{
  "best_metric": 12.426092147827148,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.9607843137254903,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0196078431372549,
      "grad_norm": 0.011493449099361897,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 12.4571,
      "step": 1
    },
    {
      "epoch": 0.0196078431372549,
      "eval_loss": 12.453781127929688,
      "eval_runtime": 0.7609,
      "eval_samples_per_second": 904.211,
      "eval_steps_per_second": 28.914,
      "step": 1
    },
    {
      "epoch": 0.0392156862745098,
      "grad_norm": 0.010760590434074402,
      "learning_rate": 2.0200000000000003e-05,
      "loss": 12.457,
      "step": 2
    },
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 0.010758738964796066,
      "learning_rate": 3.0299999999999998e-05,
      "loss": 12.4561,
      "step": 3
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 0.011239373125135899,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 12.4552,
      "step": 4
    },
    {
      "epoch": 0.09803921568627451,
      "grad_norm": 0.011815620586276054,
      "learning_rate": 5.05e-05,
      "loss": 12.4542,
      "step": 5
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 0.012975395657122135,
      "learning_rate": 6.0599999999999996e-05,
      "loss": 12.4538,
      "step": 6
    },
    {
      "epoch": 0.13725490196078433,
      "grad_norm": 0.012917593121528625,
      "learning_rate": 7.07e-05,
      "loss": 12.4582,
      "step": 7
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 0.009971358813345432,
      "learning_rate": 8.080000000000001e-05,
      "loss": 12.4562,
      "step": 8
    },
    {
      "epoch": 0.17647058823529413,
      "grad_norm": 0.010108977556228638,
      "learning_rate": 9.09e-05,
      "loss": 12.4525,
      "step": 9
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 0.010624304413795471,
      "learning_rate": 0.000101,
      "loss": 12.457,
      "step": 10
    },
    {
      "epoch": 0.21568627450980393,
      "grad_norm": 0.011670473963022232,
      "learning_rate": 0.0001002937062937063,
      "loss": 12.4541,
      "step": 11
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 0.013510797172784805,
      "learning_rate": 9.958741258741259e-05,
      "loss": 12.4538,
      "step": 12
    },
    {
      "epoch": 0.2549019607843137,
      "grad_norm": 0.014974705874919891,
      "learning_rate": 9.888111888111889e-05,
      "loss": 12.4582,
      "step": 13
    },
    {
      "epoch": 0.27450980392156865,
      "grad_norm": 0.012437070719897747,
      "learning_rate": 9.817482517482517e-05,
      "loss": 12.4567,
      "step": 14
    },
    {
      "epoch": 0.29411764705882354,
      "grad_norm": 0.010862158611416817,
      "learning_rate": 9.746853146853147e-05,
      "loss": 12.4558,
      "step": 15
    },
    {
      "epoch": 0.3137254901960784,
      "grad_norm": 0.012195524759590626,
      "learning_rate": 9.676223776223776e-05,
      "loss": 12.4559,
      "step": 16
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.013258482329547405,
      "learning_rate": 9.605594405594406e-05,
      "loss": 12.4546,
      "step": 17
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 0.015779396519064903,
      "learning_rate": 9.534965034965035e-05,
      "loss": 12.4562,
      "step": 18
    },
    {
      "epoch": 0.37254901960784315,
      "grad_norm": 0.016349563375115395,
      "learning_rate": 9.464335664335665e-05,
      "loss": 12.455,
      "step": 19
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 0.015274745412170887,
      "learning_rate": 9.393706293706294e-05,
      "loss": 12.4534,
      "step": 20
    },
    {
      "epoch": 0.4117647058823529,
      "grad_norm": 0.014877895824611187,
      "learning_rate": 9.323076923076924e-05,
      "loss": 12.4522,
      "step": 21
    },
    {
      "epoch": 0.43137254901960786,
      "grad_norm": 0.016367629170417786,
      "learning_rate": 9.252447552447552e-05,
      "loss": 12.4548,
      "step": 22
    },
    {
      "epoch": 0.45098039215686275,
