{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25588536335721596,
  "eval_steps": 250,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010235414534288639,
      "grad_norm": 2.0027730464935303,
      "learning_rate": 0.0,
      "loss": 0.7807,
      "step": 1
    },
    {
      "epoch": 0.0020470829068577278,
      "grad_norm": 2.1167027950286865,
      "learning_rate": 2e-09,
      "loss": 0.7864,
      "step": 2
    },
    {
      "epoch": 0.0030706243602865915,
      "grad_norm": 2.759631395339966,
      "learning_rate": 4e-09,
      "loss": 0.7935,
      "step": 3
    },
    {
      "epoch": 0.0040941658137154556,
      "grad_norm": 1.614827036857605,
      "learning_rate": 6e-09,
      "loss": 0.7812,
      "step": 4
    },
    {
      "epoch": 0.00511770726714432,
      "grad_norm": 2.2924065589904785,
      "learning_rate": 8e-09,
      "loss": 0.7841,
      "step": 5
    },
    {
      "epoch": 0.006141248720573183,
      "grad_norm": 2.6293888092041016,
      "learning_rate": 1e-08,
      "loss": 0.7944,
      "step": 6
    },
    {
      "epoch": 0.007164790174002047,
      "grad_norm": 1.7844728231430054,
      "learning_rate": 1.2e-08,
      "loss": 0.7793,
      "step": 7
    },
    {
      "epoch": 0.008188331627430911,
      "grad_norm": 1.4052098989486694,
      "learning_rate": 1.4000000000000001e-08,
      "loss": 0.7671,
      "step": 8
    },
    {
      "epoch": 0.009211873080859774,
      "grad_norm": 2.682335376739502,
      "learning_rate": 1.6e-08,
      "loss": 0.795,
      "step": 9
    },
    {
      "epoch": 0.01023541453428864,
      "grad_norm": 2.45478892326355,
      "learning_rate": 1.8000000000000002e-08,
      "loss": 0.7918,
      "step": 10
    },
    {
      "epoch": 0.011258955987717503,
      "grad_norm": 2.523688316345215,
      "learning_rate": 2e-08,
      "loss": 0.799,
      "step": 11
    },
    {
      "epoch": 0.012282497441146366,
      "grad_norm": 2.3234951496124268,
      "learning_rate": 2.2000000000000002e-08,
      "loss": 0.7835,
      "step": 12
    },
    {
      "epoch": 0.01330603889457523,
      "grad_norm": 2.2566919326782227,
      "learning_rate": 2.4e-08,
      "loss": 0.7926,
      "step": 13
    },
    {
      "epoch": 0.014329580348004094,
      "grad_norm": 2.3038065433502197,
      "learning_rate": 2.6e-08,
      "loss": 0.7921,
      "step": 14
    },
    {
      "epoch": 0.015353121801432957,
      "grad_norm": 2.107079267501831,
      "learning_rate": 2.8000000000000003e-08,
      "loss": 0.7864,
      "step": 15
    },
    {
      "epoch": 0.016376663254861822,
      "grad_norm": 2.129422426223755,
      "learning_rate": 3.0000000000000004e-08,
      "loss": 0.7756,
      "step": 16
    },
    {
      "epoch": 0.017400204708290685,
      "grad_norm": 1.5430221557617188,
      "learning_rate": 3.2e-08,
      "loss": 0.7695,
      "step": 17
    },
    {
      "epoch": 0.01842374616171955,
      "grad_norm": 2.061033248901367,
      "learning_rate": 3.4e-08,
      "loss": 0.7812,
      "step": 18
    },
    {
      "epoch": 0.019447287615148412,
      "grad_norm": 2.001169443130493,
      "learning_rate": 3.6000000000000005e-08,
      "loss": 0.7859,
      "step": 19
    },
    {
      "epoch": 0.02047082906857728,
      "grad_norm": 1.981490135192871,
      "learning_rate": 3.8e-08,
      "loss": 0.788,
      "step": 20
    },
    {
      "epoch": 0.021494370522006142,
      "grad_norm": 1.7497801780700684,
      "learning_rate": 4e-08,
      "loss": 0.7762,
      "step": 21
    },
    {
      "epoch": 0.022517911975435005,
      "grad_norm": 1.8900872468948364,
      "learning_rate": 4.2e-08,
      "loss": 0.7835,
      "step": 22
    },
    {
      "epoch": 0.02354145342886387,
      "grad_norm": 2.0690395832061768,
      "learning_rate": 4.4000000000000004e-08,
      "loss": 0.7795,
      "step": 23
    },
    {
      "epoch": 0.02456499488229273,
      "grad_norm": 1.251330852508545,
      "learning_rate": 4.6e-08,
      "loss": 0.7675,
      "step": 24
    },
    {
      "epoch": 0.0255885363357216,
      "grad_norm": 1.5707719326019287,
      "learning_rate": 4.8e-08,
      "loss": 0.7677,
      "step": 25
    },
    {
      "epoch": 0.02661207778915046,
      "grad_norm": 1.831811785697937,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 0.7677,
      "step": 26
    },
    {
      "epoch": 0.027635619242579325,
      "grad_norm": 1.8244602680206299,
      "learning_rate": 5.2e-08,
      "loss": 0.7714,
      "step": 27
    },
    {
      "epoch": 0.028659160696008188,
      "grad_norm": 2.0211703777313232,
      "learning_rate": 5.400000000000001e-08,
      "loss": 0.7848,
      "step": 28
    },
    {
      "epoch": 0.02968270214943705,
      "grad_norm": 1.8793987035751343,
      "learning_rate": 5.6000000000000005e-08,
      "loss": 0.7846,
      "step": 29
    },
    {
      "epoch": 0.030706243602865915,
      "grad_norm": 1.2707512378692627,
      "learning_rate": 5.8e-08,
      "loss": 0.7723,
      "step": 30
    },
    {
      "epoch": 0.03172978505629478,
      "grad_norm": 1.710810899734497,
      "learning_rate": 6.000000000000001e-08,
      "loss": 0.7788,
      "step": 31
    },
    {
      "epoch": 0.032753326509723645,
