{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3986013986013985,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013986013986013986,
      "grad_norm": 0.018208099529147148,
      "learning_rate": 1e-05,
      "loss": 10.3794,
      "step": 1
    },
    {
      "epoch": 0.013986013986013986,
      "eval_loss": 10.378853797912598,
      "eval_runtime": 0.2269,
      "eval_samples_per_second": 1057.848,
      "eval_steps_per_second": 35.262,
      "step": 1
    },
    {
      "epoch": 0.027972027972027972,
      "grad_norm": 0.019829176366329193,
      "learning_rate": 2e-05,
      "loss": 10.3791,
      "step": 2
    },
    {
      "epoch": 0.04195804195804196,
      "grad_norm": 0.015240170061588287,
      "learning_rate": 3e-05,
      "loss": 10.3763,
      "step": 3
    },
    {
      "epoch": 0.055944055944055944,
      "grad_norm": 0.015529603697359562,
      "learning_rate": 4e-05,
      "loss": 10.3774,
      "step": 4
    },
    {
      "epoch": 0.06993006993006994,
      "grad_norm": 0.01788165047764778,
      "learning_rate": 5e-05,
      "loss": 10.378,
      "step": 5
    },
    {
      "epoch": 0.08391608391608392,
      "grad_norm": 0.01706252060830593,
      "learning_rate": 6e-05,
      "loss": 10.3777,
      "step": 6
    },
    {
      "epoch": 0.0979020979020979,
      "grad_norm": 0.017586465924978256,
      "learning_rate": 7e-05,
      "loss": 10.3778,
      "step": 7
    },
    {
      "epoch": 0.11188811188811189,
      "grad_norm": 0.019204173237085342,
      "learning_rate": 8e-05,
      "loss": 10.3803,
      "step": 8
    },
    {
      "epoch": 0.1258741258741259,
      "grad_norm": 0.01797935739159584,
      "learning_rate": 9e-05,
      "loss": 10.3784,
      "step": 9
    },
    {
      "epoch": 0.1258741258741259,
      "eval_loss": 10.378623008728027,
      "eval_runtime": 0.2291,
      "eval_samples_per_second": 1047.352,
      "eval_steps_per_second": 34.912,
      "step": 9
    },
    {
      "epoch": 0.13986013986013987,
      "grad_norm": 0.01941474713385105,
      "learning_rate": 0.0001,
      "loss": 10.3797,
      "step": 10
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.01960493065416813,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3767,
      "step": 11
    },
    {
      "epoch": 0.16783216783216784,
      "grad_norm": 0.020062170922756195,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3783,
      "step": 12
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.01915978081524372,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3771,
      "step": 13
    },
    {
      "epoch": 0.1958041958041958,
      "grad_norm": 0.016005827113986015,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3767,
      "step": 14
    },
    {
      "epoch": 0.2097902097902098,
      "grad_norm": 0.016981465741991997,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.377,
      "step": 15
    },
    {
      "epoch": 0.22377622377622378,
      "grad_norm": 0.019123638048768044,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.378,
      "step": 16
    },
    {
      "epoch": 0.23776223776223776,
      "grad_norm": 0.017938820645213127,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3774,
      "step": 17
    },
    {
      "epoch": 0.2517482517482518,
      "grad_norm": 0.017268581315875053,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3773,
      "step": 18
    },
    {
      "epoch": 0.2517482517482518,
      "eval_loss": 10.378046989440918,
      "eval_runtime": 0.2254,
      "eval_samples_per_second": 1064.655,
      "eval_steps_per_second": 35.488,
      "step": 18
    },
    {
      "epoch": 0.26573426573426573,
      "grad_norm": 0.017280064523220062,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3762,
      "step": 19
    },
    {
      "epoch": 0.27972027972027974,
      "grad_norm": 0.019195018336176872,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3777,
      "step": 20
    },
    {
      "epoch": 0.2937062937062937,
      "grad_norm": 0.019608568400144577,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3781,
      "step": 21
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.018666790798306465,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3768,
      "step": 22
    },
    {
      "epoch": 0.32167832167832167,
      "grad_norm": 0.018083766102790833,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3779,
      "step": 23
    },
    {
      "epoch": 0.3356643356643357,
      "grad_norm": 0.017882829532027245,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.376,
      "step": 24
    },
    {
      "epoch": 0.34965034965034963,
      "grad_norm": 0.020201081410050392,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3759,
