{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8695652173913043,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 208.5885467529297,
      "epoch": 0.008695652173913044,
      "grad_norm": 2.329385757446289,
      "kl": 0.0,
      "learning_rate": 9.956521739130434e-07,
      "loss": 0.0,
      "reward": 1.7678645849227905,
      "reward_std": 0.3930448889732361,
      "rewards/correctness_reward_vllm": 0.7756770849227905,
      "rewards/length_reward": 0.9921875,
      "step": 1
    },
    {
      "completion_length": 199.15625,
      "epoch": 0.017391304347826087,
      "grad_norm": 3.4958019256591797,
      "kl": 0.0003414154052734375,
      "learning_rate": 9.91304347826087e-07,
      "loss": 0.0,
      "reward": 1.792708396911621,
      "reward_std": 0.37898510694503784,
      "rewards/correctness_reward_vllm": 0.7994792461395264,
      "rewards/length_reward": 0.9932291507720947,
      "step": 2
    },
    {
      "completion_length": 201.4166717529297,
      "epoch": 0.02608695652173913,
      "grad_norm": 3.472921848297119,
      "kl": 0.000431060791015625,
      "learning_rate": 9.869565217391304e-07,
      "loss": 0.0,
      "reward": 1.732135534286499,
      "reward_std": 0.41073521971702576,
      "rewards/correctness_reward_vllm": 0.7576562762260437,
      "rewards/length_reward": 0.9744791984558105,
      "step": 3
    },
    {
      "completion_length": 203.53646850585938,
      "epoch": 0.034782608695652174,
      "grad_norm": 3.1970794200897217,
      "kl": 0.0004558563232421875,
      "learning_rate": 9.826086956521739e-07,
      "loss": 0.0,
      "reward": 1.8510417938232422,
      "reward_std": 0.3472898006439209,
      "rewards/correctness_reward_vllm": 0.8645833730697632,
      "rewards/length_reward": 0.9864583015441895,
      "step": 4
    },
    {
      "completion_length": 198.92709350585938,
      "epoch": 0.043478260869565216,
      "grad_norm": 3.3482213020324707,
      "kl": 0.000408172607421875,
      "learning_rate": 9.782608695652173e-07,
      "loss": 0.0,
      "reward": 1.7761459350585938,
      "reward_std": 0.3146688938140869,
      "rewards/correctness_reward_vllm": 0.7995834350585938,
      "rewards/length_reward": 0.9765625,
      "step": 5
    },
    {
      "completion_length": 207.5,
      "epoch": 0.05217391304347826,
      "grad_norm": 4.089375972747803,
      "kl": 0.00046539306640625,
      "learning_rate": 9.73913043478261e-07,
      "loss": 0.0,
      "reward": 1.8823437690734863,
      "reward_std": 0.3251632750034332,
      "rewards/correctness_reward_vllm": 0.8891145586967468,
      "rewards/length_reward": 0.9932291507720947,
      "step": 6
    },
    {
      "completion_length": 203.44271850585938,
      "epoch": 0.06086956521739131,
      "grad_norm": 3.0994174480438232,
      "kl": 0.00042724609375,
      "learning_rate": 9.695652173913042e-07,
      "loss": 0.0,
      "reward": 1.8064062595367432,
      "reward_std": 0.3677879273891449,
      "rewards/correctness_reward_vllm": 0.8230729103088379,
      "rewards/length_reward": 0.9833333492279053,
      "step": 7
    },
    {
      "completion_length": 198.77084350585938,
      "epoch": 0.06956521739130435,
      "grad_norm": 2.4492053985595703,
      "kl": 0.00041961669921875,
      "learning_rate": 9.652173913043478e-07,
      "loss": 0.0,
      "reward": 1.8719271421432495,
      "reward_std": 0.3530654311180115,
      "rewards/correctness_reward_vllm": 0.8927604556083679,
      "rewards/length_reward": 0.9791666865348816,
      "step": 8
    },
    {
      "completion_length": 205.6510467529297,
      "epoch": 0.0782608695652174,
      "grad_norm": 2.360391855239868,
      "kl": 0.00041961669921875,
      "learning_rate": 9.608695652173912e-07,
      "loss": 0.0,
      "reward": 1.8904168605804443,
      "reward_std": 0.36921584606170654,
      "rewards/correctness_reward_vllm": 0.8904166221618652,
      "rewards/length_reward": 1.0,
      "step": 9
    },
    {
      "completion_length": 205.4791717529297,
      "epoch": 0.08695652173913043,
      "grad_norm": 3.7472403049468994,
      "kl": 0.000499725341796875,
      "learning_rate": 9.565217391304349e-07,
      "loss": 0.0,
      "reward": 1.8460416793823242,
      "reward_std": 0.3746611475944519,
      "rewards/correctness_reward_vllm": 0.8543750643730164,
      "rewards/length_reward": 0.9916666746139526,
      "step": 10
    },
    {
      "completion_length": 199.20834350585938,
      "epoch": 0.09565217391304348,
      "grad_norm": 3.843543767929077,
      "kl": 0.00051116943359375,
      "learning_rate": 9.521739130434783e-07,
      "loss": 0.0,
      "reward": 1.7471874952316284,
      "reward_std": 0.33215177059173584,
      "rewards/correctness_reward_vllm": 0.7471875548362732,
      "rewards/length_reward": 1.0,
      "step": 11
    },
    {
      "completion_length": 212.421875,
      "epoch": 0.10434782608695652,
      "grad_norm": 4.518510341644287,
      "kl": 0.00049591064453125,
      "learning_rate": 9.478260869565216e-07,
      "loss": 0.0,
      "reward": 1.9361979961395264,
      "reward_std": 0.37871116399765015,
      "rewards/correctness_reward_vllm": 0.9361978769302368,
      "rewards/length_reward": 1.0,
      "step": 12
    },
    {
      "completion_length": 196.06771850585938,
      "epoch": 0.11304347826086956,
      "grad_norm": 2.444908380508423,
      "kl": 0.000583648681640625,
