{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.984,
  "eval_steps": 500,
  "global_step": 186,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 5.864202829388014,
      "learning_rate": 4.210526315789474e-06,
      "loss": 0.7913,
      "step": 1
    },
    {
      "epoch": 0.032,
      "grad_norm": 5.872648147144048,
      "learning_rate": 8.421052631578948e-06,
      "loss": 0.7915,
      "step": 2
    },
    {
      "epoch": 0.048,
      "grad_norm": 4.448830758701059,
      "learning_rate": 1.263157894736842e-05,
      "loss": 0.7505,
      "step": 3
    },
    {
      "epoch": 0.064,
      "grad_norm": 2.157234346723898,
      "learning_rate": 1.6842105263157896e-05,
      "loss": 0.6908,
      "step": 4
    },
    {
      "epoch": 0.08,
      "grad_norm": 5.8390869826392064,
      "learning_rate": 2.105263157894737e-05,
      "loss": 0.7192,
      "step": 5
    },
    {
      "epoch": 0.096,
      "grad_norm": 10.449669701716074,
      "learning_rate": 2.526315789473684e-05,
      "loss": 0.7618,
      "step": 6
    },
    {
      "epoch": 0.112,
      "grad_norm": 7.154448692780618,
      "learning_rate": 2.9473684210526317e-05,
      "loss": 0.7162,
      "step": 7
    },
    {
      "epoch": 0.128,
      "grad_norm": 4.552028823354591,
      "learning_rate": 3.368421052631579e-05,
      "loss": 0.6638,
      "step": 8
    },
    {
      "epoch": 0.144,
      "grad_norm": 2.957730965082692,
      "learning_rate": 3.789473684210526e-05,
      "loss": 0.6244,
      "step": 9
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.1615064746513872,
      "learning_rate": 4.210526315789474e-05,
      "loss": 0.6009,
      "step": 10
    },
    {
      "epoch": 0.176,
      "grad_norm": 1.6417146425469031,
      "learning_rate": 4.6315789473684214e-05,
      "loss": 0.5816,
      "step": 11
    },
    {
      "epoch": 0.192,
      "grad_norm": 10.412899659562997,
      "learning_rate": 5.052631578947368e-05,
      "loss": 0.6001,
      "step": 12
    },
    {
      "epoch": 0.208,
      "grad_norm": 2.614556696999853,
      "learning_rate": 5.4736842105263165e-05,
      "loss": 0.5923,
      "step": 13
    },
    {
      "epoch": 0.224,
      "grad_norm": 2.5343953646048223,
      "learning_rate": 5.8947368421052634e-05,
      "loss": 0.5706,
      "step": 14
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.7460829243404183,
      "learning_rate": 6.315789473684212e-05,
      "loss": 0.5565,
      "step": 15
    },
    {
      "epoch": 0.256,
      "grad_norm": 10.716457870383207,
      "learning_rate": 6.736842105263159e-05,
      "loss": 0.5475,
      "step": 16
    },
    {
      "epoch": 0.272,
      "grad_norm": 3.630113840118509,
      "learning_rate": 7.157894736842105e-05,
      "loss": 0.6018,
      "step": 17
    },
    {
      "epoch": 0.288,
      "grad_norm": 1.658431334016499,
      "learning_rate": 7.578947368421052e-05,
      "loss": 0.5425,
      "step": 18
    },
    {
      "epoch": 0.304,
      "grad_norm": 2.6385079779437928,
      "learning_rate": 8e-05,
      "loss": 0.554,
      "step": 19
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.4726162725880063,
      "learning_rate": 7.999292243297167e-05,
      "loss": 0.5573,
      "step": 20
    },
    {
      "epoch": 0.336,
      "grad_norm": 1.3862293955306393,
      "learning_rate": 7.997169223648443e-05,
      "loss": 0.5248,
      "step": 21
    },
    {
      "epoch": 0.352,
      "grad_norm": 2.1185258579948756,
      "learning_rate": 7.993631692344518e-05,
      "loss": 0.5208,
      "step": 22
    },
    {
      "epoch": 0.368,
      "grad_norm": 1.379815852064984,
      "learning_rate": 7.988680901241142e-05,
      "loss": 0.5215,
      "step": 23
    },
    {
      "epoch": 0.384,
      "grad_norm": 1.0692164193091471,
