{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13333333333333333,
  "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": 113.171875,
      "epoch": 0.0013333333333333333,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.998766400914329e-07,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/emotion_reward_func": 0.0,
      "rewards/format_reward_func": 0.0,
      "step": 1
    },
    {
      "completion_length": 100.609375,
      "epoch": 0.0026666666666666666,
      "grad_norm": 7.206315517425537,
      "kl": 0.0,
      "learning_rate": 4.995066821070679e-07,
      "loss": 0.0,
      "reward": 0.046875,
      "reward_std": 0.1875,
      "rewards/emotion_reward_func": 0.015625,
      "rewards/format_reward_func": 0.03125,
      "step": 2
    },
    {
      "completion_length": 130.65625,
      "epoch": 0.004,
      "grad_norm": 7.190981864929199,
      "kl": 0.0008925930160330608,
      "learning_rate": 4.9889049115077e-07,
      "loss": 0.0,
      "reward": 0.0625,
      "reward_std": 0.25,
      "rewards/emotion_reward_func": 0.015625,
      "rewards/format_reward_func": 0.046875,
      "step": 3
    },
    {
      "completion_length": 112.484375,
      "epoch": 0.005333333333333333,
      "grad_norm": 4.745754718780518,
      "kl": 0.0009372199856443331,
      "learning_rate": 4.980286753286194e-07,
      "loss": 0.0,
      "reward": 0.046875,
      "reward_std": 0.1875,
      "rewards/emotion_reward_func": 0.015625,
      "rewards/format_reward_func": 0.03125,
      "step": 4
    },
    {
      "completion_length": 100.359375,
      "epoch": 0.006666666666666667,
      "grad_norm": 6.957683086395264,
      "kl": 0.0009052860696101561,
      "learning_rate": 4.969220851487844e-07,
      "loss": 0.0,
      "reward": 0.078125,
      "reward_std": 0.3125,
      "rewards/emotion_reward_func": 0.03125,
      "rewards/format_reward_func": 0.046875,
      "step": 5
    },
    {
      "completion_length": 109.5625,
      "epoch": 0.008,
      "grad_norm": 8.517982482910156,
      "kl": 0.0011545967281563208,
      "learning_rate": 4.955718126821722e-07,
      "loss": 0.0,
      "reward": 0.140625,
      "reward_std": 0.34228479862213135,
      "rewards/emotion_reward_func": 0.03125,
      "rewards/format_reward_func": 0.109375,
      "step": 6
    },
    {
      "completion_length": 117.484375,
      "epoch": 0.009333333333333334,
      "grad_norm": 2.9639530181884766,
      "kl": 0.001261903322301805,
      "learning_rate": 4.939791904846868e-07,
      "loss": 0.0,
      "reward": 0.03125,
      "reward_std": 0.125,
      "rewards/emotion_reward_func": 0.015625,
      "rewards/format_reward_func": 0.015625,
      "step": 7
    },
    {
      "completion_length": 118.234375,
      "epoch": 0.010666666666666666,
      "grad_norm": 8.49864387512207,
      "kl": 0.002180565701564774,
      "learning_rate": 4.921457902821578e-07,
      "loss": 0.0,
      "reward": 0.140625,
      "reward_std": 0.4436737596988678,
      "rewards/emotion_reward_func": 0.046875,
      "rewards/format_reward_func": 0.09375,
      "step": 8
    },
    {
      "completion_length": 106.546875,
      "epoch": 0.012,
      "grad_norm": 7.236983299255371,
      "kl": 0.0018676594190765172,
      "learning_rate": 4.900734214192358e-07,
      "loss": 0.0,
      "reward": 0.109375,
      "reward_std": 0.3186737596988678,
      "rewards/emotion_reward_func": 0.03125,
      "rewards/format_reward_func": 0.078125,
      "step": 9
    },
    {
      "completion_length": 94.640625,
      "epoch": 0.013333333333333334,
      "grad_norm": 6.612936973571777,
      "kl": 0.00287746504181996,
      "learning_rate": 4.877641290737883e-07,
      "loss": 0.0,
      "reward": 0.15625,
      "reward_std": 0.38375620543956757,
      "rewards/emotion_reward_func": 0.03125,
      "rewards/format_reward_func": 0.125,
      "step": 10
    },
    {
      "completion_length": 78.453125,
      "epoch": 0.014666666666666666,
      "grad_norm": 6.714486598968506,
      "kl": 0.0037596136680804193,
      "learning_rate": 4.852201922385564e-07,
      "loss": 0.0,
      "reward": 0.15625,
      "reward_std": 0.34297704696655273,
      "rewards/emotion_reward_func": 0.03125,
      "rewards/format_reward_func": 0.125,
      "step": 11
    },
    {
      "completion_length": 113.765625,
      "epoch": 0.016,
      "grad_norm": 6.222474098205566,
      "kl": 0.005189417512156069,
      "learning_rate": 4.824441214720628e-07,
      "loss": 0.0,
      "reward": 0.328125,
      "reward_std": 0.6560364216566086,
      "rewards/emotion_reward_func": 0.109375,
      "rewards/format_reward_func": 0.21875,
      "step": 12
    },
    {
      "completion_length": 93.890625,
      "epoch": 0.017333333333333333,
      "grad_norm": 7.199591636657715,
      "kl": 0.011019598576240242,
      "learning_rate": 4.794386564209952e-07,
      "loss": 0.0,
      "reward": 0.359375,