      "learning_rate": 9.434782608695652e-07,
      "loss": 0.0,
      "reward": 1.8197916746139526,
      "reward_std": 0.3508337140083313,
      "rewards/correctness_reward_vllm": 0.8348957896232605,
      "rewards/length_reward": 0.9848958849906921,
      "step": 13
    },
    {
      "completion_length": 198.2916717529297,
      "epoch": 0.12173913043478261,
      "grad_norm": 3.8315980434417725,
      "kl": 0.000629425048828125,
      "learning_rate": 9.391304347826087e-07,
      "loss": 0.0,
      "reward": 1.7896875143051147,
      "reward_std": 0.3679579496383667,
      "rewards/correctness_reward_vllm": 0.8021876215934753,
      "rewards/length_reward": 0.9874999523162842,
      "step": 14
    },
    {
      "completion_length": 219.5572967529297,
      "epoch": 0.13043478260869565,
      "grad_norm": 3.2742035388946533,
      "kl": 0.000690460205078125,
      "learning_rate": 9.347826086956522e-07,
      "loss": 0.0,
      "reward": 1.8117709159851074,
      "reward_std": 0.3478308320045471,
      "rewards/correctness_reward_vllm": 0.8185417056083679,
      "rewards/length_reward": 0.9932291507720947,
      "step": 15
    },
    {
      "completion_length": 200.30209350585938,
      "epoch": 0.1391304347826087,
      "grad_norm": 3.956608772277832,
      "kl": 0.000659942626953125,
      "learning_rate": 9.304347826086955e-07,
      "loss": 0.0,
      "reward": 1.8940625190734863,
      "reward_std": 0.387278288602829,
      "rewards/correctness_reward_vllm": 0.9216668009757996,
      "rewards/length_reward": 0.9723958373069763,
      "step": 16
    },
    {
      "completion_length": 202.625,
      "epoch": 0.14782608695652175,
      "grad_norm": 4.350553512573242,
      "kl": 0.000652313232421875,
      "learning_rate": 9.260869565217391e-07,
      "loss": 0.0,
      "reward": 1.854322910308838,
      "reward_std": 0.3680115342140198,
      "rewards/correctness_reward_vllm": 0.8694270849227905,
      "rewards/length_reward": 0.9848958253860474,
      "step": 17
    },
    {
      "completion_length": 204.4479217529297,
      "epoch": 0.1565217391304348,
      "grad_norm": 2.888611078262329,
      "kl": 0.000804901123046875,
      "learning_rate": 9.217391304347826e-07,
      "loss": 0.0,
      "reward": 1.8798437118530273,
      "reward_std": 0.3778643012046814,
      "rewards/correctness_reward_vllm": 0.8881769180297852,
      "rewards/length_reward": 0.9916666746139526,
      "step": 18
    },
    {
      "completion_length": 202.02084350585938,
      "epoch": 0.16521739130434782,
      "grad_norm": 4.008359909057617,
      "kl": 0.000759124755859375,
      "learning_rate": 9.17391304347826e-07,
      "loss": 0.0,
      "reward": 1.7861980199813843,
      "reward_std": 0.3587394952774048,
      "rewards/correctness_reward_vllm": 0.7945312857627869,
      "rewards/length_reward": 0.9916666746139526,
      "step": 19
    },
    {
      "completion_length": 212.41146850585938,
      "epoch": 0.17391304347826086,
      "grad_norm": 3.486192226409912,
      "kl": 0.00079345703125,
      "learning_rate": 9.130434782608695e-07,
      "loss": 0.0,
      "reward": 1.8601564168930054,
      "reward_std": 0.38853877782821655,
      "rewards/correctness_reward_vllm": 0.8736979961395264,
      "rewards/length_reward": 0.9864583015441895,
      "step": 20
    },
    {
      "completion_length": 205.70834350585938,
      "epoch": 0.1826086956521739,
      "grad_norm": 3.196575403213501,
      "kl": 0.00087738037109375,
      "learning_rate": 9.08695652173913e-07,
      "loss": 0.0,
      "reward": 1.8731770515441895,
      "reward_std": 0.3991861343383789,
      "rewards/correctness_reward_vllm": 0.8773437738418579,
      "rewards/length_reward": 0.9958333373069763,
      "step": 21
    },
    {
      "completion_length": 205.36459350585938,
      "epoch": 0.19130434782608696,
      "grad_norm": 4.234310626983643,
      "kl": 0.0009002685546875,
      "learning_rate": 9.043478260869564e-07,
      "loss": 0.0,
      "reward": 1.701145887374878,
      "reward_std": 0.3736024796962738,
      "rewards/correctness_reward_vllm": 0.7079167366027832,
      "rewards/length_reward": 0.9932291507720947,
      "step": 22
    },
    {
      "completion_length": 220.7447967529297,
      "epoch": 0.2,
      "grad_norm": 6.220200061798096,
      "kl": 0.00084686279296875,
      "learning_rate": 9e-07,
      "loss": 0.0,
      "reward": 1.84416663646698,
      "reward_std": 0.3591594696044922,
      "rewards/correctness_reward_vllm": 0.8493751287460327,
      "rewards/length_reward": 0.9947916865348816,
      "step": 23
    },
    {
      "completion_length": 200.5885467529297,
      "epoch": 0.20869565217391303,
      "grad_norm": 2.584165573120117,
      "kl": 0.00090789794921875,
      "learning_rate": 8.956521739130435e-07,
      "loss": 0.0,
      "reward": 1.8740625381469727,
      "reward_std": 0.3568645417690277,
      "rewards/correctness_reward_vllm": 0.8948957324028015,
      "rewards/length_reward": 0.9791666865348816,
      "step": 24
    },
    {
      "completion_length": 210.89584350585938,
      "epoch": 0.21739130434782608,
      "grad_norm": 3.030820608139038,
      "kl": 0.00096893310546875,
      "learning_rate": 8.913043478260869e-07,
      "loss": 0.0,
      "reward": 1.8118228912353516,
      "reward_std": 0.3701898455619812,
      "rewards/correctness_reward_vllm": 0.8264062404632568,
      "rewards/length_reward": 0.9854166507720947,