      "learning_rate": 7.982318602316107e-05,
      "loss": 0.5076,
      "step": 24
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.363683637565687,
      "learning_rate": 7.974547047049269e-05,
      "loss": 0.5094,
      "step": 25
    },
    {
      "epoch": 0.416,
      "grad_norm": 1.166001995295674,
      "learning_rate": 7.965368985625792e-05,
      "loss": 0.5012,
      "step": 26
    },
    {
      "epoch": 0.432,
      "grad_norm": 1.0753197080774943,
      "learning_rate": 7.954787665962922e-05,
      "loss": 0.5007,
      "step": 27
    },
    {
      "epoch": 0.448,
      "grad_norm": 1.4284904204862443,
      "learning_rate": 7.94280683256062e-05,
      "loss": 0.4822,
      "step": 28
    },
    {
      "epoch": 0.464,
      "grad_norm": 1.1277979040005555,
      "learning_rate": 7.929430725176456e-05,
      "loss": 0.4889,
      "step": 29
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.0432850580644155,
      "learning_rate": 7.91466407732526e-05,
      "loss": 0.4762,
      "step": 30
    },
    {
      "epoch": 0.496,
      "grad_norm": 1.1070887307945323,
      "learning_rate": 7.898512114604028e-05,
      "loss": 0.4726,
      "step": 31
    },
    {
      "epoch": 0.512,
      "grad_norm": 2.030373295391588,
      "learning_rate": 7.880980552842705e-05,
      "loss": 0.4785,
      "step": 32
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.7829256797346418,
      "learning_rate": 7.862075596081459e-05,
      "loss": 0.4755,
      "step": 33
    },
    {
      "epoch": 0.544,
      "grad_norm": 2.014060782852139,
      "learning_rate": 7.841803934375226e-05,
      "loss": 0.473,
      "step": 34
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.078945846658623,
      "learning_rate": 7.820172741426231e-05,
      "loss": 0.4751,
      "step": 35
    },
    {
      "epoch": 0.576,
      "grad_norm": 1.8168080297827258,
      "learning_rate": 7.79718967204537e-05,
      "loss": 0.4702,
      "step": 36
    },
    {
      "epoch": 0.592,
      "grad_norm": 1.4755432053603468,
      "learning_rate": 7.772862859443352e-05,
      "loss": 0.4747,
      "step": 37
    },
    {
      "epoch": 0.608,
      "grad_norm": 1.2588926553170865,
      "learning_rate": 7.747200912352512e-05,
      "loss": 0.4649,
      "step": 38
    },
    {
      "epoch": 0.624,
      "grad_norm": 1.1548094943568747,
      "learning_rate": 7.72021291198038e-05,
      "loss": 0.4545,
      "step": 39
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.9865958679876434,
      "learning_rate": 7.691908408796038e-05,
      "loss": 0.4614,
      "step": 40
    },
    {
      "epoch": 0.656,
      "grad_norm": 1.2434531732087855,
      "learning_rate": 7.66229741915041e-05,
      "loss": 0.4573,
      "step": 41
    },
    {
      "epoch": 0.672,
      "grad_norm": 1.0543164731703125,
      "learning_rate": 7.631390421731695e-05,
      "loss": 0.4548,
      "step": 42
    },
    {
      "epoch": 0.688,
      "grad_norm": 1.5040641587819343,
      "learning_rate": 7.599198353857187e-05,
      "loss": 0.4531,
      "step": 43
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.8330593510457461,
      "learning_rate": 7.565732607602794e-05,
      "loss": 0.4525,
      "step": 44
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.747249068381139,
      "learning_rate": 7.53100502577163e-05,
      "loss": 0.4613,
      "step": 45
    },
    {
      "epoch": 0.736,
      "grad_norm": 1.0849239550821672,
      "learning_rate": 7.495027897703102e-05,
      "loss": 0.4476,
      "step": 46
    },
    {
      "epoch": 0.752,
      "grad_norm": 2.2810114466095355,
      "learning_rate": 7.457813954923979e-05,
      "loss": 0.456,
      "step": 47
    },
    {
      "epoch": 0.768,
      "grad_norm": 2.1542133598504853,
