{
  "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": 0.9970224499702454,
      "learning_rate": 0.0,
      "loss": 1.0991,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.144827127456665,
      "learning_rate": 9.56e-05,
      "loss": 1.1545,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.1169440746307373,
      "learning_rate": 0.0001912,
      "loss": 1.123,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.0855385065078735,
      "learning_rate": 0.0002868,
      "loss": 0.9259,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.8469429016113281,
      "learning_rate": 0.0003824,
      "loss": 0.8556,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.7604000568389893,
      "learning_rate": 0.000478,
      "loss": 0.9009,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5317047834396362,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.9281,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.47205209732055664,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8713,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.2961072027683258,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.8788,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.38304176926612854,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.816,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.5212758779525757,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.8274,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.543552577495575,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.8489,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.4572776257991791,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.8166,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.44755756855010986,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.7803,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5597015023231506,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.801,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.39118215441703796,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.7196,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.4890790581703186,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.7744,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.5199437737464905,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7521,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4048418402671814,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.7232,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.4759422242641449,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.7887,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.373710572719574,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.7673,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3180016577243805,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.7553,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.43041887879371643,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7573,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.4632937014102936,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.7318,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3658117651939392,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.7129,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.39879968762397766,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.7212,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.4226565659046173,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.7441,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3761254549026489,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.7351,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3735473155975342,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.7274,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3605045676231384,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.7511,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.49938589334487915,
      "learning_rate": 0.00045150332594235033,
      "loss": 0.733,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3388383090496063,
      "learning_rate": 0.00045044345898004437,
      "loss": 0.7086,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.6535608768463135,
      "learning_rate": 0.0004493835920177384,
      "loss": 0.7686,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.36676231026649475,
      "learning_rate": 0.00044832372505543234,
      "loss": 0.6831,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3847268521785736,
      "learning_rate": 0.0004472638580931264,
      "loss": 0.7375,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.37475308775901794,
      "learning_rate": 0.0004462039911308204,
      "loss": 0.7084,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3576759696006775,
      "learning_rate": 0.0004451441241685144,
      "loss": 0.7693,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.33207494020462036,
      "learning_rate": 0.00044408425720620845,
      "loss": 0.7844,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.4797557592391968,
      "learning_rate": 0.0004430243902439025,
      "loss": 0.6863,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3291913866996765,
      "learning_rate": 0.0004419645232815964,
      "loss": 0.6941,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3354625701904297,
      "learning_rate": 0.00044090465631929047,
      "loss": 0.7254,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3200039267539978,
      "learning_rate": 0.0004398447893569845,
      "loss": 0.6928,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.377468079328537,
      "learning_rate": 0.0004387849223946785,
      "loss": 0.7907,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.35265693068504333,
      "learning_rate": 0.00043772505543237253,
      "loss": 0.6916,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.4030437171459198,
      "learning_rate": 0.0004366651884700666,
      "loss": 0.721,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3848680853843689,
      "learning_rate": 0.0004356053215077605,
      "loss": 0.7261,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3052960932254791,
      "learning_rate": 0.00043454545454545455,
      "loss": 0.7063,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.3832049071788788,
      "learning_rate": 0.0004334855875831486,
      "loss": 0.7652,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.3644565939903259,
      "learning_rate": 0.0004324257206208426,
      "loss": 0.8106,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3032757639884949,
      "learning_rate": 0.0004313658536585366,
      "loss": 0.7162,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3071494996547699,
      "learning_rate": 0.00043030598669623066,
      "loss": 0.7907,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.32176244258880615,
      "learning_rate": 0.0004292461197339246,
      "loss": 0.7865,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3945949375629425,
      "learning_rate": 0.00042818625277161863,
      "loss": 0.8038,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2989363968372345,
      "learning_rate": 0.00042712638580931267,
      "loss": 0.7172,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.317256361246109,
      "learning_rate": 0.00042606651884700666,
      "loss": 0.7325,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.27640077471733093,
      "learning_rate": 0.0004250066518847007,
      "loss": 0.765,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.3094281256198883,
      "learning_rate": 0.00042394678492239474,
      "loss": 0.7391,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.30334004759788513,
      "learning_rate": 0.00042288691796008867,
      "loss": 0.7486,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.3377019166946411,
      "learning_rate": 0.0004218270509977827,
      "loss": 0.7444,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.34436339139938354,
      "learning_rate": 0.00042076718403547675,
      "loss": 0.7041,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.27596402168273926,
      "learning_rate": 0.00041970731707317074,
      "loss": 0.6926,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3022932708263397,
      "learning_rate": 0.0004186474501108648,
      "loss": 0.7138,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.2816564738750458,
      "learning_rate": 0.0004175875831485588,
      "loss": 0.7261,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3032025992870331,
      "learning_rate": 0.00041652771618625275,
      "loss": 0.6791,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.26954764127731323,
      "learning_rate": 0.0004154678492239468,
      "loss": 0.7032,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3011576235294342,
      "learning_rate": 0.00041440798226164083,
      "loss": 0.7512,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.33316031098365784,
      "learning_rate": 0.0004133481152993348,
      "loss": 0.7345,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3042667508125305,
      "learning_rate": 0.00041228824833702886,
      "loss": 0.7834,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.28509846329689026,
      "learning_rate": 0.00041122838137472285,
      "loss": 0.7127,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3400508761405945,
      "learning_rate": 0.00041016851441241683,
      "loss": 0.7382,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3198228180408478,
      "learning_rate": 0.00040910864745011087,
      "loss": 0.7625,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.32544252276420593,
      "learning_rate": 0.00040804878048780486,
      "loss": 0.7485,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.345786988735199,
      "learning_rate": 0.0004069889135254989,
      "loss": 0.7448,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.2966018319129944,
      "learning_rate": 0.00040592904656319294,
      "loss": 0.6449,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.27237051725387573,
      "learning_rate": 0.0004048691796008869,
      "loss": 0.6467,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.332011342048645,
      "learning_rate": 0.00040380931263858097,
      "loss": 0.7323,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.32000380754470825,
      "learning_rate": 0.00040274944567627495,
      "loss": 0.7653,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.34098610281944275,
      "learning_rate": 0.00040168957871396894,
      "loss": 0.7202,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.2874126732349396,
      "learning_rate": 0.000400629711751663,
      "loss": 0.7367,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.322229266166687,
      "learning_rate": 0.000399569844789357,
      "loss": 0.6588,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3342168927192688,
      "learning_rate": 0.000398509977827051,
      "loss": 0.7579,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3295648396015167,
      "learning_rate": 0.00039745011086474505,
      "loss": 0.7388,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.2803487479686737,
      "learning_rate": 0.00039639024390243904,
      "loss": 0.7614,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.32823750376701355,
      "learning_rate": 0.000395330376940133,
      "loss": 0.7479,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.32557007670402527,
      "learning_rate": 0.00039427050997782706,
      "loss": 0.7527,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.33845341205596924,
      "learning_rate": 0.0003932106430155211,
      "loss": 0.7203,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.39683398604393005,
      "learning_rate": 0.0003921507760532151,
      "loss": 0.7576,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3514403998851776,
      "learning_rate": 0.00039109090909090913,
      "loss": 0.7556,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3493777811527252,
      "learning_rate": 0.0003900310421286031,
      "loss": 0.6633,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.28230881690979004,
      "learning_rate": 0.0003889711751662971,
      "loss": 0.7153,
      "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": 4.130226117500314e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}