      "step": 25
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.024009106680750847,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3777,
      "step": 26
    },
    {
      "epoch": 0.3776223776223776,
      "grad_norm": 0.021636882796883583,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3774,
      "step": 27
    },
    {
      "epoch": 0.3776223776223776,
      "eval_loss": 10.37741756439209,
      "eval_runtime": 0.227,
      "eval_samples_per_second": 1057.248,
      "eval_steps_per_second": 35.242,
      "step": 27
    },
    {
      "epoch": 0.3916083916083916,
      "grad_norm": 0.021926555782556534,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.377,
      "step": 28
    },
    {
      "epoch": 0.40559440559440557,
      "grad_norm": 0.02251768298447132,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.375,
      "step": 29
    },
    {
      "epoch": 0.4195804195804196,
      "grad_norm": 0.019395161420106888,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3764,
      "step": 30
    },
    {
      "epoch": 0.43356643356643354,
      "grad_norm": 0.02481013350188732,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3767,
      "step": 31
    },
    {
      "epoch": 0.44755244755244755,
      "grad_norm": 0.024715891107916832,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3753,
      "step": 32
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.02524632401764393,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3773,
      "step": 33
    },
    {
      "epoch": 0.4755244755244755,
      "grad_norm": 0.02561429888010025,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3758,
      "step": 34
    },
    {
      "epoch": 0.48951048951048953,
      "grad_norm": 0.025069493800401688,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3755,
      "step": 35
    },
    {
      "epoch": 0.5034965034965035,
      "grad_norm": 0.0294085294008255,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3763,
      "step": 36
    },
    {
      "epoch": 0.5034965034965035,
      "eval_loss": 10.376723289489746,
      "eval_runtime": 0.2223,
      "eval_samples_per_second": 1079.725,
      "eval_steps_per_second": 35.991,
      "step": 36
    },
    {
      "epoch": 0.5174825174825175,
      "grad_norm": 0.026126094162464142,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3763,
      "step": 37
    },
    {
      "epoch": 0.5314685314685315,
      "grad_norm": 0.02763998508453369,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3742,
      "step": 38
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.031683456152677536,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3766,
      "step": 39
    },
    {
      "epoch": 0.5594405594405595,
      "grad_norm": 0.028375782072544098,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3754,
      "step": 40
    },
    {
      "epoch": 0.5734265734265734,
      "grad_norm": 0.02905913069844246,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3767,
      "step": 41
    },
    {
      "epoch": 0.5874125874125874,
      "grad_norm": 0.02657276764512062,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3752,
      "step": 42
    },
    {
      "epoch": 0.6013986013986014,
      "grad_norm": 0.030018672347068787,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3747,
      "step": 43
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.02869054302573204,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3757,
      "step": 44
    },
    {
      "epoch": 0.6293706293706294,
      "grad_norm": 0.030864108353853226,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3759,
      "step": 45
    },
    {
      "epoch": 0.6293706293706294,
      "eval_loss": 10.375964164733887,
      "eval_runtime": 0.2391,
      "eval_samples_per_second": 1003.749,
      "eval_steps_per_second": 33.458,
      "step": 45
    },
    {
      "epoch": 0.6433566433566433,
      "grad_norm": 0.02986125275492668,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3764,
      "step": 46
    },
    {
      "epoch": 0.6573426573426573,
      "grad_norm": 0.03223278000950813,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3748,
      "step": 47
    },
    {
      "epoch": 0.6713286713286714,
      "grad_norm": 0.03329155221581459,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3759,
      "step": 48
    },
    {
      "epoch": 0.6853146853146853,
      "grad_norm": 0.03491205349564552,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3753,
      "step": 49
    },
    {
      "epoch": 0.6993006993006993,
      "grad_norm": 0.03453943133354187,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3749,
      "step": 50
    },
    {
