{
  "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": 0.557092547416687,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.8067,
      "step": 1
    },
    {
      "epoch": 0.00954653937947494,
      "eval_loss": 0.8745781183242798,
      "eval_runtime": 24.2118,
      "eval_samples_per_second": 7.31,
      "eval_steps_per_second": 0.95,
      "step": 1
    },
    {
      "epoch": 0.01909307875894988,
      "grad_norm": 0.3518330752849579,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.8173,
      "step": 2
    },
    {
      "epoch": 0.028639618138424822,
      "grad_norm": 0.44602614641189575,
      "learning_rate": 6e-06,
      "loss": 0.8109,
      "step": 3
    },
    {
      "epoch": 0.03818615751789976,
      "grad_norm": 0.3439026474952698,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.8386,
      "step": 4
    },
    {
      "epoch": 0.0477326968973747,
      "grad_norm": 0.6216179728507996,
      "learning_rate": 1e-05,
      "loss": 0.8368,
      "step": 5
    },
    {
      "epoch": 0.057279236276849645,
      "grad_norm": 0.5188976526260376,
      "learning_rate": 1.2e-05,
      "loss": 0.8412,
      "step": 6
    },
    {
      "epoch": 0.06682577565632458,
      "grad_norm": 0.56082683801651,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.8185,
      "step": 7
    },
    {
      "epoch": 0.07637231503579953,
      "grad_norm": 0.3061634302139282,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.8269,
      "step": 8
    },
    {
      "epoch": 0.08591885441527446,
      "grad_norm": 0.40400129556655884,
      "learning_rate": 1.8e-05,
      "loss": 0.9036,
      "step": 9
    },
    {
      "epoch": 0.0954653937947494,
      "grad_norm": 0.3948858976364136,
      "learning_rate": 2e-05,
      "loss": 1.0401,
      "step": 10
    },
    {
      "epoch": 0.10501193317422435,
      "grad_norm": 0.4475814402103424,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.7965,
      "step": 11
    },
    {
      "epoch": 0.11455847255369929,
      "grad_norm": 0.6639652252197266,
      "learning_rate": 2.4e-05,
      "loss": 0.8854,
      "step": 12
    },
    {
      "epoch": 0.12410501193317422,
      "grad_norm": 0.3040810823440552,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.823,
      "step": 13
    },
    {
      "epoch": 0.13365155131264916,
      "grad_norm": 0.42495399713516235,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.8349,
      "step": 14
    },
    {
      "epoch": 0.1431980906921241,
      "grad_norm": 0.3658050000667572,
      "learning_rate": 3e-05,
      "loss": 0.9066,
      "step": 15
    },
    {
      "epoch": 0.15274463007159905,
      "grad_norm": 0.5003547668457031,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.915,
      "step": 16
    },
    {
      "epoch": 0.162291169451074,
      "grad_norm": 0.36432796716690063,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.8575,
      "step": 17
    },
    {
      "epoch": 0.1718377088305489,
      "grad_norm": 0.5415899157524109,
      "learning_rate": 3.6e-05,
      "loss": 0.9126,
      "step": 18
    },
    {
      "epoch": 0.18138424821002386,
      "grad_norm": 0.47764062881469727,
      "learning_rate": 3.8e-05,
      "loss": 0.7483,
      "step": 19
    },
    {
      "epoch": 0.1909307875894988,
      "grad_norm": 0.7140861749649048,
      "learning_rate": 4e-05,
      "loss": 0.7709,
      "step": 20
    },
    {
      "epoch": 0.20047732696897375,
      "grad_norm": 0.5826449394226074,
      "learning_rate": 4.2e-05,
      "loss": 0.7296,
      "step": 21
    },
    {
      "epoch": 0.2100238663484487,
      "grad_norm": 0.5641223788261414,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.7602,
