{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 189,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_loss": 3.201144218444824,
      "eval_runtime": 137.3071,
      "eval_samples_per_second": 141.697,
      "eval_steps_per_second": 1.107,
      "step": 0
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 0.1918456107378006,
      "learning_rate": 0.0001,
      "loss": 3.2274,
      "step": 1
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 0.21201364696025848,
      "learning_rate": 0.0001,
      "loss": 2.9728,
      "step": 2
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.1865563839673996,
      "learning_rate": 0.0001,
      "loss": 3.1107,
      "step": 3
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 0.256558358669281,
      "learning_rate": 0.0001,
      "loss": 3.1054,
      "step": 4
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 0.30679622292518616,
      "learning_rate": 0.0001,
      "loss": 3.1735,
      "step": 5
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.27670395374298096,
      "learning_rate": 0.0001,
      "loss": 3.175,
      "step": 6
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.29917973279953003,
      "learning_rate": 0.0001,
      "loss": 3.0947,
      "step": 7
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 0.28829720616340637,
      "learning_rate": 0.0001,
      "loss": 2.9762,
      "step": 8
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.363932728767395,
      "learning_rate": 0.0001,
      "loss": 3.0589,
      "step": 9
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 0.3397577702999115,
      "learning_rate": 0.0001,
      "loss": 3.0165,
      "step": 10
    },
    {
      "epoch": 0.1746031746031746,
      "grad_norm": 0.3906390368938446,
      "learning_rate": 0.0001,
      "loss": 2.9656,
      "step": 11
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.39602699875831604,
      "learning_rate": 0.0001,
      "loss": 2.9934,
      "step": 12
    },
    {
      "epoch": 0.20634920634920634,
      "grad_norm": 0.5025639533996582,
      "learning_rate": 0.0001,
      "loss": 2.9371,
      "step": 13
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.41868922114372253,
      "learning_rate": 0.0001,
      "loss": 2.8788,
      "step": 14
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.4148877263069153,
      "learning_rate": 0.0001,
      "loss": 2.8633,
      "step": 15
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.36584576964378357,
      "learning_rate": 0.0001,
      "loss": 2.7781,
      "step": 16
    },
    {
      "epoch": 0.2698412698412698,
      "grad_norm": 0.5037583112716675,
      "learning_rate": 0.0001,
      "loss": 2.7633,
      "step": 17
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.37624871730804443,
      "learning_rate": 0.0001,
      "loss": 2.7114,
      "step": 18
    },
    {
      "epoch": 0.30158730158730157,
      "grad_norm": 0.3943127989768982,
      "learning_rate": 0.0001,
      "loss": 2.7029,
      "step": 19
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 0.300891250371933,
      "learning_rate": 0.0001,
      "loss": 2.5994,
      "step": 20
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.2970874309539795,
      "learning_rate": 0.0001,
      "loss": 2.6166,
      "step": 21
    },
    {
      "epoch": 0.3492063492063492,
      "grad_norm": 0.29132720828056335,
      "learning_rate": 0.0001,
      "loss": 2.627,
      "step": 22
    },
    {
      "epoch": 0.36507936507936506,
      "grad_norm": 0.259672075510025,
      "learning_rate": 0.0001,
      "loss": 2.6551,
      "step": 23
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.3438767194747925,
      "learning_rate": 0.0001,
      "loss": 2.62,
      "step": 24
    },
    {
      "epoch": 0.3968253968253968,
      "grad_norm": 0.36698848009109497,
      "learning_rate": 0.0001,
      "loss": 2.5411,
      "step": 25
    },
    {
      "epoch": 0.4126984126984127,
      "grad_norm": 0.500142514705658,
      "learning_rate": 0.0001,
      "loss": 2.5366,
      "step": 26
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3668989837169647,
      "learning_rate": 0.0001,
      "loss": 2.5864,