      "step": 25
    },
    {
      "completion_length": 208.3854217529297,
      "epoch": 0.22608695652173913,
      "grad_norm": 3.262943983078003,
      "kl": 0.00106048583984375,
      "learning_rate": 8.869565217391303e-07,
      "loss": 0.0,
      "reward": 1.9187500476837158,
      "reward_std": 0.34354889392852783,
      "rewards/correctness_reward_vllm": 0.9229166507720947,
      "rewards/length_reward": 0.9958333373069763,
      "step": 26
    },
    {
      "completion_length": 193.640625,
      "epoch": 0.23478260869565218,
      "grad_norm": 3.750316619873047,
      "kl": 0.00118255615234375,
      "learning_rate": 8.826086956521739e-07,
      "loss": 0.0,
      "reward": 1.8126041889190674,
      "reward_std": 0.3690093457698822,
      "rewards/correctness_reward_vllm": 0.8292707800865173,
      "rewards/length_reward": 0.9833333492279053,
      "step": 27
    },
    {
      "completion_length": 210.25521850585938,
      "epoch": 0.24347826086956523,
      "grad_norm": 2.774629592895508,
      "kl": 0.00115966796875,
      "learning_rate": 8.782608695652174e-07,
      "loss": 0.0,
      "reward": 1.8429688215255737,
      "reward_std": 0.3622826039791107,
      "rewards/correctness_reward_vllm": 0.8507812023162842,
      "rewards/length_reward": 0.9921875,
      "step": 28
    },
    {
      "completion_length": 220.1354217529297,
      "epoch": 0.25217391304347825,
      "grad_norm": 3.555556297302246,
      "kl": 0.0013275146484375,
      "learning_rate": 8.739130434782607e-07,
      "loss": 0.0001,
      "reward": 1.793125033378601,
      "reward_std": 0.3758922517299652,
      "rewards/correctness_reward_vllm": 0.8051042556762695,
      "rewards/length_reward": 0.9880208373069763,
      "step": 29
    },
    {
      "completion_length": 213.359375,
      "epoch": 0.2608695652173913,
      "grad_norm": 10.03189754486084,
      "kl": 0.0013580322265625,
      "learning_rate": 8.695652173913043e-07,
      "loss": 0.0001,
      "reward": 1.8984894752502441,
      "reward_std": 0.37575191259384155,
      "rewards/correctness_reward_vllm": 0.9010938405990601,
      "rewards/length_reward": 0.9973958730697632,
      "step": 30
    },
    {
      "completion_length": 206.078125,
      "epoch": 0.26956521739130435,
      "grad_norm": 3.930840253829956,
      "kl": 0.00125885009765625,
      "learning_rate": 8.652173913043478e-07,
      "loss": 0.0001,
      "reward": 1.9381771087646484,
      "reward_std": 0.346474826335907,
      "rewards/correctness_reward_vllm": 0.9381771087646484,
      "rewards/length_reward": 1.0,
      "step": 31
    },
    {
      "completion_length": 205.73959350585938,
      "epoch": 0.2782608695652174,
      "grad_norm": 2.839338779449463,
      "kl": 0.00125885009765625,
      "learning_rate": 8.608695652173913e-07,
      "loss": 0.0001,
      "reward": 1.9146875143051147,
      "reward_std": 0.3288370370864868,
      "rewards/correctness_reward_vllm": 0.9256248474121094,
      "rewards/length_reward": 0.989062488079071,
      "step": 32
    },
    {
      "completion_length": 218.8697967529297,
      "epoch": 0.28695652173913044,
      "grad_norm": 2.71004056930542,
      "kl": 0.0011749267578125,
      "learning_rate": 8.565217391304348e-07,
      "loss": 0.0,
      "reward": 1.9505729675292969,
      "reward_std": 0.36752164363861084,
      "rewards/correctness_reward_vllm": 0.9641145467758179,
      "rewards/length_reward": 0.9864583015441895,
      "step": 33
    },
    {
      "completion_length": 223.515625,
      "epoch": 0.2956521739130435,
      "grad_norm": 3.4277288913726807,
      "kl": 0.001434326171875,
      "learning_rate": 8.521739130434782e-07,
      "loss": 0.0001,
      "reward": 1.887239694595337,
      "reward_std": 0.3722625970840454,
      "rewards/correctness_reward_vllm": 0.899218738079071,
      "rewards/length_reward": 0.9880208373069763,
      "step": 34
    },
    {
      "completion_length": 202.125,
      "epoch": 0.30434782608695654,
      "grad_norm": 4.426881790161133,
      "kl": 0.00148773193359375,
      "learning_rate": 8.478260869565217e-07,
      "loss": 0.0001,
      "reward": 1.7834895849227905,
      "reward_std": 0.3372436463832855,
      "rewards/correctness_reward_vllm": 0.7886979579925537,
      "rewards/length_reward": 0.9947916865348816,
      "step": 35
    },
    {
      "completion_length": 211.09375,
      "epoch": 0.3130434782608696,
      "grad_norm": 2.230402708053589,
      "kl": 0.0015106201171875,
      "learning_rate": 8.434782608695652e-07,
      "loss": 0.0001,
      "reward": 1.8795312643051147,
      "reward_std": 0.35857951641082764,
      "rewards/correctness_reward_vllm": 0.8930728435516357,
      "rewards/length_reward": 0.9864583015441895,
      "step": 36
    },
    {
      "completion_length": 208.34896850585938,
      "epoch": 0.3217391304347826,
      "grad_norm": 19.257694244384766,
      "kl": 0.0014190673828125,
      "learning_rate": 8.391304347826087e-07,
      "loss": 0.0001,
      "reward": 1.9402083158493042,
      "reward_std": 0.3405280113220215,
      "rewards/correctness_reward_vllm": 0.9402083158493042,
      "rewards/length_reward": 1.0,
      "step": 37
    },
    {
      "completion_length": 196.92709350585938,
      "epoch": 0.33043478260869563,
      "grad_norm": 3.1662447452545166,
      "kl": 0.001678466796875,
      "learning_rate": 8.347826086956521e-07,