      "learning_rate": 7.419376366642982e-05,
      "loss": 0.4602,
      "step": 48
    },
    {
      "epoch": 0.784,
      "grad_norm": 1.2484775835760495,
      "learning_rate": 7.379728735090483e-05,
      "loss": 0.4489,
      "step": 49
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.3318281738925397,
      "learning_rate": 7.338885090704975e-05,
      "loss": 0.4426,
      "step": 50
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.9892797570742369,
      "learning_rate": 7.296859887167997e-05,
      "loss": 0.4452,
      "step": 51
    },
    {
      "epoch": 0.832,
      "grad_norm": 1.0679050135993293,
      "learning_rate": 7.253667996289298e-05,
      "loss": 0.4458,
      "step": 52
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.8781093256497718,
      "learning_rate": 7.209324702744015e-05,
      "loss": 0.4396,
      "step": 53
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.7875697278327576,
      "learning_rate": 7.163845698663763e-05,
      "loss": 0.4287,
      "step": 54
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.6302650996963544,
      "learning_rate": 7.117247078083531e-05,
      "loss": 0.4327,
      "step": 55
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.7388582241554006,
      "learning_rate": 7.069545331246348e-05,
      "loss": 0.4245,
      "step": 56
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.5712302618683613,
      "learning_rate": 7.020757338767745e-05,
      "loss": 0.429,
      "step": 57
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.5166798385795193,
      "learning_rate": 6.970900365662068e-05,
      "loss": 0.4274,
      "step": 58
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.6460391947769224,
      "learning_rate": 6.919992055232768e-05,
      "loss": 0.4349,
      "step": 59
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.79433873003954,
      "learning_rate": 6.868050422828812e-05,
      "loss": 0.4277,
      "step": 60
    },
    {
      "epoch": 0.976,
      "grad_norm": 0.6213339825027192,
      "learning_rate": 6.815093849469446e-05,
      "loss": 0.4296,
      "step": 61
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.743688598894428,
      "learning_rate": 6.761141075339546e-05,
      "loss": 0.4256,
      "step": 62
    },
    {
      "epoch": 1.012,
      "grad_norm": 1.4189759219760636,
      "learning_rate": 6.706211193157875e-05,
      "loss": 0.7285,
      "step": 63
    },
    {
      "epoch": 1.028,
      "grad_norm": 1.7305791668754007,
      "learning_rate": 6.650323641420585e-05,
      "loss": 0.4151,
      "step": 64
    },
    {
      "epoch": 1.044,
      "grad_norm": 0.5488342270834748,
      "learning_rate": 6.593498197522348e-05,
      "loss": 0.4082,
      "step": 65
    },
    {
      "epoch": 1.06,
      "grad_norm": 1.407405101124588,
      "learning_rate": 6.535754970757567e-05,
      "loss": 0.4055,
      "step": 66
    },
    {
      "epoch": 1.076,
      "grad_norm": 1.1715312695903517,
      "learning_rate": 6.477114395204142e-05,
      "loss": 0.4079,
      "step": 67
    },
    {
      "epoch": 1.092,
      "grad_norm": 0.7475361072820644,
      "learning_rate": 6.417597222492268e-05,
      "loss": 0.4013,
      "step": 68
    },
    {
      "epoch": 1.108,
      "grad_norm": 0.8282992327933414,
      "learning_rate": 6.35722451446091e-05,
      "loss": 0.4065,
      "step": 69
    },
    {
      "epoch": 1.124,
      "grad_norm": 1.330922993760041,
      "learning_rate": 6.296017635704455e-05,
      "loss": 0.3964,
      "step": 70
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 0.6478437984552811,
      "learning_rate": 6.233998246012253e-05,
      "loss": 0.4053,
      "step": 71
    },
    {
      "epoch": 1.156,
      "grad_norm": 0.7988653435688005,
