{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12445550715619166,
  "eval_steps": 10,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012445550715619166,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8073,
      "step": 1
    },
    {
      "epoch": 0.002489110143123833,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8285,
      "step": 2
    },
    {
      "epoch": 0.00373366521468575,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7975,
      "step": 3
    },
    {
      "epoch": 0.004978220286247666,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.798,
      "step": 4
    },
    {
      "epoch": 0.006222775357809583,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8443,
      "step": 5
    },
    {
      "epoch": 0.0074673304293715,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8074,
      "step": 6
    },
    {
      "epoch": 0.008711885500933417,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7588,
      "step": 7
    },
    {
      "epoch": 0.009956440572495333,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8136,
      "step": 8
    },
    {
      "epoch": 0.01120099564405725,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7397,
      "step": 9
    },
    {
      "epoch": 0.012445550715619166,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7745,
      "step": 10
    },
    {
      "epoch": 0.012445550715619166,
      "eval_loss": 2.8210322856903076,
      "eval_runtime": 43.0476,
      "eval_samples_per_second": 23.23,
      "eval_steps_per_second": 0.976,
      "step": 10
    },
    {
      "epoch": 0.013690105787181083,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8275,
      "step": 11
    },
    {
      "epoch": 0.014934660858743,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7762,
      "step": 12
    },
    {
      "epoch": 0.016179215930304917,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7799,
      "step": 13
    },
    {
      "epoch": 0.017423771001866834,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7906,
      "step": 14
    },
    {
      "epoch": 0.018668326073428748,
      "grad_norm": 5.01304292678833,
      "learning_rate": 2.0746887966804982e-08,
      "loss": 2.7712,
      "step": 15
    },
    {
      "epoch": 0.019912881144990666,
      "grad_norm": 4.976474761962891,
      "learning_rate": 4.1493775933609963e-08,
      "loss": 2.829,
      "step": 16
    },
    {
      "epoch": 0.021157436216552583,
      "grad_norm": 5.539012908935547,
      "learning_rate": 6.224066390041494e-08,
      "loss": 2.813,
      "step": 17
    },
    {
      "epoch": 0.0224019912881145,
      "grad_norm": 5.4900407791137695,
      "learning_rate": 8.298755186721993e-08,
      "loss": 2.8126,
      "step": 18
    },
    {
      "epoch": 0.023646546359676415,
      "grad_norm": 5.457218647003174,
      "learning_rate": 1.037344398340249e-07,
      "loss": 2.7482,
      "step": 19
    },
    {
      "epoch": 0.024891101431238332,
      "grad_norm": 5.231036186218262,
      "learning_rate": 1.2448132780082988e-07,
      "loss": 2.8323,
      "step": 20
    },
    {
      "epoch": 0.024891101431238332,
      "eval_loss": 2.819715738296509,
      "eval_runtime": 43.9884,
      "eval_samples_per_second": 22.733,
      "eval_steps_per_second": 0.955,
      "step": 20
    },
    {
      "epoch": 0.02613565650280025,
      "grad_norm": 5.337130546569824,
      "learning_rate": 1.4522821576763488e-07,
      "loss": 2.776,
      "step": 21
    },
    {
      "epoch": 0.027380211574362167,
      "grad_norm": 4.973108291625977,
      "learning_rate": 1.6597510373443985e-07,
      "loss": 2.8239,
      "step": 22
    },
    {
      "epoch": 0.02862476664592408,
      "grad_norm": 4.8733906745910645,
      "learning_rate": 1.8672199170124483e-07,
