward_std": 0.23231797851622105, "rewards/equation_reward_func": 0.4296875, "rewards/format_reward_func": 0.953125, "step": 264 }, { "completion_length": 410.6484375, "epoch": 0.04728888888888889, "grad_norm": 0.12843842474279485, "kl": 0.109649658203125, "learning_rate": 1.8936417287249446e-07, "loss": 0.0001, "reward": 1.3828125, "reward_std": 0.21937325038015842, "rewards/equation_reward_func": 0.3984375, "rewards/format_reward_func": 0.984375, "step": 266 }, { "completion_length": 338.921875, "epoch": 0.04764444444444445, "grad_norm": 0.1702909908327491, "kl": 0.172119140625, "learning_rate": 1.8587542202524985e-07, "loss": 0.0002, "reward": 1.390625, "reward_std": 0.18543371744453907, "rewards/equation_reward_func": 0.421875, "rewards/format_reward_func": 0.96875, "step": 268 }, { "completion_length": 415.5546875, "epoch": 0.048, "grad_norm": 0.15257037646762198, "kl": 0.125518798828125, "learning_rate": 1.82399988097123e-07, "loss": 0.0001, "reward": 1.3515625, "reward_std": 0.2567375358194113, "rewards/equation_reward_func": 0.3671875, "rewards/format_reward_func": 0.984375, "step": 270 }, { "completion_length": 491.0703125, "epoch": 0.048355555555555554, "grad_norm": 0.1015784600459762, "kl": 0.1043853759765625, "learning_rate": 1.7893859284058378e-07, "loss": 0.0001, "reward": 1.203125, "reward_std": 0.28407179936766624, "rewards/equation_reward_func": 0.2734375, "rewards/format_reward_func": 0.9296875, "step": 272 }, { "completion_length": 320.1484375, "epoch": 0.04871111111111111, "grad_norm": 0.07568286413210676, "kl": 0.19097900390625, "learning_rate": 1.7549195509265407e-07, "loss": 0.0002, "reward": 1.5625, "reward_std": 0.16097761504352093, "rewards/equation_reward_func": 0.5625, "rewards/format_reward_func": 1.0, "step": 274 }, { "completion_length": 397.09375, "epoch": 0.04906666666666667, "grad_norm": 0.15664401529813785, "kl": 0.12188720703125, "learning_rate": 1.7206079062562536e-07, "loss": 0.0001, "reward": 1.375, "reward_std": 0.2890843581408262, "rewards/equation_reward_func": 0.4296875, "rewards/format_reward_func": 0.9453125, "step": 276 }, { "completion_length": 412.875, "epoch": 0.04942222222222222, "grad_norm": 0.152716469033041, "kl": 0.215545654296875, "learning_rate": 1.6864581199841226e-07, "loss": 0.0002, "reward": 1.4140625, "reward_std": 0.24452662654221058, "rewards/equation_reward_func": 0.4453125, "rewards/format_reward_func": 0.96875, "step": 278 }, { "completion_length": 322.53125, "epoch": 0.049777777777777775, "grad_norm": 0.06465172658536934, "kl": 0.12664794921875, "learning_rate": 1.6524772840857388e-07, "loss": 0.0001, "reward": 1.59375, "reward_std": 0.14123954437673092, "rewards/equation_reward_func": 0.59375, "rewards/format_reward_func": 1.0, "step": 280 }, { "completion_length": 338.296875, "epoch": 0.050133333333333335, "grad_norm": 0.13308881483334925, "kl": 0.119415283203125, "learning_rate": 1.6186724554503237e-07, "loss": 0.0001, "reward": 1.625, "reward_std": 0.2380426600575447, "rewards/equation_reward_func": 0.6328125, "rewards/format_reward_func": 0.9921875, "step": 282 }, { "completion_length": 408.3515625, "epoch": 0.05048888888888889, "grad_norm": 0.12489806113236866, "kl": 0.099822998046875, "learning_rate": 1.5850506544152103e-07, "loss": 0.0001, "reward": 1.3359375, "reward_std": 0.2407503854483366, "rewards/equation_reward_func": 0.3671875, "rewards/format_reward_func": 0.96875, "step": 284 }, { "completion_length": 436.9921875, "epoch": 0.05084444444444444, "grad_norm": 0.1660027330528205, "kl": 0.111358642578125, "learning_rate": 1.5516188633079107e-07, "loss": 0.0001, "reward": 1.2890625, "reward_std": 0.2788218893110752, "rewards/equation_reward_func": 0.3203125, "rewards/format_reward_func": 0.96875, "step": 286 }, { "completion_length": 381.5390625, "epoch": 0.0512, "grad_norm": 0.1773949520743432, "kl": 0.1202392578125, "learning_rate": 