{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009961647656522389,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.961647656522389e-05,
      "grad_norm": 0.3748319745063782,
      "learning_rate": 1e-05,
      "loss": 1.6077,
      "step": 1
    },
    {
      "epoch": 9.961647656522389e-05,
      "eval_loss": 1.0737049579620361,
      "eval_runtime": 1789.5077,
      "eval_samples_per_second": 4.724,
      "eval_steps_per_second": 0.591,
      "step": 1
    },
    {
      "epoch": 0.00019923295313044778,
      "grad_norm": 0.47770676016807556,
      "learning_rate": 2e-05,
      "loss": 2.0602,
      "step": 2
    },
    {
      "epoch": 0.0002988494296956717,
      "grad_norm": 0.4726722538471222,
      "learning_rate": 3e-05,
      "loss": 2.2152,
      "step": 3
    },
    {
      "epoch": 0.00039846590626089557,
      "grad_norm": 0.509148359298706,
      "learning_rate": 4e-05,
      "loss": 2.2219,
      "step": 4
    },
    {
      "epoch": 0.0004980823828261194,
      "grad_norm": 0.6239567399024963,
      "learning_rate": 5e-05,
      "loss": 2.3138,
      "step": 5
    },
    {
      "epoch": 0.0005976988593913434,
      "grad_norm": 0.5875715017318726,
      "learning_rate": 6e-05,
      "loss": 2.3489,
      "step": 6
    },
    {
      "epoch": 0.0006973153359565673,
      "grad_norm": 0.47263002395629883,
      "learning_rate": 7e-05,
      "loss": 1.813,
      "step": 7
    },
    {
      "epoch": 0.0007969318125217911,
      "grad_norm": 0.5967614054679871,
      "learning_rate": 8e-05,
      "loss": 2.1826,
      "step": 8
    },
    {
      "epoch": 0.000896548289087015,
      "grad_norm": 0.750761866569519,
      "learning_rate": 9e-05,
      "loss": 2.2517,
      "step": 9
    },
    {
      "epoch": 0.000896548289087015,
      "eval_loss": 1.023254632949829,
      "eval_runtime": 1791.5954,
      "eval_samples_per_second": 4.719,
      "eval_steps_per_second": 0.59,
      "step": 9
    },
    {
      "epoch": 0.0009961647656522388,
      "grad_norm": 0.7320921421051025,
      "learning_rate": 0.0001,
      "loss": 2.3192,
      "step": 10
    },
    {
      "epoch": 0.0010957812422174628,
      "grad_norm": 0.6750331521034241,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.9599,
      "step": 11
    },
    {
      "epoch": 0.0011953977187826868,
      "grad_norm": 0.7737115025520325,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.0029,
      "step": 12
    },
    {
      "epoch": 0.0012950141953479105,
      "grad_norm": 0.7610511183738708,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.983,
      "step": 13
    },
    {
      "epoch": 0.0013946306719131345,
      "grad_norm": 0.739033043384552,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.0262,
      "step": 14
    },
    {
      "epoch": 0.0014942471484783583,
      "grad_norm": 1.2172285318374634,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.9857,
      "step": 15
    },
    {
      "epoch": 0.0015938636250435823,
      "grad_norm": 1.3501102924346924,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.0328,
      "step": 16
    },
    {
      "epoch": 0.001693480101608806,
      "grad_norm": 1.155712366104126,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.8468,
      "step": 17
    },
    {
      "epoch": 0.00179309657817403,
      "grad_norm": 0.8886969089508057,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7503,
      "step": 18
    },
    {
      "epoch": 0.00179309657817403,
      "eval_loss": 0.855793833732605,
      "eval_runtime": 1791.6889,
      "eval_samples_per_second": 4.718,
      "eval_steps_per_second": 0.59,
      "step": 18
    },
    {
      "epoch": 0.0018927130547392538,
      "grad_norm": 0.7103469967842102,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.5929,
      "step": 19
    },
    {
      "epoch": 0.0019923295313044776,
      "grad_norm": 0.7840328812599182,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.5679,
      "step": 20
    },
    {
      "epoch": 0.0020919460078697018,
      "grad_norm": 0.91854327917099,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.5348,
      "step": 21
    },
    {
      "epoch": 0.0021915624844349255,
      "grad_norm": 0.937053918838501,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.6614,
      "step": 22
    },
    {
      "epoch": 0.0022911789610001493,
      "grad_norm": 0.7176125049591064,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.42,
      "step": 23
    },
    {
      "epoch": 0.0023907954375653735,
      "grad_norm": 0.6584264636039734,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.4349,
      "step": 24
    },
    {
      "epoch": 0.0024904119141305973,
      "grad_norm": 0.8029303550720215,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5511,
      "step": 25