      "step": 27
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.5424588322639465,
      "learning_rate": 0.0001,
      "loss": 2.5303,
      "step": 28
    },
    {
      "epoch": 0.4603174603174603,
      "grad_norm": 0.4026002585887909,
      "learning_rate": 0.0001,
      "loss": 2.4917,
      "step": 29
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.5646772384643555,
      "learning_rate": 0.0001,
      "loss": 2.4438,
      "step": 30
    },
    {
      "epoch": 0.49206349206349204,
      "grad_norm": 0.43536150455474854,
      "learning_rate": 0.0001,
      "loss": 2.4743,
      "step": 31
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.34031543135643005,
      "learning_rate": 0.0001,
      "loss": 2.4207,
      "step": 32
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.30232375860214233,
      "learning_rate": 0.0001,
      "loss": 2.4499,
      "step": 33
    },
    {
      "epoch": 0.5396825396825397,
      "grad_norm": 0.31755775213241577,
      "learning_rate": 0.0001,
      "loss": 2.2954,
      "step": 34
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.2854190170764923,
      "learning_rate": 0.0001,
      "loss": 2.4148,
      "step": 35
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.2745571434497833,
      "learning_rate": 0.0001,
      "loss": 2.2658,
      "step": 36
    },
    {
      "epoch": 0.5873015873015873,
      "grad_norm": 0.26832568645477295,
      "learning_rate": 0.0001,
      "loss": 2.4336,
      "step": 37
    },
    {
      "epoch": 0.6031746031746031,
      "grad_norm": 0.2571115493774414,
      "learning_rate": 0.0001,
      "loss": 2.3325,
      "step": 38
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.27978894114494324,
      "learning_rate": 0.0001,
      "loss": 2.3623,
      "step": 39
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.27634117007255554,
      "learning_rate": 0.0001,
      "loss": 2.3947,
      "step": 40
    },
    {
      "epoch": 0.6507936507936508,
      "grad_norm": 0.2856747806072235,
      "learning_rate": 0.0001,
      "loss": 2.3065,
      "step": 41
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.273630827665329,
      "learning_rate": 0.0001,
      "loss": 2.2969,
      "step": 42
    },
    {
      "epoch": 0.6825396825396826,
      "grad_norm": 0.294461190700531,
      "learning_rate": 0.0001,
      "loss": 2.3315,
      "step": 43
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 0.27730676531791687,
      "learning_rate": 0.0001,
      "loss": 2.2656,
      "step": 44
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.28087306022644043,
      "learning_rate": 0.0001,
      "loss": 2.1831,
      "step": 45
    },
    {
      "epoch": 0.7301587301587301,
      "grad_norm": 0.2754216194152832,
      "learning_rate": 0.0001,
      "loss": 2.2577,
      "step": 46
    },
    {
      "epoch": 0.746031746031746,
      "grad_norm": 0.29807186126708984,
      "learning_rate": 0.0001,
      "loss": 2.3723,
      "step": 47
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.3020806908607483,
      "learning_rate": 0.0001,
      "loss": 2.309,
      "step": 48
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.2983008027076721,
      "learning_rate": 0.0001,
      "loss": 2.1748,
      "step": 49
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 0.30773478746414185,
      "learning_rate": 0.0001,
      "loss": 2.2758,
      "step": 50
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.30065926909446716,
      "learning_rate": 0.0001,
      "loss": 2.2587,
      "step": 51
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 0.3026188313961029,
      "learning_rate": 0.0001,
      "loss": 2.1818,
      "step": 52
    },
    {
      "epoch": 0.8412698412698413,
      "grad_norm": 0.30180782079696655,
      "learning_rate": 0.0001,
      "loss": 2.1304,
      "step": 53
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.29865095019340515,
      "learning_rate": 0.0001,
      "loss": 2.2356,
      "step": 54
    },
    {
      "epoch": 0.873015873015873,
      "grad_norm": 0.30642348527908325,
      "learning_rate": 0.0001,
      "loss": 2.2411,
      "step": 55
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.30322977900505066,