1.5183840249960784e-07, "loss": 0.0001, "reward": 1.4375, "reward_std": 0.23410366661846638, "rewards/equation_reward_func": 0.46875, "rewards/format_reward_func": 0.96875, "step": 288 }, { "completion_length": 363.2890625, "epoch": 0.051555555555555556, "grad_norm": 0.12908690460870859, "kl": 0.12237548828125, "learning_rate": 1.4853530414456612e-07, "loss": 0.0001, "reward": 1.4140625, "reward_std": 0.2874350417405367, "rewards/equation_reward_func": 0.4375, "rewards/format_reward_func": 0.9765625, "step": 290 }, { "completion_length": 398.25, "epoch": 0.05191111111111111, "grad_norm": 0.1223189167367173, "kl": 0.10498046875, "learning_rate": 1.4525327722875568e-07, "loss": 0.0001, "reward": 1.421875, "reward_std": 0.20517178811132908, "rewards/equation_reward_func": 0.4609375, "rewards/format_reward_func": 0.9609375, "step": 292 }, { "completion_length": 299.5390625, "epoch": 0.05226666666666667, "grad_norm": 0.1475307814276985, "kl": 0.138275146484375, "learning_rate": 1.4199300333930515e-07, "loss": 0.0001, "reward": 1.6171875, "reward_std": 0.15773099102079868, "rewards/equation_reward_func": 0.6328125, "rewards/format_reward_func": 0.984375, "step": 294 }, { "completion_length": 408.1484375, "epoch": 0.05262222222222222, "grad_norm": 0.15893771408986387, "kl": 0.12841796875, "learning_rate": 1.3875515954583523e-07, "loss": 0.0001, "reward": 1.375, "reward_std": 0.22043408267199993, "rewards/equation_reward_func": 0.421875, "rewards/format_reward_func": 0.953125, "step": 296 }, { "completion_length": 386.34375, "epoch": 0.052977777777777776, "grad_norm": 0.09802748245282768, "kl": 0.12982177734375, "learning_rate": 1.3554041825985e-07, "loss": 0.0001, "reward": 1.3828125, "reward_std": 0.19691260531544685, "rewards/equation_reward_func": 0.4140625, "rewards/format_reward_func": 0.96875, "step": 298 }, { "completion_length": 376.203125, "epoch": 0.05333333333333334, "grad_norm": 0.0792523065441085, "kl": 0.11859130859375, "learning_rate": 1.323494470950949e-07, "loss": 0.0001, "reward": 1.46875, "reward_std": 0.13098980858922005, "rewards/equation_reward_func": 0.4765625, "rewards/format_reward_func": 0.9921875, "step": 300 }, { "completion_length": 353.7421875, "epoch": 0.05368888888888889, "grad_norm": 0.0887805404195599, "kl": 0.125640869140625, "learning_rate": 1.2918290872891236e-07, "loss": 0.0001, "reward": 1.4921875, "reward_std": 0.16762433387339115, "rewards/equation_reward_func": 0.5, "rewards/format_reward_func": 0.9921875, "step": 302 }, { "completion_length": 440.4375, "epoch": 0.054044444444444444, "grad_norm": 0.10652059405770911, "kl": 0.104339599609375, "learning_rate": 1.260414607646213e-07, "loss": 0.0001, "reward": 1.21875, "reward_std": 0.2987973112612963, "rewards/equation_reward_func": 0.2734375, "rewards/format_reward_func": 0.9453125, "step": 304 }, { "completion_length": 369.453125, "epoch": 0.0544, "grad_norm": 0.10132439230172154, "kl": 0.143829345703125, "learning_rate": 1.2292575559495143e-07, "loss": 0.0001, "reward": 1.4609375, "reward_std": 0.22584448382258415, "rewards/equation_reward_func": 0.5, "rewards/format_reward_func": 0.9609375, "step": 306 }, { "completion_length": 424.7109375, "epoch": 0.05475555555555556, "grad_norm": 0.14438365212654558, "kl": 0.131591796875, "learning_rate": 1.1983644026655835e-07, "loss": 0.0001, "reward": 1.3203125, "reward_std": 0.2513565141707659, "rewards/equation_reward_func": 0.359375, "rewards/format_reward_func": 0.9609375, "step": 308 }, { "completion_length": 346.9375, "epoch": 0.05511111111111111, "grad_norm": 0.15713203326183722, "kl": 0.12139892578125, "learning_rate": 1.1677415634565066e-07, "loss": 0.0001, "reward": 1.546875, "reward_std": 0.1645657829940319, "rewards/equation_reward_func": 0.578125, "rewards/format_reward_func": 0.96875, "step": 310 }, { "completion_length": 373.9453125, "epoch": 