{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1718213058419244,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001718213058419244,
      "grad_norm": 0.6761467456817627,
      "learning_rate": 1e-05,
      "loss": 1.6708,
      "step": 1
    },
    {
      "epoch": 0.001718213058419244,
      "eval_loss": 0.8681759238243103,
      "eval_runtime": 89.6582,
      "eval_samples_per_second": 5.465,
      "eval_steps_per_second": 0.692,
      "step": 1
    },
    {
      "epoch": 0.003436426116838488,
      "grad_norm": 0.7584896683692932,
      "learning_rate": 2e-05,
      "loss": 1.6835,
      "step": 2
    },
    {
      "epoch": 0.005154639175257732,
      "grad_norm": 0.7306342720985413,
      "learning_rate": 3e-05,
      "loss": 1.6789,
      "step": 3
    },
    {
      "epoch": 0.006872852233676976,
      "grad_norm": 0.7050411105155945,
      "learning_rate": 4e-05,
      "loss": 1.6542,
      "step": 4
    },
    {
      "epoch": 0.00859106529209622,
      "grad_norm": 0.6465184688568115,
      "learning_rate": 5e-05,
      "loss": 1.7086,
      "step": 5
    },
    {
      "epoch": 0.010309278350515464,
      "grad_norm": 0.8069021701812744,
      "learning_rate": 6e-05,
      "loss": 1.7654,
      "step": 6
    },
    {
      "epoch": 0.012027491408934709,
      "grad_norm": 0.6647135615348816,
      "learning_rate": 7e-05,
      "loss": 1.6618,
      "step": 7
    },
    {
      "epoch": 0.013745704467353952,
      "grad_norm": 0.5612677335739136,
      "learning_rate": 8e-05,
      "loss": 1.6134,
      "step": 8
    },
    {
      "epoch": 0.015463917525773196,
      "grad_norm": 0.5844854712486267,
      "learning_rate": 9e-05,
      "loss": 1.6407,
      "step": 9
    },
    {
      "epoch": 0.015463917525773196,
      "eval_loss": 0.7763700485229492,
      "eval_runtime": 90.0866,
      "eval_samples_per_second": 5.439,
      "eval_steps_per_second": 0.688,
      "step": 9
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": 0.5475785136222839,
      "learning_rate": 0.0001,
      "loss": 1.5296,
      "step": 10
    },
    {
      "epoch": 0.018900343642611683,
      "grad_norm": 0.5951645970344543,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.4575,
      "step": 11
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 0.6151654124259949,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.39,
      "step": 12
    },
    {
      "epoch": 0.022336769759450172,
      "grad_norm": 0.7063046097755432,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.4703,
      "step": 13
    },
    {
      "epoch": 0.024054982817869417,
      "grad_norm": 0.6995747089385986,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.3235,
      "step": 14
    },
    {
      "epoch": 0.02577319587628866,
      "grad_norm": 0.7196248769760132,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.3888,
      "step": 15
    },
    {
      "epoch": 0.027491408934707903,
      "grad_norm": 0.7144644856452942,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.3411,
      "step": 16
    },
    {
      "epoch": 0.029209621993127148,
      "grad_norm": 0.6330808401107788,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.317,
      "step": 17
    },
    {
      "epoch": 0.030927835051546393,
      "grad_norm": 0.6534203290939331,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.2535,
      "step": 18
    },
    {
      "epoch": 0.030927835051546393,
      "eval_loss": 0.6600751876831055,
      "eval_runtime": 90.058,
      "eval_samples_per_second": 5.441,
      "eval_steps_per_second": 0.688,
      "step": 18
    },
    {
      "epoch": 0.03264604810996564,
      "grad_norm": 0.6205346584320068,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2726,
      "step": 19
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 0.7121386528015137,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.3972,
      "step": 20
    },
    {
      "epoch": 0.03608247422680412,
      "grad_norm": 0.6126396059989929,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.2755,
      "step": 21
    },
    {
      "epoch": 0.037800687285223365,
      "grad_norm": 0.5825527906417847,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.1983,
      "step": 22
    },
    {
      "epoch": 0.03951890034364261,
      "grad_norm": 0.5882991552352905,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.2682,
      "step": 23
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 0.6152936816215515,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.3317,
      "step": 24
    },
    {
      "epoch": 0.0429553264604811,
      "grad_norm": 0.6240371465682983,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.2499,
      "step": 25
