{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2628120893561104,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002628120893561104,
      "grad_norm": 5.410415172576904,
      "learning_rate": 1e-05,
      "loss": 7.6058,
      "step": 1
    },
    {
      "epoch": 0.002628120893561104,
      "eval_loss": 7.706796169281006,
      "eval_runtime": 7.8198,
      "eval_samples_per_second": 41.05,
      "eval_steps_per_second": 5.243,
      "step": 1
    },
    {
      "epoch": 0.005256241787122208,
      "grad_norm": 4.60823392868042,
      "learning_rate": 2e-05,
      "loss": 7.7311,
      "step": 2
    },
    {
      "epoch": 0.00788436268068331,
      "grad_norm": 4.575686931610107,
      "learning_rate": 3e-05,
      "loss": 7.018,
      "step": 3
    },
    {
      "epoch": 0.010512483574244415,
      "grad_norm": 5.470172882080078,
      "learning_rate": 4e-05,
      "loss": 8.0201,
      "step": 4
    },
    {
      "epoch": 0.013140604467805518,
      "grad_norm": 4.377795696258545,
      "learning_rate": 5e-05,
      "loss": 7.1738,
      "step": 5
    },
    {
      "epoch": 0.01576872536136662,
      "grad_norm": 5.3419294357299805,
      "learning_rate": 6e-05,
      "loss": 7.993,
      "step": 6
    },
    {
      "epoch": 0.018396846254927726,
      "grad_norm": 4.29301643371582,
      "learning_rate": 7e-05,
      "loss": 7.4565,
      "step": 7
    },
    {
      "epoch": 0.02102496714848883,
      "grad_norm": 3.220489978790283,
      "learning_rate": 8e-05,
      "loss": 7.9336,
      "step": 8
    },
    {
      "epoch": 0.023653088042049936,
      "grad_norm": 5.817854881286621,
      "learning_rate": 9e-05,
      "loss": 7.7279,
      "step": 9
    },
    {
      "epoch": 0.023653088042049936,
      "eval_loss": 7.636051654815674,
      "eval_runtime": 7.8181,
      "eval_samples_per_second": 41.059,
      "eval_steps_per_second": 5.244,
      "step": 9
    },
    {
      "epoch": 0.026281208935611037,
      "grad_norm": 3.344338893890381,
      "learning_rate": 0.0001,
      "loss": 7.4586,
      "step": 10
    },
    {
      "epoch": 0.02890932982917214,
      "grad_norm": 2.984314203262329,
      "learning_rate": 9.99695413509548e-05,
      "loss": 7.282,
      "step": 11
    },
    {
      "epoch": 0.03153745072273324,
      "grad_norm": 5.008783340454102,
      "learning_rate": 9.987820251299122e-05,
      "loss": 7.2996,
      "step": 12
    },
    {
      "epoch": 0.03416557161629435,
      "grad_norm": 5.446415901184082,
      "learning_rate": 9.972609476841367e-05,
      "loss": 7.7632,
      "step": 13
    },
    {
      "epoch": 0.03679369250985545,
      "grad_norm": 2.8699066638946533,
      "learning_rate": 9.951340343707852e-05,
      "loss": 7.6905,
      "step": 14
    },
    {
      "epoch": 0.03942181340341656,
      "grad_norm": 4.882473945617676,
      "learning_rate": 9.924038765061042e-05,
      "loss": 7.9727,
      "step": 15
    },
    {
      "epoch": 0.04204993429697766,
      "grad_norm": 3.1733548641204834,
      "learning_rate": 9.890738003669029e-05,
      "loss": 6.9207,
      "step": 16
    },
    {
      "epoch": 0.04467805519053877,
      "grad_norm": 4.807592868804932,
      "learning_rate": 9.851478631379982e-05,
      "loss": 7.7807,
      "step": 17
    },
    {
      "epoch": 0.04730617608409987,
      "grad_norm": 4.676242351531982,
      "learning_rate": 9.806308479691595e-05,
      "loss": 7.8454,
      "step": 18
    },
    {
      "epoch": 0.04730617608409987,
      "eval_loss": 7.441324234008789,
      "eval_runtime": 7.8231,
      "eval_samples_per_second": 41.032,
      "eval_steps_per_second": 5.241,
      "step": 18
    },
    {
      "epoch": 0.04993429697766097,
      "grad_norm": 4.598595142364502,
      "learning_rate": 9.755282581475769e-05,
      "loss": 7.7069,
      "step": 19
    },
    {
      "epoch": 0.052562417871222074,
      "grad_norm": 4.850493907928467,
