{
  "best_metric": 10.335372924804688,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 2.4024024024024024,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012012012012012012,
      "grad_norm": 0.13712449371814728,
      "learning_rate": 1e-05,
      "loss": 10.3748,
      "step": 1
    },
    {
      "epoch": 0.012012012012012012,
      "eval_loss": 10.37226390838623,
      "eval_runtime": 0.3238,
      "eval_samples_per_second": 432.379,
      "eval_steps_per_second": 108.095,
      "step": 1
    },
    {
      "epoch": 0.024024024024024024,
      "grad_norm": 0.14700013399124146,
      "learning_rate": 2e-05,
      "loss": 10.3753,
      "step": 2
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 0.15077437460422516,
      "learning_rate": 3e-05,
      "loss": 10.3742,
      "step": 3
    },
    {
      "epoch": 0.04804804804804805,
      "grad_norm": 0.17068171501159668,
      "learning_rate": 4e-05,
      "loss": 10.3776,
      "step": 4
    },
    {
      "epoch": 0.06006006006006006,
      "grad_norm": 0.1538737565279007,
      "learning_rate": 5e-05,
      "loss": 10.374,
      "step": 5
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 0.14699707925319672,
      "learning_rate": 6e-05,
      "loss": 10.3737,
      "step": 6
    },
    {
      "epoch": 0.08408408408408409,
      "grad_norm": 0.18090641498565674,
      "learning_rate": 7e-05,
      "loss": 10.3722,
      "step": 7
    },
    {
      "epoch": 0.0960960960960961,
      "grad_norm": 0.14958062767982483,
      "learning_rate": 8e-05,
      "loss": 10.3716,
      "step": 8
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 0.17953340709209442,
      "learning_rate": 9e-05,
      "loss": 10.3725,
      "step": 9
    },
    {
      "epoch": 0.12012012012012012,
      "grad_norm": 0.2099277526140213,
      "learning_rate": 0.0001,
      "loss": 10.3718,
      "step": 10
    },
    {
      "epoch": 0.13213213213213212,
      "grad_norm": 0.13401629030704498,
      "learning_rate": 9.999316524962345e-05,
      "loss": 10.3672,
      "step": 11
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 0.20920030772686005,
      "learning_rate": 9.997266286704631e-05,
      "loss": 10.3715,
      "step": 12
    },
    {
      "epoch": 0.15615615615615616,
      "grad_norm": 0.1917256861925125,
      "learning_rate": 9.993849845741524e-05,
      "loss": 10.3632,
      "step": 13
    },
    {
      "epoch": 0.16816816816816818,
      "grad_norm": 0.20941601693630219,
      "learning_rate": 9.989068136093873e-05,
      "loss": 10.3631,
      "step": 14
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 0.21399274468421936,
      "learning_rate": 9.98292246503335e-05,
      "loss": 10.3658,
      "step": 15
    },
    {
      "epoch": 0.1921921921921922,
      "grad_norm": 0.2468506395816803,
      "learning_rate": 9.975414512725057e-05,
      "loss": 10.3569,
      "step": 16
    },
    {
      "epoch": 0.2042042042042042,
      "grad_norm": 0.1855248212814331,
      "learning_rate": 9.966546331768191e-05,
      "loss": 10.3535,
      "step": 17
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.24662943184375763,
      "learning_rate": 9.956320346634876e-05,
      "loss": 10.3496,
      "step": 18
    },
    {
      "epoch": 0.22822822822822822,
      "grad_norm": 0.2321450412273407,
      "learning_rate": 9.944739353007344e-05,
      "loss": 10.3488,
      "step": 19
    },
    {
      "epoch": 0.24024024024024024,
      "grad_norm": 0.2801991403102875,
      "learning_rate": 9.931806517013612e-05,
      "loss": 10.3512,
      "step": 20
    },
    {
      "epoch": 0.25225225225225223,
      "grad_norm": 0.2540591359138489,
      "learning_rate": 9.917525374361912e-05,
      "loss": 10.3653,
      "step": 21
    },
    {
      "epoch": 0.26426426426426425,
      "grad_norm": 0.22488336265087128,
      "learning_rate": 9.901899829374047e-05,
      "loss": 10.3584,
      "step": 22
    },
    {
      "epoch": 0.27627627627627627,
      "grad_norm": 0.20090781152248383,
      "learning_rate": 9.884934153917997e-05,
      "loss": 10.3626,
      "step": 23
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 0.23095400631427765,
      "learning_rate": 9.86663298624003e-05,
      "loss": 10.356,
      "step": 24
    },
    {
      "epoch": 0.3003003003003003,
      "grad_norm": 0.21553294360637665,
      "learning_rate": 9.847001329696653e-05,
