{
  "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": 1.1175572872161865,
      "learning_rate": 0.0,
      "loss": 3.0744,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.2595356702804565,
      "learning_rate": 4e-05,
      "loss": 3.3519,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.1831451654434204,
      "learning_rate": 8e-05,
      "loss": 3.4142,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.1135042905807495,
      "learning_rate": 0.00012,
      "loss": 2.8473,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.6986281871795654,
      "learning_rate": 0.00016,
      "loss": 3.1145,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.8996844291687012,
      "learning_rate": 0.0002,
      "loss": 2.7206,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 1.654848337173462,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.6435,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.9960455894470215,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.6488,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.1452784538269043,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2791,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.9133374094963074,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.0621,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.7128933668136597,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.8729,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.9738520383834839,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.945,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 1.0968796014785767,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.9219,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.8448852300643921,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.7323,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.6533470153808594,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.7965,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5058298707008362,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.7675,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.5244030952453613,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.6938,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.5534260869026184,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.7475,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.49227115511894226,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.7782,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.6014466881752014,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.6281,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.46302980184555054,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.6085,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3817231357097626,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.4978,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.41959288716316223,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.7479,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.37861549854278564,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.5145,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.41947174072265625,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.6564,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.43568453192710876,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.7639,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.35360434651374817,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.7617,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.43759599328041077,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.6815,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3009309470653534,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.5048,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.37697890400886536,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.5197,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.36582183837890625,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.4953,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.4371263384819031,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.6357,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.35323941707611084,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.6407,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.4218985438346863,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.6067,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.4576883614063263,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.7649,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3939562737941742,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.7539,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3907439112663269,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.6574,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.34653839468955994,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.4845,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.30807438492774963,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.5046,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3422587811946869,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.642,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.4083802103996277,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.6177,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3902239203453064,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.6883,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.413637638092041,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.5178,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.3305671513080597,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.4925,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.3556175231933594,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.4991,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3833027482032776,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.5837,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.34828928112983704,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.4893,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.4020296335220337,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.4792,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.47377222776412964,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.5776,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.47716471552848816,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.6295,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.4160218834877014,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.5249,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.3925120234489441,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.5979,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.451288104057312,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.7045,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.44237250089645386,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.6288,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.37273454666137695,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.5214,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.4249885380268097,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.6523,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.4397568702697754,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.7857,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.37436991930007935,
      "learning_rate": 0.000176940133037694,
      "loss": 0.5266,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.3295058310031891,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.5685,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3959578275680542,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.4584,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.37387439608573914,
      "learning_rate": 0.000175609756097561,
      "loss": 0.5703,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.28911006450653076,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.4591,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.6077892184257507,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.7229,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.44933897256851196,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.4895,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.4583057463169098,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.5422,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.441131055355072,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.5039,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.37214893102645874,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.4451,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.37915486097335815,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.5498,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.43058085441589355,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.6258,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.4087371528148651,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.4304,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3702792525291443,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.5061,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.40271690487861633,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.5221,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.4654999077320099,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.5427,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.422850638628006,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.5003,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.35233739018440247,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.5353,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3508605659008026,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.5011,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.35129278898239136,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.5396,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.4907684922218323,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.5464,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.3281923234462738,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.5209,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.444183349609375,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.7176,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.5929686427116394,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.6389,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.40402573347091675,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.4612,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.4387584626674652,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.4967,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3580304682254791,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.5834,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.5472170114517212,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.5454,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.4298936426639557,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.4903,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.428013414144516,
      "learning_rate": 0.000164079822616408,
      "loss": 0.5407,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.4182053506374359,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.5558,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3617396652698517,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.4448,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.35693031549453735,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.5425,
      "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": 3.692371792990003e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}