    },
    {
      "epoch": 0.002590028390695821,
      "grad_norm": 0.7229349613189697,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.5875,
      "step": 26
    },
    {
      "epoch": 0.002689644867261045,
      "grad_norm": 0.7011633515357971,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.4422,
      "step": 27
    },
    {
      "epoch": 0.002689644867261045,
      "eval_loss": 0.8157444596290588,
      "eval_runtime": 1793.0592,
      "eval_samples_per_second": 4.715,
      "eval_steps_per_second": 0.589,
      "step": 27
    },
    {
      "epoch": 0.002789261343826269,
      "grad_norm": 0.7655370235443115,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.4044,
      "step": 28
    },
    {
      "epoch": 0.002888877820391493,
      "grad_norm": 0.7056297659873962,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.2278,
      "step": 29
    },
    {
      "epoch": 0.0029884942969567166,
      "grad_norm": 0.8524144291877747,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.7044,
      "step": 30
    },
    {
      "epoch": 0.0030881107735219403,
      "grad_norm": 0.8623614311218262,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.407,
      "step": 31
    },
    {
      "epoch": 0.0031877272500871645,
      "grad_norm": 0.6192923188209534,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.2924,
      "step": 32
    },
    {
      "epoch": 0.0032873437266523883,
      "grad_norm": 0.751940906047821,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.4389,
      "step": 33
    },
    {
      "epoch": 0.003386960203217612,
      "grad_norm": 0.8193197846412659,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.6467,
      "step": 34
    },
    {
      "epoch": 0.0034865766797828363,
      "grad_norm": 0.9100502729415894,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.8511,
      "step": 35
    },
    {
      "epoch": 0.00358619315634806,
      "grad_norm": 0.6470741629600525,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.7999,
      "step": 36
    },
    {
      "epoch": 0.00358619315634806,
      "eval_loss": 0.7980929017066956,
      "eval_runtime": 1792.1871,
      "eval_samples_per_second": 4.717,
      "eval_steps_per_second": 0.59,
      "step": 36
    },
    {
      "epoch": 0.003685809632913284,
      "grad_norm": 0.677931010723114,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5122,
      "step": 37
    },
    {
      "epoch": 0.0037854261094785076,
      "grad_norm": 0.762718677520752,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.6601,
      "step": 38
    },
    {
      "epoch": 0.0038850425860437318,
      "grad_norm": 0.9628387689590454,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.8207,
      "step": 39
    },
    {
      "epoch": 0.003984659062608955,
      "grad_norm": 0.7539001107215881,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5463,
      "step": 40
    },
    {
      "epoch": 0.004084275539174179,
      "grad_norm": 0.8410975337028503,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.6561,
      "step": 41
    },
    {
      "epoch": 0.0041838920157394035,
      "grad_norm": 0.7135648727416992,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.7115,
      "step": 42
    },
    {
      "epoch": 0.004283508492304627,
      "grad_norm": 0.6998557448387146,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.4507,
      "step": 43
    },
    {
      "epoch": 0.004383124968869851,
      "grad_norm": 0.7283175587654114,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.6081,
      "step": 44
    },
    {
      "epoch": 0.004482741445435075,
      "grad_norm": 0.8036450147628784,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5691,
      "step": 45
    },
    {
      "epoch": 0.004482741445435075,
      "eval_loss": 0.7816627025604248,
      "eval_runtime": 1792.2297,
      "eval_samples_per_second": 4.717,
      "eval_steps_per_second": 0.59,
      "step": 45
    },
    {
      "epoch": 0.004582357922000299,
      "grad_norm": 0.8214872479438782,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.6442,
      "step": 46
    },
    {
      "epoch": 0.004681974398565523,
      "grad_norm": 0.7427443861961365,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.4082,
      "step": 47
    },
    {
      "epoch": 0.004781590875130747,
      "grad_norm": 0.5892370939254761,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.3837,
      "step": 48
    },
    {
      "epoch": 0.00488120735169597,
      "grad_norm": 0.8555832505226135,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.8097,
      "step": 49
    },
    {
      "epoch": 0.0049808238282611945,
      "grad_norm": 0.7236791849136353,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.6533,
      "step": 50
    },
    {
