{
  "best_metric": 0.8692187666893005,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.2027027027027026,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006006006006006006,
      "grad_norm": 11.939387321472168,
      "learning_rate": 1e-05,
      "loss": 2.5099,
      "step": 1
    },
    {
      "epoch": 0.006006006006006006,
      "eval_loss": 2.6684772968292236,
      "eval_runtime": 17.6752,
      "eval_samples_per_second": 15.898,
      "eval_steps_per_second": 4.017,
      "step": 1
    },
    {
      "epoch": 0.012012012012012012,
      "grad_norm": 11.134116172790527,
      "learning_rate": 2e-05,
      "loss": 2.5068,
      "step": 2
    },
    {
      "epoch": 0.018018018018018018,
      "grad_norm": 10.383133888244629,
      "learning_rate": 3e-05,
      "loss": 2.3814,
      "step": 3
    },
    {
      "epoch": 0.024024024024024024,
      "grad_norm": 5.739177703857422,
      "learning_rate": 4e-05,
      "loss": 2.0885,
      "step": 4
    },
    {
      "epoch": 0.03003003003003003,
      "grad_norm": 4.936707019805908,
      "learning_rate": 5e-05,
      "loss": 1.8588,
      "step": 5
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 4.746893882751465,
      "learning_rate": 6e-05,
      "loss": 1.7283,
      "step": 6
    },
    {
      "epoch": 0.042042042042042045,
      "grad_norm": 3.2728261947631836,
      "learning_rate": 7e-05,
      "loss": 1.675,
      "step": 7
    },
    {
      "epoch": 0.04804804804804805,
      "grad_norm": 3.297927141189575,
      "learning_rate": 8e-05,
      "loss": 1.5842,
      "step": 8
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.902624249458313,
      "learning_rate": 9e-05,
      "loss": 1.6107,
      "step": 9
    },
    {
      "epoch": 0.06006006006006006,
      "grad_norm": 3.0174639225006104,
      "learning_rate": 0.0001,
      "loss": 1.5527,
      "step": 10
    },
    {
      "epoch": 0.06606606606606606,
      "grad_norm": 1.5258729457855225,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.4349,
      "step": 11
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 1.7817354202270508,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.3657,
      "step": 12
    },
    {
      "epoch": 0.07807807807807808,
      "grad_norm": 2.190635919570923,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.3467,
      "step": 13
    },
    {
      "epoch": 0.08408408408408409,
      "grad_norm": 1.5562353134155273,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.301,
      "step": 14
    },
    {
      "epoch": 0.09009009009009009,
      "grad_norm": 2.9452617168426514,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.2449,
      "step": 15
    },
    {
      "epoch": 0.0960960960960961,
      "grad_norm": 1.5747156143188477,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.2433,
      "step": 16
    },
    {
      "epoch": 0.1021021021021021,
      "grad_norm": 2.5135059356689453,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.2701,
      "step": 17
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 1.8942909240722656,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.244,
      "step": 18
    },
    {
      "epoch": 0.11411411411411411,
      "grad_norm": 1.4245126247406006,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.2817,
      "step": 19
    },
    {
      "epoch": 0.12012012012012012,
      "grad_norm": 1.312168836593628,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.2959,
      "step": 20
    },
    {
      "epoch": 0.12612612612612611,
      "grad_norm": 1.252049207687378,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.3535,
      "step": 21
    },
    {
      "epoch": 0.13213213213213212,
      "grad_norm": 0.9794065356254578,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.2349,
      "step": 22
    },
    {
      "epoch": 0.13813813813813813,
      "grad_norm": 1.2273666858673096,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.2555,
      "step": 23
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 1.1855885982513428,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.2202,
      "step": 24
    },
    {
      "epoch": 0.15015015015015015,
      "grad_norm": 1.2980982065200806,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.2209,
      "step": 25
    },
    {
      "epoch": 0.15615615615615616,
      "grad_norm": 1.151898980140686,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.1805,
      "step": 26
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 1.4162862300872803,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.1865,
      "step": 27
    },
    {
      "epoch": 0.16816816816816818,
      "grad_norm": 1.196455955505371,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.1951,
      "step": 28
    },
    {
      "epoch": 0.17417417417417416,
      "grad_norm": 1.682176947593689,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.1489,
      "step": 29
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 1.5852391719818115,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1343,
      "step": 30
    },
    {
      "epoch": 0.18618618618618618,
      "grad_norm": 1.216054916381836,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.1273,
      "step": 31
    },
    {
      "epoch": 0.1921921921921922,
      "grad_norm": 1.4298076629638672,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.1407,
      "step": 32
    },
    {
      "epoch": 0.1981981981981982,
      "grad_norm": 1.0303997993469238,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.1607,
      "step": 33
    },