      "loss": 10.3634,
      "step": 25
    },
    {
      "epoch": 0.3123123123123123,
      "grad_norm": 0.21469008922576904,
      "learning_rate": 9.826044551386744e-05,
      "loss": 10.3607,
      "step": 26
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 0.1710595041513443,
      "learning_rate": 9.803768380684242e-05,
      "loss": 10.3546,
      "step": 27
    },
    {
      "epoch": 0.33633633633633636,
      "grad_norm": 0.16814735531806946,
      "learning_rate": 9.780178907671789e-05,
      "loss": 10.3574,
      "step": 28
    },
    {
      "epoch": 0.3483483483483483,
      "grad_norm": 0.14618347585201263,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3548,
      "step": 29
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 0.15100860595703125,
      "learning_rate": 9.729086208503174e-05,
      "loss": 10.3529,
      "step": 30
    },
    {
      "epoch": 0.37237237237237236,
      "grad_norm": 0.13345609605312347,
      "learning_rate": 9.701596950580806e-05,
      "loss": 10.3509,
      "step": 31
    },
    {
      "epoch": 0.3843843843843844,
      "grad_norm": 0.13707886636257172,
      "learning_rate": 9.672822322997305e-05,
      "loss": 10.3539,
      "step": 32
    },
    {
      "epoch": 0.3963963963963964,
      "grad_norm": 0.13473767042160034,
      "learning_rate": 9.642770192448536e-05,
      "loss": 10.353,
      "step": 33
    },
    {
      "epoch": 0.4084084084084084,
      "grad_norm": 0.17853787541389465,
      "learning_rate": 9.611448774886924e-05,
      "loss": 10.3479,
      "step": 34
    },
    {
      "epoch": 0.42042042042042044,
      "grad_norm": 0.12611529231071472,
      "learning_rate": 9.578866633275288e-05,
      "loss": 10.349,
      "step": 35
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.1880243420600891,
      "learning_rate": 9.545032675245813e-05,
      "loss": 10.3393,
      "step": 36
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.23882512748241425,
      "learning_rate": 9.509956150664796e-05,
      "loss": 10.341,
      "step": 37
    },
    {
      "epoch": 0.45645645645645644,
      "grad_norm": 0.3049931228160858,
      "learning_rate": 9.473646649103818e-05,
      "loss": 10.3349,
      "step": 38
    },
    {
      "epoch": 0.46846846846846846,
      "grad_norm": 0.25676149129867554,
      "learning_rate": 9.43611409721806e-05,
      "loss": 10.3336,
      "step": 39
    },
    {
      "epoch": 0.4804804804804805,
      "grad_norm": 0.42220810055732727,
      "learning_rate": 9.397368756032445e-05,
      "loss": 10.3332,
      "step": 40
    },
    {
      "epoch": 0.4924924924924925,
      "grad_norm": 0.12722663581371307,
      "learning_rate": 9.357421218136386e-05,
      "loss": 10.3472,
      "step": 41
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 0.10271985083818436,
      "learning_rate": 9.316282404787871e-05,
      "loss": 10.3509,
      "step": 42
    },
    {
      "epoch": 0.5165165165165165,
      "grad_norm": 0.11003418266773224,
      "learning_rate": 9.273963562927695e-05,
      "loss": 10.3517,
      "step": 43
    },
    {
      "epoch": 0.5285285285285285,
      "grad_norm": 0.09108521789312363,
      "learning_rate": 9.230476262104677e-05,
      "loss": 10.3526,
      "step": 44
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.12007266283035278,
      "learning_rate": 9.185832391312644e-05,
      "loss": 10.3497,
      "step": 45
    },
    {
      "epoch": 0.5525525525525525,
      "grad_norm": 0.14361444115638733,
      "learning_rate": 9.140044155740101e-05,
      "loss": 10.3516,
      "step": 46
    },
    {
      "epoch": 0.5645645645645646,
      "grad_norm": 0.11113029718399048,
      "learning_rate": 9.093124073433463e-05,
      "loss": 10.3524,
      "step": 47
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 0.11321519315242767,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3466,
      "step": 48
    },
    {
      "epoch": 0.5885885885885885,
      "grad_norm": 0.08630157262086868,
      "learning_rate": 8.995939984474624e-05,
      "loss": 10.348,
      "step": 49
    },
    {
      "epoch": 0.6006006006006006,
      "grad_norm": 0.09268742054700851,
      "learning_rate": 8.945702546981969e-05,
      "loss": 10.3512,
      "step": 50
    },
    {
      "epoch": 0.6006006006006006,
      "eval_loss": 10.34417724609375,
      "eval_runtime": 0.312,