      "learning_rate": 6.171188292703685e-05,
      "loss": 0.3926,
      "step": 72
    },
    {
      "epoch": 1.172,
      "grad_norm": 1.0972598731114915,
      "learning_rate": 6.10761000286148e-05,
      "loss": 0.3957,
      "step": 73
    },
    {
      "epoch": 1.188,
      "grad_norm": 0.862697446731696,
      "learning_rate": 6.043285875466032e-05,
      "loss": 0.401,
      "step": 74
    },
    {
      "epoch": 1.204,
      "grad_norm": 0.5416451681744806,
      "learning_rate": 5.978238673433502e-05,
      "loss": 0.4009,
      "step": 75
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.7072795192209076,
      "learning_rate": 5.912491415560507e-05,
      "loss": 0.3976,
      "step": 76
    },
    {
      "epoch": 1.236,
      "grad_norm": 0.8609532314533869,
      "learning_rate": 5.8460673683782756e-05,
      "loss": 0.3983,
      "step": 77
    },
    {
      "epoch": 1.252,
      "grad_norm": 0.7434541182762888,
      "learning_rate": 5.7789900379191186e-05,
      "loss": 0.3989,
      "step": 78
    },
    {
      "epoch": 1.268,
      "grad_norm": 0.4898816861440509,
      "learning_rate": 5.7112831613981554e-05,
      "loss": 0.3995,
      "step": 79
    },
    {
      "epoch": 1.284,
      "grad_norm": 0.6047589566419349,
      "learning_rate": 5.64297069881323e-05,
      "loss": 0.3968,
      "step": 80
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.5063824542389925,
      "learning_rate": 5.574076824465983e-05,
      "loss": 0.3963,
      "step": 81
    },
    {
      "epoch": 1.316,
      "grad_norm": 0.4743504375272986,
      "learning_rate": 5.5046259184070894e-05,
      "loss": 0.3985,
      "step": 82
    },
    {
      "epoch": 1.332,
      "grad_norm": 0.37959186577275045,
      "learning_rate": 5.4346425578086915e-05,
      "loss": 0.3893,
      "step": 83
    },
    {
      "epoch": 1.3479999999999999,
      "grad_norm": 0.36257857231635615,
      "learning_rate": 5.364151508267064e-05,
      "loss": 0.3927,
      "step": 84
    },
    {
      "epoch": 1.3639999999999999,
      "grad_norm": 0.49654142820117314,
      "learning_rate": 5.293177715038608e-05,
      "loss": 0.3913,
      "step": 85
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.38761620057730195,
      "learning_rate": 5.2217462942122664e-05,
      "loss": 0.3893,
      "step": 86
    },
    {
      "epoch": 1.396,
      "grad_norm": 0.39789159963838117,
      "learning_rate": 5.1498825238214786e-05,
      "loss": 0.3903,
      "step": 87
    },
    {
      "epoch": 1.412,
      "grad_norm": 0.4117452965109853,
      "learning_rate": 5.077611834898839e-05,
      "loss": 0.3974,
      "step": 88
    },
    {
      "epoch": 1.428,
      "grad_norm": 0.4695252822255102,
      "learning_rate": 5.004959802476596e-05,
      "loss": 0.3912,
      "step": 89
    },
    {
      "epoch": 1.444,
      "grad_norm": 0.37317710408872046,
      "learning_rate": 4.931952136536213e-05,
      "loss": 0.3898,
      "step": 90
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.3897759717249992,
      "learning_rate": 4.858614672910155e-05,
      "loss": 0.3902,
      "step": 91
    },
    {
      "epoch": 1.476,
      "grad_norm": 0.32177578059016193,
      "learning_rate": 4.784973364139144e-05,
      "loss": 0.389,
      "step": 92
    },
    {
      "epoch": 1.492,
      "grad_norm": 0.3153711132788146,
      "learning_rate": 4.711054270288125e-05,
      "loss": 0.3923,
      "step": 93
    },
    {
      "epoch": 1.508,
      "grad_norm": 0.3481604699048208,
      "learning_rate": 4.6368835497241704e-05,
      "loss": 0.3915,
      "step": 94
    },
    {
      "epoch": 1.524,
      "grad_norm": 0.2840999008054265,
      "learning_rate": 4.562487449859594e-05,
      "loss": 0.3868,
      "step": 95
