{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.989010989010989,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.1275893449783325,
      "learning_rate": 0.0,
      "loss": 2.447,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.2668907642364502,
      "learning_rate": 4e-05,
      "loss": 2.4154,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.4068100452423096,
      "learning_rate": 8e-05,
      "loss": 2.6633,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 2.1181106567382812,
      "learning_rate": 0.00012,
      "loss": 2.957,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.079303026199341,
      "learning_rate": 0.00016,
      "loss": 2.5694,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.6251254081726074,
      "learning_rate": 0.0002,
      "loss": 2.432,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.012319803237915,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.5976,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.7803969383239746,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.477,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.9013245701789856,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.5948,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.2842018604278564,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3713,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.8976652026176453,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2224,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5004059672355652,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.3497,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.6451104283332825,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0074,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5015004277229309,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.1107,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4315488636493683,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.0685,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.41801849007606506,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.0842,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.4290252923965454,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0539,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.38355547189712524,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.1352,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.40958377718925476,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.2208,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.35323846340179443,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.1051,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3563601076602936,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0701,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.359203040599823,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.159,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.33008697628974915,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.9762,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3451750576496124,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.2121,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3095659911632538,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.0609,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.34046390652656555,
      "learning_rate": 0.00019113082039911309,
      "loss": 1.0292,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.2731463313102722,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.8801,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3196094334125519,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0598,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3618379831314087,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.13,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3907746374607086,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0604,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3152461051940918,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.9825,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3892799913883209,
      "learning_rate": 0.00018847006651884703,
      "loss": 1.0001,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.6721793413162231,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.059,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2930261492729187,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.0674,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2629822790622711,
      "learning_rate": 0.00018713968957871397,
      "loss": 1.0519,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3631236255168915,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.1936,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.29286670684814453,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.9896,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.25928613543510437,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.9899,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3072899878025055,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9495,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.36685264110565186,
      "learning_rate": 0.00018492239467849224,
      "loss": 1.1806,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.355631560087204,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.0414,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.2510671317577362,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9684,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.3216419517993927,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.0316,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.23034003376960754,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.928,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.3225923776626587,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9947,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.2578844130039215,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.8963,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.29851236939430237,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.1159,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.32333648204803467,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.059,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.3174646496772766,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.8918,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.315204381942749,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9506,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.2813481092453003,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.1047,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.2952252924442291,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.867,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.24716372787952423,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.8391,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.3835619390010834,
      "learning_rate": 0.0001787139689578714,
      "loss": 1.2473,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.2816176116466522,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.9678,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.26127851009368896,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.0918,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2856857478618622,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.9088,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.2850624918937683,
      "learning_rate": 0.000176940133037694,
      "loss": 1.1824,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.25489187240600586,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.0352,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.25980061292648315,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.9782,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.38467931747436523,
      "learning_rate": 0.000175609756097561,
      "loss": 1.0656,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.2775910794734955,
      "learning_rate": 0.00017516629711751663,
      "loss": 1.056,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.30244043469429016,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.9701,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.26982933282852173,
      "learning_rate": 0.00017427937915742792,
      "loss": 1.0842,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.2610529363155365,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.8568,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.30176976323127747,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.1878,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.2766951620578766,
      "learning_rate": 0.0001729490022172949,
      "loss": 1.2962,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.293035626411438,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9838,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.27515101432800293,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.9519,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3847554922103882,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.2802,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.35320615768432617,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.9431,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.2601383328437805,
      "learning_rate": 0.0001707317073170732,
      "loss": 1.0764,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.2759348750114441,
      "learning_rate": 0.00017028824833702883,
      "loss": 1.169,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.2849448621273041,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.8389,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.27154988050460815,
      "learning_rate": 0.00016940133037694015,
      "loss": 1.445,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.23120637238025665,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.9016,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.2870595455169678,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.9484,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.31415843963623047,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.0044,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.2773488461971283,