      "loss": 2.8069,
      "step": 23
    },
    {
      "epoch": 0.029869321717486,
      "grad_norm": 5.061434745788574,
      "learning_rate": 2.074688796680498e-07,
      "loss": 2.8063,
      "step": 24
    },
    {
      "epoch": 0.031113876789047916,
      "grad_norm": 4.782018661499023,
      "learning_rate": 2.2821576763485478e-07,
      "loss": 2.7488,
      "step": 25
    },
    {
      "epoch": 0.03235843186060983,
      "grad_norm": 4.394975662231445,
      "learning_rate": 2.4896265560165975e-07,
      "loss": 2.7683,
      "step": 26
    },
    {
      "epoch": 0.03360298693217175,
      "grad_norm": 4.475763320922852,
      "learning_rate": 2.6970954356846476e-07,
      "loss": 2.8143,
      "step": 27
    },
    {
      "epoch": 0.03484754200373367,
      "grad_norm": 4.362309455871582,
      "learning_rate": 2.9045643153526976e-07,
      "loss": 2.7875,
      "step": 28
    },
    {
      "epoch": 0.03609209707529558,
      "grad_norm": 3.9444823265075684,
      "learning_rate": 3.112033195020747e-07,
      "loss": 2.766,
      "step": 29
    },
    {
      "epoch": 0.037336652146857496,
      "grad_norm": 3.4614129066467285,
      "learning_rate": 3.319502074688797e-07,
      "loss": 2.7644,
      "step": 30
    },
    {
      "epoch": 0.037336652146857496,
      "eval_loss": 2.772022008895874,
      "eval_runtime": 45.8513,
      "eval_samples_per_second": 21.81,
      "eval_steps_per_second": 0.916,
      "step": 30
    },
    {
      "epoch": 0.038581207218419414,
      "grad_norm": 3.449410915374756,
      "learning_rate": 3.5269709543568466e-07,
      "loss": 2.7653,
      "step": 31
    },
    {
      "epoch": 0.03982576228998133,
      "grad_norm": 3.3115482330322266,
      "learning_rate": 3.7344398340248966e-07,
      "loss": 2.7032,
      "step": 32
    },
    {
      "epoch": 0.04107031736154325,
      "grad_norm": 3.2057440280914307,
      "learning_rate": 3.941908713692946e-07,
      "loss": 2.7766,
      "step": 33
    },
    {
      "epoch": 0.042314872433105166,
      "grad_norm": 3.4503021240234375,
      "learning_rate": 4.149377593360996e-07,
      "loss": 2.7214,
      "step": 34
    },
    {
      "epoch": 0.043559427504667084,
      "grad_norm": 3.1477363109588623,
      "learning_rate": 4.3568464730290456e-07,
      "loss": 2.7333,
      "step": 35
    },
    {
      "epoch": 0.044803982576229,
      "grad_norm": 2.8025119304656982,
      "learning_rate": 4.5643153526970956e-07,
      "loss": 2.7535,
      "step": 36
    },
    {
      "epoch": 0.04604853764779091,
      "grad_norm": 2.967703342437744,
      "learning_rate": 4.771784232365145e-07,
      "loss": 2.7615,
      "step": 37
    },
    {
      "epoch": 0.04729309271935283,
      "grad_norm": 2.9308114051818848,
      "learning_rate": 4.979253112033195e-07,
      "loss": 2.7115,
      "step": 38
    },
    {
      "epoch": 0.04853764779091475,
      "grad_norm": 2.9203720092773438,
      "learning_rate": 5.186721991701245e-07,
      "loss": 2.701,
      "step": 39
    },
    {
      "epoch": 0.049782202862476664,
      "grad_norm": 2.8226709365844727,
      "learning_rate": 5.394190871369295e-07,
      "loss": 2.6267,
      "step": 40
    },
    {
      "epoch": 0.049782202862476664,
      "eval_loss": 2.6964941024780273,
      "eval_runtime": 46.5181,
      "eval_samples_per_second": 21.497,
      "eval_steps_per_second": 0.903,
      "step": 40
    },
    {
      "epoch": 0.05102675793403858,
      "grad_norm": 2.7212748527526855,
      "learning_rate": 5.601659751037345e-07,
      "loss": 2.6505,
      "step": 41
    },
    {
      "epoch": 0.0522713130056005,
      "grad_norm": 2.658881425857544,
      "learning_rate": 5.809128630705395e-07,
      "loss": 2.6655,
      "step": 42
    },
    {
      "epoch": 0.053515868077162417,
