{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0023866348448687,
  "eval_steps": 27,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00954653937947494,
      "grad_norm": 1.1581295728683472,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.4365,
      "step": 1
    },
    {
      "epoch": 0.00954653937947494,
      "eval_loss": 1.4670641422271729,
      "eval_runtime": 8.1199,
      "eval_samples_per_second": 21.798,
      "eval_steps_per_second": 2.833,
      "step": 1
    },
    {
      "epoch": 0.01909307875894988,
      "grad_norm": 1.087159276008606,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.4077,
      "step": 2
    },
    {
      "epoch": 0.028639618138424822,
      "grad_norm": 1.090128779411316,
      "learning_rate": 6e-06,
      "loss": 1.4455,
      "step": 3
    },
    {
      "epoch": 0.03818615751789976,
      "grad_norm": 1.016130805015564,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.4959,
      "step": 4
    },
    {
      "epoch": 0.0477326968973747,
      "grad_norm": 1.229004979133606,
      "learning_rate": 1e-05,
      "loss": 1.5535,
      "step": 5
    },
    {
      "epoch": 0.057279236276849645,
      "grad_norm": 0.9961005449295044,
      "learning_rate": 1.2e-05,
      "loss": 1.3715,
      "step": 6
    },
    {
      "epoch": 0.06682577565632458,
      "grad_norm": 1.060661792755127,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.5691,
      "step": 7
    },
    {
      "epoch": 0.07637231503579953,
      "grad_norm": 1.1355772018432617,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.5431,
      "step": 8
    },
    {
      "epoch": 0.08591885441527446,
      "grad_norm": 1.0910701751708984,
      "learning_rate": 1.8e-05,
      "loss": 1.4848,
      "step": 9
    },
    {
      "epoch": 0.0954653937947494,
      "grad_norm": 1.2631629705429077,
      "learning_rate": 2e-05,
      "loss": 1.5394,
      "step": 10
    },
    {
      "epoch": 0.10501193317422435,
      "grad_norm": 1.1491081714630127,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.5908,
      "step": 11
    },
    {
      "epoch": 0.11455847255369929,
      "grad_norm": 1.119293212890625,
      "learning_rate": 2.4e-05,
      "loss": 1.4397,
      "step": 12
    },
    {
      "epoch": 0.12410501193317422,
      "grad_norm": 1.1145578622817993,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.4399,
      "step": 13
    },
    {
      "epoch": 0.13365155131264916,
      "grad_norm": 1.0823482275009155,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.2609,
      "step": 14
    },
    {
      "epoch": 0.1431980906921241,
      "grad_norm": 1.1908745765686035,
      "learning_rate": 3e-05,
      "loss": 1.4315,
      "step": 15
    },
    {
      "epoch": 0.15274463007159905,
      "grad_norm": 1.2168711423873901,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.4049,
      "step": 16
    },
    {
      "epoch": 0.162291169451074,
      "grad_norm": 1.1079556941986084,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.2861,
      "step": 17
    },
    {
      "epoch": 0.1718377088305489,
      "grad_norm": 1.0967084169387817,
      "learning_rate": 3.6e-05,
      "loss": 1.4193,
      "step": 18
    },
    {
      "epoch": 0.18138424821002386,
      "grad_norm": 0.9369730353355408,
      "learning_rate": 3.8e-05,
      "loss": 1.2763,
      "step": 19
    },
    {
      "epoch": 0.1909307875894988,
      "grad_norm": 0.8679376840591431,
      "learning_rate": 4e-05,
      "loss": 1.2243,
      "step": 20
    },
    {
      "epoch": 0.20047732696897375,
      "grad_norm": 0.8165419101715088,
      "learning_rate": 4.2e-05,
      "loss": 1.1128,
      "step": 21
    },
    {