      "loss": 0.0001,
      "reward": 1.8916146755218506,
      "reward_std": 0.35224398970603943,
      "rewards/correctness_reward_vllm": 0.8999478220939636,
      "rewards/length_reward": 0.9916666746139526,
      "step": 38
    },
    {
      "completion_length": 218.38021850585938,
      "epoch": 0.3391304347826087,
      "grad_norm": 2.1624081134796143,
      "kl": 0.0016021728515625,
      "learning_rate": 8.304347826086955e-07,
      "loss": 0.0001,
      "reward": 1.990781307220459,
      "reward_std": 0.34267401695251465,
      "rewards/correctness_reward_vllm": 1.0017187595367432,
      "rewards/length_reward": 0.989062488079071,
      "step": 39
    },
    {
      "completion_length": 202.94271850585938,
      "epoch": 0.34782608695652173,
      "grad_norm": 3.153355598449707,
      "kl": 0.0018310546875,
      "learning_rate": 8.260869565217391e-07,
      "loss": 0.0001,
      "reward": 1.8341145515441895,
      "reward_std": 0.3642037808895111,
      "rewards/correctness_reward_vllm": 0.8393229246139526,
      "rewards/length_reward": 0.9947916865348816,
      "step": 40
    },
    {
      "completion_length": 205.2760467529297,
      "epoch": 0.3565217391304348,
      "grad_norm": 3.370213747024536,
      "kl": 0.00193023681640625,
      "learning_rate": 8.217391304347826e-07,
      "loss": 0.0001,
      "reward": 1.8303645849227905,
      "reward_std": 0.3733619153499603,
      "rewards/correctness_reward_vllm": 0.8303646445274353,
      "rewards/length_reward": 1.0,
      "step": 41
    },
    {
      "completion_length": 206.6354217529297,
      "epoch": 0.3652173913043478,
      "grad_norm": 7.641461372375488,
      "kl": 0.00191497802734375,
      "learning_rate": 8.173913043478261e-07,
      "loss": 0.0001,
      "reward": 1.8568229675292969,
      "reward_std": 0.3796784281730652,
      "rewards/correctness_reward_vllm": 0.8677603602409363,
      "rewards/length_reward": 0.989062488079071,
      "step": 42
    },
    {
      "completion_length": 208.90625,
      "epoch": 0.3739130434782609,
      "grad_norm": 4.36552095413208,
      "kl": 0.00179290771484375,
      "learning_rate": 8.130434782608695e-07,
      "loss": 0.0001,
      "reward": 1.8441667556762695,
      "reward_std": 0.319492369890213,
      "rewards/correctness_reward_vllm": 0.84416663646698,
      "rewards/length_reward": 1.0,
      "step": 43
    },
    {
      "completion_length": 211.84896850585938,
      "epoch": 0.3826086956521739,
      "grad_norm": 3.3810644149780273,
      "kl": 0.001983642578125,
      "learning_rate": 8.08695652173913e-07,
      "loss": 0.0001,
      "reward": 1.8228124380111694,
      "reward_std": 0.39267587661743164,
      "rewards/correctness_reward_vllm": 0.8389584422111511,
      "rewards/length_reward": 0.9838541746139526,
      "step": 44
    },
    {
      "completion_length": 214.06771850585938,
      "epoch": 0.391304347826087,
      "grad_norm": 3.44265079498291,
      "kl": 0.0020751953125,
      "learning_rate": 8.043478260869565e-07,
      "loss": 0.0001,
      "reward": 1.7645833492279053,
      "reward_std": 0.40830251574516296,
      "rewards/correctness_reward_vllm": 0.7880208492279053,
      "rewards/length_reward": 0.9765625,
      "step": 45
    },
    {
      "completion_length": 213.77084350585938,
      "epoch": 0.4,
      "grad_norm": 3.346031427383423,
      "kl": 0.00194549560546875,
      "learning_rate": 8e-07,
      "loss": 0.0001,
      "reward": 1.8528125286102295,
      "reward_std": 0.39482760429382324,
      "rewards/correctness_reward_vllm": 0.8637499809265137,
      "rewards/length_reward": 0.989062488079071,
      "step": 46
    },
    {
      "completion_length": 209.72396850585938,
      "epoch": 0.40869565217391307,
      "grad_norm": 5.3741374015808105,
      "kl": 0.0023651123046875,
      "learning_rate": 7.956521739130434e-07,
      "loss": 0.0001,
      "reward": 1.8273438215255737,
      "reward_std": 0.3434736728668213,
      "rewards/correctness_reward_vllm": 0.8299479484558105,
      "rewards/length_reward": 0.9973958730697632,
      "step": 47
    },
    {
      "completion_length": 210.171875,
      "epoch": 0.41739130434782606,
      "grad_norm": 2.268425941467285,
      "kl": 0.0022125244140625,
      "learning_rate": 7.913043478260869e-07,
      "loss": 0.0001,
      "reward": 1.9866665601730347,
      "reward_std": 0.3515927195549011,
      "rewards/correctness_reward_vllm": 1.0028126239776611,
      "rewards/length_reward": 0.9838541746139526,
      "step": 48
    },
    {
      "completion_length": 214.421875,
      "epoch": 0.4260869565217391,
      "grad_norm": 3.0277607440948486,
      "kl": 0.0023193359375,
      "learning_rate": 7.869565217391305e-07,
      "loss": 0.0001,
      "reward": 1.8909896612167358,
      "reward_std": 0.3666800856590271,
      "rewards/correctness_reward_vllm": 0.8977603912353516,
      "rewards/length_reward": 0.9932291507720947,
      "step": 49
    },
    {
      "completion_length": 199.6979217529297,
      "epoch": 0.43478260869565216,
      "grad_norm": 3.3212649822235107,
      "kl": 0.002349853515625,
      "learning_rate": 7.826086956521739e-07,
      "loss": 0.0001,
      "reward": 1.8709373474121094,
      "reward_std": 0.381402850151062,
      "rewards/correctness_reward_vllm": 0.8792707920074463,
      "rewards/length_reward": 0.9916666746139526,
      "step": 50
    },
    {