      "grad_norm": 2.4534730911254883,
      "learning_rate": 6.016597510373444e-07,
      "loss": 2.7098,
      "step": 43
    },
    {
      "epoch": 0.054760423148724334,
      "grad_norm": 2.4222075939178467,
      "learning_rate": 6.224066390041494e-07,
      "loss": 2.6793,
      "step": 44
    },
    {
      "epoch": 0.056004978220286245,
      "grad_norm": 2.5824973583221436,
      "learning_rate": 6.431535269709543e-07,
      "loss": 2.6212,
      "step": 45
    },
    {
      "epoch": 0.05724953329184816,
      "grad_norm": 2.5982468128204346,
      "learning_rate": 6.639004149377594e-07,
      "loss": 2.5901,
      "step": 46
    },
    {
      "epoch": 0.05849408836341008,
      "grad_norm": 2.213388442993164,
      "learning_rate": 6.846473029045644e-07,
      "loss": 2.6156,
      "step": 47
    },
    {
      "epoch": 0.059738643434972,
      "grad_norm": 2.097372531890869,
      "learning_rate": 7.053941908713693e-07,
      "loss": 2.6154,
      "step": 48
    },
    {
      "epoch": 0.060983198506533914,
      "grad_norm": 1.9788408279418945,
      "learning_rate": 7.261410788381744e-07,
      "loss": 2.5516,
      "step": 49
    },
    {
      "epoch": 0.06222775357809583,
      "grad_norm": 2.052147150039673,
      "learning_rate": 7.468879668049793e-07,
      "loss": 2.6128,
      "step": 50
    },
    {
      "epoch": 0.06222775357809583,
      "eval_loss": 2.6048905849456787,
      "eval_runtime": 51.2137,
      "eval_samples_per_second": 19.526,
      "eval_steps_per_second": 0.82,
      "step": 50
    },
    {
      "epoch": 0.06347230864965775,
      "grad_norm": 1.8841335773468018,
      "learning_rate": 7.676348547717843e-07,
      "loss": 2.5617,
      "step": 51
    },
    {
      "epoch": 0.06471686372121967,
      "grad_norm": 2.0841684341430664,
      "learning_rate": 7.883817427385892e-07,
      "loss": 2.5627,
      "step": 52
    },
    {
      "epoch": 0.06596141879278158,
      "grad_norm": 1.8119730949401855,
      "learning_rate": 8.091286307053943e-07,
      "loss": 2.5572,
      "step": 53
    },
    {
      "epoch": 0.0672059738643435,
      "grad_norm": 1.7168290615081787,
      "learning_rate": 8.298755186721992e-07,
      "loss": 2.5465,
      "step": 54
    },
    {
      "epoch": 0.06845052893590542,
      "grad_norm": 1.7731754779815674,
      "learning_rate": 8.506224066390042e-07,
      "loss": 2.543,
      "step": 55
    },
    {
      "epoch": 0.06969508400746734,
      "grad_norm": 1.9654561281204224,
      "learning_rate": 8.713692946058091e-07,
      "loss": 2.5547,
      "step": 56
    },
    {
      "epoch": 0.07093963907902924,
      "grad_norm": 1.8032375574111938,
      "learning_rate": 8.921161825726142e-07,
      "loss": 2.5319,
      "step": 57
    },
    {
      "epoch": 0.07218419415059116,
      "grad_norm": 1.8775644302368164,
      "learning_rate": 9.128630705394191e-07,
      "loss": 2.5533,
      "step": 58
    },
    {
      "epoch": 0.07342874922215308,
      "grad_norm": 1.6019998788833618,
      "learning_rate": 9.336099585062241e-07,
      "loss": 2.5402,
      "step": 59
    },
    {
      "epoch": 0.07467330429371499,
      "grad_norm": 1.7785435914993286,
      "learning_rate": 9.54356846473029e-07,
      "loss": 2.4704,
      "step": 60
    },
    {
      "epoch": 0.07467330429371499,
      "eval_loss": 2.541548252105713,
      "eval_runtime": 51.1601,
      "eval_samples_per_second": 19.546,
      "eval_steps_per_second": 0.821,
      "step": 60
    },
    {
      "epoch": 0.07591785936527691,
      "grad_norm": 1.5377200841903687,
      "learning_rate": 9.751037344398341e-07,
      "loss": 2.5028,
      "step": 61
    },
    {
      "epoch": 0.07716241443683883,
      "grad_norm": 1.7212916612625122,
      "learning_rate": 9.95850622406639e-07,
      "loss": 2.4621,
