{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 98,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 160.0,
      "epoch": 0.01020408163265306,
      "grad_norm": 0.16015149652957916,
      "kl": 0.0,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0,
      "reward": 0.13549137115478516,
      "reward_std": 0.122966468334198,
      "rewards/<lambda>": 0.13549137115478516,
      "step": 1
    },
    {
      "completion_length": 160.0,
      "epoch": 0.02040816326530612,
      "grad_norm": 0.1122620478272438,
      "kl": 0.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "reward": 0.1350748986005783,
      "reward_std": 0.13239088654518127,
      "rewards/<lambda>": 0.1350748986005783,
      "step": 2
    },
    {
      "completion_length": 160.0,
      "epoch": 0.030612244897959183,
      "grad_norm": 0.10055773705244064,
      "kl": 0.0009823411237448454,
      "learning_rate": 3e-06,
      "loss": 0.0,
      "reward": 0.11044053733348846,
      "reward_std": 0.09149592369794846,
      "rewards/<lambda>": 0.11044053733348846,
      "step": 3
    },
    {
      "completion_length": 160.0,
      "epoch": 0.04081632653061224,
      "grad_norm": 0.1106867864727974,
      "kl": 0.0011138569097965956,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "reward": 0.14424282312393188,
      "reward_std": 0.08860041201114655,
      "rewards/<lambda>": 0.14424282312393188,
      "step": 4
    },
    {
      "completion_length": 160.0,
      "epoch": 0.05102040816326531,
      "grad_norm": 0.10906749963760376,
      "kl": 0.0009323786944150925,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "reward": 0.15370804071426392,
      "reward_std": 0.12023884057998657,
      "rewards/<lambda>": 0.15370804071426392,
      "step": 5
    },
    {
      "completion_length": 160.0,
      "epoch": 0.061224489795918366,
      "grad_norm": 0.0973278358578682,
      "kl": 0.000986273866146803,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "reward": 0.16775861382484436,
      "reward_std": 0.11324145644903183,
      "rewards/<lambda>": 0.16775861382484436,
      "step": 6
    },
    {
      "completion_length": 160.0,
      "epoch": 0.07142857142857142,
      "grad_norm": 0.11650331318378448,
      "kl": 0.0009559993632137775,
      "learning_rate": 7.000000000000001e-06,
      "loss": 0.0,
      "reward": 0.12161540985107422,
      "reward_std": 0.09721754491329193,
      "rewards/<lambda>": 0.12161540985107422,
      "step": 7
    },
    {
      "completion_length": 160.0,
      "epoch": 0.08163265306122448,
      "grad_norm": 0.14426998794078827,
      "kl": 0.001172696123830974,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "reward": 0.10382680594921112,
      "reward_std": 0.08653440326452255,
      "rewards/<lambda>": 0.10382680594921112,
      "step": 8
    },
    {
      "completion_length": 160.0,
      "epoch": 0.09183673469387756,
      "grad_norm": 0.09224210679531097,
      "kl": 0.0009267181158065796,
      "learning_rate": 9e-06,
      "loss": 0.0,
      "reward": 0.15248040854930878,
      "reward_std": 0.10083242505788803,
      "rewards/<lambda>": 0.15248040854930878,
      "step": 9
    },
    {
      "completion_length": 160.0,
      "epoch": 0.10204081632653061,
      "grad_norm": 0.10662151873111725,
      "kl": 0.001049146056175232,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.10904872417449951,
      "reward_std": 0.07905881851911545,
      "rewards/<lambda>": 0.10904872417449951,
      "step": 10
    },
    {
      "completion_length": 160.0,
      "epoch": 0.11224489795918367,
      "grad_norm": 0.08880773186683655,
      "kl": 0.0009575427393428981,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.0,
      "reward": 0.1023264229297638,
      "reward_std": 0.09154930710792542,
      "rewards/<lambda>": 0.1023264229297638,
      "step": 11
    },
    {
      "completion_length": 160.0,
      "epoch": 0.12244897959183673,
      "grad_norm": 0.1399761289358139,
      "kl": 0.0010016188025474548,
      "learning_rate": 1.2e-05,
      "loss": 0.0,
      "reward": 0.12774227559566498,
      "reward_std": 0.10531343519687653,
      "rewards/<lambda>": 0.12774227559566498,
      "step": 12
    },
    {
      "completion_length": 160.0,
      "epoch": 0.1326530612244898,
      "grad_norm": 0.10604196786880493,