      "reward_std": 0.647876650094986,
      "rewards/emotion_reward_func": 0.125,
      "rewards/format_reward_func": 0.234375,
      "step": 13
    },
    {
      "completion_length": 93.6875,
      "epoch": 0.018666666666666668,
      "grad_norm": 7.459893226623535,
      "kl": 0.012794358422979712,
      "learning_rate": 4.762067631165049e-07,
      "loss": 0.0,
      "reward": 0.28125,
      "reward_std": 0.4561576098203659,
      "rewards/emotion_reward_func": 0.015625,
      "rewards/format_reward_func": 0.265625,
      "step": 14
    },
    {
      "completion_length": 114.03125,
      "epoch": 0.02,
      "grad_norm": 7.204787731170654,
      "kl": 0.01207199739292264,
      "learning_rate": 4.7275163104709194e-07,
      "loss": 0.0,
      "reward": 0.421875,
      "reward_std": 0.6076867878437042,
      "rewards/emotion_reward_func": 0.0625,
      "rewards/format_reward_func": 0.359375,
      "step": 15
    },
    {
      "completion_length": 90.1875,
      "epoch": 0.021333333333333333,
      "grad_norm": 6.9398369789123535,
      "kl": 0.012930819648317993,
      "learning_rate": 4.6907667001096585e-07,
      "loss": 0.0,
      "reward": 0.296875,
      "reward_std": 0.6791985481977463,
      "rewards/emotion_reward_func": 0.125,
      "rewards/format_reward_func": 0.171875,
      "step": 16
    },
    {
      "completion_length": 100.265625,
      "epoch": 0.02266666666666667,
      "grad_norm": 7.01741361618042,
      "kl": 0.014807499013841152,
      "learning_rate": 4.6518550675098587e-07,
      "loss": 0.0,
      "reward": 0.609375,
      "reward_std": 0.7960269749164581,
      "rewards/emotion_reward_func": 0.1875,
      "rewards/format_reward_func": 0.421875,
      "step": 17
    },
    {
      "completion_length": 101.59375,
      "epoch": 0.024,
      "grad_norm": 6.980762004852295,
      "kl": 0.02019192511215806,
      "learning_rate": 4.6108198137550377e-07,
      "loss": 0.0,
      "reward": 0.53125,
      "reward_std": 0.6885540634393692,
      "rewards/emotion_reward_func": 0.125,
      "rewards/format_reward_func": 0.40625,
      "step": 18
    },
    {
      "completion_length": 93.859375,
      "epoch": 0.025333333333333333,
      "grad_norm": 8.390938758850098,
      "kl": 0.03694334626197815,
      "learning_rate": 4.567701435686404e-07,
      "loss": 0.0,
      "reward": 0.65625,
      "reward_std": 0.651764303445816,
      "rewards/emotion_reward_func": 0.125,
      "rewards/format_reward_func": 0.53125,
      "step": 19
    },
    {
      "completion_length": 85.546875,
      "epoch": 0.02666666666666667,
      "grad_norm": 8.39484691619873,
      "kl": 0.03380461875349283,
      "learning_rate": 4.5225424859373684e-07,
      "loss": 0.0,
      "reward": 0.765625,
      "reward_std": 0.7304560542106628,
      "rewards/emotion_reward_func": 0.203125,
      "rewards/format_reward_func": 0.5625,
      "step": 20
    },
    {
      "completion_length": 91.3125,
      "epoch": 0.028,
      "grad_norm": 6.440164089202881,
      "kl": 0.04492605570703745,
      "learning_rate": 4.475387530939226e-07,
      "loss": 0.0,
      "reward": 0.765625,
      "reward_std": 0.5731314420700073,
      "rewards/emotion_reward_func": 0.078125,
      "rewards/format_reward_func": 0.6875,
      "step": 21
    },
    {
      "completion_length": 91.0625,
      "epoch": 0.029333333333333333,
      "grad_norm": 6.099334716796875,
      "kl": 0.040256964042782784,
      "learning_rate": 4.426283106939473e-07,
      "loss": 0.0,
      "reward": 1.1875,
      "reward_std": 0.6744011342525482,
      "rewards/emotion_reward_func": 0.390625,
      "rewards/format_reward_func": 0.796875,
      "step": 22
    },
    {
      "completion_length": 79.328125,
      "epoch": 0.030666666666666665,
      "grad_norm": 7.1284871101379395,
      "kl": 0.04640346672385931,
      "learning_rate": 4.375277674076149e-07,
      "loss": 0.0,
      "reward": 1.21875,
      "reward_std": 0.7463032901287079,
      "rewards/emotion_reward_func": 0.4375,
      "rewards/format_reward_func": 0.78125,
      "step": 23
    },
    {
      "completion_length": 71.84375,
      "epoch": 0.032,
      "grad_norm": 6.066468715667725,
      "kl": 0.07137730903923512,
      "learning_rate": 4.3224215685535287e-07,
      "loss": 0.0001,
      "reward": 1.328125,
      "reward_std": 0.8113406747579575,
      "rewards/emotion_reward_func": 0.546875,
      "rewards/format_reward_func": 0.78125,
      "step": 24
    },
    {
      "completion_length": 101.0625,
      "epoch": 0.03333333333333333,
      "grad_norm": 5.047848224639893,
      "kl": 0.0665823919698596,
      "learning_rate": 4.2677669529663686e-07,
      "loss": 0.0001,
      "reward": 0.828125,
      "reward_std": 0.5247472077608109,
      "rewards/emotion_reward_func": 0.078125,
      "rewards/format_reward_func": 0.75,
      "step": 25
    },
    {
      "completion_length": 68.1875,