      "step": 62
    },
    {
      "epoch": 0.07840696950840075,
      "grad_norm": 1.632606029510498,
      "learning_rate": 1.0165975103734441e-06,
      "loss": 2.4868,
      "step": 63
    },
    {
      "epoch": 0.07965152457996266,
      "grad_norm": 1.8643872737884521,
      "learning_rate": 1.037344398340249e-06,
      "loss": 2.4582,
      "step": 64
    },
    {
      "epoch": 0.08089607965152458,
      "grad_norm": 1.8329377174377441,
      "learning_rate": 1.058091286307054e-06,
      "loss": 2.464,
      "step": 65
    },
    {
      "epoch": 0.0821406347230865,
      "grad_norm": 1.9488356113433838,
      "learning_rate": 1.078838174273859e-06,
      "loss": 2.4275,
      "step": 66
    },
    {
      "epoch": 0.08338518979464841,
      "grad_norm": 1.7663215398788452,
      "learning_rate": 1.099585062240664e-06,
      "loss": 2.516,
      "step": 67
    },
    {
      "epoch": 0.08462974486621033,
      "grad_norm": 1.7675347328186035,
      "learning_rate": 1.120331950207469e-06,
      "loss": 2.4535,
      "step": 68
    },
    {
      "epoch": 0.08587429993777225,
      "grad_norm": 1.7481404542922974,
      "learning_rate": 1.141078838174274e-06,
      "loss": 2.4089,
      "step": 69
    },
    {
      "epoch": 0.08711885500933417,
      "grad_norm": 1.7963330745697021,
      "learning_rate": 1.161825726141079e-06,
      "loss": 2.4408,
      "step": 70
    },
    {
      "epoch": 0.08711885500933417,
      "eval_loss": 2.466163396835327,
      "eval_runtime": 50.4204,
      "eval_samples_per_second": 19.833,
      "eval_steps_per_second": 0.833,
      "step": 70
    },
    {
      "epoch": 0.08836341008089608,
      "grad_norm": 2.053469657897949,
      "learning_rate": 1.182572614107884e-06,
      "loss": 2.408,
      "step": 71
    },
    {
      "epoch": 0.089607965152458,
      "grad_norm": 1.900294303894043,
      "learning_rate": 1.2033195020746888e-06,
      "loss": 2.4066,
      "step": 72
    },
    {
      "epoch": 0.09085252022401992,
      "grad_norm": 2.38637113571167,
      "learning_rate": 1.224066390041494e-06,
      "loss": 2.3548,
      "step": 73
    },
    {
      "epoch": 0.09209707529558182,
      "grad_norm": 1.8274579048156738,
      "learning_rate": 1.2448132780082988e-06,
      "loss": 2.3844,
      "step": 74
    },
    {
      "epoch": 0.09334163036714374,
      "grad_norm": 1.9040184020996094,
      "learning_rate": 1.2655601659751037e-06,
      "loss": 2.4406,
      "step": 75
    },
    {
      "epoch": 0.09458618543870566,
      "grad_norm": 2.0351619720458984,
      "learning_rate": 1.2863070539419086e-06,
      "loss": 2.3624,
      "step": 76
    },
    {
      "epoch": 0.09583074051026758,
      "grad_norm": 1.989876627922058,
      "learning_rate": 1.307053941908714e-06,
      "loss": 2.4097,
      "step": 77
    },
    {
      "epoch": 0.0970752955818295,
      "grad_norm": 1.8507741689682007,
      "learning_rate": 1.3278008298755188e-06,
      "loss": 2.4482,
      "step": 78
    },
    {
      "epoch": 0.09831985065339141,
      "grad_norm": 2.6118454933166504,
      "learning_rate": 1.3485477178423237e-06,
      "loss": 2.3178,
      "step": 79
    },
    {
      "epoch": 0.09956440572495333,
      "grad_norm": 1.9467326402664185,
      "learning_rate": 1.3692946058091288e-06,
      "loss": 2.3175,
      "step": 80
    },
    {
      "epoch": 0.09956440572495333,
      "eval_loss": 2.3719911575317383,
      "eval_runtime": 52.3293,
      "eval_samples_per_second": 19.11,
      "eval_steps_per_second": 0.803,
      "step": 80
    },
    {
      "epoch": 0.10080896079651525,
      "grad_norm": 2.4913370609283447,
      "learning_rate": 1.3900414937759337e-06,
      "loss": 2.3063,
      "step": 81
    },
    {
      "epoch": 0.10205351586807716,
      "grad_norm": 2.4838919639587402,
