{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.19398642095053345,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019398642095053346,
      "grad_norm": 5.092199802398682,
      "learning_rate": 1e-05,
      "loss": 4.7383,
      "step": 1
    },
    {
      "epoch": 0.0019398642095053346,
      "eval_loss": 4.821082592010498,
      "eval_runtime": 9.658,
      "eval_samples_per_second": 44.937,
      "eval_steps_per_second": 5.695,
      "step": 1
    },
    {
      "epoch": 0.0038797284190106693,
      "grad_norm": 4.449008464813232,
      "learning_rate": 2e-05,
      "loss": 4.6036,
      "step": 2
    },
    {
      "epoch": 0.005819592628516004,
      "grad_norm": 4.542291164398193,
      "learning_rate": 3e-05,
      "loss": 4.7654,
      "step": 3
    },
    {
      "epoch": 0.007759456838021339,
      "grad_norm": 4.831502437591553,
      "learning_rate": 4e-05,
      "loss": 4.6307,
      "step": 4
    },
    {
      "epoch": 0.009699321047526674,
      "grad_norm": 4.798445224761963,
      "learning_rate": 5e-05,
      "loss": 4.689,
      "step": 5
    },
    {
      "epoch": 0.011639185257032008,
      "grad_norm": 4.600784778594971,
      "learning_rate": 6e-05,
      "loss": 4.4962,
      "step": 6
    },
    {
      "epoch": 0.013579049466537343,
      "grad_norm": 4.6975178718566895,
      "learning_rate": 7e-05,
      "loss": 4.6526,
      "step": 7
    },
    {
      "epoch": 0.015518913676042677,
      "grad_norm": 4.297379970550537,
      "learning_rate": 8e-05,
      "loss": 4.4603,
      "step": 8
    },
    {
      "epoch": 0.01745877788554801,
      "grad_norm": 4.602691650390625,
      "learning_rate": 9e-05,
      "loss": 4.0801,
      "step": 9
    },
    {
      "epoch": 0.01745877788554801,
      "eval_loss": 3.935520887374878,
      "eval_runtime": 7.7589,
      "eval_samples_per_second": 55.935,
      "eval_steps_per_second": 7.089,
      "step": 9
    },
    {
      "epoch": 0.019398642095053348,
      "grad_norm": 3.76698899269104,
      "learning_rate": 0.0001,
      "loss": 3.9645,
      "step": 10
    },
    {
      "epoch": 0.02133850630455868,
      "grad_norm": 3.087214708328247,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.9473,
      "step": 11
    },
    {
      "epoch": 0.023278370514064017,
      "grad_norm": 3.322976589202881,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.652,
      "step": 12
    },
    {
      "epoch": 0.02521823472356935,
      "grad_norm": 3.5539023876190186,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.3627,
      "step": 13
    },
    {
      "epoch": 0.027158098933074686,
      "grad_norm": 3.190157413482666,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.1173,
      "step": 14
    },
    {
      "epoch": 0.029097963142580018,
      "grad_norm": 3.779177188873291,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.8321,
      "step": 15
    },
    {
      "epoch": 0.031037827352085354,
      "grad_norm": 3.7224929332733154,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.504,
      "step": 16
    },
    {
      "epoch": 0.03297769156159069,
      "grad_norm": 3.4633424282073975,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.2944,
      "step": 17
    },
    {
      "epoch": 0.03491755577109602,
      "grad_norm": 2.928765296936035,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.2625,
      "step": 18
    },
    {
      "epoch": 0.03491755577109602,
      "eval_loss": 2.196943759918213,
      "eval_runtime": 7.7522,
      "eval_samples_per_second": 55.984,
      "eval_steps_per_second": 7.095,
      "step": 18
    },
    {
      "epoch": 0.03685741998060136,
      "grad_norm": 3.9546890258789062,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.3878,
      "step": 19
    },
    {
      "epoch": 0.038797284190106696,
      "grad_norm": 4.105186462402344,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.1788,
      "step": 20
    },
    {
      "epoch": 0.040737148399612025,
      "grad_norm": 3.8948333263397217,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.8275,
      "step": 21
    },
    {
      "epoch": 0.04267701260911736,
      "grad_norm": 3.057760238647461,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.621,
      "step": 22
    },
    {
      "epoch": 0.0446168768186227,
      "grad_norm": 2.3399696350097656,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.655,
      "step": 23
    },
    {
      "epoch": 0.04655674102812803,
      "grad_norm": 2.517136335372925,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.7654,
      "step": 24
    },
    {
      "epoch": 0.04849660523763336,
      "grad_norm": 2.6656148433685303,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.7639,
      "step": 25
    },
