{
  "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": 0.7729991674423218,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.3528,
      "step": 1
    },
    {
      "epoch": 0.00954653937947494,
      "eval_loss": 1.3760640621185303,
      "eval_runtime": 15.1437,
      "eval_samples_per_second": 11.688,
      "eval_steps_per_second": 1.519,
      "step": 1
    },
    {
      "epoch": 0.01909307875894988,
      "grad_norm": 0.7421318292617798,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.3201,
      "step": 2
    },
    {
      "epoch": 0.028639618138424822,
      "grad_norm": 0.78169846534729,
      "learning_rate": 6e-06,
      "loss": 1.3624,
      "step": 3
    },
    {
      "epoch": 0.03818615751789976,
      "grad_norm": 0.8786423802375793,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.4064,
      "step": 4
    },
    {
      "epoch": 0.0477326968973747,
      "grad_norm": 0.7897927761077881,
      "learning_rate": 1e-05,
      "loss": 1.434,
      "step": 5
    },
    {
      "epoch": 0.057279236276849645,
      "grad_norm": 0.6319752335548401,
      "learning_rate": 1.2e-05,
      "loss": 1.2343,
      "step": 6
    },
    {
      "epoch": 0.06682577565632458,
      "grad_norm": 1.120063066482544,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.485,
      "step": 7
    },
    {
      "epoch": 0.07637231503579953,
      "grad_norm": 0.7847329378128052,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.4859,
      "step": 8
    },
    {
      "epoch": 0.08591885441527446,
      "grad_norm": 0.7287946939468384,
      "learning_rate": 1.8e-05,
      "loss": 1.3822,
      "step": 9
    },
    {
      "epoch": 0.0954653937947494,
      "grad_norm": 0.8428781628608704,
      "learning_rate": 2e-05,
      "loss": 1.4751,
      "step": 10
    },
    {
      "epoch": 0.10501193317422435,
      "grad_norm": 0.8861404657363892,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.5565,
      "step": 11
    },
    {
      "epoch": 0.11455847255369929,
      "grad_norm": 0.9515293836593628,
      "learning_rate": 2.4e-05,
      "loss": 1.3618,
      "step": 12
    },
    {
      "epoch": 0.12410501193317422,
      "grad_norm": 0.8454254865646362,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.3776,
      "step": 13
    },
    {
      "epoch": 0.13365155131264916,
      "grad_norm": 0.7682939767837524,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.1797,
      "step": 14
    },
    {
      "epoch": 0.1431980906921241,
      "grad_norm": 0.9922129511833191,
      "learning_rate": 3e-05,
      "loss": 1.3945,
      "step": 15
    },
    {
      "epoch": 0.15274463007159905,
      "grad_norm": 0.9234315752983093,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.3053,
      "step": 16
    },
    {
      "epoch": 0.162291169451074,
      "grad_norm": 0.8765308856964111,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.2208,
      "step": 17
    },
    {
      "epoch": 0.1718377088305489,
      "grad_norm": 0.8325808048248291,
      "learning_rate": 3.6e-05,
      "loss": 1.3017,
      "step": 18
    },
    {
      "epoch": 0.18138424821002386,
      "grad_norm": 0.7791624665260315,
      "learning_rate": 3.8e-05,
      "loss": 1.1869,
      "step": 19
    },
    {
      "epoch": 0.1909307875894988,
      "grad_norm": 0.6950303912162781,
      "learning_rate": 4e-05,
      "loss": 1.1057,
      "step": 20
    },
    {
      "epoch": 0.20047732696897375,
      "grad_norm": 0.6519060134887695,
      "learning_rate": 4.2e-05,
      "loss": 1.0183,
      "step": 21
    },
    {
      "epoch": 0.2100238663484487,
      "grad_norm": 0.5761366486549377,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.0397,