      "step": 22
    },
    {
      "epoch": 0.21957040572792363,
      "grad_norm": 0.3947891592979431,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.7261,
      "step": 23
    },
    {
      "epoch": 0.22911694510739858,
      "grad_norm": 0.5210841298103333,
      "learning_rate": 4.8e-05,
      "loss": 0.7717,
      "step": 24
    },
    {
      "epoch": 0.2386634844868735,
      "grad_norm": 0.5490278005599976,
      "learning_rate": 5e-05,
      "loss": 0.7453,
      "step": 25
    },
    {
      "epoch": 0.24821002386634844,
      "grad_norm": 0.37281742691993713,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.8168,
      "step": 26
    },
    {
      "epoch": 0.2577565632458234,
      "grad_norm": 0.44266802072525024,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.7166,
      "step": 27
    },
    {
      "epoch": 0.2577565632458234,
      "eval_loss": 0.766373872756958,
      "eval_runtime": 23.8576,
      "eval_samples_per_second": 7.419,
      "eval_steps_per_second": 0.964,
      "step": 27
    },
    {
      "epoch": 0.26730310262529833,
      "grad_norm": 0.3665648400783539,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.767,
      "step": 28
    },
    {
      "epoch": 0.27684964200477324,
      "grad_norm": 0.8591362237930298,
      "learning_rate": 5.8e-05,
      "loss": 0.705,
      "step": 29
    },
    {
      "epoch": 0.2863961813842482,
      "grad_norm": 0.41430267691612244,
      "learning_rate": 6e-05,
      "loss": 0.8619,
      "step": 30
    },
    {
      "epoch": 0.29594272076372313,
      "grad_norm": 0.39334383606910706,
      "learning_rate": 6.2e-05,
      "loss": 0.6811,
      "step": 31
    },
    {
      "epoch": 0.3054892601431981,
      "grad_norm": 0.40349045395851135,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.7721,
      "step": 32
    },
    {
      "epoch": 0.315035799522673,
      "grad_norm": 1.0046414136886597,
      "learning_rate": 6.6e-05,
      "loss": 0.6848,
      "step": 33
    },
    {
      "epoch": 0.324582338902148,
      "grad_norm": 0.3854268789291382,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.66,
      "step": 34
    },
    {
      "epoch": 0.3341288782816229,
      "grad_norm": 0.4841301441192627,
      "learning_rate": 7e-05,
      "loss": 0.7041,
      "step": 35
    },
    {
      "epoch": 0.3436754176610978,
      "grad_norm": 0.5415286421775818,
      "learning_rate": 7.2e-05,
      "loss": 0.7231,
      "step": 36
    },
    {
      "epoch": 0.3532219570405728,
      "grad_norm": 0.5308293104171753,
      "learning_rate": 7.4e-05,
      "loss": 0.7049,
      "step": 37
    },
    {
      "epoch": 0.3627684964200477,
      "grad_norm": 0.6722102761268616,
      "learning_rate": 7.6e-05,
      "loss": 0.74,
      "step": 38
    },
    {
      "epoch": 0.3723150357995227,
      "grad_norm": 0.32239794731140137,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.7882,
      "step": 39
    },
    {
      "epoch": 0.3818615751789976,
      "grad_norm": 0.45458799600601196,
      "learning_rate": 8e-05,
      "loss": 0.7267,
      "step": 40
    },
    {
      "epoch": 0.3914081145584726,
      "grad_norm": 0.3064737319946289,
      "learning_rate": 8.2e-05,
      "loss": 0.7723,
      "step": 41
    },
    {
      "epoch": 0.4009546539379475,
      "grad_norm": 0.30180808901786804,
      "learning_rate": 8.4e-05,
      "loss": 0.7049,
      "step": 42
    },
    {
      "epoch": 0.4105011933174224,
      "grad_norm": 0.29743000864982605,
      "learning_rate": 8.6e-05,
      "loss": 0.7717,
      "step": 43
    },
    {
      "epoch": 0.4200477326968974,