    {
      "epoch": 0.2042042042042042,
      "grad_norm": 1.330358624458313,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.0708,
      "step": 34
    },
    {
      "epoch": 0.21021021021021022,
      "grad_norm": 1.1829297542572021,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.1132,
      "step": 35
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 1.2306973934173584,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.0942,
      "step": 36
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.036027193069458,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.1022,
      "step": 37
    },
    {
      "epoch": 0.22822822822822822,
      "grad_norm": 1.177780032157898,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.0687,
      "step": 38
    },
    {
      "epoch": 0.23423423423423423,
      "grad_norm": 1.0785988569259644,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.0862,
      "step": 39
    },
    {
      "epoch": 0.24024024024024024,
      "grad_norm": 1.0600802898406982,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.0568,
      "step": 40
    },
    {
      "epoch": 0.24624624624624625,
      "grad_norm": 0.9225219488143921,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.0081,
      "step": 41
    },
    {
      "epoch": 0.25225225225225223,
      "grad_norm": 2.197932720184326,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.0368,
      "step": 42
    },
    {
      "epoch": 0.25825825825825827,
      "grad_norm": 1.3498945236206055,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.0562,
      "step": 43
    },
    {
      "epoch": 0.26426426426426425,
      "grad_norm": 1.2378123998641968,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.0269,
      "step": 44
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 1.4406875371932983,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.0394,
      "step": 45
    },
    {
      "epoch": 0.27627627627627627,
      "grad_norm": 1.5316462516784668,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.9193,
      "step": 46
    },
    {
      "epoch": 0.2822822822822823,
      "grad_norm": 1.5557087659835815,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.9704,
      "step": 47
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 1.268043875694275,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.9842,
      "step": 48
    },
    {
      "epoch": 0.29429429429429427,
      "grad_norm": 1.1008268594741821,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.9844,
      "step": 49
    },
    {
      "epoch": 0.3003003003003003,
      "grad_norm": 1.0313293933868408,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.9615,
      "step": 50
    },
    {
      "epoch": 0.3003003003003003,
      "eval_loss": 1.0298943519592285,
      "eval_runtime": 18.0134,
      "eval_samples_per_second": 15.599,
      "eval_steps_per_second": 3.942,
      "step": 50
    },
    {
      "epoch": 0.3063063063063063,
      "grad_norm": 1.051007628440857,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.9629,
      "step": 51
    },
    {
      "epoch": 0.3123123123123123,
      "grad_norm": 1.2950942516326904,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.9977,
      "step": 52
    },
    {
      "epoch": 0.3183183183183183,
      "grad_norm": 1.1288374662399292,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.9234,
      "step": 53
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 1.2416094541549683,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.9568,
      "step": 54
    },
    {
      "epoch": 0.3303303303303303,
      "grad_norm": 0.8908717036247253,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.9483,
      "step": 55
    },
    {
      "epoch": 0.33633633633633636,
      "grad_norm": 1.257003903388977,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.9535,
      "step": 56
    },
    {
      "epoch": 0.34234234234234234,
      "grad_norm": 0.8720048069953918,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.9155,
      "step": 57
    },
    {
      "epoch": 0.3483483483483483,
      "grad_norm": 1.0944340229034424,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.9203,
      "step": 58
    },
    {
      "epoch": 0.35435435435435436,
      "grad_norm": 0.8649797439575195,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.9157,
      "step": 59
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 0.9637596011161804,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.9014,
      "step": 60
    },
    {
      "epoch": 0.3663663663663664,
      "grad_norm": 0.8522753119468689,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.9578,
      "step": 61
    },
    {
      "epoch": 0.37237237237237236,
      "grad_norm": 0.9288323521614075,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.9745,
      "step": 62
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 0.7352877259254456,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.0141,
      "step": 63
    },
    {
      "epoch": 0.3843843843843844,
      "grad_norm": 0.8249340057373047,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9456,
      "step": 64
    },
    {
      "epoch": 0.39039039039039036,
      "grad_norm": 0.9949619770050049,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.0047,
      "step": 65
    },
    {
      "epoch": 0.3963963963963964,
      "grad_norm": 0.8370471000671387,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9629,
      "step": 66
    },
    {
      "epoch": 0.4024024024024024,
