jdqqjr's picture
Upload folder using huggingface_hub
0feded0 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.15057060126043265,
"eval_steps": 100,
"global_step": 221,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"completion_length": 701.7250213623047,
"epoch": 0.0013626298756600238,
"grad_norm": 0.826935350894928,
"kl": 0.0,
"learning_rate": 1.7391304347826088e-06,
"loss": -0.0,
"reward": 3.2898273691534996,
"reward_std": 1.2225780645385385,
"rewards/AnswerChecker_LenCheck_Reward": 0.41482741106301546,
"rewards/all-MiniLM-L6-v2": -0.07499999832361937,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9500000029802322,
"step": 2
},
{
"completion_length": 832.4125137329102,
"epoch": 0.0027252597513200477,
"grad_norm": 0.6933600902557373,
"kl": 0.00024503469467163086,
"learning_rate": 3.4782608695652175e-06,
"loss": 0.0,
"reward": 3.45002019405365,
"reward_std": 1.13982825120911,
"rewards/AnswerChecker_LenCheck_Reward": 0.4375201063230634,
"rewards/all-MiniLM-L6-v2": 0.11249999888241291,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9000000059604645,
"step": 4
},
{
"completion_length": 731.8750114440918,
"epoch": 0.004087889626980072,
"grad_norm": 0.7940042614936829,
"kl": 0.0002880692481994629,
"learning_rate": 5.2173913043478265e-06,
"loss": 0.0,
"reward": 2.9608234241604805,
"reward_std": 1.052665668539703,
"rewards/AnswerChecker_LenCheck_Reward": 0.4483234500512481,
"rewards/all-MiniLM-L6-v2": -0.3874999973922968,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9000000013038516,
"step": 6
},
{
"completion_length": 787.5625152587891,
"epoch": 0.005450519502640095,
"grad_norm": 0.7262738347053528,
"kl": 0.00028836727142333984,
"learning_rate": 6.956521739130435e-06,
"loss": 0.0,
"reward": 2.5098357554525137,
"reward_std": 1.7445468110963702,
"rewards/AnswerChecker_LenCheck_Reward": 0.409835753031075,
"rewards/all-MiniLM-L6-v2": -0.4249999960884452,
"rewards/format_reward_beginEndSolutionFormat": 1.8499999977648258,
"rewards/length_reward": 0.6750000044703484,
"step": 8
},
{
"completion_length": 751.5000133514404,
"epoch": 0.00681314937830012,
"grad_norm": 0.7745183110237122,
"kl": 0.0004850625991821289,
"learning_rate": 8.695652173913044e-06,
"loss": 0.0,
"reward": 2.9620843827724457,
"reward_std": 1.278110965853557,
"rewards/AnswerChecker_LenCheck_Reward": 0.47458438016474247,
"rewards/all-MiniLM-L6-v2": -0.2749999985098839,
"rewards/format_reward_beginEndSolutionFormat": 1.9624999985098839,
"rewards/length_reward": 0.8000000091269612,
"step": 10
},
{
"completion_length": 744.9250144958496,
"epoch": 0.008175779253960144,
"grad_norm": 0.7855518460273743,
"kl": 0.0019762516021728516,
"learning_rate": 1.0434782608695653e-05,
"loss": 0.0001,
"reward": 2.617582857608795,
"reward_std": 1.4501504292711616,
"rewards/AnswerChecker_LenCheck_Reward": 0.41758283600211143,
"rewards/all-MiniLM-L6-v2": -0.49999999813735485,
"rewards/format_reward_beginEndSolutionFormat": 1.9249999970197678,
"rewards/length_reward": 0.7750000087544322,
"step": 12
},
{
"completion_length": 853.975025177002,
"epoch": 0.009538409129620166,
"grad_norm": 0.7132939100265503,
"kl": 0.0023059844970703125,
"learning_rate": 1.2173913043478263e-05,
"loss": 0.0001,
"reward": 3.0857974849641323,
"reward_std": 1.1976260086521506,
"rewards/AnswerChecker_LenCheck_Reward": 0.3857975276187062,
"rewards/all-MiniLM-L6-v2": -0.11249999608844519,
"rewards/format_reward_beginEndSolutionFormat": 1.9624999985098839,
"rewards/length_reward": 0.850000006146729,
"step": 14
},
{
"completion_length": 809.7375106811523,
"epoch": 0.01090103900528019,
"grad_norm": 0.7411205172538757,
"kl": 0.0045413970947265625,
"learning_rate": 1.391304347826087e-05,
"loss": 0.0002,
"reward": 3.3214251101017,
"reward_std": 0.94907569559291,
"rewards/AnswerChecker_LenCheck_Reward": 0.40892498986795545,
"rewards/all-MiniLM-L6-v2": 0.037500000558793545,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.8750000046566129,
"step": 16
},
{
"completion_length": 813.1250114440918,
"epoch": 0.012263668880940215,
"grad_norm": 14.433080673217773,
"kl": 0.2021026611328125,
"learning_rate": 1.565217391304348e-05,
"loss": 0.0081,
"reward": 3.0686260610818863,
"reward_std": 1.5170891038142145,
"rewards/AnswerChecker_LenCheck_Reward": 0.48112595453858376,
"rewards/all-MiniLM-L6-v2": -0.2374999951571226,
"rewards/format_reward_beginEndSolutionFormat": 1.9249999970197678,
"rewards/length_reward": 0.9000000059604645,
"step": 18
},
{
"completion_length": 754.1750144958496,
"epoch": 0.01362629875660024,
"grad_norm": 2.9093778133392334,
"kl": 0.06426239013671875,
"learning_rate": 1.739130434782609e-05,
"loss": 0.0026,
"reward": 3.807109519839287,
"reward_std": 0.7755511063151062,
"rewards/AnswerChecker_LenCheck_Reward": 0.5696093924343586,
"rewards/all-MiniLM-L6-v2": 0.2875000014901161,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9500000029802322,
"step": 20
},
{
"completion_length": 758.8125038146973,
"epoch": 0.014988928632260262,
"grad_norm": 0.8031071424484253,
"kl": 0.020557403564453125,
"learning_rate": 1.9130434782608697e-05,
"loss": 0.0008,
"reward": 3.0672582909464836,
"reward_std": 0.7253409158438444,
"rewards/AnswerChecker_LenCheck_Reward": 0.5797582101076841,
"rewards/all-MiniLM-L6-v2": -0.46249999944120646,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9500000029802322,
"step": 22
},
{
"completion_length": 738.9500198364258,
"epoch": 0.016351558507920288,
"grad_norm": 0.7532008290290833,
"kl": 0.036285400390625,
"learning_rate": 1.9998741276738753e-05,
"loss": 0.0015,
"reward": 3.575051836669445,
"reward_std": 0.8001346649834886,
"rewards/AnswerChecker_LenCheck_Reward": 0.6000517811626196,
"rewards/all-MiniLM-L6-v2": 0.025000003166496754,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9500000029802322,
"step": 24
},
{
"completion_length": 772.2625160217285,
"epoch": 0.01771418838358031,
"grad_norm": 0.7200579643249512,
"kl": 0.08385467529296875,
"learning_rate": 1.9988673391830082e-05,
"loss": 0.0034,
"reward": 3.486709274351597,
"reward_std": 1.1654404955916107,
"rewards/AnswerChecker_LenCheck_Reward": 0.5367092387750745,
"rewards/all-MiniLM-L6-v2": 0.02500000409781933,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9250000044703484,
"step": 26
},
{
"completion_length": 759.0875091552734,
"epoch": 0.019076818259240333,
"grad_norm": 0.7885477542877197,
"kl": 0.0690155029296875,
"learning_rate": 1.9968547759519426e-05,
"loss": 0.0028,
"reward": 3.937687858939171,
"reward_std": 0.8582523697987199,
"rewards/AnswerChecker_LenCheck_Reward": 0.6376878507435322,
"rewards/all-MiniLM-L6-v2": 0.4000000022351742,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9000000031664968,
"step": 28
},
{
"completion_length": 733.7500076293945,
"epoch": 0.020439448134900357,
"grad_norm": 0.6713956594467163,
"kl": 0.0721435546875,