      "completion_length": 210.41146850585938,
      "epoch": 0.4434782608695652,
      "grad_norm": 2.650980234146118,
      "kl": 0.002227783203125,
      "learning_rate": 7.782608695652173e-07,
      "loss": 0.0001,
      "reward": 1.9605729579925537,
      "reward_std": 0.3226872384548187,
      "rewards/correctness_reward_vllm": 0.9673436880111694,
      "rewards/length_reward": 0.9932291507720947,
      "step": 51
    },
    {
      "completion_length": 210.3072967529297,
      "epoch": 0.45217391304347826,
      "grad_norm": 2.7690789699554443,
      "kl": 0.002410888671875,
      "learning_rate": 7.739130434782608e-07,
      "loss": 0.0001,
      "reward": 1.937760591506958,
      "reward_std": 0.34728074073791504,
      "rewards/correctness_reward_vllm": 0.9513019919395447,
      "rewards/length_reward": 0.9864583015441895,
      "step": 52
    },
    {
      "completion_length": 202.38021850585938,
      "epoch": 0.4608695652173913,
      "grad_norm": 3.0100247859954834,
      "kl": 0.002288818359375,
      "learning_rate": 7.695652173913043e-07,
      "loss": 0.0001,
      "reward": 1.8619270324707031,
      "reward_std": 0.3619835376739502,
      "rewards/correctness_reward_vllm": 0.8619270324707031,
      "rewards/length_reward": 1.0,
      "step": 53
    },
    {
      "completion_length": 207.6666717529297,
      "epoch": 0.46956521739130436,
      "grad_norm": 4.956729888916016,
      "kl": 0.0023956298828125,
      "learning_rate": 7.652173913043478e-07,
      "loss": 0.0001,
      "reward": 1.8556770086288452,
      "reward_std": 0.3410601019859314,
      "rewards/correctness_reward_vllm": 0.8666146993637085,
      "rewards/length_reward": 0.989062488079071,
      "step": 54
    },
    {
      "completion_length": 210.65625,
      "epoch": 0.4782608695652174,
      "grad_norm": 6.263027191162109,
      "kl": 0.0027008056640625,
      "learning_rate": 7.608695652173913e-07,
      "loss": 0.0001,
      "reward": 1.796875,
      "reward_std": 0.3679881989955902,
      "rewards/correctness_reward_vllm": 0.8020833730697632,
      "rewards/length_reward": 0.9947916865348816,
      "step": 55
    },
    {
      "completion_length": 209.0416717529297,
      "epoch": 0.48695652173913045,
      "grad_norm": 3.7194344997406006,
      "kl": 0.002960205078125,
      "learning_rate": 7.565217391304347e-07,
      "loss": 0.0001,
      "reward": 1.902083396911621,
      "reward_std": 0.3579518496990204,
      "rewards/correctness_reward_vllm": 0.9020832777023315,
      "rewards/length_reward": 1.0,
      "step": 56
    },
    {
      "completion_length": 213.625,
      "epoch": 0.4956521739130435,
      "grad_norm": 7.1098246574401855,
      "kl": 0.002716064453125,
      "learning_rate": 7.521739130434782e-07,
      "loss": 0.0001,
      "reward": 1.8305728435516357,
      "reward_std": 0.3378227949142456,
      "rewards/correctness_reward_vllm": 0.8482812643051147,
      "rewards/length_reward": 0.9822916984558105,
      "step": 57
    },
    {
      "completion_length": 210.109375,
      "epoch": 0.5043478260869565,
      "grad_norm": 2.48675799369812,
      "kl": 0.0030517578125,
      "learning_rate": 7.478260869565217e-07,
      "loss": 0.0001,
      "reward": 1.8633334636688232,
      "reward_std": 0.3492564558982849,
      "rewards/correctness_reward_vllm": 0.8659374713897705,
      "rewards/length_reward": 0.9973958730697632,
      "step": 58
    },
    {
      "completion_length": 218.73959350585938,
      "epoch": 0.5130434782608696,
      "grad_norm": 3.753242254257202,
      "kl": 0.0026702880859375,
      "learning_rate": 7.434782608695653e-07,
      "loss": 0.0001,
      "reward": 1.9696353673934937,
      "reward_std": 0.33653122186660767,
      "rewards/correctness_reward_vllm": 0.9883853793144226,
      "rewards/length_reward": 0.981249988079071,
      "step": 59
    },
    {
      "completion_length": 221.8072967529297,
      "epoch": 0.5217391304347826,
      "grad_norm": 2.6025142669677734,
      "kl": 0.0027618408203125,
      "learning_rate": 7.391304347826086e-07,
      "loss": 0.0001,
      "reward": 1.8679168224334717,
      "reward_std": 0.3256112039089203,
      "rewards/correctness_reward_vllm": 0.8788542151451111,
      "rewards/length_reward": 0.989062488079071,
      "step": 60
    },
    {
      "completion_length": 210.16146850585938,
      "epoch": 0.5304347826086957,
      "grad_norm": 3.2735888957977295,
      "kl": 0.002960205078125,
      "learning_rate": 7.347826086956521e-07,
      "loss": 0.0001,
      "reward": 1.9982812404632568,
      "reward_std": 0.36957651376724243,
      "rewards/correctness_reward_vllm": 1.005052089691162,
      "rewards/length_reward": 0.9932291507720947,
      "step": 61
    },
    {
      "completion_length": 217.3229217529297,
      "epoch": 0.5391304347826087,
      "grad_norm": 5.706833362579346,
      "kl": 0.0030364990234375,
      "learning_rate": 7.304347826086957e-07,
      "loss": 0.0001,
      "reward": 1.949479103088379,
      "reward_std": 0.3874410390853882,
      "rewards/correctness_reward_vllm": 0.9619792699813843,
      "rewards/length_reward": 0.9875000715255737,
      "step": 62
    },
    {
      "completion_length": 230.703125,
      "epoch": 0.5478260869565217,
      "grad_norm": 2.584719657897949,
      "kl": 0.0027923583984375,
      "learning_rate": 7.260869565217391e-07,
      "loss": 0.0001,
      "reward": 1.8884896039962769,