      "grad_norm": 0.27107685804367065,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.6435,
      "step": 44
    },
    {
      "epoch": 0.4295942720763723,
      "grad_norm": 0.5112220048904419,
      "learning_rate": 9e-05,
      "loss": 0.6855,
      "step": 45
    },
    {
      "epoch": 0.43914081145584727,
      "grad_norm": 0.31432729959487915,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.7694,
      "step": 46
    },
    {
      "epoch": 0.4486873508353222,
      "grad_norm": 0.28413301706314087,
      "learning_rate": 9.4e-05,
      "loss": 0.6846,
      "step": 47
    },
    {
      "epoch": 0.45823389021479716,
      "grad_norm": 0.24350856244564056,
      "learning_rate": 9.6e-05,
      "loss": 0.6338,
      "step": 48
    },
    {
      "epoch": 0.4677804295942721,
      "grad_norm": 0.4011653959751129,
      "learning_rate": 9.8e-05,
      "loss": 0.7449,
      "step": 49
    },
    {
      "epoch": 0.477326968973747,
      "grad_norm": 1.8651820421218872,
      "learning_rate": 0.0001,
      "loss": 0.7579,
      "step": 50
    },
    {
      "epoch": 0.48687350835322196,
      "grad_norm": 0.35909950733184814,
      "learning_rate": 9.991845519630678e-05,
      "loss": 0.7355,
      "step": 51
    },
    {
      "epoch": 0.4964200477326969,
      "grad_norm": 0.3429948091506958,
      "learning_rate": 9.967408676742751e-05,
      "loss": 0.769,
      "step": 52
    },
    {
      "epoch": 0.5059665871121718,
      "grad_norm": 0.2979097068309784,
      "learning_rate": 9.926769179238466e-05,
      "loss": 0.7101,
      "step": 53
    },
    {
      "epoch": 0.5155131264916468,
      "grad_norm": 0.4369233250617981,
      "learning_rate": 9.870059584711668e-05,
      "loss": 0.7202,
      "step": 54
    },
    {
      "epoch": 0.5155131264916468,
      "eval_loss": 0.727745771408081,
      "eval_runtime": 24.7767,
      "eval_samples_per_second": 7.144,
      "eval_steps_per_second": 0.928,
      "step": 54
    },
    {
      "epoch": 0.5250596658711217,
      "grad_norm": 0.30109623074531555,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.7224,
      "step": 55
    },
    {
      "epoch": 0.5346062052505967,
      "grad_norm": 0.3661574125289917,
      "learning_rate": 9.709221818197624e-05,
      "loss": 0.6922,
      "step": 56
    },
    {
      "epoch": 0.5441527446300716,
      "grad_norm": 0.6971948146820068,
      "learning_rate": 9.60561826557425e-05,
      "loss": 0.6352,
      "step": 57
    },
    {
      "epoch": 0.5536992840095465,
      "grad_norm": 0.3875482976436615,
      "learning_rate": 9.486992143456792e-05,
      "loss": 0.7978,
      "step": 58
    },
    {
      "epoch": 0.5632458233890215,
      "grad_norm": 0.36422282457351685,
      "learning_rate": 9.353730385598887e-05,
      "loss": 0.6756,
      "step": 59
    },
    {
      "epoch": 0.5727923627684964,
      "grad_norm": 0.2757071852684021,
      "learning_rate": 9.206267664155907e-05,
      "loss": 0.6597,
      "step": 60
    },
    {
      "epoch": 0.5823389021479713,
      "grad_norm": 0.41333040595054626,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7087,
      "step": 61
    },
    {
      "epoch": 0.5918854415274463,
      "grad_norm": 0.2851635217666626,
      "learning_rate": 8.870708053195413e-05,
      "loss": 0.6639,
      "step": 62
    },
    {
      "epoch": 0.6014319809069213,
      "grad_norm": 0.8846507668495178,
      "learning_rate": 8.683705689382024e-05,
      "loss": 0.7019,
      "step": 63
    },
    {
      "epoch": 0.6109785202863962,
      "grad_norm": 0.4758082926273346,
      "learning_rate": 8.484687843276469e-05,
      "loss": 0.7133,
      "step": 64
    },
