{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6923076923076923,
  "eval_steps": 500,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.6841859817504883,
      "learning_rate": 0.0,
      "loss": 2.6699,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.6275595426559448,
      "learning_rate": 4e-05,
      "loss": 2.8927,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.8733887672424316,
      "learning_rate": 8e-05,
      "loss": 2.892,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 2.217374324798584,
      "learning_rate": 0.00012,
      "loss": 3.1736,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.244591474533081,
      "learning_rate": 0.00016,
      "loss": 2.9009,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.151010036468506,
      "learning_rate": 0.0002,
      "loss": 2.9239,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.4616637229919434,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.6906,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.9495002031326294,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.3796,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.0036247968673706,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.4208,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.268955111503601,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.1932,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.9355878233909607,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.3019,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.6264943480491638,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.3045,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.48183032870292664,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0772,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.4918908178806305,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.1073,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.47716087102890015,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.0682,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5131794810295105,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.235,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.374526709318161,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0192,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.42145562171936035,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.1169,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.3757359981536865,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.0849,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.39348798990249634,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.8945,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3551047742366791,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.8459,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.49977052211761475,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1775,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.40330278873443604,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.045,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3608703315258026,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.1339,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3405609130859375,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.1932,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3685476779937744,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9513,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3427353799343109,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9238,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.31721019744873047,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.9311,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.33064839243888855,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9628,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.40480926632881165,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0018,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3145495355129242,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.7893,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3124920129776001,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.902,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.33218735456466675,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9481,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.29943299293518066,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.9887,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2689051330089569,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.8745,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3515532910823822,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.0236,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.4234579801559448,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.9152,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.23922260105609894,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.8792,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.33698251843452454,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.0251,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3279472589492798,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.944,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3242871165275574,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.0269,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.23830707371234894,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.7736,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.31032833456993103,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.1615,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.34291455149650574,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.9362,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.3425392508506775,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.8127,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3245941996574402,
      "learning_rate": 0.00018226164079822616,
      "loss": 1.0144,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.30251234769821167,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.7219,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.33010566234588623,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.1277,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.34598809480667114,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.0634,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.29939746856689453,
      "learning_rate": 0.0001804878048780488,
      "loss": 1.0615,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3273846209049225,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0597,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.29587024450302124,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.9912,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3769407570362091,
      "learning_rate": 0.00017915742793791575,
      "loss": 1.1541,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.33768051862716675,
      "learning_rate": 0.0001787139689578714,
      "loss": 1.0642,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.34447458386421204,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.8971,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.21314434707164764,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.6039,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.31818050146102905,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.7694,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.31640103459358215,
      "learning_rate": 0.000176940133037694,
      "loss": 0.904,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.3352418839931488,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.949,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.2662431001663208,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.0311,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.30483973026275635,
      "learning_rate": 0.000175609756097561,
      "loss": 1.0855,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.36452263593673706,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.8468,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.30326971411705017,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0586,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.24980409443378448,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.9535,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.4103758931159973,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.8719,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.39455509185791016,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.2655,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.3029159605503082,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9434,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.2612789273262024,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9328,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.27301448583602905,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.8727,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3540093004703522,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.0226,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.35511624813079834,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.0837,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.30946084856987,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.955,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.27514076232910156,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8824,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.32071107625961304,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.9625,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.32895898818969727,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.8895,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.27520042657852173,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.8647,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.2894044816493988,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.051,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3063855767250061,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.9467,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.3323456048965454,
      "learning_rate": 0.00016762749445676275,
      "loss": 1.0092,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.2992066740989685,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.8565,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.35619041323661804,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.8428,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.31528913974761963,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.0285,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3301350474357605,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.8895,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.287077397108078,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.9325,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.3263772428035736,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.0485,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.4456893503665924,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.9331,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3191007971763611,
      "learning_rate": 0.000164079822616408,
      "loss": 1.151,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.30760490894317627,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.0333,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.29519811272621155,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8138,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.2646964490413666,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.8292,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.28049373626708984,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.9276,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3945385813713074,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.8175,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.3451618254184723,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.9411,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.25848403573036194,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.7706,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.29975318908691406,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.8506,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.2926693260669708,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.9974,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.2618350684642792,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7716,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.2566186487674713,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.787,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.295584112405777,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.9429,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3691546618938446,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9469,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.33327218890190125,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.9988,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.35731151700019836,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.8776,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.37254080176353455,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9446,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3828260004520416,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.9977,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3122965395450592,
      "learning_rate": 0.00015609756097560978,
      "loss": 1.042,
      "step": 105
    }
  ],
  "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": 1.7210333456498688e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}