      "grad_norm": 1.5903525352478027,
      "learning_rate": 6.2e-08,
      "loss": 0.7775,
      "step": 32
    },
    {
      "epoch": 0.033776867963152504,
      "grad_norm": 2.2208263874053955,
      "learning_rate": 6.4e-08,
      "loss": 0.78,
      "step": 33
    },
    {
      "epoch": 0.03480040941658137,
      "grad_norm": 2.3763325214385986,
      "learning_rate": 6.600000000000001e-08,
      "loss": 0.7939,
      "step": 34
    },
    {
      "epoch": 0.03582395087001024,
      "grad_norm": 1.6977214813232422,
      "learning_rate": 6.8e-08,
      "loss": 0.7745,
      "step": 35
    },
    {
      "epoch": 0.0368474923234391,
      "grad_norm": 2.1862456798553467,
      "learning_rate": 7e-08,
      "loss": 0.7844,
      "step": 36
    },
    {
      "epoch": 0.037871033776867964,
      "grad_norm": 1.8891886472702026,
      "learning_rate": 7.200000000000001e-08,
      "loss": 0.775,
      "step": 37
    },
    {
      "epoch": 0.038894575230296824,
      "grad_norm": 2.0394537448883057,
      "learning_rate": 7.400000000000001e-08,
      "loss": 0.7771,
      "step": 38
    },
    {
      "epoch": 0.03991811668372569,
      "grad_norm": 2.105576992034912,
      "learning_rate": 7.6e-08,
      "loss": 0.7862,
      "step": 39
    },
    {
      "epoch": 0.04094165813715456,
      "grad_norm": 2.123842477798462,
      "learning_rate": 7.8e-08,
      "loss": 0.7804,
      "step": 40
    },
    {
      "epoch": 0.04196519959058342,
      "grad_norm": 1.3442330360412598,
      "learning_rate": 8e-08,
      "loss": 0.7676,
      "step": 41
    },
    {
      "epoch": 0.042988741044012284,
      "grad_norm": 2.431581735610962,
      "learning_rate": 8.200000000000002e-08,
      "loss": 0.7785,
      "step": 42
    },
    {
      "epoch": 0.044012282497441144,
      "grad_norm": 2.3671112060546875,
      "learning_rate": 8.4e-08,
      "loss": 0.7996,
      "step": 43
    },
    {
      "epoch": 0.04503582395087001,
      "grad_norm": 2.2737319469451904,
      "learning_rate": 8.6e-08,
      "loss": 0.7794,
      "step": 44
    },
    {
      "epoch": 0.04605936540429888,
      "grad_norm": 1.5326226949691772,
      "learning_rate": 8.800000000000001e-08,
      "loss": 0.774,
      "step": 45
    },
    {
      "epoch": 0.04708290685772774,
      "grad_norm": 1.845044493675232,
      "learning_rate": 9e-08,
      "loss": 0.7875,
      "step": 46
    },
    {
      "epoch": 0.048106448311156604,
      "grad_norm": 2.3159587383270264,
      "learning_rate": 9.2e-08,
      "loss": 0.7916,
      "step": 47
    },
    {
      "epoch": 0.04912998976458546,
      "grad_norm": 1.6539689302444458,
      "learning_rate": 9.400000000000001e-08,
      "loss": 0.775,
      "step": 48
    },
    {
      "epoch": 0.05015353121801433,
      "grad_norm": 1.5031073093414307,
      "learning_rate": 9.6e-08,
      "loss": 0.777,
      "step": 49
    },
    {
      "epoch": 0.0511770726714432,
      "grad_norm": 1.9059022665023804,
      "learning_rate": 9.8e-08,
      "loss": 0.7836,
      "step": 50
    },
    {
      "epoch": 0.052200614124872056,
      "grad_norm": 2.2032649517059326,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 0.7862,
      "step": 51
    },
    {
      "epoch": 0.05322415557830092,
      "grad_norm": 1.2774498462677002,
      "learning_rate": 1.0200000000000001e-07,
      "loss": 0.7691,
      "step": 52
    },
    {
      "epoch": 0.05424769703172978,
      "grad_norm": 1.7091227769851685,
      "learning_rate": 1.04e-07,
      "loss": 0.7843,
      "step": 53
    },
    {
      "epoch": 0.05527123848515865,
      "grad_norm": 1.3407061100006104,
      "learning_rate": 1.0600000000000001e-07,
      "loss": 0.7704,
      "step": 54
    },
    {
      "epoch": 0.05629477993858751,
      "grad_norm": 1.7370580434799194,
      "learning_rate": 1.0800000000000001e-07,
      "loss": 0.7803,
      "step": 55
    },
    {
      "epoch": 0.057318321392016376,
      "grad_norm": 2.144951105117798,
      "learning_rate": 1.1e-07,
      "loss": 0.7816,
      "step": 56
    },
    {
      "epoch": 0.05834186284544524,
      "grad_norm": 1.5752339363098145,
      "learning_rate": 1.1200000000000001e-07,
      "loss": 0.7723,
      "step": 57
    },
    {
      "epoch": 0.0593654042988741,
      "grad_norm": 1.595261573791504,
      "learning_rate": 1.1400000000000001e-07,
      "loss": 0.7785,
      "step": 58
    },
    {
      "epoch": 0.06038894575230297,
      "grad_norm": 2.0418097972869873,
      "learning_rate": 1.16e-07,
      "loss": 0.7864,
      "step": 59
    },
    {
      "epoch": 0.06141248720573183,
      "grad_norm": 1.6113048791885376,
      "learning_rate": 1.1800000000000001e-07,
      "loss": 0.7719,
      "step": 60
    },
    {
      "epoch": 0.062436028659160696,
      "grad_norm": 1.533006191253662,
      "learning_rate": 1.2000000000000002e-07,
      "loss": 0.7743,
      "step": 61
    },
    {
      "epoch": 0.06345957011258956,
      "grad_norm": 0.9601923823356628,
      "learning_rate": 1.22e-07,
      "loss": 0.7737,
      "step": 62
    },
    {
      "epoch": 0.06448311156601842,
      "grad_norm": 1.3146189451217651,
      "learning_rate": 1.24e-07,
      "loss": 0.7683,
      "step": 63
    },
    {
