{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.546448087431694,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00546448087431694,
      "grad_norm": 0.020383281633257866,
      "learning_rate": 1e-05,
      "loss": 10.3792,
      "step": 1
    },
    {
      "epoch": 0.00546448087431694,
      "eval_loss": 10.379307746887207,
      "eval_runtime": 0.8415,
      "eval_samples_per_second": 732.051,
      "eval_steps_per_second": 23.768,
      "step": 1
    },
    {
      "epoch": 0.01092896174863388,
      "grad_norm": 0.020612839609384537,
      "learning_rate": 2e-05,
      "loss": 10.3791,
      "step": 2
    },
    {
      "epoch": 0.01639344262295082,
      "grad_norm": 0.020167216658592224,
      "learning_rate": 3e-05,
      "loss": 10.3788,
      "step": 3
    },
    {
      "epoch": 0.02185792349726776,
      "grad_norm": 0.021242409944534302,
      "learning_rate": 4e-05,
      "loss": 10.3802,
      "step": 4
    },
    {
      "epoch": 0.0273224043715847,
      "grad_norm": 0.021846434101462364,
      "learning_rate": 5e-05,
      "loss": 10.3788,
      "step": 5
    },
    {
      "epoch": 0.03278688524590164,
      "grad_norm": 0.02111602947115898,
      "learning_rate": 6e-05,
      "loss": 10.3795,
      "step": 6
    },
    {
      "epoch": 0.03825136612021858,
      "grad_norm": 0.02254120633006096,
      "learning_rate": 7e-05,
      "loss": 10.3797,
      "step": 7
    },
    {
      "epoch": 0.04371584699453552,
      "grad_norm": 0.02077510766685009,
      "learning_rate": 8e-05,
      "loss": 10.3792,
      "step": 8
    },
    {
      "epoch": 0.04918032786885246,
      "grad_norm": 0.023137113079428673,
      "learning_rate": 9e-05,
      "loss": 10.3782,
      "step": 9
    },
    {
      "epoch": 0.04918032786885246,
      "eval_loss": 10.37905216217041,
      "eval_runtime": 0.8366,
      "eval_samples_per_second": 736.287,
      "eval_steps_per_second": 23.905,
      "step": 9
    },
    {
      "epoch": 0.0546448087431694,
      "grad_norm": 0.0223676897585392,
      "learning_rate": 0.0001,
      "loss": 10.3792,
      "step": 10
    },
    {
      "epoch": 0.060109289617486336,
      "grad_norm": 0.02123025432229042,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3791,
      "step": 11
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 0.022941257804632187,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3797,
      "step": 12
    },
    {
      "epoch": 0.07103825136612021,
      "grad_norm": 0.02323402650654316,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.378,
      "step": 13
    },
    {
      "epoch": 0.07650273224043716,
      "grad_norm": 0.022610928863286972,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3785,
      "step": 14
    },
    {
      "epoch": 0.08196721311475409,
      "grad_norm": 0.023305339738726616,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3784,
      "step": 15
    },
    {
      "epoch": 0.08743169398907104,
      "grad_norm": 0.02502063848078251,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3788,
      "step": 16
    },
    {
      "epoch": 0.09289617486338798,
      "grad_norm": 0.02342299558222294,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3776,
      "step": 17
    },
    {
      "epoch": 0.09836065573770492,
      "grad_norm": 0.023943260312080383,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3783,
      "step": 18
    },
    {
      "epoch": 0.09836065573770492,
      "eval_loss": 10.378381729125977,
      "eval_runtime": 0.8351,
      "eval_samples_per_second": 737.614,
      "eval_steps_per_second": 23.948,
      "step": 18
    },
    {
      "epoch": 0.10382513661202186,
      "grad_norm": 0.023626631125807762,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3767,
      "step": 19
    },
    {
      "epoch": 0.1092896174863388,
      "grad_norm": 0.02358776144683361,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.378,
      "step": 20
    },
    {
      "epoch": 0.11475409836065574,
      "grad_norm": 0.022744785994291306,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3792,
      "step": 21
    },
    {
      "epoch": 0.12021857923497267,
      "grad_norm": 0.026644982397556305,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3774,
      "step": 22
    },
    {
      "epoch": 0.12568306010928962,
      "grad_norm": 0.025849616155028343,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3783,
      "step": 23
    },
    {
      "epoch": 0.13114754098360656,
      "grad_norm": 0.02618810161948204,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3776,
      "step": 24
    },
    {
      "epoch": 0.1366120218579235,
      "grad_norm": 0.025136524811387062,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3781,