      "epoch": 0.034666666666666665,
      "grad_norm": 6.7862958908081055,
      "kl": 0.07357331551611423,
      "learning_rate": 4.2113677648217216e-07,
      "loss": 0.0001,
      "reward": 1.515625,
      "reward_std": 0.7178780436515808,
      "rewards/emotion_reward_func": 0.671875,
      "rewards/format_reward_func": 0.84375,
      "step": 26
    },
    {
      "completion_length": 73.5625,
      "epoch": 0.036,
      "grad_norm": 6.041502475738525,
      "kl": 0.0839837146922946,
      "learning_rate": 4.1532796633091294e-07,
      "loss": 0.0001,
      "reward": 1.0,
      "reward_std": 0.5787727609276772,
      "rewards/emotion_reward_func": 0.1875,
      "rewards/format_reward_func": 0.8125,
      "step": 27
    },
    {
      "completion_length": 75.515625,
      "epoch": 0.037333333333333336,
      "grad_norm": 5.880768299102783,
      "kl": 0.07887133583426476,
      "learning_rate": 4.0935599743717244e-07,
      "loss": 0.0001,
      "reward": 1.265625,
      "reward_std": 0.6387931928038597,
      "rewards/emotion_reward_func": 0.390625,
      "rewards/format_reward_func": 0.875,
      "step": 28
    },
    {
      "completion_length": 84.65625,
      "epoch": 0.03866666666666667,
      "grad_norm": 4.456689357757568,
      "kl": 0.05541729833930731,
      "learning_rate": 4.0322676341324414e-07,
      "loss": 0.0001,
      "reward": 1.546875,
      "reward_std": 0.6021395623683929,
      "rewards/emotion_reward_func": 0.6875,
      "rewards/format_reward_func": 0.859375,
      "step": 29
    },
    {
      "completion_length": 72.03125,
      "epoch": 0.04,
      "grad_norm": 6.281215667724609,
      "kl": 0.07642886973917484,
      "learning_rate": 3.9694631307311825e-07,
      "loss": 0.0001,
      "reward": 1.421875,
      "reward_std": 0.6625982969999313,
      "rewards/emotion_reward_func": 0.515625,
      "rewards/format_reward_func": 0.90625,
      "step": 30
    },
    {
      "completion_length": 64.96875,
      "epoch": 0.04133333333333333,
      "grad_norm": 6.267475128173828,
      "kl": 0.07545926049351692,
      "learning_rate": 3.9052084446303265e-07,
      "loss": 0.0001,
      "reward": 1.28125,
      "reward_std": 0.5209204778075218,
      "rewards/emotion_reward_func": 0.34375,
      "rewards/format_reward_func": 0.9375,
      "step": 31
    },
    {
      "completion_length": 74.28125,
      "epoch": 0.042666666666666665,
      "grad_norm": 6.10364294052124,
      "kl": 0.08546704892069101,
      "learning_rate": 3.839566987447491e-07,
      "loss": 0.0001,
      "reward": 1.59375,
      "reward_std": 0.7168828397989273,
      "rewards/emotion_reward_func": 0.71875,
      "rewards/format_reward_func": 0.875,
      "step": 32
    },
    {
      "completion_length": 70.03125,
      "epoch": 0.044,
      "grad_norm": 4.039772033691406,
      "kl": 0.06002845522016287,
      "learning_rate": 3.7726035393759283e-07,
      "loss": 0.0001,
      "reward": 1.3125,
      "reward_std": 0.2808031141757965,
      "rewards/emotion_reward_func": 0.390625,
      "rewards/format_reward_func": 0.921875,
      "step": 33
    },
    {
      "completion_length": 83.109375,
      "epoch": 0.04533333333333334,
      "grad_norm": 6.683216094970703,
      "kl": 0.0706396009773016,
      "learning_rate": 3.704384185254288e-07,
      "loss": 0.0001,
      "reward": 1.421875,
      "reward_std": 0.7211004346609116,
      "rewards/emotion_reward_func": 0.578125,
      "rewards/format_reward_func": 0.84375,
      "step": 34
    },
    {
      "completion_length": 72.765625,
      "epoch": 0.04666666666666667,
      "grad_norm": 6.402747631072998,
      "kl": 0.10811681114137173,
      "learning_rate": 3.634976249348867e-07,
      "loss": 0.0001,
      "reward": 1.28125,
      "reward_std": 0.5904398858547211,
      "rewards/emotion_reward_func": 0.375,
      "rewards/format_reward_func": 0.90625,
      "step": 35
    },
    {
      "completion_length": 78.734375,
      "epoch": 0.048,
      "grad_norm": 5.202386856079102,
      "kl": 0.07850308250635862,
      "learning_rate": 3.5644482289126813e-07,
      "loss": 0.0001,
      "reward": 1.09375,
      "reward_std": 0.5113069340586662,
      "rewards/emotion_reward_func": 0.203125,
      "rewards/format_reward_func": 0.890625,
      "step": 36
    },
    {
      "completion_length": 68.953125,
      "epoch": 0.04933333333333333,
      "grad_norm": 7.1071085929870605,
      "kl": 0.08383779786527157,
      "learning_rate": 3.492869726586951e-07,
      "loss": 0.0001,
      "reward": 1.1875,
      "reward_std": 0.4691474586725235,
      "rewards/emotion_reward_func": 0.21875,
      "rewards/format_reward_func": 0.96875,
      "step": 37
    },
    {
      "completion_length": 65.734375,
      "epoch": 0.050666666666666665,
      "grad_norm": 6.272955417633057,
      "kl": 0.06441066134721041,
      "learning_rate": 3.4203113817116953e-07,
      "loss": 0.0001,
