{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018417902200939314,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018417902200939314,
      "grad_norm": 0.2921212315559387,
      "learning_rate": 1e-05,
      "loss": 1.9392,
      "step": 1
    },
    {
      "epoch": 0.00018417902200939314,
      "eval_loss": 0.9574140310287476,
      "eval_runtime": 1373.9612,
      "eval_samples_per_second": 3.328,
      "eval_steps_per_second": 0.416,
      "step": 1
    },
    {
      "epoch": 0.0003683580440187863,
      "grad_norm": 0.3181455433368683,
      "learning_rate": 2e-05,
      "loss": 1.8757,
      "step": 2
    },
    {
      "epoch": 0.0005525370660281794,
      "grad_norm": 0.3106219470500946,
      "learning_rate": 3e-05,
      "loss": 1.9617,
      "step": 3
    },
    {
      "epoch": 0.0007367160880375726,
      "grad_norm": 0.2979538142681122,
      "learning_rate": 4e-05,
      "loss": 2.0062,
      "step": 4
    },
    {
      "epoch": 0.0009208951100469656,
      "grad_norm": 0.40445128083229065,
      "learning_rate": 5e-05,
      "loss": 1.9287,
      "step": 5
    },
    {
      "epoch": 0.0011050741320563588,
      "grad_norm": 0.3349987864494324,
      "learning_rate": 6e-05,
      "loss": 1.8478,
      "step": 6
    },
    {
      "epoch": 0.0012892531540657519,
      "grad_norm": 0.3821425139904022,
      "learning_rate": 7e-05,
      "loss": 1.8783,
      "step": 7
    },
    {
      "epoch": 0.0014734321760751451,
      "grad_norm": 0.4201582968235016,
      "learning_rate": 8e-05,
      "loss": 1.7756,
      "step": 8
    },
    {
      "epoch": 0.0016576111980845382,
      "grad_norm": 0.3667738735675812,
      "learning_rate": 9e-05,
      "loss": 1.8022,
      "step": 9
    },
    {
      "epoch": 0.0016576111980845382,
      "eval_loss": 0.9071351885795593,
      "eval_runtime": 1374.715,
      "eval_samples_per_second": 3.327,
      "eval_steps_per_second": 0.416,
      "step": 9
    },
    {
      "epoch": 0.0018417902200939312,
      "grad_norm": 0.333757609128952,
      "learning_rate": 0.0001,
      "loss": 1.8004,
      "step": 10
    },
    {
      "epoch": 0.0020259692421033242,
      "grad_norm": 0.35505855083465576,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.8251,
      "step": 11
    },
    {
      "epoch": 0.0022101482641127177,
      "grad_norm": 0.4806636869907379,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.7435,
      "step": 12
    },
    {
      "epoch": 0.0023943272861221107,
      "grad_norm": 0.6464740037918091,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.7984,
      "step": 13
    },
    {
      "epoch": 0.0025785063081315038,
      "grad_norm": 0.4599541425704956,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.7413,
      "step": 14
    },
    {
      "epoch": 0.002762685330140897,
      "grad_norm": 0.44121336936950684,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.6598,
      "step": 15
    },
    {
      "epoch": 0.0029468643521502903,
      "grad_norm": 0.35761019587516785,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.6543,
      "step": 16
    },
    {
      "epoch": 0.0031310433741596833,
      "grad_norm": 0.35534200072288513,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.6462,
      "step": 17
    },
    {
      "epoch": 0.0033152223961690763,
      "grad_norm": 0.44417276978492737,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7202,
      "step": 18
    },
    {
      "epoch": 0.0033152223961690763,
      "eval_loss": 0.8204256892204285,
      "eval_runtime": 1374.7317,
      "eval_samples_per_second": 3.326,
      "eval_steps_per_second": 0.416,
      "step": 18
    },
    {
      "epoch": 0.0034994014181784694,
      "grad_norm": 0.5218469500541687,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.7099,
      "step": 19
    },
    {
      "epoch": 0.0036835804401878624,
      "grad_norm": 0.45016589760780334,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.598,
      "step": 20
    },
    {
      "epoch": 0.003867759462197256,
      "grad_norm": 0.39672884345054626,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.5986,
      "step": 21
    },
    {
      "epoch": 0.0040519384842066485,
      "grad_norm": 0.38238945603370667,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.5799,
      "step": 22
    },
    {
      "epoch": 0.004236117506216042,
      "grad_norm": 0.344881147146225,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.5341,
      "step": 23
    },
    {
      "epoch": 0.004420296528225435,
      "grad_norm": 0.3711905777454376,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.5143,
      "step": 24
    },
    {
      "epoch": 0.004604475550234828,
      "grad_norm": 0.36525073647499084,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6421,