      "epoch": 0.2100238663484487,
      "grad_norm": 0.795780599117279,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.1408,
      "step": 22
    },
    {
      "epoch": 0.21957040572792363,
      "grad_norm": 0.855648934841156,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.0223,
      "step": 23
    },
    {
      "epoch": 0.22911694510739858,
      "grad_norm": 0.9288350343704224,
      "learning_rate": 4.8e-05,
      "loss": 1.1839,
      "step": 24
    },
    {
      "epoch": 0.2386634844868735,
      "grad_norm": 0.8809741735458374,
      "learning_rate": 5e-05,
      "loss": 1.1453,
      "step": 25
    },
    {
      "epoch": 0.24821002386634844,
      "grad_norm": 1.0089377164840698,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.2415,
      "step": 26
    },
    {
      "epoch": 0.2577565632458234,
      "grad_norm": 0.946299135684967,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.1781,
      "step": 27
    },
    {
      "epoch": 0.2577565632458234,
      "eval_loss": 1.0924198627471924,
      "eval_runtime": 8.1984,
      "eval_samples_per_second": 21.59,
      "eval_steps_per_second": 2.805,
      "step": 27
    },
    {
      "epoch": 0.26730310262529833,
      "grad_norm": 0.8230865001678467,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.9903,
      "step": 28
    },
    {
      "epoch": 0.27684964200477324,
      "grad_norm": 0.7844314575195312,
      "learning_rate": 5.8e-05,
      "loss": 0.9783,
      "step": 29
    },
    {
      "epoch": 0.2863961813842482,
      "grad_norm": 0.9001813530921936,
      "learning_rate": 6e-05,
      "loss": 1.1791,
      "step": 30
    },
    {
      "epoch": 0.29594272076372313,
      "grad_norm": 0.7716610431671143,
      "learning_rate": 6.2e-05,
      "loss": 0.836,
      "step": 31
    },
    {
      "epoch": 0.3054892601431981,
      "grad_norm": 0.8092612624168396,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.9514,
      "step": 32
    },
    {
      "epoch": 0.315035799522673,
      "grad_norm": 0.6922733187675476,
      "learning_rate": 6.6e-05,
      "loss": 0.9482,
      "step": 33
    },
    {
      "epoch": 0.324582338902148,
      "grad_norm": 0.8486894369125366,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.1341,
      "step": 34
    },
    {
      "epoch": 0.3341288782816229,
      "grad_norm": 0.7794960737228394,
      "learning_rate": 7e-05,
      "loss": 0.9095,
      "step": 35
    },
    {
      "epoch": 0.3436754176610978,
      "grad_norm": 0.6831135749816895,
      "learning_rate": 7.2e-05,
      "loss": 0.8577,
      "step": 36
    },
    {
      "epoch": 0.3532219570405728,
      "grad_norm": 0.6687945127487183,
      "learning_rate": 7.4e-05,
      "loss": 0.9191,
      "step": 37
    },
    {
      "epoch": 0.3627684964200477,
      "grad_norm": 0.814834713935852,
      "learning_rate": 7.6e-05,
      "loss": 1.1101,
      "step": 38
    },
    {
      "epoch": 0.3723150357995227,
      "grad_norm": 0.688315212726593,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.9378,
      "step": 39
    },
    {
      "epoch": 0.3818615751789976,
      "grad_norm": 0.6707736849784851,
      "learning_rate": 8e-05,
      "loss": 1.0117,
      "step": 40
    },
    {
      "epoch": 0.3914081145584726,
      "grad_norm": 0.7500569820404053,
      "learning_rate": 8.2e-05,
      "loss": 0.977,
      "step": 41
    },
    {
      "epoch": 0.4009546539379475,
      "grad_norm": 0.705565869808197,
      "learning_rate": 8.4e-05,
      "loss": 0.9934,
      "step": 42
    },
    {
      "epoch": 0.4105011933174224,
      "grad_norm": 0.6945461630821228,
      "learning_rate": 8.6e-05,
      "loss": 1.0087,
      "step": 43