"learning_rate": 1.9938384644612542e-05,
"loss": 0.0029,
"reward": 3.545550711452961,
"reward_std": 1.1149344076402485,
"rewards/AnswerChecker_LenCheck_Reward": 0.5705506596714258,
"rewards/all-MiniLM-L6-v2": 0.0625000037252903,
"rewards/format_reward_beginEndSolutionFormat": 1.9624999985098839,
"rewards/length_reward": 0.9500000029802322,
"step": 30
},
{
"completion_length": 793.4125213623047,
"epoch": 0.02180207801056038,
"grad_norm": 0.6639223098754883,
"kl": 0.06781005859375,
"learning_rate": 1.989821441880933e-05,
"loss": 0.0027,
"reward": 3.9647994488477707,
"reward_std": 1.1172373143490404,
"rewards/AnswerChecker_LenCheck_Reward": 0.6397993620485067,
"rewards/all-MiniLM-L6-v2": 0.4375,
"rewards/format_reward_beginEndSolutionFormat": 1.9624999985098839,
"rewards/length_reward": 0.9250000044703484,
"step": 32
},
{
"completion_length": 713.4125213623047,
"epoch": 0.023164707886220406,
"grad_norm": 0.6671966910362244,
"kl": 0.0789947509765625,
"learning_rate": 1.9848077530122083e-05,
"loss": 0.0032,
"reward": 4.12811366468668,
"reward_std": 0.6696655503474176,
"rewards/AnswerChecker_LenCheck_Reward": 0.6656134920194745,
"rewards/all-MiniLM-L6-v2": 0.5125000011175871,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9500000001862645,
"step": 34
},
{
"completion_length": 621.1875171661377,
"epoch": 0.02452733776188043,
"grad_norm": 0.6927969455718994,
"kl": 0.100311279296875,
"learning_rate": 1.978802446214779e-05,
"loss": 0.004,
"reward": 3.9949512034654617,
"reward_std": 1.0779171623289585,
"rewards/AnswerChecker_LenCheck_Reward": 0.6824510861188173,
"rewards/all-MiniLM-L6-v2": 0.3375000050291419,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9750000014901161,
"step": 36
},
{
"completion_length": 561.4625148773193,
"epoch": 0.025889967637540454,
"grad_norm": 0.8079332113265991,
"kl": 0.105621337890625,
"learning_rate": 1.9718115683235418e-05,
"loss": 0.0042,
"reward": 3.3487851433455944,
"reward_std": 1.0449772235006094,
"rewards/AnswerChecker_LenCheck_Reward": 0.6237850617617369,
"rewards/all-MiniLM-L6-v2": -0.049999997951090336,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.7750000106170774,
"step": 38
},
{
"completion_length": 600.0875129699707,
"epoch": 0.02725259751320048,
"grad_norm": 0.7116134762763977,
"kl": 0.100372314453125,
"learning_rate": 1.9638421585599422e-05,
"loss": 0.004,
"reward": 4.384867042303085,
"reward_std": 0.719090289901942,
"rewards/AnswerChecker_LenCheck_Reward": 0.7348670326173306,
"rewards/all-MiniLM-L6-v2": 0.7750000013038516,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.8750000074505806,
"step": 40
},
{
"completion_length": 598.8750190734863,
"epoch": 0.0286152273888605,
"grad_norm": 0.7759160399436951,
"kl": 0.143280029296875,
"learning_rate": 1.9549022414440738e-05,
"loss": 0.0057,
"reward": 3.826561488211155,
"reward_std": 0.9282979969866574,
"rewards/AnswerChecker_LenCheck_Reward": 0.6765614040195942,
"rewards/all-MiniLM-L6-v2": 0.2249999986961484,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9250000044703484,
"step": 42
},
{
"completion_length": 625.4625110626221,
"epoch": 0.029977857264520524,
"grad_norm": 0.7551826238632202,
"kl": 0.116241455078125,
"learning_rate": 1.9450008187146685e-05,
"loss": 0.0046,
"reward": 4.079624235630035,
"reward_std": 1.025521146133542,
"rewards/AnswerChecker_LenCheck_Reward": 0.7171240504831076,
"rewards/all-MiniLM-L6-v2": 0.4375000009313226,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9250000016763806,
"step": 44
},
{
"completion_length": 759.9500160217285,
"epoch": 0.03134048714018055,
"grad_norm": 0.6660957932472229,
"kl": 0.10888671875,
"learning_rate": 1.9341478602651068e-05,
"loss": 0.0044,
"reward": 3.9495397955179214,
"reward_std": 1.2625608062371612,
"rewards/AnswerChecker_LenCheck_Reward": 0.7370398119091988,
"rewards/all-MiniLM-L6-v2": 0.3625000026077032,
"rewards/format_reward_beginEndSolutionFormat": 1.9249999970197678,
"rewards/length_reward": 0.9250000016763806,
"step": 46
},
{
"completion_length": 826.0875129699707,
"epoch": 0.032703117015840576,
"grad_norm": 0.6011426448822021,
"kl": 0.118682861328125,
"learning_rate": 1.9223542941045817e-05,
"loss": 0.0047,
"reward": 3.5684720501303673,
"reward_std": 0.6631585191935301,
"rewards/AnswerChecker_LenCheck_Reward": 0.6809719651937485,
"rewards/all-MiniLM-L6-v2": -0.012500000186264515,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9000000031664968,
"step": 48
},
{
"completion_length": 938.2875137329102,
"epoch": 0.034065746891500596,
"grad_norm": 0.6014713048934937,
"kl": 0.126922607421875,
"learning_rate": 1.9096319953545186e-05,
"loss": 0.0051,
"reward": 3.5386421233415604,
"reward_std": 1.796545386314392,
"rewards/AnswerChecker_LenCheck_Reward": 0.6011420339345932,
"rewards/all-MiniLM-L6-v2": 0.4000000022351742,
"rewards/format_reward_beginEndSolutionFormat": 1.8124999925494194,
"rewards/length_reward": 0.7250000089406967,
"step": 50
},
{
"completion_length": 936.8000183105469,
"epoch": 0.03542837676716062,
"grad_norm": 0.623587429523468,
"kl": 0.138763427734375,
"learning_rate": 1.895993774291336e-05,
"loss": 0.0056,
"reward": 3.6302099227905273,
"reward_std": 1.3007243419997394,
"rewards/AnswerChecker_LenCheck_Reward": 0.6302098724991083,
"rewards/all-MiniLM-L6-v2": 0.3375000022351742,
"rewards/format_reward_beginEndSolutionFormat": 1.9624999985098839,
"rewards/length_reward": 0.7000000076368451,
"step": 52
},
{
"completion_length": 774.3875160217285,
"epoch": 0.036791006642820645,
"grad_norm": 0.5999850630760193,
"kl": 0.15771484375,
"learning_rate": 1.881453363447582e-05,
"loss": 0.0063,
"reward": 4.047312401235104,
"reward_std": 0.8825826905667782,
"rewards/AnswerChecker_LenCheck_Reward": 0.6848122831434011,
"rewards/all-MiniLM-L6-v2": 0.4125000024214387,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9500000029802322,
"step": 54
},
{
"completion_length": 664.0375175476074,
"epoch": 0.038153636518480666,
"grad_norm": 0.6805257201194763,
"kl": 0.1588134765625,
"learning_rate": 1.866025403784439e-05,
"loss": 0.0064,
"reward": 3.92198596149683,
"reward_std": 0.7282474122475833,
"rewards/AnswerChecker_LenCheck_Reward": 0.6469858698546886,
"rewards/all-MiniLM-L6-v2": 0.34999999962747097,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9250000016763806,
"step": 56
},
{
"completion_length": 702.6375160217285,
"epoch": 0.039516266394140694,
"grad_norm": 0.7188987135887146,
"kl": 0.14849853515625,
"learning_rate": 1.8497254299495147e-05,
"loss": 0.0059,
"reward": 3.4211702197790146,
"reward_std": 1.4494188777171075,
"rewards/AnswerChecker_LenCheck_Reward": 0.5586702147556935,
"rewards/all-MiniLM-L6-v2": 0.2875000052154064,
"rewards/format_reward_beginEndSolutionFormat": 1.8499999977648258,
"rewards/length_reward": 0.725000006146729,
"step": 58
},
{
"completion_length": 641.7625064849854,
"epoch": 0.040878896269800714,