      "epoch": 0.005080440304826418,
      "grad_norm": 0.812048614025116,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.638,
      "step": 51
    },
    {
      "epoch": 0.005180056781391642,
      "grad_norm": 0.7956192493438721,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.5583,
      "step": 52
    },
    {
      "epoch": 0.005279673257956866,
      "grad_norm": 0.6739868521690369,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.3027,
      "step": 53
    },
    {
      "epoch": 0.00537928973452209,
      "grad_norm": 0.9760400652885437,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.7331,
      "step": 54
    },
    {
      "epoch": 0.00537928973452209,
      "eval_loss": 0.7753952741622925,
      "eval_runtime": 1791.7807,
      "eval_samples_per_second": 4.718,
      "eval_steps_per_second": 0.59,
      "step": 54
    },
    {
      "epoch": 0.005478906211087314,
      "grad_norm": 0.6633710265159607,
      "learning_rate": 5e-05,
      "loss": 1.4165,
      "step": 55
    },
    {
      "epoch": 0.005578522687652538,
      "grad_norm": 0.7722735404968262,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.7353,
      "step": 56
    },
    {
      "epoch": 0.005678139164217761,
      "grad_norm": 0.6650843620300293,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.4496,
      "step": 57
    },
    {
      "epoch": 0.005777755640782986,
      "grad_norm": 0.7399047017097473,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.715,
      "step": 58
    },
    {
      "epoch": 0.00587737211734821,
      "grad_norm": 0.7280799150466919,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.7639,
      "step": 59
    },
    {
      "epoch": 0.005976988593913433,
      "grad_norm": 1.0678982734680176,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.6916,
      "step": 60
    },
    {
      "epoch": 0.006076605070478657,
      "grad_norm": 0.8208115100860596,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.4452,
      "step": 61
    },
    {
      "epoch": 0.006176221547043881,
      "grad_norm": 0.6927385330200195,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.4143,
      "step": 62
    },
    {
      "epoch": 0.006275838023609105,
      "grad_norm": 0.9399744272232056,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.5787,
      "step": 63
    },
    {
      "epoch": 0.006275838023609105,
      "eval_loss": 0.770902156829834,
      "eval_runtime": 1791.4077,
      "eval_samples_per_second": 4.719,
      "eval_steps_per_second": 0.59,
      "step": 63
    },
    {
      "epoch": 0.006375454500174329,
      "grad_norm": 0.7469996213912964,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.59,
      "step": 64
    },
    {
      "epoch": 0.006475070976739552,
      "grad_norm": 0.7040720582008362,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.3536,
      "step": 65
    },
    {
      "epoch": 0.006574687453304777,
      "grad_norm": 0.6951753497123718,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.4466,
      "step": 66
    },
    {
      "epoch": 0.006674303929870001,
      "grad_norm": 0.8452994227409363,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.7814,
      "step": 67
    },
    {
      "epoch": 0.006773920406435224,
      "grad_norm": 0.8350580334663391,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.7372,
      "step": 68
    },
    {
      "epoch": 0.006873536883000448,
      "grad_norm": 0.7877200841903687,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.8383,
      "step": 69
    },
    {
      "epoch": 0.0069731533595656725,
      "grad_norm": 0.7458710670471191,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.5072,
      "step": 70
    },
    {
      "epoch": 0.007072769836130896,
      "grad_norm": 0.8738251328468323,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.8373,
      "step": 71
    },
    {
      "epoch": 0.00717238631269612,
      "grad_norm": 0.937622606754303,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.6339,
      "step": 72
    },
    {
      "epoch": 0.00717238631269612,
      "eval_loss": 0.7681018710136414,
      "eval_runtime": 1791.6374,
      "eval_samples_per_second": 4.719,
      "eval_steps_per_second": 0.59,
      "step": 72
    },
    {
      "epoch": 0.007272002789261343,
      "grad_norm": 0.6866787672042847,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.3402,
      "step": 73
    },
    {
      "epoch": 0.007371619265826568,
      "grad_norm": 0.8870444893836975,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.671,
      "step": 74
    },
    {
      "epoch": 0.007471235742391792,
      "grad_norm": 0.6555038690567017,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.3535,
      "step": 75
    },
    {
      "epoch": 0.007570852218957015,