      "learning_rate": 0.0001,
      "loss": 2.2252,
      "step": 56
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.2848075032234192,
      "learning_rate": 0.0001,
      "loss": 2.1687,
      "step": 57
    },
    {
      "epoch": 0.9206349206349206,
      "grad_norm": 0.2916617691516876,
      "learning_rate": 0.0001,
      "loss": 2.1998,
      "step": 58
    },
    {
      "epoch": 0.9365079365079365,
      "grad_norm": 0.2930757999420166,
      "learning_rate": 0.0001,
      "loss": 2.2222,
      "step": 59
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.28044334053993225,
      "learning_rate": 0.0001,
      "loss": 2.1614,
      "step": 60
    },
    {
      "epoch": 0.9682539682539683,
      "grad_norm": 0.29108643531799316,
      "learning_rate": 0.0001,
      "loss": 2.2684,
      "step": 61
    },
    {
      "epoch": 0.9841269841269841,
      "grad_norm": 0.2764103412628174,
      "learning_rate": 0.0001,
      "loss": 2.152,
      "step": 62
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.290540486574173,
      "learning_rate": 0.0001,
      "loss": 2.2189,
      "step": 63
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.1553854942321777,
      "eval_runtime": 134.4627,
      "eval_samples_per_second": 144.694,
      "eval_steps_per_second": 1.13,
      "step": 63
    },
    {
      "epoch": 1.0158730158730158,
      "grad_norm": 0.28722119331359863,
      "learning_rate": 0.0001,
      "loss": 2.119,
      "step": 64
    },
    {
      "epoch": 1.0317460317460316,
      "grad_norm": 0.2941075265407562,
      "learning_rate": 0.0001,
      "loss": 2.1355,
      "step": 65
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.27956002950668335,
      "learning_rate": 0.0001,
      "loss": 2.0956,
      "step": 66
    },
    {
      "epoch": 1.0634920634920635,
      "grad_norm": 0.2902751863002777,
      "learning_rate": 0.0001,
      "loss": 2.1677,
      "step": 67
    },
    {
      "epoch": 1.0793650793650793,
      "grad_norm": 0.28545236587524414,
      "learning_rate": 0.0001,
      "loss": 2.1038,
      "step": 68
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.28611037135124207,
      "learning_rate": 0.0001,
      "loss": 2.0701,
      "step": 69
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.2909831404685974,
      "learning_rate": 0.0001,
      "loss": 2.1483,
      "step": 70
    },
    {
      "epoch": 1.126984126984127,
      "grad_norm": 0.29801449179649353,
      "learning_rate": 0.0001,
      "loss": 2.0127,
      "step": 71
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.3016774356365204,
      "learning_rate": 0.0001,
      "loss": 2.072,
      "step": 72
    },
    {
      "epoch": 1.1587301587301586,
      "grad_norm": 0.302207887172699,
      "learning_rate": 0.0001,
      "loss": 2.0818,
      "step": 73
    },
    {
      "epoch": 1.1746031746031746,
      "grad_norm": 0.3024630844593048,
      "learning_rate": 0.0001,
      "loss": 2.0775,
      "step": 74
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.3113912045955658,
      "learning_rate": 0.0001,
      "loss": 2.0484,
      "step": 75
    },
    {
      "epoch": 1.2063492063492063,
      "grad_norm": 0.3100714385509491,
      "learning_rate": 0.0001,
      "loss": 2.0322,
      "step": 76
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.31157463788986206,
      "learning_rate": 0.0001,
      "loss": 2.0123,
      "step": 77
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.30897048115730286,
      "learning_rate": 0.0001,
      "loss": 2.0196,
      "step": 78
    },
    {
      "epoch": 1.253968253968254,
      "grad_norm": 0.32494208216667175,
      "learning_rate": 0.0001,
      "loss": 2.1164,
      "step": 79
    },
    {
      "epoch": 1.2698412698412698,
      "grad_norm": 0.3228481113910675,
      "learning_rate": 0.0001,
      "loss": 2.0119,
      "step": 80
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.31433093547821045,
      "learning_rate": 0.0001,
      "loss": 1.9773,
      "step": 81
    },
    {
      "epoch": 1.3015873015873016,
      "grad_norm": 0.33841848373413086,
      "learning_rate": 0.0001,
      "loss": 2.0676,