      "learning_rate": 9.698463103929542e-05,
      "loss": 7.5851,
      "step": 20
    },
    {
      "epoch": 0.05519053876478318,
      "grad_norm": 3.774733781814575,
      "learning_rate": 9.635919272833938e-05,
      "loss": 7.1,
      "step": 21
    },
    {
      "epoch": 0.05781865965834428,
      "grad_norm": 3.955918550491333,
      "learning_rate": 9.567727288213005e-05,
      "loss": 7.3246,
      "step": 22
    },
    {
      "epoch": 0.06044678055190539,
      "grad_norm": 3.4571104049682617,
      "learning_rate": 9.493970231495835e-05,
      "loss": 6.9312,
      "step": 23
    },
    {
      "epoch": 0.06307490144546649,
      "grad_norm": 3.994743585586548,
      "learning_rate": 9.414737964294636e-05,
      "loss": 7.5883,
      "step": 24
    },
    {
      "epoch": 0.0657030223390276,
      "grad_norm": 3.493082284927368,
      "learning_rate": 9.330127018922194e-05,
      "loss": 7.5821,
      "step": 25
    },
    {
      "epoch": 0.0683311432325887,
      "grad_norm": 4.332574844360352,
      "learning_rate": 9.24024048078213e-05,
      "loss": 7.2888,
      "step": 26
    },
    {
      "epoch": 0.07095926412614981,
      "grad_norm": 4.837662696838379,
      "learning_rate": 9.145187862775209e-05,
      "loss": 6.845,
      "step": 27
    },
    {
      "epoch": 0.07095926412614981,
      "eval_loss": 7.245150089263916,
      "eval_runtime": 7.8267,
      "eval_samples_per_second": 41.013,
      "eval_steps_per_second": 5.238,
      "step": 27
    },
    {
      "epoch": 0.0735873850197109,
      "grad_norm": 4.511839866638184,
      "learning_rate": 9.045084971874738e-05,
      "loss": 7.7317,
      "step": 28
    },
    {
      "epoch": 0.07621550591327202,
      "grad_norm": 3.5038013458251953,
      "learning_rate": 8.940053768033609e-05,
      "loss": 7.1144,
      "step": 29
    },
    {
      "epoch": 0.07884362680683311,
      "grad_norm": 3.6477413177490234,
      "learning_rate": 8.83022221559489e-05,
      "loss": 6.769,
      "step": 30
    },
    {
      "epoch": 0.08147174770039421,
      "grad_norm": 3.408693790435791,
      "learning_rate": 8.715724127386972e-05,
      "loss": 6.6021,
      "step": 31
    },
    {
      "epoch": 0.08409986859395532,
      "grad_norm": 4.711971282958984,
      "learning_rate": 8.596699001693255e-05,
      "loss": 7.4735,
      "step": 32
    },
    {
      "epoch": 0.08672798948751642,
      "grad_norm": 5.069206237792969,
      "learning_rate": 8.473291852294987e-05,
      "loss": 7.4584,
      "step": 33
    },
    {
      "epoch": 0.08935611038107753,
      "grad_norm": 4.098939418792725,
      "learning_rate": 8.345653031794292e-05,
      "loss": 7.27,
      "step": 34
    },
    {
      "epoch": 0.09198423127463863,
      "grad_norm": 3.993582010269165,
      "learning_rate": 8.213938048432697e-05,
      "loss": 6.6474,
      "step": 35
    },
    {
      "epoch": 0.09461235216819974,
      "grad_norm": 4.524712562561035,
      "learning_rate": 8.07830737662829e-05,
      "loss": 7.0525,
      "step": 36
    },
    {
      "epoch": 0.09461235216819974,
      "eval_loss": 7.079109191894531,
      "eval_runtime": 7.8096,
      "eval_samples_per_second": 41.103,
      "eval_steps_per_second": 5.25,
      "step": 36
    },
    {
      "epoch": 0.09724047306176084,
      "grad_norm": 3.9363136291503906,
      "learning_rate": 7.938926261462366e-05,
      "loss": 7.2766,
      "step": 37
    },
    {
      "epoch": 0.09986859395532194,
      "grad_norm": 3.650977849960327,
      "learning_rate": 7.795964517353735e-05,
      "loss": 6.9182,
      "step": 38
    },
    {
      "epoch": 0.10249671484888305,
      "grad_norm": 3.0577781200408936,
      "learning_rate": 7.649596321166024e-05,
      "loss": 6.5284,
      "step": 39
    },
    {
      "epoch": 0.10512483574244415,
      "grad_norm": 3.7681539058685303,
      "learning_rate": 7.500000000000001e-05,