      "kl": 0.0010334912221878767,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.0,
      "reward": 0.13598087430000305,
      "reward_std": 0.12228463590145111,
      "rewards/<lambda>": 0.13598087430000305,
      "step": 13
    },
    {
      "completion_length": 160.0,
      "epoch": 0.14285714285714285,
      "grad_norm": 0.1302865892648697,
      "kl": 0.0010531357256695628,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.0,
      "reward": 0.09349755942821503,
      "reward_std": 0.07072040438652039,
      "rewards/<lambda>": 0.09349755942821503,
      "step": 14
    },
    {
      "completion_length": 160.0,
      "epoch": 0.15306122448979592,
      "grad_norm": 0.12415535002946854,
      "kl": 0.0009964585769921541,
      "learning_rate": 1.5e-05,
      "loss": 0.0,
      "reward": 0.11064597219228745,
      "reward_std": 0.08005572855472565,
      "rewards/<lambda>": 0.11064597219228745,
      "step": 15
    },
    {
      "completion_length": 160.0,
      "epoch": 0.16326530612244897,
      "grad_norm": 0.11816220730543137,
      "kl": 0.0009764357237145305,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0,
      "reward": 0.1383560299873352,
      "reward_std": 0.09371937811374664,
      "rewards/<lambda>": 0.1383560299873352,
      "step": 16
    },
    {
      "completion_length": 160.0,
      "epoch": 0.17346938775510204,
      "grad_norm": 0.10982600599527359,
      "kl": 0.0009334891801699996,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.0,
      "reward": 0.12855608761310577,
      "reward_std": 0.11154236644506454,
      "rewards/<lambda>": 0.12855608761310577,
      "step": 17
    },
    {
      "completion_length": 160.0,
      "epoch": 0.1836734693877551,
      "grad_norm": 0.09776873886585236,
      "kl": 0.0008928977185860276,
      "learning_rate": 1.8e-05,
      "loss": 0.0,
      "reward": 0.15613257884979248,
      "reward_std": 0.13504436612129211,
      "rewards/<lambda>": 0.15613257884979248,
      "step": 18
    },
    {
      "completion_length": 160.0,
      "epoch": 0.19387755102040816,
      "grad_norm": 0.12221962213516235,
      "kl": 0.0010021468624472618,
      "learning_rate": 1.9e-05,
      "loss": 0.0,
      "reward": 0.15936216711997986,
      "reward_std": 0.09952296316623688,
      "rewards/<lambda>": 0.15936216711997986,
      "step": 19
    },
    {
      "completion_length": 160.0,
      "epoch": 0.20408163265306123,
      "grad_norm": 0.09339983761310577,
      "kl": 0.0011222452158108354,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "reward": 0.09720780700445175,
      "reward_std": 0.08142109215259552,
      "rewards/<lambda>": 0.09720780700445175,
      "step": 20
    },
    {
      "completion_length": 160.0,
      "epoch": 0.21428571428571427,
      "grad_norm": 0.11736761033535004,
      "kl": 0.0011920102406293154,
      "learning_rate": 2.1e-05,
      "loss": 0.0,
      "reward": 0.15125760436058044,
      "reward_std": 0.10276186466217041,
      "rewards/<lambda>": 0.15125760436058044,
      "step": 21
    },
    {
      "completion_length": 160.0,
      "epoch": 0.22448979591836735,
      "grad_norm": 0.13611504435539246,
      "kl": 0.00114919594489038,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.0,
      "reward": 0.1826939433813095,
      "reward_std": 0.12737450003623962,
      "rewards/<lambda>": 0.1826939433813095,
      "step": 22
    },
    {
      "completion_length": 160.0,
      "epoch": 0.23469387755102042,
      "grad_norm": 0.12078937888145447,
      "kl": 0.001010789768770337,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.0,
      "reward": 0.15208037197589874,
      "reward_std": 0.13148412108421326,
      "rewards/<lambda>": 0.15208037197589874,
      "step": 23
    },
    {
      "completion_length": 160.0,
      "epoch": 0.24489795918367346,
      "grad_norm": 0.14114625751972198,
      "kl": 0.0011141165159642696,
      "learning_rate": 2.4e-05,
      "loss": 0.0,
      "reward": 0.13319575786590576,
      "reward_std": 0.10379491746425629,
      "rewards/<lambda>": 0.13319575786590576,
      "step": 24
    },
    {
      "completion_length": 160.0,
      "epoch": 0.25510204081632654,
      "grad_norm": 0.08827733993530273,
      "kl": 0.0010151572059839964,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "reward": 0.1206921935081482,