"grad_norm": 0.9523748159408569,
"kl": 0.1611328125,
"learning_rate": 1.8325698546347714e-05,
"loss": 0.0064,
"reward": 3.841396249830723,
"reward_std": 1.1254777936264873,
"rewards/AnswerChecker_LenCheck_Reward": 0.6538961809128523,
"rewards/all-MiniLM-L6-v2": 0.43750000186264515,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.7500000093132257,
"step": 60
},
{
"completion_length": 704.0375175476074,
"epoch": 0.04224152614546074,
"grad_norm": 0.7048397064208984,
"kl": 0.164093017578125,
"learning_rate": 1.814575952050336e-05,
"loss": 0.0066,
"reward": 3.5937935784459114,
"reward_std": 1.1683010547421873,
"rewards/AnswerChecker_LenCheck_Reward": 0.71879349835217,
"rewards/all-MiniLM-L6-v2": 0.13750000018626451,
"rewards/format_reward_beginEndSolutionFormat": 1.9624999985098839,
"rewards/length_reward": 0.7750000059604645,
"step": 62
},
{
"completion_length": 609.1125087738037,
"epoch": 0.04360415602112076,
"grad_norm": 0.8203504085540771,
"kl": 0.178314208984375,
"learning_rate": 1.7957618405308323e-05,
"loss": 0.0071,
"reward": 3.6722382232546806,
"reward_std": 1.1893206317909062,
"rewards/AnswerChecker_LenCheck_Reward": 0.6222381666302681,
"rewards/all-MiniLM-L6-v2": 0.3000000035390258,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.7500000093132257,
"step": 64
},
{
"completion_length": 640.1500129699707,
"epoch": 0.044966785896780784,
"grad_norm": 0.7613713145256042,
"kl": 0.1834259033203125,
"learning_rate": 1.776146464291757e-05,
"loss": 0.0073,
"reward": 4.024308562278748,
"reward_std": 1.0513806878589094,
"rewards/AnswerChecker_LenCheck_Reward": 0.6868084445595741,
"rewards/all-MiniLM-L6-v2": 0.3624999988824129,
"rewards/format_reward_beginEndSolutionFormat": 2.0,
"rewards/length_reward": 0.9750000014901161,
"step": 66
},
{
"completion_length": 793.487512588501,
"epoch": 0.04632941577244081,
"grad_norm": 0.7231267094612122,
"kl": 0.26812744140625,
"learning_rate": 1.7557495743542586e-05,
"loss": 0.0107,
"reward": 2.855987273156643,
"reward_std": 1.688657500082627,
"rewards/AnswerChecker_LenCheck_Reward": 0.6434871796518564,
"rewards/all-MiniLM-L6-v2": -0.012499998323619366,
"rewards/format_reward_beginEndSolutionFormat": 1.8499999986961484,
"rewards/length_reward": 0.3750000046566129,
"step": 68
},
{
"completion_length": 789.1500263214111,
"epoch": 0.04769204564810083,
"grad_norm": 0.9249826669692993,
"kl": 0.33258056640625,
"learning_rate": 1.734591708657533e-05,
"loss": 0.0133,
"reward": 2.242995586246252,
"reward_std": 2.346400245092809,
"rewards/AnswerChecker_LenCheck_Reward": 0.5554955210536718,
"rewards/all-MiniLM-L6-v2": -0.19999999832361937,
"rewards/format_reward_beginEndSolutionFormat": 1.6624999940395355,
"rewards/length_reward": 0.22500000149011612,
"step": 70
},
{
"completion_length": 702.3250160217285,
"epoch": 0.04905467552376086,
"grad_norm": 1.8796899318695068,
"kl": 0.3321533203125,
"learning_rate": 1.7126941713788633e-05,
"loss": 0.0133,
"reward": 3.2902688309550285,
"reward_std": 1.93663672497496,
"rewards/AnswerChecker_LenCheck_Reward": 0.7652687635272741,
"rewards/all-MiniLM-L6-v2": 0.17500000167638063,
"rewards/format_reward_beginEndSolutionFormat": 1.8500000014901161,
"rewards/length_reward": 0.500000006519258,
"step": 72
},
{
"completion_length": 796.2000179290771,
"epoch": 0.05041730539942088,
"grad_norm": 1.0197867155075073,
"kl": 0.45782470703125,
"learning_rate": 1.6900790114821122e-05,
"loss": 0.0183,
"reward": 2.451604187488556,
"reward_std": 2.372755976160988,
"rewards/AnswerChecker_LenCheck_Reward": 0.6391041371971369,
"rewards/all-MiniLM-L6-v2": 0.10000000335276127,
"rewards/format_reward_beginEndSolutionFormat": 1.3624999970197678,
"rewards/length_reward": 0.35000001080334187,
"step": 74
},
{
"completion_length": 716.0625038146973,
"epoch": 0.05177993527508091,
"grad_norm": 1.0521018505096436,
"kl": 0.38922119140625,
"learning_rate": 1.666769000516292e-05,
"loss": 0.0156,
"reward": 3.2886771922931075,
"reward_std": 2.0216886228881776,
"rewards/AnswerChecker_LenCheck_Reward": 0.7261771578341722,
"rewards/all-MiniLM-L6-v2": 0.17500000074505806,
"rewards/format_reward_beginEndSolutionFormat": 1.737500000745058,
"rewards/length_reward": 0.6500000106170774,
"step": 76
},
{
"completion_length": 835.2875137329102,
"epoch": 0.05314256515074093,
"grad_norm": 1.5486301183700562,
"kl": 0.5540771484375,
"learning_rate": 1.6427876096865394e-05,
"loss": 0.0222,
"reward": 2.288073843345046,
"reward_std": 2.585562598425895,
"rewards/AnswerChecker_LenCheck_Reward": 0.6880737878382206,
"rewards/all-MiniLM-L6-v2": -0.16250000149011612,
"rewards/format_reward_beginEndSolutionFormat": 1.2875000014901161,
"rewards/length_reward": 0.47500000335276127,
"step": 78
},
{
"completion_length": 842.4875106811523,
"epoch": 0.05450519502640096,
"grad_norm": 0.7873005867004395,
"kl": 0.5556640625,
"learning_rate": 1.6181589862206053e-05,
"loss": 0.0222,
"reward": 2.895622299052775,
"reward_std": 2.1268671478610486,
"rewards/AnswerChecker_LenCheck_Reward": 0.570622275583446,
"rewards/all-MiniLM-L6-v2": 0.10000000428408384,
"rewards/format_reward_beginEndSolutionFormat": 1.7749999910593033,
"rewards/length_reward": 0.45000000298023224,
"step": 80
},
{
"completion_length": 866.9500141143799,
"epoch": 0.05586782490206098,
"grad_norm": 0.8428084254264832,
"kl": 0.599456787109375,
"learning_rate": 1.5929079290546408e-05,
"loss": 0.024,
"reward": 2.1291475765174255,
"reward_std": 2.3366958047263324,
"rewards/AnswerChecker_LenCheck_Reward": 0.5416475932579488,
"rewards/all-MiniLM-L6-v2": -0.3124999953433871,
"rewards/format_reward_beginEndSolutionFormat": 1.6249999925494194,
"rewards/length_reward": 0.27500000316649675,
"step": 82
},
{
"completion_length": 709.7125110626221,
"epoch": 0.057230454777721,
"grad_norm": 0.714391827583313,
"kl": 0.534912109375,
"learning_rate": 1.5670598638627707e-05,
"loss": 0.0214,
"reward": 2.692725880071521,
"reward_std": 2.575832322239876,
"rewards/AnswerChecker_LenCheck_Reward": 0.6302258470095694,
"rewards/all-MiniLM-L6-v2": 0.10000000428408384,
"rewards/format_reward_beginEndSolutionFormat": 1.662499994970858,
"rewards/length_reward": 0.30000000447034836,
"step": 84
},
{
"completion_length": 653.9125118255615,
"epoch": 0.058593084653381027,
"grad_norm": 2.24059796333313,
"kl": 0.57843017578125,
"learning_rate": 1.5406408174555978e-05,
"loss": 0.0232,
"reward": 2.6488085128366947,
"reward_std": 2.0597222729120404,
"rewards/AnswerChecker_LenCheck_Reward": 0.6988084595650434,
"rewards/all-MiniLM-L6-v2": -0.050000001676380634,
"rewards/format_reward_beginEndSolutionFormat": 1.6999999955296516,
"rewards/length_reward": 0.30000000540167093,
"step": 86
},
{
"completion_length": 530.4875144958496,
"epoch": 0.05995571452904105,
"grad_norm": 0.9869608283042908,
"kl": 0.4842529296875,
"learning_rate": 1.5136773915734067e-05,
"loss": 0.0194,
