{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3716608594657375,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004645760743321719,
      "grad_norm": 5.007833918054177,
      "learning_rate": 0.0,
      "loss": 0.3559,
      "step": 1
    },
    {
      "epoch": 0.009291521486643438,
      "grad_norm": 6.095402413693695,
      "learning_rate": 2.3255813953488374e-07,
      "loss": 0.4478,
      "step": 2
    },
    {
      "epoch": 0.013937282229965157,
      "grad_norm": 5.711860921252622,
      "learning_rate": 4.651162790697675e-07,
      "loss": 0.4202,
      "step": 3
    },
    {
      "epoch": 0.018583042973286876,
      "grad_norm": 4.919598888513217,
      "learning_rate": 6.976744186046513e-07,
      "loss": 0.3667,
      "step": 4
    },
    {
      "epoch": 0.023228803716608595,
      "grad_norm": 5.323101120637421,
      "learning_rate": 9.30232558139535e-07,
      "loss": 0.392,
      "step": 5
    },
    {
      "epoch": 0.027874564459930314,
      "grad_norm": 4.825973626019842,
      "learning_rate": 1.1627906976744188e-06,
      "loss": 0.3745,
      "step": 6
    },
    {
      "epoch": 0.032520325203252036,
      "grad_norm": 4.722030575751275,
      "learning_rate": 1.3953488372093025e-06,
      "loss": 0.372,
      "step": 7
    },
    {
      "epoch": 0.03716608594657375,
      "grad_norm": 3.204008987512321,
      "learning_rate": 1.6279069767441862e-06,
      "loss": 0.3266,
      "step": 8
    },
    {
      "epoch": 0.041811846689895474,
      "grad_norm": 3.462779060517298,
      "learning_rate": 1.86046511627907e-06,
      "loss": 0.3531,
      "step": 9
    },
    {
      "epoch": 0.04645760743321719,
      "grad_norm": 2.2912708740881493,
      "learning_rate": 2.0930232558139536e-06,
      "loss": 0.2766,
      "step": 10
    },
    {
      "epoch": 0.05110336817653891,
      "grad_norm": 2.360020281101277,
      "learning_rate": 2.3255813953488376e-06,
      "loss": 0.2708,
      "step": 11
    },
    {
      "epoch": 0.05574912891986063,
      "grad_norm": 2.210016095359394,
      "learning_rate": 2.558139534883721e-06,
      "loss": 0.2772,
      "step": 12
    },
    {
      "epoch": 0.06039488966318235,
      "grad_norm": 2.0430891492298042,
      "learning_rate": 2.790697674418605e-06,
      "loss": 0.2116,
      "step": 13
    },
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 1.1937018297310904,
      "learning_rate": 3.0232558139534885e-06,
      "loss": 0.1785,
      "step": 14
    },
    {
      "epoch": 0.06968641114982578,
      "grad_norm": 2.293421959275872,
      "learning_rate": 3.2558139534883724e-06,
      "loss": 0.162,
      "step": 15
    },
    {
      "epoch": 0.0743321718931475,
      "grad_norm": 2.491793718040822,
      "learning_rate": 3.4883720930232564e-06,
      "loss": 0.1625,
      "step": 16
    },
    {
      "epoch": 0.07897793263646923,
      "grad_norm": 1.0576667987718384,
      "learning_rate": 3.72093023255814e-06,
      "loss": 0.2098,
      "step": 17
    },
    {
      "epoch": 0.08362369337979095,
      "grad_norm": 1.3362976538502087,
      "learning_rate": 3.953488372093024e-06,
      "loss": 0.2079,
      "step": 18
    },
    {
      "epoch": 0.08826945412311266,
      "grad_norm": 0.8210443873224946,
      "learning_rate": 4.186046511627907e-06,
      "loss": 0.1393,
      "step": 19
    },
    {
      "epoch": 0.09291521486643438,
      "grad_norm": 1.3763061922656377,
      "learning_rate": 4.418604651162791e-06,
