{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0029549954197570995,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.9549954197570995e-05,
      "grad_norm": 1.7046966552734375,
      "learning_rate": 1e-05,
      "loss": 5.3688,
      "step": 1
    },
    {
      "epoch": 2.9549954197570995e-05,
      "eval_loss": 2.7874948978424072,
      "eval_runtime": 5872.5219,
      "eval_samples_per_second": 4.853,
      "eval_steps_per_second": 0.607,
      "step": 1
    },
    {
      "epoch": 5.909990839514199e-05,
      "grad_norm": 1.7891077995300293,
      "learning_rate": 2e-05,
      "loss": 6.4573,
      "step": 2
    },
    {
      "epoch": 8.864986259271298e-05,
      "grad_norm": 2.004990816116333,
      "learning_rate": 3e-05,
      "loss": 5.4868,
      "step": 3
    },
    {
      "epoch": 0.00011819981679028398,
      "grad_norm": 2.252960443496704,
      "learning_rate": 4e-05,
      "loss": 5.4998,
      "step": 4
    },
    {
      "epoch": 0.00014774977098785496,
      "grad_norm": 2.160506248474121,
      "learning_rate": 5e-05,
      "loss": 5.5228,
      "step": 5
    },
    {
      "epoch": 0.00017729972518542596,
      "grad_norm": 1.7997329235076904,
      "learning_rate": 6e-05,
      "loss": 5.5993,
      "step": 6
    },
    {
      "epoch": 0.00020684967938299696,
      "grad_norm": 2.4111554622650146,
      "learning_rate": 7e-05,
      "loss": 5.5457,
      "step": 7
    },
    {
      "epoch": 0.00023639963358056796,
      "grad_norm": 2.166750907897949,
      "learning_rate": 8e-05,
      "loss": 5.1787,
      "step": 8
    },
    {
      "epoch": 0.00026594958777813896,
      "grad_norm": 2.529693603515625,
      "learning_rate": 9e-05,
      "loss": 4.6661,
      "step": 9
    },
    {
      "epoch": 0.00026594958777813896,
      "eval_loss": 2.4073753356933594,
      "eval_runtime": 5874.5347,
      "eval_samples_per_second": 4.851,
      "eval_steps_per_second": 0.607,
      "step": 9
    },
    {
      "epoch": 0.00029549954197570993,
      "grad_norm": 2.6786551475524902,
      "learning_rate": 0.0001,
      "loss": 4.8934,
      "step": 10
    },
    {
      "epoch": 0.00032504949617328095,
      "grad_norm": 3.189528703689575,
      "learning_rate": 9.99695413509548e-05,
      "loss": 4.7974,
      "step": 11
    },
    {
      "epoch": 0.0003545994503708519,
      "grad_norm": 3.0472705364227295,
      "learning_rate": 9.987820251299122e-05,
      "loss": 4.1945,
      "step": 12
    },
    {
      "epoch": 0.0003841494045684229,
      "grad_norm": 3.659665822982788,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.1629,
      "step": 13
    },
    {
      "epoch": 0.0004136993587659939,
      "grad_norm": 2.923701286315918,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.184,
      "step": 14
    },
    {
      "epoch": 0.0004432493129635649,
      "grad_norm": 3.409031629562378,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.0742,
      "step": 15
    },
    {
      "epoch": 0.0004727992671611359,
      "grad_norm": 3.4968302249908447,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.9005,
      "step": 16
    },
    {
      "epoch": 0.0005023492213587069,
      "grad_norm": 4.491170883178711,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.6972,
      "step": 17
    },
    {
      "epoch": 0.0005318991755562779,
      "grad_norm": 4.6056671142578125,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.5791,
      "step": 18
    },
    {
      "epoch": 0.0005318991755562779,
      "eval_loss": 1.2582483291625977,
      "eval_runtime": 5874.2012,
      "eval_samples_per_second": 4.851,
      "eval_steps_per_second": 0.607,
      "step": 18
    },
    {
      "epoch": 0.0005614491297538488,
      "grad_norm": 3.1649529933929443,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1894,
      "step": 19
    },
    {
      "epoch": 0.0005909990839514199,
      "grad_norm": 3.7243709564208984,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.4584,
      "step": 20
    },
    {
      "epoch": 0.0006205490381489909,
      "grad_norm": 5.015127658843994,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.0168,
      "step": 21
    },
    {
      "epoch": 0.0006500989923465619,
      "grad_norm": 3.6835927963256836,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.5988,
      "step": 22
    },
    {
      "epoch": 0.0006796489465441328,
      "grad_norm": 3.002901792526245,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.566,
      "step": 23
    },
    {
      "epoch": 0.0007091989007417038,
      "grad_norm": 3.6929385662078857,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.3708,
      "step": 24
    },
    {
      "epoch": 0.0007387488549392749,
      "grad_norm": 4.158296585083008,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.4414,
      "step": 25