      "step": 82
    },
    {
      "epoch": 1.3174603174603174,
      "grad_norm": 0.33233773708343506,
      "learning_rate": 0.0001,
      "loss": 2.0717,
      "step": 83
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.34447962045669556,
      "learning_rate": 0.0001,
      "loss": 2.1348,
      "step": 84
    },
    {
      "epoch": 1.3492063492063493,
      "grad_norm": 0.33957433700561523,
      "learning_rate": 0.0001,
      "loss": 2.0339,
      "step": 85
    },
    {
      "epoch": 1.3650793650793651,
      "grad_norm": 0.3519391715526581,
      "learning_rate": 0.0001,
      "loss": 2.0317,
      "step": 86
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.3266676068305969,
      "learning_rate": 0.0001,
      "loss": 1.9932,
      "step": 87
    },
    {
      "epoch": 1.3968253968253967,
      "grad_norm": 0.3306258022785187,
      "learning_rate": 0.0001,
      "loss": 1.9695,
      "step": 88
    },
    {
      "epoch": 1.4126984126984126,
      "grad_norm": 0.3315640389919281,
      "learning_rate": 0.0001,
      "loss": 1.9975,
      "step": 89
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.33888551592826843,
      "learning_rate": 0.0001,
      "loss": 2.0804,
      "step": 90
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.3356088399887085,
      "learning_rate": 0.0001,
      "loss": 2.0882,
      "step": 91
    },
    {
      "epoch": 1.4603174603174602,
      "grad_norm": 0.3448535203933716,
      "learning_rate": 0.0001,
      "loss": 2.0641,
      "step": 92
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.33544135093688965,
      "learning_rate": 0.0001,
      "loss": 2.0657,
      "step": 93
    },
    {
      "epoch": 1.492063492063492,
      "grad_norm": 0.32962003350257874,
      "learning_rate": 0.0001,
      "loss": 1.9702,
      "step": 94
    },
    {
      "epoch": 1.507936507936508,
      "grad_norm": 0.3348037898540497,
      "learning_rate": 0.0001,
      "loss": 2.0495,
      "step": 95
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.35935646295547485,
      "learning_rate": 0.0001,
      "loss": 2.0343,
      "step": 96
    },
    {
      "epoch": 1.5396825396825395,
      "grad_norm": 0.35089877247810364,
      "learning_rate": 0.0001,
      "loss": 1.9913,
      "step": 97
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.35951006412506104,
      "learning_rate": 0.0001,
      "loss": 2.036,
      "step": 98
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.3543176054954529,
      "learning_rate": 0.0001,
      "loss": 2.0005,
      "step": 99
    },
    {
      "epoch": 1.5873015873015874,
      "grad_norm": 0.34387317299842834,
      "learning_rate": 0.0001,
      "loss": 2.0283,
      "step": 100
    },
    {
      "epoch": 1.6031746031746033,
      "grad_norm": 0.3506092429161072,
      "learning_rate": 0.0001,
      "loss": 2.0301,
      "step": 101
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.3446710705757141,
      "learning_rate": 0.0001,
      "loss": 1.9749,
      "step": 102
    },
    {
      "epoch": 1.6349206349206349,
      "grad_norm": 0.3415977656841278,
      "learning_rate": 0.0001,
      "loss": 1.9853,
      "step": 103
    },
    {
      "epoch": 1.6507936507936507,
      "grad_norm": 0.3609831631183624,
      "learning_rate": 0.0001,
      "loss": 2.0477,
      "step": 104
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.35015106201171875,
      "learning_rate": 0.0001,
      "loss": 2.0356,
      "step": 105
    },
    {
      "epoch": 1.6825396825396826,
      "grad_norm": 0.3593216836452484,
      "learning_rate": 0.0001,
      "loss": 1.8311,
      "step": 106
    },
    {
      "epoch": 1.6984126984126984,
      "grad_norm": 0.35230639576911926,
      "learning_rate": 0.0001,
      "loss": 1.9562,
      "step": 107
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.3519164025783539,
      "learning_rate": 0.0001,
      "loss": 2.0257,
      "step": 108
    },
    {
      "epoch": 1.7301587301587302,
      "grad_norm": 0.3627997934818268,
      "learning_rate": 0.0001,
      "loss": 2.0012,
      "step": 109
    },
    {
      "epoch": 1.746031746031746,
      "grad_norm": 0.37876084446907043,
      "learning_rate": 0.0001,