    {
      "epoch": 0.0504364694471387,
      "grad_norm": 3.310025930404663,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.3531,
      "step": 26
    },
    {
      "epoch": 0.052376333656644035,
      "grad_norm": 2.69954776763916,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.1658,
      "step": 27
    },
    {
      "epoch": 0.052376333656644035,
      "eval_loss": 1.3316627740859985,
      "eval_runtime": 7.7784,
      "eval_samples_per_second": 55.796,
      "eval_steps_per_second": 7.071,
      "step": 27
    },
    {
      "epoch": 0.05431619786614937,
      "grad_norm": 2.0734622478485107,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3399,
      "step": 28
    },
    {
      "epoch": 0.05625606207565471,
      "grad_norm": 2.7428479194641113,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.4039,
      "step": 29
    },
    {
      "epoch": 0.058195926285160036,
      "grad_norm": 1.9327542781829834,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.9577,
      "step": 30
    },
    {
      "epoch": 0.06013579049466537,
      "grad_norm": 2.079310417175293,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.9913,
      "step": 31
    },
    {
      "epoch": 0.06207565470417071,
      "grad_norm": 2.0377795696258545,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.9515,
      "step": 32
    },
    {
      "epoch": 0.06401551891367604,
      "grad_norm": 1.990349292755127,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.1051,
      "step": 33
    },
    {
      "epoch": 0.06595538312318137,
      "grad_norm": 2.111757755279541,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.0754,
      "step": 34
    },
    {
      "epoch": 0.06789524733268672,
      "grad_norm": 2.61749005317688,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.0685,
      "step": 35
    },
    {
      "epoch": 0.06983511154219205,
      "grad_norm": 1.9351005554199219,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.8439,
      "step": 36
    },
    {
      "epoch": 0.06983511154219205,
      "eval_loss": 0.8821842670440674,
      "eval_runtime": 7.7414,
      "eval_samples_per_second": 56.063,
      "eval_steps_per_second": 7.105,
      "step": 36
    },
    {
      "epoch": 0.07177497575169738,
      "grad_norm": 1.9722400903701782,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.9561,
      "step": 37
    },
    {
      "epoch": 0.07371483996120272,
      "grad_norm": 2.1616642475128174,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.0384,
      "step": 38
    },
    {
      "epoch": 0.07565470417070805,
      "grad_norm": 1.5446350574493408,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.7242,
      "step": 39
    },
    {
      "epoch": 0.07759456838021339,
      "grad_norm": 1.5929559469223022,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.843,
      "step": 40
    },
    {
      "epoch": 0.07953443258971872,
      "grad_norm": 1.5796291828155518,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.8905,
      "step": 41
    },
    {
      "epoch": 0.08147429679922405,
      "grad_norm": 1.9490644931793213,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.7645,
      "step": 42
    },
    {
      "epoch": 0.08341416100872939,
      "grad_norm": 1.8810855150222778,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.7698,
      "step": 43
    },
    {
      "epoch": 0.08535402521823472,
      "grad_norm": 2.4278464317321777,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.795,
      "step": 44
    },
    {
      "epoch": 0.08729388942774007,
      "grad_norm": 1.4299455881118774,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.5331,
      "step": 45
    },
    {
      "epoch": 0.08729388942774007,
      "eval_loss": 0.6151111721992493,
      "eval_runtime": 7.7408,
      "eval_samples_per_second": 56.067,
      "eval_steps_per_second": 7.105,
      "step": 45
    },
    {
      "epoch": 0.0892337536372454,
      "grad_norm": 1.8526909351348877,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7683,
      "step": 46
    },
    {
      "epoch": 0.09117361784675072,
      "grad_norm": 1.4803686141967773,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.5607,
      "step": 47
    },
    {
      "epoch": 0.09311348205625607,
      "grad_norm": 1.5188422203063965,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.4849,
      "step": 48
    },
    {
      "epoch": 0.0950533462657614,
      "grad_norm": 1.1162447929382324,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.4439,
      "step": 49
    },
    {
      "epoch": 0.09699321047526673,
      "grad_norm": 1.8776347637176514,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.575,
      "step": 50
    },
    {
      "epoch": 0.09893307468477207,