      "step": 25
    },
    {
      "epoch": 0.14207650273224043,
      "grad_norm": 0.02928001433610916,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3773,
      "step": 26
    },
    {
      "epoch": 0.14754098360655737,
      "grad_norm": 0.027695804834365845,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3766,
      "step": 27
    },
    {
      "epoch": 0.14754098360655737,
      "eval_loss": 10.377593994140625,
      "eval_runtime": 0.8333,
      "eval_samples_per_second": 739.27,
      "eval_steps_per_second": 24.002,
      "step": 27
    },
    {
      "epoch": 0.15300546448087432,
      "grad_norm": 0.0281513761729002,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3775,
      "step": 28
    },
    {
      "epoch": 0.15846994535519127,
      "grad_norm": 0.028438687324523926,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3773,
      "step": 29
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 0.02885403297841549,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3769,
      "step": 30
    },
    {
      "epoch": 0.16939890710382513,
      "grad_norm": 0.02971421554684639,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3776,
      "step": 31
    },
    {
      "epoch": 0.17486338797814208,
      "grad_norm": 0.033431265503168106,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3759,
      "step": 32
    },
    {
      "epoch": 0.18032786885245902,
      "grad_norm": 0.03296530991792679,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3772,
      "step": 33
    },
    {
      "epoch": 0.18579234972677597,
      "grad_norm": 0.03332926705479622,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.377,
      "step": 34
    },
    {
      "epoch": 0.1912568306010929,
      "grad_norm": 0.03217661380767822,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3761,
      "step": 35
    },
    {
      "epoch": 0.19672131147540983,
      "grad_norm": 0.033675920218229294,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3767,
      "step": 36
    },
    {
      "epoch": 0.19672131147540983,
      "eval_loss": 10.376678466796875,
      "eval_runtime": 0.8446,
      "eval_samples_per_second": 729.317,
      "eval_steps_per_second": 23.679,
      "step": 36
    },
    {
      "epoch": 0.20218579234972678,
      "grad_norm": 0.0315808467566967,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3776,
      "step": 37
    },
    {
      "epoch": 0.20765027322404372,
      "grad_norm": 0.038899537175893784,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3754,
      "step": 38
    },
    {
      "epoch": 0.21311475409836064,
      "grad_norm": 0.03773730248212814,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3778,
      "step": 39
    },
    {
      "epoch": 0.2185792349726776,
      "grad_norm": 0.04042154923081398,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3765,
      "step": 40
    },
    {
      "epoch": 0.22404371584699453,
      "grad_norm": 0.039911359548568726,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3754,
      "step": 41
    },
    {
      "epoch": 0.22950819672131148,
      "grad_norm": 0.04403088241815567,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3759,
      "step": 42
    },
    {
      "epoch": 0.23497267759562843,
      "grad_norm": 0.03892216086387634,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3762,
      "step": 43
    },
    {
      "epoch": 0.24043715846994534,
      "grad_norm": 0.038504015654325485,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3756,
      "step": 44
    },
    {
      "epoch": 0.2459016393442623,
      "grad_norm": 0.04363120719790459,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.376,
      "step": 45
    },
    {
      "epoch": 0.2459016393442623,
      "eval_loss": 10.375645637512207,
      "eval_runtime": 0.8348,
      "eval_samples_per_second": 737.924,
      "eval_steps_per_second": 23.959,
      "step": 45
    },
    {
      "epoch": 0.25136612021857924,
      "grad_norm": 0.043945375829935074,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3751,
      "step": 46
    },
    {
      "epoch": 0.2568306010928962,
      "grad_norm": 0.04311802238225937,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3757,
      "step": 47
    },
    {
      "epoch": 0.26229508196721313,
      "grad_norm": 0.04382125660777092,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3757,
      "step": 48
    },
    {
      "epoch": 0.2677595628415301,
      "grad_norm": 0.04658404737710953,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3758,
      "step": 49
    },
    {
      "epoch": 0.273224043715847,
      "grad_norm": 0.045132722705602646,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3745,
      "step": 50