      "step": 25
    },
    {
      "epoch": 0.0047886545722442215,
      "grad_norm": 0.3915397524833679,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.6122,
      "step": 26
    },
    {
      "epoch": 0.0049728335942536145,
      "grad_norm": 0.37893590331077576,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.5547,
      "step": 27
    },
    {
      "epoch": 0.0049728335942536145,
      "eval_loss": 0.7771932482719421,
      "eval_runtime": 1376.0045,
      "eval_samples_per_second": 3.323,
      "eval_steps_per_second": 0.416,
      "step": 27
    },
    {
      "epoch": 0.0051570126162630075,
      "grad_norm": 0.3783082962036133,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.4962,
      "step": 28
    },
    {
      "epoch": 0.0053411916382724006,
      "grad_norm": 0.3691401183605194,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.5948,
      "step": 29
    },
    {
      "epoch": 0.005525370660281794,
      "grad_norm": 0.3751038908958435,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.5963,
      "step": 30
    },
    {
      "epoch": 0.005709549682291187,
      "grad_norm": 0.3624536097049713,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.5946,
      "step": 31
    },
    {
      "epoch": 0.0058937287043005805,
      "grad_norm": 0.39687982201576233,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.5151,
      "step": 32
    },
    {
      "epoch": 0.0060779077263099736,
      "grad_norm": 0.4228801727294922,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.4669,
      "step": 33
    },
    {
      "epoch": 0.006262086748319367,
      "grad_norm": 0.4128759801387787,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.5956,
      "step": 34
    },
    {
      "epoch": 0.00644626577032876,
      "grad_norm": 0.3779587745666504,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.5461,
      "step": 35
    },
    {
      "epoch": 0.006630444792338153,
      "grad_norm": 0.41748321056365967,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.5276,
      "step": 36
    },
    {
      "epoch": 0.006630444792338153,
      "eval_loss": 0.7516466975212097,
      "eval_runtime": 1374.6875,
      "eval_samples_per_second": 3.327,
      "eval_steps_per_second": 0.416,
      "step": 36
    },
    {
      "epoch": 0.006814623814347546,
      "grad_norm": 0.39948129653930664,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5585,
      "step": 37
    },
    {
      "epoch": 0.006998802836356939,
      "grad_norm": 0.42794620990753174,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.5564,
      "step": 38
    },
    {
      "epoch": 0.007182981858366332,
      "grad_norm": 0.43983128666877747,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.5118,
      "step": 39
    },
    {
      "epoch": 0.007367160880375725,
      "grad_norm": 0.464037150144577,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.4393,
      "step": 40
    },
    {
      "epoch": 0.007551339902385119,
      "grad_norm": 0.41590768098831177,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.5129,
      "step": 41
    },
    {
      "epoch": 0.007735518924394512,
      "grad_norm": 0.4561501741409302,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.4509,
      "step": 42
    },
    {
      "epoch": 0.007919697946403905,
      "grad_norm": 0.45559948682785034,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.458,
      "step": 43
    },
    {
      "epoch": 0.008103876968413297,
      "grad_norm": 0.446026474237442,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.4758,
      "step": 44
    },
    {
      "epoch": 0.00828805599042269,
      "grad_norm": 0.4749871790409088,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5615,
      "step": 45
    },
    {
      "epoch": 0.00828805599042269,
      "eval_loss": 0.7331555485725403,
      "eval_runtime": 1375.0551,
      "eval_samples_per_second": 3.326,
      "eval_steps_per_second": 0.416,
      "step": 45
    },
    {
      "epoch": 0.008472235012432085,
      "grad_norm": 0.48077258467674255,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5522,
      "step": 46
    },
    {
      "epoch": 0.008656414034441477,
      "grad_norm": 0.44574302434921265,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.4592,
      "step": 47
    },
    {
      "epoch": 0.00884059305645087,
      "grad_norm": 0.47824907302856445,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.4913,
      "step": 48
    },
    {
      "epoch": 0.009024772078460263,
      "grad_norm": 0.46212729811668396,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.5488,
      "step": 49
    },
    {
      "epoch": 0.009208951100469657,
      "grad_norm": 0.47716400027275085,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.5031,
      "step": 50
    },
    {