    {
      "epoch": 0.6205250596658711,
      "grad_norm": 0.5413456559181213,
      "learning_rate": 8.274303669726426e-05,
      "loss": 0.6502,
      "step": 65
    },
    {
      "epoch": 0.630071599045346,
      "grad_norm": 0.2852914333343506,
      "learning_rate": 8.053239398177191e-05,
      "loss": 0.7473,
      "step": 66
    },
    {
      "epoch": 0.639618138424821,
      "grad_norm": 0.2875913381576538,
      "learning_rate": 7.822216094333847e-05,
      "loss": 0.7285,
      "step": 67
    },
    {
      "epoch": 0.649164677804296,
      "grad_norm": 0.38858604431152344,
      "learning_rate": 7.58198730819481e-05,
      "loss": 0.7041,
      "step": 68
    },
    {
      "epoch": 0.6587112171837709,
      "grad_norm": 0.3244612216949463,
      "learning_rate": 7.333336616128369e-05,
      "loss": 0.7474,
      "step": 69
    },
    {
      "epoch": 0.6682577565632458,
      "grad_norm": 0.422497421503067,
      "learning_rate": 7.077075065009433e-05,
      "loss": 0.7319,
      "step": 70
    },
    {
      "epoch": 0.6778042959427207,
      "grad_norm": 0.5892928838729858,
      "learning_rate": 6.814038526753205e-05,
      "loss": 0.7233,
      "step": 71
    },
    {
      "epoch": 0.6873508353221957,
      "grad_norm": 0.36724957823753357,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.719,
      "step": 72
    },
    {
      "epoch": 0.6968973747016707,
      "grad_norm": 0.31456321477890015,
      "learning_rate": 6.271091670967436e-05,
      "loss": 0.7036,
      "step": 73
    },
    {
      "epoch": 0.7064439140811456,
      "grad_norm": 0.3656250536441803,
      "learning_rate": 5.992952333228728e-05,
      "loss": 0.7342,
      "step": 74
    },
    {
      "epoch": 0.7159904534606205,
      "grad_norm": 0.46808162331581116,
      "learning_rate": 5.7115741913664264e-05,
      "loss": 0.7315,
      "step": 75
    },
    {
      "epoch": 0.7255369928400954,
      "grad_norm": 0.24579700827598572,
      "learning_rate": 5.427875042394199e-05,
      "loss": 0.7165,
      "step": 76
    },
    {
      "epoch": 0.7350835322195705,
      "grad_norm": 0.3572556674480438,
      "learning_rate": 5.142780253968481e-05,
      "loss": 0.8029,
      "step": 77
    },
    {
      "epoch": 0.7446300715990454,
      "grad_norm": 0.32164067029953003,
      "learning_rate": 4.85721974603152e-05,
      "loss": 0.7031,
      "step": 78
    },
    {
      "epoch": 0.7541766109785203,
      "grad_norm": 0.4904593825340271,
      "learning_rate": 4.5721249576058027e-05,
      "loss": 0.7183,
      "step": 79
    },
    {
      "epoch": 0.7637231503579952,
      "grad_norm": 0.3569331765174866,
      "learning_rate": 4.288425808633575e-05,
      "loss": 0.6614,
      "step": 80
    },
    {
      "epoch": 0.7732696897374701,
      "grad_norm": 0.25237053632736206,
      "learning_rate": 4.007047666771274e-05,
      "loss": 0.5782,
      "step": 81
    },
    {
      "epoch": 0.7732696897374701,
      "eval_loss": 0.716273307800293,
      "eval_runtime": 23.8764,
      "eval_samples_per_second": 7.413,
      "eval_steps_per_second": 0.963,
      "step": 81
    },
    {
      "epoch": 0.7828162291169452,
      "grad_norm": 0.5811595916748047,
      "learning_rate": 3.728908329032567e-05,
      "loss": 0.751,
      "step": 82
    },
    {
      "epoch": 0.7923627684964201,
      "grad_norm": 0.3307061493396759,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6591,
      "step": 83
    },
    {
      "epoch": 0.801909307875895,
      "grad_norm": 0.37130656838417053,
      "learning_rate": 3.1859614732467954e-05,
      "loss": 0.6976,
      "step": 84
    },
    {
      "epoch": 0.8114558472553699,