      "reward_std": 0.3631989657878876,
      "rewards/correctness_reward_vllm": 0.905677080154419,
      "rewards/length_reward": 0.9828125238418579,
      "step": 63
    },
    {
      "completion_length": 206.375,
      "epoch": 0.5565217391304348,
      "grad_norm": 4.763845443725586,
      "kl": 0.0034332275390625,
      "learning_rate": 7.217391304347826e-07,
      "loss": 0.0001,
      "reward": 1.813020944595337,
      "reward_std": 0.36838170886039734,
      "rewards/correctness_reward_vllm": 0.8276041746139526,
      "rewards/length_reward": 0.9854166507720947,
      "step": 64
    },
    {
      "completion_length": 213.7291717529297,
      "epoch": 0.5652173913043478,
      "grad_norm": 2.8753910064697266,
      "kl": 0.003021240234375,
      "learning_rate": 7.17391304347826e-07,
      "loss": 0.0001,
      "reward": 1.838854193687439,
      "reward_std": 0.3463793992996216,
      "rewards/correctness_reward_vllm": 0.8456250429153442,
      "rewards/length_reward": 0.9932291507720947,
      "step": 65
    },
    {
      "completion_length": 221.125,
      "epoch": 0.5739130434782609,
      "grad_norm": 5.015041828155518,
      "kl": 0.0030670166015625,
      "learning_rate": 7.130434782608695e-07,
      "loss": 0.0001,
      "reward": 1.9818229675292969,
      "reward_std": 0.3662077784538269,
      "rewards/correctness_reward_vllm": 0.9844271540641785,
      "rewards/length_reward": 0.9973958730697632,
      "step": 66
    },
    {
      "completion_length": 214.05209350585938,
      "epoch": 0.5826086956521739,
      "grad_norm": 4.653159141540527,
      "kl": 0.0031585693359375,
      "learning_rate": 7.08695652173913e-07,
      "loss": 0.0001,
      "reward": 1.8708856105804443,
      "reward_std": 0.3716661334037781,
      "rewards/correctness_reward_vllm": 0.8859895467758179,
      "rewards/length_reward": 0.9848958849906921,
      "step": 67
    },
    {
      "completion_length": 202.1197967529297,
      "epoch": 0.591304347826087,
      "grad_norm": 19.68362808227539,
      "kl": 0.0040283203125,
      "learning_rate": 7.043478260869565e-07,
      "loss": 0.0002,
      "reward": 1.8791146278381348,
      "reward_std": 0.38598939776420593,
      "rewards/correctness_reward_vllm": 0.8832812309265137,
      "rewards/length_reward": 0.9958333373069763,
      "step": 68
    },
    {
      "completion_length": 219.765625,
      "epoch": 0.6,
      "grad_norm": 5.806125164031982,
      "kl": 0.0033721923828125,
      "learning_rate": 7e-07,
      "loss": 0.0001,
      "reward": 1.8771874904632568,
      "reward_std": 0.38062548637390137,
      "rewards/correctness_reward_vllm": 0.8964582681655884,
      "rewards/length_reward": 0.9807292222976685,
      "step": 69
    },
    {
      "completion_length": 218.140625,
      "epoch": 0.6086956521739131,
      "grad_norm": 4.798632621765137,
      "kl": 0.0035247802734375,
      "learning_rate": 6.956521739130434e-07,
      "loss": 0.0001,
      "reward": 1.8987500667572021,
      "reward_std": 0.3669140338897705,
      "rewards/correctness_reward_vllm": 0.9081250429153442,
      "rewards/length_reward": 0.9906250238418579,
      "step": 70
    },
    {
      "completion_length": 215.59896850585938,
      "epoch": 0.6173913043478261,
      "grad_norm": 2.9346864223480225,
      "kl": 0.0033111572265625,
      "learning_rate": 6.913043478260869e-07,
      "loss": 0.0001,
      "reward": 1.8859374523162842,
      "reward_std": 0.3378005623817444,
      "rewards/correctness_reward_vllm": 0.9036458730697632,
      "rewards/length_reward": 0.9822916984558105,
      "step": 71
    },
    {
      "completion_length": 215.5729217529297,
      "epoch": 0.6260869565217392,
      "grad_norm": 14.938803672790527,
      "kl": 0.003631591796875,
      "learning_rate": 6.869565217391305e-07,
      "loss": 0.0001,
      "reward": 1.9791147708892822,
      "reward_std": 0.3305058479309082,
      "rewards/correctness_reward_vllm": 0.98848956823349,
      "rewards/length_reward": 0.9906250238418579,
      "step": 72
    },
    {
      "completion_length": 222.48959350585938,
      "epoch": 0.6347826086956522,
      "grad_norm": 3.483288288116455,
      "kl": 0.0037841796875,
      "learning_rate": 6.826086956521738e-07,
      "loss": 0.0002,
      "reward": 1.9103645086288452,
      "reward_std": 0.3817846179008484,
      "rewards/correctness_reward_vllm": 0.9249479174613953,
      "rewards/length_reward": 0.9854166507720947,
      "step": 73
    },
    {
      "completion_length": 217.9947967529297,
      "epoch": 0.6434782608695652,
      "grad_norm": 4.190740585327148,
      "kl": 0.0034027099609375,
      "learning_rate": 6.782608695652173e-07,
      "loss": 0.0001,
      "reward": 2.024218797683716,
      "reward_std": 0.3620142936706543,
      "rewards/correctness_reward_vllm": 1.0294270515441895,
      "rewards/length_reward": 0.9947916865348816,
      "step": 74
    },
    {
      "completion_length": 216.03646850585938,
      "epoch": 0.6521739130434783,
      "grad_norm": 3.1468451023101807,
      "kl": 0.0037994384765625,
      "learning_rate": 6.739130434782609e-07,
      "loss": 0.0002,
      "reward": 1.9498958587646484,
      "reward_std": 0.343797892332077,
      "rewards/correctness_reward_vllm": 0.9566665887832642,
      "rewards/length_reward": 0.9932291507720947,
      "step": 75
    },
    {
      "completion_length": 205.484375,