      "eval_samples_per_second": 448.743,
      "eval_steps_per_second": 112.186,
      "step": 50
    },
    {
      "epoch": 0.6126126126126126,
      "grad_norm": 0.11005628108978271,
      "learning_rate": 8.894386393810563e-05,
      "loss": 10.3462,
      "step": 51
    },
    {
      "epoch": 0.6246246246246246,
      "grad_norm": 0.1283239722251892,
      "learning_rate": 8.842005554284296e-05,
      "loss": 10.3446,
      "step": 52
    },
    {
      "epoch": 0.6366366366366366,
      "grad_norm": 0.12633970379829407,
      "learning_rate": 8.788574348801675e-05,
      "loss": 10.3436,
      "step": 53
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.12627284228801727,
      "learning_rate": 8.73410738492077e-05,
      "loss": 10.341,
      "step": 54
    },
    {
      "epoch": 0.6606606606606606,
      "grad_norm": 0.17371974885463715,
      "learning_rate": 8.678619553365659e-05,
      "loss": 10.3423,
      "step": 55
    },
    {
      "epoch": 0.6726726726726727,
      "grad_norm": 0.15444986522197723,
      "learning_rate": 8.622126023955446e-05,
      "loss": 10.3388,
      "step": 56
    },
    {
      "epoch": 0.6846846846846847,
      "grad_norm": 0.20892584323883057,
      "learning_rate": 8.564642241456986e-05,
      "loss": 10.3352,
      "step": 57
    },
    {
      "epoch": 0.6966966966966966,
      "grad_norm": 0.29763954877853394,
      "learning_rate": 8.506183921362443e-05,
      "loss": 10.3306,
      "step": 58
    },
    {
      "epoch": 0.7087087087087087,
      "grad_norm": 0.26667994260787964,
      "learning_rate": 8.44676704559283e-05,
      "loss": 10.3327,
      "step": 59
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 0.2271106243133545,
      "learning_rate": 8.386407858128706e-05,
      "loss": 10.3211,
      "step": 60
    },
    {
      "epoch": 0.7327327327327328,
      "grad_norm": 0.14037537574768066,
      "learning_rate": 8.32512286056924e-05,
      "loss": 10.3483,
      "step": 61
    },
    {
      "epoch": 0.7447447447447447,
      "grad_norm": 0.11639165133237839,
      "learning_rate": 8.262928807620843e-05,
      "loss": 10.3437,
      "step": 62
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 0.1376139521598816,
      "learning_rate": 8.199842702516583e-05,
      "loss": 10.3524,
      "step": 63
    },
    {
      "epoch": 0.7687687687687688,
      "grad_norm": 0.11980290710926056,
      "learning_rate": 8.135881792367686e-05,
      "loss": 10.3434,
      "step": 64
    },
    {
      "epoch": 0.7807807807807807,
      "grad_norm": 0.1528472751379013,
      "learning_rate": 8.07106356344834e-05,
      "loss": 10.3471,
      "step": 65
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 0.10372594743967056,
      "learning_rate": 8.005405736415126e-05,
      "loss": 10.3467,
      "step": 66
    },
    {
      "epoch": 0.8048048048048048,
      "grad_norm": 0.10141345858573914,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3468,
      "step": 67
    },
    {
      "epoch": 0.8168168168168168,
      "grad_norm": 0.12832210958003998,
      "learning_rate": 7.871643313414718e-05,
      "loss": 10.346,
      "step": 68
    },
    {
      "epoch": 0.8288288288288288,
      "grad_norm": 0.1653580218553543,
      "learning_rate": 7.803575286758364e-05,
      "loss": 10.3475,
      "step": 69
    },
    {
      "epoch": 0.8408408408408409,
      "grad_norm": 0.09908397495746613,
      "learning_rate": 7.734740790612136e-05,
      "loss": 10.3464,
      "step": 70
    },
    {
      "epoch": 0.8528528528528528,
      "grad_norm": 0.11229545623064041,
      "learning_rate": 7.66515864363997e-05,
      "loss": 10.344,
      "step": 71
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.11439208686351776,
      "learning_rate": 7.594847868906076e-05,
      "loss": 10.3421,
      "step": 72
    },
    {
      "epoch": 0.8768768768768769,
      "grad_norm": 0.14968939125537872,
      "learning_rate": 7.52382768867422e-05,
      "loss": 10.3331,
      "step": 73
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.16251546144485474,
      "learning_rate": 7.452117519152542e-05,
      "loss": 10.3347,
      "step": 74
    },
    {
      "epoch": 0.9009009009009009,
      "grad_norm": 0.12764830887317657,
      "learning_rate": 7.379736965185368e-05,
      "loss": 10.3388,
      "step": 75
    },
    {
      "epoch": 0.9129129129129129,