    },
    {
      "epoch": 0.4200477326968974,
      "grad_norm": 0.6348851919174194,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.9125,
      "step": 44
    },
    {
      "epoch": 0.4295942720763723,
      "grad_norm": 0.7663906812667847,
      "learning_rate": 9e-05,
      "loss": 1.0911,
      "step": 45
    },
    {
      "epoch": 0.43914081145584727,
      "grad_norm": 0.7021864056587219,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.968,
      "step": 46
    },
    {
      "epoch": 0.4486873508353222,
      "grad_norm": 0.7950401902198792,
      "learning_rate": 9.4e-05,
      "loss": 1.0305,
      "step": 47
    },
    {
      "epoch": 0.45823389021479716,
      "grad_norm": 0.6142714023590088,
      "learning_rate": 9.6e-05,
      "loss": 0.8971,
      "step": 48
    },
    {
      "epoch": 0.4677804295942721,
      "grad_norm": 0.7328237891197205,
      "learning_rate": 9.8e-05,
      "loss": 0.9588,
      "step": 49
    },
    {
      "epoch": 0.477326968973747,
      "grad_norm": 0.6805174350738525,
      "learning_rate": 0.0001,
      "loss": 1.0522,
      "step": 50
    },
    {
      "epoch": 0.48687350835322196,
      "grad_norm": 0.711742639541626,
      "learning_rate": 9.991845519630678e-05,
      "loss": 0.9688,
      "step": 51
    },
    {
      "epoch": 0.4964200477326969,
      "grad_norm": 0.7530347108840942,
      "learning_rate": 9.967408676742751e-05,
      "loss": 1.1328,
      "step": 52
    },
    {
      "epoch": 0.5059665871121718,
      "grad_norm": 0.7360132932662964,
      "learning_rate": 9.926769179238466e-05,
      "loss": 0.9473,
      "step": 53
    },
    {
      "epoch": 0.5155131264916468,
      "grad_norm": 0.7543603777885437,
      "learning_rate": 9.870059584711668e-05,
      "loss": 0.9832,
      "step": 54
    },
    {
      "epoch": 0.5155131264916468,
      "eval_loss": 0.9416201114654541,
      "eval_runtime": 8.2245,
      "eval_samples_per_second": 21.521,
      "eval_steps_per_second": 2.797,
      "step": 54
    },
    {
      "epoch": 0.5250596658711217,
      "grad_norm": 0.7905960083007812,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.9173,
      "step": 55
    },
    {
      "epoch": 0.5346062052505967,
      "grad_norm": 0.6153451800346375,
      "learning_rate": 9.709221818197624e-05,
      "loss": 0.9088,
      "step": 56
    },
    {
      "epoch": 0.5441527446300716,
      "grad_norm": 0.720894992351532,
      "learning_rate": 9.60561826557425e-05,
      "loss": 0.8903,
      "step": 57
    },
    {
      "epoch": 0.5536992840095465,
      "grad_norm": 0.7339727878570557,
      "learning_rate": 9.486992143456792e-05,
      "loss": 0.94,
      "step": 58
    },
    {
      "epoch": 0.5632458233890215,
      "grad_norm": 0.5987541675567627,
      "learning_rate": 9.353730385598887e-05,
      "loss": 0.8702,
      "step": 59
    },
    {
      "epoch": 0.5727923627684964,
      "grad_norm": 0.7179649472236633,
      "learning_rate": 9.206267664155907e-05,
      "loss": 0.8679,
      "step": 60
    },
    {
      "epoch": 0.5823389021479713,
      "grad_norm": 0.6728019714355469,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8726,
      "step": 61
    },
    {
      "epoch": 0.5918854415274463,
      "grad_norm": 0.6495327353477478,
      "learning_rate": 8.870708053195413e-05,
      "loss": 0.823,
      "step": 62
    },
    {
      "epoch": 0.6014319809069213,
      "grad_norm": 0.597614586353302,
      "learning_rate": 8.683705689382024e-05,
      "loss": 0.8773,
      "step": 63
    },
    {
      "epoch": 0.6109785202863962,
      "grad_norm": 0.7181035876274109,
      "learning_rate": 8.484687843276469e-05,
      "loss": 0.8716,
      "step": 64