    },
    {
      "epoch": 0.0007682988091368458,
      "grad_norm": 2.872539520263672,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.0839,
      "step": 26
    },
    {
      "epoch": 0.0007978487633344168,
      "grad_norm": 3.146365165710449,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.1332,
      "step": 27
    },
    {
      "epoch": 0.0007978487633344168,
      "eval_loss": 1.0715131759643555,
      "eval_runtime": 5871.8151,
      "eval_samples_per_second": 4.853,
      "eval_steps_per_second": 0.607,
      "step": 27
    },
    {
      "epoch": 0.0008273987175319878,
      "grad_norm": 5.3669538497924805,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.253,
      "step": 28
    },
    {
      "epoch": 0.0008569486717295589,
      "grad_norm": 2.2301602363586426,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.9265,
      "step": 29
    },
    {
      "epoch": 0.0008864986259271298,
      "grad_norm": 3.5137948989868164,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.5722,
      "step": 30
    },
    {
      "epoch": 0.0009160485801247008,
      "grad_norm": 2.713407516479492,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.2216,
      "step": 31
    },
    {
      "epoch": 0.0009455985343222718,
      "grad_norm": 2.0557379722595215,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.8588,
      "step": 32
    },
    {
      "epoch": 0.0009751484885198428,
      "grad_norm": 2.0198111534118652,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.8648,
      "step": 33
    },
    {
      "epoch": 0.0010046984427174138,
      "grad_norm": 2.3632073402404785,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.1044,
      "step": 34
    },
    {
      "epoch": 0.0010342483969149848,
      "grad_norm": 1.9320204257965088,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.8379,
      "step": 35
    },
    {
      "epoch": 0.0010637983511125558,
      "grad_norm": 1.7286494970321655,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.3026,
      "step": 36
    },
    {
      "epoch": 0.0010637983511125558,
      "eval_loss": 0.9508614540100098,
      "eval_runtime": 5872.34,
      "eval_samples_per_second": 4.853,
      "eval_steps_per_second": 0.607,
      "step": 36
    },
    {
      "epoch": 0.0010933483053101269,
      "grad_norm": 1.882214069366455,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5322,
      "step": 37
    },
    {
      "epoch": 0.0011228982595076977,
      "grad_norm": 1.8262519836425781,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.5499,
      "step": 38
    },
    {
      "epoch": 0.0011524482137052687,
      "grad_norm": 2.2393839359283447,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.9446,
      "step": 39
    },
    {
      "epoch": 0.0011819981679028397,
      "grad_norm": 1.8406883478164673,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3716,
      "step": 40
    },
    {
      "epoch": 0.0012115481221004107,
      "grad_norm": 2.10400128364563,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.1462,
      "step": 41
    },
    {
      "epoch": 0.0012410980762979818,
      "grad_norm": 2.732954978942871,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.8046,
      "step": 42
    },
    {
      "epoch": 0.0012706480304955528,
      "grad_norm": 2.190100908279419,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.6991,
      "step": 43
    },
    {
      "epoch": 0.0013001979846931238,
      "grad_norm": 2.131598472595215,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.7265,
      "step": 44
    },
    {
      "epoch": 0.0013297479388906946,
      "grad_norm": 2.4191086292266846,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.0866,
      "step": 45
    },
    {
      "epoch": 0.0013297479388906946,
      "eval_loss": 0.9063876867294312,
      "eval_runtime": 5872.647,
      "eval_samples_per_second": 4.853,
      "eval_steps_per_second": 0.607,
      "step": 45
    },
    {
      "epoch": 0.0013592978930882656,
      "grad_norm": 2.1638476848602295,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.636,
      "step": 46
    },
    {
      "epoch": 0.0013888478472858367,
      "grad_norm": 3.2080116271972656,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.1953,
      "step": 47
    },
    {
      "epoch": 0.0014183978014834077,
      "grad_norm": 2.4850316047668457,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.1594,
      "step": 48
    },
    {
      "epoch": 0.0014479477556809787,
      "grad_norm": 2.722036123275757,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.6908,
      "step": 49
    },
    {
      "epoch": 0.0014774977098785497,
      "grad_norm": 2.7537569999694824,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.0251,
      "step": 50
    },
    {