      "reward_std": 0.11820320785045624,
      "rewards/<lambda>": 0.1206921935081482,
      "step": 25
    },
    {
      "completion_length": 160.0,
      "epoch": 0.2653061224489796,
      "grad_norm": 0.10461141169071198,
      "kl": 0.0010629891185089946,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.0,
      "reward": 0.12660565972328186,
      "reward_std": 0.09369075298309326,
      "rewards/<lambda>": 0.12660565972328186,
      "step": 26
    },
    {
      "completion_length": 160.0,
      "epoch": 0.2755102040816326,
      "grad_norm": 0.12817198038101196,
      "kl": 0.0014134375378489494,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.0001,
      "reward": 0.15190695226192474,
      "reward_std": 0.1361895054578781,
      "rewards/<lambda>": 0.15190695226192474,
      "step": 27
    },
    {
      "completion_length": 160.0,
      "epoch": 0.2857142857142857,
      "grad_norm": 0.14398054778575897,
      "kl": 0.0014005769044160843,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.0001,
      "reward": 0.11002078652381897,
      "reward_std": 0.08406772464513779,
      "rewards/<lambda>": 0.11002078652381897,
      "step": 28
    },
    {
      "completion_length": 160.0,
      "epoch": 0.29591836734693877,
      "grad_norm": 0.12125135213136673,
      "kl": 0.001406812109053135,
      "learning_rate": 2.9e-05,
      "loss": 0.0001,
      "reward": 0.1488090455532074,
      "reward_std": 0.09648909419775009,
      "rewards/<lambda>": 0.1488090455532074,
      "step": 29
    },
    {
      "completion_length": 160.0,
      "epoch": 0.30612244897959184,
      "grad_norm": 0.1116093099117279,
      "kl": 0.001532193971797824,
      "learning_rate": 3e-05,
      "loss": 0.0001,
      "reward": 0.1401943415403366,
      "reward_std": 0.10262932628393173,
      "rewards/<lambda>": 0.1401943415403366,
      "step": 30
    },
    {
      "completion_length": 160.0,
      "epoch": 0.3163265306122449,
      "grad_norm": 0.11590556800365448,
      "kl": 0.0013668447500094771,
      "learning_rate": 3.1e-05,
      "loss": 0.0001,
      "reward": 0.15992209315299988,
      "reward_std": 0.13228771090507507,
      "rewards/<lambda>": 0.15992209315299988,
      "step": 31
    },
    {
      "completion_length": 160.0,
      "epoch": 0.32653061224489793,
      "grad_norm": 0.22361916303634644,
      "kl": 0.0015757133951410651,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.0001,
      "reward": 0.14634232223033905,
      "reward_std": 0.0937654972076416,
      "rewards/<lambda>": 0.14634232223033905,
      "step": 32
    },
    {
      "completion_length": 160.0,
      "epoch": 0.336734693877551,
      "grad_norm": 0.11585766822099686,
      "kl": 0.0013871926348656416,
      "learning_rate": 3.3e-05,
      "loss": 0.0001,
      "reward": 0.1371658891439438,
      "reward_std": 0.0987061858177185,
      "rewards/<lambda>": 0.1371658891439438,
      "step": 33
    },
    {
      "completion_length": 160.0,
      "epoch": 0.3469387755102041,
      "grad_norm": 0.12178175151348114,
      "kl": 0.00142570654861629,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.0001,
      "reward": 0.12351685017347336,
      "reward_std": 0.11602398008108139,
      "rewards/<lambda>": 0.12351685017347336,
      "step": 34
    },
    {
      "completion_length": 160.0,
      "epoch": 0.35714285714285715,
      "grad_norm": 0.0959494486451149,
      "kl": 0.0016183136031031609,
      "learning_rate": 3.5e-05,
      "loss": 0.0001,
      "reward": 0.08838998526334763,
      "reward_std": 0.08110953867435455,
      "rewards/<lambda>": 0.08838998526334763,
      "step": 35
    },
    {
      "completion_length": 160.0,
      "epoch": 0.3673469387755102,
      "grad_norm": 0.10338612645864487,
      "kl": 0.0017382192891091108,
      "learning_rate": 3.6e-05,
      "loss": 0.0001,
      "reward": 0.16435359418392181,
      "reward_std": 0.13644874095916748,
      "rewards/<lambda>": 0.16435359418392181,
      "step": 36
    },
    {
      "completion_length": 160.0,
      "epoch": 0.37755102040816324,
      "grad_norm": 0.08886157721281052,
      "kl": 0.00104477908462286,
      "learning_rate": 3.7e-05,
      "loss": 0.0,
      "reward": 0.12062600255012512,
      "reward_std": 0.10176925361156464,
      "rewards/<lambda>": 0.12062600255012512,