      "epoch": 0.06550665301944729,
      "grad_norm": 1.5222556591033936,
      "learning_rate": 1.2600000000000002e-07,
      "loss": 0.7739,
      "step": 64
    },
    {
      "epoch": 0.06653019447287616,
      "grad_norm": 1.4367096424102783,
      "learning_rate": 1.28e-07,
      "loss": 0.7726,
      "step": 65
    },
    {
      "epoch": 0.06755373592630501,
      "grad_norm": 1.03805673122406,
      "learning_rate": 1.3e-07,
      "loss": 0.7638,
      "step": 66
    },
    {
      "epoch": 0.06857727737973388,
      "grad_norm": 1.9511936902999878,
      "learning_rate": 1.3200000000000002e-07,
      "loss": 0.7815,
      "step": 67
    },
    {
      "epoch": 0.06960081883316274,
      "grad_norm": 1.5974836349487305,
      "learning_rate": 1.34e-07,
      "loss": 0.7713,
      "step": 68
    },
    {
      "epoch": 0.07062436028659161,
      "grad_norm": 1.4479100704193115,
      "learning_rate": 1.36e-07,
      "loss": 0.7761,
      "step": 69
    },
    {
      "epoch": 0.07164790174002048,
      "grad_norm": 1.4680284261703491,
      "learning_rate": 1.3800000000000002e-07,
      "loss": 0.766,
      "step": 70
    },
    {
      "epoch": 0.07267144319344933,
      "grad_norm": 1.4755054712295532,
      "learning_rate": 1.4e-07,
      "loss": 0.7713,
      "step": 71
    },
    {
      "epoch": 0.0736949846468782,
      "grad_norm": 1.3230453729629517,
      "learning_rate": 1.4200000000000003e-07,
      "loss": 0.7755,
      "step": 72
    },
    {
      "epoch": 0.07471852610030706,
      "grad_norm": 1.8009718656539917,
      "learning_rate": 1.4400000000000002e-07,
      "loss": 0.7833,
      "step": 73
    },
    {
      "epoch": 0.07574206755373593,
      "grad_norm": 1.5481526851654053,
      "learning_rate": 1.46e-07,
      "loss": 0.7806,
      "step": 74
    },
    {
      "epoch": 0.0767656090071648,
      "grad_norm": 0.9285205602645874,
      "learning_rate": 1.4800000000000003e-07,
      "loss": 0.767,
      "step": 75
    },
    {
      "epoch": 0.07778915046059365,
      "grad_norm": 1.6149866580963135,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 0.7802,
      "step": 76
    },
    {
      "epoch": 0.07881269191402251,
      "grad_norm": 1.667980670928955,
      "learning_rate": 1.52e-07,
      "loss": 0.7757,
      "step": 77
    },
    {
      "epoch": 0.07983623336745138,
      "grad_norm": 1.862239956855774,
      "learning_rate": 1.5400000000000003e-07,
      "loss": 0.771,
      "step": 78
    },
    {
      "epoch": 0.08085977482088025,
      "grad_norm": 1.3772761821746826,
      "learning_rate": 1.56e-07,
      "loss": 0.782,
      "step": 79
    },
    {
      "epoch": 0.08188331627430911,
      "grad_norm": 1.9442654848098755,
      "learning_rate": 1.5800000000000004e-07,
      "loss": 0.7746,
      "step": 80
    },
    {
      "epoch": 0.08290685772773797,
      "grad_norm": 1.420366644859314,
      "learning_rate": 1.6e-07,
      "loss": 0.7749,
      "step": 81
    },
    {
      "epoch": 0.08393039918116683,
      "grad_norm": 1.7965872287750244,
      "learning_rate": 1.62e-07,
      "loss": 0.776,
      "step": 82
    },
    {
      "epoch": 0.0849539406345957,
      "grad_norm": 1.811287522315979,
      "learning_rate": 1.6400000000000004e-07,
      "loss": 0.7794,
      "step": 83
    },
    {
      "epoch": 0.08597748208802457,
      "grad_norm": 1.489158034324646,
      "learning_rate": 1.66e-07,
      "loss": 0.7785,
      "step": 84
    },
    {
      "epoch": 0.08700102354145343,
      "grad_norm": 1.527341604232788,
      "learning_rate": 1.68e-07,
      "loss": 0.7804,
      "step": 85
    },
    {
      "epoch": 0.08802456499488229,
      "grad_norm": 1.0682123899459839,
      "learning_rate": 1.7000000000000001e-07,
      "loss": 0.7717,
      "step": 86
    },
    {
      "epoch": 0.08904810644831115,
      "grad_norm": 0.7309737205505371,
      "learning_rate": 1.72e-07,
      "loss": 0.7644,
      "step": 87
    },
    {
      "epoch": 0.09007164790174002,
      "grad_norm": 1.156342625617981,
      "learning_rate": 1.74e-07,
      "loss": 0.7703,
      "step": 88
    },
    {
      "epoch": 0.09109518935516889,
      "grad_norm": 1.4098986387252808,
      "learning_rate": 1.7600000000000001e-07,
      "loss": 0.774,
      "step": 89
    },
    {
      "epoch": 0.09211873080859775,
      "grad_norm": 1.740477204322815,
      "learning_rate": 1.78e-07,
      "loss": 0.7737,
      "step": 90
    },
    {
      "epoch": 0.0931422722620266,
      "grad_norm": 1.291332721710205,
      "learning_rate": 1.8e-07,
      "loss": 0.769,
      "step": 91
    },
    {
      "epoch": 0.09416581371545547,
      "grad_norm": 1.403385877609253,
      "learning_rate": 1.8200000000000002e-07,
      "loss": 0.777,
      "step": 92
    },
    {
      "epoch": 0.09518935516888434,
      "grad_norm": 1.0460313558578491,
      "learning_rate": 1.84e-07,
      "loss": 0.7654,
      "step": 93
    },
    {
      "epoch": 0.09621289662231321,
      "grad_norm": 0.8738810420036316,
      "learning_rate": 1.86e-07,
      "loss": 0.7645,
      "step": 94
    },
    {
      "epoch": 0.09723643807574207,
      "grad_norm": 1.2067152261734009,
      "learning_rate": 1.8800000000000002e-07,