      "grad_norm": 0.34512534737586975,
      "learning_rate": 2.9229249349905684e-05,
      "loss": 0.6458,
      "step": 85
    },
    {
      "epoch": 0.8210023866348448,
      "grad_norm": 0.7749953866004944,
      "learning_rate": 2.6666633838716314e-05,
      "loss": 0.6685,
      "step": 86
    },
    {
      "epoch": 0.8305489260143198,
      "grad_norm": 0.4207349419593811,
      "learning_rate": 2.418012691805191e-05,
      "loss": 0.7796,
      "step": 87
    },
    {
      "epoch": 0.8400954653937948,
      "grad_norm": 0.4382290244102478,
      "learning_rate": 2.1777839056661554e-05,
      "loss": 0.7064,
      "step": 88
    },
    {
      "epoch": 0.8496420047732697,
      "grad_norm": 0.2827201783657074,
      "learning_rate": 1.946760601822809e-05,
      "loss": 0.7097,
      "step": 89
    },
    {
      "epoch": 0.8591885441527446,
      "grad_norm": 1.0254180431365967,
      "learning_rate": 1.725696330273575e-05,
      "loss": 0.7281,
      "step": 90
    },
    {
      "epoch": 0.8687350835322196,
      "grad_norm": 0.36662358045578003,
      "learning_rate": 1.5153121567235335e-05,
      "loss": 0.6881,
      "step": 91
    },
    {
      "epoch": 0.8782816229116945,
      "grad_norm": 0.4404708445072174,
      "learning_rate": 1.3162943106179749e-05,
      "loss": 0.7104,
      "step": 92
    },
    {
      "epoch": 0.8878281622911695,
      "grad_norm": 0.35020115971565247,
      "learning_rate": 1.1292919468045877e-05,
      "loss": 0.8352,
      "step": 93
    },
    {
      "epoch": 0.8973747016706444,
      "grad_norm": 0.31341487169265747,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.747,
      "step": 94
    },
    {
      "epoch": 0.9069212410501193,
      "grad_norm": 0.29987096786499023,
      "learning_rate": 7.937323358440935e-06,
      "loss": 0.7966,
      "step": 95
    },
    {
      "epoch": 0.9164677804295943,
      "grad_norm": 0.32762154936790466,
      "learning_rate": 6.462696144011149e-06,
      "loss": 0.7366,
      "step": 96
    },
    {
      "epoch": 0.9260143198090692,
      "grad_norm": 0.7294496893882751,
      "learning_rate": 5.13007856543209e-06,
      "loss": 0.6375,
      "step": 97
    },
    {
      "epoch": 0.9355608591885441,
      "grad_norm": 0.4568740725517273,
      "learning_rate": 3.9438173442575e-06,
      "loss": 0.6917,
      "step": 98
    },
    {
      "epoch": 0.9451073985680191,
      "grad_norm": 0.37320995330810547,
      "learning_rate": 2.9077818180237693e-06,
      "loss": 0.6043,
      "step": 99
    },
    {
      "epoch": 0.954653937947494,
      "grad_norm": 0.4177183508872986,
      "learning_rate": 2.0253513192751373e-06,
      "loss": 0.643,
      "step": 100
    },
    {
      "epoch": 0.964200477326969,
      "grad_norm": 0.3155246078968048,
      "learning_rate": 1.2994041528833266e-06,
      "loss": 0.6766,
      "step": 101
    },
    {
      "epoch": 0.9737470167064439,
      "grad_norm": 0.23985552787780762,
      "learning_rate": 7.323082076153509e-07,
      "loss": 0.6213,
      "step": 102
    },
    {
      "epoch": 0.9832935560859188,
      "grad_norm": 0.3547389805316925,
      "learning_rate": 3.2591323257248893e-07,
      "loss": 0.7614,
      "step": 103
    },
    {
      "epoch": 0.9928400954653938,
      "grad_norm": 0.31457066535949707,
      "learning_rate": 8.15448036932176e-08,
      "loss": 0.6257,
      "step": 104
    },
    {
      "epoch": 1.0023866348448687,
      "grad_norm": 0.42900577187538147,
      "learning_rate": 0.0,
      "loss": 0.6607,
      "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": 6.231853181907763e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}