      "reward": 1.75,
      "reward_std": 0.41095855832099915,
      "rewards/emotion_reward_func": 0.765625,
      "rewards/format_reward_func": 0.984375,
      "step": 38
    },
    {
      "completion_length": 69.9375,
      "epoch": 0.052,
      "grad_norm": 3.7793548107147217,
      "kl": 0.06628133170306683,
      "learning_rate": 3.346844800613229e-07,
      "loss": 0.0001,
      "reward": 1.078125,
      "reward_std": 0.21347813308238983,
      "rewards/emotion_reward_func": 0.109375,
      "rewards/format_reward_func": 0.96875,
      "step": 39
    },
    {
      "completion_length": 64.34375,
      "epoch": 0.05333333333333334,
      "grad_norm": 6.500398635864258,
      "kl": 0.06995576526969671,
      "learning_rate": 3.272542485937368e-07,
      "loss": 0.0001,
      "reward": 1.546875,
      "reward_std": 0.47020626068115234,
      "rewards/emotion_reward_func": 0.5625,
      "rewards/format_reward_func": 0.984375,
      "step": 40
    },
    {
      "completion_length": 73.375,
      "epoch": 0.05466666666666667,
      "grad_norm": 4.637302875518799,
      "kl": 0.06445631105452776,
      "learning_rate": 3.1974777650980734e-07,
      "loss": 0.0001,
      "reward": 1.578125,
      "reward_std": 0.38923946768045425,
      "rewards/emotion_reward_func": 0.609375,
      "rewards/format_reward_func": 0.96875,
      "step": 41
    },
    {
      "completion_length": 69.875,
      "epoch": 0.056,
      "grad_norm": 5.5001220703125,
      "kl": 0.06374164298176765,
      "learning_rate": 3.121724717912138e-07,
      "loss": 0.0001,
      "reward": 1.671875,
      "reward_std": 0.18616947531700134,
      "rewards/emotion_reward_func": 0.671875,
      "rewards/format_reward_func": 1.0,
      "step": 42
    },
    {
      "completion_length": 65.75,
      "epoch": 0.05733333333333333,
      "grad_norm": 5.561408996582031,
      "kl": 0.11185399815440178,
      "learning_rate": 3.0453581034913565e-07,
      "loss": 0.0001,
      "reward": 1.125,
      "reward_std": 0.4263191595673561,
      "rewards/emotion_reward_func": 0.1875,
      "rewards/format_reward_func": 0.9375,
      "step": 43
    },
    {
      "completion_length": 57.59375,
      "epoch": 0.058666666666666666,
      "grad_norm": 6.903532028198242,
      "kl": 0.08089348301291466,
      "learning_rate": 2.968453286464312e-07,
      "loss": 0.0001,
      "reward": 1.75,
      "reward_std": 0.3838024437427521,
      "rewards/emotion_reward_func": 0.765625,
      "rewards/format_reward_func": 0.984375,
      "step": 44
    },
    {
      "completion_length": 81.0625,
      "epoch": 0.06,
      "grad_norm": 5.9377288818359375,
      "kl": 0.06169276125729084,
      "learning_rate": 2.8910861626005773e-07,
      "loss": 0.0001,
      "reward": 1.375,
      "reward_std": 0.5583916157484055,
      "rewards/emotion_reward_func": 0.421875,
      "rewards/format_reward_func": 0.953125,
      "step": 45
    },
    {
      "completion_length": 64.09375,
      "epoch": 0.06133333333333333,
      "grad_norm": 6.421321392059326,
      "kl": 0.08067317306995392,
      "learning_rate": 2.8133330839107604e-07,
      "loss": 0.0001,
      "reward": 1.484375,
      "reward_std": 0.6873095482587814,
      "rewards/emotion_reward_func": 0.59375,
      "rewards/format_reward_func": 0.890625,
      "step": 46
    },
    {
      "completion_length": 65.859375,
      "epoch": 0.06266666666666666,
      "grad_norm": 5.465454578399658,
      "kl": 0.08742601610720158,
      "learning_rate": 2.735270783296286e-07,
      "loss": 0.0001,
      "reward": 1.421875,
      "reward_std": 0.37412673234939575,
      "rewards/emotion_reward_func": 0.4375,
      "rewards/format_reward_func": 0.984375,
      "step": 47
    },
    {
      "completion_length": 61.734375,
      "epoch": 0.064,
      "grad_norm": 6.597202777862549,
      "kl": 0.09020566754043102,
      "learning_rate": 2.6569762988232837e-07,
      "loss": 0.0001,
      "reward": 1.203125,
      "reward_std": 0.4003961533308029,
      "rewards/emotion_reward_func": 0.265625,
      "rewards/format_reward_func": 0.9375,
      "step": 48
    },
    {
      "completion_length": 63.21875,
      "epoch": 0.06533333333333333,
      "grad_norm": 5.847234725952148,
      "kl": 0.09095379617065191,
      "learning_rate": 2.5785268976953204e-07,
      "loss": 0.0001,
      "reward": 1.375,
      "reward_std": 0.3876233473420143,
      "rewards/emotion_reward_func": 0.390625,
      "rewards/format_reward_func": 0.984375,
      "step": 49
    },
    {
      "completion_length": 59.890625,
      "epoch": 0.06666666666666667,
      "grad_norm": 7.6002936363220215,
      "kl": 0.08561510033905506,
      "learning_rate": 2.5e-07,
      "loss": 0.0001,
      "reward": 1.25,
      "reward_std": 0.3925696462392807,
      "rewards/emotion_reward_func": 0.28125,
      "rewards/format_reward_func": 0.96875,
      "step": 50
    },