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.23128563796625934,
      "learning_rate": 4.4878922978635686e-05,
      "loss": 0.3901,
      "step": 96
    },
    {
      "epoch": 1.556,
      "grad_norm": 0.31644599189945527,
      "learning_rate": 4.4131244913455064e-05,
      "loss": 0.3918,
      "step": 97
    },
    {
      "epoch": 1.572,
      "grad_norm": 0.27458323292125525,
      "learning_rate": 4.3382104890135164e-05,
      "loss": 0.3857,
      "step": 98
    },
    {
      "epoch": 1.588,
      "grad_norm": 0.2671626515653335,
      "learning_rate": 4.263176801311243e-05,
      "loss": 0.3872,
      "step": 99
    },
    {
      "epoch": 1.604,
      "grad_norm": 0.2634055661736952,
      "learning_rate": 4.1880499810363906e-05,
      "loss": 0.386,
      "step": 100
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.31168502886080895,
      "learning_rate": 4.112856613944265e-05,
      "loss": 0.3858,
      "step": 101
    },
    {
      "epoch": 1.6360000000000001,
      "grad_norm": 0.28772714634529506,
      "learning_rate": 4.03762330933965e-05,
      "loss": 0.3867,
      "step": 102
    },
    {
      "epoch": 1.6520000000000001,
      "grad_norm": 0.22254705016216964,
      "learning_rate": 3.962376690660352e-05,
      "loss": 0.3818,
      "step": 103
    },
    {
      "epoch": 1.6680000000000001,
      "grad_norm": 0.2510682576803876,
      "learning_rate": 3.8871433860557365e-05,
      "loss": 0.3856,
      "step": 104
    },
    {
      "epoch": 1.6840000000000002,
      "grad_norm": 0.31237598815995105,
      "learning_rate": 3.811950018963611e-05,
      "loss": 0.389,
      "step": 105
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.23942776865557513,
      "learning_rate": 3.736823198688758e-05,
      "loss": 0.3876,
      "step": 106
    },
    {
      "epoch": 1.716,
      "grad_norm": 0.27005716759409326,
      "learning_rate": 3.6617895109864836e-05,
      "loss": 0.3849,
      "step": 107
    },
    {
      "epoch": 1.732,
      "grad_norm": 0.3015434191544345,
      "learning_rate": 3.586875508654495e-05,
      "loss": 0.3881,
      "step": 108
    },
    {
      "epoch": 1.748,
      "grad_norm": 0.19166539999174675,
      "learning_rate": 3.512107702136432e-05,
      "loss": 0.3882,
      "step": 109
    },
    {
      "epoch": 1.764,
      "grad_norm": 0.21230418165639647,
      "learning_rate": 3.437512550140408e-05,
      "loss": 0.3796,
      "step": 110
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.25002720097786907,
      "learning_rate": 3.363116450275831e-05,
      "loss": 0.3807,
      "step": 111
    },
    {
      "epoch": 1.796,
      "grad_norm": 0.20135016309524,
      "learning_rate": 3.2889457297118754e-05,
      "loss": 0.3898,
      "step": 112
    },
    {
      "epoch": 1.812,
      "grad_norm": 0.18671037288899267,
      "learning_rate": 3.2150266358608566e-05,
      "loss": 0.3829,
      "step": 113
    },
    {
      "epoch": 1.8279999999999998,
      "grad_norm": 0.20612969013889648,
      "learning_rate": 3.1413853270898456e-05,
      "loss": 0.3831,
      "step": 114
    },
    {
      "epoch": 1.8439999999999999,
      "grad_norm": 0.1695900113836421,
      "learning_rate": 3.0680478634637876e-05,
      "loss": 0.3797,
      "step": 115
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 0.16849043151908083,
      "learning_rate": 2.9950401975234053e-05,
      "loss": 0.3784,
      "step": 116
    },
    {
      "epoch": 1.876,
      "grad_norm": 0.16791616048036132,
      "learning_rate": 2.922388165101164e-05,
      "loss": 0.38,
      "step": 117
    },
    {
      "epoch": 1.892,
      "grad_norm": 0.1867473422097629,
      "learning_rate": 2.8501174761785227e-05,
      "loss": 0.383,
      "step": 118
    },
    {
