{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 1.811,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.792,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.7009,
      "step": 3
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.3867,
      "step": 4
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019996629653035126,
      "loss": 1.3896,
      "step": 5
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019986520883988232,
      "loss": 1.4298,
      "step": 6
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019969680506871137,
      "loss": 1.3719,
      "step": 7
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019946119873266613,
      "loss": 1.3228,
      "step": 8
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019915854864676664,
      "loss": 1.2356,
      "step": 9
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019878905881817252,
      "loss": 1.344,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019835297830866826,
      "loss": 1.2708,
      "step": 11
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019785060106677818,
      "loss": 1.1977,
      "step": 12
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019728226572962473,
      "loss": 1.191,
      "step": 13
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001966483553946637,
      "loss": 1.2541,
      "step": 14
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019594929736144976,
      "loss": 1.1434,
      "step": 15
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019518556284360696,
      "loss": 1.151,
      "step": 16
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001943576666511982,
      "loss": 1.2481,
      "step": 17
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001934661668437073,
      "loss": 1.1546,
      "step": 18
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001925116643538684,
      "loss": 1.2652,
      "step": 19
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019149480258259533,
      "loss": 1.2271,
      "step": 20
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019041626696528503,
      "loss": 1.1398,
      "step": 21
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001892767845097864,
      "loss": 1.306,
      "step": 22
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018807712330634642,
      "loss": 1.3013,
      "step": 23
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001868180920098644,
      "loss": 1.186,
      "step": 24
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018550053929480202,
      "loss": 1.256,
      "step": 25
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018412535328311814,
      "loss": 1.1417,
      "step": 26
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001826934609456129,
      "loss": 1.1401,
      "step": 27
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018120582747708502,
      "loss": 1.1121,
      "step": 28
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001796634556457236,
      "loss": 1.1384,
      "step": 29
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001780673851171728,
      "loss": 1.0576,
      "step": 30
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017641869175372493,
      "loss": 1.1719,
      "step": 31
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017471848688911464,
      "loss": 1.1988,
      "step": 32
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000172967916579403,
      "loss": 1.1403,
      "step": 33
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017116816083045602,
      "loss": 1.1546,
      "step": 34
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001693204328025389,
      "loss": 1.1366,
      "step": 35
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016742597799256182,
      "loss": 1.1908,
      "step": 36
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016548607339452853,
      "loss": 1.198,
      "step": 37
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016350202663875386,
      "loss": 1.1083,
      "step": 38
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001614751751104301,
      "loss": 1.1103,
      "step": 39
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015940688504813662,
      "loss": 1.1205,
      "step": 40
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015729855062290022,
      "loss": 1.1252,
      "step": 41
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015515159299842707,
      "loss": 1.0998,
      "step": 42
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015296745937313987,
      "loss": 1.1261,
      "step": 43
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015074762200466556,
      "loss": 1.1013,
      "step": 44
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014849357721743168,
      "loss": 1.1126,
      "step": 45
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014620684439403962,
      "loss": 1.0665,
      "step": 46
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001438889649510956,
      "loss": 1.2455,
      "step": 47
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014154150130018866,
      "loss": 1.1824,
      "step": 48
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013916603579471705,
      "loss": 1.1314,
      "step": 49
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000136764169663272,
      "loss": 1.1713,
      "step": 50
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013433752193029886,
      "loss": 1.1747,
      "step": 51
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013188772832476188,
      "loss": 1.2117,
      "step": 52
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012941644017754964,
      "loss": 1.1668,
      "step": 53
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012692532330836346,
      "loss": 1.1652,
      "step": 54
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012441605690283915,
      "loss": 1.0743,
      "step": 55
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001218903323806595,
      "loss": 1.0586,
      "step": 56
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011934985225541998,
      "loss": 1.1211,
      "step": 57
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011679632898701649,
      "loss": 1.0606,
      "step": 58
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011423148382732853,
      "loss": 1.1001,
      "step": 59
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011165704565997593,
      "loss": 1.1847,
      "step": 60
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010907474983493144,
      "loss": 1.1075,
      "step": 61
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001064863369987743,
      "loss": 1.1444,
      "step": 62
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010389355192137377,
      "loss": 1.0845,
      "step": 63
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001012981423197931,
      "loss": 1.0034,
      "step": 64
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.870185768020693e-05,
      "loss": 1.1456,
      "step": 65
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.610644807862625e-05,
