{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1130342635111268,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011303426351112682,
      "grad_norm": 0.4267180860042572,
      "learning_rate": 1e-05,
      "loss": 1.2983,
      "step": 1
    },
    {
      "epoch": 0.0011303426351112682,
      "eval_loss": 1.2833271026611328,
      "eval_runtime": 275.3923,
      "eval_samples_per_second": 5.41,
      "eval_steps_per_second": 2.705,
      "step": 1
    },
    {
      "epoch": 0.0022606852702225363,
      "grad_norm": 0.4324004650115967,
      "learning_rate": 2e-05,
      "loss": 1.3099,
      "step": 2
    },
    {
      "epoch": 0.0033910279053338045,
      "grad_norm": 0.386563241481781,
      "learning_rate": 3e-05,
      "loss": 1.2479,
      "step": 3
    },
    {
      "epoch": 0.004521370540445073,
      "grad_norm": 0.3651917278766632,
      "learning_rate": 4e-05,
      "loss": 1.1986,
      "step": 4
    },
    {
      "epoch": 0.00565171317555634,
      "grad_norm": 0.4020462930202484,
      "learning_rate": 5e-05,
      "loss": 1.2329,
      "step": 5
    },
    {
      "epoch": 0.006782055810667609,
      "grad_norm": 0.4143919050693512,
      "learning_rate": 6e-05,
      "loss": 1.1849,
      "step": 6
    },
    {
      "epoch": 0.007912398445778877,
      "grad_norm": 0.46201300621032715,
      "learning_rate": 7e-05,
      "loss": 1.1534,
      "step": 7
    },
    {
      "epoch": 0.009042741080890145,
      "grad_norm": 0.4803551435470581,
      "learning_rate": 8e-05,
      "loss": 1.1099,
      "step": 8
    },
    {
      "epoch": 0.010173083716001412,
      "grad_norm": 0.4682976007461548,
      "learning_rate": 9e-05,
      "loss": 1.0332,
      "step": 9
    },
    {
      "epoch": 0.01130342635111268,
      "grad_norm": 0.4358697235584259,
      "learning_rate": 0.0001,
      "loss": 0.9534,
      "step": 10
    },
    {
      "epoch": 0.01243376898622395,
      "grad_norm": 0.4125397205352783,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.9076,
      "step": 11
    },
    {
      "epoch": 0.013564111621335218,
      "grad_norm": 0.3886691927909851,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.8131,
      "step": 12
    },
    {
      "epoch": 0.014694454256446485,
      "grad_norm": 0.38308605551719666,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.8085,
      "step": 13
    },
    {
      "epoch": 0.015824796891557753,
      "grad_norm": 0.4111347198486328,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.7065,
      "step": 14
    },
    {
      "epoch": 0.016955139526669022,
      "grad_norm": 0.46617141366004944,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.6313,
      "step": 15
    },
    {
      "epoch": 0.01808548216178029,
      "grad_norm": 0.4996795058250427,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.5647,
      "step": 16
    },
    {
      "epoch": 0.01921582479689156,
      "grad_norm": 0.4880048632621765,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.5264,
      "step": 17
    },
    {
      "epoch": 0.020346167432002824,
      "grad_norm": 0.4479418992996216,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.4685,
      "step": 18
    },
    {
      "epoch": 0.021476510067114093,
      "grad_norm": 0.41051650047302246,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4071,
      "step": 19
    },
    {
      "epoch": 0.02260685270222536,
      "grad_norm": 0.3480631411075592,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.3368,
      "step": 20
    },
    {
      "epoch": 0.02373719533733663,
      "grad_norm": 0.34411585330963135,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.2895,
      "step": 21
    },
    {
      "epoch": 0.0248675379724479,
      "grad_norm": 0.28736212849617004,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.2816,
      "step": 22
    },
    {
      "epoch": 0.025997880607559167,
      "grad_norm": 0.21256913244724274,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.2353,
      "step": 23
    },
    {
      "epoch": 0.027128223242670436,
      "grad_norm": 0.20762597024440765,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.2539,
      "step": 24
    },
    {
      "epoch": 0.0282585658777817,
      "grad_norm": 0.18623079359531403,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2402,
      "step": 25
    },
    {
      "epoch": 0.0282585658777817,
      "eval_loss": 0.23738591372966766,
      "eval_runtime": 120.4653,
      "eval_samples_per_second": 12.369,
      "eval_steps_per_second": 6.184,
      "step": 25
    },
    {
      "epoch": 0.02938890851289297,
      "grad_norm": 0.18665114045143127,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.2385,
      "step": 26
    },
    {
      "epoch": 0.030519251148004238,
      "grad_norm": 0.18654821813106537,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.2451,
      "step": 27
    },
    {
      "epoch": 0.03164959378311551,
      "grad_norm": 0.16335079073905945,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.22,
      "step": 28
    },
    {
      "epoch": 0.032779936418226775,
      "grad_norm": 0.17224492132663727,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.2387,
      "step": 29
    },
    {
      "epoch": 0.033910279053338044,
      "grad_norm": 0.13631552457809448,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2071,
      "step": 30
    },
    {
      "epoch": 0.03504062168844931,
      "grad_norm": 0.1457497626543045,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.2329,
      "step": 31
    },
    {
      "epoch": 0.03617096432356058,
      "grad_norm": 0.1276518702507019,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.2079,
      "step": 32
    },
    {
      "epoch": 0.03730130695867185,
      "grad_norm": 0.12294354289770126,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.1839,
      "step": 33