      "grad_norm": 0.10238677263259888,
      "learning_rate": 7.30670581489344e-05,
      "loss": 10.3359,
      "step": 76
    },
    {
      "epoch": 0.924924924924925,
      "grad_norm": 0.1670926958322525,
      "learning_rate": 7.233044034264034e-05,
      "loss": 10.3311,
      "step": 77
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 0.16249431669712067,
      "learning_rate": 7.158771761692464e-05,
      "loss": 10.3279,
      "step": 78
    },
    {
      "epoch": 0.948948948948949,
      "grad_norm": 0.2530360817909241,
      "learning_rate": 7.083909302476453e-05,
      "loss": 10.3207,
      "step": 79
    },
    {
      "epoch": 0.960960960960961,
      "grad_norm": 0.20138835906982422,
      "learning_rate": 7.008477123264848e-05,
      "loss": 10.32,
      "step": 80
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 0.0904163345694542,
      "learning_rate": 6.932495846462261e-05,
      "loss": 10.3481,
      "step": 81
    },
    {
      "epoch": 0.984984984984985,
      "grad_norm": 0.1367456614971161,
      "learning_rate": 6.855986244591104e-05,
      "loss": 10.3481,
      "step": 82
    },
    {
      "epoch": 0.996996996996997,
      "grad_norm": 0.09853681176900864,
      "learning_rate": 6.778969234612584e-05,
      "loss": 10.33,
      "step": 83
    },
    {
      "epoch": 1.009009009009009,
      "grad_norm": 0.329206258058548,
      "learning_rate": 6.701465872208216e-05,
      "loss": 18.2979,
      "step": 84
    },
    {
      "epoch": 1.021021021021021,
      "grad_norm": 0.08560223132371902,
      "learning_rate": 6.623497346023418e-05,
      "loss": 10.2406,
      "step": 85
    },
    {
      "epoch": 1.033033033033033,
      "grad_norm": 0.12694305181503296,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.2553,
      "step": 86
    },
    {
      "epoch": 1.045045045045045,
      "grad_norm": 0.13173314929008484,
      "learning_rate": 6.466250186922325e-05,
      "loss": 10.3897,
      "step": 87
    },
    {
      "epoch": 1.057057057057057,
      "grad_norm": 0.07554960250854492,
      "learning_rate": 6.387014543809223e-05,
      "loss": 10.2751,
      "step": 88
    },
    {
      "epoch": 1.069069069069069,
      "grad_norm": 0.12087619304656982,
      "learning_rate": 6.307399704769099e-05,
      "loss": 10.4917,
      "step": 89
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.10280382633209229,
      "learning_rate": 6.227427435703997e-05,
      "loss": 10.3331,
      "step": 90
    },
    {
      "epoch": 1.093093093093093,
      "grad_norm": 0.08563369512557983,
      "learning_rate": 6.147119600233758e-05,
      "loss": 10.085,
      "step": 91
    },
    {
      "epoch": 1.105105105105105,
      "grad_norm": 0.10621888190507889,
      "learning_rate": 6.066498153718735e-05,
      "loss": 10.4992,
      "step": 92
    },
    {
      "epoch": 1.117117117117117,
      "grad_norm": 0.1010512039065361,
      "learning_rate": 5.985585137257401e-05,
      "loss": 10.3674,
      "step": 93
    },
    {
      "epoch": 1.1291291291291292,
      "grad_norm": 0.05635261535644531,
      "learning_rate": 5.90440267166055e-05,
      "loss": 10.3798,
      "step": 94
    },
    {
      "epoch": 1.1411411411411412,
      "grad_norm": 0.1029537096619606,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 10.7289,
      "step": 95
    },
    {
      "epoch": 1.1531531531531531,
      "grad_norm": 0.09132973849773407,
      "learning_rate": 5.74131823855921e-05,
      "loss": 9.798,
      "step": 96
    },
    {
      "epoch": 1.165165165165165,
      "grad_norm": 0.08823306858539581,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 10.6509,
      "step": 97
    },
    {
      "epoch": 1.1771771771771773,
      "grad_norm": 0.1097550317645073,
      "learning_rate": 5.577423184847932e-05,
      "loss": 10.1196,
      "step": 98
    },
    {
      "epoch": 1.1891891891891893,
      "grad_norm": 0.11960261315107346,
      "learning_rate": 5.495227651252315e-05,
      "loss": 10.5804,
      "step": 99
    },
    {
      "epoch": 1.2012012012012012,
      "grad_norm": 0.1370476484298706,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 10.135,
      "step": 100
    },
    {
      "epoch": 1.2012012012012012,
      "eval_loss": 10.336760520935059,
      "eval_runtime": 0.3127,
      "eval_samples_per_second": 447.659,
      "eval_steps_per_second": 111.915,