"reward": 3.0965824760496616,
"reward_std": 1.8650478832423687,
"rewards/AnswerChecker_LenCheck_Reward": 0.7215823549777269,
"rewards/all-MiniLM-L6-v2": 0.3625000035390258,
"rewards/format_reward_beginEndSolutionFormat": 1.8124999925494194,
"rewards/length_reward": 0.2000000076368451,
"step": 88
},
{
"completion_length": 572.0000076293945,
"epoch": 0.061318344404701075,
"grad_norm": 0.7383394241333008,
"kl": 0.4207763671875,
"learning_rate": 1.4861967361004687e-05,
"loss": 0.0168,
"reward": 2.8489164412021637,
"reward_std": 2.041708583943546,
"rewards/AnswerChecker_LenCheck_Reward": 0.6489164028316736,
"rewards/all-MiniLM-L6-v2": -0.04999999701976776,
"rewards/format_reward_beginEndSolutionFormat": 1.7749999947845936,
"rewards/length_reward": 0.4750000089406967,
"step": 90
},
{
"completion_length": 643.6000156402588,
"epoch": 0.0626809742803611,
"grad_norm": 0.7305729389190674,
"kl": 0.417236328125,
"learning_rate": 1.4582265217274105e-05,
"loss": 0.0167,
"reward": 3.1850010380148888,
"reward_std": 1.72700658114627,
"rewards/AnswerChecker_LenCheck_Reward": 0.6975009143352509,
"rewards/all-MiniLM-L6-v2": 0.22499999962747097,
"rewards/format_reward_beginEndSolutionFormat": 1.6624999977648258,
"rewards/length_reward": 0.6000000089406967,
"step": 92
},
{
"completion_length": 843.2000122070312,
"epoch": 0.06404360415602112,
"grad_norm": 0.5814893841743469,
"kl": 0.44672393798828125,
"learning_rate": 1.4297949120891718e-05,
"loss": 0.0179,
"reward": 2.340944491326809,
"reward_std": 2.093850734643638,
"rewards/AnswerChecker_LenCheck_Reward": 0.6159445056691766,
"rewards/all-MiniLM-L6-v2": -0.31249999813735485,
"rewards/format_reward_beginEndSolutionFormat": 1.5124999964609742,
"rewards/length_reward": 0.5250000022351742,
"step": 94
},
{
"completion_length": 767.9875068664551,
"epoch": 0.06540623403168115,
"grad_norm": 0.5642020106315613,
"kl": 0.41064453125,
"learning_rate": 1.4009305354066138e-05,
"loss": 0.0164,
"reward": 3.0814263820648193,
"reward_std": 2.0845829099416733,
"rewards/AnswerChecker_LenCheck_Reward": 0.7064263448119164,
"rewards/all-MiniLM-L6-v2": 0.07499999925494194,
"rewards/format_reward_beginEndSolutionFormat": 1.625,
"rewards/length_reward": 0.6750000054016709,
"step": 96
},
{
"completion_length": 732.2500190734863,
"epoch": 0.06676886390734117,
"grad_norm": 0.6293222904205322,
"kl": 0.4149169921875,
"learning_rate": 1.3716624556603275e-05,
"loss": 0.0166,
"reward": 3.167923970380798,
"reward_std": 1.9076070357114077,
"rewards/AnswerChecker_LenCheck_Reward": 0.6679238956421614,
"rewards/all-MiniLM-L6-v2": 0.12500000093132257,
"rewards/format_reward_beginEndSolutionFormat": 1.6999999955296516,
"rewards/length_reward": 0.6750000091269612,
"step": 98
},
{
"completion_length": 770.9750061035156,
"epoch": 0.06813149378300119,
"grad_norm": 0.608492910861969,
"kl": 0.38108062744140625,
"learning_rate": 1.342020143325669e-05,
"loss": 0.0153,
"reward": 2.9613163992762566,
"reward_std": 1.8579347440972924,
"rewards/AnswerChecker_LenCheck_Reward": 0.6363163664937019,
"rewards/all-MiniLM-L6-v2": -0.049999997951090336,
"rewards/format_reward_beginEndSolutionFormat": 1.8499999977648258,
"rewards/length_reward": 0.5250000059604645,
"step": 100
},
{
"epoch": 0.06813149378300119,
"eval_completion_length": 719.5635530948639,
"eval_kl": 0.42165565490722656,
"eval_loss": 0.01686381734907627,
"eval_reward": 3.1516319193760864,
"eval_reward_std": 1.9167220215313137,
"eval_rewards/AnswerChecker_LenCheck_Reward": 0.6703818460227922,
"eval_rewards/all-MiniLM-L6-v2": 0.06250000081490725,
"eval_rewards/format_reward_beginEndSolutionFormat": 1.7374999963212758,
"eval_rewards/length_reward": 0.6812500089872628,
"eval_runtime": 1234.6422,
"eval_samples_per_second": 0.104,
"eval_steps_per_second": 0.021,
"step": 100
},
{
"completion_length": 708.6000080108643,
"epoch": 0.06949412365866121,
"grad_norm": 0.5848133563995361,
"kl": 0.41204833984375,
"learning_rate": 1.3120334456984871e-05,
"loss": 0.0165,
"reward": 3.301197201013565,
"reward_std": 2.1839559585787356,
"rewards/AnswerChecker_LenCheck_Reward": 0.6011971952393651,
"rewards/all-MiniLM-L6-v2": 0.24999999906867743,
"rewards/format_reward_beginEndSolutionFormat": 1.699999988079071,
"rewards/length_reward": 0.7500000093132257,
"step": 102
},
{
"completion_length": 660.3000183105469,
"epoch": 0.07085675353432123,
"grad_norm": 1.3479467630386353,
"kl": 0.50341796875,
"learning_rate": 1.2817325568414299e-05,
"loss": 0.0201,
"reward": 2.9223585426807404,
"reward_std": 1.763994950801134,
"rewards/AnswerChecker_LenCheck_Reward": 0.6473584100604057,
"rewards/all-MiniLM-L6-v2": -0.17499999701976776,
"rewards/format_reward_beginEndSolutionFormat": 1.7749999985098839,
"rewards/length_reward": 0.6750000081956387,
"step": 104
},
{
"completion_length": 684.8875122070312,
"epoch": 0.07221938340998127,
"grad_norm": 0.6432397365570068,
"kl": 0.3974609375,
"learning_rate": 1.2511479871810792e-05,
"loss": 0.0159,
"reward": 3.2463276791386306,
"reward_std": 1.709463362582028,
"rewards/AnswerChecker_LenCheck_Reward": 0.6588275767862797,
"rewards/all-MiniLM-L6-v2": 0.02500000037252903,
"rewards/format_reward_beginEndSolutionFormat": 1.8124999925494194,
"rewards/length_reward": 0.7500000046566129,
"step": 106
},
{
"completion_length": 671.6875095367432,
"epoch": 0.07358201328564129,
"grad_norm": 0.6950499415397644,
"kl": 0.41790771484375,
"learning_rate": 1.2203105327865407e-05,
"loss": 0.0167,
"reward": 3.2045797668397427,
"reward_std": 1.9101572453510016,
"rewards/AnswerChecker_LenCheck_Reward": 0.7170797474682331,
"rewards/all-MiniLM-L6-v2": 0.14999999944120646,
"rewards/format_reward_beginEndSolutionFormat": 1.6624999986961484,
"rewards/length_reward": 0.6750000072643161,
"step": 108
},
{
"completion_length": 808.1000099182129,
"epoch": 0.07494464316130131,
"grad_norm": 0.5721182227134705,
"kl": 0.511962890625,
"learning_rate": 1.1892512443604103e-05,
"loss": 0.0205,
"reward": 2.2793450676836073,
"reward_std": 2.890487961471081,
"rewards/AnswerChecker_LenCheck_Reward": 0.6168450396507978,
"rewards/all-MiniLM-L6-v2": -0.3124999972060323,
"rewards/format_reward_beginEndSolutionFormat": 1.5499999970197678,
"rewards/length_reward": 0.4250000100582838,
"step": 110
},
{
"completion_length": 693.9000129699707,
"epoch": 0.07630727303696133,
"grad_norm": 0.5843067765235901,
"kl": 0.41845703125,
"learning_rate": 1.15800139597335e-05,
"loss": 0.0167,
"reward": 3.066192142665386,
"reward_std": 2.348536633886397,
"rewards/AnswerChecker_LenCheck_Reward": 0.6661920826882124,
"rewards/all-MiniLM-L6-v2": -0.01249999925494194,
"rewards/format_reward_beginEndSolutionFormat": 1.7374999895691872,
"rewards/length_reward": 0.675000011920929,
"step": 112
},
{
"completion_length": 868.7250137329102,
"epoch": 0.07766990291262135,
"grad_norm": 0.5749533772468567,
"kl": 0.63037109375,
