{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5934065934065934,
  "eval_steps": 500,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 5.459638595581055,
      "learning_rate": 0.0,
      "loss": 5.1572,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 4.408932209014893,
      "learning_rate": 4e-05,
      "loss": 4.941,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 5.487926959991455,
      "learning_rate": 8e-05,
      "loss": 5.5698,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 5.361940860748291,
      "learning_rate": 0.00012,
      "loss": 5.4254,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 5.856925010681152,
      "learning_rate": 0.00016,
      "loss": 4.9638,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 6.2031073570251465,
      "learning_rate": 0.0002,
      "loss": 4.1384,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 6.153454780578613,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.5665,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.060917615890503,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.335,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.5414468050003052,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2202,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 2.760967493057251,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3177,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.4582066535949707,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.1973,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.800369918346405,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1367,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.8436974287033081,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.2465,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.9210023283958435,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0176,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.8066878318786621,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.9148,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.8594912886619568,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.0468,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.6237018704414368,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0676,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.6330975294113159,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9913,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.7443146705627441,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.8187,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.7366983890533447,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.1666,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.571020781993866,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.9126,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.6713335514068604,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.7393,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.5838486552238464,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.9377,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.6766859889030457,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.1663,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.6486108303070068,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.8836,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.6390822529792786,
      "learning_rate": 0.00019113082039911309,
      "loss": 1.0328,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.6051312685012817,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.1173,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.539639949798584,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.8195,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.6244184970855713,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9956,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.5312393307685852,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.9427,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.6213347911834717,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.0347,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.5339341759681702,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.8984,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.5304893851280212,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.8964,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.6589417457580566,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.3518,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.6399314403533936,
      "learning_rate": 0.00018713968957871397,
      "loss": 1.1438,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.545724630355835,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.9772,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.5593492984771729,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.883,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.5673443078994751,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.9052,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.6377619504928589,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9566,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.5556446313858032,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.8046,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.5751636624336243,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.9647,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.8823965191841125,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.914,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.4730704128742218,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.8514,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.527775764465332,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.8588,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 1.2125602960586548,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9817,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.46695390343666077,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.7875,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.45550069212913513,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.7247,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.5238901972770691,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.788,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.5668091773986816,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.8173,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.5564643740653992,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9231,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.4617767035961151,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.8297,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.47752270102500916,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.7544,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.535720705986023,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9407,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.47505563497543335,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.8374,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.6126910448074341,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.0878,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.5779691934585571,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.0181,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.5656658411026001,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.8647,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.5828663110733032,
      "learning_rate": 0.000176940133037694,
      "loss": 0.7128,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.5121160745620728,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.9738,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.621181309223175,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.808,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.5183335542678833,
      "learning_rate": 0.000175609756097561,
      "loss": 0.8703,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.6565868258476257,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.9312,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.6722279191017151,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0824,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.6071406006813049,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.891,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.513313889503479,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.742,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.5047631859779358,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.9423,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.5646599531173706,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.8566,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.5328014492988586,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.8397,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.6697370409965515,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.9044,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.7905986309051514,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.9489,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.5284698605537415,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.7049,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.5368447303771973,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.8274,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.5713925361633301,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.6653,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.5431435108184814,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.9738,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.5508645176887512,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.7946,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.5687035918235779,
      "learning_rate": 0.00016895787139689582,
      "loss": 1.1262,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.499746710062027,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.0047,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.59474116563797,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.1529,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.6204425096511841,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.8883,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.5115718245506287,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.8317,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.5380851030349731,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.9325,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.5884971618652344,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.0196,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.6122893691062927,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.787,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.5914639830589294,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.928,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.6377210021018982,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.953,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.5960861444473267,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.8375,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.5654808282852173,
      "learning_rate": 0.000164079822616408,
      "loss": 0.7931,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.6073900461196899,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.0419,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.5416488647460938,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8963,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.48589223623275757,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.8119,
      "step": 90
    }
  ],
  "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": 9446976516882432.0,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}