    },
    {
      "epoch": 0.2786885245901639,
      "grad_norm": 0.04402737319469452,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3748,
      "step": 51
    },
    {
      "epoch": 0.28415300546448086,
      "grad_norm": 0.04508426785469055,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3746,
      "step": 52
    },
    {
      "epoch": 0.2896174863387978,
      "grad_norm": 0.04800768941640854,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3748,
      "step": 53
    },
    {
      "epoch": 0.29508196721311475,
      "grad_norm": 0.04819543659687042,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3755,
      "step": 54
    },
    {
      "epoch": 0.29508196721311475,
      "eval_loss": 10.374573707580566,
      "eval_runtime": 0.8298,
      "eval_samples_per_second": 742.379,
      "eval_steps_per_second": 24.103,
      "step": 54
    },
    {
      "epoch": 0.3005464480874317,
      "grad_norm": 0.051205698400735855,
      "learning_rate": 5e-05,
      "loss": 10.375,
      "step": 55
    },
    {
      "epoch": 0.30601092896174864,
      "grad_norm": 0.05164771154522896,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3743,
      "step": 56
    },
    {
      "epoch": 0.3114754098360656,
      "grad_norm": 0.05184890702366829,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3746,
      "step": 57
    },
    {
      "epoch": 0.31693989071038253,
      "grad_norm": 0.05557376146316528,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3744,
      "step": 58
    },
    {
      "epoch": 0.3224043715846995,
      "grad_norm": 0.054270245134830475,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3743,
      "step": 59
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 0.05667842924594879,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3747,
      "step": 60
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.059168748557567596,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3726,
      "step": 61
    },
    {
      "epoch": 0.33879781420765026,
      "grad_norm": 0.05808443948626518,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3739,
      "step": 62
    },
    {
      "epoch": 0.3442622950819672,
      "grad_norm": 0.05408474802970886,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3742,
      "step": 63
    },
    {
      "epoch": 0.3442622950819672,
      "eval_loss": 10.373579025268555,
      "eval_runtime": 0.836,
      "eval_samples_per_second": 736.823,
      "eval_steps_per_second": 23.923,
      "step": 63
    },
    {
      "epoch": 0.34972677595628415,
      "grad_norm": 0.05801790952682495,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3738,
      "step": 64
    },
    {
      "epoch": 0.3551912568306011,
      "grad_norm": 0.05648942291736603,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3744,
      "step": 65
    },
    {
      "epoch": 0.36065573770491804,
      "grad_norm": 0.056558702141046524,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3727,
      "step": 66
    },
    {
      "epoch": 0.366120218579235,
      "grad_norm": 0.057507459074258804,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3728,
      "step": 67
    },
    {
      "epoch": 0.37158469945355194,
      "grad_norm": 0.06369660794734955,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3734,
      "step": 68
    },
    {
      "epoch": 0.3770491803278688,
      "grad_norm": 0.06289859116077423,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.373,
      "step": 69
    },
    {
      "epoch": 0.3825136612021858,
      "grad_norm": 0.06389268487691879,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3732,
      "step": 70
    },
    {
      "epoch": 0.3879781420765027,
      "grad_norm": 0.06123030185699463,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3719,
      "step": 71
    },
    {
      "epoch": 0.39344262295081966,
      "grad_norm": 0.06595779210329056,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.373,
      "step": 72
    },
    {
      "epoch": 0.39344262295081966,
      "eval_loss": 10.372864723205566,
      "eval_runtime": 0.8341,
      "eval_samples_per_second": 738.515,
      "eval_steps_per_second": 23.978,
      "step": 72
    },
    {
      "epoch": 0.3989071038251366,
      "grad_norm": 0.06698242574930191,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3733,
      "step": 73
    },
    {
      "epoch": 0.40437158469945356,
      "grad_norm": 0.06163797155022621,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.373,
      "step": 74
    },
    {
      "epoch": 0.4098360655737705,
      "grad_norm": 0.06621850281953812,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3736,
      "step": 75
    },
    {
      "epoch": 0.41530054644808745,