      "grad_norm": 0.7806390523910522,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.985,
      "step": 67
    },
    {
      "epoch": 0.4084084084084084,
      "grad_norm": 0.805853009223938,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9609,
      "step": 68
    },
    {
      "epoch": 0.4144144144144144,
      "grad_norm": 0.8984209895133972,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.9926,
      "step": 69
    },
    {
      "epoch": 0.42042042042042044,
      "grad_norm": 0.7500899434089661,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.9789,
      "step": 70
    },
    {
      "epoch": 0.4264264264264264,
      "grad_norm": 0.9195863604545593,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.9954,
      "step": 71
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 1.0043126344680786,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.9879,
      "step": 72
    },
    {
      "epoch": 0.43843843843843844,
      "grad_norm": 0.9990636706352234,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.9575,
      "step": 73
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.8164543509483337,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9857,
      "step": 74
    },
    {
      "epoch": 0.45045045045045046,
      "grad_norm": 0.7417972087860107,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.9557,
      "step": 75
    },
    {
      "epoch": 0.45645645645645644,
      "grad_norm": 0.8482620716094971,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.9613,
      "step": 76
    },
    {
      "epoch": 0.4624624624624625,
      "grad_norm": 0.9520698189735413,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.9774,
      "step": 77
    },
    {
      "epoch": 0.46846846846846846,
      "grad_norm": 1.0005433559417725,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8996,
      "step": 78
    },
    {
      "epoch": 0.4744744744744745,
      "grad_norm": 1.1836864948272705,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.9765,
      "step": 79
    },
    {
      "epoch": 0.4804804804804805,
      "grad_norm": 1.205776572227478,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.9086,
      "step": 80
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 1.2043135166168213,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.936,
      "step": 81
    },
    {
      "epoch": 0.4924924924924925,
      "grad_norm": 1.310430884361267,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.9194,
      "step": 82
    },
    {
      "epoch": 0.4984984984984985,
      "grad_norm": 1.4059784412384033,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.9135,
      "step": 83
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 1.1116178035736084,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.9117,
      "step": 84
    },
    {
      "epoch": 0.5105105105105106,
      "grad_norm": 1.09409761428833,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.9052,
      "step": 85
    },
    {
      "epoch": 0.5165165165165165,
      "grad_norm": 0.98567795753479,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8695,
      "step": 86
    },
    {
      "epoch": 0.5225225225225225,
      "grad_norm": 1.088504672050476,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.9383,
      "step": 87
    },
    {
      "epoch": 0.5285285285285285,
      "grad_norm": 1.044263482093811,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.8757,
      "step": 88
    },
    {
      "epoch": 0.5345345345345346,
      "grad_norm": 0.8426089882850647,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.9611,
      "step": 89
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 1.213052749633789,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.865,
      "step": 90
    },
    {
      "epoch": 0.5465465465465466,
      "grad_norm": 0.860582709312439,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8819,
      "step": 91
    },
    {
      "epoch": 0.5525525525525525,
      "grad_norm": 0.8560044765472412,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.8612,
      "step": 92
    },
    {
      "epoch": 0.5585585585585585,
      "grad_norm": 0.9745939373970032,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.8467,
      "step": 93
    },
    {
      "epoch": 0.5645645645645646,
      "grad_norm": 0.8247107863426208,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.838,
      "step": 94
    },
    {
      "epoch": 0.5705705705705706,
      "grad_norm": 1.0038293600082397,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.8094,
      "step": 95
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 0.7708703875541687,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.8946,
      "step": 96
    },
    {
      "epoch": 0.5825825825825826,
      "grad_norm": 1.0348100662231445,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.8235,
      "step": 97
    },
    {
      "epoch": 0.5885885885885885,
      "grad_norm": 0.8654219508171082,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.8755,
      "step": 98
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 0.7367492318153381,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.8784,
      "step": 99
    },
    {
      "epoch": 0.6006006006006006,
      "grad_norm": 0.8014348745346069,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8345,
      "step": 100
    },
    {
      "epoch": 0.6006006006006006,
      "eval_loss": 0.9171533584594727,
      "eval_runtime": 18.0075,
      "eval_samples_per_second": 15.605,
      "eval_steps_per_second": 3.943,
      "step": 100