    },
    {
      "epoch": 0.044673539518900345,
      "grad_norm": 0.5625409483909607,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.23,
      "step": 26
    },
    {
      "epoch": 0.04639175257731959,
      "grad_norm": 0.5756645798683167,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.3085,
      "step": 27
    },
    {
      "epoch": 0.04639175257731959,
      "eval_loss": 0.6129422783851624,
      "eval_runtime": 90.0726,
      "eval_samples_per_second": 5.44,
      "eval_steps_per_second": 0.688,
      "step": 27
    },
    {
      "epoch": 0.048109965635738834,
      "grad_norm": 0.660899817943573,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2661,
      "step": 28
    },
    {
      "epoch": 0.04982817869415808,
      "grad_norm": 0.5710423588752747,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.2704,
      "step": 29
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 0.5831442475318909,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.1818,
      "step": 30
    },
    {
      "epoch": 0.05326460481099656,
      "grad_norm": 0.5942109823226929,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.132,
      "step": 31
    },
    {
      "epoch": 0.054982817869415807,
      "grad_norm": 0.5549724102020264,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.0963,
      "step": 32
    },
    {
      "epoch": 0.05670103092783505,
      "grad_norm": 0.6371067762374878,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.3632,
      "step": 33
    },
    {
      "epoch": 0.058419243986254296,
      "grad_norm": 0.6509641408920288,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.1494,
      "step": 34
    },
    {
      "epoch": 0.06013745704467354,
      "grad_norm": 0.6082617044448853,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.1516,
      "step": 35
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 0.6625918745994568,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.3591,
      "step": 36
    },
    {
      "epoch": 0.061855670103092786,
      "eval_loss": 0.5890389680862427,
      "eval_runtime": 90.0729,
      "eval_samples_per_second": 5.44,
      "eval_steps_per_second": 0.688,
      "step": 36
    },
    {
      "epoch": 0.06357388316151202,
      "grad_norm": 0.5958872437477112,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.1325,
      "step": 37
    },
    {
      "epoch": 0.06529209621993128,
      "grad_norm": 0.6519022583961487,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.2628,
      "step": 38
    },
    {
      "epoch": 0.06701030927835051,
      "grad_norm": 0.6372320055961609,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.2151,
      "step": 39
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 0.635481595993042,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.24,
      "step": 40
    },
    {
      "epoch": 0.070446735395189,
      "grad_norm": 0.6580904722213745,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.2194,
      "step": 41
    },
    {
      "epoch": 0.07216494845360824,
      "grad_norm": 0.7618088126182556,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.2026,
      "step": 42
    },
    {
      "epoch": 0.07388316151202749,
      "grad_norm": 0.5822939872741699,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.1265,
      "step": 43
    },
    {
      "epoch": 0.07560137457044673,
      "grad_norm": 0.660304844379425,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.0953,
      "step": 44
    },
    {
      "epoch": 0.07731958762886598,
      "grad_norm": 0.5835567712783813,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.1231,
      "step": 45
    },
    {
      "epoch": 0.07731958762886598,
      "eval_loss": 0.571000337600708,
      "eval_runtime": 90.0919,
      "eval_samples_per_second": 5.439,
      "eval_steps_per_second": 0.688,
      "step": 45
    },
    {
      "epoch": 0.07903780068728522,
      "grad_norm": 0.6019623279571533,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.141,
      "step": 46
    },
    {
      "epoch": 0.08075601374570447,
      "grad_norm": 0.6385236978530884,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.0045,
      "step": 47
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.6389127373695374,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.1072,
      "step": 48
    },
    {
      "epoch": 0.08419243986254296,
      "grad_norm": 0.7257405519485474,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.2243,
      "step": 49
    },
    {
      "epoch": 0.0859106529209622,
      "grad_norm": 0.675135612487793,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.1236,
      "step": 50
    },
    {
      "epoch": 0.08762886597938144,