"learning_rate": 1.1265924535737494e-05,
"loss": 0.0252,
"reward": 1.36430923640728,
"reward_std": 3.1500269323587418,
"rewards/AnswerChecker_LenCheck_Reward": 0.514309162274003,
"rewards/all-MiniLM-L6-v2": -0.6499999975785613,
"rewards/format_reward_beginEndSolutionFormat": 1.0999999940395355,
"rewards/length_reward": 0.4000000050291419,
"step": 114
},
{
"completion_length": 725.7375068664551,
"epoch": 0.07903253278828139,
"grad_norm": 0.5346440672874451,
"kl": 0.4619140625,
"learning_rate": 1.0950560433041825e-05,
"loss": 0.0185,
"reward": 2.963149979710579,
"reward_std": 2.0242148893885314,
"rewards/AnswerChecker_LenCheck_Reward": 0.6506498479284346,
"rewards/all-MiniLM-L6-v2": -0.16249999776482582,
"rewards/format_reward_beginEndSolutionFormat": 1.8499999940395355,
"rewards/length_reward": 0.6250000093132257,
"step": 116
},
{
"completion_length": 773.3750152587891,
"epoch": 0.08039516266394141,
"grad_norm": 0.6365153193473816,
"kl": 0.4718017578125,
"learning_rate": 1.0634239196565646e-05,
"loss": 0.0189,
"reward": 2.2029636511579156,
"reward_std": 2.7039426697883755,
"rewards/AnswerChecker_LenCheck_Reward": 0.6029636058956385,
"rewards/all-MiniLM-L6-v2": -0.3499999986961484,
"rewards/format_reward_beginEndSolutionFormat": 1.474999993108213,
"rewards/length_reward": 0.4750000098720193,
"step": 118
},
{
"completion_length": 775.962516784668,
"epoch": 0.08175779253960143,
"grad_norm": 0.5627033710479736,
"kl": 0.5267333984375,
"learning_rate": 1.031727933498068e-05,
"loss": 0.0211,
"reward": 2.5474718529731035,
"reward_std": 2.10833885287866,
"rewards/AnswerChecker_LenCheck_Reward": 0.6349717965349555,
"rewards/all-MiniLM-L6-v2": -0.27499999944120646,
"rewards/format_reward_beginEndSolutionFormat": 1.6624999940395355,
"rewards/length_reward": 0.5250000078231096,
"step": 120
},
{
"completion_length": 641.2125091552734,
"epoch": 0.08312042241526145,
"grad_norm": 0.5676293969154358,
"kl": 0.413330078125,
"learning_rate": 1e-05,
"loss": 0.0165,
"reward": 3.1914120875298977,
"reward_std": 1.7586256829090416,
"rewards/AnswerChecker_LenCheck_Reward": 0.7289120629429817,
"rewards/all-MiniLM-L6-v2": -0.11249999981373549,
"rewards/format_reward_beginEndSolutionFormat": 1.8499999940395355,
"rewards/length_reward": 0.7250000108033419,
"step": 122
},
{
"completion_length": 708.8875179290771,
"epoch": 0.08448305229092148,
"grad_norm": 0.6845495700836182,
"kl": 0.5447998046875,
"learning_rate": 9.682720665019325e-06,
"loss": 0.0218,
"reward": 2.7032833639532328,
"reward_std": 2.0250429082661867,
"rewards/AnswerChecker_LenCheck_Reward": 0.6782832983881235,
"rewards/all-MiniLM-L6-v2": -0.125,
"rewards/format_reward_beginEndSolutionFormat": 1.6249999962747097,
"rewards/length_reward": 0.5250000078231096,
"step": 124
},
{
"completion_length": 693.4625110626221,
"epoch": 0.0858456821665815,
"grad_norm": 0.7195069193840027,
"kl": 0.4825439453125,
"learning_rate": 9.365760803434356e-06,
"loss": 0.0193,
"reward": 2.8621206106618047,
"reward_std": 2.122805818915367,
"rewards/AnswerChecker_LenCheck_Reward": 0.6871205642819405,
"rewards/all-MiniLM-L6-v2": -0.19999999832361937,
"rewards/format_reward_beginEndSolutionFormat": 1.7749999947845936,
"rewards/length_reward": 0.6000000080093741,
"step": 126
},
{
"completion_length": 716.3250122070312,
"epoch": 0.08720831204224153,
"grad_norm": 0.678680419921875,
"kl": 0.4881591796875,
"learning_rate": 9.049439566958176e-06,
"loss": 0.0195,
"reward": 3.0072994977235794,
"reward_std": 2.460042350925505,
"rewards/AnswerChecker_LenCheck_Reward": 0.6822993978857994,
"rewards/all-MiniLM-L6-v2": -0.012499997392296791,
"rewards/format_reward_beginEndSolutionFormat": 1.6624999903142452,
"rewards/length_reward": 0.6750000109896064,
"step": 128
},
{
"completion_length": 656.1500129699707,
"epoch": 0.08857094191790155,
"grad_norm": 0.49265533685684204,
"kl": 0.39990234375,
"learning_rate": 8.734075464262507e-06,
"loss": 0.016,
"reward": 3.324027754366398,
"reward_std": 1.9725347934290767,
"rewards/AnswerChecker_LenCheck_Reward": 0.7615277506411076,
"rewards/all-MiniLM-L6-v2": 1.862645149230957e-09,
"rewards/format_reward_beginEndSolutionFormat": 1.7374999932944775,
"rewards/length_reward": 0.8250000104308128,
"step": 130
},
{
"completion_length": 780.5625152587891,
"epoch": 0.08993357179356157,
"grad_norm": 0.5680932402610779,
"kl": 0.452880859375,
"learning_rate": 8.419986040266502e-06,
"loss": 0.0181,
"reward": 3.1687414944171906,
"reward_std": 2.452119631692767,
"rewards/AnswerChecker_LenCheck_Reward": 0.6687414180487394,
"rewards/all-MiniLM-L6-v2": 0.25,
"rewards/format_reward_beginEndSolutionFormat": 1.624999988824129,
"rewards/length_reward": 0.625000006519258,
"step": 132
},
{
"completion_length": 787.3375110626221,
"epoch": 0.0912962016692216,
"grad_norm": 0.5462779998779297,
"kl": 0.43536376953125,
"learning_rate": 8.107487556395902e-06,
"loss": 0.0174,
"reward": 2.4839657694101334,
"reward_std": 2.853791818022728,
"rewards/AnswerChecker_LenCheck_Reward": 0.6589657235890627,
"rewards/all-MiniLM-L6-v2": -0.2625000011175871,
"rewards/format_reward_beginEndSolutionFormat": 1.5124999964609742,
"rewards/length_reward": 0.5750000094994903,
"step": 134
},
{
"completion_length": 820.3000240325928,
"epoch": 0.09265883154488162,
"grad_norm": 0.5613769292831421,
"kl": 0.524169921875,
"learning_rate": 7.796894672134594e-06,
"loss": 0.021,
"reward": 1.7514715013094246,
"reward_std": 3.1442014798521996,
"rewards/AnswerChecker_LenCheck_Reward": 0.613971471786499,
"rewards/all-MiniLM-L6-v2": -0.46250000037252903,
"rewards/format_reward_beginEndSolutionFormat": 1.1749999951571226,
"rewards/length_reward": 0.42500001192092896,
"step": 136
},
{
"completion_length": 772.2000160217285,
"epoch": 0.09402146142054164,
"grad_norm": 0.5531837940216064,
"kl": 0.4697265625,
"learning_rate": 7.488520128189209e-06,
"loss": 0.0188,
"reward": 2.512004946358502,
"reward_std": 2.8804666833020747,
"rewards/AnswerChecker_LenCheck_Reward": 0.6370048951357603,
"rewards/all-MiniLM-L6-v2": -0.16249999962747097,
"rewards/format_reward_beginEndSolutionFormat": 1.4374999897554517,
"rewards/length_reward": 0.6000000163912773,
"step": 138
},
{
"completion_length": 798.4750156402588,
"epoch": 0.09538409129620166,
"grad_norm": 0.5136257410049438,
"kl": 0.46234130859375,
"learning_rate": 7.182674431585703e-06,
"loss": 0.0185,
"reward": 2.3262645918875933,
"reward_std": 3.08097755163908,
"rewards/AnswerChecker_LenCheck_Reward": 0.5512645365670323,
"rewards/all-MiniLM-L6-v2": -0.16250000055879354,
"rewards/format_reward_beginEndSolutionFormat": 1.4374999944120646,
"rewards/length_reward": 0.5000000121071935,
"step": 140
},
{
"completion_length": 826.4000129699707,
"epoch": 0.0967467211718617,
"grad_norm": 0.5762442946434021,
"kl": 0.52813720703125,
"learning_rate": 6.87966554301513e-06,
"loss": 0.0211,
"reward": 1.824558557709679,