      "grad_norm": 1.4063315391540527,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.5396,
      "step": 51
    },
    {
      "epoch": 0.1008729388942774,
      "grad_norm": 1.2367199659347534,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.4351,
      "step": 52
    },
    {
      "epoch": 0.10281280310378274,
      "grad_norm": 1.320259928703308,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.4758,
      "step": 53
    },
    {
      "epoch": 0.10475266731328807,
      "grad_norm": 1.6481106281280518,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.5796,
      "step": 54
    },
    {
      "epoch": 0.10475266731328807,
      "eval_loss": 0.4402259886264801,
      "eval_runtime": 7.7586,
      "eval_samples_per_second": 55.938,
      "eval_steps_per_second": 7.089,
      "step": 54
    },
    {
      "epoch": 0.1066925315227934,
      "grad_norm": 1.4706881046295166,
      "learning_rate": 5e-05,
      "loss": 0.5325,
      "step": 55
    },
    {
      "epoch": 0.10863239573229874,
      "grad_norm": 1.681864619255066,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.5644,
      "step": 56
    },
    {
      "epoch": 0.11057225994180407,
      "grad_norm": 1.4026848077774048,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.3279,
      "step": 57
    },
    {
      "epoch": 0.11251212415130941,
      "grad_norm": 1.2170274257659912,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.3805,
      "step": 58
    },
    {
      "epoch": 0.11445198836081474,
      "grad_norm": 1.9468257427215576,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.5186,
      "step": 59
    },
    {
      "epoch": 0.11639185257032007,
      "grad_norm": 1.2916088104248047,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2757,
      "step": 60
    },
    {
      "epoch": 0.11833171677982542,
      "grad_norm": 1.548339605331421,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.3923,
      "step": 61
    },
    {
      "epoch": 0.12027158098933075,
      "grad_norm": 2.265233039855957,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.6105,
      "step": 62
    },
    {
      "epoch": 0.12221144519883609,
      "grad_norm": 1.4970910549163818,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.4189,
      "step": 63
    },
    {
      "epoch": 0.12221144519883609,
      "eval_loss": 0.3442797064781189,
      "eval_runtime": 7.745,
      "eval_samples_per_second": 56.036,
      "eval_steps_per_second": 7.101,
      "step": 63
    },
    {
      "epoch": 0.12415130940834142,
      "grad_norm": 1.1539958715438843,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2965,
      "step": 64
    },
    {
      "epoch": 0.12609117361784675,
      "grad_norm": 1.2717357873916626,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.3565,
      "step": 65
    },
    {
      "epoch": 0.1280310378273521,
      "grad_norm": 1.1463826894760132,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.3243,
      "step": 66
    },
    {
      "epoch": 0.12997090203685743,
      "grad_norm": 2.083845615386963,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.4723,
      "step": 67
    },
    {
      "epoch": 0.13191076624636275,
      "grad_norm": 1.220322608947754,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.3566,
      "step": 68
    },
    {
      "epoch": 0.1338506304558681,
      "grad_norm": 1.4377970695495605,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.384,
      "step": 69
    },
    {
      "epoch": 0.13579049466537343,
      "grad_norm": 1.6574350595474243,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.3038,
      "step": 70
    },
    {
      "epoch": 0.13773035887487875,
      "grad_norm": 1.2186497449874878,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.2762,
      "step": 71
    },
    {
      "epoch": 0.1396702230843841,
      "grad_norm": 1.6001431941986084,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.25,
      "step": 72
    },
    {
      "epoch": 0.1396702230843841,
      "eval_loss": 0.3006916642189026,
      "eval_runtime": 7.7498,
      "eval_samples_per_second": 56.001,
      "eval_steps_per_second": 7.097,
      "step": 72
    },
    {
      "epoch": 0.14161008729388944,
      "grad_norm": 1.6216119527816772,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.391,
      "step": 73
    },
    {
      "epoch": 0.14354995150339475,
      "grad_norm": 2.5727713108062744,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.5055,
      "step": 74
    },
    {
      "epoch": 0.1454898157129001,
      "grad_norm": 1.4488884210586548,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.3118,
      "step": 75
    },
    {
      "epoch": 0.14742967992240544,