    },
    {
      "epoch": 0.6066066066066066,
      "grad_norm": 0.8355028033256531,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.8232,
      "step": 101
    },
    {
      "epoch": 0.6126126126126126,
      "grad_norm": 0.6168224811553955,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.908,
      "step": 102
    },
    {
      "epoch": 0.6186186186186187,
      "grad_norm": 0.7613393664360046,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9736,
      "step": 103
    },
    {
      "epoch": 0.6246246246246246,
      "grad_norm": 0.7606231570243835,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.9362,
      "step": 104
    },
    {
      "epoch": 0.6306306306306306,
      "grad_norm": 0.6035923957824707,
      "learning_rate": 5e-05,
      "loss": 0.9375,
      "step": 105
    },
    {
      "epoch": 0.6366366366366366,
      "grad_norm": 0.7837689518928528,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.8615,
      "step": 106
    },
    {
      "epoch": 0.6426426426426426,
      "grad_norm": 0.8466827869415283,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.9437,
      "step": 107
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.7450090050697327,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.9288,
      "step": 108
    },
    {
      "epoch": 0.6546546546546547,
      "grad_norm": 0.7823922634124756,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8864,
      "step": 109
    },
    {
      "epoch": 0.6606606606606606,
      "grad_norm": 0.7928395867347717,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8979,
      "step": 110
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.8492867946624756,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9318,
      "step": 111
    },
    {
      "epoch": 0.6726726726726727,
      "grad_norm": 0.789612352848053,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.9292,
      "step": 112
    },
    {
      "epoch": 0.6786786786786787,
      "grad_norm": 0.8383537530899048,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.9287,
      "step": 113
    },
    {
      "epoch": 0.6846846846846847,
      "grad_norm": 0.8910871148109436,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.9144,
      "step": 114
    },
    {
      "epoch": 0.6906906906906907,
      "grad_norm": 0.6498334407806396,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.9461,
      "step": 115
    },
    {
      "epoch": 0.6966966966966966,
      "grad_norm": 0.70673668384552,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.8729,
      "step": 116
    },
    {
      "epoch": 0.7027027027027027,
      "grad_norm": 0.7191166281700134,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.8869,
      "step": 117
    },
    {
      "epoch": 0.7087087087087087,
      "grad_norm": 0.7417476177215576,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.8824,
      "step": 118
    },
    {
      "epoch": 0.7147147147147147,
      "grad_norm": 0.6482788324356079,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8724,
      "step": 119
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 0.767522931098938,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8828,
      "step": 120
    },
    {
      "epoch": 0.7267267267267268,
      "grad_norm": 0.8187276124954224,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.9052,
      "step": 121
    },
    {
      "epoch": 0.7327327327327328,
      "grad_norm": 0.9104949831962585,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.8651,
      "step": 122
    },
    {
      "epoch": 0.7387387387387387,
      "grad_norm": 0.9946015477180481,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.8444,
      "step": 123
    },
    {
      "epoch": 0.7447447447447447,
      "grad_norm": 1.3974273204803467,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8705,
      "step": 124
    },
    {
      "epoch": 0.7507507507507507,
      "grad_norm": 1.1792829036712646,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.8189,
      "step": 125
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 0.8684128522872925,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.8141,
      "step": 126
    },
    {
      "epoch": 0.7627627627627628,
      "grad_norm": 1.0640795230865479,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.8378,
      "step": 127
    },
    {
      "epoch": 0.7687687687687688,
      "grad_norm": 0.8010351657867432,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.8413,
      "step": 128
    },
    {
      "epoch": 0.7747747747747747,
      "grad_norm": 0.8019711971282959,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.8243,
      "step": 129
    },
    {
      "epoch": 0.7807807807807807,
      "grad_norm": 0.8309069275856018,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.8918,
      "step": 130
    },
    {
      "epoch": 0.7867867867867868,
      "grad_norm": 0.6657477617263794,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.8263,
      "step": 131
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 0.5976794958114624,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.8137,
      "step": 132
    },
    {
      "epoch": 0.7987987987987988,
      "grad_norm": 0.7813435196876526,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8584,
      "step": 133
    },
    {
      "epoch": 0.8048048048048048,
      "grad_norm": 0.6679612994194031,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.8087,
      "step": 134
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 0.6129650473594666,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7949,