"reward_std": 2.8447077772580087,
"rewards/AnswerChecker_LenCheck_Reward": 0.5995585434138775,
"rewards/all-MiniLM-L6-v2": -0.36249999422580004,
"rewards/format_reward_beginEndSolutionFormat": 1.2124999975785613,
"rewards/length_reward": 0.3750000046566129,
"step": 142
},
{
"completion_length": 750.8875217437744,
"epoch": 0.09810935104752172,
"grad_norm": 0.6162233948707581,
"kl": 0.4547119140625,
"learning_rate": 6.579798566743314e-06,
"loss": 0.0182,
"reward": 2.420007437467575,
"reward_std": 2.7739858217537403,
"rewards/AnswerChecker_LenCheck_Reward": 0.6075074281543493,
"rewards/all-MiniLM-L6-v2": -0.19999999832361937,
"rewards/format_reward_beginEndSolutionFormat": 1.437499993480742,
"rewards/length_reward": 0.575000012293458,
"step": 144
},
{
"completion_length": 734.2625026702881,
"epoch": 0.09947198092318174,
"grad_norm": 0.5969240069389343,
"kl": 0.5074462890625,
"learning_rate": 6.283375443396726e-06,
"loss": 0.0203,
"reward": 2.7079888563603163,
"reward_std": 2.7715829075314105,
"rewards/AnswerChecker_LenCheck_Reward": 0.6204887935891747,
"rewards/all-MiniLM-L6-v2": 0.11249999888241291,
"rewards/format_reward_beginEndSolutionFormat": 1.3999999957159162,
"rewards/length_reward": 0.5750000076368451,
"step": 146
},
{
"completion_length": 684.1750106811523,
"epoch": 0.10083461079884176,
"grad_norm": 0.6124630570411682,
"kl": 0.4541015625,
"learning_rate": 5.990694645933866e-06,
"loss": 0.0182,
"reward": 2.8833600133657455,
"reward_std": 2.8265584837645292,
"rewards/AnswerChecker_LenCheck_Reward": 0.6833599451929331,
"rewards/all-MiniLM-L6-v2": 0.21249999944120646,
"rewards/format_reward_beginEndSolutionFormat": 1.437499993480742,
"rewards/length_reward": 0.550000011920929,
"step": 148
},
{
"completion_length": 623.0000114440918,
"epoch": 0.10219724067450178,
"grad_norm": 0.6724729537963867,
"kl": 0.4202880859375,
"learning_rate": 5.702050879108284e-06,
"loss": 0.0168,
"reward": 3.6663911901414394,
"reward_std": 1.9338009762577713,
"rewards/AnswerChecker_LenCheck_Reward": 0.7163911033421755,
"rewards/all-MiniLM-L6-v2": 0.4750000014901161,
"rewards/format_reward_beginEndSolutionFormat": 1.699999992735684,
"rewards/length_reward": 0.7750000106170774,
"step": 150
},
{
"completion_length": 674.3875122070312,
"epoch": 0.10355987055016182,
"grad_norm": 0.5944858193397522,
"kl": 0.4415283203125,
"learning_rate": 5.417734782725896e-06,
"loss": 0.0177,
"reward": 3.1010947674512863,
"reward_std": 2.580965321045369,
"rewards/AnswerChecker_LenCheck_Reward": 0.7135947253555059,
"rewards/all-MiniLM-L6-v2": 0.28749999962747097,
"rewards/format_reward_beginEndSolutionFormat": 1.5499999932944775,
"rewards/length_reward": 0.5500000081956387,
"step": 152
},
{
"completion_length": 717.3375110626221,
"epoch": 0.10492250042582184,
"grad_norm": 0.6234627366065979,
"kl": 0.489990234375,
"learning_rate": 5.138032638995315e-06,
"loss": 0.0196,
"reward": 2.735639053862542,
"reward_std": 2.6947292862460017,
"rewards/AnswerChecker_LenCheck_Reward": 0.6606389936059713,
"rewards/all-MiniLM-L6-v2": 0.062499999068677425,
"rewards/format_reward_beginEndSolutionFormat": 1.5874999957159162,
"rewards/length_reward": 0.4250000072643161,
"step": 154
},
{
"completion_length": 629.3750095367432,
"epoch": 0.10628513030148186,
"grad_norm": 0.6413260102272034,
"kl": 0.4696044921875,
"learning_rate": 4.863226084265939e-06,
"loss": 0.0188,
"reward": 3.1933979094028473,
"reward_std": 2.0305717810988426,
"rewards/AnswerChecker_LenCheck_Reward": 0.71839783154428,
"rewards/all-MiniLM-L6-v2": 0.2875000024214387,
"rewards/format_reward_beginEndSolutionFormat": 1.5874999929219484,
"rewards/length_reward": 0.6000000080093741,
"step": 156
},
{
"completion_length": 742.8625106811523,
"epoch": 0.10764776017714188,
"grad_norm": 0.5482673645019531,
"kl": 0.4775390625,
"learning_rate": 4.593591825444028e-06,
"loss": 0.0191,
"reward": 2.9363540150225163,
"reward_std": 2.4036293793469667,
"rewards/AnswerChecker_LenCheck_Reward": 0.6613539699465036,
"rewards/all-MiniLM-L6-v2": 0.1000000024214387,
"rewards/format_reward_beginEndSolutionFormat": 1.6249999897554517,
"rewards/length_reward": 0.5500000109896064,
"step": 158
},
{
"completion_length": 828.2000198364258,
"epoch": 0.10901039005280191,
"grad_norm": 0.534371018409729,
"kl": 0.58740234375,
"learning_rate": 4.3294013613722944e-06,
"loss": 0.0235,
"reward": 2.148466292768717,
"reward_std": 2.682615263853222,
"rewards/AnswerChecker_LenCheck_Reward": 0.6359662003815174,
"rewards/all-MiniLM-L6-v2": -0.34999999962747097,
"rewards/format_reward_beginEndSolutionFormat": 1.4374999962747097,
"rewards/length_reward": 0.42500000540167093,
"step": 160
},
{
"completion_length": 742.5875148773193,
"epoch": 0.11037301992846194,
"grad_norm": 0.5626158714294434,
"kl": 0.444580078125,
"learning_rate": 4.070920709453597e-06,
"loss": 0.0178,
"reward": 2.9018475273624063,
"reward_std": 2.3305454067885876,
"rewards/AnswerChecker_LenCheck_Reward": 0.7143475078046322,
"rewards/all-MiniLM-L6-v2": -0.08750000037252903,
"rewards/format_reward_beginEndSolutionFormat": 1.6249999962747097,
"rewards/length_reward": 0.650000006891787,
"step": 162
},
{
"completion_length": 766.9125213623047,
"epoch": 0.11173564980412196,
"grad_norm": 0.5314887762069702,
"kl": 0.4736328125,
"learning_rate": 3.818410137793947e-06,
"loss": 0.019,
"reward": 2.8508432680973783,
"reward_std": 2.2408911171369255,
"rewards/AnswerChecker_LenCheck_Reward": 0.7008432727307081,
"rewards/all-MiniLM-L6-v2": -0.08749999944120646,
"rewards/format_reward_beginEndSolutionFormat": 1.5874999929219484,
"rewards/length_reward": 0.6500000124797225,
"step": 164
},
{
"completion_length": 800.5875053405762,
"epoch": 0.11309827967978198,
"grad_norm": 0.6379206776618958,
"kl": 0.4525146484375,
"learning_rate": 3.5721239031346067e-06,
"loss": 0.0181,
"reward": 2.8181837666779757,
"reward_std": 1.9853734835051,
"rewards/AnswerChecker_LenCheck_Reward": 0.7431836733594537,
"rewards/all-MiniLM-L6-v2": -0.07500000111758709,
"rewards/format_reward_beginEndSolutionFormat": 1.549999998882413,
"rewards/length_reward": 0.6000000042840838,
"step": 166
},
{
"completion_length": 709.2625160217285,
"epoch": 0.114460909555442,
"grad_norm": 0.596421480178833,
"kl": 0.461669921875,
"learning_rate": 3.3323099948370853e-06,
"loss": 0.0185,
"reward": 3.579191967844963,
"reward_std": 1.6637917342595756,
"rewards/AnswerChecker_LenCheck_Reward": 0.7166919354349375,
"rewards/all-MiniLM-L6-v2": 0.32499999925494194,
"rewards/format_reward_beginEndSolutionFormat": 1.7374999932944775,
"rewards/length_reward": 0.8000000063329935,
"step": 168
},
{
"completion_length": 778.4750156402588,
"epoch": 0.11582353943110203,
"grad_norm": 0.5588167309761047,
"kl": 0.4560546875,
"learning_rate": 3.099209885178882e-06,
"loss": 0.0182,
"reward": 2.6490836143493652,
"reward_std": 2.552674914477393,