      "step": 100
    },
    {
      "epoch": 1.2132132132132132,
      "grad_norm": 0.1661449819803238,
      "learning_rate": 5.330452921628497e-05,
      "loss": 10.4603,
      "step": 101
    },
    {
      "epoch": 1.2252252252252251,
      "grad_norm": 0.2294112890958786,
      "learning_rate": 5.247918773366112e-05,
      "loss": 10.0375,
      "step": 102
    },
    {
      "epoch": 1.2372372372372373,
      "grad_norm": 0.20430868864059448,
      "learning_rate": 5.165316846586541e-05,
      "loss": 10.8531,
      "step": 103
    },
    {
      "epoch": 1.2492492492492493,
      "grad_norm": 0.07456423342227936,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 10.042,
      "step": 104
    },
    {
      "epoch": 1.2612612612612613,
      "grad_norm": 0.09096924215555191,
      "learning_rate": 5e-05,
      "loss": 10.1142,
      "step": 105
    },
    {
      "epoch": 1.2732732732732732,
      "grad_norm": 0.08972084522247314,
      "learning_rate": 4.917330276168208e-05,
      "loss": 10.2932,
      "step": 106
    },
    {
      "epoch": 1.2852852852852852,
      "grad_norm": 0.0873250886797905,
      "learning_rate": 4.834683153413459e-05,
      "loss": 10.5269,
      "step": 107
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": 0.0817558765411377,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 10.0447,
      "step": 108
    },
    {
      "epoch": 1.3093093093093093,
      "grad_norm": 0.1015278697013855,
      "learning_rate": 4.669547078371504e-05,
      "loss": 10.8067,
      "step": 109
    },
    {
      "epoch": 1.3213213213213213,
      "grad_norm": 0.08310439437627792,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 10.3178,
      "step": 110
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.08530978113412857,
      "learning_rate": 4.504772348747687e-05,
      "loss": 10.0777,
      "step": 111
    },
    {
      "epoch": 1.3453453453453452,
      "grad_norm": 0.08957183361053467,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 10.5409,
      "step": 112
    },
    {
      "epoch": 1.3573573573573574,
      "grad_norm": 0.08344922214746475,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 10.2941,
      "step": 113
    },
    {
      "epoch": 1.3693693693693694,
      "grad_norm": 0.10529579967260361,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 9.5459,
      "step": 114
    },
    {
      "epoch": 1.3813813813813813,
      "grad_norm": 0.09550967067480087,
      "learning_rate": 4.17702704859633e-05,
      "loss": 10.9248,
      "step": 115
    },
    {
      "epoch": 1.3933933933933935,
      "grad_norm": 0.0786777213215828,
      "learning_rate": 4.095597328339452e-05,
      "loss": 10.6538,
      "step": 116
    },
    {
      "epoch": 1.4054054054054055,
      "grad_norm": 0.09044484049081802,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 10.025,
      "step": 117
    },
    {
      "epoch": 1.4174174174174174,
      "grad_norm": 0.0718880295753479,
      "learning_rate": 3.933501846281267e-05,
      "loss": 10.5677,
      "step": 118
    },
    {
      "epoch": 1.4294294294294294,
      "grad_norm": 0.1045968160033226,
      "learning_rate": 3.852880399766243e-05,
      "loss": 10.1979,
      "step": 119
    },
    {
      "epoch": 1.4414414414414414,
      "grad_norm": 0.10970161855220795,
      "learning_rate": 3.772572564296005e-05,
      "loss": 10.6073,
      "step": 120
    },
    {
      "epoch": 1.4534534534534536,
      "grad_norm": 0.15321913361549377,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 10.3441,
      "step": 121
    },
    {
      "epoch": 1.4654654654654655,
      "grad_norm": 0.19315050542354584,
      "learning_rate": 3.612985456190778e-05,
      "loss": 10.0456,
      "step": 122
    },
    {
      "epoch": 1.4774774774774775,
      "grad_norm": 0.2239733636379242,
      "learning_rate": 3.533749813077677e-05,
      "loss": 10.8621,
      "step": 123
    },
    {
      "epoch": 1.4894894894894894,
      "grad_norm": 0.088536337018013,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.0326,
      "step": 124
    },
    {
      "epoch": 1.5015015015015014,
      "grad_norm": 0.07116547971963882,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 10.1143,
      "step": 125
    },
    {
      "epoch": 1.5135135135135136,
      "grad_norm": 0.08354531973600388,
      "learning_rate": 3.298534127791785e-05,
