{
  "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": 4.417632102966309,
      "learning_rate": 0.0,
      "loss": 4.6066,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 3.824070453643799,
      "learning_rate": 4e-05,
      "loss": 4.5809,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 4.764647960662842,
      "learning_rate": 8e-05,
      "loss": 4.8428,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 5.026129722595215,
      "learning_rate": 0.00012,
      "loss": 5.3246,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 5.568634033203125,
      "learning_rate": 0.00016,
      "loss": 5.0766,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 7.791904926300049,
      "learning_rate": 0.0002,
      "loss": 4.4789,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 5.971574306488037,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.7773,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 3.3475728034973145,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.6269,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 2.5669748783111572,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.6002,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 2.079508066177368,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.561,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.5781028270721436,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.188,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.8474287390708923,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1719,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.7965599894523621,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0825,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.67277592420578,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.991,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.7163275480270386,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.1508,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.8085870146751404,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.2109,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.7520304322242737,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0903,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.680241048336029,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9543,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.8143166303634644,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.2347,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.7142716646194458,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0114,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.5970592498779297,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0567,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.7442165017127991,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.8508,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.6935762763023376,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.089,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.6430759429931641,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.7555,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.610454261302948,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.0817,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.6211035847663879,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9037,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.6100361943244934,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.0705,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.5219504237174988,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.8251,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.5593066811561584,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.0416,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.5467231273651123,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.9379,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.8338480591773987,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.8073,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.6652135848999023,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.959,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.6371573805809021,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.0453,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.5541828274726868,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.8059,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.6239511966705322,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.9681,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.6381208896636963,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.8827,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.5363917946815491,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.989,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.6242470741271973,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.6724,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.531095027923584,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.7495,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.6587176322937012,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.9717,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.5573552250862122,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.9977,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.6289750933647156,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9671,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.5671831965446472,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.8712,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.603140115737915,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.9699,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.5726262927055359,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.073,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.57386714220047,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9159,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.5615765452384949,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.0575,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.47419869899749756,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.8356,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.5028887987136841,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.0313,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.5023750066757202,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.8376,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.4543537199497223,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.7145,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.4374978244304657,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.7464,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.47209376096725464,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9299,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.5425230264663696,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.8528,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.5343915820121765,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.7878,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.5154897570610046,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.8451,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.48188620805740356,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.9204,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.42773884534835815,
      "learning_rate": 0.000176940133037694,
      "loss": 0.7443,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.6305500268936157,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.0036,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.571887731552124,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.8989,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.5789161324501038,
      "learning_rate": 0.000175609756097561,
      "loss": 0.9057,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.5388776063919067,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.9811,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.5069330334663391,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.8072,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.6007671356201172,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.9287,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.5581125020980835,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9263,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.6751324534416199,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.8119,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.4773782789707184,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.6753,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.6136070489883423,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.8526,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.6497328281402588,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.7758,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.6036306023597717,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.941,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.5378339290618896,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.9566,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.4954136908054352,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.9078,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.5501747727394104,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8474,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.5908843874931335,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.9218,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.4488467574119568,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.8638,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.5528292059898376,
      "learning_rate": 0.00016895787139689582,
      "loss": 1.1412,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.4880754351615906,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.7314,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.5529576539993286,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.0243,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.5193362832069397,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.9398,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.5076447129249573,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.6084,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.5762174129486084,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.9232,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.5628107786178589,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.9185,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.5657719969749451,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.8769,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.676673173904419,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.9929,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.5039803981781006,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.88,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.5343524217605591,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.7667,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.6614826917648315,
      "learning_rate": 0.000164079822616408,
      "loss": 0.7338,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.6496767997741699,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.0196,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.5414061546325684,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.9439,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.5283159017562866,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.6371,
      "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": 9377378069790720.0,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}