      "step": 37
    },
    {
      "completion_length": 160.0,
      "epoch": 0.3877551020408163,
      "grad_norm": 0.16644084453582764,
      "kl": 0.001502887113019824,
      "learning_rate": 3.8e-05,
      "loss": 0.0001,
      "reward": 0.12538418173789978,
      "reward_std": 0.11342241615056992,
      "rewards/<lambda>": 0.12538418173789978,
      "step": 38
    },
    {
      "completion_length": 160.0,
      "epoch": 0.3979591836734694,
      "grad_norm": 0.10507523268461227,
      "kl": 0.0016810973174870014,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.0001,
      "reward": 0.1384812593460083,
      "reward_std": 0.10060354322195053,
      "rewards/<lambda>": 0.1384812593460083,
      "step": 39
    },
    {
      "completion_length": 156.89584350585938,
      "epoch": 0.40816326530612246,
      "grad_norm": 0.13816726207733154,
      "kl": 0.002180024515837431,
      "learning_rate": 4e-05,
      "loss": 0.0001,
      "reward": 0.1627415418624878,
      "reward_std": 0.09559802711009979,
      "rewards/<lambda>": 0.1627415418624878,
      "step": 40
    },
    {
      "completion_length": 160.0,
      "epoch": 0.41836734693877553,
      "grad_norm": 0.09595762193202972,
      "kl": 0.001595992362126708,
      "learning_rate": 4.1e-05,
      "loss": 0.0001,
      "reward": 0.1617720127105713,
      "reward_std": 0.09887909144163132,
      "rewards/<lambda>": 0.1617720127105713,
      "step": 41
    },
    {
      "completion_length": 160.0,
      "epoch": 0.42857142857142855,
      "grad_norm": 0.19110041856765747,
      "kl": 0.002547662705183029,
      "learning_rate": 4.2e-05,
      "loss": 0.0001,
      "reward": 0.19862735271453857,
      "reward_std": 0.11392591893672943,
      "rewards/<lambda>": 0.19862735271453857,
      "step": 42
    },
    {
      "completion_length": 160.0,
      "epoch": 0.4387755102040816,
      "grad_norm": 0.09072164446115494,
      "kl": 0.0016248103929683566,
      "learning_rate": 4.3e-05,
      "loss": 0.0001,
      "reward": 0.13210207223892212,
      "reward_std": 0.09667991101741791,
      "rewards/<lambda>": 0.13210207223892212,
      "step": 43
    },
    {
      "completion_length": 160.0,
      "epoch": 0.4489795918367347,
      "grad_norm": 0.10356740653514862,
      "kl": 0.002113830065354705,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.0001,
      "reward": 0.14277184009552002,
      "reward_std": 0.09977956861257553,
      "rewards/<lambda>": 0.14277184009552002,
      "step": 44
    },
    {
      "completion_length": 160.0,
      "epoch": 0.45918367346938777,
      "grad_norm": 0.1663713902235031,
      "kl": 0.0063522434793412685,
      "learning_rate": 4.5e-05,
      "loss": 0.0003,
      "reward": 0.16242042183876038,
      "reward_std": 0.12298040091991425,
      "rewards/<lambda>": 0.16242042183876038,
      "step": 45
    },
    {
      "completion_length": 160.0,
      "epoch": 0.46938775510204084,
      "grad_norm": 0.11778972297906876,
      "kl": 0.0025551035068929195,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.0001,
      "reward": 0.12898343801498413,
      "reward_std": 0.09911265969276428,
      "rewards/<lambda>": 0.12898343801498413,
      "step": 46
    },
    {
      "completion_length": 160.0,
      "epoch": 0.47959183673469385,
      "grad_norm": 0.13733811676502228,
      "kl": 0.004000469576567411,
      "learning_rate": 4.7e-05,
      "loss": 0.0002,
      "reward": 0.18428276479244232,
      "reward_std": 0.1296135038137436,
      "rewards/<lambda>": 0.18428276479244232,
      "step": 47
    },
    {
      "completion_length": 160.0,
      "epoch": 0.4897959183673469,
      "grad_norm": 0.10343091934919357,
      "kl": 0.0036480827257037163,
      "learning_rate": 4.8e-05,
      "loss": 0.0001,
      "reward": 0.1390620619058609,
      "reward_std": 0.10592266172170639,
      "rewards/<lambda>": 0.1390620619058609,
      "step": 48
    },
    {
      "completion_length": 160.0,
      "epoch": 0.5,
      "grad_norm": 0.1648188680410385,
      "kl": 0.003458770690485835,
      "learning_rate": 4.9e-05,
      "loss": 0.0001,
      "reward": 0.16380682587623596,
      "reward_std": 0.10548572242259979,
      "rewards/<lambda>": 0.16380682587623596,
      "step": 49
    },
    {
      "completion_length": 160.0,