      "loss": 0.771,
      "step": 95
    },
    {
      "epoch": 0.09825997952917093,
      "grad_norm": 0.7921656370162964,
      "learning_rate": 1.9e-07,
      "loss": 0.7673,
      "step": 96
    },
    {
      "epoch": 0.0992835209825998,
      "grad_norm": 1.2949451208114624,
      "learning_rate": 1.92e-07,
      "loss": 0.771,
      "step": 97
    },
    {
      "epoch": 0.10030706243602866,
      "grad_norm": 1.0598716735839844,
      "learning_rate": 1.9400000000000002e-07,
      "loss": 0.7661,
      "step": 98
    },
    {
      "epoch": 0.10133060388945753,
      "grad_norm": 0.5756526589393616,
      "learning_rate": 1.96e-07,
      "loss": 0.7629,
      "step": 99
    },
    {
      "epoch": 0.1023541453428864,
      "grad_norm": 0.9098894596099854,
      "learning_rate": 1.9800000000000003e-07,
      "loss": 0.7613,
      "step": 100
    },
    {
      "epoch": 0.10337768679631525,
      "grad_norm": 1.3523019552230835,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.7753,
      "step": 101
    },
    {
      "epoch": 0.10440122824974411,
      "grad_norm": 0.9900273680686951,
      "learning_rate": 2.02e-07,
      "loss": 0.7761,
      "step": 102
    },
    {
      "epoch": 0.10542476970317298,
      "grad_norm": 0.7855979204177856,
      "learning_rate": 2.0400000000000003e-07,
      "loss": 0.7651,
      "step": 103
    },
    {
      "epoch": 0.10644831115660185,
      "grad_norm": 1.0023835897445679,
      "learning_rate": 2.0600000000000002e-07,
      "loss": 0.7677,
      "step": 104
    },
    {
      "epoch": 0.10747185261003071,
      "grad_norm": 0.6019173860549927,
      "learning_rate": 2.08e-07,
      "loss": 0.7606,
      "step": 105
    },
    {
      "epoch": 0.10849539406345957,
      "grad_norm": 0.9002220630645752,
      "learning_rate": 2.1000000000000003e-07,
      "loss": 0.7701,
      "step": 106
    },
    {
      "epoch": 0.10951893551688843,
      "grad_norm": 0.8429995775222778,
      "learning_rate": 2.1200000000000002e-07,
      "loss": 0.7656,
      "step": 107
    },
    {
      "epoch": 0.1105424769703173,
      "grad_norm": 0.5726915001869202,
      "learning_rate": 2.14e-07,
      "loss": 0.7667,
      "step": 108
    },
    {
      "epoch": 0.11156601842374617,
      "grad_norm": 0.49694034457206726,
      "learning_rate": 2.1600000000000003e-07,
      "loss": 0.7614,
      "step": 109
    },
    {
      "epoch": 0.11258955987717502,
      "grad_norm": 0.5831499099731445,
      "learning_rate": 2.1800000000000002e-07,
      "loss": 0.7646,
      "step": 110
    },
    {
      "epoch": 0.11361310133060389,
      "grad_norm": 0.49775540828704834,
      "learning_rate": 2.2e-07,
      "loss": 0.7611,
      "step": 111
    },
    {
      "epoch": 0.11463664278403275,
      "grad_norm": 1.5634126663208008,
      "learning_rate": 2.2200000000000003e-07,
      "loss": 0.7824,
      "step": 112
    },
    {
      "epoch": 0.11566018423746162,
      "grad_norm": 0.9528007507324219,
      "learning_rate": 2.2400000000000002e-07,
      "loss": 0.7595,
      "step": 113
    },
    {
      "epoch": 0.11668372569089049,
      "grad_norm": 0.5957873463630676,
      "learning_rate": 2.26e-07,
      "loss": 0.761,
      "step": 114
    },
    {
      "epoch": 0.11770726714431934,
      "grad_norm": 0.6020492911338806,
      "learning_rate": 2.2800000000000003e-07,
      "loss": 0.7605,
      "step": 115
    },
    {
      "epoch": 0.1187308085977482,
      "grad_norm": 0.578925371170044,
      "learning_rate": 2.3000000000000002e-07,
      "loss": 0.768,
      "step": 116
    },
    {
      "epoch": 0.11975435005117707,
      "grad_norm": 0.5749679207801819,
      "learning_rate": 2.32e-07,
      "loss": 0.7636,
      "step": 117
    },
    {
      "epoch": 0.12077789150460594,
      "grad_norm": 1.0057039260864258,
      "learning_rate": 2.3400000000000003e-07,
      "loss": 0.7591,
      "step": 118
    },
    {
      "epoch": 0.1218014329580348,
      "grad_norm": 0.5447669625282288,
      "learning_rate": 2.3600000000000002e-07,
      "loss": 0.7671,
      "step": 119
    },
    {
      "epoch": 0.12282497441146366,
      "grad_norm": 0.5045008063316345,
      "learning_rate": 2.3800000000000004e-07,
      "loss": 0.7614,
      "step": 120
    },
    {
      "epoch": 0.12384851586489252,
      "grad_norm": 1.2467900514602661,
      "learning_rate": 2.4000000000000003e-07,
      "loss": 0.7683,
      "step": 121
    },
    {
      "epoch": 0.12487205731832139,
      "grad_norm": 0.49536195397377014,
      "learning_rate": 2.42e-07,
      "loss": 0.7626,
      "step": 122
    },
    {
      "epoch": 0.12589559877175024,
      "grad_norm": 1.1078747510910034,
      "learning_rate": 2.44e-07,
      "loss": 0.7679,
      "step": 123
    },
    {
      "epoch": 0.1269191402251791,
      "grad_norm": 0.5230876207351685,
      "learning_rate": 2.46e-07,
      "loss": 0.7579,
      "step": 124
    },
    {
      "epoch": 0.12794268167860798,
      "grad_norm": 0.7761886119842529,
      "learning_rate": 2.48e-07,
      "loss": 0.768,
      "step": 125
    },
    {
      "epoch": 0.12896622313203684,
      "grad_norm": 0.4926793575286865,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 0.7639,