      "step": 135
    },
    {
      "epoch": 0.8168168168168168,
      "grad_norm": 0.6864893436431885,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.8103,
      "step": 136
    },
    {
      "epoch": 0.8228228228228228,
      "grad_norm": 0.6034263968467712,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.828,
      "step": 137
    },
    {
      "epoch": 0.8288288288288288,
      "grad_norm": 0.6357901692390442,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.8134,
      "step": 138
    },
    {
      "epoch": 0.8348348348348348,
      "grad_norm": 0.5727288126945496,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.87,
      "step": 139
    },
    {
      "epoch": 0.8408408408408409,
      "grad_norm": 0.6429306864738464,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7983,
      "step": 140
    },
    {
      "epoch": 0.8468468468468469,
      "grad_norm": 0.6352106332778931,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.8433,
      "step": 141
    },
    {
      "epoch": 0.8528528528528528,
      "grad_norm": 0.5029008984565735,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.8472,
      "step": 142
    },
    {
      "epoch": 0.8588588588588588,
      "grad_norm": 0.6047132611274719,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9459,
      "step": 143
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.5680246353149414,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.893,
      "step": 144
    },
    {
      "epoch": 0.8708708708708709,
      "grad_norm": 0.6317458152770996,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.8893,
      "step": 145
    },
    {
      "epoch": 0.8768768768768769,
      "grad_norm": 0.5886130332946777,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.8869,
      "step": 146
    },
    {
      "epoch": 0.8828828828828829,
      "grad_norm": 0.5545299649238586,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.9035,
      "step": 147
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.6034277677536011,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.8871,
      "step": 148
    },
    {
      "epoch": 0.8948948948948949,
      "grad_norm": 0.6021369695663452,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.8822,
      "step": 149
    },
    {
      "epoch": 0.9009009009009009,
      "grad_norm": 0.6074609160423279,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.8712,
      "step": 150
    },
    {
      "epoch": 0.9009009009009009,
      "eval_loss": 0.8779696822166443,
      "eval_runtime": 18.0057,
      "eval_samples_per_second": 15.606,
      "eval_steps_per_second": 3.943,
      "step": 150
    },
    {
      "epoch": 0.9069069069069069,
      "grad_norm": 0.5972970724105835,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.9172,
      "step": 151
    },
    {
      "epoch": 0.9129129129129129,
      "grad_norm": 0.582316517829895,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.8924,
      "step": 152
    },
    {
      "epoch": 0.918918918918919,
      "grad_norm": 0.6640623807907104,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.8428,
      "step": 153
    },
    {
      "epoch": 0.924924924924925,
      "grad_norm": 0.6095839738845825,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.8875,
      "step": 154
    },
    {
      "epoch": 0.9309309309309309,
      "grad_norm": 0.5643842220306396,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.8932,
      "step": 155
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 0.5507370829582214,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.8816,
      "step": 156
    },
    {
      "epoch": 0.9429429429429429,
      "grad_norm": 0.6196346282958984,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.8979,
      "step": 157
    },
    {
      "epoch": 0.948948948948949,
      "grad_norm": 0.662056565284729,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.8548,
      "step": 158
    },
    {
      "epoch": 0.954954954954955,
      "grad_norm": 0.6531519293785095,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8438,
      "step": 159
    },
    {
      "epoch": 0.960960960960961,
      "grad_norm": 0.6297209858894348,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.9005,
      "step": 160
    },
    {
      "epoch": 0.9669669669669669,
      "grad_norm": 0.6573077440261841,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.8544,
      "step": 161
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 0.7002811431884766,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8407,
      "step": 162
    },
    {
      "epoch": 0.978978978978979,
      "grad_norm": 0.7205744385719299,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.8791,
      "step": 163
    },
    {
      "epoch": 0.984984984984985,
      "grad_norm": 1.0088785886764526,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.8784,
      "step": 164
    },
    {
      "epoch": 0.990990990990991,
      "grad_norm": 1.1316860914230347,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.8128,
      "step": 165
    },
    {
      "epoch": 0.996996996996997,
      "grad_norm": 1.0013597011566162,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.9126,
      "step": 166
    },
    {
      "epoch": 1.0045045045045045,
      "grad_norm": 1.601672649383545,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.4815,
      "step": 167
    },
    {
      "epoch": 1.0105105105105106,
      "grad_norm": 0.8222581148147583,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.848,