      "grad_norm": 0.6229404807090759,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.0744,
      "step": 51
    },
    {
      "epoch": 0.08934707903780069,
      "grad_norm": 0.6649324297904968,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.2195,
      "step": 52
    },
    {
      "epoch": 0.09106529209621993,
      "grad_norm": 0.6774650812149048,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.1679,
      "step": 53
    },
    {
      "epoch": 0.09278350515463918,
      "grad_norm": 0.7095744013786316,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.108,
      "step": 54
    },
    {
      "epoch": 0.09278350515463918,
      "eval_loss": 0.5606745481491089,
      "eval_runtime": 90.1119,
      "eval_samples_per_second": 5.438,
      "eval_steps_per_second": 0.688,
      "step": 54
    },
    {
      "epoch": 0.09450171821305842,
      "grad_norm": 0.6476197838783264,
      "learning_rate": 5e-05,
      "loss": 1.1153,
      "step": 55
    },
    {
      "epoch": 0.09621993127147767,
      "grad_norm": 0.6215334534645081,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.0411,
      "step": 56
    },
    {
      "epoch": 0.0979381443298969,
      "grad_norm": 0.6149742603302002,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.065,
      "step": 57
    },
    {
      "epoch": 0.09965635738831616,
      "grad_norm": 0.6694630980491638,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.1175,
      "step": 58
    },
    {
      "epoch": 0.1013745704467354,
      "grad_norm": 0.651583731174469,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.0373,
      "step": 59
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 0.7086051106452942,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.1749,
      "step": 60
    },
    {
      "epoch": 0.10481099656357389,
      "grad_norm": 0.6843875050544739,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.1709,
      "step": 61
    },
    {
      "epoch": 0.10652920962199312,
      "grad_norm": 0.6379663944244385,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.0606,
      "step": 62
    },
    {
      "epoch": 0.10824742268041238,
      "grad_norm": 0.6318539381027222,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.0532,
      "step": 63
    },
    {
      "epoch": 0.10824742268041238,
      "eval_loss": 0.5513098835945129,
      "eval_runtime": 90.0773,
      "eval_samples_per_second": 5.44,
      "eval_steps_per_second": 0.688,
      "step": 63
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": 0.6428488492965698,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1226,
      "step": 64
    },
    {
      "epoch": 0.11168384879725086,
      "grad_norm": 0.645643413066864,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.0735,
      "step": 65
    },
    {
      "epoch": 0.1134020618556701,
      "grad_norm": 0.6907498836517334,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.1535,
      "step": 66
    },
    {
      "epoch": 0.11512027491408934,
      "grad_norm": 0.694670557975769,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.1467,
      "step": 67
    },
    {
      "epoch": 0.11683848797250859,
      "grad_norm": 0.6445086598396301,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.203,
      "step": 68
    },
    {
      "epoch": 0.11855670103092783,
      "grad_norm": 0.6669037342071533,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.1215,
      "step": 69
    },
    {
      "epoch": 0.12027491408934708,
      "grad_norm": 0.6564927697181702,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0801,
      "step": 70
    },
    {
      "epoch": 0.12199312714776632,
      "grad_norm": 0.6863424181938171,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.0468,
      "step": 71
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.6587359309196472,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.1093,
      "step": 72
    },
    {
      "epoch": 0.12371134020618557,
      "eval_loss": 0.545613706111908,
      "eval_runtime": 90.0987,
      "eval_samples_per_second": 5.438,
      "eval_steps_per_second": 0.688,
      "step": 72
    },
    {
      "epoch": 0.1254295532646048,
      "grad_norm": 0.6815155148506165,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.1796,
      "step": 73
    },
    {
      "epoch": 0.12714776632302405,
      "grad_norm": 0.6789014339447021,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.09,
      "step": 74
    },
    {
      "epoch": 0.12886597938144329,
      "grad_norm": 0.5994151830673218,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.0405,
      "step": 75
    },
    {
      "epoch": 0.13058419243986255,