      "grad_norm": 0.02055247500538826,
      "learning_rate": 9.181818181818182e-05,
      "loss": 12.4551,
      "step": 23
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.023789655417203903,
      "learning_rate": 9.111188811188811e-05,
      "loss": 12.4569,
      "step": 24
    },
    {
      "epoch": 0.49019607843137253,
      "grad_norm": 0.025931550189852715,
      "learning_rate": 9.04055944055944e-05,
      "loss": 12.4531,
      "step": 25
    },
    {
      "epoch": 0.5098039215686274,
      "grad_norm": 0.01956542581319809,
      "learning_rate": 8.96993006993007e-05,
      "loss": 12.4564,
      "step": 26
    },
    {
      "epoch": 0.5294117647058824,
      "grad_norm": 0.02145051211118698,
      "learning_rate": 8.8993006993007e-05,
      "loss": 12.452,
      "step": 27
    },
    {
      "epoch": 0.5490196078431373,
      "grad_norm": 0.024554729461669922,
      "learning_rate": 8.828671328671329e-05,
      "loss": 12.4567,
      "step": 28
    },
    {
      "epoch": 0.5686274509803921,
      "grad_norm": 0.028146198019385338,
      "learning_rate": 8.758041958041957e-05,
      "loss": 12.4539,
      "step": 29
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.03251597285270691,
      "learning_rate": 8.687412587412587e-05,
      "loss": 12.4546,
      "step": 30
    },
    {
      "epoch": 0.6078431372549019,
      "grad_norm": 0.039151743054389954,
      "learning_rate": 8.616783216783216e-05,
      "loss": 12.456,
      "step": 31
    },
    {
      "epoch": 0.6274509803921569,
      "grad_norm": 0.030295705422759056,
      "learning_rate": 8.546153846153846e-05,
      "loss": 12.4572,
      "step": 32
    },
    {
      "epoch": 0.6470588235294118,
      "grad_norm": 0.029417822137475014,
      "learning_rate": 8.475524475524476e-05,
      "loss": 12.457,
      "step": 33
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.03694408759474754,
      "learning_rate": 8.404895104895105e-05,
      "loss": 12.4547,
      "step": 34
    },
    {
      "epoch": 0.6862745098039216,
      "grad_norm": 0.04618909955024719,
      "learning_rate": 8.334265734265735e-05,
      "loss": 12.4523,
      "step": 35
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.054282210767269135,
      "learning_rate": 8.263636363636364e-05,
      "loss": 12.453,
      "step": 36
    },
    {
      "epoch": 0.7254901960784313,
      "grad_norm": 0.06975057721138,
      "learning_rate": 8.193006993006992e-05,
      "loss": 12.4552,
      "step": 37
    },
    {
      "epoch": 0.7450980392156863,
      "grad_norm": 0.048148512840270996,
      "learning_rate": 8.122377622377622e-05,
      "loss": 12.4534,
      "step": 38
    },
    {
      "epoch": 0.7647058823529411,
      "grad_norm": 0.04206012561917305,
      "learning_rate": 8.051748251748251e-05,
      "loss": 12.4553,
      "step": 39
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 0.05756961926817894,
      "learning_rate": 7.981118881118881e-05,
      "loss": 12.4519,
      "step": 40
    },
    {
      "epoch": 0.803921568627451,
      "grad_norm": 0.061868276447057724,
      "learning_rate": 7.91048951048951e-05,
      "loss": 12.4548,
      "step": 41
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 0.07480663061141968,
      "learning_rate": 7.83986013986014e-05,
      "loss": 12.4546,
      "step": 42
    },
    {
      "epoch": 0.8431372549019608,
      "grad_norm": 0.0910768136382103,
      "learning_rate": 7.76923076923077e-05,
      "loss": 12.4513,
      "step": 43
    },
    {
      "epoch": 0.8627450980392157,
      "grad_norm": 0.08593326061964035,
      "learning_rate": 7.698601398601398e-05,
      "loss": 12.449,
      "step": 44
    },
    {
      "epoch": 0.8823529411764706,
      "grad_norm": 0.06495288014411926,
      "learning_rate": 7.627972027972027e-05,
      "loss": 12.4546,
      "step": 45
    },
    {
      "epoch": 0.9019607843137255,
      "grad_norm": 0.08239670842885971,
      "learning_rate": 7.557342657342657e-05,
      "loss": 12.4522,
      "step": 46
    },
    {
      "epoch": 0.9215686274509803,