      "step": 168
    },
    {
      "epoch": 1.0165165165165164,
      "grad_norm": 0.6949058175086975,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.7578,
      "step": 169
    },
    {
      "epoch": 1.0225225225225225,
      "grad_norm": 0.7635194063186646,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.8686,
      "step": 170
    },
    {
      "epoch": 1.0285285285285286,
      "grad_norm": 0.6866496801376343,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7957,
      "step": 171
    },
    {
      "epoch": 1.0345345345345345,
      "grad_norm": 0.6219164729118347,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7845,
      "step": 172
    },
    {
      "epoch": 1.0405405405405406,
      "grad_norm": 0.673335611820221,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.8038,
      "step": 173
    },
    {
      "epoch": 1.0465465465465464,
      "grad_norm": 0.5561545491218567,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.8503,
      "step": 174
    },
    {
      "epoch": 1.0525525525525525,
      "grad_norm": 0.5972916483879089,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.814,
      "step": 175
    },
    {
      "epoch": 1.0585585585585586,
      "grad_norm": 0.5003646016120911,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.8021,
      "step": 176
    },
    {
      "epoch": 1.0645645645645645,
      "grad_norm": 0.5118160247802734,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.8035,
      "step": 177
    },
    {
      "epoch": 1.0705705705705706,
      "grad_norm": 0.538970947265625,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.8393,
      "step": 178
    },
    {
      "epoch": 1.0765765765765765,
      "grad_norm": 0.5180559158325195,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.768,
      "step": 179
    },
    {
      "epoch": 1.0825825825825826,
      "grad_norm": 0.5948973894119263,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.832,
      "step": 180
    },
    {
      "epoch": 1.0885885885885886,
      "grad_norm": 0.5173677802085876,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.846,
      "step": 181
    },
    {
      "epoch": 1.0945945945945945,
      "grad_norm": 0.5123527646064758,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.8473,
      "step": 182
    },
    {
      "epoch": 1.1006006006006006,
      "grad_norm": 0.5374675989151001,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.8384,
      "step": 183
    },
    {
      "epoch": 1.1066066066066067,
      "grad_norm": 0.48775914311408997,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.8437,
      "step": 184
    },
    {
      "epoch": 1.1126126126126126,
      "grad_norm": 0.4917081296443939,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.8516,
      "step": 185
    },
    {
      "epoch": 1.1186186186186187,
      "grad_norm": 0.5778480768203735,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.8817,
      "step": 186
    },
    {
      "epoch": 1.1246246246246245,
      "grad_norm": 0.5765755772590637,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.8946,
      "step": 187
    },
    {
      "epoch": 1.1306306306306306,
      "grad_norm": 0.5951379537582397,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.8741,
      "step": 188
    },
    {
      "epoch": 1.1366366366366367,
      "grad_norm": 0.5706170797348022,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.8683,
      "step": 189
    },
    {
      "epoch": 1.1426426426426426,
      "grad_norm": 0.6110479831695557,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.8762,
      "step": 190
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 0.597766637802124,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.9191,
      "step": 191
    },
    {
      "epoch": 1.1546546546546548,
      "grad_norm": 0.5983462333679199,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.8505,
      "step": 192
    },
    {
      "epoch": 1.1606606606606606,
      "grad_norm": 0.6395205855369568,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.8722,
      "step": 193
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 0.6160947680473328,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.8459,
      "step": 194
    },
    {
      "epoch": 1.1726726726726726,
      "grad_norm": 0.6518352627754211,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.8803,
      "step": 195
    },
    {
      "epoch": 1.1786786786786787,
      "grad_norm": 0.6724955439567566,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.8771,
      "step": 196
    },
    {
      "epoch": 1.1846846846846848,
      "grad_norm": 0.6574990153312683,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.9043,
      "step": 197
    },
    {
      "epoch": 1.1906906906906907,
      "grad_norm": 0.7296738624572754,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.8882,
      "step": 198
    },
    {
      "epoch": 1.1966966966966968,
      "grad_norm": 0.6836444139480591,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.8861,
      "step": 199
    },
    {
      "epoch": 1.2027027027027026,
      "grad_norm": 0.7030710577964783,
      "learning_rate": 0.0,
      "loss": 0.8901,
      "step": 200
    },
    {
      "epoch": 1.2027027027027026,
      "eval_loss": 0.8692187666893005,
      "eval_runtime": 18.0109,
      "eval_samples_per_second": 15.602,
      "eval_steps_per_second": 3.942,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.51904084557824e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}