{
  "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": 1.0904711484909058,
      "learning_rate": 0.0,
      "loss": 3.1329,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.194968819618225,
      "learning_rate": 4e-05,
      "loss": 3.6094,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.1164450645446777,
      "learning_rate": 8e-05,
      "loss": 3.0412,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.1624926328659058,
      "learning_rate": 0.00012,
      "loss": 2.9338,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.5745073556900024,
      "learning_rate": 0.00016,
      "loss": 3.274,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.7036746740341187,
      "learning_rate": 0.0002,
      "loss": 2.4334,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 1.8973665237426758,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.0627,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.289609432220459,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.5525,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.131475567817688,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.3678,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.6904632449150085,
      "learning_rate": 0.00019822616407982261,
      "loss": 0.7552,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.884515106678009,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.9467,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.9904367327690125,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.0084,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.8777419328689575,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.7461,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.7277262210845947,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.772,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.6279889345169067,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.6998,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5881436467170715,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.8344,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.5195655226707458,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.7791,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.464557945728302,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.7235,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4548377990722656,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.6601,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.44950956106185913,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.5868,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.5051064491271973,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.7179,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.4204910099506378,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.8455,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.487579345703125,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.6916,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.49214768409729004,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.7523,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.46010738611221313,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.5995,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.4043605327606201,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.7526,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.4564755856990814,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.6029,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.4226926267147064,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.6855,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3979853093624115,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.6834,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.4517277479171753,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.7183,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3381803631782532,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.6249,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3961849808692932,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.7238,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.475576251745224,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.6638,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3843558430671692,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.5917,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.33360686898231506,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.5933,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.31211772561073303,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.6047,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.4541437327861786,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.7337,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3357751667499542,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.563,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3497297167778015,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.6105,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.5382171273231506,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.777,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.46289727091789246,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.5519,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.45685848593711853,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.5663,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.30779364705085754,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.5699,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.46814775466918945,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.659,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2591197192668915,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.4421,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3040383458137512,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.4688,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3322198987007141,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.5025,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.3934444189071655,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.6126,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.41803842782974243,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.6893,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3833474814891815,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.5678,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3115043044090271,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.5805,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.4171527028083801,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.5915,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3966691792011261,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.5636,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.4638712704181671,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.5092,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.4100938141345978,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.5893,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.43879401683807373,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.6023,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.35753703117370605,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.6184,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.4090399742126465,
      "learning_rate": 0.000176940133037694,
      "loss": 0.6497,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.47983500361442566,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.6835,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.42642199993133545,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.4971,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.34762364625930786,
      "learning_rate": 0.000175609756097561,
      "loss": 0.4361,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.35311388969421387,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.5189,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3966199457645416,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.7028,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3628181517124176,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.5183,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.5134937167167664,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.7435,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.4752194285392761,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.4935,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.40037086606025696,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.5544,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.4528057873249054,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.627,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.48125362396240234,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.5712,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.41042086482048035,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.5978,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.4792564809322357,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.6607,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.46171724796295166,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.6435,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.40180259943008423,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.5813,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.40912848711013794,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.5139,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.4367366433143616,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.5397,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.46934279799461365,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.5032,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.4804418981075287,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.4986,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.4636159837245941,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.6137,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.4361138641834259,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.5287,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.42685630917549133,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.4833,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.46646246314048767,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.5974,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3888683617115021,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.4866,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.43256884813308716,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.5691,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.4895230233669281,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.5397,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.506166934967041,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.516,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.5024157762527466,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.5014,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.32683488726615906,
      "learning_rate": 0.000164079822616408,
      "loss": 0.5191,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.43097981810569763,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.5393,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.4409153461456299,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.6214,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.3960947096347809,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.6535,
      "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": 3.747407779055002e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}