    },
    {
      "epoch": 0.03843164959378312,
      "grad_norm": 0.13454532623291016,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1972,
      "step": 34
    },
    {
      "epoch": 0.03956199222889439,
      "grad_norm": 0.1205684021115303,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.2071,
      "step": 35
    },
    {
      "epoch": 0.04069233486400565,
      "grad_norm": 0.11395933479070663,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1872,
      "step": 36
    },
    {
      "epoch": 0.04182267749911692,
      "grad_norm": 0.11452674865722656,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1975,
      "step": 37
    },
    {
      "epoch": 0.042953020134228186,
      "grad_norm": 0.11387357115745544,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.1841,
      "step": 38
    },
    {
      "epoch": 0.044083362769339454,
      "grad_norm": 0.10960604250431061,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.1937,
      "step": 39
    },
    {
      "epoch": 0.04521370540445072,
      "grad_norm": 0.10804131627082825,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1686,
      "step": 40
    },
    {
      "epoch": 0.04634404803956199,
      "grad_norm": 0.1007540300488472,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.1639,
      "step": 41
    },
    {
      "epoch": 0.04747439067467326,
      "grad_norm": 0.10301187634468079,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.1953,
      "step": 42
    },
    {
      "epoch": 0.04860473330978453,
      "grad_norm": 0.1033124104142189,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.1619,
      "step": 43
    },
    {
      "epoch": 0.0497350759448958,
      "grad_norm": 0.10108724236488342,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.1761,
      "step": 44
    },
    {
      "epoch": 0.050865418580007066,
      "grad_norm": 0.10317586362361908,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.1857,
      "step": 45
    },
    {
      "epoch": 0.051995761215118334,
      "grad_norm": 0.10117630660533905,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.181,
      "step": 46
    },
    {
      "epoch": 0.0531261038502296,
      "grad_norm": 0.10242675989866257,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.1481,
      "step": 47
    },
    {
      "epoch": 0.05425644648534087,
      "grad_norm": 0.10420997440814972,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.1807,
      "step": 48
    },
    {
      "epoch": 0.05538678912045214,
      "grad_norm": 0.10270124673843384,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.1637,
      "step": 49
    },
    {
      "epoch": 0.0565171317555634,
      "grad_norm": 0.09528330713510513,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.1463,
      "step": 50
    },
    {
      "epoch": 0.0565171317555634,
      "eval_loss": 0.15754836797714233,
      "eval_runtime": 108.1535,
      "eval_samples_per_second": 13.777,
      "eval_steps_per_second": 6.888,
      "step": 50
    },
    {
      "epoch": 0.05764747439067467,
      "grad_norm": 0.10484740883111954,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1664,
      "step": 51
    },
    {
      "epoch": 0.05877781702578594,
      "grad_norm": 0.09817209094762802,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.1572,
      "step": 52
    },
    {
      "epoch": 0.05990815966089721,
      "grad_norm": 0.09848269075155258,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.1595,
      "step": 53
    },
    {
      "epoch": 0.061038502296008476,
      "grad_norm": 0.09713145345449448,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.1644,
      "step": 54
    },
    {
      "epoch": 0.062168844931119745,
      "grad_norm": 0.11254185438156128,
      "learning_rate": 5e-05,
      "loss": 0.153,
      "step": 55
    },
    {
      "epoch": 0.06329918756623101,
      "grad_norm": 0.10281391441822052,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.1617,
      "step": 56
    },
    {
      "epoch": 0.06442953020134229,
      "grad_norm": 0.09166331589221954,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.145,
      "step": 57
    },
    {
      "epoch": 0.06555987283645355,
      "grad_norm": 0.09803515672683716,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1616,
      "step": 58
    },
    {
      "epoch": 0.06669021547156481,
      "grad_norm": 0.0987379401922226,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.1689,
      "step": 59
    },
    {
      "epoch": 0.06782055810667609,
      "grad_norm": 0.09968309849500656,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1529,
      "step": 60
    },
    {
      "epoch": 0.06895090074178735,
      "grad_norm": 0.09657073765993118,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.1593,
      "step": 61
    },
    {
      "epoch": 0.07008124337689862,
      "grad_norm": 0.10319285094738007,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.1617,
      "step": 62
    },
    {
      "epoch": 0.07121158601200989,
      "grad_norm": 0.09319040179252625,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.1388,
      "step": 63
    },
    {
      "epoch": 0.07234192864712116,
      "grad_norm": 0.10078910738229752,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.157,
      "step": 64
    },
    {
      "epoch": 0.07347227128223242,
      "grad_norm": 0.0971289873123169,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.157,
      "step": 65
    },
    {
      "epoch": 0.0746026139173437,
      "grad_norm": 0.09027408063411713,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.1278,
      "step": 66
    },
    {
      "epoch": 0.07573295655245496,
      "grad_norm": 0.09577968716621399,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.1476,
      "step": 67
    },
    {
      "epoch": 0.07686329918756624,