0.055466666666666664, "grad_norm": 0.08389325726469715, "kl": 0.11663818359375, "learning_rate": 1.1373953978475353e-07, "loss": 0.0001, "reward": 1.40625, "reward_std": 0.21595830656588078, "rewards/equation_reward_func": 0.421875, "rewards/format_reward_func": 0.984375, "step": 312 }, { "completion_length": 363.4140625, "epoch": 0.055822222222222224, "grad_norm": 0.14102614011841097, "kl": 0.332305908203125, "learning_rate": 1.1073322079063913e-07, "loss": 0.0003, "reward": 1.484375, "reward_std": 0.19039457477629185, "rewards/equation_reward_func": 0.5, "rewards/format_reward_func": 0.984375, "step": 314 }, { "completion_length": 443.2109375, "epoch": 0.05617777777777778, "grad_norm": 0.19363787374064304, "kl": 0.104736328125, "learning_rate": 1.0775582369344946e-07, "loss": 0.0001, "reward": 1.2109375, "reward_std": 0.15991678275167942, "rewards/equation_reward_func": 0.2265625, "rewards/format_reward_func": 0.984375, "step": 316 }, { "completion_length": 382.5703125, "epoch": 0.05653333333333333, "grad_norm": 0.09292657488720626, "kl": 0.16693115234375, "learning_rate": 1.0480796681704077e-07, "loss": 0.0002, "reward": 1.4375, "reward_std": 0.2001592293381691, "rewards/equation_reward_func": 0.46875, "rewards/format_reward_func": 0.96875, "step": 318 }, { "completion_length": 327.9765625, "epoch": 0.05688888888888889, "grad_norm": 0.10755681115568093, "kl": 0.128448486328125, "learning_rate": 1.018902623505741e-07, "loss": 0.0001, "reward": 1.4765625, "reward_std": 0.20858673192560673, "rewards/equation_reward_func": 0.5, "rewards/format_reward_func": 0.9765625, "step": 320 }, { "completion_length": 391.078125, "epoch": 0.057244444444444445, "grad_norm": 0.1090245479572572, "kl": 0.11785888671875, "learning_rate": 9.900331622138063e-08, "loss": 0.0001, "reward": 1.4765625, "reward_std": 0.1649293415248394, "rewards/equation_reward_func": 0.4921875, "rewards/format_reward_func": 0.984375, "step": 322 }, { "completion_length": 355.6015625, "epoch": 0.0576, "grad_norm": 0.10346963676894178, "kl": 0.13653564453125, "learning_rate": 9.614772796912681e-08, "loss": 0.0001, "reward": 1.5, "reward_std": 0.15650183893740177, "rewards/equation_reward_func": 0.515625, "rewards/format_reward_func": 0.984375, "step": 324 }, { "completion_length": 356.0, "epoch": 0.05795555555555556, "grad_norm": 0.1293537003023565, "kl": 0.134002685546875, "learning_rate": 9.332409062130686e-08, "loss": 0.0001, "reward": 1.3984375, "reward_std": 0.19833699613809586, "rewards/equation_reward_func": 0.421875, "rewards/format_reward_func": 0.9765625, "step": 326 }, { "completion_length": 385.75, "epoch": 0.05831111111111111, "grad_norm": 0.09266992787765642, "kl": 0.327056884765625, "learning_rate": 9.053299057008699e-08, "loss": 0.0003, "reward": 1.328125, "reward_std": 0.09863808192312717, "rewards/equation_reward_func": 0.34375, "rewards/format_reward_func": 0.984375, "step": 328 }, { "completion_length": 448.9609375, "epoch": 0.058666666666666666, "grad_norm": 0.10795996998035878, "kl": 0.119293212890625, "learning_rate": 8.777500745052743e-08, "loss": 0.0001, "reward": 1.2421875, "reward_std": 0.15308689512312412, "rewards/equation_reward_func": 0.25, "rewards/format_reward_func": 0.9921875, "step": 330 }, { "completion_length": 382.96875, "epoch": 0.05902222222222222, "grad_norm": 0.16527711592141753, "kl": 0.118896484375, "learning_rate": 8.505071402020892e-08, "loss": 0.0001, "reward": 1.46875, "reward_std": 0.2238539308309555, "rewards/equation_reward_func": 0.4921875, "rewards/format_reward_func": 0.9765625, "step": 332 }, { "completion_length": 330.5625, "epoch": 0.05937777777777778, "grad_norm": 0.09535910660673434, "kl": 0.156768798828125, "learning_rate": 8.236067604028562e-08, "loss": 0.0002, "reward": 1.4921875, "reward_std": 0.17859892547130585, "rewards/equation_reward_func": 0.5078125, "rewards/format_reward_func": 