      "grad_norm": 0.10047987848520279,
      "learning_rate": 7.486713286713286e-05,
      "loss": 12.4537,
      "step": 47
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.10524290055036545,
      "learning_rate": 7.416083916083916e-05,
      "loss": 12.45,
      "step": 48
    },
    {
      "epoch": 0.9607843137254902,
      "grad_norm": 0.1392570436000824,
      "learning_rate": 7.345454545454545e-05,
      "loss": 12.4494,
      "step": 49
    },
    {
      "epoch": 0.9803921568627451,
      "grad_norm": 0.18665827810764313,
      "learning_rate": 7.274825174825175e-05,
      "loss": 12.447,
      "step": 50
    },
    {
      "epoch": 0.9803921568627451,
      "eval_loss": 12.44759750366211,
      "eval_runtime": 0.791,
      "eval_samples_per_second": 869.826,
      "eval_steps_per_second": 27.814,
      "step": 50
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.11416830867528915,
      "learning_rate": 7.204195804195805e-05,
      "loss": 12.453,
      "step": 51
    },
    {
      "epoch": 1.0196078431372548,
      "grad_norm": 0.08539585024118423,
      "learning_rate": 7.133566433566433e-05,
      "loss": 12.4519,
      "step": 52
    },
    {
      "epoch": 1.0392156862745099,
      "grad_norm": 0.11319365352392197,
      "learning_rate": 7.062937062937062e-05,
      "loss": 12.448,
      "step": 53
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 0.14616349339485168,
      "learning_rate": 6.992307692307692e-05,
      "loss": 12.4479,
      "step": 54
    },
    {
      "epoch": 1.0784313725490196,
      "grad_norm": 0.15833082795143127,
      "learning_rate": 6.921678321678321e-05,
      "loss": 12.4471,
      "step": 55
    },
    {
      "epoch": 1.0980392156862746,
      "grad_norm": 0.19201552867889404,
      "learning_rate": 6.851048951048951e-05,
      "loss": 12.4455,
      "step": 56
    },
    {
      "epoch": 1.1176470588235294,
      "grad_norm": 0.23073577880859375,
      "learning_rate": 6.78041958041958e-05,
      "loss": 12.442,
      "step": 57
    },
    {
      "epoch": 1.1372549019607843,
      "grad_norm": 0.13355469703674316,
      "learning_rate": 6.70979020979021e-05,
      "loss": 12.4496,
      "step": 58
    },
    {
      "epoch": 1.156862745098039,
      "grad_norm": 0.15398786962032318,
      "learning_rate": 6.639160839160838e-05,
      "loss": 12.4465,
      "step": 59
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.1663445234298706,
      "learning_rate": 6.568531468531468e-05,
      "loss": 12.4482,
      "step": 60
    },
    {
      "epoch": 1.196078431372549,
      "grad_norm": 0.2090064436197281,
      "learning_rate": 6.497902097902097e-05,
      "loss": 12.4475,
      "step": 61
    },
    {
      "epoch": 1.215686274509804,
      "grad_norm": 0.2399904429912567,
      "learning_rate": 6.427272727272727e-05,
      "loss": 12.4436,
      "step": 62
    },
    {
      "epoch": 1.2352941176470589,
      "grad_norm": 0.24960361421108246,
      "learning_rate": 6.356643356643356e-05,
      "loss": 12.444,
      "step": 63
    },
    {
      "epoch": 1.2549019607843137,
      "grad_norm": 0.18903537094593048,
      "learning_rate": 6.286013986013986e-05,
      "loss": 12.4457,
      "step": 64
    },
    {
      "epoch": 1.2745098039215685,
      "grad_norm": 0.16718223690986633,
      "learning_rate": 6.215384615384615e-05,
      "loss": 12.4481,
      "step": 65
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 0.2060553878545761,
      "learning_rate": 6.144755244755245e-05,
      "loss": 12.4452,
      "step": 66
    },
    {
      "epoch": 1.3137254901960784,
      "grad_norm": 0.22543393075466156,
      "learning_rate": 6.074125874125874e-05,
      "loss": 12.4413,
      "step": 67
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.27220749855041504,
      "learning_rate": 6.0034965034965033e-05,
      "loss": 12.4421,
      "step": 68
    },
    {
      "epoch": 1.3529411764705883,
      "grad_norm": 0.2713835835456848,
      "learning_rate": 5.932867132867133e-05,
      "loss": 12.4424,
      "step": 69
    },
    {