      "loss": 1.2247,
      "step": 66
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.35136630012257e-05,
      "loss": 1.0866,
      "step": 67
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.092525016506858e-05,
      "loss": 1.1255,
      "step": 68
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.83429543400241e-05,
      "loss": 1.0372,
      "step": 69
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.57685161726715e-05,
      "loss": 1.13,
      "step": 70
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.320367101298351e-05,
      "loss": 1.0964,
      "step": 71
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.065014774458003e-05,
      "loss": 1.0564,
      "step": 72
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.810966761934053e-05,
      "loss": 1.0624,
      "step": 73
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.558394309716088e-05,
      "loss": 1.2015,
      "step": 74
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.307467669163655e-05,
      "loss": 1.1124,
      "step": 75
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.058355982245037e-05,
      "loss": 1.1802,
      "step": 76
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.811227167523815e-05,
      "loss": 1.1669,
      "step": 77
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.566247806970119e-05,
      "loss": 1.0088,
      "step": 78
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.323583033672799e-05,
      "loss": 1.0864,
      "step": 79
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.083396420528298e-05,
      "loss": 1.1167,
      "step": 80
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.845849869981137e-05,
      "loss": 1.0915,
      "step": 81
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.611103504890444e-05,
      "loss": 0.9354,
      "step": 82
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.379315560596038e-05,
      "loss": 1.2242,
      "step": 83
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.1506422782568345e-05,
      "loss": 0.9804,
      "step": 84
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.9252377995334444e-05,
      "loss": 1.1305,
      "step": 85
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.703254062686017e-05,
      "loss": 1.0413,
      "step": 86
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.484840700157295e-05,
      "loss": 1.0736,
      "step": 87
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.270144937709981e-05,
      "loss": 1.1271,
      "step": 88
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.059311495186338e-05,
      "loss": 1.1304,
      "step": 89
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.852482488956992e-05,
      "loss": 1.1108,
      "step": 90
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.649797336124615e-05,
      "loss": 1.0248,
      "step": 91
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.45139266054715e-05,
      "loss": 1.1286,
      "step": 92
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.257402200743821e-05,
      "loss": 1.1333,
      "step": 93
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0679567197461134e-05,
      "loss": 1.0761,
      "step": 94
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8831839169543996e-05,
      "loss": 1.0164,
      "step": 95
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7032083420597e-05,
      "loss": 1.0243,
      "step": 96
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.528151311088537e-05,
      "loss": 1.1018,
      "step": 97
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3581308246275103e-05,
      "loss": 0.9879,
      "step": 98
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1932614882827197e-05,
      "loss": 1.1489,
      "step": 99
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.03365443542764e-05,
      "loss": 1.1236,
      "step": 100
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.879417252291502e-05,
      "loss": 1.1755,
      "step": 101
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.730653905438714e-05,
      "loss": 1.1681,
      "step": 102
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.587464671688187e-05,
      "loss": 0.9978,
      "step": 103
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4499460705197998e-05,
      "loss": 1.1827,
      "step": 104
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3181907990135622e-05,
      "loss": 1.1735,
      "step": 105
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1922876693653585e-05,
      "loss": 1.0854,
      "step": 106
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0723215490213634e-05,
      "loss": 1.0449,
      "step": 107
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.583733034714981e-06,
      "loss": 1.0684,
      "step": 108
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.505197417404687e-06,
      "loss": 1.2016,
      "step": 109
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.488335646131628e-06,
      "loss": 1.0506,
      "step": 110
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.533833156292679e-06,
      "loss": 1.0901,
      "step": 111
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.6423333488018095e-06,
      "loss": 1.0818,
      "step": 112
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.8144371563930476e-06,
      "loss": 1.0643,
      "step": 113
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.050702638550275e-06,
      "loss": 1.0642,
      "step": 114
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.3516446053363015e-06,
      "loss": 1.0714,
      "step": 115
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.717734270375272e-06,
      "loss": 1.1996,
      "step": 116
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1493989332218468e-06,
      "loss": 1.0276,
      "step": 117
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.6470216913317626e-06,
      "loss": 1.0351,
      "step": 118
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2109411818274852e-06,
      "loss": 0.9994,
      "step": 119
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.41451353233369e-07,
      "loss": 1.0391,
      "step": 120
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.388012673338661e-07,
      "loss": 0.996,
      "step": 121
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.0319493128866396e-07,
      "loss": 1.1088,
      "step": 122
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3479116011769767e-07,
      "loss": 1.0071,
      "step": 123
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.370346964876036e-08,
      "loss": 1.0029,
      "step": 124
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.0194,
      "step": 125
    },
    {
      "epoch": 1.0,
      "step": 125,
      "total_flos": 2.302215965166797e+16,
      "train_loss": 1.1489679989814758,
      "train_runtime": 762.0881,
      "train_samples_per_second": 2.624,
      "train_steps_per_second": 0.164
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 2.302215965166797e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}