      "epoch": 0.0015070476640761208,
      "grad_norm": 2.1360747814178467,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.9877,
      "step": 51
    },
    {
      "epoch": 0.0015365976182736916,
      "grad_norm": 2.371792793273926,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.6839,
      "step": 52
    },
    {
      "epoch": 0.0015661475724712626,
      "grad_norm": 2.199202060699463,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.432,
      "step": 53
    },
    {
      "epoch": 0.0015956975266688336,
      "grad_norm": 2.497410535812378,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.9416,
      "step": 54
    },
    {
      "epoch": 0.0015956975266688336,
      "eval_loss": 0.8744269013404846,
      "eval_runtime": 5873.0123,
      "eval_samples_per_second": 4.852,
      "eval_steps_per_second": 0.607,
      "step": 54
    },
    {
      "epoch": 0.0016252474808664047,
      "grad_norm": 2.1169345378875732,
      "learning_rate": 5e-05,
      "loss": 1.7463,
      "step": 55
    },
    {
      "epoch": 0.0016547974350639757,
      "grad_norm": 2.2265374660491943,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.3274,
      "step": 56
    },
    {
      "epoch": 0.0016843473892615467,
      "grad_norm": 1.975367546081543,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.5586,
      "step": 57
    },
    {
      "epoch": 0.0017138973434591177,
      "grad_norm": 2.8126513957977295,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.7839,
      "step": 58
    },
    {
      "epoch": 0.0017434472976566885,
      "grad_norm": 2.17903995513916,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.2133,
      "step": 59
    },
    {
      "epoch": 0.0017729972518542596,
      "grad_norm": 2.8695647716522217,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.0455,
      "step": 60
    },
    {
      "epoch": 0.0018025472060518306,
      "grad_norm": 2.3486835956573486,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.9759,
      "step": 61
    },
    {
      "epoch": 0.0018320971602494016,
      "grad_norm": 1.5872043371200562,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.0783,
      "step": 62
    },
    {
      "epoch": 0.0018616471144469726,
      "grad_norm": 2.655707836151123,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.0831,
      "step": 63
    },
    {
      "epoch": 0.0018616471144469726,
      "eval_loss": 0.8404533863067627,
      "eval_runtime": 5873.7876,
      "eval_samples_per_second": 4.852,
      "eval_steps_per_second": 0.607,
      "step": 63
    },
    {
      "epoch": 0.0018911970686445437,
      "grad_norm": 1.9231730699539185,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.7464,
      "step": 64
    },
    {
      "epoch": 0.0019207470228421147,
      "grad_norm": 1.8210548162460327,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.2927,
      "step": 65
    },
    {
      "epoch": 0.0019502969770396855,
      "grad_norm": 1.9554582834243774,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.2465,
      "step": 66
    },
    {
      "epoch": 0.0019798469312372565,
      "grad_norm": 2.3461174964904785,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.5785,
      "step": 67
    },
    {
      "epoch": 0.0020093968854348276,
      "grad_norm": 2.1599013805389404,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.6371,
      "step": 68
    },
    {
      "epoch": 0.0020389468396323986,
      "grad_norm": 2.21620512008667,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.9272,
      "step": 69
    },
    {
      "epoch": 0.0020684967938299696,
      "grad_norm": 2.197643756866455,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.5105,
      "step": 70
    },
    {
      "epoch": 0.0020980467480275406,
      "grad_norm": 1.9392749071121216,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.8498,
      "step": 71
    },
    {
      "epoch": 0.0021275967022251117,
      "grad_norm": 2.3518924713134766,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.5962,
      "step": 72
    },
    {
      "epoch": 0.0021275967022251117,
      "eval_loss": 0.8251545429229736,
      "eval_runtime": 5872.6028,
      "eval_samples_per_second": 4.853,
      "eval_steps_per_second": 0.607,
      "step": 72
    },
    {
      "epoch": 0.0021571466564226827,
      "grad_norm": 2.2290399074554443,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.2628,
      "step": 73
    },
    {
      "epoch": 0.0021866966106202537,
      "grad_norm": 2.336202621459961,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.51,
      "step": 74
    },
    {
      "epoch": 0.0022162465648178247,
      "grad_norm": 1.708642601966858,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.3518,
      "step": 75
    },
    {
      "epoch": 0.0022457965190153953,