      "grad_norm": 1.5707823038101196,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.329,
      "step": 76
    },
    {
      "epoch": 0.14936954413191075,
      "grad_norm": 0.8776403069496155,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.2757,
      "step": 77
    },
    {
      "epoch": 0.1513094083414161,
      "grad_norm": 1.9407877922058105,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.348,
      "step": 78
    },
    {
      "epoch": 0.15324927255092144,
      "grad_norm": 1.6693557500839233,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.3072,
      "step": 79
    },
    {
      "epoch": 0.15518913676042678,
      "grad_norm": 0.9786368608474731,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.2356,
      "step": 80
    },
    {
      "epoch": 0.1571290009699321,
      "grad_norm": 1.0574125051498413,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.1978,
      "step": 81
    },
    {
      "epoch": 0.1571290009699321,
      "eval_loss": 0.2722632586956024,
      "eval_runtime": 7.7369,
      "eval_samples_per_second": 56.095,
      "eval_steps_per_second": 7.109,
      "step": 81
    },
    {
      "epoch": 0.15906886517943744,
      "grad_norm": 1.628749966621399,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2687,
      "step": 82
    },
    {
      "epoch": 0.16100872938894278,
      "grad_norm": 1.5231091976165771,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.307,
      "step": 83
    },
    {
      "epoch": 0.1629485935984481,
      "grad_norm": 0.9854992032051086,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.183,
      "step": 84
    },
    {
      "epoch": 0.16488845780795344,
      "grad_norm": 1.5809539556503296,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2977,
      "step": 85
    },
    {
      "epoch": 0.16682832201745879,
      "grad_norm": 1.4216303825378418,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.275,
      "step": 86
    },
    {
      "epoch": 0.1687681862269641,
      "grad_norm": 1.5944830179214478,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.296,
      "step": 87
    },
    {
      "epoch": 0.17070805043646944,
      "grad_norm": 1.6960701942443848,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.3684,
      "step": 88
    },
    {
      "epoch": 0.1726479146459748,
      "grad_norm": 1.3024052381515503,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.304,
      "step": 89
    },
    {
      "epoch": 0.17458777885548013,
      "grad_norm": 1.6905990839004517,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.3042,
      "step": 90
    },
    {
      "epoch": 0.17458777885548013,
      "eval_loss": 0.26292115449905396,
      "eval_runtime": 7.7439,
      "eval_samples_per_second": 56.044,
      "eval_steps_per_second": 7.102,
      "step": 90
    },
    {
      "epoch": 0.17652764306498545,
      "grad_norm": 1.0282114744186401,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.227,
      "step": 91
    },
    {
      "epoch": 0.1784675072744908,
      "grad_norm": 1.2541886568069458,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.2273,
      "step": 92
    },
    {
      "epoch": 0.18040737148399613,
      "grad_norm": 1.7235442399978638,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.3701,
      "step": 93
    },
    {
      "epoch": 0.18234723569350145,
      "grad_norm": 1.2627227306365967,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.3245,
      "step": 94
    },
    {
      "epoch": 0.1842870999030068,
      "grad_norm": 1.996457815170288,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.3793,
      "step": 95
    },
    {
      "epoch": 0.18622696411251213,
      "grad_norm": 1.1682064533233643,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2895,
      "step": 96
    },
    {
      "epoch": 0.18816682832201745,
      "grad_norm": 0.9628655910491943,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.2685,
      "step": 97
    },
    {
      "epoch": 0.1901066925315228,
      "grad_norm": 1.4077612161636353,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.2579,
      "step": 98
    },
    {
      "epoch": 0.19204655674102813,
      "grad_norm": 1.1800073385238647,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.2709,
      "step": 99
    },
    {
      "epoch": 0.19204655674102813,
      "eval_loss": 0.26203885674476624,
      "eval_runtime": 7.7497,
      "eval_samples_per_second": 56.002,
      "eval_steps_per_second": 7.097,
      "step": 99
    },
    {
      "epoch": 0.19398642095053345,
      "grad_norm": 1.5470740795135498,
      "learning_rate": 0.0,
      "loss": 0.2969,
      "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": 2596262859767808.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}