0.984375, "step": 334 }, { "completion_length": 331.328125, "epoch": 0.05973333333333333, "grad_norm": 0.10463153558356299, "kl": 0.165557861328125, "learning_rate": 7.970545215799327e-08, "loss": 0.0002, "reward": 1.5703125, "reward_std": 0.15360604040324688, "rewards/equation_reward_func": 0.5703125, "rewards/format_reward_func": 1.0, "step": 336 }, { "completion_length": 355.625, "epoch": 0.060088888888888886, "grad_norm": 0.1913964658824772, "kl": 0.151611328125, "learning_rate": 7.708559379063204e-08, "loss": 0.0002, "reward": 1.4609375, "reward_std": 0.25224412232637405, "rewards/equation_reward_func": 0.484375, "rewards/format_reward_func": 0.9765625, "step": 338 }, { "completion_length": 404.421875, "epoch": 0.060444444444444446, "grad_norm": 0.14713103619518464, "kl": 0.11785888671875, "learning_rate": 7.45016450110534e-08, "loss": 0.0001, "reward": 1.40625, "reward_std": 0.32176715694367886, "rewards/equation_reward_func": 0.4375, "rewards/format_reward_func": 0.96875, "step": 340 }, { "completion_length": 422.7421875, "epoch": 0.0608, "grad_norm": 0.1327901388939736, "kl": 0.125274658203125, "learning_rate": 7.195414243467029e-08, "loss": 0.0001, "reward": 1.359375, "reward_std": 0.17464719898998737, "rewards/equation_reward_func": 0.359375, "rewards/format_reward_func": 1.0, "step": 342 }, { "completion_length": 405.5078125, "epoch": 0.06115555555555555, "grad_norm": 0.15507152679168051, "kl": 0.1173095703125, "learning_rate": 6.944361510801763e-08, "loss": 0.0001, "reward": 1.4609375, "reward_std": 0.2535423059016466, "rewards/equation_reward_func": 0.46875, "rewards/format_reward_func": 0.9921875, "step": 344 }, { "completion_length": 390.125, "epoch": 0.061511111111111114, "grad_norm": 0.09613630702325471, "kl": 0.133941650390625, "learning_rate": 6.697058439888283e-08, "loss": 0.0001, "reward": 1.3828125, "reward_std": 0.16781240701675415, "rewards/equation_reward_func": 0.40625, "rewards/format_reward_func": 0.9765625, "step": 346 }, { "completion_length": 322.09375, "epoch": 0.06186666666666667, "grad_norm": 0.13920858828391514, "kl": 0.144439697265625, "learning_rate": 6.453556388803288e-08, "loss": 0.0001, "reward": 1.5703125, "reward_std": 0.17854722402989864, "rewards/equation_reward_func": 0.5859375, "rewards/format_reward_func": 0.984375, "step": 348 }, { "completion_length": 442.453125, "epoch": 0.06222222222222222, "grad_norm": 0.10472362379988483, "kl": 0.11431884765625, "learning_rate": 6.213905926255697e-08, "loss": 0.0001, "reward": 1.25, "reward_std": 0.11279274709522724, "rewards/equation_reward_func": 0.2734375, "rewards/format_reward_func": 0.9765625, "step": 350 }, { "completion_length": 318.703125, "epoch": 0.06257777777777777, "grad_norm": 0.13606380997377993, "kl": 0.167205810546875, "learning_rate": 5.978156821084987e-08, "loss": 0.0002, "reward": 1.6171875, "reward_std": 0.21070839650928974, "rewards/equation_reward_func": 0.625, "rewards/format_reward_func": 0.9921875, "step": 352 }, { "completion_length": 400.1328125, "epoch": 0.06293333333333333, "grad_norm": 0.06894639690652522, "kl": 0.1187744140625, "learning_rate": 5.7463580319254853e-08, "loss": 0.0001, "reward": 1.375, "reward_std": 0.0883883461356163, "rewards/equation_reward_func": 0.3828125, "rewards/format_reward_func": 0.9921875, "step": 354 }, { "completion_length": 396.875, "epoch": 0.0632888888888889, "grad_norm": 0.17070490178918976, "kl": 0.140167236328125, "learning_rate": 5.518557697039081e-08, "loss": 0.0001, "reward": 1.375, "reward_std": 0.30904704704880714, "rewards/equation_reward_func": 0.3828125, "rewards/format_reward_func": 0.9921875, "step": 356 }, { "completion_length": 414.6640625, "epoch": 0.06364444444444445, "grad_norm": 0.15235608953158414, "kl": 0.129058837890625, "learning_rate": 5.294803124318145e-08, "loss": 0.0001, "reward": 1.3671875, "reward_std": 