      "epoch": 0.5102040816326531,
      "grad_norm": 0.0953877791762352,
      "kl": 0.002513691782951355,
      "learning_rate": 5e-05,
      "loss": 0.0001,
      "reward": 0.14581327140331268,
      "reward_std": 0.12193475663661957,
      "rewards/<lambda>": 0.14581327140331268,
      "step": 50
    },
    {
      "completion_length": 160.0,
      "epoch": 0.5204081632653061,
      "grad_norm": 0.14063876867294312,
      "kl": 0.004633021075278521,
      "learning_rate": 5.1000000000000006e-05,
      "loss": 0.0002,
      "reward": 0.20702508091926575,
      "reward_std": 0.13710586726665497,
      "rewards/<lambda>": 0.20702508091926575,
      "step": 51
    },
    {
      "completion_length": 160.0,
      "epoch": 0.5306122448979592,
      "grad_norm": 0.1019497662782669,
      "kl": 0.0037124312948435545,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.0001,
      "reward": 0.13214847445487976,
      "reward_std": 0.09029597043991089,
      "rewards/<lambda>": 0.13214847445487976,
      "step": 52
    },
    {
      "completion_length": 160.0,
      "epoch": 0.5408163265306123,
      "grad_norm": 0.12852047383785248,
      "kl": 0.004707551561295986,
      "learning_rate": 5.300000000000001e-05,
      "loss": 0.0002,
      "reward": 0.1572979986667633,
      "reward_std": 0.11500580608844757,
      "rewards/<lambda>": 0.1572979986667633,
      "step": 53
    },
    {
      "completion_length": 160.0,
      "epoch": 0.5510204081632653,
      "grad_norm": 0.1126970499753952,
      "kl": 0.0029443646781146526,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.0001,
      "reward": 0.11422993242740631,
      "reward_std": 0.1095927357673645,
      "rewards/<lambda>": 0.11422993242740631,
      "step": 54
    },
    {
      "completion_length": 160.0,
      "epoch": 0.5612244897959183,
      "grad_norm": 0.1265789270401001,
      "kl": 0.004524104297161102,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0002,
      "reward": 0.1222875714302063,
      "reward_std": 0.0923609733581543,
      "rewards/<lambda>": 0.1222875714302063,
      "step": 55
    },
    {
      "completion_length": 160.0,
      "epoch": 0.5714285714285714,
      "grad_norm": 0.12009646743535995,
      "kl": 0.0038815774023532867,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.0002,
      "reward": 0.1649770438671112,
      "reward_std": 0.10861348360776901,
      "rewards/<lambda>": 0.1649770438671112,
      "step": 56
    },
    {
      "completion_length": 160.0,
      "epoch": 0.5816326530612245,
      "grad_norm": 0.1011093482375145,
      "kl": 0.0032921030651777983,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 0.0001,
      "reward": 0.17336896061897278,
      "reward_std": 0.12328130006790161,
      "rewards/<lambda>": 0.17336896061897278,
      "step": 57
    },
    {
      "completion_length": 160.0,
      "epoch": 0.5918367346938775,
      "grad_norm": 0.10525462031364441,
      "kl": 0.004167443141341209,
      "learning_rate": 5.8e-05,
      "loss": 0.0002,
      "reward": 0.1390347182750702,
      "reward_std": 0.11740852892398834,
      "rewards/<lambda>": 0.1390347182750702,
      "step": 58
    },
    {
      "completion_length": 160.0,
      "epoch": 0.6020408163265306,
      "grad_norm": 0.3547665774822235,
      "kl": 0.00994147639721632,
      "learning_rate": 5.9e-05,
      "loss": 0.0004,
      "reward": 0.1372447907924652,
      "reward_std": 0.08885445445775986,
      "rewards/<lambda>": 0.1372447907924652,
      "step": 59
    },
    {
      "completion_length": 160.0,
      "epoch": 0.6122448979591837,
      "grad_norm": 0.14041198790073395,
      "kl": 0.005412312224507332,
      "learning_rate": 6e-05,
      "loss": 0.0002,
      "reward": 0.14578765630722046,
      "reward_std": 0.095134437084198,
      "rewards/<lambda>": 0.14578765630722046,
      "step": 60
    },
    {
      "completion_length": 160.0,
      "epoch": 0.6224489795918368,
      "grad_norm": 0.13052710890769958,
      "kl": 0.004689443856477737,
      "learning_rate": 6.1e-05,
      "loss": 0.0002,
      "reward": 0.09727954864501953,
      "reward_std": 0.06896870583295822,
      "rewards/<lambda>": 0.09727954864501953,
      "step": 61
    },
    {
      "completion_length": 157.1875,
      "epoch": 0.6326530612244898,
      "grad_norm": 0.1129918321967125,