      "grad_norm": 0.095377616584301,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.1401,
      "step": 68
    },
    {
      "epoch": 0.0779936418226775,
      "grad_norm": 0.09206076711416245,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.145,
      "step": 69
    },
    {
      "epoch": 0.07912398445778877,
      "grad_norm": 0.10833960771560669,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.144,
      "step": 70
    },
    {
      "epoch": 0.08025432709290004,
      "grad_norm": 0.10532192140817642,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.1684,
      "step": 71
    },
    {
      "epoch": 0.0813846697280113,
      "grad_norm": 0.09503438323736191,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.1353,
      "step": 72
    },
    {
      "epoch": 0.08251501236312257,
      "grad_norm": 0.10530933737754822,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1293,
      "step": 73
    },
    {
      "epoch": 0.08364535499823383,
      "grad_norm": 0.0886959508061409,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.1283,
      "step": 74
    },
    {
      "epoch": 0.08477569763334511,
      "grad_norm": 0.09509113430976868,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1503,
      "step": 75
    },
    {
      "epoch": 0.08477569763334511,
      "eval_loss": 0.14312788844108582,
      "eval_runtime": 108.0678,
      "eval_samples_per_second": 13.788,
      "eval_steps_per_second": 6.894,
      "step": 75
    },
    {
      "epoch": 0.08590604026845637,
      "grad_norm": 0.09077107161283493,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1332,
      "step": 76
    },
    {
      "epoch": 0.08703638290356765,
      "grad_norm": 0.10361814498901367,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.135,
      "step": 77
    },
    {
      "epoch": 0.08816672553867891,
      "grad_norm": 0.10831114649772644,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1379,
      "step": 78
    },
    {
      "epoch": 0.08929706817379018,
      "grad_norm": 0.09642671793699265,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.1438,
      "step": 79
    },
    {
      "epoch": 0.09042741080890145,
      "grad_norm": 0.08902038633823395,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1436,
      "step": 80
    },
    {
      "epoch": 0.09155775344401272,
      "grad_norm": 0.09570778906345367,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.1531,
      "step": 81
    },
    {
      "epoch": 0.09268809607912398,
      "grad_norm": 0.09648874402046204,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1443,
      "step": 82
    },
    {
      "epoch": 0.09381843871423526,
      "grad_norm": 0.08864925056695938,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.1288,
      "step": 83
    },
    {
      "epoch": 0.09494878134934652,
      "grad_norm": 0.09058023989200592,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1392,
      "step": 84
    },
    {
      "epoch": 0.0960791239844578,
      "grad_norm": 0.09723956137895584,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1493,
      "step": 85
    },
    {
      "epoch": 0.09720946661956906,
      "grad_norm": 0.09518659114837646,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.1431,
      "step": 86
    },
    {
      "epoch": 0.09833980925468032,
      "grad_norm": 0.08945231884717941,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.1373,
      "step": 87
    },
    {
      "epoch": 0.0994701518897916,
      "grad_norm": 0.09025212377309799,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1234,
      "step": 88
    },
    {
      "epoch": 0.10060049452490286,
      "grad_norm": 0.10804665088653564,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.1557,
      "step": 89
    },
    {
      "epoch": 0.10173083716001413,
      "grad_norm": 0.08853819221258163,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1394,
      "step": 90
    },
    {
      "epoch": 0.1028611797951254,
      "grad_norm": 0.0921025276184082,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1445,
      "step": 91
    },
    {
      "epoch": 0.10399152243023667,
      "grad_norm": 0.10122989118099213,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.1488,
      "step": 92
    },
    {
      "epoch": 0.10512186506534793,
      "grad_norm": 0.08481209725141525,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1257,
      "step": 93
    },
    {
      "epoch": 0.1062522077004592,
      "grad_norm": 0.09517021477222443,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1624,
      "step": 94
    },
    {
      "epoch": 0.10738255033557047,
      "grad_norm": 0.0911594033241272,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.1288,
      "step": 95
    },
    {
      "epoch": 0.10851289297068174,
      "grad_norm": 0.08819227665662766,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.1291,
      "step": 96
    },
    {
      "epoch": 0.109643235605793,
      "grad_norm": 0.0909503921866417,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.136,
      "step": 97
    },
    {
      "epoch": 0.11077357824090428,
      "grad_norm": 0.09741980582475662,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.1484,
      "step": 98
    },
    {
      "epoch": 0.11190392087601554,
      "grad_norm": 0.08844106644392014,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.1469,
      "step": 99
    },
    {
      "epoch": 0.1130342635111268,
      "grad_norm": 0.11220452934503555,
      "learning_rate": 0.0,
      "loss": 0.1474,
      "step": 100
    },
    {
      "epoch": 0.1130342635111268,
      "eval_loss": 0.14100638031959534,
      "eval_runtime": 137.5482,
      "eval_samples_per_second": 10.833,
      "eval_steps_per_second": 5.416,
      "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": 2.53296434479104e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}