      "step": 126
    },
    {
      "epoch": 0.1299897645854657,
      "grad_norm": 0.7263102531433105,
      "learning_rate": 2.5200000000000003e-07,
      "loss": 0.7619,
      "step": 127
    },
    {
      "epoch": 0.13101330603889458,
      "grad_norm": 0.846560537815094,
      "learning_rate": 2.54e-07,
      "loss": 0.7656,
      "step": 128
    },
    {
      "epoch": 0.13203684749232344,
      "grad_norm": 1.296027421951294,
      "learning_rate": 2.56e-07,
      "loss": 0.7713,
      "step": 129
    },
    {
      "epoch": 0.1330603889457523,
      "grad_norm": 1.0898621082305908,
      "learning_rate": 2.58e-07,
      "loss": 0.7644,
      "step": 130
    },
    {
      "epoch": 0.13408393039918118,
      "grad_norm": 0.9062381982803345,
      "learning_rate": 2.6e-07,
      "loss": 0.7606,
      "step": 131
    },
    {
      "epoch": 0.13510747185261002,
      "grad_norm": 0.9521744847297668,
      "learning_rate": 2.6200000000000004e-07,
      "loss": 0.7563,
      "step": 132
    },
    {
      "epoch": 0.13613101330603888,
      "grad_norm": 0.5530220866203308,
      "learning_rate": 2.6400000000000003e-07,
      "loss": 0.7647,
      "step": 133
    },
    {
      "epoch": 0.13715455475946775,
      "grad_norm": 0.6682366132736206,
      "learning_rate": 2.66e-07,
      "loss": 0.7605,
      "step": 134
    },
    {
      "epoch": 0.13817809621289662,
      "grad_norm": 0.647662341594696,
      "learning_rate": 2.68e-07,
      "loss": 0.7725,
      "step": 135
    },
    {
      "epoch": 0.13920163766632548,
      "grad_norm": 0.4923568665981293,
      "learning_rate": 2.7e-07,
      "loss": 0.7535,
      "step": 136
    },
    {
      "epoch": 0.14022517911975435,
      "grad_norm": 0.661147952079773,
      "learning_rate": 2.72e-07,
      "loss": 0.7634,
      "step": 137
    },
    {
      "epoch": 0.14124872057318322,
      "grad_norm": 0.5441955924034119,
      "learning_rate": 2.7400000000000004e-07,
      "loss": 0.7635,
      "step": 138
    },
    {
      "epoch": 0.14227226202661208,
      "grad_norm": 0.4902069568634033,
      "learning_rate": 2.7600000000000004e-07,
      "loss": 0.7602,
      "step": 139
    },
    {
      "epoch": 0.14329580348004095,
      "grad_norm": 0.9088981747627258,
      "learning_rate": 2.7800000000000003e-07,
      "loss": 0.7597,
      "step": 140
    },
    {
      "epoch": 0.14431934493346982,
      "grad_norm": 0.8669309020042419,
      "learning_rate": 2.8e-07,
      "loss": 0.763,
      "step": 141
    },
    {
      "epoch": 0.14534288638689866,
      "grad_norm": 1.1272106170654297,
      "learning_rate": 2.82e-07,
      "loss": 0.7685,
      "step": 142
    },
    {
      "epoch": 0.14636642784032752,
      "grad_norm": 0.9253846406936646,
      "learning_rate": 2.8400000000000005e-07,
      "loss": 0.761,
      "step": 143
    },
    {
      "epoch": 0.1473899692937564,
      "grad_norm": 0.6668679118156433,
      "learning_rate": 2.8600000000000005e-07,
      "loss": 0.7636,
      "step": 144
    },
    {
      "epoch": 0.14841351074718526,
      "grad_norm": 0.6984054446220398,
      "learning_rate": 2.8800000000000004e-07,
      "loss": 0.7639,
      "step": 145
    },
    {
      "epoch": 0.14943705220061412,
      "grad_norm": 0.5088668465614319,
      "learning_rate": 2.9000000000000003e-07,
      "loss": 0.7575,
      "step": 146
    },
    {
      "epoch": 0.150460593654043,
      "grad_norm": 0.8230961561203003,
      "learning_rate": 2.92e-07,
      "loss": 0.763,
      "step": 147
    },
    {
      "epoch": 0.15148413510747186,
      "grad_norm": 0.5158461332321167,
      "learning_rate": 2.94e-07,
      "loss": 0.7626,
      "step": 148
    },
    {
      "epoch": 0.15250767656090072,
      "grad_norm": 1.0442547798156738,
      "learning_rate": 2.9600000000000006e-07,
      "loss": 0.7615,
      "step": 149
    },
    {
      "epoch": 0.1535312180143296,
      "grad_norm": 0.5645190477371216,
      "learning_rate": 2.9800000000000005e-07,
      "loss": 0.7549,
      "step": 150
    },
    {
      "epoch": 0.15455475946775846,
      "grad_norm": 0.4772261083126068,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.7645,
      "step": 151
    },
    {
      "epoch": 0.1555783009211873,
      "grad_norm": 0.5313320159912109,
      "learning_rate": 3.0200000000000003e-07,
      "loss": 0.7589,
      "step": 152
    },
    {
      "epoch": 0.15660184237461616,
      "grad_norm": 0.5733660459518433,
      "learning_rate": 3.04e-07,
      "loss": 0.7556,
      "step": 153
    },
    {
      "epoch": 0.15762538382804503,
      "grad_norm": 0.7178833484649658,
      "learning_rate": 3.06e-07,
      "loss": 0.7575,
      "step": 154
    },
    {
      "epoch": 0.1586489252814739,
      "grad_norm": 0.4526512026786804,
      "learning_rate": 3.0800000000000006e-07,
      "loss": 0.7578,
      "step": 155
    },
    {
      "epoch": 0.15967246673490276,
      "grad_norm": 0.5467422008514404,
      "learning_rate": 3.1000000000000005e-07,
      "loss": 0.7574,
      "step": 156
    },
    {
      "epoch": 0.16069600818833163,
      "grad_norm": 0.6100950241088867,
      "learning_rate": 3.12e-07,
      "loss": 0.7575,
      "step": 157
    },
    {
      "epoch": 0.1617195496417605,