      "kl": 0.004512472078204155,
      "learning_rate": 6.2e-05,
      "loss": 0.0002,
      "reward": 0.17984223365783691,
      "reward_std": 0.09912577271461487,
      "rewards/<lambda>": 0.17984223365783691,
      "step": 62
    },
    {
      "completion_length": 160.0,
      "epoch": 0.6428571428571429,
      "grad_norm": 0.11350245773792267,
      "kl": 0.005884611513465643,
      "learning_rate": 6.3e-05,
      "loss": 0.0002,
      "reward": 0.13487395644187927,
      "reward_std": 0.09702014178037643,
      "rewards/<lambda>": 0.13487395644187927,
      "step": 63
    },
    {
      "completion_length": 160.0,
      "epoch": 0.6530612244897959,
      "grad_norm": 0.1478883922100067,
      "kl": 0.0060376739129424095,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.0002,
      "reward": 0.13012471795082092,
      "reward_std": 0.09517987817525864,
      "rewards/<lambda>": 0.13012471795082092,
      "step": 64
    },
    {
      "completion_length": 160.0,
      "epoch": 0.6632653061224489,
      "grad_norm": 0.09250291436910629,
      "kl": 0.005326719488948584,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.0002,
      "reward": 0.17718777060508728,
      "reward_std": 0.11379577964544296,
      "rewards/<lambda>": 0.17718777060508728,
      "step": 65
    },
    {
      "completion_length": 160.0,
      "epoch": 0.673469387755102,
      "grad_norm": 0.18939143419265747,
      "kl": 0.0049583157524466515,
      "learning_rate": 6.6e-05,
      "loss": 0.0002,
      "reward": 0.14007148146629333,
      "reward_std": 0.09873458743095398,
      "rewards/<lambda>": 0.14007148146629333,
      "step": 66
    },
    {
      "completion_length": 160.0,
      "epoch": 0.6836734693877551,
      "grad_norm": 0.09305741637945175,
      "kl": 0.00586826354265213,
      "learning_rate": 6.7e-05,
      "loss": 0.0002,
      "reward": 0.10462306439876556,
      "reward_std": 0.09117605537176132,
      "rewards/<lambda>": 0.10462306439876556,
      "step": 67
    },
    {
      "completion_length": 160.0,
      "epoch": 0.6938775510204082,
      "grad_norm": 0.14123046398162842,
      "kl": 0.006275478284806013,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.0003,
      "reward": 0.16492299735546112,
      "reward_std": 0.1278476119041443,
      "rewards/<lambda>": 0.16492299735546112,
      "step": 68
    },
    {
      "completion_length": 160.0,
      "epoch": 0.7040816326530612,
      "grad_norm": 0.10926412045955658,
      "kl": 0.005929266568273306,
      "learning_rate": 6.9e-05,
      "loss": 0.0002,
      "reward": 0.1173870787024498,
      "reward_std": 0.09027393907308578,
      "rewards/<lambda>": 0.1173870787024498,
      "step": 69
    },
    {
      "completion_length": 160.0,
      "epoch": 0.7142857142857143,
      "grad_norm": 0.11727511882781982,
      "kl": 0.007982933893799782,
      "learning_rate": 7e-05,
      "loss": 0.0003,
      "reward": 0.1433873325586319,
      "reward_std": 0.09991258382797241,
      "rewards/<lambda>": 0.1433873325586319,
      "step": 70
    },
    {
      "completion_length": 160.0,
      "epoch": 0.7244897959183674,
      "grad_norm": 0.09994583576917648,
      "kl": 0.008151376619935036,
      "learning_rate": 7.1e-05,
      "loss": 0.0003,
      "reward": 0.17650912702083588,
      "reward_std": 0.1265939176082611,
      "rewards/<lambda>": 0.17650912702083588,
      "step": 71
    },
    {
      "completion_length": 160.0,
      "epoch": 0.7346938775510204,
      "grad_norm": 0.11233754456043243,
      "kl": 0.008668525144457817,
      "learning_rate": 7.2e-05,
      "loss": 0.0003,
      "reward": 0.1490788459777832,
      "reward_std": 0.10998384654521942,
      "rewards/<lambda>": 0.1490788459777832,
      "step": 72
    },
    {
      "completion_length": 160.0,
      "epoch": 0.7448979591836735,
      "grad_norm": 0.15177902579307556,
      "kl": 0.008991223759949207,
      "learning_rate": 7.3e-05,
      "loss": 0.0004,
      "reward": 0.1158258318901062,
      "reward_std": 0.09271200001239777,
      "rewards/<lambda>": 0.1158258318901062,
      "step": 73
    },
    {
      "completion_length": 160.0,
      "epoch": 0.7551020408163265,
      "grad_norm": 0.12361659109592438,
      "kl": 0.009935474023222923,
      "learning_rate": 7.4e-05,
      "loss": 0.0004,
      "reward": 0.16675977408885956,