      "learning_rate": 0.00016762749445676275,
      "loss": 1.2775,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.30678775906562805,
      "learning_rate": 0.00016718403547671842,
      "loss": 1.102,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3076689839363098,
      "learning_rate": 0.00016674057649667407,
      "loss": 1.0533,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.29335227608680725,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.1136,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3012673854827881,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.9623,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3172266483306885,
      "learning_rate": 0.00016541019955654103,
      "loss": 1.0932,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.34161606431007385,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.0621,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.2700536847114563,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.9319,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3212398588657379,
      "learning_rate": 0.000164079822616408,
      "loss": 1.1078,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.28530454635620117,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9302,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3433068096637726,
      "learning_rate": 0.0001631929046563193,
      "loss": 1.0066,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.2919917404651642,
      "learning_rate": 0.00016274944567627495,
      "loss": 1.1102,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.32052382826805115,
      "learning_rate": 0.0001623059866962306,
      "loss": 1.3246,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3160792887210846,
      "learning_rate": 0.00016186252771618626,
      "loss": 1.1178,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.32350850105285645,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.9709,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.29178914427757263,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.8593,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.3640948235988617,
      "learning_rate": 0.00016053215077605322,
      "loss": 1.1563,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3233107030391693,
      "learning_rate": 0.00016008869179600887,
      "loss": 1.1142,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.24741512537002563,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.78,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.38984784483909607,
      "learning_rate": 0.00015920177383592018,
      "loss": 1.0431,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.39468371868133545,
      "learning_rate": 0.00015875831485587586,
      "loss": 1.0567,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.4342367947101593,
      "learning_rate": 0.0001583148558758315,
      "loss": 1.1111,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.35820114612579346,
      "learning_rate": 0.00015787139689578714,
      "loss": 1.0769,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.24846765398979187,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.9368,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.36143532395362854,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9289,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3192337155342102,
      "learning_rate": 0.0001565410199556541,
      "loss": 1.0965,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.29100948572158813,
      "learning_rate": 0.00015609756097560978,
      "loss": 1.01,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.28475266695022583,
      "learning_rate": 0.00015565410199556542,
      "loss": 1.0026,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.3198554515838623,
      "learning_rate": 0.00015521064301552106,
      "loss": 1.0519,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.3227159380912781,
      "learning_rate": 0.0001547671840354767,
      "loss": 1.129,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.3094928562641144,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.9207,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.34968990087509155,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.8445,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.30247947573661804,
      "learning_rate": 0.0001534368070953437,
      "loss": 1.0486,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.31378185749053955,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.9698,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.2863531708717346,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.8932,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.35312584042549133,
      "learning_rate": 0.00015210643015521066,
      "loss": 1.2283,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.32800766825675964,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.9127,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.39109963178634644,
      "learning_rate": 0.00015121951219512197,
      "loss": 1.2758,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.32078978419303894,
      "learning_rate": 0.00015077605321507762,
      "loss": 1.1391,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3119417428970337,
      "learning_rate": 0.0001503325942350333,
      "loss": 1.3061,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.36127007007598877,
      "learning_rate": 0.0001498891352549889,
      "loss": 1.1257,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.3820135295391083,
      "learning_rate": 0.00014944567627494458,
      "loss": 1.124,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.3388823866844177,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.9999,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.2975907623767853,
      "learning_rate": 0.0001485587583148559,
      "loss": 1.0155,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.26753824949264526,
      "learning_rate": 0.00014811529933481154,
      "loss": 1.0454,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.2487502247095108,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.907,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.3011381924152374,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.927,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.2729976773262024,
      "learning_rate": 0.0001467849223946785,
      "loss": 1.0346,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.2819596230983734,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.989,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.31051334738731384,
      "learning_rate": 0.0001458980044345898,
      "loss": 1.1402,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.32962939143180847,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.1213,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.27292338013648987,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.9858,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.43814074993133545,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.9997,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.3418039083480835,
      "learning_rate": 0.00014412416851441242,
      "loss": 1.1602,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.3146732449531555,
      "learning_rate": 0.00014368070953436806,
      "loss": 1.0862,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.3306737542152405,
      "learning_rate": 0.00014323725055432373,
      "loss": 1.2866,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.2804040312767029,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.838,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.4057348370552063,
      "learning_rate": 0.00014235033259423505,
      "loss": 1.2383,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.354050874710083,
      "learning_rate": 0.0001419068736141907,
      "loss": 1.0859,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3702743649482727,
      "learning_rate": 0.00014146341463414634,
      "loss": 1.0339,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.4241447150707245,
      "learning_rate": 0.000141019955654102,
      "loss": 1.0838,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.34522998332977295,
      "learning_rate": 0.00014057649667405765,
      "loss": 1.0124,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.30751296877861023,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.9647,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.2644519805908203,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.9655,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.30129289627075195,
      "learning_rate": 0.00013924611973392464,
      "loss": 1.2719,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.3330751955509186,
      "learning_rate": 0.00013880266075388026,
      "loss": 1.0329,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.2408718466758728,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.9571,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.2590923607349396,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.8574,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.320601224899292,
      "learning_rate": 0.00013747228381374724,
      "loss": 1.0379,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.36639603972435,
      "learning_rate": 0.0001370288248337029,
      "loss": 1.0785,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.39748233556747437,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.9833,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.33682262897491455,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.9659,
      "step": 150
    }
  ],
  "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": 2.678214528324403e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}