{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13689253935660506,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013689253935660506,
      "grad_norm": 0.47028085589408875,
      "learning_rate": 1e-05,
      "loss": 0.9599,
      "step": 1
    },
    {
      "epoch": 0.0013689253935660506,
      "eval_loss": 0.8199331760406494,
      "eval_runtime": 75.0079,
      "eval_samples_per_second": 8.199,
      "eval_steps_per_second": 1.027,
      "step": 1
    },
    {
      "epoch": 0.0027378507871321013,
      "grad_norm": 0.4163288176059723,
      "learning_rate": 2e-05,
      "loss": 0.8721,
      "step": 2
    },
    {
      "epoch": 0.004106776180698152,
      "grad_norm": 0.4103744924068451,
      "learning_rate": 3e-05,
      "loss": 0.788,
      "step": 3
    },
    {
      "epoch": 0.0054757015742642025,
      "grad_norm": 0.4232425093650818,
      "learning_rate": 4e-05,
      "loss": 0.7012,
      "step": 4
    },
    {
      "epoch": 0.006844626967830253,
      "grad_norm": 0.533936083316803,
      "learning_rate": 5e-05,
      "loss": 0.861,
      "step": 5
    },
    {
      "epoch": 0.008213552361396304,
      "grad_norm": 0.4576689302921295,
      "learning_rate": 6e-05,
      "loss": 0.7727,
      "step": 6
    },
    {
      "epoch": 0.009582477754962354,
      "grad_norm": 0.49289608001708984,
      "learning_rate": 7e-05,
      "loss": 0.756,
      "step": 7
    },
    {
      "epoch": 0.010951403148528405,
      "grad_norm": 0.5408239364624023,
      "learning_rate": 8e-05,
      "loss": 0.7876,
      "step": 8
    },
    {
      "epoch": 0.012320328542094456,
      "grad_norm": 3.409960985183716,
      "learning_rate": 9e-05,
      "loss": 0.8148,
      "step": 9
    },
    {
      "epoch": 0.012320328542094456,
      "eval_loss": 0.7577440142631531,
      "eval_runtime": 74.3877,
      "eval_samples_per_second": 8.267,
      "eval_steps_per_second": 1.035,
      "step": 9
    },
    {
      "epoch": 0.013689253935660506,
      "grad_norm": 0.7750980257987976,
      "learning_rate": 0.0001,
      "loss": 0.8364,
      "step": 10
    },
    {
      "epoch": 0.015058179329226557,
      "grad_norm": 0.5185539126396179,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.6172,
      "step": 11
    },
    {
      "epoch": 0.01642710472279261,
      "grad_norm": 0.5646676421165466,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.7574,
      "step": 12
    },
    {
      "epoch": 0.01779603011635866,
      "grad_norm": 0.45777517557144165,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.6742,
      "step": 13
    },
    {
      "epoch": 0.019164955509924708,
      "grad_norm": 0.447923481464386,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.6765,
      "step": 14
    },
    {
      "epoch": 0.02053388090349076,
      "grad_norm": 0.40678051114082336,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.6349,
      "step": 15
    },
    {
      "epoch": 0.02190280629705681,
      "grad_norm": 0.3485918939113617,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.5954,
      "step": 16
    },
    {
      "epoch": 0.02327173169062286,
      "grad_norm": 0.7467722296714783,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.5957,
      "step": 17
    },
    {
      "epoch": 0.024640657084188913,
      "grad_norm": 0.47727644443511963,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.7095,
      "step": 18
    },
    {
      "epoch": 0.024640657084188913,
      "eval_loss": 0.7046098113059998,
      "eval_runtime": 74.3695,
      "eval_samples_per_second": 8.27,
      "eval_steps_per_second": 1.035,
      "step": 18
    },
    {
      "epoch": 0.026009582477754964,
      "grad_norm": 0.5402064323425293,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8371,
      "step": 19
    },
    {
      "epoch": 0.02737850787132101,
      "grad_norm": 0.438669353723526,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.5731,
      "step": 20
    },
    {
      "epoch": 0.028747433264887063,
      "grad_norm": 0.42985856533050537,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.6567,
      "step": 21
    },
    {
      "epoch": 0.030116358658453114,
      "grad_norm": 0.5449309945106506,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.7491,
      "step": 22
    },
    {
      "epoch": 0.03148528405201916,
      "grad_norm": 0.5267610549926758,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.7055,
      "step": 23
    },
    {
      "epoch": 0.03285420944558522,
      "grad_norm": 0.4330902397632599,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.7348,
      "step": 24
    },
    {
      "epoch": 0.034223134839151265,
      "grad_norm": 0.4672941267490387,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.8232,
      "step": 25