      "loss": 1.9746,
      "step": 110
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.37692707777023315,
      "learning_rate": 0.0001,
      "loss": 2.0422,
      "step": 111
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.3628651201725006,
      "learning_rate": 0.0001,
      "loss": 1.9981,
      "step": 112
    },
    {
      "epoch": 1.7936507936507935,
      "grad_norm": 0.35194242000579834,
      "learning_rate": 0.0001,
      "loss": 1.9343,
      "step": 113
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.36310839653015137,
      "learning_rate": 0.0001,
      "loss": 2.0421,
      "step": 114
    },
    {
      "epoch": 1.8253968253968254,
      "grad_norm": 0.3339640200138092,
      "learning_rate": 0.0001,
      "loss": 1.9606,
      "step": 115
    },
    {
      "epoch": 1.8412698412698414,
      "grad_norm": 0.3632456958293915,
      "learning_rate": 0.0001,
      "loss": 1.8558,
      "step": 116
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.36308878660202026,
      "learning_rate": 0.0001,
      "loss": 2.0127,
      "step": 117
    },
    {
      "epoch": 1.873015873015873,
      "grad_norm": 0.3537601828575134,
      "learning_rate": 0.0001,
      "loss": 1.9704,
      "step": 118
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.3581252098083496,
      "learning_rate": 0.0001,
      "loss": 1.9086,
      "step": 119
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.37275415658950806,
      "learning_rate": 0.0001,
      "loss": 2.0914,
      "step": 120
    },
    {
      "epoch": 1.9206349206349205,
      "grad_norm": 0.36517035961151123,
      "learning_rate": 0.0001,
      "loss": 1.9529,
      "step": 121
    },
    {
      "epoch": 1.9365079365079365,
      "grad_norm": 0.3566952049732208,
      "learning_rate": 0.0001,
      "loss": 1.8498,
      "step": 122
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.36236587166786194,
      "learning_rate": 0.0001,
      "loss": 1.9652,
      "step": 123
    },
    {
      "epoch": 1.9682539682539684,
      "grad_norm": 0.3652929663658142,
      "learning_rate": 0.0001,
      "loss": 2.0085,
      "step": 124
    },
    {
      "epoch": 1.9841269841269842,
      "grad_norm": 0.3546443581581116,
      "learning_rate": 0.0001,
      "loss": 1.9192,
      "step": 125
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3752649128437042,
      "learning_rate": 0.0001,
      "loss": 1.9932,
      "step": 126
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.9884382486343384,
      "eval_runtime": 134.41,
      "eval_samples_per_second": 144.751,
      "eval_steps_per_second": 1.131,
      "step": 126
    },
    {
      "epoch": 2.015873015873016,
      "grad_norm": 0.35680314898490906,
      "learning_rate": 0.0001,
      "loss": 2.0274,
      "step": 127
    },
    {
      "epoch": 2.0317460317460316,
      "grad_norm": 0.34379494190216064,
      "learning_rate": 0.0001,
      "loss": 1.944,
      "step": 128
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 0.351840615272522,
      "learning_rate": 0.0001,
      "loss": 1.9053,
      "step": 129
    },
    {
      "epoch": 2.0634920634920633,
      "grad_norm": 0.38462555408477783,
      "learning_rate": 0.0001,
      "loss": 1.9082,
      "step": 130
    },
    {
      "epoch": 2.0793650793650795,
      "grad_norm": 0.37032756209373474,
      "learning_rate": 0.0001,
      "loss": 1.9048,
      "step": 131
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.36423760652542114,
      "learning_rate": 0.0001,
      "loss": 1.9041,
      "step": 132
    },
    {
      "epoch": 2.111111111111111,
      "grad_norm": 0.36103999614715576,
      "learning_rate": 0.0001,
      "loss": 1.7832,
      "step": 133
    },
    {
      "epoch": 2.126984126984127,
      "grad_norm": 0.36970341205596924,
      "learning_rate": 0.0001,
      "loss": 1.8562,
      "step": 134
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.38281646370887756,
      "learning_rate": 0.0001,
      "loss": 1.8671,
      "step": 135
    },
    {
      "epoch": 2.1587301587301586,
      "grad_norm": 0.4053700864315033,
      "learning_rate": 0.0001,
      "loss": 2.0125,
      "step": 136
    },
    {