0.34888696670532227, "rewards/equation_reward_func": 0.40625, "rewards/format_reward_func": 0.9609375, "step": 358 }, { "completion_length": 363.8984375, "epoch": 0.064, "grad_norm": 0.14985273857090523, "kl": 0.124176025390625, "learning_rate": 5.07514078146106e-08, "loss": 0.0001, "reward": 1.4609375, "reward_std": 0.2845958489924669, "rewards/equation_reward_func": 0.4609375, "rewards/format_reward_func": 1.0, "step": 360 }, { "completion_length": 424.5625, "epoch": 0.06435555555555555, "grad_norm": 0.11123767098843869, "kl": 0.125823974609375, "learning_rate": 4.859616286322094e-08, "loss": 0.0001, "reward": 1.296875, "reward_std": 0.2488291785120964, "rewards/equation_reward_func": 0.3359375, "rewards/format_reward_func": 0.9609375, "step": 362 }, { "completion_length": 350.8828125, "epoch": 0.06471111111111111, "grad_norm": 0.09977313666369174, "kl": 0.148895263671875, "learning_rate": 4.648274397437829e-08, "loss": 0.0001, "reward": 1.5, "reward_std": 0.1462521031498909, "rewards/equation_reward_func": 0.5078125, "rewards/format_reward_func": 0.9921875, "step": 364 }, { "completion_length": 298.3125, "epoch": 0.06506666666666666, "grad_norm": 0.14198944071871591, "kl": 0.1343994140625, "learning_rate": 4.4411590047320617e-08, "loss": 0.0001, "reward": 1.6328125, "reward_std": 0.18649454973638058, "rewards/equation_reward_func": 0.6484375, "rewards/format_reward_func": 0.984375, "step": 366 }, { "completion_length": 405.453125, "epoch": 0.06542222222222223, "grad_norm": 0.12595363853356176, "kl": 0.1236572265625, "learning_rate": 4.2383131204010494e-08, "loss": 0.0001, "reward": 1.3828125, "reward_std": 0.2517249770462513, "rewards/equation_reward_func": 0.4140625, "rewards/format_reward_func": 0.96875, "step": 368 }, { "completion_length": 337.7890625, "epoch": 0.06577777777777778, "grad_norm": 0.15385943707708435, "kl": 0.12908935546875, "learning_rate": 4.039778869981064e-08, "loss": 0.0001, "reward": 1.5546875, "reward_std": 0.21778053976595402, "rewards/equation_reward_func": 0.5546875, "rewards/format_reward_func": 1.0, "step": 370 }, { "completion_length": 321.765625, "epoch": 0.06613333333333334, "grad_norm": 0.17092942527418264, "kl": 0.1295166015625, "learning_rate": 3.845597483600049e-08, "loss": 0.0001, "reward": 1.6328125, "reward_std": 0.1701665185391903, "rewards/equation_reward_func": 0.6328125, "rewards/format_reward_func": 1.0, "step": 372 }, { "completion_length": 403.3671875, "epoch": 0.06648888888888889, "grad_norm": 0.1280050801798591, "kl": 0.208740234375, "learning_rate": 3.655809287415284e-08, "loss": 0.0002, "reward": 1.375, "reward_std": 0.21542152389883995, "rewards/equation_reward_func": 0.3984375, "rewards/format_reward_func": 0.9765625, "step": 374 }, { "completion_length": 404.90625, "epoch": 0.06684444444444444, "grad_norm": 0.18022228135215232, "kl": 0.125, "learning_rate": 3.4704536952387285e-08, "loss": 0.0001, "reward": 1.375, "reward_std": 0.29555559158325195, "rewards/equation_reward_func": 0.4140625, "rewards/format_reward_func": 0.9609375, "step": 376 }, { "completion_length": 314.6953125, "epoch": 0.0672, "grad_norm": 0.14022337811828436, "kl": 0.13714599609375, "learning_rate": 3.2895692003518575e-08, "loss": 0.0001, "reward": 1.6171875, "reward_std": 0.24056999571621418, "rewards/equation_reward_func": 0.6484375, "rewards/format_reward_func": 0.96875, "step": 378 }, { "completion_length": 370.1875, "epoch": 0.06755555555555555, "grad_norm": 0.0019306138405977334, "kl": 0.1578369140625, "learning_rate": 3.113193367511635e-08, "loss": 0.0002, "reward": 1.3984375, "reward_std": 0.15756267122924328, "rewards/equation_reward_func": 0.40625, "rewards/format_reward_func": 0.9921875, "step": 380 }, { "completion_length": 382.078125, "epoch": 0.06791111111111112, "grad_norm": 0.11573688091221201, "kl": 0.148834228515625, "learning_rate": 