    },
    {
      "epoch": 0.03559206023271732,
      "grad_norm": 0.5835238695144653,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.8318,
      "step": 26
    },
    {
      "epoch": 0.03696098562628337,
      "grad_norm": 0.5640889406204224,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.6287,
      "step": 27
    },
    {
      "epoch": 0.03696098562628337,
      "eval_loss": 0.6857778429985046,
      "eval_runtime": 74.3478,
      "eval_samples_per_second": 8.272,
      "eval_steps_per_second": 1.036,
      "step": 27
    },
    {
      "epoch": 0.038329911019849415,
      "grad_norm": 0.39191463589668274,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.5312,
      "step": 28
    },
    {
      "epoch": 0.03969883641341547,
      "grad_norm": 0.5952765941619873,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.6684,
      "step": 29
    },
    {
      "epoch": 0.04106776180698152,
      "grad_norm": 0.3688013255596161,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.6102,
      "step": 30
    },
    {
      "epoch": 0.04243668720054757,
      "grad_norm": 0.4253442883491516,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.627,
      "step": 31
    },
    {
      "epoch": 0.04380561259411362,
      "grad_norm": 1.0554460287094116,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.7601,
      "step": 32
    },
    {
      "epoch": 0.045174537987679675,
      "grad_norm": 0.4247450828552246,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.6297,
      "step": 33
    },
    {
      "epoch": 0.04654346338124572,
      "grad_norm": 0.5144878625869751,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.7983,
      "step": 34
    },
    {
      "epoch": 0.04791238877481177,
      "grad_norm": 0.5229074358940125,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.6953,
      "step": 35
    },
    {
      "epoch": 0.049281314168377825,
      "grad_norm": 0.34169769287109375,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.5641,
      "step": 36
    },
    {
      "epoch": 0.049281314168377825,
      "eval_loss": 0.6807133555412292,
      "eval_runtime": 74.4526,
      "eval_samples_per_second": 8.26,
      "eval_steps_per_second": 1.034,
      "step": 36
    },
    {
      "epoch": 0.05065023956194387,
      "grad_norm": 0.4419800639152527,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.749,
      "step": 37
    },
    {
      "epoch": 0.05201916495550993,
      "grad_norm": 0.4952910244464874,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.7368,
      "step": 38
    },
    {
      "epoch": 0.053388090349075976,
      "grad_norm": 0.4826696515083313,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.7935,
      "step": 39
    },
    {
      "epoch": 0.05475701574264202,
      "grad_norm": 0.4916459619998932,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7001,
      "step": 40
    },
    {
      "epoch": 0.05612594113620808,
      "grad_norm": 0.4626803696155548,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.7093,
      "step": 41
    },
    {
      "epoch": 0.057494866529774126,
      "grad_norm": 0.4791833162307739,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.7564,
      "step": 42
    },
    {
      "epoch": 0.05886379192334018,
      "grad_norm": 1.042473554611206,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.6795,
      "step": 43
    },
    {
      "epoch": 0.06023271731690623,
      "grad_norm": 0.45567044615745544,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.7083,
      "step": 44
    },
    {
      "epoch": 0.061601642710472276,
      "grad_norm": 0.3763144910335541,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.5822,
      "step": 45
    },
    {
      "epoch": 0.061601642710472276,
      "eval_loss": 0.6748601794242859,
      "eval_runtime": 74.4713,
      "eval_samples_per_second": 8.258,
      "eval_steps_per_second": 1.034,
      "step": 45
    },
    {
      "epoch": 0.06297056810403832,
      "grad_norm": 0.35519787669181824,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4535,
      "step": 46
    },
    {
      "epoch": 0.06433949349760439,
      "grad_norm": 0.34709632396698,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.5541,
      "step": 47
    },
    {
      "epoch": 0.06570841889117043,
      "grad_norm": 0.45019999146461487,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.7018,
      "step": 48
    },
    {
      "epoch": 0.06707734428473648,
      "grad_norm": 0.518768310546875,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.8068,
      "step": 49
    },
    {
      "epoch": 0.06844626967830253,
      "grad_norm": 0.38476040959358215,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.6661,
      "step": 50
    },
    {