      "epoch": 0.7132867132867133,
      "grad_norm": 0.031059524044394493,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3751,
      "step": 51
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.037967417389154434,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3764,
      "step": 52
    },
    {
      "epoch": 0.7412587412587412,
      "grad_norm": 0.03357519581913948,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3734,
      "step": 53
    },
    {
      "epoch": 0.7552447552447552,
      "grad_norm": 0.03755338490009308,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3767,
      "step": 54
    },
    {
      "epoch": 0.7552447552447552,
      "eval_loss": 10.375212669372559,
      "eval_runtime": 0.2375,
      "eval_samples_per_second": 1010.492,
      "eval_steps_per_second": 33.683,
      "step": 54
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.036303672939538956,
      "learning_rate": 5e-05,
      "loss": 10.3755,
      "step": 55
    },
    {
      "epoch": 0.7832167832167832,
      "grad_norm": 0.035945743322372437,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3737,
      "step": 56
    },
    {
      "epoch": 0.7972027972027972,
      "grad_norm": 0.03665671497583389,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3742,
      "step": 57
    },
    {
      "epoch": 0.8111888111888111,
      "grad_norm": 0.03903292864561081,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3754,
      "step": 58
    },
    {
      "epoch": 0.8251748251748252,
      "grad_norm": 0.037477292120456696,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3737,
      "step": 59
    },
    {
      "epoch": 0.8391608391608392,
      "grad_norm": 0.03761836886405945,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3753,
      "step": 60
    },
    {
      "epoch": 0.8531468531468531,
      "grad_norm": 0.03947959467768669,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.375,
      "step": 61
    },
    {
      "epoch": 0.8671328671328671,
      "grad_norm": 0.04931560531258583,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3738,
      "step": 62
    },
    {
      "epoch": 0.8811188811188811,
      "grad_norm": 0.04289368912577629,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3736,
      "step": 63
    },
    {
      "epoch": 0.8811188811188811,
      "eval_loss": 10.374542236328125,
      "eval_runtime": 0.2332,
      "eval_samples_per_second": 1029.334,
      "eval_steps_per_second": 34.311,
      "step": 63
    },
    {
      "epoch": 0.8951048951048951,
      "grad_norm": 0.04646448791027069,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.374,
      "step": 64
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.041442107409238815,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3741,
      "step": 65
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.0464664064347744,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3735,
      "step": 66
    },
    {
      "epoch": 0.9370629370629371,
      "grad_norm": 0.045736297965049744,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3745,
      "step": 67
    },
    {
      "epoch": 0.951048951048951,
      "grad_norm": 0.04584592953324318,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3769,
      "step": 68
    },
    {
      "epoch": 0.965034965034965,
      "grad_norm": 0.04951049014925957,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3726,
      "step": 69
    },
    {
      "epoch": 0.9790209790209791,
      "grad_norm": 0.04482301324605942,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3733,
      "step": 70
    },
    {
      "epoch": 0.993006993006993,
      "grad_norm": 0.035766538232564926,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3749,
      "step": 71
    },
    {
      "epoch": 1.006993006993007,
      "grad_norm": 0.0610295832157135,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 15.5208,
      "step": 72
    },
    {
      "epoch": 1.006993006993007,
      "eval_loss": 10.374032020568848,
      "eval_runtime": 0.2214,
      "eval_samples_per_second": 1083.829,
      "eval_steps_per_second": 36.128,
      "step": 72
    },
    {
      "epoch": 1.020979020979021,
      "grad_norm": 0.05227012559771538,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.218,
      "step": 73
    },
    {
      "epoch": 1.034965034965035,
      "grad_norm": 0.050558362156152725,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.4773,
      "step": 74
    },
    {
      "epoch": 1.048951048951049,
      "grad_norm": 0.04764160141348839,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.0928,
      "step": 75
    },
    {
      "epoch": 1.062937062937063,