      "loss": 10.3608,
      "step": 126
    },
    {
      "epoch": 1.5255255255255256,
      "grad_norm": 0.08625448495149612,
      "learning_rate": 3.221030765387417e-05,
      "loss": 10.3084,
      "step": 127
    },
    {
      "epoch": 1.5375375375375375,
      "grad_norm": 0.06358657777309418,
      "learning_rate": 3.144013755408895e-05,
      "loss": 10.2493,
      "step": 128
    },
    {
      "epoch": 1.5495495495495497,
      "grad_norm": 0.06960482895374298,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 10.4456,
      "step": 129
    },
    {
      "epoch": 1.5615615615615615,
      "grad_norm": 0.04875503107905388,
      "learning_rate": 2.991522876735154e-05,
      "loss": 10.3582,
      "step": 130
    },
    {
      "epoch": 1.5735735735735736,
      "grad_norm": 0.10694701969623566,
      "learning_rate": 2.916090697523549e-05,
      "loss": 10.4269,
      "step": 131
    },
    {
      "epoch": 1.5855855855855856,
      "grad_norm": 0.06640373915433884,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 10.4773,
      "step": 132
    },
    {
      "epoch": 1.5975975975975976,
      "grad_norm": 0.07115697860717773,
      "learning_rate": 2.766955965735968e-05,
      "loss": 9.9671,
      "step": 133
    },
    {
      "epoch": 1.6096096096096097,
      "grad_norm": 0.05700429528951645,
      "learning_rate": 2.693294185106562e-05,
      "loss": 10.4053,
      "step": 134
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 0.0735587403178215,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 10.3518,
      "step": 135
    },
    {
      "epoch": 1.6336336336336337,
      "grad_norm": 0.10514887422323227,
      "learning_rate": 2.547882480847461e-05,
      "loss": 10.3786,
      "step": 136
    },
    {
      "epoch": 1.6456456456456456,
      "grad_norm": 0.07943972945213318,
      "learning_rate": 2.476172311325783e-05,
      "loss": 10.5937,
      "step": 137
    },
    {
      "epoch": 1.6576576576576576,
      "grad_norm": 0.10129807144403458,
      "learning_rate": 2.405152131093926e-05,
      "loss": 10.0529,
      "step": 138
    },
    {
      "epoch": 1.6696696696696698,
      "grad_norm": 0.08390870690345764,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 10.7421,
      "step": 139
    },
    {
      "epoch": 1.6816816816816815,
      "grad_norm": 0.14785560965538025,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 10.141,
      "step": 140
    },
    {
      "epoch": 1.6936936936936937,
      "grad_norm": 0.10688117891550064,
      "learning_rate": 2.196424713241637e-05,
      "loss": 10.4243,
      "step": 141
    },
    {
      "epoch": 1.7057057057057057,
      "grad_norm": 0.1796332746744156,
      "learning_rate": 2.128356686585282e-05,
      "loss": 10.3919,
      "step": 142
    },
    {
      "epoch": 1.7177177177177176,
      "grad_norm": 0.2192201018333435,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.2674,
      "step": 143
    },
    {
      "epoch": 1.7297297297297298,
      "grad_norm": 0.07705210149288177,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 10.0963,
      "step": 144
    },
    {
      "epoch": 1.7417417417417418,
      "grad_norm": 0.08380719274282455,
      "learning_rate": 1.928936436551661e-05,
      "loss": 10.3028,
      "step": 145
    },
    {
      "epoch": 1.7537537537537538,
      "grad_norm": 0.0687675029039383,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 10.3645,
      "step": 146
    },
    {
      "epoch": 1.7657657657657657,
      "grad_norm": 0.0813685953617096,
      "learning_rate": 1.800157297483417e-05,
      "loss": 10.303,
      "step": 147
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.08012548089027405,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 10.4183,
      "step": 148
    },
    {
      "epoch": 1.7897897897897899,
      "grad_norm": 0.07338238507509232,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 10.1842,
      "step": 149
    },
    {
      "epoch": 1.8018018018018018,
      "grad_norm": 0.08725876361131668,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 10.4413,
      "step": 150
    },
    {
      "epoch": 1.8018018018018018,
      "eval_loss": 10.335372924804688,
      "eval_runtime": 0.3118,
      "eval_samples_per_second": 449.015,
      "eval_steps_per_second": 112.254,
      "step": 150
    },
    {