    {
      "completion_length": 57.890625,
      "epoch": 0.068,
      "grad_norm": 6.88557243347168,
      "kl": 0.08306531235575676,
      "learning_rate": 2.4214731023046794e-07,
      "loss": 0.0001,
      "reward": 1.453125,
      "reward_std": 0.5443578287959099,
      "rewards/emotion_reward_func": 0.515625,
      "rewards/format_reward_func": 0.9375,
      "step": 51
    },
    {
      "completion_length": 64.234375,
      "epoch": 0.06933333333333333,
      "grad_norm": 6.265974044799805,
      "kl": 0.09051466174423695,
      "learning_rate": 2.3430237011767164e-07,
      "loss": 0.0001,
      "reward": 1.484375,
      "reward_std": 0.1875,
      "rewards/emotion_reward_func": 0.484375,
      "rewards/format_reward_func": 1.0,
      "step": 52
    },
    {
      "completion_length": 55.609375,
      "epoch": 0.07066666666666667,
      "grad_norm": 5.614126205444336,
      "kl": 0.0768609419465065,
      "learning_rate": 2.264729216703714e-07,
      "loss": 0.0001,
      "reward": 1.875,
      "reward_std": 0.31027980148792267,
      "rewards/emotion_reward_func": 0.890625,
      "rewards/format_reward_func": 0.984375,
      "step": 53
    },
    {
      "completion_length": 68.859375,
      "epoch": 0.072,
      "grad_norm": 5.596243381500244,
      "kl": 0.07597188651561737,
      "learning_rate": 2.1866669160892389e-07,
      "loss": 0.0001,
      "reward": 1.125,
      "reward_std": 0.3412870988249779,
      "rewards/emotion_reward_func": 0.171875,
      "rewards/format_reward_func": 0.953125,
      "step": 54
    },
    {
      "completion_length": 51.609375,
      "epoch": 0.07333333333333333,
      "grad_norm": 7.993938446044922,
      "kl": 0.09897390753030777,
      "learning_rate": 2.1089138373994222e-07,
      "loss": 0.0001,
      "reward": 1.578125,
      "reward_std": 0.47475843876600266,
      "rewards/emotion_reward_func": 0.625,
      "rewards/format_reward_func": 0.953125,
      "step": 55
    },
    {
      "completion_length": 48.265625,
      "epoch": 0.07466666666666667,
      "grad_norm": 8.550956726074219,
      "kl": 0.10356861166656017,
      "learning_rate": 2.0315467135356878e-07,
      "loss": 0.0001,
      "reward": 1.28125,
      "reward_std": 0.3340607285499573,
      "rewards/emotion_reward_func": 0.28125,
      "rewards/format_reward_func": 1.0,
      "step": 56
    },
    {
      "completion_length": 56.953125,
      "epoch": 0.076,
      "grad_norm": 6.799314498901367,
      "kl": 0.11332254763692617,
      "learning_rate": 1.954641896508644e-07,
      "loss": 0.0001,
      "reward": 1.671875,
      "reward_std": 0.3965607285499573,
      "rewards/emotion_reward_func": 0.6875,
      "rewards/format_reward_func": 0.984375,
      "step": 57
    },
    {
      "completion_length": 57.15625,
      "epoch": 0.07733333333333334,
      "grad_norm": 6.939026832580566,
      "kl": 0.1864840853959322,
      "learning_rate": 1.8782752820878633e-07,
      "loss": 0.0002,
      "reward": 1.53125,
      "reward_std": 0.4032272547483444,
      "rewards/emotion_reward_func": 0.609375,
      "rewards/format_reward_func": 0.921875,
      "step": 58
    },
    {
      "completion_length": 50.34375,
      "epoch": 0.07866666666666666,
      "grad_norm": 7.448709487915039,
      "kl": 0.15000650100409985,
      "learning_rate": 1.802522234901927e-07,
      "loss": 0.0002,
      "reward": 1.453125,
      "reward_std": 0.4035460501909256,
      "rewards/emotion_reward_func": 0.46875,
      "rewards/format_reward_func": 0.984375,
      "step": 59
    },
    {
      "completion_length": 56.296875,
      "epoch": 0.08,
      "grad_norm": 6.004992485046387,
      "kl": 0.08795534446835518,
      "learning_rate": 1.7274575140626315e-07,
      "loss": 0.0001,
      "reward": 1.53125,
      "reward_std": 0.4612579345703125,
      "rewards/emotion_reward_func": 0.546875,
      "rewards/format_reward_func": 0.984375,
      "step": 60
    },
    {
      "completion_length": 55.703125,
      "epoch": 0.08133333333333333,
      "grad_norm": 6.890044212341309,
      "kl": 0.09031901508569717,
      "learning_rate": 1.6531551993867715e-07,
      "loss": 0.0001,
      "reward": 1.453125,
      "reward_std": 0.41576120257377625,
      "rewards/emotion_reward_func": 0.484375,
      "rewards/format_reward_func": 0.96875,
      "step": 61
    },
    {
      "completion_length": 58.625,
      "epoch": 0.08266666666666667,
      "grad_norm": 6.977153778076172,
      "kl": 0.09828664548695087,
      "learning_rate": 1.579688618288305e-07,
      "loss": 0.0001,
      "reward": 1.609375,
      "reward_std": 0.3605812340974808,
      "rewards/emotion_reward_func": 0.609375,
      "rewards/format_reward_func": 1.0,
      "step": 62
    },
    {
      "completion_length": 52.421875,
      "epoch": 0.084,
      "grad_norm": 3.109772205352783,
      "kl": 0.1292141806334257,
      "learning_rate": 1.5071302734130486e-07,