      "grad_norm": 0.8664092421531677,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.4339,
      "step": 76
    },
    {
      "epoch": 0.007670468695522239,
      "grad_norm": 0.794583261013031,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.5005,
      "step": 77
    },
    {
      "epoch": 0.0077700851720874636,
      "grad_norm": 0.6714551448822021,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.3048,
      "step": 78
    },
    {
      "epoch": 0.007869701648652687,
      "grad_norm": 0.7981712222099304,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.4734,
      "step": 79
    },
    {
      "epoch": 0.00796931812521791,
      "grad_norm": 0.8687072396278381,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.8168,
      "step": 80
    },
    {
      "epoch": 0.008068934601783135,
      "grad_norm": 0.8038095831871033,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.6298,
      "step": 81
    },
    {
      "epoch": 0.008068934601783135,
      "eval_loss": 0.7665637731552124,
      "eval_runtime": 1791.3829,
      "eval_samples_per_second": 4.719,
      "eval_steps_per_second": 0.59,
      "step": 81
    },
    {
      "epoch": 0.008168551078348359,
      "grad_norm": 0.6158639788627625,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2939,
      "step": 82
    },
    {
      "epoch": 0.008268167554913582,
      "grad_norm": 0.6034613847732544,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.3772,
      "step": 83
    },
    {
      "epoch": 0.008367784031478807,
      "grad_norm": 0.6227165460586548,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.3024,
      "step": 84
    },
    {
      "epoch": 0.00846740050804403,
      "grad_norm": 0.7155154347419739,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.4845,
      "step": 85
    },
    {
      "epoch": 0.008567016984609254,
      "grad_norm": 0.7330078482627869,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.4502,
      "step": 86
    },
    {
      "epoch": 0.008666633461174479,
      "grad_norm": 0.6891200542449951,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.5192,
      "step": 87
    },
    {
      "epoch": 0.008766249937739702,
      "grad_norm": 0.7983207702636719,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.6114,
      "step": 88
    },
    {
      "epoch": 0.008865866414304925,
      "grad_norm": 0.7906274795532227,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.6496,
      "step": 89
    },
    {
      "epoch": 0.00896548289087015,
      "grad_norm": 0.6719912886619568,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.3213,
      "step": 90
    },
    {
      "epoch": 0.00896548289087015,
      "eval_loss": 0.7659702897071838,
      "eval_runtime": 1791.5576,
      "eval_samples_per_second": 4.719,
      "eval_steps_per_second": 0.59,
      "step": 90
    },
    {
      "epoch": 0.009065099367435374,
      "grad_norm": 0.7697194814682007,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.6372,
      "step": 91
    },
    {
      "epoch": 0.009164715844000597,
      "grad_norm": 0.6751009225845337,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.318,
      "step": 92
    },
    {
      "epoch": 0.009264332320565822,
      "grad_norm": 0.6714102625846863,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.297,
      "step": 93
    },
    {
      "epoch": 0.009363948797131046,
      "grad_norm": 0.8002302050590515,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.6453,
      "step": 94
    },
    {
      "epoch": 0.009463565273696269,
      "grad_norm": 0.6762931942939758,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.5121,
      "step": 95
    },
    {
      "epoch": 0.009563181750261494,
      "grad_norm": 0.7909438610076904,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.3313,
      "step": 96
    },
    {
      "epoch": 0.009662798226826717,
      "grad_norm": 0.6866534352302551,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.543,
      "step": 97
    },
    {
      "epoch": 0.00976241470339194,
      "grad_norm": 0.6734254360198975,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.4738,
      "step": 98
    },
    {
      "epoch": 0.009862031179957166,
      "grad_norm": 0.6834343671798706,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.4935,
      "step": 99
    },
    {
      "epoch": 0.009862031179957166,
      "eval_loss": 0.7658064365386963,
      "eval_runtime": 1791.8569,
      "eval_samples_per_second": 4.718,
      "eval_steps_per_second": 0.59,
      "step": 99
    },
    {
      "epoch": 0.009961647656522389,
      "grad_norm": 0.6811820864677429,
      "learning_rate": 0.0,
      "loss": 1.5149,
      "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": 1.2886094823555072e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}