      "step": 22
    },
    {
      "epoch": 0.21957040572792363,
      "grad_norm": 0.6834986209869385,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.9179,
      "step": 23
    },
    {
      "epoch": 0.22911694510739858,
      "grad_norm": 0.5663191676139832,
      "learning_rate": 4.8e-05,
      "loss": 1.057,
      "step": 24
    },
    {
      "epoch": 0.2386634844868735,
      "grad_norm": 0.5898824334144592,
      "learning_rate": 5e-05,
      "loss": 1.0437,
      "step": 25
    },
    {
      "epoch": 0.24821002386634844,
      "grad_norm": 0.6880398392677307,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.0976,
      "step": 26
    },
    {
      "epoch": 0.2577565632458234,
      "grad_norm": 0.6800498962402344,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.0418,
      "step": 27
    },
    {
      "epoch": 0.2577565632458234,
      "eval_loss": 0.9930962324142456,
      "eval_runtime": 15.2027,
      "eval_samples_per_second": 11.643,
      "eval_steps_per_second": 1.513,
      "step": 27
    },
    {
      "epoch": 0.26730310262529833,
      "grad_norm": 0.6793673634529114,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.8749,
      "step": 28
    },
    {
      "epoch": 0.27684964200477324,
      "grad_norm": 0.5967351198196411,
      "learning_rate": 5.8e-05,
      "loss": 0.8837,
      "step": 29
    },
    {
      "epoch": 0.2863961813842482,
      "grad_norm": 0.7227113246917725,
      "learning_rate": 6e-05,
      "loss": 1.0474,
      "step": 30
    },
    {
      "epoch": 0.29594272076372313,
      "grad_norm": 0.5008341073989868,
      "learning_rate": 6.2e-05,
      "loss": 0.7315,
      "step": 31
    },
    {
      "epoch": 0.3054892601431981,
      "grad_norm": 0.5201082825660706,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.8185,
      "step": 32
    },
    {
      "epoch": 0.315035799522673,
      "grad_norm": 0.49358299374580383,
      "learning_rate": 6.6e-05,
      "loss": 0.8082,
      "step": 33
    },
    {
      "epoch": 0.324582338902148,
      "grad_norm": 0.6238221526145935,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.9792,
      "step": 34
    },
    {
      "epoch": 0.3341288782816229,
      "grad_norm": 0.5519028902053833,
      "learning_rate": 7e-05,
      "loss": 0.8038,
      "step": 35
    },
    {
      "epoch": 0.3436754176610978,
      "grad_norm": 0.4811299443244934,
      "learning_rate": 7.2e-05,
      "loss": 0.7199,
      "step": 36
    },
    {
      "epoch": 0.3532219570405728,
      "grad_norm": 0.4762420058250427,
      "learning_rate": 7.4e-05,
      "loss": 0.7721,
      "step": 37
    },
    {
      "epoch": 0.3627684964200477,
      "grad_norm": 0.48886463046073914,
      "learning_rate": 7.6e-05,
      "loss": 0.9468,
      "step": 38
    },
    {
      "epoch": 0.3723150357995227,
      "grad_norm": 0.4723183214664459,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.8051,
      "step": 39
    },
    {
      "epoch": 0.3818615751789976,
      "grad_norm": 0.4841081202030182,
      "learning_rate": 8e-05,
      "loss": 0.8858,
      "step": 40
    },
    {
      "epoch": 0.3914081145584726,
      "grad_norm": 0.5030905604362488,
      "learning_rate": 8.2e-05,
      "loss": 0.8501,
      "step": 41
    },
    {
      "epoch": 0.4009546539379475,
      "grad_norm": 0.48235172033309937,
      "learning_rate": 8.4e-05,
      "loss": 0.8726,
      "step": 42
    },
    {
      "epoch": 0.4105011933174224,
      "grad_norm": 0.44874662160873413,
      "learning_rate": 8.6e-05,
      "loss": 0.8708,
      "step": 43
    },
    {
      "epoch": 0.4200477326968974,