2.9413628251493934e-08, "loss": 0.0001, "reward": 1.515625, "reward_std": 0.25513992086052895, "rewards/equation_reward_func": 0.5390625, "rewards/format_reward_func": 0.9765625, "step": 382 }, { "completion_length": 324.90625, "epoch": 0.06826666666666667, "grad_norm": 0.17809327173629308, "kl": 0.16400146484375, "learning_rate": 2.774113257764066e-08, "loss": 0.0002, "reward": 1.5546875, "reward_std": 0.17859892547130585, "rewards/equation_reward_func": 0.5625, "rewards/format_reward_func": 0.9921875, "step": 384 }, { "completion_length": 332.84375, "epoch": 0.06862222222222222, "grad_norm": 0.06792283881086807, "kl": 0.132476806640625, "learning_rate": 2.611479398511518e-08, "loss": 0.0001, "reward": 1.5390625, "reward_std": 0.1237865537405014, "rewards/equation_reward_func": 0.5546875, "rewards/format_reward_func": 0.984375, "step": 386 }, { "completion_length": 423.6015625, "epoch": 0.06897777777777778, "grad_norm": 0.13085284140188322, "kl": 0.140411376953125, "learning_rate": 2.4534950219914057e-08, "loss": 0.0001, "reward": 1.296875, "reward_std": 0.21900969184935093, "rewards/equation_reward_func": 0.3359375, "rewards/format_reward_func": 0.9609375, "step": 388 }, { "completion_length": 375.953125, "epoch": 0.06933333333333333, "grad_norm": 0.21027045668269104, "kl": 0.14263916015625, "learning_rate": 2.300192937233128e-08, "loss": 0.0001, "reward": 1.375, "reward_std": 0.24777325056493282, "rewards/equation_reward_func": 0.390625, "rewards/format_reward_func": 0.984375, "step": 390 }, { "completion_length": 259.9609375, "epoch": 0.06968888888888888, "grad_norm": 0.06740235405182507, "kl": 0.177703857421875, "learning_rate": 2.1516049808822935e-08, "loss": 0.0002, "reward": 1.7109375, "reward_std": 0.09969891421496868, "rewards/equation_reward_func": 0.71875, "rewards/format_reward_func": 0.9921875, "step": 392 }, { "completion_length": 408.7734375, "epoch": 0.07004444444444445, "grad_norm": 0.12862412677248317, "kl": 0.12994384765625, "learning_rate": 2.007762010589098e-08, "loss": 0.0001, "reward": 1.3125, "reward_std": 0.25707351230084896, "rewards/equation_reward_func": 0.3828125, "rewards/format_reward_func": 0.9296875, "step": 394 }, { "completion_length": 376.734375, "epoch": 0.0704, "grad_norm": 0.12418206496249037, "kl": 0.124755859375, "learning_rate": 1.8686938986000627e-08, "loss": 0.0001, "reward": 1.375, "reward_std": 0.20593318901956081, "rewards/equation_reward_func": 0.375, "rewards/format_reward_func": 1.0, "step": 396 }, { "completion_length": 449.6328125, "epoch": 0.07075555555555556, "grad_norm": 0.19881539319315003, "kl": 0.1287078857421875, "learning_rate": 1.734429525554365e-08, "loss": 0.0001, "reward": 1.2109375, "reward_std": 0.31295688077807426, "rewards/equation_reward_func": 0.28125, "rewards/format_reward_func": 0.9296875, "step": 398 }, { "completion_length": 375.9140625, "epoch": 0.07111111111111111, "grad_norm": 0.14489917455194734, "kl": 0.122894287109375, "learning_rate": 1.604996774486145e-08, "loss": 0.0001, "reward": 1.4296875, "reward_std": 0.30127294547855854, "rewards/equation_reward_func": 0.4609375, "rewards/format_reward_func": 0.96875, "step": 400 }, { "completion_length": 274.84375, "epoch": 0.07146666666666666, "grad_norm": 0.2041697074289669, "kl": 0.155670166015625, "learning_rate": 1.4804225250339281e-08, "loss": 0.0002, "reward": 1.640625, "reward_std": 0.15992168709635735, "rewards/equation_reward_func": 0.65625, "rewards/format_reward_func": 0.984375, "step": 402 }, { "completion_length": 309.875, "epoch": 0.07182222222222222, "grad_norm": 0.11843339954382205, "kl": 0.169708251953125, "learning_rate": 1.360732647858498e-08, "loss": 0.0002, "reward": 1.625, "reward_std": 0.17176413349807262, "rewards/equation_reward_func": 0.640625, "rewards/format_reward_func": 0.984375, "step": 404 }, { "completion_length": 421.8984375, "epoch": 