      "epoch": 0.009393130122479049,
      "grad_norm": 0.48197489976882935,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.4917,
      "step": 51
    },
    {
      "epoch": 0.009577309144488443,
      "grad_norm": 0.4541970491409302,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.4553,
      "step": 52
    },
    {
      "epoch": 0.009761488166497835,
      "grad_norm": 0.4238864779472351,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.3545,
      "step": 53
    },
    {
      "epoch": 0.009945667188507229,
      "grad_norm": 0.4670512080192566,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.3978,
      "step": 54
    },
    {
      "epoch": 0.009945667188507229,
      "eval_loss": 0.7208191752433777,
      "eval_runtime": 1374.6568,
      "eval_samples_per_second": 3.327,
      "eval_steps_per_second": 0.416,
      "step": 54
    },
    {
      "epoch": 0.010129846210516623,
      "grad_norm": 0.4541580379009247,
      "learning_rate": 5e-05,
      "loss": 1.4369,
      "step": 55
    },
    {
      "epoch": 0.010314025232526015,
      "grad_norm": 0.4919944703578949,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.4631,
      "step": 56
    },
    {
      "epoch": 0.010498204254535409,
      "grad_norm": 0.48064664006233215,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.4647,
      "step": 57
    },
    {
      "epoch": 0.010682383276544801,
      "grad_norm": 0.49237197637557983,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.5043,
      "step": 58
    },
    {
      "epoch": 0.010866562298554195,
      "grad_norm": 0.46440890431404114,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.3985,
      "step": 59
    },
    {
      "epoch": 0.011050741320563587,
      "grad_norm": 0.5166982412338257,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.4689,
      "step": 60
    },
    {
      "epoch": 0.011234920342572981,
      "grad_norm": 0.49635982513427734,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.4694,
      "step": 61
    },
    {
      "epoch": 0.011419099364582373,
      "grad_norm": 0.500831127166748,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.4218,
      "step": 62
    },
    {
      "epoch": 0.011603278386591767,
      "grad_norm": 0.47681158781051636,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.4313,
      "step": 63
    },
    {
      "epoch": 0.011603278386591767,
      "eval_loss": 0.7120449542999268,
      "eval_runtime": 1375.9058,
      "eval_samples_per_second": 3.324,
      "eval_steps_per_second": 0.416,
      "step": 63
    },
    {
      "epoch": 0.011787457408601161,
      "grad_norm": 0.5092172622680664,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.3518,
      "step": 64
    },
    {
      "epoch": 0.011971636430610553,
      "grad_norm": 0.5099927186965942,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.4548,
      "step": 65
    },
    {
      "epoch": 0.012155815452619947,
      "grad_norm": 0.5201544761657715,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.3549,
      "step": 66
    },
    {
      "epoch": 0.01233999447462934,
      "grad_norm": 0.4881454110145569,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.3745,
      "step": 67
    },
    {
      "epoch": 0.012524173496638733,
      "grad_norm": 0.49978435039520264,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.408,
      "step": 68
    },
    {
      "epoch": 0.012708352518648125,
      "grad_norm": 0.5017417073249817,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.4365,
      "step": 69
    },
    {
      "epoch": 0.01289253154065752,
      "grad_norm": 0.5562594532966614,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.4129,
      "step": 70
    },
    {
      "epoch": 0.013076710562666911,
      "grad_norm": 0.510033369064331,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.462,
      "step": 71
    },
    {
      "epoch": 0.013260889584676305,
      "grad_norm": 0.5131986737251282,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.4247,
      "step": 72
    },
    {
      "epoch": 0.013260889584676305,
      "eval_loss": 0.7056426405906677,
      "eval_runtime": 1374.8167,
      "eval_samples_per_second": 3.326,
      "eval_steps_per_second": 0.416,
      "step": 72
    },
    {
      "epoch": 0.0134450686066857,
      "grad_norm": 0.535476803779602,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.3656,
      "step": 73
    },
    {
      "epoch": 0.013629247628695091,
      "grad_norm": 0.5137998461723328,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.4385,
      "step": 74
    },
    {
      "epoch": 0.013813426650704485,
      "grad_norm": 0.5598435997962952,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.4534,
      "step": 75
    },
    {
      "epoch": 0.013997605672713877,