      "loss": 0.1836,
      "step": 20
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.8540487861144667,
      "learning_rate": 4.651162790697675e-06,
      "loss": 0.1726,
      "step": 21
    },
    {
      "epoch": 0.10220673635307782,
      "grad_norm": 0.9965597925413834,
      "learning_rate": 4.883720930232559e-06,
      "loss": 0.1594,
      "step": 22
    },
    {
      "epoch": 0.10685249709639953,
      "grad_norm": 0.8124932586870112,
      "learning_rate": 5.116279069767442e-06,
      "loss": 0.1645,
      "step": 23
    },
    {
      "epoch": 0.11149825783972125,
      "grad_norm": 0.765248257044288,
      "learning_rate": 5.348837209302326e-06,
      "loss": 0.1689,
      "step": 24
    },
    {
      "epoch": 0.11614401858304298,
      "grad_norm": 0.6535802502844509,
      "learning_rate": 5.58139534883721e-06,
      "loss": 0.1221,
      "step": 25
    },
    {
      "epoch": 0.1207897793263647,
      "grad_norm": 0.9332551865412465,
      "learning_rate": 5.8139534883720935e-06,
      "loss": 0.1441,
      "step": 26
    },
    {
      "epoch": 0.1254355400696864,
      "grad_norm": 0.6281977004298958,
      "learning_rate": 6.046511627906977e-06,
      "loss": 0.145,
      "step": 27
    },
    {
      "epoch": 0.13008130081300814,
      "grad_norm": 0.6506862696473351,
      "learning_rate": 6.279069767441861e-06,
      "loss": 0.143,
      "step": 28
    },
    {
      "epoch": 0.13472706155632985,
      "grad_norm": 0.5925406859408308,
      "learning_rate": 6.511627906976745e-06,
      "loss": 0.114,
      "step": 29
    },
    {
      "epoch": 0.13937282229965156,
      "grad_norm": 0.6169180678569642,
      "learning_rate": 6.744186046511628e-06,
      "loss": 0.1468,
      "step": 30
    },
    {
      "epoch": 0.1440185830429733,
      "grad_norm": 0.6614089477540361,
      "learning_rate": 6.976744186046513e-06,
      "loss": 0.1499,
      "step": 31
    },
    {
      "epoch": 0.148664343786295,
      "grad_norm": 0.5308532041753055,
      "learning_rate": 7.209302325581395e-06,
      "loss": 0.1215,
      "step": 32
    },
    {
      "epoch": 0.15331010452961671,
      "grad_norm": 0.5280217992451164,
      "learning_rate": 7.44186046511628e-06,
      "loss": 0.1152,
      "step": 33
    },
    {
      "epoch": 0.15795586527293845,
      "grad_norm": 0.5648689606705951,
      "learning_rate": 7.674418604651164e-06,
      "loss": 0.1272,
      "step": 34
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 0.6245478572825075,
      "learning_rate": 7.906976744186048e-06,
      "loss": 0.1239,
      "step": 35
    },
    {
      "epoch": 0.1672473867595819,
      "grad_norm": 0.5730808630246532,
      "learning_rate": 8.139534883720931e-06,
      "loss": 0.1471,
      "step": 36
    },
    {
      "epoch": 0.1718931475029036,
      "grad_norm": 0.8015364328717397,
      "learning_rate": 8.372093023255815e-06,
      "loss": 0.1294,
      "step": 37
    },
    {
      "epoch": 0.1765389082462253,
      "grad_norm": 0.5068324361347291,
      "learning_rate": 8.604651162790698e-06,
      "loss": 0.1143,
      "step": 38
    },
    {
      "epoch": 0.18118466898954705,
      "grad_norm": 0.43809350886606024,
      "learning_rate": 8.837209302325582e-06,
      "loss": 0.1036,
      "step": 39
    },
    {
      "epoch": 0.18583042973286876,
      "grad_norm": 0.6474622607168083,
      "learning_rate": 9.069767441860465e-06,
      "loss": 0.1293,
      "step": 40