0.07217777777777777, "grad_norm": 0.1323247597342515, "kl": 0.11968994140625, "learning_rate": 1.2459519992702311e-08, "loss": 0.0001, "reward": 1.3671875, "reward_std": 0.28508093021810055, "rewards/equation_reward_func": 0.3984375, "rewards/format_reward_func": 0.96875, "step": 406 }, { "completion_length": 353.96875, "epoch": 0.07253333333333334, "grad_norm": 0.13268080952152958, "kl": 0.137847900390625, "learning_rate": 1.1361044160671629e-08, "loss": 0.0001, "reward": 1.4765625, "reward_std": 0.15756267122924328, "rewards/equation_reward_func": 0.515625, "rewards/format_reward_func": 0.9609375, "step": 408 }, { "completion_length": 382.5078125, "epoch": 0.07288888888888889, "grad_norm": 0.08449676532401729, "kl": 0.125823974609375, "learning_rate": 1.0312127105846947e-08, "loss": 0.0001, "reward": 1.484375, "reward_std": 0.13204573653638363, "rewards/equation_reward_func": 0.484375, "rewards/format_reward_func": 1.0, "step": 410 }, { "completion_length": 325.953125, "epoch": 0.07324444444444445, "grad_norm": 0.1977511977193377, "kl": 0.147247314453125, "learning_rate": 9.312986659581301e-09, "loss": 0.0001, "reward": 1.46875, "reward_std": 0.2290911078453064, "rewards/equation_reward_func": 0.46875, "rewards/format_reward_func": 1.0, "step": 412 }, { "completion_length": 381.5390625, "epoch": 0.0736, "grad_norm": 0.13775437493448475, "kl": 0.1502685546875, "learning_rate": 8.363830315988945e-09, "loss": 0.0002, "reward": 1.453125, "reward_std": 0.2527858093380928, "rewards/equation_reward_func": 0.4921875, "rewards/format_reward_func": 0.9609375, "step": 414 }, { "completion_length": 391.96875, "epoch": 0.07395555555555555, "grad_norm": 0.16627374730160457, "kl": 0.130828857421875, "learning_rate": 7.46485518885462e-09, "loss": 0.0001, "reward": 1.4375, "reward_std": 0.2887158952653408, "rewards/equation_reward_func": 0.46875, "rewards/format_reward_func": 0.96875, "step": 416 }, { "completion_length": 379.6328125, "epoch": 0.0743111111111111, "grad_norm": 0.20602437534961654, "kl": 0.15301513671875, "learning_rate": 6.616247970698319e-09, "loss": 0.0002, "reward": 1.4453125, "reward_std": 0.21095065213739872, "rewards/equation_reward_func": 0.4609375, "rewards/format_reward_func": 0.984375, "step": 418 }, { "completion_length": 443.8515625, "epoch": 0.07466666666666667, "grad_norm": 0.0967545808782271, "kl": 0.118255615234375, "learning_rate": 5.8181848940044855e-09, "loss": 0.0001, "reward": 1.2578125, "reward_std": 0.2395910546183586, "rewards/equation_reward_func": 0.3125, "rewards/format_reward_func": 0.9453125, "step": 420 }, { "completion_length": 428.65625, "epoch": 0.07502222222222223, "grad_norm": 0.15101166210394215, "kl": 0.174652099609375, "learning_rate": 5.070831694623135e-09, "loss": 0.0002, "reward": 1.3125, "reward_std": 0.23410366661846638, "rewards/equation_reward_func": 0.3515625, "rewards/format_reward_func": 0.9609375, "step": 422 }, { "completion_length": 395.5078125, "epoch": 0.07537777777777778, "grad_norm": 0.15966375032382485, "kl": 0.12115478515625, "learning_rate": 4.374343577351336e-09, "loss": 0.0001, "reward": 1.3515625, "reward_std": 0.3044727724045515, "rewards/equation_reward_func": 0.390625, "rewards/format_reward_func": 0.9609375, "step": 424 }, { "completion_length": 358.5625, "epoch": 0.07573333333333333, "grad_norm": 0.11716508707747059, "kl": 0.128387451171875, "learning_rate": 3.7288651837012745e-09, "loss": 0.0001, "reward": 1.5390625, "reward_std": 0.19728106819093227, "rewards/equation_reward_func": 0.5625, "rewards/format_reward_func": 0.9765625, "step": 426 }, { "completion_length": 399.2109375, "epoch": 0.07608888888888889, "grad_norm": 0.06036882983312084, "kl": 0.11102294921875, "learning_rate": 3.134530561862081e-09, "loss": 0.0001, "reward": 1.4765625, "reward_std": 0.14465448819100857, "rewards/equation_reward_func": 0.4765625, "rewards/format_reward_func": 