      "grad_norm": 0.44614189863204956,
      "learning_rate": 3.14e-07,
      "loss": 0.7581,
      "step": 158
    },
    {
      "epoch": 0.16274309109518936,
      "grad_norm": 0.5598356127738953,
      "learning_rate": 3.160000000000001e-07,
      "loss": 0.7617,
      "step": 159
    },
    {
      "epoch": 0.16376663254861823,
      "grad_norm": 0.5831120610237122,
      "learning_rate": 3.1800000000000007e-07,
      "loss": 0.7619,
      "step": 160
    },
    {
      "epoch": 0.1647901740020471,
      "grad_norm": 0.47710853815078735,
      "learning_rate": 3.2e-07,
      "loss": 0.7576,
      "step": 161
    },
    {
      "epoch": 0.16581371545547594,
      "grad_norm": 0.4452659487724304,
      "learning_rate": 3.22e-07,
      "loss": 0.763,
      "step": 162
    },
    {
      "epoch": 0.1668372569089048,
      "grad_norm": 0.5317380428314209,
      "learning_rate": 3.24e-07,
      "loss": 0.7594,
      "step": 163
    },
    {
      "epoch": 0.16786079836233367,
      "grad_norm": 0.5500309467315674,
      "learning_rate": 3.26e-07,
      "loss": 0.7523,
      "step": 164
    },
    {
      "epoch": 0.16888433981576254,
      "grad_norm": 0.5401707291603088,
      "learning_rate": 3.280000000000001e-07,
      "loss": 0.7635,
      "step": 165
    },
    {
      "epoch": 0.1699078812691914,
      "grad_norm": 0.6862873435020447,
      "learning_rate": 3.3e-07,
      "loss": 0.7547,
      "step": 166
    },
    {
      "epoch": 0.17093142272262027,
      "grad_norm": 0.4394344687461853,
      "learning_rate": 3.32e-07,
      "loss": 0.7542,
      "step": 167
    },
    {
      "epoch": 0.17195496417604914,
      "grad_norm": 0.46235671639442444,
      "learning_rate": 3.34e-07,
      "loss": 0.7493,
      "step": 168
    },
    {
      "epoch": 0.172978505629478,
      "grad_norm": 0.5838847756385803,
      "learning_rate": 3.36e-07,
      "loss": 0.7618,
      "step": 169
    },
    {
      "epoch": 0.17400204708290687,
      "grad_norm": 0.760307788848877,
      "learning_rate": 3.38e-07,
      "loss": 0.75,
      "step": 170
    },
    {
      "epoch": 0.1750255885363357,
      "grad_norm": 0.5808561444282532,
      "learning_rate": 3.4000000000000003e-07,
      "loss": 0.7603,
      "step": 171
    },
    {
      "epoch": 0.17604912998976457,
      "grad_norm": 0.7596063613891602,
      "learning_rate": 3.42e-07,
      "loss": 0.7549,
      "step": 172
    },
    {
      "epoch": 0.17707267144319344,
      "grad_norm": 0.6428470015525818,
      "learning_rate": 3.44e-07,
      "loss": 0.7548,
      "step": 173
    },
    {
      "epoch": 0.1780962128966223,
      "grad_norm": 0.47784337401390076,
      "learning_rate": 3.46e-07,
      "loss": 0.7647,
      "step": 174
    },
    {
      "epoch": 0.17911975435005117,
      "grad_norm": 0.42269936203956604,
      "learning_rate": 3.48e-07,
      "loss": 0.7577,
      "step": 175
    },
    {
      "epoch": 0.18014329580348004,
      "grad_norm": 0.6663862466812134,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 0.7593,
      "step": 176
    },
    {
      "epoch": 0.1811668372569089,
      "grad_norm": 0.443998783826828,
      "learning_rate": 3.5200000000000003e-07,
      "loss": 0.7524,
      "step": 177
    },
    {
      "epoch": 0.18219037871033777,
      "grad_norm": 0.5712008476257324,
      "learning_rate": 3.54e-07,
      "loss": 0.7624,
      "step": 178
    },
    {
      "epoch": 0.18321392016376664,
      "grad_norm": 0.5632140636444092,
      "learning_rate": 3.56e-07,
      "loss": 0.7631,
      "step": 179
    },
    {
      "epoch": 0.1842374616171955,
      "grad_norm": 0.5184634327888489,
      "learning_rate": 3.58e-07,
      "loss": 0.7572,
      "step": 180
    },
    {
      "epoch": 0.18526100307062435,
      "grad_norm": 0.5643100142478943,
      "learning_rate": 3.6e-07,
      "loss": 0.7588,
      "step": 181
    },
    {
      "epoch": 0.1862845445240532,
      "grad_norm": 0.4550904333591461,
      "learning_rate": 3.6200000000000004e-07,
      "loss": 0.7603,
      "step": 182
    },
    {
      "epoch": 0.18730808597748208,
      "grad_norm": 0.6727386713027954,
      "learning_rate": 3.6400000000000003e-07,
      "loss": 0.755,
      "step": 183
    },
    {
      "epoch": 0.18833162743091095,
      "grad_norm": 0.4629902243614197,
      "learning_rate": 3.66e-07,
      "loss": 0.764,
      "step": 184
    },
    {
      "epoch": 0.18935516888433981,
      "grad_norm": 0.5423149466514587,
      "learning_rate": 3.68e-07,
      "loss": 0.7583,
      "step": 185
    },
    {
      "epoch": 0.19037871033776868,
      "grad_norm": 0.5308339595794678,
      "learning_rate": 3.7e-07,
      "loss": 0.7535,
      "step": 186
    },
    {
      "epoch": 0.19140225179119755,
      "grad_norm": 0.497243732213974,
      "learning_rate": 3.72e-07,
      "loss": 0.7566,
      "step": 187
    },
    {
      "epoch": 0.19242579324462641,
      "grad_norm": 0.5698720216751099,
      "learning_rate": 3.7400000000000004e-07,
      "loss": 0.7576,
      "step": 188
    },
    {
      "epoch": 0.19344933469805528,
      "grad_norm": 0.546074628829956,
      "learning_rate": 3.7600000000000003e-07,
      "loss": 0.7543,
      "step": 189
    },