    },
    {
      "epoch": 0.6205250596658711,
      "grad_norm": 0.7859545350074768,
      "learning_rate": 8.274303669726426e-05,
      "loss": 0.9172,
      "step": 65
    },
    {
      "epoch": 0.630071599045346,
      "grad_norm": 0.7442716360092163,
      "learning_rate": 8.053239398177191e-05,
      "loss": 0.9197,
      "step": 66
    },
    {
      "epoch": 0.639618138424821,
      "grad_norm": 0.7191454172134399,
      "learning_rate": 7.822216094333847e-05,
      "loss": 0.9585,
      "step": 67
    },
    {
      "epoch": 0.649164677804296,
      "grad_norm": 0.6757006645202637,
      "learning_rate": 7.58198730819481e-05,
      "loss": 0.811,
      "step": 68
    },
    {
      "epoch": 0.6587112171837709,
      "grad_norm": 0.7337505221366882,
      "learning_rate": 7.333336616128369e-05,
      "loss": 0.8943,
      "step": 69
    },
    {
      "epoch": 0.6682577565632458,
      "grad_norm": 0.7532724142074585,
      "learning_rate": 7.077075065009433e-05,
      "loss": 0.9695,
      "step": 70
    },
    {
      "epoch": 0.6778042959427207,
      "grad_norm": 0.7243386507034302,
      "learning_rate": 6.814038526753205e-05,
      "loss": 0.8509,
      "step": 71
    },
    {
      "epoch": 0.6873508353221957,
      "grad_norm": 0.5878617167472839,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7937,
      "step": 72
    },
    {
      "epoch": 0.6968973747016707,
      "grad_norm": 0.704180121421814,
      "learning_rate": 6.271091670967436e-05,
      "loss": 0.9021,
      "step": 73
    },
    {
      "epoch": 0.7064439140811456,
      "grad_norm": 0.6195005178451538,
      "learning_rate": 5.992952333228728e-05,
      "loss": 0.8891,
      "step": 74
    },
    {
      "epoch": 0.7159904534606205,
      "grad_norm": 0.7697818279266357,
      "learning_rate": 5.7115741913664264e-05,
      "loss": 0.9174,
      "step": 75
    },
    {
      "epoch": 0.7255369928400954,
      "grad_norm": 0.6679143309593201,
      "learning_rate": 5.427875042394199e-05,
      "loss": 0.8582,
      "step": 76
    },
    {
      "epoch": 0.7350835322195705,
      "grad_norm": 0.6472037434577942,
      "learning_rate": 5.142780253968481e-05,
      "loss": 0.9191,
      "step": 77
    },
    {
      "epoch": 0.7446300715990454,
      "grad_norm": 0.7160825729370117,
      "learning_rate": 4.85721974603152e-05,
      "loss": 0.9225,
      "step": 78
    },
    {
      "epoch": 0.7541766109785203,
      "grad_norm": 0.7306458353996277,
      "learning_rate": 4.5721249576058027e-05,
      "loss": 1.0029,
      "step": 79
    },
    {
      "epoch": 0.7637231503579952,
      "grad_norm": 0.6334691047668457,
      "learning_rate": 4.288425808633575e-05,
      "loss": 0.7884,
      "step": 80
    },
    {
      "epoch": 0.7732696897374701,
      "grad_norm": 0.6406896710395813,
      "learning_rate": 4.007047666771274e-05,
      "loss": 0.7667,
      "step": 81
    },
    {
      "epoch": 0.7732696897374701,
      "eval_loss": 0.9063246846199036,
      "eval_runtime": 8.2312,
      "eval_samples_per_second": 21.503,
      "eval_steps_per_second": 2.794,
      "step": 81
    },
    {
      "epoch": 0.7828162291169452,
      "grad_norm": 0.6602100133895874,
      "learning_rate": 3.728908329032567e-05,
      "loss": 0.9741,
      "step": 82
    },
    {
      "epoch": 0.7923627684964201,
      "grad_norm": 0.6851309537887573,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8647,
      "step": 83
    },
    {
      "epoch": 0.801909307875895,
      "grad_norm": 0.680729329586029,
      "learning_rate": 3.1859614732467954e-05,
      "loss": 0.7929,
      "step": 84
    },
    {
      "epoch": 0.8114558472553699,