      "loss": 6.9426,
      "step": 40
    },
    {
      "epoch": 0.10775295663600526,
      "grad_norm": 3.7199325561523438,
      "learning_rate": 7.347357813929454e-05,
      "loss": 7.1631,
      "step": 41
    },
    {
      "epoch": 0.11038107752956636,
      "grad_norm": 4.243125915527344,
      "learning_rate": 7.191855733945387e-05,
      "loss": 7.092,
      "step": 42
    },
    {
      "epoch": 0.11300919842312747,
      "grad_norm": 4.146131992340088,
      "learning_rate": 7.033683215379002e-05,
      "loss": 7.5549,
      "step": 43
    },
    {
      "epoch": 0.11563731931668857,
      "grad_norm": 3.312317132949829,
      "learning_rate": 6.873032967079561e-05,
      "loss": 7.0711,
      "step": 44
    },
    {
      "epoch": 0.11826544021024968,
      "grad_norm": 3.4535398483276367,
      "learning_rate": 6.710100716628344e-05,
      "loss": 7.2084,
      "step": 45
    },
    {
      "epoch": 0.11826544021024968,
      "eval_loss": 6.981412410736084,
      "eval_runtime": 7.8222,
      "eval_samples_per_second": 41.037,
      "eval_steps_per_second": 5.241,
      "step": 45
    },
    {
      "epoch": 0.12089356110381078,
      "grad_norm": 3.1890342235565186,
      "learning_rate": 6.545084971874738e-05,
      "loss": 6.7782,
      "step": 46
    },
    {
      "epoch": 0.12352168199737187,
      "grad_norm": 3.076508045196533,
      "learning_rate": 6.378186779084995e-05,
      "loss": 6.8948,
      "step": 47
    },
    {
      "epoch": 0.12614980289093297,
      "grad_norm": 4.208280563354492,
      "learning_rate": 6.209609477998338e-05,
      "loss": 7.0109,
      "step": 48
    },
    {
      "epoch": 0.1287779237844941,
      "grad_norm": 2.896726369857788,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 6.866,
      "step": 49
    },
    {
      "epoch": 0.1314060446780552,
      "grad_norm": 5.758768558502197,
      "learning_rate": 5.868240888334653e-05,
      "loss": 6.5004,
      "step": 50
    },
    {
      "epoch": 0.1340341655716163,
      "grad_norm": 2.622481107711792,
      "learning_rate": 5.695865504800327e-05,
      "loss": 6.5451,
      "step": 51
    },
    {
      "epoch": 0.1366622864651774,
      "grad_norm": 3.3432939052581787,
      "learning_rate": 5.522642316338268e-05,
      "loss": 7.1003,
      "step": 52
    },
    {
      "epoch": 0.1392904073587385,
      "grad_norm": 3.460822820663452,
      "learning_rate": 5.348782368720626e-05,
      "loss": 7.5412,
      "step": 53
    },
    {
      "epoch": 0.14191852825229961,
      "grad_norm": 4.498050689697266,
      "learning_rate": 5.174497483512506e-05,
      "loss": 7.1544,
      "step": 54
    },
    {
      "epoch": 0.14191852825229961,
      "eval_loss": 6.912955284118652,
      "eval_runtime": 7.8343,
      "eval_samples_per_second": 40.974,
      "eval_steps_per_second": 5.233,
      "step": 54
    },
    {
      "epoch": 0.1445466491458607,
      "grad_norm": 3.7371087074279785,
      "learning_rate": 5e-05,
      "loss": 6.9554,
      "step": 55
    },
    {
      "epoch": 0.1471747700394218,
      "grad_norm": 3.3637523651123047,
      "learning_rate": 4.825502516487497e-05,
      "loss": 6.8556,
      "step": 56
    },
    {
      "epoch": 0.1498028909329829,
      "grad_norm": 3.845339298248291,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 7.8125,
      "step": 57
    },
    {
      "epoch": 0.15243101182654403,
      "grad_norm": 2.977215051651001,
      "learning_rate": 4.477357683661734e-05,
      "loss": 6.8587,
      "step": 58
    },
    {
      "epoch": 0.15505913272010513,
      "grad_norm": 2.899541139602661,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 7.1409,
      "step": 59
    },
    {
      "epoch": 0.15768725361366623,
      "grad_norm": 3.146878719329834,
      "learning_rate": 4.131759111665349e-05,
      "loss": 7.0631,
      "step": 60
    },
    {
      "epoch": 0.16031537450722733,