      "epoch": 1.908,
      "grad_norm": 0.16677580216318222,
      "learning_rate": 2.7782537057877353e-05,
      "loss": 0.3803,
      "step": 119
    },
    {
      "epoch": 1.924,
      "grad_norm": 0.1905216502882764,
      "learning_rate": 2.7068222849613924e-05,
      "loss": 0.3828,
      "step": 120
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.16487804894112876,
      "learning_rate": 2.635848491732936e-05,
      "loss": 0.3807,
      "step": 121
    },
    {
      "epoch": 1.956,
      "grad_norm": 0.22163492772363522,
      "learning_rate": 2.56535744219131e-05,
      "loss": 0.3762,
      "step": 122
    },
    {
      "epoch": 1.972,
      "grad_norm": 0.16836461157466331,
      "learning_rate": 2.4953740815929112e-05,
      "loss": 0.3779,
      "step": 123
    },
    {
      "epoch": 1.988,
      "grad_norm": 0.22449736267068884,
      "learning_rate": 2.4259231755340185e-05,
      "loss": 0.3772,
      "step": 124
    },
    {
      "epoch": 2.008,
      "grad_norm": 0.29425089250674447,
      "learning_rate": 2.3570293011867705e-05,
      "loss": 0.6469,
      "step": 125
    },
    {
      "epoch": 2.024,
      "grad_norm": 0.20003275394226644,
      "learning_rate": 2.2887168386018446e-05,
      "loss": 0.3551,
      "step": 126
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.19001926769088684,
      "learning_rate": 2.221009962080883e-05,
      "loss": 0.3608,
      "step": 127
    },
    {
      "epoch": 2.056,
      "grad_norm": 0.18422402408869987,
      "learning_rate": 2.153932631621725e-05,
      "loss": 0.3618,
      "step": 128
    },
    {
      "epoch": 2.072,
      "grad_norm": 0.1729886118160922,
      "learning_rate": 2.0875085844394933e-05,
      "loss": 0.36,
      "step": 129
    },
    {
      "epoch": 2.088,
      "grad_norm": 0.1851607233564855,
      "learning_rate": 2.021761326566499e-05,
      "loss": 0.366,
      "step": 130
    },
    {
      "epoch": 2.104,
      "grad_norm": 0.19992169897269865,
      "learning_rate": 1.9567141245339695e-05,
      "loss": 0.3577,
      "step": 131
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.16441974122210465,
      "learning_rate": 1.8923899971385215e-05,
      "loss": 0.3628,
      "step": 132
    },
    {
      "epoch": 2.136,
      "grad_norm": 0.16834557329643168,
      "learning_rate": 1.828811707296315e-05,
      "loss": 0.3596,
      "step": 133
    },
    {
      "epoch": 2.152,
      "grad_norm": 0.1662004780531857,
      "learning_rate": 1.766001753987748e-05,
      "loss": 0.3576,
      "step": 134
    },
    {
      "epoch": 2.168,
      "grad_norm": 0.16194237818485746,
      "learning_rate": 1.7039823642955458e-05,
      "loss": 0.3625,
      "step": 135
    },
    {
      "epoch": 2.184,
      "grad_norm": 0.15877853767585423,
      "learning_rate": 1.642775485539092e-05,
      "loss": 0.3579,
      "step": 136
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.17226140130729017,
      "learning_rate": 1.5824027775077322e-05,
      "loss": 0.3584,
      "step": 137
    },
    {
      "epoch": 2.216,
      "grad_norm": 0.1824547271309309,
      "learning_rate": 1.5228856047958603e-05,
      "loss": 0.359,
      "step": 138
    },
    {
      "epoch": 2.232,
      "grad_norm": 0.14742431009044868,
      "learning_rate": 1.4642450292424326e-05,
      "loss": 0.3659,
      "step": 139
    },
    {
      "epoch": 2.248,
      "grad_norm": 0.18857304621628812,
      "learning_rate": 1.4065018024776533e-05,
      "loss": 0.3572,
      "step": 140
    },
    {
      "epoch": 2.2640000000000002,
      "grad_norm": 0.16549233991248866,
      "learning_rate": 1.3496763585794166e-05,
      "loss": 0.365,
      "step": 141
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.14586726135391748,