    {
      "epoch": 0.19447287615148415,
      "grad_norm": 0.6073132157325745,
      "learning_rate": 3.78e-07,
      "loss": 0.7473,
      "step": 190
    },
    {
      "epoch": 0.195496417604913,
      "grad_norm": 0.5039142370223999,
      "learning_rate": 3.8e-07,
      "loss": 0.7528,
      "step": 191
    },
    {
      "epoch": 0.19651995905834185,
      "grad_norm": 0.5228015780448914,
      "learning_rate": 3.82e-07,
      "loss": 0.7657,
      "step": 192
    },
    {
      "epoch": 0.19754350051177072,
      "grad_norm": 0.43683943152427673,
      "learning_rate": 3.84e-07,
      "loss": 0.7541,
      "step": 193
    },
    {
      "epoch": 0.1985670419651996,
      "grad_norm": 0.42550554871559143,
      "learning_rate": 3.8600000000000004e-07,
      "loss": 0.752,
      "step": 194
    },
    {
      "epoch": 0.19959058341862845,
      "grad_norm": 0.5053896307945251,
      "learning_rate": 3.8800000000000003e-07,
      "loss": 0.7558,
      "step": 195
    },
    {
      "epoch": 0.20061412487205732,
      "grad_norm": 0.6906818151473999,
      "learning_rate": 3.9e-07,
      "loss": 0.7576,
      "step": 196
    },
    {
      "epoch": 0.2016376663254862,
      "grad_norm": 0.46059173345565796,
      "learning_rate": 3.92e-07,
      "loss": 0.7549,
      "step": 197
    },
    {
      "epoch": 0.20266120777891505,
      "grad_norm": 0.4829753339290619,
      "learning_rate": 3.94e-07,
      "loss": 0.7594,
      "step": 198
    },
    {
      "epoch": 0.20368474923234392,
      "grad_norm": 0.504260241985321,
      "learning_rate": 3.9600000000000005e-07,
      "loss": 0.7564,
      "step": 199
    },
    {
      "epoch": 0.2047082906857728,
      "grad_norm": 0.6687684655189514,
      "learning_rate": 3.9800000000000004e-07,
      "loss": 0.7524,
      "step": 200
    },
    {
      "epoch": 0.20573183213920163,
      "grad_norm": 0.5243176817893982,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.7576,
      "step": 201
    },
    {
      "epoch": 0.2067553735926305,
      "grad_norm": 0.6751272082328796,
      "learning_rate": 4.02e-07,
      "loss": 0.7609,
      "step": 202
    },
    {
      "epoch": 0.20777891504605936,
      "grad_norm": 0.5937652587890625,
      "learning_rate": 4.04e-07,
      "loss": 0.7561,
      "step": 203
    },
    {
      "epoch": 0.20880245649948823,
      "grad_norm": 0.6328868269920349,
      "learning_rate": 4.06e-07,
      "loss": 0.7544,
      "step": 204
    },
    {
      "epoch": 0.2098259979529171,
      "grad_norm": 0.46846815943717957,
      "learning_rate": 4.0800000000000005e-07,
      "loss": 0.7582,
      "step": 205
    },
    {
      "epoch": 0.21084953940634596,
      "grad_norm": 0.4920537769794464,
      "learning_rate": 4.1000000000000004e-07,
      "loss": 0.7542,
      "step": 206
    },
    {
      "epoch": 0.21187308085977483,
      "grad_norm": 0.455229789018631,
      "learning_rate": 4.1200000000000004e-07,
      "loss": 0.7571,
      "step": 207
    },
    {
      "epoch": 0.2128966223132037,
      "grad_norm": 0.4706554114818573,
      "learning_rate": 4.1400000000000003e-07,
      "loss": 0.7583,
      "step": 208
    },
    {
      "epoch": 0.21392016376663256,
      "grad_norm": 0.5521472096443176,
      "learning_rate": 4.16e-07,
      "loss": 0.7564,
      "step": 209
    },
    {
      "epoch": 0.21494370522006143,
      "grad_norm": 0.45866256952285767,
      "learning_rate": 4.18e-07,
      "loss": 0.755,
      "step": 210
    },
    {
      "epoch": 0.21596724667349027,
      "grad_norm": 0.5188294649124146,
      "learning_rate": 4.2000000000000006e-07,
      "loss": 0.7544,
      "step": 211
    },
    {
      "epoch": 0.21699078812691913,
      "grad_norm": 0.413843035697937,
      "learning_rate": 4.2200000000000005e-07,
      "loss": 0.7508,
      "step": 212
    },
    {
      "epoch": 0.218014329580348,
      "grad_norm": 0.4665946066379547,
      "learning_rate": 4.2400000000000004e-07,
      "loss": 0.7557,
      "step": 213
    },
    {
      "epoch": 0.21903787103377687,
      "grad_norm": 0.5579046010971069,
      "learning_rate": 4.2600000000000003e-07,
      "loss": 0.7511,
      "step": 214
    },
    {
      "epoch": 0.22006141248720573,
      "grad_norm": 0.4209223687648773,
      "learning_rate": 4.28e-07,
      "loss": 0.7516,
      "step": 215
    },
    {
      "epoch": 0.2210849539406346,
      "grad_norm": 0.7076475024223328,
      "learning_rate": 4.3e-07,
      "loss": 0.7507,
      "step": 216
    },
    {
      "epoch": 0.22210849539406347,
      "grad_norm": 0.5781177282333374,
      "learning_rate": 4.3200000000000006e-07,
      "loss": 0.7475,
      "step": 217
    },
    {
      "epoch": 0.22313203684749233,
      "grad_norm": 0.8091248273849487,
      "learning_rate": 4.3400000000000005e-07,
      "loss": 0.7503,
      "step": 218
    },
    {
      "epoch": 0.2241555783009212,
      "grad_norm": 0.46331843733787537,
      "learning_rate": 4.3600000000000004e-07,
      "loss": 0.756,
      "step": 219
    },
    {
      "epoch": 0.22517911975435004,
      "grad_norm": 0.4318588674068451,
      "learning_rate": 4.3800000000000003e-07,
      "loss": 0.7534,
      "step": 220
    },
    {
      "epoch": 0.2262026612077789,