      "grad_norm": 0.04595685005187988,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.9266,
      "step": 76
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.049153126776218414,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3148,
      "step": 77
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.05073670297861099,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.641,
      "step": 78
    },
    {
      "epoch": 1.104895104895105,
      "grad_norm": 0.044325049966573715,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.0433,
      "step": 79
    },
    {
      "epoch": 1.118881118881119,
      "grad_norm": 0.04824868589639664,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.0382,
      "step": 80
    },
    {
      "epoch": 1.132867132867133,
      "grad_norm": 0.050049543380737305,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.8138,
      "step": 81
    },
    {
      "epoch": 1.132867132867133,
      "eval_loss": 10.373720169067383,
      "eval_runtime": 0.2474,
      "eval_samples_per_second": 970.223,
      "eval_steps_per_second": 32.341,
      "step": 81
    },
    {
      "epoch": 1.1468531468531469,
      "grad_norm": 0.05412643030285835,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.0682,
      "step": 82
    },
    {
      "epoch": 1.1608391608391608,
      "grad_norm": 0.04766753688454628,
      "learning_rate": 8.548121372247918e-06,
      "loss": 9.9111,
      "step": 83
    },
    {
      "epoch": 1.1748251748251748,
      "grad_norm": 0.049063920974731445,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.8495,
      "step": 84
    },
    {
      "epoch": 1.1888111888111887,
      "grad_norm": 0.05320300906896591,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.4015,
      "step": 85
    },
    {
      "epoch": 1.2027972027972027,
      "grad_norm": 0.052162427455186844,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.1188,
      "step": 86
    },
    {
      "epoch": 1.2167832167832167,
      "grad_norm": 0.05713256821036339,
      "learning_rate": 5.060297685041659e-06,
      "loss": 11.3542,
      "step": 87
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.03999221324920654,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3934,
      "step": 88
    },
    {
      "epoch": 1.2447552447552448,
      "grad_norm": 0.04331766068935394,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 8.8227,
      "step": 89
    },
    {
      "epoch": 1.2587412587412588,
      "grad_norm": 0.061157867312431335,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 11.7923,
      "step": 90
    },
    {
      "epoch": 1.2587412587412588,
      "eval_loss": 10.373579025268555,
      "eval_runtime": 0.227,
      "eval_samples_per_second": 1057.372,
      "eval_steps_per_second": 35.246,
      "step": 90
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.04732262343168259,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 9.998,
      "step": 91
    },
    {
      "epoch": 1.2867132867132867,
      "grad_norm": 0.04708394780755043,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 9.6389,
      "step": 92
    },
    {
      "epoch": 1.3006993006993006,
      "grad_norm": 0.05312468856573105,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 11.1191,
      "step": 93
    },
    {
      "epoch": 1.3146853146853146,
      "grad_norm": 0.05056404694914818,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.2935,
      "step": 94
    },
    {
      "epoch": 1.3286713286713288,
      "grad_norm": 0.0460284948348999,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.076,
      "step": 95
    },
    {
      "epoch": 1.3426573426573427,
      "grad_norm": 0.04575815796852112,
      "learning_rate": 4.865965629214819e-07,
      "loss": 9.8108,
      "step": 96
    },
    {
      "epoch": 1.3566433566433567,
      "grad_norm": 0.05185329541563988,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 11.363,
      "step": 97
    },
    {
      "epoch": 1.3706293706293706,
      "grad_norm": 0.04732576757669449,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.0063,
      "step": 98
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.046071410179138184,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.6642,
      "step": 99
    },
    {
      "epoch": 1.3846153846153846,
      "eval_loss": 10.373554229736328,
      "eval_runtime": 0.2254,
      "eval_samples_per_second": 1065.008,
      "eval_steps_per_second": 35.5,
      "step": 99
    },
    {
      "epoch": 1.3986013986013985,
      "grad_norm": 0.055754274129867554,
      "learning_rate": 0.0,
      "loss": 10.3559,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 31381467955200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}