      "grad_norm": 2.8929479122161865,
      "learning_rate": 3.960441545911204e-05,
      "loss": 6.9279,
      "step": 61
    },
    {
      "epoch": 0.16294349540078842,
      "grad_norm": 3.5399699211120605,
      "learning_rate": 3.790390522001662e-05,
      "loss": 6.9131,
      "step": 62
    },
    {
      "epoch": 0.16557161629434955,
      "grad_norm": 2.8847124576568604,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 6.5008,
      "step": 63
    },
    {
      "epoch": 0.16557161629434955,
      "eval_loss": 6.859212398529053,
      "eval_runtime": 7.823,
      "eval_samples_per_second": 41.033,
      "eval_steps_per_second": 5.241,
      "step": 63
    },
    {
      "epoch": 0.16819973718791065,
      "grad_norm": 3.6189582347869873,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 6.6061,
      "step": 64
    },
    {
      "epoch": 0.17082785808147175,
      "grad_norm": 4.201334476470947,
      "learning_rate": 3.289899283371657e-05,
      "loss": 7.1914,
      "step": 65
    },
    {
      "epoch": 0.17345597897503284,
      "grad_norm": 4.052191257476807,
      "learning_rate": 3.12696703292044e-05,
      "loss": 6.8996,
      "step": 66
    },
    {
      "epoch": 0.17608409986859397,
      "grad_norm": 2.797459125518799,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 7.1348,
      "step": 67
    },
    {
      "epoch": 0.17871222076215507,
      "grad_norm": 3.1193556785583496,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 7.3041,
      "step": 68
    },
    {
      "epoch": 0.18134034165571616,
      "grad_norm": 3.285179376602173,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 6.87,
      "step": 69
    },
    {
      "epoch": 0.18396846254927726,
      "grad_norm": 3.520158052444458,
      "learning_rate": 2.500000000000001e-05,
      "loss": 6.8825,
      "step": 70
    },
    {
      "epoch": 0.18659658344283836,
      "grad_norm": 3.528801918029785,
      "learning_rate": 2.350403678833976e-05,
      "loss": 6.9256,
      "step": 71
    },
    {
      "epoch": 0.18922470433639949,
      "grad_norm": 3.827869415283203,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 6.7786,
      "step": 72
    },
    {
      "epoch": 0.18922470433639949,
      "eval_loss": 6.8246331214904785,
      "eval_runtime": 7.8447,
      "eval_samples_per_second": 40.919,
      "eval_steps_per_second": 5.226,
      "step": 72
    },
    {
      "epoch": 0.19185282522996058,
      "grad_norm": 4.021266937255859,
      "learning_rate": 2.061073738537635e-05,
      "loss": 6.4212,
      "step": 73
    },
    {
      "epoch": 0.19448094612352168,
      "grad_norm": 3.4979543685913086,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 6.6614,
      "step": 74
    },
    {
      "epoch": 0.19710906701708278,
      "grad_norm": 2.2178640365600586,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 7.0153,
      "step": 75
    },
    {
      "epoch": 0.19973718791064388,
      "grad_norm": 3.0247833728790283,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 6.9312,
      "step": 76
    },
    {
      "epoch": 0.202365308804205,
      "grad_norm": 3.42531418800354,
      "learning_rate": 1.526708147705013e-05,
      "loss": 6.4775,
      "step": 77
    },
    {
      "epoch": 0.2049934296977661,
      "grad_norm": 3.9694366455078125,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 7.1735,
      "step": 78
    },
    {
      "epoch": 0.2076215505913272,
      "grad_norm": 3.074192523956299,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 7.3444,
      "step": 79
    },
    {
      "epoch": 0.2102496714848883,
      "grad_norm": 3.740687847137451,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 6.5621,
      "step": 80
    },
    {
      "epoch": 0.21287779237844942,
      "grad_norm": 3.3163349628448486,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 6.883,
      "step": 81
    },
    {