      "epoch": 0.06981519507186858,
      "grad_norm": 0.3735754191875458,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.609,
      "step": 51
    },
    {
      "epoch": 0.07118412046543464,
      "grad_norm": 0.522163987159729,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.9778,
      "step": 52
    },
    {
      "epoch": 0.07255304585900069,
      "grad_norm": 0.5541468858718872,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.6605,
      "step": 53
    },
    {
      "epoch": 0.07392197125256673,
      "grad_norm": 0.41681209206581116,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.5411,
      "step": 54
    },
    {
      "epoch": 0.07392197125256673,
      "eval_loss": 0.6697789430618286,
      "eval_runtime": 74.4006,
      "eval_samples_per_second": 8.266,
      "eval_steps_per_second": 1.035,
      "step": 54
    },
    {
      "epoch": 0.07529089664613278,
      "grad_norm": 0.44614672660827637,
      "learning_rate": 5e-05,
      "loss": 0.6513,
      "step": 55
    },
    {
      "epoch": 0.07665982203969883,
      "grad_norm": 1.471266508102417,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.7593,
      "step": 56
    },
    {
      "epoch": 0.07802874743326489,
      "grad_norm": 0.47901928424835205,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.6847,
      "step": 57
    },
    {
      "epoch": 0.07939767282683094,
      "grad_norm": 0.46592554450035095,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.675,
      "step": 58
    },
    {
      "epoch": 0.08076659822039699,
      "grad_norm": 0.3815876841545105,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.6465,
      "step": 59
    },
    {
      "epoch": 0.08213552361396304,
      "grad_norm": 1.053325891494751,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.5586,
      "step": 60
    },
    {
      "epoch": 0.08350444900752908,
      "grad_norm": 0.3873910903930664,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.6183,
      "step": 61
    },
    {
      "epoch": 0.08487337440109514,
      "grad_norm": 0.3977397382259369,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.5275,
      "step": 62
    },
    {
      "epoch": 0.08624229979466119,
      "grad_norm": 0.5254124402999878,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.738,
      "step": 63
    },
    {
      "epoch": 0.08624229979466119,
      "eval_loss": 0.6687828898429871,
      "eval_runtime": 74.4036,
      "eval_samples_per_second": 8.266,
      "eval_steps_per_second": 1.035,
      "step": 63
    },
    {
      "epoch": 0.08761122518822724,
      "grad_norm": 0.4818817675113678,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7758,
      "step": 64
    },
    {
      "epoch": 0.08898015058179329,
      "grad_norm": 0.5889857411384583,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.8023,
      "step": 65
    },
    {
      "epoch": 0.09034907597535935,
      "grad_norm": 0.5434287190437317,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.7313,
      "step": 66
    },
    {
      "epoch": 0.0917180013689254,
      "grad_norm": 0.3886515498161316,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.4546,
      "step": 67
    },
    {
      "epoch": 0.09308692676249145,
      "grad_norm": 0.4786166250705719,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.7378,
      "step": 68
    },
    {
      "epoch": 0.0944558521560575,
      "grad_norm": 0.41036534309387207,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.576,
      "step": 69
    },
    {
      "epoch": 0.09582477754962354,
      "grad_norm": 0.5122431516647339,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.6415,
      "step": 70
    },
    {
      "epoch": 0.0971937029431896,
      "grad_norm": 0.43372029066085815,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.5321,
      "step": 71
    },
    {
      "epoch": 0.09856262833675565,
      "grad_norm": 0.44713297486305237,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.5858,
      "step": 72
    },
    {
      "epoch": 0.09856262833675565,
      "eval_loss": 0.6657363772392273,
      "eval_runtime": 74.4181,
      "eval_samples_per_second": 8.264,
      "eval_steps_per_second": 1.035,
      "step": 72
    },
    {
      "epoch": 0.0999315537303217,
      "grad_norm": 0.4709993302822113,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7491,
      "step": 73
    },
    {
      "epoch": 0.10130047912388775,
      "grad_norm": 0.4615752696990967,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.7767,
      "step": 74
    },
    {
      "epoch": 0.1026694045174538,
      "grad_norm": 0.4100381135940552,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.6297,
      "step": 75
    },
    {
      "epoch": 0.10403832991101986,