      "grad_norm": 0.5669639706611633,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.3964,
      "step": 76
    },
    {
      "epoch": 0.014181784694723271,
      "grad_norm": 0.525967538356781,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.4936,
      "step": 77
    },
    {
      "epoch": 0.014365963716732663,
      "grad_norm": 0.4990406632423401,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.4064,
      "step": 78
    },
    {
      "epoch": 0.014550142738742057,
      "grad_norm": 0.5157889127731323,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.4292,
      "step": 79
    },
    {
      "epoch": 0.01473432176075145,
      "grad_norm": 0.5075008869171143,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.4307,
      "step": 80
    },
    {
      "epoch": 0.014918500782760843,
      "grad_norm": 0.520317554473877,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.3444,
      "step": 81
    },
    {
      "epoch": 0.014918500782760843,
      "eval_loss": 0.7018651366233826,
      "eval_runtime": 1374.6373,
      "eval_samples_per_second": 3.327,
      "eval_steps_per_second": 0.416,
      "step": 81
    },
    {
      "epoch": 0.015102679804770237,
      "grad_norm": 0.49962204694747925,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.4096,
      "step": 82
    },
    {
      "epoch": 0.01528685882677963,
      "grad_norm": 0.4933731257915497,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.4033,
      "step": 83
    },
    {
      "epoch": 0.015471037848789023,
      "grad_norm": 0.49985840916633606,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.4229,
      "step": 84
    },
    {
      "epoch": 0.015655216870798416,
      "grad_norm": 0.5326341986656189,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.3568,
      "step": 85
    },
    {
      "epoch": 0.01583939589280781,
      "grad_norm": 0.4729391634464264,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.3532,
      "step": 86
    },
    {
      "epoch": 0.016023574914817203,
      "grad_norm": 0.5575768947601318,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.3965,
      "step": 87
    },
    {
      "epoch": 0.016207753936826594,
      "grad_norm": 0.5217925906181335,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.3991,
      "step": 88
    },
    {
      "epoch": 0.016391932958835988,
      "grad_norm": 0.5065118074417114,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.315,
      "step": 89
    },
    {
      "epoch": 0.01657611198084538,
      "grad_norm": 0.48693209886550903,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.415,
      "step": 90
    },
    {
      "epoch": 0.01657611198084538,
      "eval_loss": 0.7002039551734924,
      "eval_runtime": 1374.6772,
      "eval_samples_per_second": 3.327,
      "eval_steps_per_second": 0.416,
      "step": 90
    },
    {
      "epoch": 0.016760291002854776,
      "grad_norm": 0.5162665843963623,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.2998,
      "step": 91
    },
    {
      "epoch": 0.01694447002486417,
      "grad_norm": 0.5575674176216125,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.4777,
      "step": 92
    },
    {
      "epoch": 0.01712864904687356,
      "grad_norm": 0.5292540192604065,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.3472,
      "step": 93
    },
    {
      "epoch": 0.017312828068882954,
      "grad_norm": 0.5513125658035278,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.4452,
      "step": 94
    },
    {
      "epoch": 0.017497007090892348,
      "grad_norm": 0.572922945022583,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.4552,
      "step": 95
    },
    {
      "epoch": 0.01768118611290174,
      "grad_norm": 0.5762553811073303,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.5259,
      "step": 96
    },
    {
      "epoch": 0.017865365134911132,
      "grad_norm": 0.5325009226799011,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.3222,
      "step": 97
    },
    {
      "epoch": 0.018049544156920526,
      "grad_norm": 0.5096551775932312,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.3978,
      "step": 98
    },
    {
      "epoch": 0.01823372317892992,
      "grad_norm": 0.5625472068786621,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.355,
      "step": 99
    },
    {
      "epoch": 0.01823372317892992,
      "eval_loss": 0.6998289227485657,
      "eval_runtime": 1376.3591,
      "eval_samples_per_second": 3.323,
      "eval_steps_per_second": 0.416,
      "step": 99
    },
    {
      "epoch": 0.018417902200939314,
      "grad_norm": 0.5077269673347473,
      "learning_rate": 0.0,
      "loss": 1.3856,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.437551243657216e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}