      "reward_std": 0.11429008096456528,
      "rewards/<lambda>": 0.16675977408885956,
      "step": 74
    },
    {
      "completion_length": 160.0,
      "epoch": 0.7653061224489796,
      "grad_norm": 0.10791321843862534,
      "kl": 0.01029084250330925,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0004,
      "reward": 0.1560361236333847,
      "reward_std": 0.12631307542324066,
      "rewards/<lambda>": 0.1560361236333847,
      "step": 75
    },
    {
      "completion_length": 160.0,
      "epoch": 0.7755102040816326,
      "grad_norm": 0.11729063093662262,
      "kl": 0.013020636513829231,
      "learning_rate": 7.6e-05,
      "loss": 0.0005,
      "reward": 0.13625627756118774,
      "reward_std": 0.09627413749694824,
      "rewards/<lambda>": 0.13625627756118774,
      "step": 76
    },
    {
      "completion_length": 160.0,
      "epoch": 0.7857142857142857,
      "grad_norm": 0.14529183506965637,
      "kl": 0.016384603455662727,
      "learning_rate": 7.7e-05,
      "loss": 0.0007,
      "reward": 0.1917780488729477,
      "reward_std": 0.10966574400663376,
      "rewards/<lambda>": 0.1917780488729477,
      "step": 77
    },
    {
      "completion_length": 160.0,
      "epoch": 0.7959183673469388,
      "grad_norm": 0.11583904176950455,
      "kl": 0.016116080805659294,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.0006,
      "reward": 0.1915496587753296,
      "reward_std": 0.12190195918083191,
      "rewards/<lambda>": 0.1915496587753296,
      "step": 78
    },
    {
      "completion_length": 160.0,
      "epoch": 0.8061224489795918,
      "grad_norm": 0.10830377042293549,
      "kl": 0.015441562049090862,
      "learning_rate": 7.900000000000001e-05,
      "loss": 0.0006,
      "reward": 0.15522490441799164,
      "reward_std": 0.08264317363500595,
      "rewards/<lambda>": 0.15522490441799164,
      "step": 79
    },
    {
      "completion_length": 160.0,
      "epoch": 0.8163265306122449,
      "grad_norm": 0.11148685216903687,
      "kl": 0.01857638917863369,
      "learning_rate": 8e-05,
      "loss": 0.0007,
      "reward": 0.21693138778209686,
      "reward_std": 0.132161483168602,
      "rewards/<lambda>": 0.21693138778209686,
      "step": 80
    },
    {
      "completion_length": 160.0,
      "epoch": 0.826530612244898,
      "grad_norm": 0.1557169258594513,
      "kl": 0.01583457738161087,
      "learning_rate": 8.1e-05,
      "loss": 0.0006,
      "reward": 0.1813575029373169,
      "reward_std": 0.12332402914762497,
      "rewards/<lambda>": 0.1813575029373169,
      "step": 81
    },
    {
      "completion_length": 160.0,
      "epoch": 0.8367346938775511,
      "grad_norm": 0.11910691857337952,
      "kl": 0.025130536407232285,
      "learning_rate": 8.2e-05,
      "loss": 0.001,
      "reward": 0.1874808669090271,
      "reward_std": 0.13184116780757904,
      "rewards/<lambda>": 0.1874808669090271,
      "step": 82
    },
    {
      "completion_length": 160.0,
      "epoch": 0.8469387755102041,
      "grad_norm": 0.09641101211309433,
      "kl": 0.020103760063648224,
      "learning_rate": 8.3e-05,
      "loss": 0.0008,
      "reward": 0.16875742375850677,
      "reward_std": 0.12786784768104553,
      "rewards/<lambda>": 0.16875742375850677,
      "step": 83
    },
    {
      "completion_length": 160.0,
      "epoch": 0.8571428571428571,
      "grad_norm": 0.11505434662103653,
      "kl": 0.03201855719089508,
      "learning_rate": 8.4e-05,
      "loss": 0.0013,
      "reward": 0.1941194385290146,
      "reward_std": 0.1352878361940384,
      "rewards/<lambda>": 0.1941194385290146,
      "step": 84
    },
    {
      "completion_length": 160.0,
      "epoch": 0.8673469387755102,
      "grad_norm": 0.20420552790164948,
      "kl": 0.025220511481165886,
      "learning_rate": 8.5e-05,
      "loss": 0.001,
      "reward": 0.1499064564704895,
      "reward_std": 0.10931651294231415,
      "rewards/<lambda>": 0.1499064564704895,
      "step": 85
    },
    {
      "completion_length": 160.0,
      "epoch": 0.8775510204081632,
      "grad_norm": 0.1504613608121872,
      "kl": 0.030149614438414574,
      "learning_rate": 8.6e-05,
      "loss": 0.0012,
      "reward": 0.2021590918302536,
      "reward_std": 0.11808289587497711,
      "rewards/<lambda>": 0.2021590918302536,