      "grad_norm": 0.42467233538627625,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.7977,
      "step": 44
    },
    {
      "epoch": 0.4295942720763723,
      "grad_norm": 0.5132670998573303,
      "learning_rate": 9e-05,
      "loss": 0.9207,
      "step": 45
    },
    {
      "epoch": 0.43914081145584727,
      "grad_norm": 0.46287962794303894,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.8661,
      "step": 46
    },
    {
      "epoch": 0.4486873508353222,
      "grad_norm": 0.5267254114151001,
      "learning_rate": 9.4e-05,
      "loss": 0.8881,
      "step": 47
    },
    {
      "epoch": 0.45823389021479716,
      "grad_norm": 0.40659984946250916,
      "learning_rate": 9.6e-05,
      "loss": 0.767,
      "step": 48
    },
    {
      "epoch": 0.4677804295942721,
      "grad_norm": 0.4650416672229767,
      "learning_rate": 9.8e-05,
      "loss": 0.8193,
      "step": 49
    },
    {
      "epoch": 0.477326968973747,
      "grad_norm": 0.4663059115409851,
      "learning_rate": 0.0001,
      "loss": 0.8991,
      "step": 50
    },
    {
      "epoch": 0.48687350835322196,
      "grad_norm": 0.4561784863471985,
      "learning_rate": 9.991845519630678e-05,
      "loss": 0.8328,
      "step": 51
    },
    {
      "epoch": 0.4964200477326969,
      "grad_norm": 0.47212183475494385,
      "learning_rate": 9.967408676742751e-05,
      "loss": 1.0138,
      "step": 52
    },
    {
      "epoch": 0.5059665871121718,
      "grad_norm": 0.4596843421459198,
      "learning_rate": 9.926769179238466e-05,
      "loss": 0.8194,
      "step": 53
    },
    {
      "epoch": 0.5155131264916468,
      "grad_norm": 0.48445579409599304,
      "learning_rate": 9.870059584711668e-05,
      "loss": 0.8578,
      "step": 54
    },
    {
      "epoch": 0.5155131264916468,
      "eval_loss": 0.8235141038894653,
      "eval_runtime": 15.2912,
      "eval_samples_per_second": 11.575,
      "eval_steps_per_second": 1.504,
      "step": 54
    },
    {
      "epoch": 0.5250596658711217,
      "grad_norm": 0.5108307003974915,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.7965,
      "step": 55
    },
    {
      "epoch": 0.5346062052505967,
      "grad_norm": 0.4277663826942444,
      "learning_rate": 9.709221818197624e-05,
      "loss": 0.7909,
      "step": 56
    },
    {
      "epoch": 0.5441527446300716,
      "grad_norm": 0.5081710815429688,
      "learning_rate": 9.60561826557425e-05,
      "loss": 0.7809,
      "step": 57
    },
    {
      "epoch": 0.5536992840095465,
      "grad_norm": 0.4631445109844208,
      "learning_rate": 9.486992143456792e-05,
      "loss": 0.7974,
      "step": 58
    },
    {
      "epoch": 0.5632458233890215,
      "grad_norm": 0.39287981390953064,
      "learning_rate": 9.353730385598887e-05,
      "loss": 0.7537,
      "step": 59
    },
    {
      "epoch": 0.5727923627684964,
      "grad_norm": 0.48041170835494995,
      "learning_rate": 9.206267664155907e-05,
      "loss": 0.7408,
      "step": 60
    },
    {
      "epoch": 0.5823389021479713,
      "grad_norm": 0.44933608174324036,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7646,
      "step": 61
    },
    {
      "epoch": 0.5918854415274463,
      "grad_norm": 0.41547736525535583,
      "learning_rate": 8.870708053195413e-05,
      "loss": 0.7062,
      "step": 62
    },
    {
      "epoch": 0.6014319809069213,
      "grad_norm": 0.4186669886112213,
      "learning_rate": 8.683705689382024e-05,
      "loss": 0.7477,
      "step": 63
    },
    {
      "epoch": 0.6109785202863962,
      "grad_norm": 0.4994564950466156,
      "learning_rate": 8.484687843276469e-05,
      "loss": 0.7413,
      "step": 64