      "epoch": 1.8138138138138138,
      "grad_norm": 0.08203451335430145,
      "learning_rate": 1.553232954407171e-05,
      "loss": 10.0847,
      "step": 151
    },
    {
      "epoch": 1.825825825825826,
      "grad_norm": 0.10485396534204483,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 10.4735,
      "step": 152
    },
    {
      "epoch": 1.8378378378378377,
      "grad_norm": 0.08351816236972809,
      "learning_rate": 1.435357758543015e-05,
      "loss": 10.376,
      "step": 153
    },
    {
      "epoch": 1.84984984984985,
      "grad_norm": 0.08282805979251862,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 10.4858,
      "step": 154
    },
    {
      "epoch": 1.8618618618618619,
      "grad_norm": 0.06912698596715927,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 10.4977,
      "step": 155
    },
    {
      "epoch": 1.8738738738738738,
      "grad_norm": 0.05990024656057358,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 10.1305,
      "step": 156
    },
    {
      "epoch": 1.885885885885886,
      "grad_norm": 0.09366833418607712,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 10.4212,
      "step": 157
    },
    {
      "epoch": 1.8978978978978978,
      "grad_norm": 0.08317462354898453,
      "learning_rate": 1.157994445715706e-05,
      "loss": 10.2669,
      "step": 158
    },
    {
      "epoch": 1.90990990990991,
      "grad_norm": 0.06542299687862396,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 10.5,
      "step": 159
    },
    {
      "epoch": 1.921921921921922,
      "grad_norm": 0.11974980682134628,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 10.2073,
      "step": 160
    },
    {
      "epoch": 1.9339339339339339,
      "grad_norm": 0.12192590534687042,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 10.3949,
      "step": 161
    },
    {
      "epoch": 1.945945945945946,
      "grad_norm": 0.18741394579410553,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.462,
      "step": 162
    },
    {
      "epoch": 1.9579579579579578,
      "grad_norm": 0.21047306060791016,
      "learning_rate": 9.068759265665384e-06,
      "loss": 10.4403,
      "step": 163
    },
    {
      "epoch": 1.96996996996997,
      "grad_norm": 0.09633217006921768,
      "learning_rate": 8.599558442598998e-06,
      "loss": 10.4283,
      "step": 164
    },
    {
      "epoch": 1.981981981981982,
      "grad_norm": 0.09279535710811615,
      "learning_rate": 8.141676086873572e-06,
      "loss": 10.5016,
      "step": 165
    },
    {
      "epoch": 1.993993993993994,
      "grad_norm": 0.1264590471982956,
      "learning_rate": 7.695237378953223e-06,
      "loss": 10.232,
      "step": 166
    },
    {
      "epoch": 2.006006006006006,
      "grad_norm": 0.5660918951034546,
      "learning_rate": 7.260364370723044e-06,
      "loss": 17.5015,
      "step": 167
    },
    {
      "epoch": 2.018018018018018,
      "grad_norm": 0.07636700570583344,
      "learning_rate": 6.837175952121306e-06,
      "loss": 10.3312,
      "step": 168
    },
    {
      "epoch": 2.03003003003003,
      "grad_norm": 0.08472772687673569,
      "learning_rate": 6.425787818636131e-06,
      "loss": 10.4095,
      "step": 169
    },
    {
      "epoch": 2.042042042042042,
      "grad_norm": 0.07472264766693115,
      "learning_rate": 6.026312439675552e-06,
      "loss": 10.1201,
      "step": 170
    },
    {
      "epoch": 2.054054054054054,
      "grad_norm": 0.06900706142187119,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 10.7351,
      "step": 171
    },
    {
      "epoch": 2.066066066066066,
      "grad_norm": 0.09336791932582855,
      "learning_rate": 5.263533508961827e-06,
      "loss": 10.1279,
      "step": 172
    },
    {
      "epoch": 2.078078078078078,
      "grad_norm": 0.07351528853178024,
      "learning_rate": 4.900438493352055e-06,
      "loss": 10.4047,
      "step": 173
    },
    {
      "epoch": 2.09009009009009,
      "grad_norm": 0.1067480817437172,
      "learning_rate": 4.549673247541875e-06,
      "loss": 10.1926,
      "step": 174
    },
    {
      "epoch": 2.1021021021021022,
      "grad_norm": 0.10185723751783371,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 10.4406,
      "step": 175
    },
    {
      "epoch": 2.114114114114114,
      "grad_norm": 0.07974503189325333,
      "learning_rate": 3.885512251130763e-06,
      "loss": 10.3356,