"rewards/AnswerChecker_LenCheck_Reward": 0.7615835480391979,
"rewards/all-MiniLM-L6-v2": -0.18749999813735485,
"rewards/format_reward_beginEndSolutionFormat": 1.4749999921768904,
"rewards/length_reward": 0.6000000108033419,
"step": 170
},
{
"completion_length": 792.4125118255615,
"epoch": 0.11718616930676205,
"grad_norm": 0.5151498317718506,
"kl": 0.47119140625,
"learning_rate": 2.8730582862113743e-06,
"loss": 0.0188,
"reward": 2.72108455048874,
"reward_std": 2.322652825154364,
"rewards/AnswerChecker_LenCheck_Reward": 0.7460845243185759,
"rewards/all-MiniLM-L6-v2": -0.27499999944120646,
"rewards/format_reward_beginEndSolutionFormat": 1.6249999925494194,
"rewards/length_reward": 0.6250000139698386,
"step": 172
},
{
"completion_length": 821.4250068664551,
"epoch": 0.11854879918242207,
"grad_norm": 0.5205643773078918,
"kl": 0.52734375,
"learning_rate": 2.6540829134246683e-06,
"loss": 0.0211,
"reward": 2.610885198402684,
"reward_std": 3.1788224331103265,
"rewards/AnswerChecker_LenCheck_Reward": 0.6858852654695511,
"rewards/all-MiniLM-L6-v2": -0.01249999925494194,
"rewards/format_reward_beginEndSolutionFormat": 1.3624999867752194,
"rewards/length_reward": 0.5750000169500709,
"step": 174
},
{
"completion_length": 837.5875053405762,
"epoch": 0.1199114290580821,
"grad_norm": 0.5888510942459106,
"kl": 0.466461181640625,
"learning_rate": 2.4425042564574186e-06,
"loss": 0.0187,
"reward": 2.845615219324827,
"reward_std": 2.686575308907777,
"rewards/AnswerChecker_LenCheck_Reward": 0.708115229383111,
"rewards/all-MiniLM-L6-v2": 0.1000000024214387,
"rewards/format_reward_beginEndSolutionFormat": 1.4374999897554517,
"rewards/length_reward": 0.6000000108033419,
"step": 176
},
{
"completion_length": 891.9000205993652,
"epoch": 0.12127405893374212,
"grad_norm": 0.5735381841659546,
"kl": 0.5396728515625,
"learning_rate": 2.2385353570824308e-06,
"loss": 0.0216,
"reward": 2.17099030315876,
"reward_std": 2.5423294971697032,
"rewards/AnswerChecker_LenCheck_Reward": 0.6709902733564377,
"rewards/all-MiniLM-L6-v2": -0.2999999998137355,
"rewards/format_reward_beginEndSolutionFormat": 1.3249999964609742,
"rewards/length_reward": 0.47500000707805157,
"step": 178
},
{
"completion_length": 876.9625091552734,
"epoch": 0.12263668880940215,
"grad_norm": 0.4231950342655182,
"kl": 0.4525146484375,
"learning_rate": 2.0423815946916783e-06,
"loss": 0.0181,
"reward": 2.40277567692101,
"reward_std": 2.6864251531660557,
"rewards/AnswerChecker_LenCheck_Reward": 0.6652756258845329,
"rewards/all-MiniLM-L6-v2": -0.38749999925494194,
"rewards/format_reward_beginEndSolutionFormat": 1.5499999932944775,
"rewards/length_reward": 0.5750000150874257,
"step": 180
},
{
"completion_length": 771.4625129699707,
"epoch": 0.12399931868506217,
"grad_norm": 0.6879674196243286,
"kl": 0.4241943359375,
"learning_rate": 1.854240479496643e-06,
"loss": 0.017,
"reward": 2.696409245952964,
"reward_std": 2.6794386385008693,
"rewards/AnswerChecker_LenCheck_Reward": 0.7464092001318932,
"rewards/all-MiniLM-L6-v2": -0.16249999962747097,
"rewards/format_reward_beginEndSolutionFormat": 1.512499999254942,
"rewards/length_reward": 0.600000006146729,
"step": 182
},
{
"completion_length": 856.8250198364258,
"epoch": 0.1253619485607222,
"grad_norm": 0.5000143051147461,
"kl": 0.489013671875,
"learning_rate": 1.6743014536522872e-06,
"loss": 0.0196,
"reward": 2.656417434802279,
"reward_std": 2.805582005530596,
"rewards/AnswerChecker_LenCheck_Reward": 0.6689173814374954,
"rewards/all-MiniLM-L6-v2": 0.10000000055879354,
"rewards/format_reward_beginEndSolutionFormat": 1.2874999940395355,
"rewards/length_reward": 0.6000000108033419,
"step": 184
},
{
"completion_length": 966.1875114440918,
"epoch": 0.1267245784363822,
"grad_norm": 0.5162502527236938,
"kl": 0.565032958984375,
"learning_rate": 1.5027457005048573e-06,
"loss": 0.0226,
"reward": 2.036801053909585,
"reward_std": 2.7416782565414906,
"rewards/AnswerChecker_LenCheck_Reward": 0.6243010433390737,
"rewards/all-MiniLM-L6-v2": -0.16250000149011612,
"rewards/format_reward_beginEndSolutionFormat": 1.1749999970197678,
"rewards/length_reward": 0.4000000013038516,
"step": 186
},
{
"completion_length": 861.5000190734863,
"epoch": 0.12808720831204223,
"grad_norm": 0.5157842040061951,
"kl": 0.493896484375,
"learning_rate": 1.339745962155613e-06,
"loss": 0.0197,
"reward": 2.1817345349118114,
"reward_std": 2.4753956105560064,
"rewards/AnswerChecker_LenCheck_Reward": 0.6442344710230827,
"rewards/all-MiniLM-L6-v2": -0.49999999813735485,
"rewards/format_reward_beginEndSolutionFormat": 1.5124999918043613,
"rewards/length_reward": 0.525000006891787,
"step": 188
},
{
"completion_length": 839.6875190734863,
"epoch": 0.12944983818770225,
"grad_norm": 0.4954194128513336,
"kl": 0.483642578125,
"learning_rate": 1.1854663655241804e-06,
"loss": 0.0193,
"reward": 2.925493508577347,
"reward_std": 2.9417885206639767,
"rewards/AnswerChecker_LenCheck_Reward": 0.7129934653639793,
"rewards/all-MiniLM-L6-v2": 0.06250000186264515,
"rewards/format_reward_beginEndSolutionFormat": 1.4749999903142452,
"rewards/length_reward": 0.6750000109896064,
"step": 190
},
{
"completion_length": 824.5375061035156,
"epoch": 0.1308124680633623,
"grad_norm": 0.4791363477706909,
"kl": 0.4300537109375,
"learning_rate": 1.0400622570866426e-06,
"loss": 0.0172,
"reward": 2.805993139743805,
"reward_std": 2.586992080323398,
"rewards/AnswerChecker_LenCheck_Reward": 0.7059930665418506,
"rewards/all-MiniLM-L6-v2": -0.050000001676380634,
"rewards/format_reward_beginEndSolutionFormat": 1.5499999932944775,
"rewards/length_reward": 0.6000000108033419,
"step": 192
},
{
"completion_length": 923.1625137329102,
"epoch": 0.13217509793902232,
"grad_norm": 0.40569427609443665,
"kl": 0.61822509765625,
"learning_rate": 9.036800464548157e-07,
"loss": 0.0247,
"reward": 2.090137917548418,
"reward_std": 3.2905192878097296,
"rewards/AnswerChecker_LenCheck_Reward": 0.6651378944516182,
"rewards/all-MiniLM-L6-v2": -0.23750000447034836,
"rewards/format_reward_beginEndSolutionFormat": 1.2124999891966581,
"rewards/length_reward": 0.45000001043081284,
"step": 194
},
{
"completion_length": 860.8375129699707,
"epoch": 0.13353772781468234,
"grad_norm": 0.49536529183387756,
"kl": 0.450927734375,
"learning_rate": 7.764570589541876e-07,
"loss": 0.018,
"reward": 2.6283551678061485,
"reward_std": 2.2464691884815693,
"rewards/AnswerChecker_LenCheck_Reward": 0.7033550683408976,
"rewards/all-MiniLM-L6-v2": -0.23749999701976776,
"rewards/format_reward_beginEndSolutionFormat": 1.5874999919906259,
"rewards/length_reward": 0.5750000067055225,
"step": 196
},
{
"completion_length": 886.8375091552734,
"epoch": 0.13490035769034237,
"grad_norm": 0.5045952200889587,
"kl": 0.5023193359375,
"learning_rate": 6.585213973489335e-07,
"loss": 0.0201,
"reward": 2.5980349611490965,
"reward_std": 2.6176577494479716,
"rewards/AnswerChecker_LenCheck_Reward": 0.6730349091812968,