      "learning_rate": 1.4107883817427386e-06,
      "loss": 2.3534,
      "step": 82
    },
    {
      "epoch": 0.10329807093963908,
      "grad_norm": 2.798588991165161,
      "learning_rate": 1.4315352697095435e-06,
      "loss": 2.2732,
      "step": 83
    },
    {
      "epoch": 0.104542626011201,
      "grad_norm": 2.688399076461792,
      "learning_rate": 1.4522821576763488e-06,
      "loss": 2.3112,
      "step": 84
    },
    {
      "epoch": 0.10578718108276292,
      "grad_norm": 2.7367143630981445,
      "learning_rate": 1.4730290456431537e-06,
      "loss": 2.3055,
      "step": 85
    },
    {
      "epoch": 0.10703173615432483,
      "grad_norm": 2.6406664848327637,
      "learning_rate": 1.4937759336099586e-06,
      "loss": 2.312,
      "step": 86
    },
    {
      "epoch": 0.10827629122588675,
      "grad_norm": 2.703355312347412,
      "learning_rate": 1.5145228215767635e-06,
      "loss": 2.3305,
      "step": 87
    },
    {
      "epoch": 0.10952084629744867,
      "grad_norm": 2.420084238052368,
      "learning_rate": 1.5352697095435686e-06,
      "loss": 2.2608,
      "step": 88
    },
    {
      "epoch": 0.11076540136901059,
      "grad_norm": 2.999835729598999,
      "learning_rate": 1.5560165975103735e-06,
      "loss": 2.2389,
      "step": 89
    },
    {
      "epoch": 0.11200995644057249,
      "grad_norm": 2.35611629486084,
      "learning_rate": 1.5767634854771784e-06,
      "loss": 2.2671,
      "step": 90
    },
    {
      "epoch": 0.11200995644057249,
      "eval_loss": 2.2900290489196777,
      "eval_runtime": 52.1871,
      "eval_samples_per_second": 19.162,
      "eval_steps_per_second": 0.805,
      "step": 90
    },
    {
      "epoch": 0.1132545115121344,
      "grad_norm": 2.2686431407928467,
      "learning_rate": 1.5975103734439833e-06,
      "loss": 2.2405,
      "step": 91
    },
    {
      "epoch": 0.11449906658369632,
      "grad_norm": 2.883517265319824,
      "learning_rate": 1.6182572614107886e-06,
      "loss": 2.2364,
      "step": 92
    },
    {
      "epoch": 0.11574362165525824,
      "grad_norm": 2.4562909603118896,
      "learning_rate": 1.6390041493775935e-06,
      "loss": 2.2308,
      "step": 93
    },
    {
      "epoch": 0.11698817672682016,
      "grad_norm": 2.7968456745147705,
      "learning_rate": 1.6597510373443984e-06,
      "loss": 2.1959,
      "step": 94
    },
    {
      "epoch": 0.11823273179838208,
      "grad_norm": 2.8692259788513184,
      "learning_rate": 1.6804979253112035e-06,
      "loss": 2.215,
      "step": 95
    },
    {
      "epoch": 0.119477286869944,
      "grad_norm": 2.8436100482940674,
      "learning_rate": 1.7012448132780084e-06,
      "loss": 2.1816,
      "step": 96
    },
    {
      "epoch": 0.12072184194150591,
      "grad_norm": 2.4477386474609375,
      "learning_rate": 1.7219917012448133e-06,
      "loss": 2.1684,
      "step": 97
    },
    {
      "epoch": 0.12196639701306783,
      "grad_norm": 2.610046863555908,
      "learning_rate": 1.7427385892116182e-06,
      "loss": 2.1656,
      "step": 98
    },
    {
      "epoch": 0.12321095208462975,
      "grad_norm": 2.698709487915039,
      "learning_rate": 1.7634854771784235e-06,
      "loss": 2.2115,
      "step": 99
    },
    {
      "epoch": 0.12445550715619166,
      "grad_norm": 2.476600408554077,
      "learning_rate": 1.7842323651452284e-06,
      "loss": 2.1619,
      "step": 100
    },
    {
      "epoch": 0.12445550715619166,
      "eval_loss": 2.221313953399658,
      "eval_runtime": 51.6214,
      "eval_samples_per_second": 19.372,
      "eval_steps_per_second": 0.814,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 2409,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.11730940936192e+16,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}