      "grad_norm": 0.05782744288444519,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3741,
      "step": 76
    },
    {
      "epoch": 0.4207650273224044,
      "grad_norm": 0.06212912127375603,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3724,
      "step": 77
    },
    {
      "epoch": 0.4262295081967213,
      "grad_norm": 0.05933624878525734,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3718,
      "step": 78
    },
    {
      "epoch": 0.43169398907103823,
      "grad_norm": 0.06697092950344086,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3723,
      "step": 79
    },
    {
      "epoch": 0.4371584699453552,
      "grad_norm": 0.07022427767515182,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3724,
      "step": 80
    },
    {
      "epoch": 0.4426229508196721,
      "grad_norm": 0.0685114711523056,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3733,
      "step": 81
    },
    {
      "epoch": 0.4426229508196721,
      "eval_loss": 10.37241268157959,
      "eval_runtime": 0.8287,
      "eval_samples_per_second": 743.363,
      "eval_steps_per_second": 24.135,
      "step": 81
    },
    {
      "epoch": 0.44808743169398907,
      "grad_norm": 0.06889978051185608,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3733,
      "step": 82
    },
    {
      "epoch": 0.453551912568306,
      "grad_norm": 0.06139597296714783,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3727,
      "step": 83
    },
    {
      "epoch": 0.45901639344262296,
      "grad_norm": 0.06276782602071762,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3731,
      "step": 84
    },
    {
      "epoch": 0.4644808743169399,
      "grad_norm": 0.06612912565469742,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3714,
      "step": 85
    },
    {
      "epoch": 0.46994535519125685,
      "grad_norm": 0.07081400603055954,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3717,
      "step": 86
    },
    {
      "epoch": 0.47540983606557374,
      "grad_norm": 0.0591704323887825,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3735,
      "step": 87
    },
    {
      "epoch": 0.4808743169398907,
      "grad_norm": 0.06865952908992767,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3724,
      "step": 88
    },
    {
      "epoch": 0.48633879781420764,
      "grad_norm": 0.06752797216176987,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3725,
      "step": 89
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 0.06979833543300629,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3714,
      "step": 90
    },
    {
      "epoch": 0.4918032786885246,
      "eval_loss": 10.372178077697754,
      "eval_runtime": 0.8396,
      "eval_samples_per_second": 733.682,
      "eval_steps_per_second": 23.821,
      "step": 90
    },
    {
      "epoch": 0.4972677595628415,
      "grad_norm": 0.06850720196962357,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3721,
      "step": 91
    },
    {
      "epoch": 0.5027322404371585,
      "grad_norm": 0.06722009181976318,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3729,
      "step": 92
    },
    {
      "epoch": 0.5081967213114754,
      "grad_norm": 0.06894061714410782,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3715,
      "step": 93
    },
    {
      "epoch": 0.5136612021857924,
      "grad_norm": 0.06594067066907883,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3724,
      "step": 94
    },
    {
      "epoch": 0.5191256830601093,
      "grad_norm": 0.0674702599644661,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3722,
      "step": 95
    },
    {
      "epoch": 0.5245901639344263,
      "grad_norm": 0.06486930698156357,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3736,
      "step": 96
    },
    {
      "epoch": 0.5300546448087432,
      "grad_norm": 0.06004992127418518,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3725,
      "step": 97
    },
    {
      "epoch": 0.5355191256830601,
      "grad_norm": 0.07898783683776855,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3715,
      "step": 98
    },
    {
      "epoch": 0.5409836065573771,
      "grad_norm": 0.06925985962152481,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3717,
      "step": 99
    },
    {
      "epoch": 0.5409836065573771,
      "eval_loss": 10.372146606445312,
      "eval_runtime": 0.8336,
      "eval_samples_per_second": 738.92,
      "eval_steps_per_second": 23.991,
      "step": 99
    },
    {
      "epoch": 0.546448087431694,
      "grad_norm": 0.06981387734413147,
      "learning_rate": 0.0,
      "loss": 10.3721,
      "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": 41841957273600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}