{
  "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": 1.1258277893066406,
      "learning_rate": 0.0,
      "loss": 3.0295,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.0469061136245728,
      "learning_rate": 4e-05,
      "loss": 2.8199,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.9328632354736328,
      "learning_rate": 8e-05,
      "loss": 2.6328,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.3742667436599731,
      "learning_rate": 0.00012,
      "loss": 2.9986,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.3568042516708374,
      "learning_rate": 0.00016,
      "loss": 2.5623,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.9343546628952026,
      "learning_rate": 0.0002,
      "loss": 2.5039,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 1.6630727052688599,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.7366,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.5585440397262573,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.8155,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.9433563351631165,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.1226,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.9606233835220337,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.0042,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.7951949238777161,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.9564,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.7159879207611084,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.7373,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.805880069732666,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.792,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.6829606294631958,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.6215,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5796816945075989,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.8198,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5503753423690796,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.7578,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.5514731407165527,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.7522,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4225347340106964,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.6527,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4526655375957489,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.607,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.481832891702652,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.6847,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.4877224862575531,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.7136,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3743646740913391,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.5966,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.4489605128765106,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.6452,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.45275574922561646,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.5869,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.4297250807285309,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.61,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3726891875267029,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.6145,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.38317251205444336,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.6995,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.39017173647880554,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.5878,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3254614472389221,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.501,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.47432705760002136,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.62,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.4453403055667877,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.6706,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.35256972908973694,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.5292,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.36604660749435425,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.537,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.36700016260147095,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.5214,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.29663094878196716,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.5031,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.28732767701148987,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.4768,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3642386794090271,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.574,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.40244248509407043,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.4877,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3658510744571686,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.5191,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.4025786817073822,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.5328,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.41957223415374756,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.5718,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3137666881084442,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.4743,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.4241214692592621,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.5761,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.35041534900665283,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.5104,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.44434788823127747,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.539,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.30492666363716125,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.6963,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.38742250204086304,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.5314,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.3342526853084564,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.5585,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.3805127739906311,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.5723,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3670502007007599,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.5283,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3458058834075928,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.4398,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.4033033549785614,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.5544,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3558763563632965,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.4877,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.3886813521385193,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.6995,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.38272568583488464,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.4899,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.48774710297584534,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.5643,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.42786574363708496,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.5489,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3868570923805237,
      "learning_rate": 0.000176940133037694,
      "loss": 0.5215,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.3829129934310913,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.5186,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.329976886510849,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.5287,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.3485603332519531,
      "learning_rate": 0.000175609756097561,
      "loss": 0.5313,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3575219511985779,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.5349,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3275308310985565,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.4863,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.42464715242385864,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.5776,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3628101646900177,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.5751,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3428574502468109,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.4941,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.2916024923324585,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.4345,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.33352556824684143,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.4253,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3252923786640167,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.4447,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3962821364402771,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.4752,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.49113529920578003,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.5114,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.35567113757133484,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.4933,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.3056921660900116,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.4618,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.42156627774238586,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.5053,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.4406984746456146,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.5012,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.42425596714019775,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.5621,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.35644426941871643,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.5384,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.28911274671554565,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.508,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.32456129789352417,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.6684,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.4201291501522064,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.4951,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.4306047558784485,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.4994,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3155696988105774,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.4537,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.33225157856941223,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.4942,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.4080914556980133,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.6126,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.3456087112426758,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.3832,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.34410449862480164,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.4581,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3481915295124054,
      "learning_rate": 0.000164079822616408,
      "loss": 0.5581,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.4316079318523407,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.5078,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.4453663229942322,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.5025,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.3725511133670807,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.5028,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.41532671451568604,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.5095,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.2991493344306946,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.3922,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.422572523355484,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.4997,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3846403658390045,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.4912,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.3804264962673187,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.4565,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.34783074259757996,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.53,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3216366171836853,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.4462,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.41518279910087585,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.5432,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.38873574137687683,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.468,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.415010541677475,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.5427,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.48093146085739136,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.4513,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.2963591516017914,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.4207,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.3437178134918213,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.4672,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.4175635874271393,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.4549,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.5979942679405212,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.5752,
      "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": 4.225041515261952e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}