      "grad_norm": 0.5794275999069214,
      "learning_rate": 4.4e-07,
      "loss": 0.7563,
      "step": 221
    },
    {
      "epoch": 0.22722620266120777,
      "grad_norm": 0.5097821354866028,
      "learning_rate": 4.4200000000000007e-07,
      "loss": 0.7553,
      "step": 222
    },
    {
      "epoch": 0.22824974411463664,
      "grad_norm": 0.4925571084022522,
      "learning_rate": 4.4400000000000006e-07,
      "loss": 0.7549,
      "step": 223
    },
    {
      "epoch": 0.2292732855680655,
      "grad_norm": 0.5328956842422485,
      "learning_rate": 4.4600000000000005e-07,
      "loss": 0.757,
      "step": 224
    },
    {
      "epoch": 0.23029682702149437,
      "grad_norm": 0.4485833942890167,
      "learning_rate": 4.4800000000000004e-07,
      "loss": 0.7535,
      "step": 225
    },
    {
      "epoch": 0.23132036847492324,
      "grad_norm": 0.538770854473114,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 0.7551,
      "step": 226
    },
    {
      "epoch": 0.2323439099283521,
      "grad_norm": 0.5424289703369141,
      "learning_rate": 4.52e-07,
      "loss": 0.7528,
      "step": 227
    },
    {
      "epoch": 0.23336745138178097,
      "grad_norm": 0.5607970356941223,
      "learning_rate": 4.5400000000000007e-07,
      "loss": 0.7534,
      "step": 228
    },
    {
      "epoch": 0.23439099283520984,
      "grad_norm": 0.5806226134300232,
      "learning_rate": 4.5600000000000006e-07,
      "loss": 0.7516,
      "step": 229
    },
    {
      "epoch": 0.23541453428863868,
      "grad_norm": 0.47338593006134033,
      "learning_rate": 4.5800000000000005e-07,
      "loss": 0.75,
      "step": 230
    },
    {
      "epoch": 0.23643807574206754,
      "grad_norm": 0.805225670337677,
      "learning_rate": 4.6000000000000004e-07,
      "loss": 0.7498,
      "step": 231
    },
    {
      "epoch": 0.2374616171954964,
      "grad_norm": 0.5711566209793091,
      "learning_rate": 4.6200000000000003e-07,
      "loss": 0.7527,
      "step": 232
    },
    {
      "epoch": 0.23848515864892528,
      "grad_norm": 0.4319440722465515,
      "learning_rate": 4.64e-07,
      "loss": 0.7493,
      "step": 233
    },
    {
      "epoch": 0.23950870010235414,
      "grad_norm": 0.49590882658958435,
      "learning_rate": 4.6600000000000007e-07,
      "loss": 0.752,
      "step": 234
    },
    {
      "epoch": 0.240532241555783,
      "grad_norm": 0.6124209761619568,
      "learning_rate": 4.6800000000000006e-07,
      "loss": 0.7517,
      "step": 235
    },
    {
      "epoch": 0.24155578300921188,
      "grad_norm": 0.4623505771160126,
      "learning_rate": 4.7000000000000005e-07,
      "loss": 0.7558,
      "step": 236
    },
    {
      "epoch": 0.24257932446264074,
      "grad_norm": 0.43490421772003174,
      "learning_rate": 4.7200000000000004e-07,
      "loss": 0.754,
      "step": 237
    },
    {
      "epoch": 0.2436028659160696,
      "grad_norm": 0.41201770305633545,
      "learning_rate": 4.7400000000000004e-07,
      "loss": 0.7554,
      "step": 238
    },
    {
      "epoch": 0.24462640736949848,
      "grad_norm": 0.5332440137863159,
      "learning_rate": 4.760000000000001e-07,
      "loss": 0.7523,
      "step": 239
    },
    {
      "epoch": 0.24564994882292732,
      "grad_norm": 0.45751631259918213,
      "learning_rate": 4.78e-07,
      "loss": 0.7501,
      "step": 240
    },
    {
      "epoch": 0.24667349027635618,
      "grad_norm": 0.46563875675201416,
      "learning_rate": 4.800000000000001e-07,
      "loss": 0.7475,
      "step": 241
    },
    {
      "epoch": 0.24769703172978505,
      "grad_norm": 0.4648246765136719,
      "learning_rate": 4.82e-07,
      "loss": 0.7607,
      "step": 242
    },
    {
      "epoch": 0.24872057318321392,
      "grad_norm": 0.42473065853118896,
      "learning_rate": 4.84e-07,
      "loss": 0.7521,
      "step": 243
    },
    {
      "epoch": 0.24974411463664278,
      "grad_norm": 0.4116007387638092,
      "learning_rate": 4.86e-07,
      "loss": 0.753,
      "step": 244
    },
    {
      "epoch": 0.2507676560900716,
      "grad_norm": 0.4429609477519989,
      "learning_rate": 4.88e-07,
      "loss": 0.7513,
      "step": 245
    },
    {
      "epoch": 0.2517911975435005,
      "grad_norm": 0.40569669008255005,
      "learning_rate": 4.900000000000001e-07,
      "loss": 0.7466,
      "step": 246
    },
    {
      "epoch": 0.25281473899692936,
      "grad_norm": 0.6898592114448547,
      "learning_rate": 4.92e-07,
      "loss": 0.7488,
      "step": 247
    },
    {
      "epoch": 0.2538382804503582,
      "grad_norm": 0.5965420603752136,
      "learning_rate": 4.940000000000001e-07,
      "loss": 0.7496,
      "step": 248
    },
    {
      "epoch": 0.2548618219037871,
      "grad_norm": 0.4469277858734131,
      "learning_rate": 4.96e-07,
      "loss": 0.7554,
      "step": 249
    },
    {
      "epoch": 0.25588536335721596,
      "grad_norm": 0.5688977837562561,
      "learning_rate": 4.98e-07,
      "loss": 0.761,
      "step": 250
    }
  ],
  "logging_steps": 1,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 103,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1024,
  "trial_name": null,
  "trial_params": null
}