      "epoch": 0.21287779237844942,
      "eval_loss": 6.806041240692139,
      "eval_runtime": 7.8241,
      "eval_samples_per_second": 41.027,
      "eval_steps_per_second": 5.24,
      "step": 81
    },
    {
      "epoch": 0.21550591327201052,
      "grad_norm": 3.510040283203125,
      "learning_rate": 9.549150281252633e-06,
      "loss": 6.4147,
      "step": 82
    },
    {
      "epoch": 0.21813403416557162,
      "grad_norm": 3.3240206241607666,
      "learning_rate": 8.548121372247918e-06,
      "loss": 6.5435,
      "step": 83
    },
    {
      "epoch": 0.22076215505913271,
      "grad_norm": 3.137699604034424,
      "learning_rate": 7.597595192178702e-06,
      "loss": 6.5122,
      "step": 84
    },
    {
      "epoch": 0.2233902759526938,
      "grad_norm": 3.389455795288086,
      "learning_rate": 6.698729810778065e-06,
      "loss": 6.9796,
      "step": 85
    },
    {
      "epoch": 0.22601839684625494,
      "grad_norm": 4.588552951812744,
      "learning_rate": 5.852620357053651e-06,
      "loss": 6.7471,
      "step": 86
    },
    {
      "epoch": 0.22864651773981604,
      "grad_norm": 3.3164541721343994,
      "learning_rate": 5.060297685041659e-06,
      "loss": 7.0089,
      "step": 87
    },
    {
      "epoch": 0.23127463863337713,
      "grad_norm": 4.035533905029297,
      "learning_rate": 4.322727117869951e-06,
      "loss": 6.8038,
      "step": 88
    },
    {
      "epoch": 0.23390275952693823,
      "grad_norm": 3.418544292449951,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 6.3053,
      "step": 89
    },
    {
      "epoch": 0.23653088042049936,
      "grad_norm": 3.443645477294922,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 7.12,
      "step": 90
    },
    {
      "epoch": 0.23653088042049936,
      "eval_loss": 6.798569679260254,
      "eval_runtime": 7.8396,
      "eval_samples_per_second": 40.946,
      "eval_steps_per_second": 5.23,
      "step": 90
    },
    {
      "epoch": 0.23915900131406045,
      "grad_norm": 3.201587677001953,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 6.7507,
      "step": 91
    },
    {
      "epoch": 0.24178712220762155,
      "grad_norm": 3.0061752796173096,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 6.8862,
      "step": 92
    },
    {
      "epoch": 0.24441524310118265,
      "grad_norm": 2.538280963897705,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 7.023,
      "step": 93
    },
    {
      "epoch": 0.24704336399474375,
      "grad_norm": 3.575631856918335,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 7.1501,
      "step": 94
    },
    {
      "epoch": 0.24967148488830487,
      "grad_norm": 3.6927804946899414,
      "learning_rate": 7.596123493895991e-07,
      "loss": 6.4113,
      "step": 95
    },
    {
      "epoch": 0.25229960578186594,
      "grad_norm": 3.6118414402008057,
      "learning_rate": 4.865965629214819e-07,
      "loss": 6.7738,
      "step": 96
    },
    {
      "epoch": 0.25492772667542707,
      "grad_norm": 4.216277122497559,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 6.6602,
      "step": 97
    },
    {
      "epoch": 0.2575558475689882,
      "grad_norm": 3.5179567337036133,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 6.7022,
      "step": 98
    },
    {
      "epoch": 0.26018396846254926,
      "grad_norm": 4.385186195373535,
      "learning_rate": 3.04586490452119e-08,
      "loss": 6.6645,
      "step": 99
    },
    {
      "epoch": 0.26018396846254926,
      "eval_loss": 6.796245098114014,
      "eval_runtime": 7.8349,
      "eval_samples_per_second": 40.97,
      "eval_steps_per_second": 5.233,
      "step": 99
    },
    {
      "epoch": 0.2628120893561104,
      "grad_norm": 3.6011836528778076,
      "learning_rate": 0.0,
      "loss": 6.8888,
      "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": 47104417333248.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}