      "step": 176
    },
    {
      "epoch": 2.126126126126126,
      "grad_norm": 0.10168915241956711,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 10.429,
      "step": 177
    },
    {
      "epoch": 2.138138138138138,
      "grad_norm": 0.0855264887213707,
      "learning_rate": 3.271776770026963e-06,
      "loss": 10.4118,
      "step": 178
    },
    {
      "epoch": 2.15015015015015,
      "grad_norm": 0.06459216773509979,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 10.4516,
      "step": 179
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 0.08227691799402237,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 10.3692,
      "step": 180
    },
    {
      "epoch": 2.174174174174174,
      "grad_norm": 0.08134052157402039,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.0423,
      "step": 181
    },
    {
      "epoch": 2.186186186186186,
      "grad_norm": 0.1169663667678833,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 10.2857,
      "step": 182
    },
    {
      "epoch": 2.1981981981981984,
      "grad_norm": 0.11807834357023239,
      "learning_rate": 1.962316193157593e-06,
      "loss": 10.3408,
      "step": 183
    },
    {
      "epoch": 2.21021021021021,
      "grad_norm": 0.13462962210178375,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 10.8249,
      "step": 184
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.17719753086566925,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 10.001,
      "step": 185
    },
    {
      "epoch": 2.234234234234234,
      "grad_norm": 0.18614676594734192,
      "learning_rate": 1.333670137599713e-06,
      "loss": 10.4575,
      "step": 186
    },
    {
      "epoch": 2.2462462462462462,
      "grad_norm": 0.12907378375530243,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 10.2002,
      "step": 187
    },
    {
      "epoch": 2.2582582582582584,
      "grad_norm": 0.10864003747701645,
      "learning_rate": 9.810017062595322e-07,
      "loss": 10.0162,
      "step": 188
    },
    {
      "epoch": 2.27027027027027,
      "grad_norm": 0.08046580106019974,
      "learning_rate": 8.247462563808817e-07,
      "loss": 10.5991,
      "step": 189
    },
    {
      "epoch": 2.2822822822822824,
      "grad_norm": 0.06014268472790718,
      "learning_rate": 6.819348298638839e-07,
      "loss": 10.2142,
      "step": 190
    },
    {
      "epoch": 2.294294294294294,
      "grad_norm": 0.07127836346626282,
      "learning_rate": 5.526064699265753e-07,
      "loss": 10.2936,
      "step": 191
    },
    {
      "epoch": 2.3063063063063063,
      "grad_norm": 0.07464353740215302,
      "learning_rate": 4.367965336512403e-07,
      "loss": 10.4045,
      "step": 192
    },
    {
      "epoch": 2.3183183183183185,
      "grad_norm": 0.08217864483594894,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 10.3816,
      "step": 193
    },
    {
      "epoch": 2.33033033033033,
      "grad_norm": 0.052305858582258224,
      "learning_rate": 2.458548727494292e-07,
      "loss": 10.0796,
      "step": 194
    },
    {
      "epoch": 2.3423423423423424,
      "grad_norm": 0.07987543940544128,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 10.6084,
      "step": 195
    },
    {
      "epoch": 2.3543543543543546,
      "grad_norm": 0.10201536864042282,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 10.3774,
      "step": 196
    },
    {
      "epoch": 2.3663663663663663,
      "grad_norm": 0.08694560825824738,
      "learning_rate": 6.150154258476315e-08,
      "loss": 10.5723,
      "step": 197
    },
    {
      "epoch": 2.3783783783783785,
      "grad_norm": 0.07485759258270264,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 10.2715,
      "step": 198
    },
    {
      "epoch": 2.3903903903903903,
      "grad_norm": 0.09124989062547684,
      "learning_rate": 6.834750376549792e-09,
      "loss": 9.9672,
      "step": 199
    },
    {
      "epoch": 2.4024024024024024,
      "grad_norm": 0.10986769944429398,
      "learning_rate": 0.0,
      "loss": 10.7202,
      "step": 200
    },
    {
      "epoch": 2.4024024024024024,
      "eval_loss": 10.33564281463623,
      "eval_runtime": 0.3116,
      "eval_samples_per_second": 449.315,
      "eval_steps_per_second": 112.329,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 22282244456448.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}