      "grad_norm": 1.7539479732513428,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.4559,
      "step": 76
    },
    {
      "epoch": 0.0022753464732129663,
      "grad_norm": 3.0132052898406982,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.3995,
      "step": 77
    },
    {
      "epoch": 0.0023048964274105374,
      "grad_norm": 1.756522536277771,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.3779,
      "step": 78
    },
    {
      "epoch": 0.0023344463816081084,
      "grad_norm": 1.5066357851028442,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.0589,
      "step": 79
    },
    {
      "epoch": 0.0023639963358056794,
      "grad_norm": 2.2123162746429443,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.8266,
      "step": 80
    },
    {
      "epoch": 0.0023935462900032504,
      "grad_norm": 1.886515736579895,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.243,
      "step": 81
    },
    {
      "epoch": 0.0023935462900032504,
      "eval_loss": 0.8142053484916687,
      "eval_runtime": 5878.778,
      "eval_samples_per_second": 4.848,
      "eval_steps_per_second": 0.606,
      "step": 81
    },
    {
      "epoch": 0.0024230962442008215,
      "grad_norm": 2.1723697185516357,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.4304,
      "step": 82
    },
    {
      "epoch": 0.0024526461983983925,
      "grad_norm": 2.0525877475738525,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.8475,
      "step": 83
    },
    {
      "epoch": 0.0024821961525959635,
      "grad_norm": 2.5386929512023926,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.6719,
      "step": 84
    },
    {
      "epoch": 0.0025117461067935345,
      "grad_norm": 2.252152681350708,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.4212,
      "step": 85
    },
    {
      "epoch": 0.0025412960609911056,
      "grad_norm": 1.8140268325805664,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.5093,
      "step": 86
    },
    {
      "epoch": 0.0025708460151886766,
      "grad_norm": 1.8527106046676636,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.2675,
      "step": 87
    },
    {
      "epoch": 0.0026003959693862476,
      "grad_norm": 2.5611603260040283,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.6779,
      "step": 88
    },
    {
      "epoch": 0.0026299459235838187,
      "grad_norm": 1.9794793128967285,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.4951,
      "step": 89
    },
    {
      "epoch": 0.0026594958777813892,
      "grad_norm": 2.645522356033325,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.1865,
      "step": 90
    },
    {
      "epoch": 0.0026594958777813892,
      "eval_loss": 0.8100898861885071,
      "eval_runtime": 5873.9152,
      "eval_samples_per_second": 4.852,
      "eval_steps_per_second": 0.607,
      "step": 90
    },
    {
      "epoch": 0.0026890458319789603,
      "grad_norm": 2.2799620628356934,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.8531,
      "step": 91
    },
    {
      "epoch": 0.0027185957861765313,
      "grad_norm": 2.1321165561676025,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.8171,
      "step": 92
    },
    {
      "epoch": 0.0027481457403741023,
      "grad_norm": 2.29913067817688,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.4964,
      "step": 93
    },
    {
      "epoch": 0.0027776956945716733,
      "grad_norm": 1.9983808994293213,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.6192,
      "step": 94
    },
    {
      "epoch": 0.0028072456487692444,
      "grad_norm": 2.9566855430603027,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.0019,
      "step": 95
    },
    {
      "epoch": 0.0028367956029668154,
      "grad_norm": 1.9108870029449463,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.1594,
      "step": 96
    },
    {
      "epoch": 0.0028663455571643864,
      "grad_norm": 2.6722331047058105,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.5236,
      "step": 97
    },
    {
      "epoch": 0.0028958955113619574,
      "grad_norm": 2.226942300796509,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.7669,
      "step": 98
    },
    {
      "epoch": 0.0029254454655595285,
      "grad_norm": 2.0672061443328857,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.5335,
      "step": 99
    },
    {
      "epoch": 0.0029254454655595285,
      "eval_loss": 0.8091546893119812,
      "eval_runtime": 5873.6433,
      "eval_samples_per_second": 4.852,
      "eval_steps_per_second": 0.607,
      "step": 99
    },
    {
      "epoch": 0.0029549954197570995,
      "grad_norm": 2.509993314743042,
      "learning_rate": 0.0,
      "loss": 1.5607,
      "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": 1.26956599246848e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}