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.398228005633473,
      "learning_rate": 9.30232558139535e-06,
      "loss": 0.0795,
      "step": 41
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.5722673746771715,
      "learning_rate": 9.534883720930234e-06,
      "loss": 0.1195,
      "step": 42
    },
    {
      "epoch": 0.1997677119628339,
      "grad_norm": 0.6387829720867708,
      "learning_rate": 9.767441860465117e-06,
      "loss": 0.0944,
      "step": 43
    },
    {
      "epoch": 0.20441347270615565,
      "grad_norm": 0.7262386990022901,
      "learning_rate": 1e-05,
      "loss": 0.1238,
      "step": 44
    },
    {
      "epoch": 0.20905923344947736,
      "grad_norm": 0.6415131233839582,
      "learning_rate": 9.999835253787472e-06,
      "loss": 0.0962,
      "step": 45
    },
    {
      "epoch": 0.21370499419279906,
      "grad_norm": 0.49038910043998885,
      "learning_rate": 9.99934102600642e-06,
      "loss": 0.1138,
      "step": 46
    },
    {
      "epoch": 0.2183507549361208,
      "grad_norm": 0.4998657774910992,
      "learning_rate": 9.998517349225698e-06,
      "loss": 0.1167,
      "step": 47
    },
    {
      "epoch": 0.2229965156794425,
      "grad_norm": 0.5526423671759817,
      "learning_rate": 9.997364277724362e-06,
      "loss": 0.1139,
      "step": 48
    },
    {
      "epoch": 0.22764227642276422,
      "grad_norm": 0.6758176165629011,
      "learning_rate": 9.99588188748808e-06,
      "loss": 0.1228,
      "step": 49
    },
    {
      "epoch": 0.23228803716608595,
      "grad_norm": 0.4301604798832004,
      "learning_rate": 9.994070276204115e-06,
      "loss": 0.1064,
      "step": 50
    },
    {
      "epoch": 0.23693379790940766,
      "grad_norm": 0.46902072966952235,
      "learning_rate": 9.991929563254913e-06,
      "loss": 0.1108,
      "step": 51
    },
    {
      "epoch": 0.2415795586527294,
      "grad_norm": 0.4794902114805145,
      "learning_rate": 9.989459889710214e-06,
      "loss": 0.1186,
      "step": 52
    },
    {
      "epoch": 0.2462253193960511,
      "grad_norm": 0.5285811649673939,
      "learning_rate": 9.986661418317759e-06,
      "loss": 0.1122,
      "step": 53
    },
    {
      "epoch": 0.2508710801393728,
      "grad_norm": 0.47633553231292913,
      "learning_rate": 9.983534333492575e-06,
      "loss": 0.1082,
      "step": 54
    },
    {
      "epoch": 0.25551684088269455,
      "grad_norm": 0.44801729878550234,
      "learning_rate": 9.980078841304817e-06,
      "loss": 0.099,
      "step": 55
    },
    {
      "epoch": 0.2601626016260163,
      "grad_norm": 0.5171140926967782,
      "learning_rate": 9.97629516946618e-06,
      "loss": 0.1325,
      "step": 56
    },
    {
      "epoch": 0.26480836236933797,
      "grad_norm": 0.5256667140476758,
      "learning_rate": 9.97218356731491e-06,
      "loss": 0.1182,
      "step": 57
    },
    {
      "epoch": 0.2694541231126597,
      "grad_norm": 0.5021698137895357,
      "learning_rate": 9.967744305799358e-06,
      "loss": 0.116,
      "step": 58
    },
    {
      "epoch": 0.27409988385598144,
      "grad_norm": 0.4524730076882164,
      "learning_rate": 9.962977677460132e-06,
      "loss": 0.105,
      "step": 59
    },
    {
      "epoch": 0.2787456445993031,
      "grad_norm": 0.4865312647490816,
      "learning_rate": 9.957883996410821e-06,
      "loss": 0.0996,
      "step": 60
    },
    {
      "epoch": 0.28339140534262486,
      "grad_norm": 0.6154932122623457,
      "learning_rate": 9.952463598317286e-06,