      "step": 86
    },
    {
      "completion_length": 160.0,
      "epoch": 0.8877551020408163,
      "grad_norm": 0.12947432696819305,
      "kl": 0.03943827003240585,
      "learning_rate": 8.7e-05,
      "loss": 0.0016,
      "reward": 0.16302035748958588,
      "reward_std": 0.12248598039150238,
      "rewards/<lambda>": 0.16302035748958588,
      "step": 87
    },
    {
      "completion_length": 160.0,
      "epoch": 0.8979591836734694,
      "grad_norm": 0.10003241151571274,
      "kl": 0.031025437638163567,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.0012,
      "reward": 0.17104387283325195,
      "reward_std": 0.11305706948041916,
      "rewards/<lambda>": 0.17104387283325195,
      "step": 88
    },
    {
      "completion_length": 160.0,
      "epoch": 0.9081632653061225,
      "grad_norm": 0.178684264421463,
      "kl": 0.0443422794342041,
      "learning_rate": 8.900000000000001e-05,
      "loss": 0.0018,
      "reward": 0.21491599082946777,
      "reward_std": 0.11920367181301117,
      "rewards/<lambda>": 0.21491599082946777,
      "step": 89
    },
    {
      "completion_length": 160.0,
      "epoch": 0.9183673469387755,
      "grad_norm": 0.4619559347629547,
      "kl": 0.14378872513771057,
      "learning_rate": 9e-05,
      "loss": 0.0058,
      "reward": 0.170355886220932,
      "reward_std": 0.11420422047376633,
      "rewards/<lambda>": 0.170355886220932,
      "step": 90
    },
    {
      "completion_length": 160.0,
      "epoch": 0.9285714285714286,
      "grad_norm": 0.18158575892448425,
      "kl": 0.05551178380846977,
      "learning_rate": 9.1e-05,
      "loss": 0.0022,
      "reward": 0.17519733309745789,
      "reward_std": 0.1182706207036972,
      "rewards/<lambda>": 0.17519733309745789,
      "step": 91
    },
    {
      "completion_length": 160.0,
      "epoch": 0.9387755102040817,
      "grad_norm": 0.1649360954761505,
      "kl": 0.0335373729467392,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.0013,
      "reward": 0.19423919916152954,
      "reward_std": 0.13439567387104034,
      "rewards/<lambda>": 0.19423919916152954,
      "step": 92
    },
    {
      "completion_length": 160.0,
      "epoch": 0.9489795918367347,
      "grad_norm": 0.10932810604572296,
      "kl": 0.035153284668922424,
      "learning_rate": 9.300000000000001e-05,
      "loss": 0.0014,
      "reward": 0.15611481666564941,
      "reward_std": 0.09644447267055511,
      "rewards/<lambda>": 0.15611481666564941,
      "step": 93
    },
    {
      "completion_length": 160.0,
      "epoch": 0.9591836734693877,
      "grad_norm": 0.099422886967659,
      "kl": 0.03238137811422348,
      "learning_rate": 9.4e-05,
      "loss": 0.0013,
      "reward": 0.1927059292793274,
      "reward_std": 0.11067558825016022,
      "rewards/<lambda>": 0.1927059292793274,
      "step": 94
    },
    {
      "completion_length": 160.0,
      "epoch": 0.9693877551020408,
      "grad_norm": 0.1119072213768959,
      "kl": 0.027582138776779175,
      "learning_rate": 9.5e-05,
      "loss": 0.0011,
      "reward": 0.2055554836988449,
      "reward_std": 0.14050546288490295,
      "rewards/<lambda>": 0.2055554836988449,
      "step": 95
    },
    {
      "completion_length": 160.0,
      "epoch": 0.9795918367346939,
      "grad_norm": 0.119843028485775,
      "kl": 0.029401419684290886,
      "learning_rate": 9.6e-05,
      "loss": 0.0012,
      "reward": 0.19861146807670593,
      "reward_std": 0.12701785564422607,
      "rewards/<lambda>": 0.19861146807670593,
      "step": 96
    },
    {
      "completion_length": 160.0,
      "epoch": 0.9897959183673469,
      "grad_norm": 0.10992871224880219,
      "kl": 0.03312207758426666,
      "learning_rate": 9.7e-05,
      "loss": 0.0013,
      "reward": 0.15577931702136993,
      "reward_std": 0.10662981122732162,
      "rewards/<lambda>": 0.15577931702136993,
      "step": 97
    },
    {
      "completion_length": 160.0,
      "epoch": 1.0,
      "grad_norm": 0.13580623269081116,
      "kl": 0.0318591445684433,
      "learning_rate": 9.8e-05,
      "loss": 0.0013,
      "reward": 0.256815642118454,
      "reward_std": 0.17193631827831268,
      "rewards/<lambda>": 0.256815642118454,
      "step": 98
    }
  ],
  "logging_steps": 1,
  "max_steps": 98,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}