      "epoch": 0.6608695652173913,
      "grad_norm": 7.804642200469971,
      "kl": 0.003814697265625,
      "learning_rate": 6.695652173913044e-07,
      "loss": 0.0002,
      "reward": 1.9136979579925537,
      "reward_std": 0.33026009798049927,
      "rewards/correctness_reward_vllm": 0.9178646802902222,
      "rewards/length_reward": 0.9958333373069763,
      "step": 76
    },
    {
      "completion_length": 209.2604217529297,
      "epoch": 0.6695652173913044,
      "grad_norm": 2.271778106689453,
      "kl": 0.00347900390625,
      "learning_rate": 6.652173913043478e-07,
      "loss": 0.0001,
      "reward": 2.0001044273376465,
      "reward_std": 0.3248264789581299,
      "rewards/correctness_reward_vllm": 1.0084375143051147,
      "rewards/length_reward": 0.9916666746139526,
      "step": 77
    },
    {
      "completion_length": 215.70834350585938,
      "epoch": 0.6782608695652174,
      "grad_norm": 3.02213191986084,
      "kl": 0.00341796875,
      "learning_rate": 6.608695652173912e-07,
      "loss": 0.0001,
      "reward": 1.9772396087646484,
      "reward_std": 0.3613937795162201,
      "rewards/correctness_reward_vllm": 0.977239727973938,
      "rewards/length_reward": 1.0,
      "step": 78
    },
    {
      "completion_length": 212.40625,
      "epoch": 0.6869565217391305,
      "grad_norm": 6.0936055183410645,
      "kl": 0.003753662109375,
      "learning_rate": 6.565217391304348e-07,
      "loss": 0.0001,
      "reward": 1.9798438549041748,
      "reward_std": 0.3753187656402588,
      "rewards/correctness_reward_vllm": 0.9892187118530273,
      "rewards/length_reward": 0.9906250238418579,
      "step": 79
    },
    {
      "completion_length": 221.2291717529297,
      "epoch": 0.6956521739130435,
      "grad_norm": 17.235055923461914,
      "kl": 0.0036163330078125,
      "learning_rate": 6.521739130434782e-07,
      "loss": 0.0001,
      "reward": 1.9942710399627686,
      "reward_std": 0.3695635199546814,
      "rewards/correctness_reward_vllm": 1.0078125,
      "rewards/length_reward": 0.9864583015441895,
      "step": 80
    },
    {
      "completion_length": 221.046875,
      "epoch": 0.7043478260869566,
      "grad_norm": 2.6756632328033447,
      "kl": 0.003875732421875,
      "learning_rate": 6.478260869565217e-07,
      "loss": 0.0002,
      "reward": 2.012760639190674,
      "reward_std": 0.3683191239833832,
      "rewards/correctness_reward_vllm": 1.015364646911621,
      "rewards/length_reward": 0.9973958730697632,
      "step": 81
    },
    {
      "completion_length": 209.78646850585938,
      "epoch": 0.7130434782608696,
      "grad_norm": 3.258723020553589,
      "kl": 0.003692626953125,
      "learning_rate": 6.434782608695652e-07,
      "loss": 0.0001,
      "reward": 1.91057288646698,
      "reward_std": 0.3535638451576233,
      "rewards/correctness_reward_vllm": 0.91734379529953,
      "rewards/length_reward": 0.9932291507720947,
      "step": 82
    },
    {
      "completion_length": 222.11459350585938,
      "epoch": 0.7217391304347827,
      "grad_norm": 3.031001329421997,
      "kl": 0.00408935546875,
      "learning_rate": 6.391304347826086e-07,
      "loss": 0.0002,
      "reward": 1.874010443687439,
      "reward_std": 0.34764736890792847,
      "rewards/correctness_reward_vllm": 0.8859896063804626,
      "rewards/length_reward": 0.9880208373069763,
      "step": 83
    },
    {
      "completion_length": 214.171875,
      "epoch": 0.7304347826086957,
      "grad_norm": 3.0759449005126953,
      "kl": 0.004058837890625,
      "learning_rate": 6.347826086956521e-07,
      "loss": 0.0002,
      "reward": 1.9028127193450928,
      "reward_std": 0.34005099534988403,
      "rewards/correctness_reward_vllm": 0.909583330154419,
      "rewards/length_reward": 0.9932291507720947,
      "step": 84
    },
    {
      "completion_length": 202.20834350585938,
      "epoch": 0.7391304347826086,
      "grad_norm": 2.5407440662384033,
      "kl": 0.00421142578125,
      "learning_rate": 6.304347826086957e-07,
      "loss": 0.0002,
      "reward": 1.8680729866027832,
      "reward_std": 0.3732559084892273,
      "rewards/correctness_reward_vllm": 0.8831771612167358,
      "rewards/length_reward": 0.9848958849906921,
      "step": 85
    },
    {
      "completion_length": 219.9635467529297,
      "epoch": 0.7478260869565218,
      "grad_norm": 3.382174015045166,
      "kl": 0.00457763671875,
      "learning_rate": 6.260869565217392e-07,
      "loss": 0.0002,
      "reward": 1.9778646230697632,
      "reward_std": 0.3570324778556824,
      "rewards/correctness_reward_vllm": 0.9830728769302368,
      "rewards/length_reward": 0.9947916865348816,
      "step": 86
    },
    {
      "completion_length": 208.31771850585938,
      "epoch": 0.7565217391304347,
      "grad_norm": 4.980509281158447,
      "kl": 0.0042724609375,
      "learning_rate": 6.217391304347825e-07,
      "loss": 0.0002,
      "reward": 1.9402084350585938,
      "reward_std": 0.3678310811519623,
      "rewards/correctness_reward_vllm": 0.9527082443237305,
      "rewards/length_reward": 0.9874999523162842,
      "step": 87
    },
    {
      "completion_length": 218.546875,
      "epoch": 0.7652173913043478,
      "grad_norm": 6.500480651855469,
      "kl": 0.004241943359375,
      "learning_rate": 6.17391304347826e-07,
      "loss": 0.0002,
      "reward": 1.88979172706604,
      "reward_std": 0.36772656440734863,