      "learning_rate": 1.2937888068421254e-05,
      "loss": 0.3513,
      "step": 142
    },
    {
      "epoch": 2.296,
      "grad_norm": 0.17868762335531224,
      "learning_rate": 1.238858924660456e-05,
      "loss": 0.3515,
      "step": 143
    },
    {
      "epoch": 2.312,
      "grad_norm": 0.1231709928263777,
      "learning_rate": 1.184906150530555e-05,
      "loss": 0.3576,
      "step": 144
    },
    {
      "epoch": 2.328,
      "grad_norm": 0.11583163070452697,
      "learning_rate": 1.1319495771711884e-05,
      "loss": 0.3611,
      "step": 145
    },
    {
      "epoch": 2.344,
      "grad_norm": 0.16102203297114398,
      "learning_rate": 1.0800079447672318e-05,
      "loss": 0.3584,
      "step": 146
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.12131478717359077,
      "learning_rate": 1.0290996343379316e-05,
      "loss": 0.3596,
      "step": 147
    },
    {
      "epoch": 2.376,
      "grad_norm": 0.11478795957786868,
      "learning_rate": 9.79242661232256e-06,
      "loss": 0.3631,
      "step": 148
    },
    {
      "epoch": 2.392,
      "grad_norm": 0.13320908433173181,
      "learning_rate": 9.304546687536523e-06,
      "loss": 0.3597,
      "step": 149
    },
    {
      "epoch": 2.408,
      "grad_norm": 0.12093270155957273,
      "learning_rate": 8.827529219164704e-06,
      "loss": 0.3593,
      "step": 150
    },
    {
      "epoch": 2.424,
      "grad_norm": 0.1041619528441601,
      "learning_rate": 8.361543013362384e-06,
      "loss": 0.3578,
      "step": 151
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.12990258536636803,
      "learning_rate": 7.90675297255986e-06,
      "loss": 0.3564,
      "step": 152
    },
    {
      "epoch": 2.456,
      "grad_norm": 0.13418689782006024,
      "learning_rate": 7.463320037107018e-06,
      "loss": 0.3555,
      "step": 153
    },
    {
      "epoch": 2.472,
      "grad_norm": 0.1033047329894609,
      "learning_rate": 7.031401128320019e-06,
      "loss": 0.3618,
      "step": 154
    },
    {
      "epoch": 2.488,
      "grad_norm": 0.11229925264342833,
      "learning_rate": 6.61114909295026e-06,
      "loss": 0.3623,
      "step": 155
    },
    {
      "epoch": 2.504,
      "grad_norm": 0.11335812258557738,
      "learning_rate": 6.202712649095177e-06,
      "loss": 0.3576,
      "step": 156
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.10858403644770878,
      "learning_rate": 5.806236333570203e-06,
      "loss": 0.3618,
      "step": 157
    },
    {
      "epoch": 2.536,
      "grad_norm": 0.09670915625383128,
      "learning_rate": 5.421860450760226e-06,
      "loss": 0.3573,
      "step": 158
    },
    {
      "epoch": 2.552,
      "grad_norm": 0.09519799807892575,
      "learning_rate": 5.04972102296899e-06,
      "loss": 0.3555,
      "step": 159
    },
    {
      "epoch": 2.568,
      "grad_norm": 0.09889559191933857,
      "learning_rate": 4.6899497422837035e-06,
      "loss": 0.3596,
      "step": 160
    },
    {
      "epoch": 2.584,
      "grad_norm": 0.09837408849770972,
      "learning_rate": 4.34267392397206e-06,
      "loss": 0.3558,
      "step": 161
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.08865406915783132,
      "learning_rate": 4.0080164614281395e-06,
      "loss": 0.3534,
      "step": 162
    },
    {
      "epoch": 2.616,
      "grad_norm": 0.09991828929700397,
      "learning_rate": 3.6860957826830545e-06,
      "loss": 0.3596,
      "step": 163
    },
    {
      "epoch": 2.632,
      "grad_norm": 0.10236445503716023,
      "learning_rate": 3.377025808495913e-06,
      "loss": 0.3552,
      "step": 164
    },
    {
      "epoch": 2.648,
      "grad_norm": 0.08439473747294635,
      "learning_rate": 3.080915912039628e-06,
      "loss": 0.3581,
      "step": 165
    },
    {