    },
    {
      "epoch": 0.6205250596658711,
      "grad_norm": 0.5049386024475098,
      "learning_rate": 8.274303669726426e-05,
      "loss": 0.7716,
      "step": 65
    },
    {
      "epoch": 0.630071599045346,
      "grad_norm": 0.47772884368896484,
      "learning_rate": 8.053239398177191e-05,
      "loss": 0.7985,
      "step": 66
    },
    {
      "epoch": 0.639618138424821,
      "grad_norm": 0.48465287685394287,
      "learning_rate": 7.822216094333847e-05,
      "loss": 0.8437,
      "step": 67
    },
    {
      "epoch": 0.649164677804296,
      "grad_norm": 0.4179917573928833,
      "learning_rate": 7.58198730819481e-05,
      "loss": 0.6818,
      "step": 68
    },
    {
      "epoch": 0.6587112171837709,
      "grad_norm": 0.47298485040664673,
      "learning_rate": 7.333336616128369e-05,
      "loss": 0.765,
      "step": 69
    },
    {
      "epoch": 0.6682577565632458,
      "grad_norm": 0.4757786691188812,
      "learning_rate": 7.077075065009433e-05,
      "loss": 0.8309,
      "step": 70
    },
    {
      "epoch": 0.6778042959427207,
      "grad_norm": 0.5239489078521729,
      "learning_rate": 6.814038526753205e-05,
      "loss": 0.7407,
      "step": 71
    },
    {
      "epoch": 0.6873508353221957,
      "grad_norm": 0.41038060188293457,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.697,
      "step": 72
    },
    {
      "epoch": 0.6968973747016707,
      "grad_norm": 0.46868184208869934,
      "learning_rate": 6.271091670967436e-05,
      "loss": 0.7811,
      "step": 73
    },
    {
      "epoch": 0.7064439140811456,
      "grad_norm": 0.4154309332370758,
      "learning_rate": 5.992952333228728e-05,
      "loss": 0.7807,
      "step": 74
    },
    {
      "epoch": 0.7159904534606205,
      "grad_norm": 0.5158439874649048,
      "learning_rate": 5.7115741913664264e-05,
      "loss": 0.781,
      "step": 75
    },
    {
      "epoch": 0.7255369928400954,
      "grad_norm": 0.4497659206390381,
      "learning_rate": 5.427875042394199e-05,
      "loss": 0.7352,
      "step": 76
    },
    {
      "epoch": 0.7350835322195705,
      "grad_norm": 0.4497024714946747,
      "learning_rate": 5.142780253968481e-05,
      "loss": 0.8149,
      "step": 77
    },
    {
      "epoch": 0.7446300715990454,
      "grad_norm": 0.5153495669364929,
      "learning_rate": 4.85721974603152e-05,
      "loss": 0.803,
      "step": 78
    },
    {
      "epoch": 0.7541766109785203,
      "grad_norm": 0.5138677954673767,
      "learning_rate": 4.5721249576058027e-05,
      "loss": 0.8476,
      "step": 79
    },
    {
      "epoch": 0.7637231503579952,
      "grad_norm": 0.44010061025619507,
      "learning_rate": 4.288425808633575e-05,
      "loss": 0.6618,
      "step": 80
    },
    {
      "epoch": 0.7732696897374701,
      "grad_norm": 0.47962653636932373,
      "learning_rate": 4.007047666771274e-05,
      "loss": 0.6646,
      "step": 81
    },
    {
      "epoch": 0.7732696897374701,
      "eval_loss": 0.7901555299758911,
      "eval_runtime": 15.3642,
      "eval_samples_per_second": 11.52,
      "eval_steps_per_second": 1.497,
      "step": 81
    },
    {
      "epoch": 0.7828162291169452,
      "grad_norm": 0.47462138533592224,
      "learning_rate": 3.728908329032567e-05,
      "loss": 0.8627,
      "step": 82
    },
    {
      "epoch": 0.7923627684964201,
      "grad_norm": 0.47427991032600403,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7332,
      "step": 83
    },
    {
      "epoch": 0.801909307875895,
      "grad_norm": 0.47528794407844543,
      "learning_rate": 3.1859614732467954e-05,
      "loss": 0.7013,
      "step": 84
    },
    {
      "epoch": 0.8114558472553699,