      "rewards/correctness_reward_vllm": 0.9017707705497742,
      "rewards/length_reward": 0.9880208373069763,
      "step": 88
    },
    {
      "completion_length": 215.0416717529297,
      "epoch": 0.7739130434782608,
      "grad_norm": 2.6303582191467285,
      "kl": 0.004150390625,
      "learning_rate": 6.130434782608696e-07,
      "loss": 0.0002,
      "reward": 1.9179166555404663,
      "reward_std": 0.39331650733947754,
      "rewards/correctness_reward_vllm": 0.9246875643730164,
      "rewards/length_reward": 0.9932291507720947,
      "step": 89
    },
    {
      "completion_length": 210.0729217529297,
      "epoch": 0.782608695652174,
      "grad_norm": 3.609468460083008,
      "kl": 0.00439453125,
      "learning_rate": 6.08695652173913e-07,
      "loss": 0.0002,
      "reward": 1.836041808128357,
      "reward_std": 0.32552263140678406,
      "rewards/correctness_reward_vllm": 0.838645875453949,
      "rewards/length_reward": 0.9973958730697632,
      "step": 90
    },
    {
      "completion_length": 209.734375,
      "epoch": 0.7913043478260869,
      "grad_norm": 6.067314624786377,
      "kl": 0.004547119140625,
      "learning_rate": 6.043478260869564e-07,
      "loss": 0.0002,
      "reward": 1.9498958587646484,
      "reward_std": 0.34004995226860046,
      "rewards/correctness_reward_vllm": 0.9540625810623169,
      "rewards/length_reward": 0.9958333373069763,
      "step": 91
    },
    {
      "completion_length": 210.1510467529297,
      "epoch": 0.8,
      "grad_norm": 1.9421336650848389,
      "kl": 0.00457763671875,
      "learning_rate": 6e-07,
      "loss": 0.0002,
      "reward": 1.9082813262939453,
      "reward_std": 0.3142109513282776,
      "rewards/correctness_reward_vllm": 0.92598956823349,
      "rewards/length_reward": 0.9822916388511658,
      "step": 92
    },
    {
      "completion_length": 213.8229217529297,
      "epoch": 0.808695652173913,
      "grad_norm": 5.914642810821533,
      "kl": 0.004241943359375,
      "learning_rate": 5.956521739130435e-07,
      "loss": 0.0002,
      "reward": 1.8783854246139526,
      "reward_std": 0.3885143995285034,
      "rewards/correctness_reward_vllm": 0.88776034116745,
      "rewards/length_reward": 0.9906250238418579,
      "step": 93
    },
    {
      "completion_length": 215.73959350585938,
      "epoch": 0.8173913043478261,
      "grad_norm": 4.0509867668151855,
      "kl": 0.004119873046875,
      "learning_rate": 5.913043478260869e-07,
      "loss": 0.0002,
      "reward": 1.8941667079925537,
      "reward_std": 0.33366817235946655,
      "rewards/correctness_reward_vllm": 0.8941666483879089,
      "rewards/length_reward": 1.0,
      "step": 94
    },
    {
      "completion_length": 212.50521850585938,
      "epoch": 0.8260869565217391,
      "grad_norm": 4.238688945770264,
      "kl": 0.004608154296875,
      "learning_rate": 5.869565217391305e-07,
      "loss": 0.0002,
      "reward": 1.847812533378601,
      "reward_std": 0.3324012756347656,
      "rewards/correctness_reward_vllm": 0.869687557220459,
      "rewards/length_reward": 0.9781250357627869,
      "step": 95
    },
    {
      "completion_length": 215.03125,
      "epoch": 0.8347826086956521,
      "grad_norm": 2.5241854190826416,
      "kl": 0.004180908203125,
      "learning_rate": 5.826086956521739e-07,
      "loss": 0.0002,
      "reward": 1.8808854818344116,
      "reward_std": 0.3407609462738037,
      "rewards/correctness_reward_vllm": 0.8834896087646484,
      "rewards/length_reward": 0.9973958730697632,
      "step": 96
    },
    {
      "completion_length": 212.80209350585938,
      "epoch": 0.8434782608695652,
      "grad_norm": 2.265584707260132,
      "kl": 0.00408935546875,
      "learning_rate": 5.782608695652173e-07,
      "loss": 0.0002,
      "reward": 1.93052077293396,
      "reward_std": 0.36047881841659546,
      "rewards/correctness_reward_vllm": 0.9372917413711548,
      "rewards/length_reward": 0.9932291507720947,
      "step": 97
    },
    {
      "completion_length": 213.67709350585938,
      "epoch": 0.8521739130434782,
      "grad_norm": 4.020750522613525,
      "kl": 0.004547119140625,
      "learning_rate": 5.739130434782609e-07,
      "loss": 0.0002,
      "reward": 1.8923959732055664,
      "reward_std": 0.3393206000328064,
      "rewards/correctness_reward_vllm": 0.8950001001358032,
      "rewards/length_reward": 0.9973958730697632,
      "step": 98
    },
    {
      "completion_length": 207.59896850585938,
      "epoch": 0.8608695652173913,
      "grad_norm": 14.120591163635254,
      "kl": 0.004302978515625,
      "learning_rate": 5.695652173913044e-07,
      "loss": 0.0002,
      "reward": 2.019479274749756,
      "reward_std": 0.34421300888061523,
      "rewards/correctness_reward_vllm": 1.0236458778381348,
      "rewards/length_reward": 0.9958333373069763,
      "step": 99
    },
    {
      "completion_length": 210.15625,
      "epoch": 0.8695652173913043,
      "grad_norm": 2.4444007873535156,
      "kl": 0.004730224609375,
      "learning_rate": 5.652173913043477e-07,
      "loss": 0.0002,
      "reward": 1.8682812452316284,
      "reward_std": 0.3285192549228668,
      "rewards/correctness_reward_vllm": 0.8734895586967468,
      "rewards/length_reward": 0.9947916865348816,
      "step": 100
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 230,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}