{
  "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": 1.068535327911377,
      "learning_rate": 0.0,
      "loss": 1.0606,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.268423318862915,
      "learning_rate": 9.56e-05,
      "loss": 1.1983,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.045927882194519,
      "learning_rate": 0.0001912,
      "loss": 1.0628,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.028908371925354,
      "learning_rate": 0.0002868,
      "loss": 0.9173,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.6483846306800842,
      "learning_rate": 0.0003824,
      "loss": 0.7759,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.7689517736434937,
      "learning_rate": 0.000478,
      "loss": 0.9309,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5526404976844788,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.96,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.4260517656803131,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8695,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.34387385845184326,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.8246,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.33756059408187866,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.805,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.5314936637878418,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.8365,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5229127407073975,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.838,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.48703446984291077,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.773,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.524895966053009,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.7794,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5241197347640991,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.7233,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.427020788192749,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.7957,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.5390051603317261,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.8339,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.31555530428886414,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7379,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.3968167304992676,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.6715,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.37160152196884155,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.7653,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.40373656153678894,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.7728,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.360177218914032,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.7641,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.5294693112373352,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7356,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.353331595659256,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.7071,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.49404677748680115,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.7861,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3531878590583801,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.7469,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.4992196261882782,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.7605,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.39656317234039307,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.772,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.41846686601638794,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.7356,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.4010296165943146,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.7164,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.39482295513153076,
      "learning_rate": 0.00045150332594235033,
      "loss": 0.7471,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.4151882231235504,
      "learning_rate": 0.00045044345898004437,
      "loss": 0.6996,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.36281782388687134,
      "learning_rate": 0.0004493835920177384,
      "loss": 0.6891,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.34789708256721497,
      "learning_rate": 0.00044832372505543234,
      "loss": 0.7758,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.324373722076416,
      "learning_rate": 0.0004472638580931264,
      "loss": 0.7226,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.42178890109062195,
      "learning_rate": 0.0004462039911308204,
      "loss": 0.7202,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.308438241481781,
      "learning_rate": 0.0004451441241685144,
      "loss": 0.6874,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3963092267513275,
      "learning_rate": 0.00044408425720620845,
      "loss": 0.7376,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.44302892684936523,
      "learning_rate": 0.0004430243902439025,
      "loss": 0.7081,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3021492063999176,
      "learning_rate": 0.0004419645232815964,
      "loss": 0.6247,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.43004491925239563,
      "learning_rate": 0.00044090465631929047,
      "loss": 0.7669,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3463588058948517,
      "learning_rate": 0.0004398447893569845,
      "loss": 0.7017,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.34282755851745605,
      "learning_rate": 0.0004387849223946785,
      "loss": 0.689,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.3126462996006012,
      "learning_rate": 0.00043772505543237253,
      "loss": 0.6595,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.4455788731575012,
      "learning_rate": 0.0004366651884700666,
      "loss": 0.7789,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.43091949820518494,
      "learning_rate": 0.0004356053215077605,
      "loss": 0.6629,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3956051170825958,
      "learning_rate": 0.00043454545454545455,
      "loss": 0.7038,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.34474050998687744,
      "learning_rate": 0.0004334855875831486,
      "loss": 0.6247,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.34399884939193726,
      "learning_rate": 0.0004324257206208426,
      "loss": 0.7179,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.40537482500076294,
      "learning_rate": 0.0004313658536585366,
      "loss": 0.7844,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.2834356427192688,
      "learning_rate": 0.00043030598669623066,
      "loss": 0.7072,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.4583128094673157,
      "learning_rate": 0.0004292461197339246,
      "loss": 0.6838,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.368510901927948,
      "learning_rate": 0.00042818625277161863,
      "loss": 0.7243,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.3794223964214325,
      "learning_rate": 0.00042712638580931267,
      "loss": 0.6682,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3720533847808838,
      "learning_rate": 0.00042606651884700666,
      "loss": 0.7399,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.26934292912483215,
      "learning_rate": 0.0004250066518847007,
      "loss": 0.7528,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2473444938659668,
      "learning_rate": 0.00042394678492239474,
      "loss": 0.7546,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.29776763916015625,
      "learning_rate": 0.00042288691796008867,
      "loss": 0.7134,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.30960676074028015,
      "learning_rate": 0.0004218270509977827,
      "loss": 0.6635,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.29519444704055786,
      "learning_rate": 0.00042076718403547675,
      "loss": 0.7917,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.30791789293289185,
      "learning_rate": 0.00041970731707317074,
      "loss": 0.747,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3696693778038025,
      "learning_rate": 0.0004186474501108648,
      "loss": 0.654,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3656329810619354,
      "learning_rate": 0.0004175875831485588,
      "loss": 0.7181,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.33191412687301636,
      "learning_rate": 0.00041652771618625275,
      "loss": 0.7213,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.37534675002098083,
      "learning_rate": 0.0004154678492239468,
      "loss": 0.6989,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.31701603531837463,
      "learning_rate": 0.00041440798226164083,
      "loss": 0.7248,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.33182188868522644,
      "learning_rate": 0.0004133481152993348,
      "loss": 0.693,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.37241753935813904,
      "learning_rate": 0.00041228824833702886,
      "loss": 0.7017,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.2879069745540619,
      "learning_rate": 0.00041122838137472285,
      "loss": 0.7336,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3153330981731415,
      "learning_rate": 0.00041016851441241683,
      "loss": 0.6674,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.28542593121528625,
      "learning_rate": 0.00040910864745011087,
      "loss": 0.6966,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.35462895035743713,
      "learning_rate": 0.00040804878048780486,
      "loss": 0.662,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.3499428927898407,
      "learning_rate": 0.0004069889135254989,
      "loss": 0.616,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3505977392196655,
      "learning_rate": 0.00040592904656319294,
      "loss": 0.6786,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.45479053258895874,
      "learning_rate": 0.0004048691796008869,
      "loss": 0.6899,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3608059287071228,
      "learning_rate": 0.00040380931263858097,
      "loss": 0.773,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.29298636317253113,
      "learning_rate": 0.00040274944567627495,
      "loss": 0.7471,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3075357973575592,
      "learning_rate": 0.00040168957871396894,
      "loss": 0.6878,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.33668023347854614,
      "learning_rate": 0.000400629711751663,
      "loss": 0.6526,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.38277485966682434,
      "learning_rate": 0.000399569844789357,
      "loss": 0.6973,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.31462499499320984,
      "learning_rate": 0.000398509977827051,
      "loss": 0.6926,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.39728376269340515,
      "learning_rate": 0.00039745011086474505,
      "loss": 0.7752,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.4079730212688446,
      "learning_rate": 0.00039639024390243904,
      "loss": 0.7529,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.2829400897026062,
      "learning_rate": 0.000395330376940133,
      "loss": 0.6805,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.28787168860435486,
      "learning_rate": 0.00039427050997782706,
      "loss": 0.6955,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3676906228065491,
      "learning_rate": 0.0003932106430155211,
      "loss": 0.7451,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.30598631501197815,
      "learning_rate": 0.0003921507760532151,
      "loss": 0.6962,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.2758977711200714,
      "learning_rate": 0.00039109090909090913,
      "loss": 0.6525,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.2694230079650879,
      "learning_rate": 0.0003900310421286031,
      "loss": 0.6458,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.35207247734069824,
      "learning_rate": 0.0003889711751662971,
      "loss": 0.7354,
      "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": 4.117777501604659e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}