      "epoch": 2.1746031746031744,
      "grad_norm": 0.40937232971191406,
      "learning_rate": 0.0001,
      "loss": 1.9053,
      "step": 137
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.39173007011413574,
      "learning_rate": 0.0001,
      "loss": 1.9645,
      "step": 138
    },
    {
      "epoch": 2.2063492063492065,
      "grad_norm": 0.39559757709503174,
      "learning_rate": 0.0001,
      "loss": 1.9285,
      "step": 139
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.4081740975379944,
      "learning_rate": 0.0001,
      "loss": 1.8501,
      "step": 140
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 0.4095621705055237,
      "learning_rate": 0.0001,
      "loss": 1.9005,
      "step": 141
    },
    {
      "epoch": 2.253968253968254,
      "grad_norm": 0.4242890179157257,
      "learning_rate": 0.0001,
      "loss": 1.8266,
      "step": 142
    },
    {
      "epoch": 2.2698412698412698,
      "grad_norm": 0.4077770709991455,
      "learning_rate": 0.0001,
      "loss": 1.8656,
      "step": 143
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.4218343496322632,
      "learning_rate": 0.0001,
      "loss": 1.9931,
      "step": 144
    },
    {
      "epoch": 2.3015873015873014,
      "grad_norm": 0.3991089463233948,
      "learning_rate": 0.0001,
      "loss": 1.8629,
      "step": 145
    },
    {
      "epoch": 2.317460317460317,
      "grad_norm": 0.42081835865974426,
      "learning_rate": 0.0001,
      "loss": 1.8855,
      "step": 146
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.4178907573223114,
      "learning_rate": 0.0001,
      "loss": 1.8834,
      "step": 147
    },
    {
      "epoch": 2.3492063492063493,
      "grad_norm": 0.4098721146583557,
      "learning_rate": 0.0001,
      "loss": 1.7691,
      "step": 148
    },
    {
      "epoch": 2.365079365079365,
      "grad_norm": 0.4463600814342499,
      "learning_rate": 0.0001,
      "loss": 2.0333,
      "step": 149
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.4598867893218994,
      "learning_rate": 0.0001,
      "loss": 1.8711,
      "step": 150
    },
    {
      "epoch": 2.3968253968253967,
      "grad_norm": 0.42520642280578613,
      "learning_rate": 0.0001,
      "loss": 1.8435,
      "step": 151
    },
    {
      "epoch": 2.4126984126984126,
      "grad_norm": 0.43913593888282776,
      "learning_rate": 0.0001,
      "loss": 1.9094,
      "step": 152
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.4239555299282074,
      "learning_rate": 0.0001,
      "loss": 1.795,
      "step": 153
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.43195414543151855,
      "learning_rate": 0.0001,
      "loss": 1.9467,
      "step": 154
    },
    {
      "epoch": 2.4603174603174605,
      "grad_norm": 0.42905962467193604,
      "learning_rate": 0.0001,
      "loss": 1.8613,
      "step": 155
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.44274038076400757,
      "learning_rate": 0.0001,
      "loss": 1.9131,
      "step": 156
    },
    {
      "epoch": 2.492063492063492,
      "grad_norm": 0.42327380180358887,
      "learning_rate": 0.0001,
      "loss": 1.8945,
      "step": 157
    },
    {
      "epoch": 2.507936507936508,
      "grad_norm": 0.43506136536598206,
      "learning_rate": 0.0001,
      "loss": 1.8626,
      "step": 158
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 0.4368724524974823,
      "learning_rate": 0.0001,
      "loss": 1.8973,
      "step": 159
    },
    {
      "epoch": 2.5396825396825395,
      "grad_norm": 0.43993279337882996,
      "learning_rate": 0.0001,
      "loss": 1.8404,
      "step": 160
    },
    {
      "epoch": 2.5555555555555554,
      "grad_norm": 0.43752744793891907,
      "learning_rate": 0.0001,
      "loss": 1.9374,
      "step": 161
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.4344784915447235,
      "learning_rate": 0.0001,
      "loss": 1.8943,
      "step": 162
    },
    {
      "epoch": 2.5873015873015874,
      "grad_norm": 0.41896679997444153,
      "learning_rate": 0.0001,
      "loss": 1.8438,
      "step": 163
    },
    {
      "epoch": 2.6031746031746033,
      "grad_norm": 0.43420085310935974,
      "learning_rate": 0.0001,