      "grad_norm": 0.6434558629989624,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.1474,
      "step": 76
    },
    {
      "epoch": 0.1323024054982818,
      "grad_norm": 0.7437100410461426,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.2151,
      "step": 77
    },
    {
      "epoch": 0.13402061855670103,
      "grad_norm": 0.6664707064628601,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.1721,
      "step": 78
    },
    {
      "epoch": 0.13573883161512026,
      "grad_norm": 0.6813791394233704,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.0832,
      "step": 79
    },
    {
      "epoch": 0.13745704467353953,
      "grad_norm": 0.6612464189529419,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.0722,
      "step": 80
    },
    {
      "epoch": 0.13917525773195877,
      "grad_norm": 0.6873725056648254,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.0193,
      "step": 81
    },
    {
      "epoch": 0.13917525773195877,
      "eval_loss": 0.5418484807014465,
      "eval_runtime": 90.091,
      "eval_samples_per_second": 5.439,
      "eval_steps_per_second": 0.688,
      "step": 81
    },
    {
      "epoch": 0.140893470790378,
      "grad_norm": 0.7357692122459412,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.1107,
      "step": 82
    },
    {
      "epoch": 0.14261168384879724,
      "grad_norm": 0.6933891773223877,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.2102,
      "step": 83
    },
    {
      "epoch": 0.14432989690721648,
      "grad_norm": 0.6409657001495361,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.0662,
      "step": 84
    },
    {
      "epoch": 0.14604810996563575,
      "grad_norm": 0.6849522590637207,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.0757,
      "step": 85
    },
    {
      "epoch": 0.14776632302405499,
      "grad_norm": 0.666235625743866,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.0345,
      "step": 86
    },
    {
      "epoch": 0.14948453608247422,
      "grad_norm": 0.7493944764137268,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.1229,
      "step": 87
    },
    {
      "epoch": 0.15120274914089346,
      "grad_norm": 0.6612552404403687,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.0169,
      "step": 88
    },
    {
      "epoch": 0.15292096219931273,
      "grad_norm": 0.7491831183433533,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.098,
      "step": 89
    },
    {
      "epoch": 0.15463917525773196,
      "grad_norm": 0.702360987663269,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.0957,
      "step": 90
    },
    {
      "epoch": 0.15463917525773196,
      "eval_loss": 0.5402591824531555,
      "eval_runtime": 90.1321,
      "eval_samples_per_second": 5.436,
      "eval_steps_per_second": 0.688,
      "step": 90
    },
    {
      "epoch": 0.1563573883161512,
      "grad_norm": 0.654188871383667,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.0253,
      "step": 91
    },
    {
      "epoch": 0.15807560137457044,
      "grad_norm": 0.6523233652114868,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.0829,
      "step": 92
    },
    {
      "epoch": 0.15979381443298968,
      "grad_norm": 0.6463702917098999,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.0892,
      "step": 93
    },
    {
      "epoch": 0.16151202749140894,
      "grad_norm": 0.6319651007652283,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.9806,
      "step": 94
    },
    {
      "epoch": 0.16323024054982818,
      "grad_norm": 0.7006255984306335,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.122,
      "step": 95
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.7132532596588135,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.0599,
      "step": 96
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.63579261302948,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.0059,
      "step": 97
    },
    {
      "epoch": 0.16838487972508592,
      "grad_norm": 0.7264676690101624,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.0731,
      "step": 98
    },
    {
      "epoch": 0.17010309278350516,
      "grad_norm": 0.6729429960250854,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.0864,
      "step": 99
    },
    {
      "epoch": 0.17010309278350516,
      "eval_loss": 0.5399183034896851,
      "eval_runtime": 90.1569,
      "eval_samples_per_second": 5.435,
      "eval_steps_per_second": 0.688,
      "step": 99
    },
    {
      "epoch": 0.1718213058419244,
      "grad_norm": 0.6568922400474548,
      "learning_rate": 0.0,
      "loss": 1.0962,
      "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": 1.306916403806208e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}