"rewards/all-MiniLM-L6-v2": -0.125,
"rewards/format_reward_beginEndSolutionFormat": 1.474999994970858,
"rewards/length_reward": 0.5750000094994903,
"step": 198
},
{
"completion_length": 821.5750122070312,
"epoch": 0.13626298756600239,
"grad_norm": 0.5383718609809875,
"kl": 0.44384765625,
"learning_rate": 5.499918128533155e-07,
"loss": 0.0178,
"reward": 2.671635969541967,
"reward_std": 2.3409718545153737,
"rewards/AnswerChecker_LenCheck_Reward": 0.7591358739882708,
"rewards/all-MiniLM-L6-v2": -0.3124999990686774,
"rewards/format_reward_beginEndSolutionFormat": 1.6249999972060323,
"rewards/length_reward": 0.600000012665987,
"step": 200
},
{
"epoch": 0.13626298756600239,
"eval_completion_length": 901.0770969390869,
"eval_kl": 0.51776123046875,
"eval_loss": 0.020734939724206924,
"eval_reward": 2.2421040004119277,
"eval_reward_std": 3.041678664914798,
"eval_rewards/AnswerChecker_LenCheck_Reward": 0.6764789510052651,
"eval_rewards/all-MiniLM-L6-v2": -0.21718749997671694,
"eval_rewards/format_reward_beginEndSolutionFormat": 1.2921874948078766,
"eval_rewards/length_reward": 0.4906250089406967,
"eval_runtime": 1491.0997,
"eval_samples_per_second": 0.086,
"eval_steps_per_second": 0.017,
"step": 200
},
{
"completion_length": 868.400016784668,
"epoch": 0.1376256174416624,
"grad_norm": 0.5225978493690491,
"kl": 0.470703125,
"learning_rate": 4.509775855592613e-07,
"loss": 0.0188,
"reward": 2.6535421311855316,
"reward_std": 2.792340838816017,
"rewards/AnswerChecker_LenCheck_Reward": 0.6660420242697,
"rewards/all-MiniLM-L6-v2": 0.08750000316649675,
"rewards/format_reward_beginEndSolutionFormat": 1.3249999936670065,
"rewards/length_reward": 0.5750000094994903,
"step": 202
},
{
"completion_length": 866.7875213623047,
"epoch": 0.13898824731732243,
"grad_norm": 0.4848329722881317,
"kl": 0.485107421875,
"learning_rate": 3.615784144005796e-07,
"loss": 0.0194,
"reward": 2.717348374426365,
"reward_std": 3.1343387353699654,
"rewards/AnswerChecker_LenCheck_Reward": 0.7048483230173588,
"rewards/all-MiniLM-L6-v2": 0.06250000186264515,
"rewards/format_reward_beginEndSolutionFormat": 1.3999999919906259,
"rewards/length_reward": 0.550000011920929,
"step": 204
},
{
"completion_length": 899.8250122070312,
"epoch": 0.14035087719298245,
"grad_norm": 0.7146245837211609,
"kl": 1.0164794921875,
"learning_rate": 2.818843167645835e-07,
"loss": 0.0407,
"reward": 2.0691821854561567,
"reward_std": 3.262540274299681,
"rewards/AnswerChecker_LenCheck_Reward": 0.6441821809858084,
"rewards/all-MiniLM-L6-v2": -0.23750000074505806,
"rewards/format_reward_beginEndSolutionFormat": 1.2124999957159162,
"rewards/length_reward": 0.4500000076368451,
"step": 206
},
{
"completion_length": 891.0625190734863,
"epoch": 0.14171350706864247,
"grad_norm": 0.4813491702079773,
"kl": 0.4830322265625,
"learning_rate": 2.119755378522137e-07,
"loss": 0.0193,
"reward": 2.4804067488294095,
"reward_std": 2.613793831784278,
"rewards/AnswerChecker_LenCheck_Reward": 0.680406715720892,
"rewards/all-MiniLM-L6-v2": -0.04999999608844519,
"rewards/format_reward_beginEndSolutionFormat": 1.325000001117587,
"rewards/length_reward": 0.5250000078231096,
"step": 208
},
{
"completion_length": 837.337516784668,
"epoch": 0.1430761369443025,
"grad_norm": 0.4959147870540619,
"kl": 0.4730224609375,
"learning_rate": 1.519224698779198e-07,
"loss": 0.0189,
"reward": 2.9152769446372986,
"reward_std": 2.3198010358028114,
"rewards/AnswerChecker_LenCheck_Reward": 0.7527768295258284,
"rewards/all-MiniLM-L6-v2": 1.862645149230957e-09,
"rewards/format_reward_beginEndSolutionFormat": 1.5874999957159162,
"rewards/length_reward": 0.5750000039115548,
"step": 210
},
{
"completion_length": 871.5125160217285,
"epoch": 0.14443876681996254,
"grad_norm": 0.9553112387657166,
"kl": 0.5531005859375,
"learning_rate": 1.0178558119067316e-07,
"loss": 0.0221,
"reward": 2.6484466195106506,
"reward_std": 2.807733765337616,
"rewards/AnswerChecker_LenCheck_Reward": 0.6984465261921287,
"rewards/all-MiniLM-L6-v2": 0.08750000223517418,
"rewards/format_reward_beginEndSolutionFormat": 1.2874999893829226,
"rewards/length_reward": 0.5750000076368451,
"step": 212
},
{
"completion_length": 909.4750137329102,
"epoch": 0.14580139669562256,
"grad_norm": 0.5723004937171936,
"kl": 0.57098388671875,
"learning_rate": 6.161535538745877e-08,
"loss": 0.0229,
"reward": 1.5668016755953431,
"reward_std": 2.593209580751136,
"rewards/AnswerChecker_LenCheck_Reward": 0.6418016445823014,
"rewards/all-MiniLM-L6-v2": -0.5000000027939677,
"rewards/format_reward_beginEndSolutionFormat": 1.0249999966472387,
"rewards/length_reward": 0.40000000316649675,
"step": 214
},
{
"completion_length": 968.3375205993652,
"epoch": 0.14716402657128258,
"grad_norm": 0.4992906153202057,
"kl": 0.6209716796875,
"learning_rate": 3.1452240480577265e-08,
"loss": 0.0248,
"reward": 1.5952948506455868,
"reward_std": 3.052502178354189,
"rewards/AnswerChecker_LenCheck_Reward": 0.6452948525547981,
"rewards/all-MiniLM-L6-v2": -0.462499993853271,
"rewards/format_reward_beginEndSolutionFormat": 1.062499993480742,
"rewards/length_reward": 0.350000006146729,
"step": 216
},
{
"completion_length": 888.4625244140625,
"epoch": 0.1485266564469426,
"grad_norm": 0.5244458913803101,
"kl": 0.5447998046875,
"learning_rate": 1.1326608169920373e-08,
"loss": 0.0218,
"reward": 2.0069867819547653,
"reward_std": 2.44455174729228,
"rewards/AnswerChecker_LenCheck_Reward": 0.6694867238402367,
"rewards/all-MiniLM-L6-v2": -0.4124999986961484,
"rewards/format_reward_beginEndSolutionFormat": 1.2499999990686774,
"rewards/length_reward": 0.5000000046566129,
"step": 218
},
{
"completion_length": 940.7250213623047,
"epoch": 0.14988928632260262,
"grad_norm": 0.45825526118278503,
"kl": 0.569427490234375,
"learning_rate": 1.2587232612493172e-09,
"loss": 0.0228,
"reward": 2.0391996294492856,
"reward_std": 3.5446557994000614,
"rewards/AnswerChecker_LenCheck_Reward": 0.6266996059566736,
"rewards/all-MiniLM-L6-v2": -0.04999999608844519,
"rewards/format_reward_beginEndSolutionFormat": 1.0624999953433871,
"rewards/length_reward": 0.40000000689178705,
"step": 220
},
{
"completion_length": 826.150016784668,
"epoch": 0.15057060126043265,
"kl": 0.503173828125,
"reward": 2.8795320093631744,
"reward_std": 2.7599759995937347,
"rewards/AnswerChecker_LenCheck_Reward": 0.7045319639146328,
"rewards/all-MiniLM-L6-v2": -0.04999999701976776,
"rewards/format_reward_beginEndSolutionFormat": 1.6249999925494194,
"rewards/length_reward": 0.600000012665987,
"step": 221,
"total_flos": 0.0,
"train_loss": 0.014638028192195337,
"train_runtime": 22832.117,
"train_samples_per_second": 0.077,
"train_steps_per_second": 0.01
}
],
"logging_steps": 2,
"max_steps": 221,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 30,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 5,
"trial_name": null,
"trial_params": null
}