{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0857142857142856,
  "eval_steps": 500,
  "global_step": 165,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 0.7566928863525391,
      "learning_rate": 0.0,
      "loss": 0.8968,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 0.8072069883346558,
      "learning_rate": 4e-05,
      "loss": 0.9227,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.8303298950195312,
      "learning_rate": 8e-05,
      "loss": 0.9508,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 0.9258667826652527,
      "learning_rate": 0.00012,
      "loss": 0.9527,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.9558561444282532,
      "learning_rate": 0.00016,
      "loss": 0.9178,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.47254669666290283,
      "learning_rate": 0.0002,
      "loss": 0.7227,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5736677646636963,
      "learning_rate": 0.00019955654101995565,
      "loss": 0.7945,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.6585658192634583,
      "learning_rate": 0.00019911308203991133,
      "loss": 0.9034,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.6045550107955933,
      "learning_rate": 0.00019866962305986697,
      "loss": 0.8399,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.4790070056915283,
      "learning_rate": 0.00019822616407982261,
      "loss": 0.8234,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.3827012777328491,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.8281,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.31580132246017456,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.7572,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.2703302502632141,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.7605,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.2565660774707794,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.8042,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.19942161440849304,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.7443,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.21022649109363556,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.6641,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.2277892380952835,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.7432,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.33732736110687256,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.7787,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.27139249444007874,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.7951,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.2788768410682678,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.719,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.2770022451877594,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.7604,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.2961127460002899,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.7834,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.42819708585739136,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.7302,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.2841340899467468,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.7261,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.2913196384906769,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.7212,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3300360143184662,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.6494,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.27701273560523987,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.6838,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.2448320835828781,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.6998,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.2562633454799652,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.7449,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.2887221574783325,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.6676,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.2212107628583908,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.7629,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.26358944177627563,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.7497,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.19833838939666748,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.7787,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.21352550387382507,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.7513,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2602783739566803,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.7423,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.25566816329956055,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.7049,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.26156026124954224,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.7342,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.2607591450214386,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.6492,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.2538753151893616,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.6907,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.25195640325546265,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.7535,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.2823958098888397,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.6653,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.2609056532382965,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.6967,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.21727432310581207,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.7071,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.28144368529319763,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.7169,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.23335450887680054,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.7365,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.2892163097858429,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.6403,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.2446267455816269,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.6869,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.24830380082130432,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.6407,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.32878631353378296,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.6962,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.23604710400104523,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.7427,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.20495985448360443,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.6272,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.21541891992092133,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.7157,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.2712082266807556,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.7132,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2737255096435547,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.7115,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3590952455997467,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.7041,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.22194194793701172,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.6017,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2181357890367508,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.7292,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.2543794512748718,
      "learning_rate": 0.000176940133037694,
      "loss": 0.7028,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.33169296383857727,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.6646,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.27475646138191223,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.7889,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.2369152307510376,
      "learning_rate": 0.000175609756097561,
      "loss": 0.7018,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.21613454818725586,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.6715,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.20882739126682281,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.6892,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.2187095731496811,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.6436,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.2040148377418518,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.6512,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.2536020874977112,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.7019,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.24403820931911469,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.6723,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.2113356590270996,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.7119,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.2046196013689041,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.7191,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.22032175958156586,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.7159,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.2522450387477875,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.7039,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.2568543553352356,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.6842,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.21719902753829956,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.6942,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.22592927515506744,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.7966,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.241453617811203,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.7412,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.23723702132701874,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.7148,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.20009562373161316,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.7143,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.2050897777080536,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.6766,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.22315199673175812,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.7,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.20680196583271027,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.6356,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.23944680392742157,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.6559,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.22115568816661835,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.6644,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.2396654337644577,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.6972,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.2545161545276642,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.7242,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.2548670172691345,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.756,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.2570771872997284,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.7392,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.25188854336738586,
      "learning_rate": 0.000164079822616408,
      "loss": 0.7504,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.24089300632476807,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.6831,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.21377258002758026,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.6904,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.22940956056118011,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.7223,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.23013509809970856,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.6743,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.2341698855161667,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.6031,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.21239612996578217,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.6043,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.21493980288505554,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.6019,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.2181602418422699,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.6601,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.2473670393228531,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.7301,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.23289376497268677,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7493,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.22319060564041138,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.7057,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.24551022052764893,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.6467,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.21545983850955963,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.7107,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.2510841190814972,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.658,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.23200248181819916,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.7351,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.2180459201335907,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.6992,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.23387350142002106,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.7398,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.22272081673145294,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.6528,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.22667521238327026,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.76,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.2085743099451065,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.6842,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.24620012938976288,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.738,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.23256433010101318,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.6475,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.2518521249294281,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.6764,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.22852903604507446,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.6797,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.22933068871498108,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.7095,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.22621572017669678,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.6587,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.24995188415050507,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.7068,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.25118041038513184,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.6904,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.21053656935691833,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.549,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.2095535695552826,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.6875,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.21824686229228973,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.6729,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.2307584136724472,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.6493,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.22242283821105957,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.668,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.22179292142391205,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.6386,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.23222969472408295,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.6712,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.2495681792497635,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.6295,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.2647445797920227,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.7005,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.24217277765274048,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.6311,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.2461085021495819,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.6446,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.2610090970993042,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.7045,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.2201678454875946,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.6436,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.22592248022556305,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.6608,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.22529453039169312,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.6401,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.2538209855556488,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.6788,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.22796444594860077,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.7022,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.20975171029567719,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.6779,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.22414448857307434,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.7459,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.270942747592926,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.6682,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.25628402829170227,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.6759,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.2702762484550476,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.7287,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.23527158796787262,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.6365,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.2638787031173706,
      "learning_rate": 0.000141019955654102,
      "loss": 0.7456,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.2431294023990631,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.655,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.26322004199028015,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.6694,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.22624383866786957,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.6025,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.20489341020584106,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.6544,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.23127716779708862,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.748,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.23263822495937347,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.674,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.23276172578334808,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.7082,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.2461167722940445,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.7059,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.24031785130500793,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.6732,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.21587732434272766,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.6605,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.22994357347488403,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.6609,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.2200823873281479,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.7032,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.26850587129592896,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.7507,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.23838046193122864,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.6686,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.21873874962329865,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.759,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.22888495028018951,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.5565,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.21489110589027405,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.6417,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.23249667882919312,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.6282,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.2237980216741562,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.68,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.2389901876449585,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.6522,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.23192445933818817,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.6478,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.25663626194000244,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.7291,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.22465288639068604,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.6243,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.22050045430660248,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.6577,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.2221308797597885,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.6401,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.24798862636089325,
      "learning_rate": 0.000129490022172949,
      "loss": 0.6871,
      "step": 165
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.594081144602624e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}