      "loss": 0.0001,
      "reward": 1.65625,
      "reward_std": 0.15478479862213135,
      "rewards/emotion_reward_func": 0.671875,
      "rewards/format_reward_func": 0.984375,
      "step": 63
    },
    {
      "completion_length": 53.578125,
      "epoch": 0.08533333333333333,
      "grad_norm": 7.28511905670166,
      "kl": 0.1237227451056242,
      "learning_rate": 1.4355517710873182e-07,
      "loss": 0.0001,
      "reward": 1.765625,
      "reward_std": 0.5836244821548462,
      "rewards/emotion_reward_func": 0.84375,
      "rewards/format_reward_func": 0.921875,
      "step": 64
    },
    {
      "completion_length": 54.265625,
      "epoch": 0.08666666666666667,
      "grad_norm": 5.760799884796143,
      "kl": 0.10565520823001862,
      "learning_rate": 1.365023750651133e-07,
      "loss": 0.0001,
      "reward": 1.59375,
      "reward_std": 0.38039760291576385,
      "rewards/emotion_reward_func": 0.609375,
      "rewards/format_reward_func": 0.984375,
      "step": 65
    },
    {
      "completion_length": 55.9375,
      "epoch": 0.088,
      "grad_norm": 7.823127269744873,
      "kl": 0.09790175035595894,
      "learning_rate": 1.2956158147457114e-07,
      "loss": 0.0001,
      "reward": 1.625,
      "reward_std": 0.40478479862213135,
      "rewards/emotion_reward_func": 0.65625,
      "rewards/format_reward_func": 0.96875,
      "step": 66
    },
    {
      "completion_length": 44.671875,
      "epoch": 0.08933333333333333,
      "grad_norm": 4.364702224731445,
      "kl": 0.11339546367526054,
      "learning_rate": 1.2273964606240718e-07,
      "loss": 0.0001,
      "reward": 1.34375,
      "reward_std": 0.18217839300632477,
      "rewards/emotion_reward_func": 0.34375,
      "rewards/format_reward_func": 1.0,
      "step": 67
    },
    {
      "completion_length": 57.421875,
      "epoch": 0.09066666666666667,
      "grad_norm": 5.267661094665527,
      "kl": 0.10790612921118736,
      "learning_rate": 1.1604330125525078e-07,
      "loss": 0.0001,
      "reward": 1.1875,
      "reward_std": 0.2545653209090233,
      "rewards/emotion_reward_func": 0.21875,
      "rewards/format_reward_func": 0.96875,
      "step": 68
    },
    {
      "completion_length": 48.921875,
      "epoch": 0.092,
      "grad_norm": 5.409526824951172,
      "kl": 0.11567417718470097,
      "learning_rate": 1.0947915553696741e-07,
      "loss": 0.0001,
      "reward": 1.453125,
      "reward_std": 0.23328250646591187,
      "rewards/emotion_reward_func": 0.453125,
      "rewards/format_reward_func": 1.0,
      "step": 69
    },
    {
      "completion_length": 55.828125,
      "epoch": 0.09333333333333334,
      "grad_norm": 7.669867992401123,
      "kl": 3.9372363202273846,
      "learning_rate": 1.0305368692688174e-07,
      "loss": 0.0039,
      "reward": 1.34375,
      "reward_std": 0.3306438848376274,
      "rewards/emotion_reward_func": 0.359375,
      "rewards/format_reward_func": 0.984375,
      "step": 70
    },
    {
      "completion_length": 43.125,
      "epoch": 0.09466666666666666,
      "grad_norm": 8.619794845581055,
      "kl": 0.13703159242868423,
      "learning_rate": 9.677323658675593e-08,
      "loss": 0.0001,
      "reward": 1.5625,
      "reward_std": 0.3234764039516449,
      "rewards/emotion_reward_func": 0.578125,
      "rewards/format_reward_func": 0.984375,
      "step": 71
    },
    {
      "completion_length": 47.484375,
      "epoch": 0.096,
      "grad_norm": 5.2266740798950195,
      "kl": 0.1516919508576393,
      "learning_rate": 9.064400256282755e-08,
      "loss": 0.0002,
      "reward": 1.296875,
      "reward_std": 0.34940721094608307,
      "rewards/emotion_reward_func": 0.3125,
      "rewards/format_reward_func": 0.984375,
      "step": 72
    },
    {
      "completion_length": 60.5,
      "epoch": 0.09733333333333333,
      "grad_norm": 6.890865325927734,
      "kl": 0.10698151029646397,
      "learning_rate": 8.467203366908707e-08,
      "loss": 0.0001,
      "reward": 1.375,
      "reward_std": 0.3380199372768402,
      "rewards/emotion_reward_func": 0.40625,
      "rewards/format_reward_func": 0.96875,
      "step": 73
    },
    {
      "completion_length": 45.8125,
      "epoch": 0.09866666666666667,
      "grad_norm": 4.76033878326416,
      "kl": 0.2001918088644743,
      "learning_rate": 7.886322351782782e-08,
      "loss": 0.0002,
      "reward": 1.6875,
      "reward_std": 0.26933756470680237,
      "rewards/emotion_reward_func": 0.703125,
      "rewards/format_reward_func": 0.984375,
      "step": 74
    },
    {
      "completion_length": 53.640625,
      "epoch": 0.1,
      "grad_norm": 7.104291915893555,
      "kl": 0.09334802068769932,
      "learning_rate": 7.322330470336313e-08,
      "loss": 0.0001,
      "reward": 1.453125,
      "reward_std": 0.3290881961584091,
      "rewards/emotion_reward_func": 0.484375,
      "rewards/format_reward_func": 0.96875,