      "grad_norm": 0.6340180039405823,
      "learning_rate": 2.9229249349905684e-05,
      "loss": 0.9433,
      "step": 85
    },
    {
      "epoch": 0.8210023866348448,
      "grad_norm": 0.6609524488449097,
      "learning_rate": 2.6666633838716314e-05,
      "loss": 0.8995,
      "step": 86
    },
    {
      "epoch": 0.8305489260143198,
      "grad_norm": 0.7029539346694946,
      "learning_rate": 2.418012691805191e-05,
      "loss": 0.8734,
      "step": 87
    },
    {
      "epoch": 0.8400954653937948,
      "grad_norm": 0.6024286150932312,
      "learning_rate": 2.1777839056661554e-05,
      "loss": 0.9002,
      "step": 88
    },
    {
      "epoch": 0.8496420047732697,
      "grad_norm": 0.7673961520195007,
      "learning_rate": 1.946760601822809e-05,
      "loss": 0.8419,
      "step": 89
    },
    {
      "epoch": 0.8591885441527446,
      "grad_norm": 0.7521714568138123,
      "learning_rate": 1.725696330273575e-05,
      "loss": 0.832,
      "step": 90
    },
    {
      "epoch": 0.8687350835322196,
      "grad_norm": 0.6552139520645142,
      "learning_rate": 1.5153121567235335e-05,
      "loss": 0.9092,
      "step": 91
    },
    {
      "epoch": 0.8782816229116945,
      "grad_norm": 0.6894174814224243,
      "learning_rate": 1.3162943106179749e-05,
      "loss": 0.9305,
      "step": 92
    },
    {
      "epoch": 0.8878281622911695,
      "grad_norm": 0.6434057354927063,
      "learning_rate": 1.1292919468045877e-05,
      "loss": 0.9907,
      "step": 93
    },
    {
      "epoch": 0.8973747016706444,
      "grad_norm": 0.7067898511886597,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8351,
      "step": 94
    },
    {
      "epoch": 0.9069212410501193,
      "grad_norm": 0.6394110918045044,
      "learning_rate": 7.937323358440935e-06,
      "loss": 0.8929,
      "step": 95
    },
    {
      "epoch": 0.9164677804295943,
      "grad_norm": 0.6856904029846191,
      "learning_rate": 6.462696144011149e-06,
      "loss": 1.0369,
      "step": 96
    },
    {
      "epoch": 0.9260143198090692,
      "grad_norm": 0.6826223134994507,
      "learning_rate": 5.13007856543209e-06,
      "loss": 0.9873,
      "step": 97
    },
    {
      "epoch": 0.9355608591885441,
      "grad_norm": 0.7302625775337219,
      "learning_rate": 3.9438173442575e-06,
      "loss": 0.7765,
      "step": 98
    },
    {
      "epoch": 0.9451073985680191,
      "grad_norm": 0.5783309936523438,
      "learning_rate": 2.9077818180237693e-06,
      "loss": 0.8436,
      "step": 99
    },
    {
      "epoch": 0.954653937947494,
      "grad_norm": 0.6663295030593872,
      "learning_rate": 2.0253513192751373e-06,
      "loss": 0.8694,
      "step": 100
    },
    {
      "epoch": 0.964200477326969,
      "grad_norm": 0.699268639087677,
      "learning_rate": 1.2994041528833266e-06,
      "loss": 0.8382,
      "step": 101
    },
    {
      "epoch": 0.9737470167064439,
      "grad_norm": 0.7265623807907104,
      "learning_rate": 7.323082076153509e-07,
      "loss": 0.8254,
      "step": 102
    },
    {
      "epoch": 0.9832935560859188,
      "grad_norm": 0.7307024002075195,
      "learning_rate": 3.2591323257248893e-07,
      "loss": 0.8123,
      "step": 103
    },
    {
      "epoch": 0.9928400954653938,
      "grad_norm": 0.5885692834854126,
      "learning_rate": 8.15448036932176e-08,
      "loss": 0.9573,
      "step": 104
    },
    {
      "epoch": 1.0023866348448687,
      "grad_norm": 0.711481511592865,
      "learning_rate": 0.0,
      "loss": 0.8124,
      "step": 105
    }
  ],
  "logging_steps": 1,
  "max_steps": 105,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.128869584338944e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}