      "loss": 0.1032,
      "step": 61
    },
    {
      "epoch": 0.2880371660859466,
      "grad_norm": 0.5720328273849398,
      "learning_rate": 9.946716840375552e-06,
      "loss": 0.1235,
      "step": 62
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 0.5353383236460627,
      "learning_rate": 9.940644101288259e-06,
      "loss": 0.1319,
      "step": 63
    },
    {
      "epoch": 0.29732868757259,
      "grad_norm": 0.5699498931307571,
      "learning_rate": 9.934245781239714e-06,
      "loss": 0.1222,
      "step": 64
    },
    {
      "epoch": 0.30197444831591175,
      "grad_norm": 0.5041655852014973,
      "learning_rate": 9.927522301869515e-06,
      "loss": 0.1185,
      "step": 65
    },
    {
      "epoch": 0.30662020905923343,
      "grad_norm": 0.560593382940921,
      "learning_rate": 9.920474106244764e-06,
      "loss": 0.1258,
      "step": 66
    },
    {
      "epoch": 0.31126596980255516,
      "grad_norm": 0.47113303080753793,
      "learning_rate": 9.913101658830879e-06,
      "loss": 0.0992,
      "step": 67
    },
    {
      "epoch": 0.3159117305458769,
      "grad_norm": 0.4949311762244736,
      "learning_rate": 9.905405445460972e-06,
      "loss": 0.1086,
      "step": 68
    },
    {
      "epoch": 0.3205574912891986,
      "grad_norm": 0.5118809629828459,
      "learning_rate": 9.897385973303845e-06,
      "loss": 0.1115,
      "step": 69
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 0.45743773717890135,
      "learning_rate": 9.889043770830566e-06,
      "loss": 0.0981,
      "step": 70
    },
    {
      "epoch": 0.32984901277584205,
      "grad_norm": 0.41235204595203667,
      "learning_rate": 9.880379387779637e-06,
      "loss": 0.0966,
      "step": 71
    },
    {
      "epoch": 0.3344947735191638,
      "grad_norm": 0.4726483178511245,
      "learning_rate": 9.871393395120774e-06,
      "loss": 0.0956,
      "step": 72
    },
    {
      "epoch": 0.33914053426248547,
      "grad_norm": 0.4601067106108247,
      "learning_rate": 9.862086385017283e-06,
      "loss": 0.0988,
      "step": 73
    },
    {
      "epoch": 0.3437862950058072,
      "grad_norm": 0.4731203086011778,
      "learning_rate": 9.852458970787027e-06,
      "loss": 0.1149,
      "step": 74
    },
    {
      "epoch": 0.34843205574912894,
      "grad_norm": 0.5764782890777245,
      "learning_rate": 9.842511786862018e-06,
      "loss": 0.1327,
      "step": 75
    },
    {
      "epoch": 0.3530778164924506,
      "grad_norm": 0.48832588953944156,
      "learning_rate": 9.832245488746612e-06,
      "loss": 0.1019,
      "step": 76
    },
    {
      "epoch": 0.35772357723577236,
      "grad_norm": 0.44229595011423917,
      "learning_rate": 9.821660752974294e-06,
      "loss": 0.1067,
      "step": 77
    },
    {
      "epoch": 0.3623693379790941,
      "grad_norm": 0.4796942954547918,
      "learning_rate": 9.81075827706312e-06,
      "loss": 0.0825,
      "step": 78
    },
    {
      "epoch": 0.3670150987224158,
      "grad_norm": 0.40318849008254065,
      "learning_rate": 9.799538779469734e-06,
      "loss": 0.0998,
      "step": 79
    },
    {
      "epoch": 0.3716608594657375,
      "grad_norm": 0.5193073119324224,
      "learning_rate": 9.78800299954203e-06,
      "loss": 0.0857,
      "step": 80
    }
  ],
  "logging_steps": 1,
  "max_steps": 430,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.063277885531095e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}