      "grad_norm": 0.44222989678382874,
      "learning_rate": 2.9229249349905684e-05,
      "loss": 0.8364,
      "step": 85
    },
    {
      "epoch": 0.8210023866348448,
      "grad_norm": 0.47421371936798096,
      "learning_rate": 2.6666633838716314e-05,
      "loss": 0.8119,
      "step": 86
    },
    {
      "epoch": 0.8305489260143198,
      "grad_norm": 0.4924468994140625,
      "learning_rate": 2.418012691805191e-05,
      "loss": 0.77,
      "step": 87
    },
    {
      "epoch": 0.8400954653937948,
      "grad_norm": 0.40210720896720886,
      "learning_rate": 2.1777839056661554e-05,
      "loss": 0.7803,
      "step": 88
    },
    {
      "epoch": 0.8496420047732697,
      "grad_norm": 0.5243187546730042,
      "learning_rate": 1.946760601822809e-05,
      "loss": 0.7299,
      "step": 89
    },
    {
      "epoch": 0.8591885441527446,
      "grad_norm": 0.5231001973152161,
      "learning_rate": 1.725696330273575e-05,
      "loss": 0.7132,
      "step": 90
    },
    {
      "epoch": 0.8687350835322196,
      "grad_norm": 0.45164862275123596,
      "learning_rate": 1.5153121567235335e-05,
      "loss": 0.789,
      "step": 91
    },
    {
      "epoch": 0.8782816229116945,
      "grad_norm": 0.4867713153362274,
      "learning_rate": 1.3162943106179749e-05,
      "loss": 0.813,
      "step": 92
    },
    {
      "epoch": 0.8878281622911695,
      "grad_norm": 0.4710329473018646,
      "learning_rate": 1.1292919468045877e-05,
      "loss": 0.8684,
      "step": 93
    },
    {
      "epoch": 0.8973747016706444,
      "grad_norm": 0.48433560132980347,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7324,
      "step": 94
    },
    {
      "epoch": 0.9069212410501193,
      "grad_norm": 0.4514448046684265,
      "learning_rate": 7.937323358440935e-06,
      "loss": 0.7719,
      "step": 95
    },
    {
      "epoch": 0.9164677804295943,
      "grad_norm": 0.4830509126186371,
      "learning_rate": 6.462696144011149e-06,
      "loss": 0.8987,
      "step": 96
    },
    {
      "epoch": 0.9260143198090692,
      "grad_norm": 0.5141445994377136,
      "learning_rate": 5.13007856543209e-06,
      "loss": 0.8597,
      "step": 97
    },
    {
      "epoch": 0.9355608591885441,
      "grad_norm": 0.4968259632587433,
      "learning_rate": 3.9438173442575e-06,
      "loss": 0.6708,
      "step": 98
    },
    {
      "epoch": 0.9451073985680191,
      "grad_norm": 0.41604942083358765,
      "learning_rate": 2.9077818180237693e-06,
      "loss": 0.7536,
      "step": 99
    },
    {
      "epoch": 0.954653937947494,
      "grad_norm": 0.4381095767021179,
      "learning_rate": 2.0253513192751373e-06,
      "loss": 0.7521,
      "step": 100
    },
    {
      "epoch": 0.964200477326969,
      "grad_norm": 0.478782594203949,
      "learning_rate": 1.2994041528833266e-06,
      "loss": 0.7407,
      "step": 101
    },
    {
      "epoch": 0.9737470167064439,
      "grad_norm": 0.5015021562576294,
      "learning_rate": 7.323082076153509e-07,
      "loss": 0.6993,
      "step": 102
    },
    {
      "epoch": 0.9832935560859188,
      "grad_norm": 0.5261812210083008,
      "learning_rate": 3.2591323257248893e-07,
      "loss": 0.7057,
      "step": 103
    },
    {
      "epoch": 0.9928400954653938,
      "grad_norm": 0.39763128757476807,
      "learning_rate": 8.15448036932176e-08,
      "loss": 0.8127,
      "step": 104
    },
    {
      "epoch": 1.0023866348448687,
      "grad_norm": 0.5115617513656616,
      "learning_rate": 0.0,
      "loss": 0.7129,
      "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": 2.3476680605564928e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}