      "step": 75
    },
    {
      "completion_length": 45.109375,
      "epoch": 0.10133333333333333,
      "grad_norm": 10.217005729675293,
      "kl": 0.12721979059278965,
      "learning_rate": 6.775784314464716e-08,
      "loss": 0.0001,
      "reward": 1.4375,
      "reward_std": 0.3354101926088333,
      "rewards/emotion_reward_func": 0.4375,
      "rewards/format_reward_func": 1.0,
      "step": 76
    },
    {
      "completion_length": 49.390625,
      "epoch": 0.10266666666666667,
      "grad_norm": 5.090665817260742,
      "kl": 0.1952703520655632,
      "learning_rate": 6.24722325923851e-08,
      "loss": 0.0002,
      "reward": 1.5625,
      "reward_std": 0.21039125323295593,
      "rewards/emotion_reward_func": 0.5625,
      "rewards/format_reward_func": 1.0,
      "step": 77
    },
    {
      "completion_length": 40.953125,
      "epoch": 0.104,
      "grad_norm": 10.18713665008545,
      "kl": 0.1544223688542843,
      "learning_rate": 5.737168930605271e-08,
      "loss": 0.0002,
      "reward": 1.609375,
      "reward_std": 0.44701361656188965,
      "rewards/emotion_reward_func": 0.640625,
      "rewards/format_reward_func": 0.96875,
      "step": 78
    },
    {
      "completion_length": 45.84375,
      "epoch": 0.10533333333333333,
      "grad_norm": 6.143667221069336,
      "kl": 0.14481117203831673,
      "learning_rate": 5.246124690607739e-08,
      "loss": 0.0001,
      "reward": 1.515625,
      "reward_std": 0.2715607285499573,
      "rewards/emotion_reward_func": 0.515625,
      "rewards/format_reward_func": 1.0,
      "step": 79
    },
    {
      "completion_length": 46.59375,
      "epoch": 0.10666666666666667,
      "grad_norm": 5.600602149963379,
      "kl": 0.10117345489561558,
      "learning_rate": 4.774575140626316e-08,
      "loss": 0.0001,
      "reward": 1.890625,
      "reward_std": 0.1280868798494339,
      "rewards/emotion_reward_func": 0.890625,
      "rewards/format_reward_func": 1.0,
      "step": 80
    },
    {
      "completion_length": 55.265625,
      "epoch": 0.108,
      "grad_norm": 8.253979682922363,
      "kl": 0.11770397983491421,
      "learning_rate": 4.3229856431359513e-08,
      "loss": 0.0001,
      "reward": 1.515625,
      "reward_std": 0.5620162785053253,
      "rewards/emotion_reward_func": 0.5625,
      "rewards/format_reward_func": 0.953125,
      "step": 81
    },
    {
      "completion_length": 55.34375,
      "epoch": 0.10933333333333334,
      "grad_norm": 7.1831135749816895,
      "kl": 0.1115355659276247,
      "learning_rate": 3.8918018624496286e-08,
      "loss": 0.0001,
      "reward": 1.375,
      "reward_std": 0.3838024437427521,
      "rewards/emotion_reward_func": 0.390625,
      "rewards/format_reward_func": 0.984375,
      "step": 82
    },
    {
      "completion_length": 48.40625,
      "epoch": 0.11066666666666666,
      "grad_norm": 7.065600395202637,
      "kl": 0.14161021262407303,
      "learning_rate": 3.481449324901411e-08,
      "loss": 0.0001,
      "reward": 1.515625,
      "reward_std": 0.3940916210412979,
      "rewards/emotion_reward_func": 0.546875,
      "rewards/format_reward_func": 0.96875,
      "step": 83
    },
    {
      "completion_length": 52.5625,
      "epoch": 0.112,
      "grad_norm": 7.827910423278809,
      "kl": 0.16811930015683174,
      "learning_rate": 3.092332998903416e-08,
      "loss": 0.0002,
      "reward": 1.5,
      "reward_std": 0.5367372632026672,
      "rewards/emotion_reward_func": 0.546875,
      "rewards/format_reward_func": 0.953125,
      "step": 84
    },
    {
      "completion_length": 51.328125,
      "epoch": 0.11333333333333333,
      "grad_norm": 4.83447265625,
      "kl": 0.11310878023505211,
      "learning_rate": 2.724836895290805e-08,
      "loss": 0.0001,
      "reward": 1.640625,
      "reward_std": 0.1280868798494339,
      "rewards/emotion_reward_func": 0.640625,
      "rewards/format_reward_func": 1.0,
      "step": 85
    },
    {
      "completion_length": 47.578125,
      "epoch": 0.11466666666666667,
      "grad_norm": 5.901933670043945,
      "kl": 0.1336957048624754,
      "learning_rate": 2.379323688349516e-08,
      "loss": 0.0001,
      "reward": 1.375,
      "reward_std": 0.21039125323295593,
      "rewards/emotion_reward_func": 0.375,
      "rewards/format_reward_func": 1.0,
      "step": 86
    },
    {
      "completion_length": 50.53125,
      "epoch": 0.116,
      "grad_norm": 5.392825603485107,
      "kl": 0.1246971283107996,
      "learning_rate": 2.0561343579004715e-08,
      "loss": 0.0001,
      "reward": 1.6875,
      "reward_std": 0.3024514466524124,
      "rewards/emotion_reward_func": 0.71875,
      "rewards/format_reward_func": 0.96875,
      "step": 87
    },
    {
      "completion_length": 52.515625,
      "epoch": 0.11733333333333333,
      "grad_norm": 7.34331750869751,
      "kl": 0.11970937624573708,