      "grad_norm": 0.44120532274246216,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.7765,
      "step": 76
    },
    {
      "epoch": 0.1054072553045859,
      "grad_norm": 1.9037666320800781,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.6803,
      "step": 77
    },
    {
      "epoch": 0.10677618069815195,
      "grad_norm": 0.45346400141716003,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.7157,
      "step": 78
    },
    {
      "epoch": 0.108145106091718,
      "grad_norm": 0.4818764626979828,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.6556,
      "step": 79
    },
    {
      "epoch": 0.10951403148528405,
      "grad_norm": 0.5118398666381836,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.7823,
      "step": 80
    },
    {
      "epoch": 0.11088295687885011,
      "grad_norm": 0.34270375967025757,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.4997,
      "step": 81
    },
    {
      "epoch": 0.11088295687885011,
      "eval_loss": 0.6642004251480103,
      "eval_runtime": 74.3716,
      "eval_samples_per_second": 8.269,
      "eval_steps_per_second": 1.035,
      "step": 81
    },
    {
      "epoch": 0.11225188227241616,
      "grad_norm": 0.42225101590156555,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.62,
      "step": 82
    },
    {
      "epoch": 0.1136208076659822,
      "grad_norm": 0.4483337700366974,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.7652,
      "step": 83
    },
    {
      "epoch": 0.11498973305954825,
      "grad_norm": 0.4929339587688446,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.6474,
      "step": 84
    },
    {
      "epoch": 0.1163586584531143,
      "grad_norm": 0.39407509565353394,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.6639,
      "step": 85
    },
    {
      "epoch": 0.11772758384668036,
      "grad_norm": 0.4424348771572113,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.7365,
      "step": 86
    },
    {
      "epoch": 0.11909650924024641,
      "grad_norm": 0.4193890690803528,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.6342,
      "step": 87
    },
    {
      "epoch": 0.12046543463381246,
      "grad_norm": 0.41241002082824707,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.6202,
      "step": 88
    },
    {
      "epoch": 0.1218343600273785,
      "grad_norm": 0.42866218090057373,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.6356,
      "step": 89
    },
    {
      "epoch": 0.12320328542094455,
      "grad_norm": 0.4685119688510895,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.9237,
      "step": 90
    },
    {
      "epoch": 0.12320328542094455,
      "eval_loss": 0.66357421875,
      "eval_runtime": 74.3634,
      "eval_samples_per_second": 8.27,
      "eval_steps_per_second": 1.035,
      "step": 90
    },
    {
      "epoch": 0.12457221081451061,
      "grad_norm": 0.47847598791122437,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7759,
      "step": 91
    },
    {
      "epoch": 0.12594113620807665,
      "grad_norm": 0.5083461403846741,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.727,
      "step": 92
    },
    {
      "epoch": 0.1273100616016427,
      "grad_norm": 0.4595864713191986,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.7233,
      "step": 93
    },
    {
      "epoch": 0.12867898699520877,
      "grad_norm": 0.4057812988758087,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.711,
      "step": 94
    },
    {
      "epoch": 0.1300479123887748,
      "grad_norm": 0.4001869559288025,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.574,
      "step": 95
    },
    {
      "epoch": 0.13141683778234087,
      "grad_norm": 0.39253801107406616,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.5436,
      "step": 96
    },
    {
      "epoch": 0.1327857631759069,
      "grad_norm": 0.44381529092788696,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.7024,
      "step": 97
    },
    {
      "epoch": 0.13415468856947296,
      "grad_norm": 0.4743292033672333,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.769,
      "step": 98
    },
    {
      "epoch": 0.13552361396303902,
      "grad_norm": 0.4314176142215729,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.6409,
      "step": 99
    },
    {
      "epoch": 0.13552361396303902,
      "eval_loss": 0.6634355783462524,
      "eval_runtime": 74.4126,
      "eval_samples_per_second": 8.265,
      "eval_steps_per_second": 1.035,
      "step": 99
    },
    {
      "epoch": 0.13689253935660506,
      "grad_norm": 1.5824023485183716,
      "learning_rate": 0.0,
      "loss": 0.6406,
      "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": 8.49460939676713e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}