      "epoch": 2.664,
      "grad_norm": 0.08954435303382993,
      "learning_rate": 2.797870880196203e-06,
      "loss": 0.3547,
      "step": 166
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.09218355997294332,
      "learning_rate": 2.527990876474893e-06,
      "loss": 0.3601,
      "step": 167
    },
    {
      "epoch": 2.6959999999999997,
      "grad_norm": 0.08584647995949408,
      "learning_rate": 2.271371405566485e-06,
      "loss": 0.3545,
      "step": 168
    },
    {
      "epoch": 2.7119999999999997,
      "grad_norm": 0.08273734564915391,
      "learning_rate": 2.0281032795462963e-06,
      "loss": 0.3553,
      "step": 169
    },
    {
      "epoch": 2.7279999999999998,
      "grad_norm": 0.08006013416615393,
      "learning_rate": 1.7982725857377036e-06,
      "loss": 0.3575,
      "step": 170
    },
    {
      "epoch": 2.7439999999999998,
      "grad_norm": 0.08474559651311726,
      "learning_rate": 1.5819606562477475e-06,
      "loss": 0.3552,
      "step": 171
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.08815499678673341,
      "learning_rate": 1.3792440391854122e-06,
      "loss": 0.3559,
      "step": 172
    },
    {
      "epoch": 2.776,
      "grad_norm": 0.08633285045942303,
      "learning_rate": 1.190194471572963e-06,
      "loss": 0.3593,
      "step": 173
    },
    {
      "epoch": 2.792,
      "grad_norm": 0.0802807002308741,
      "learning_rate": 1.0148788539597176e-06,
      "loss": 0.3621,
      "step": 174
    },
    {
      "epoch": 2.808,
      "grad_norm": 0.08660360505575548,
      "learning_rate": 8.533592267474166e-07,
      "loss": 0.3589,
      "step": 175
    },
    {
      "epoch": 2.824,
      "grad_norm": 0.08068230637387531,
      "learning_rate": 7.056927482354514e-07,
      "loss": 0.3563,
      "step": 176
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.07523651247335839,
      "learning_rate": 5.719316743938086e-07,
      "loss": 0.3547,
      "step": 177
    },
    {
      "epoch": 2.856,
      "grad_norm": 0.0797260677230398,
      "learning_rate": 4.521233403707781e-07,
      "loss": 0.3514,
      "step": 178
    },
    {
      "epoch": 2.872,
      "grad_norm": 0.076655921195965,
      "learning_rate": 3.463101437420857e-07,
      "loss": 0.3576,
      "step": 179
    },
    {
      "epoch": 2.888,
      "grad_norm": 0.07807817201802293,
      "learning_rate": 2.5452952950732136e-07,
      "loss": 0.3496,
      "step": 180
    },
    {
      "epoch": 2.904,
      "grad_norm": 0.08466849233747002,
      "learning_rate": 1.768139768389343e-07,
      "loss": 0.3584,
      "step": 181
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.07987580277852142,
      "learning_rate": 1.1319098758858726e-07,
      "loss": 0.3559,
      "step": 182
    },
    {
      "epoch": 2.936,
      "grad_norm": 0.07757053010174227,
      "learning_rate": 6.368307655482576e-08,
      "loss": 0.3566,
      "step": 183
    },
    {
      "epoch": 2.952,
      "grad_norm": 0.07422516712369932,
      "learning_rate": 2.830776351558484e-08,
      "loss": 0.3628,
      "step": 184
    },
    {
      "epoch": 2.968,
      "grad_norm": 0.08498877761473865,
      "learning_rate": 7.077567028335175e-09,
      "loss": 0.3557,
      "step": 185
    },
    {
      "epoch": 2.984,
      "grad_norm": 0.08178318612333094,
      "learning_rate": 0.0,
      "loss": 0.3594,
      "step": 186
    },
    {
      "epoch": 2.984,
      "step": 186,
      "total_flos": 4.786332995139142e+18,
      "train_loss": 0.42651380758772617,
      "train_runtime": 40803.7285,
      "train_samples_per_second": 2.352,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 186,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.786332995139142e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}