1.0, "step": 428 }, { "completion_length": 382.3359375, "epoch": 0.07644444444444444, "grad_norm": 0.612962185519629, "kl": 0.1231689453125, "learning_rate": 2.5914631388619103e-09, "loss": 0.0001, "reward": 1.4765625, "reward_std": 0.15756267122924328, "rewards/equation_reward_func": 0.4921875, "rewards/format_reward_func": 0.984375, "step": 430 }, { "completion_length": 241.8125, "epoch": 0.0768, "grad_norm": 0.12381992051598001, "kl": 0.15179443359375, "learning_rate": 2.0997756949353297e-09, "loss": 0.0002, "reward": 1.8046875, "reward_std": 0.19637582264840603, "rewards/equation_reward_func": 0.8125, "rewards/format_reward_func": 0.9921875, "step": 432 }, { "completion_length": 392.546875, "epoch": 0.07715555555555556, "grad_norm": 0.10938935972335283, "kl": 0.1282958984375, "learning_rate": 1.6595703401020844e-09, "loss": 0.0001, "reward": 1.4296875, "reward_std": 0.16834918968379498, "rewards/equation_reward_func": 0.4453125, "rewards/format_reward_func": 0.984375, "step": 434 }, { "completion_length": 301.4609375, "epoch": 0.07751111111111111, "grad_norm": 0.11017165117960269, "kl": 0.1378173828125, "learning_rate": 1.2709384929615596e-09, "loss": 0.0001, "reward": 1.6640625, "reward_std": 0.18630647659301758, "rewards/equation_reward_func": 0.6875, "rewards/format_reward_func": 0.9765625, "step": 436 }, { "completion_length": 336.8359375, "epoch": 0.07786666666666667, "grad_norm": 0.13100046865623674, "kl": 0.13287353515625, "learning_rate": 9.339608617077165e-10, "loss": 0.0001, "reward": 1.5546875, "reward_std": 0.277237007394433, "rewards/equation_reward_func": 0.5703125, "rewards/format_reward_func": 0.984375, "step": 438 }, { "completion_length": 412.5625, "epoch": 0.07822222222222222, "grad_norm": 0.13909584980828368, "kl": 0.115570068359375, "learning_rate": 6.487074273681114e-10, "loss": 0.0001, "reward": 1.3125, "reward_std": 0.21884137205779552, "rewards/equation_reward_func": 0.328125, "rewards/format_reward_func": 0.984375, "step": 440 }, { "completion_length": 358.8984375, "epoch": 0.07857777777777777, "grad_norm": 0.1263095691692818, "kl": 0.136993408203125, "learning_rate": 4.152374292708538e-10, "loss": 0.0001, "reward": 1.4609375, "reward_std": 0.12073516845703125, "rewards/equation_reward_func": 0.4609375, "rewards/format_reward_func": 1.0, "step": 442 }, { "completion_length": 414.4140625, "epoch": 0.07893333333333333, "grad_norm": 0.1266338639368109, "kl": 0.13043212890625, "learning_rate": 2.3359935274214204e-10, "loss": 0.0001, "reward": 1.3828125, "reward_std": 0.141234640032053, "rewards/equation_reward_func": 0.390625, "rewards/format_reward_func": 0.9921875, "step": 444 }, { "completion_length": 314.1640625, "epoch": 0.0792888888888889, "grad_norm": 0.09004410832047449, "kl": 0.15936279296875, "learning_rate": 1.0383091903720665e-10, "loss": 0.0002, "reward": 1.6171875, "reward_std": 0.10994865000247955, "rewards/equation_reward_func": 0.625, "rewards/format_reward_func": 0.9921875, "step": 446 }, { "completion_length": 471.28125, "epoch": 0.07964444444444445, "grad_norm": 0.06872113403307542, "kl": 0.1243896484375, "learning_rate": 2.595907750671533e-11, "loss": 0.0001, "reward": 1.234375, "reward_std": 0.08337578736245632, "rewards/equation_reward_func": 0.2421875, "rewards/format_reward_func": 0.9921875, "step": 448 }, { "completion_length": 365.1015625, "epoch": 0.08, "grad_norm": 0.2033994999207491, "kl": 0.13482666015625, "learning_rate": 0.0, "loss": 0.0001, "reward": 1.4609375, "reward_std": 0.22567616403102875, "rewards/equation_reward_func": 0.484375, "rewards/format_reward_func": 0.9765625, "step": 450 }, { "epoch": 0.08, "step": 450, "total_flos": 0.0, "train_loss": 9.454646318052558e-05, "train_runtime": 16471.8629, "train_samples_per_second": 0.219, "train_steps_per_second": 0.027 } ], "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 }