      "loss": 1.9431,
      "step": 164
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.444305419921875,
      "learning_rate": 0.0001,
      "loss": 1.8149,
      "step": 165
    },
    {
      "epoch": 2.634920634920635,
      "grad_norm": 0.44758594036102295,
      "learning_rate": 0.0001,
      "loss": 1.8166,
      "step": 166
    },
    {
      "epoch": 2.6507936507936507,
      "grad_norm": 0.44555145502090454,
      "learning_rate": 0.0001,
      "loss": 1.9017,
      "step": 167
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.4599977135658264,
      "learning_rate": 0.0001,
      "loss": 1.8222,
      "step": 168
    },
    {
      "epoch": 2.682539682539683,
      "grad_norm": 0.4442943036556244,
      "learning_rate": 0.0001,
      "loss": 1.8178,
      "step": 169
    },
    {
      "epoch": 2.6984126984126986,
      "grad_norm": 0.4303114116191864,
      "learning_rate": 0.0001,
      "loss": 1.8585,
      "step": 170
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.45859652757644653,
      "learning_rate": 0.0001,
      "loss": 1.8548,
      "step": 171
    },
    {
      "epoch": 2.7301587301587302,
      "grad_norm": 0.449211448431015,
      "learning_rate": 0.0001,
      "loss": 1.7996,
      "step": 172
    },
    {
      "epoch": 2.746031746031746,
      "grad_norm": 0.458112508058548,
      "learning_rate": 0.0001,
      "loss": 1.8924,
      "step": 173
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.4440052807331085,
      "learning_rate": 0.0001,
      "loss": 1.8414,
      "step": 174
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.4355706572532654,
      "learning_rate": 0.0001,
      "loss": 1.8404,
      "step": 175
    },
    {
      "epoch": 2.7936507936507935,
      "grad_norm": 0.4662310779094696,
      "learning_rate": 0.0001,
      "loss": 1.9346,
      "step": 176
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 0.44040319323539734,
      "learning_rate": 0.0001,
      "loss": 1.8736,
      "step": 177
    },
    {
      "epoch": 2.825396825396825,
      "grad_norm": 0.4506472945213318,
      "learning_rate": 0.0001,
      "loss": 1.9329,
      "step": 178
    },
    {
      "epoch": 2.8412698412698414,
      "grad_norm": 0.44710540771484375,
      "learning_rate": 0.0001,
      "loss": 1.8787,
      "step": 179
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.43612954020500183,
      "learning_rate": 0.0001,
      "loss": 1.8405,
      "step": 180
    },
    {
      "epoch": 2.873015873015873,
      "grad_norm": 0.4578387439250946,
      "learning_rate": 0.0001,
      "loss": 1.746,
      "step": 181
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.4509958326816559,
      "learning_rate": 0.0001,
      "loss": 1.8539,
      "step": 182
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 0.44833552837371826,
      "learning_rate": 0.0001,
      "loss": 1.8407,
      "step": 183
    },
    {
      "epoch": 2.9206349206349205,
      "grad_norm": 0.4552953541278839,
      "learning_rate": 0.0001,
      "loss": 1.8312,
      "step": 184
    },
    {
      "epoch": 2.9365079365079367,
      "grad_norm": 0.4556235671043396,
      "learning_rate": 0.0001,
      "loss": 1.8324,
      "step": 185
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.44649648666381836,
      "learning_rate": 0.0001,
      "loss": 1.9377,
      "step": 186
    },
    {
      "epoch": 2.9682539682539684,
      "grad_norm": 0.47388994693756104,
      "learning_rate": 0.0001,
      "loss": 1.9287,
      "step": 187
    },
    {
      "epoch": 2.984126984126984,
      "grad_norm": 0.43568143248558044,
      "learning_rate": 0.0001,
      "loss": 1.854,
      "step": 188
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.44688650965690613,
      "learning_rate": 0.0001,
      "loss": 1.8136,
      "step": 189
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.9275089502334595,
      "eval_runtime": 134.3105,
      "eval_samples_per_second": 144.858,
      "eval_steps_per_second": 1.132,
      "step": 189
    }
  ],
  "logging_steps": 1,
  "max_steps": 504,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0791279677637919e+18,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}