      "learning_rate": 1.7555878527937163e-08,
      "loss": 0.0001,
      "reward": 1.34375,
      "reward_std": 0.40886765718460083,
      "rewards/emotion_reward_func": 0.359375,
      "rewards/format_reward_func": 0.984375,
      "step": 88
    },
    {
      "completion_length": 58.03125,
      "epoch": 0.11866666666666667,
      "grad_norm": 4.543256759643555,
      "kl": 0.12226046249270439,
      "learning_rate": 1.4779807761443635e-08,
      "loss": 0.0001,
      "reward": 1.546875,
      "reward_std": 0.3359370082616806,
      "rewards/emotion_reward_func": 0.578125,
      "rewards/format_reward_func": 0.96875,
      "step": 89
    },
    {
      "completion_length": 52.265625,
      "epoch": 0.12,
      "grad_norm": 7.780374050140381,
      "kl": 0.1240895576775074,
      "learning_rate": 1.2235870926211616e-08,
      "loss": 0.0001,
      "reward": 1.59375,
      "reward_std": 0.25,
      "rewards/emotion_reward_func": 0.59375,
      "rewards/format_reward_func": 1.0,
      "step": 90
    },
    {
      "completion_length": 52.5,
      "epoch": 0.12133333333333333,
      "grad_norm": 3.1433615684509277,
      "kl": 0.10472103767096996,
      "learning_rate": 9.926578580764234e-09,
      "loss": 0.0001,
      "reward": 1.734375,
      "reward_std": 0.0625,
      "rewards/emotion_reward_func": 0.734375,
      "rewards/format_reward_func": 1.0,
      "step": 91
    },
    {
      "completion_length": 50.921875,
      "epoch": 0.12266666666666666,
      "grad_norm": 7.484493732452393,
      "kl": 0.10997971147298813,
      "learning_rate": 7.85420971784223e-09,
      "loss": 0.0001,
      "reward": 1.640625,
      "reward_std": 0.2829566150903702,
      "rewards/emotion_reward_func": 0.640625,
      "rewards/format_reward_func": 1.0,
      "step": 92
    },
    {
      "completion_length": 52.015625,
      "epoch": 0.124,
      "grad_norm": 8.367355346679688,
      "kl": 0.1366768404841423,
      "learning_rate": 6.020809515313141e-09,
      "loss": 0.0001,
      "reward": 1.28125,
      "reward_std": 0.3538651019334793,
      "rewards/emotion_reward_func": 0.28125,
      "rewards/format_reward_func": 1.0,
      "step": 93
    },
    {
      "completion_length": 45.796875,
      "epoch": 0.12533333333333332,
      "grad_norm": 6.152498245239258,
      "kl": 0.1532982587814331,
      "learning_rate": 4.4281873178278475e-09,
      "loss": 0.0002,
      "reward": 1.640625,
      "reward_std": 0.414583221077919,
      "rewards/emotion_reward_func": 0.671875,
      "rewards/format_reward_func": 0.96875,
      "step": 94
    },
    {
      "completion_length": 50.25,
      "epoch": 0.12666666666666668,
      "grad_norm": 0.020403465256094933,
      "kl": 0.11631555296480656,
      "learning_rate": 3.077914851215585e-09,
      "loss": 0.0001,
      "reward": 1.5,
      "reward_std": 0.0,
      "rewards/emotion_reward_func": 0.5,
      "rewards/format_reward_func": 1.0,
      "step": 95
    },
    {
      "completion_length": 53.671875,
      "epoch": 0.128,
      "grad_norm": 6.355586528778076,
      "kl": 0.11114749684929848,
      "learning_rate": 1.9713246713805587e-09,
      "loss": 0.0001,
      "reward": 1.578125,
      "reward_std": 0.33949775248765945,
      "rewards/emotion_reward_func": 0.59375,
      "rewards/format_reward_func": 0.984375,
      "step": 96
    },
    {
      "completion_length": 51.921875,
      "epoch": 0.12933333333333333,
      "grad_norm": 7.896821022033691,
      "kl": 0.14222519844770432,
      "learning_rate": 1.1095088492300008e-09,
      "loss": 0.0001,
      "reward": 1.625,
      "reward_std": 0.1905868798494339,
      "rewards/emotion_reward_func": 0.625,
      "rewards/format_reward_func": 1.0,
      "step": 97
    },
    {
      "completion_length": 52.90625,
      "epoch": 0.13066666666666665,
      "grad_norm": 8.117393493652344,
      "kl": 0.29374901205301285,
      "learning_rate": 4.933178929321102e-10,
      "loss": 0.0003,
      "reward": 1.65625,
      "reward_std": 0.5836337506771088,
      "rewards/emotion_reward_func": 0.71875,
      "rewards/format_reward_func": 0.9375,
      "step": 98
    },
    {
      "completion_length": 49.234375,
      "epoch": 0.132,
      "grad_norm": 4.081859111785889,
      "kl": 0.12134127877652645,
      "learning_rate": 1.2335990856709998e-10,
      "loss": 0.0001,
      "reward": 1.75,
      "reward_std": 0.2367546260356903,
      "rewards/emotion_reward_func": 0.765625,
      "rewards/format_reward_func": 0.984375,
      "step": 99
    },
    {
      "completion_length": 51.25,
      "epoch": 0.13333333333333333,
      "grad_norm": 6.719541072845459,
      "kl": 0.1454935073852539,
      "learning_rate": 0.0,
      "loss": 0.0001,
      "reward": 1.609375,
      "reward_std": 0.36967839300632477,
      "rewards/emotion_reward_func": 0.640625,
      "rewards/format_reward_func": 0.96875,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}