      "epoch": 1.3725490196078431,
      "grad_norm": 0.23676316440105438,
      "learning_rate": 5.8622377622377624e-05,
      "loss": 12.4398,
      "step": 70
    },
    {
      "epoch": 1.392156862745098,
      "grad_norm": 0.1754506677389145,
      "learning_rate": 5.791608391608392e-05,
      "loss": 12.4448,
      "step": 71
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.2169537991285324,
      "learning_rate": 5.7209790209790215e-05,
      "loss": 12.4407,
      "step": 72
    },
    {
      "epoch": 1.4313725490196079,
      "grad_norm": 0.2186908721923828,
      "learning_rate": 5.650349650349651e-05,
      "loss": 12.4367,
      "step": 73
    },
    {
      "epoch": 1.4509803921568627,
      "grad_norm": 0.24410758912563324,
      "learning_rate": 5.579720279720279e-05,
      "loss": 12.4392,
      "step": 74
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 0.2627074122428894,
      "learning_rate": 5.509090909090909e-05,
      "loss": 12.4316,
      "step": 75
    },
    {
      "epoch": 1.4901960784313726,
      "grad_norm": 0.2872616946697235,
      "learning_rate": 5.438461538461538e-05,
      "loss": 12.4323,
      "step": 76
    },
    {
      "epoch": 1.5098039215686274,
      "grad_norm": 0.13781462609767914,
      "learning_rate": 5.367832167832168e-05,
      "loss": 12.443,
      "step": 77
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 0.19649550318717957,
      "learning_rate": 5.2972027972027974e-05,
      "loss": 12.4353,
      "step": 78
    },
    {
      "epoch": 1.5490196078431373,
      "grad_norm": 0.19505800306797028,
      "learning_rate": 5.226573426573427e-05,
      "loss": 12.4398,
      "step": 79
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": 0.20190319418907166,
      "learning_rate": 5.1559440559440565e-05,
      "loss": 12.4362,
      "step": 80
    },
    {
      "epoch": 1.5882352941176472,
      "grad_norm": 0.18724848330020905,
      "learning_rate": 5.085314685314686e-05,
      "loss": 12.434,
      "step": 81
    },
    {
      "epoch": 1.607843137254902,
      "grad_norm": 0.2352747619152069,
      "learning_rate": 5.014685314685315e-05,
      "loss": 12.4278,
      "step": 82
    },
    {
      "epoch": 1.6274509803921569,
      "grad_norm": 0.14110158383846283,
      "learning_rate": 4.9440559440559444e-05,
      "loss": 12.4396,
      "step": 83
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.1315547674894333,
      "learning_rate": 4.873426573426573e-05,
      "loss": 12.4396,
      "step": 84
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.13215842843055725,
      "learning_rate": 4.802797202797203e-05,
      "loss": 12.4354,
      "step": 85
    },
    {
      "epoch": 1.6862745098039216,
      "grad_norm": 0.14507846534252167,
      "learning_rate": 4.7321678321678324e-05,
      "loss": 12.4371,
      "step": 86
    },
    {
      "epoch": 1.7058823529411766,
      "grad_norm": 0.1558404117822647,
      "learning_rate": 4.661538461538462e-05,
      "loss": 12.4326,
      "step": 87
    },
    {
      "epoch": 1.7254901960784315,
      "grad_norm": 0.16582131385803223,
      "learning_rate": 4.590909090909091e-05,
      "loss": 12.4294,
      "step": 88
    },
    {
      "epoch": 1.7450980392156863,
      "grad_norm": 0.12328918278217316,
      "learning_rate": 4.52027972027972e-05,
      "loss": 12.4346,
      "step": 89
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.10181323438882828,
      "learning_rate": 4.44965034965035e-05,
      "loss": 12.4404,
      "step": 90
    },
    {
      "epoch": 1.784313725490196,
      "grad_norm": 0.11123471707105637,
      "learning_rate": 4.379020979020979e-05,
      "loss": 12.435,
      "step": 91
    },
    {
      "epoch": 1.803921568627451,
      "grad_norm": 0.11661916226148605,
      "learning_rate": 4.308391608391608e-05,
      "loss": 12.4312,
      "step": 92
    },
    {
      "epoch": 1.8235294117647058,
      "grad_norm": 0.09935862571001053,
      "learning_rate": 4.237762237762238e-05,
      "loss": 12.4318,
      "step": 93
    },
    {
      "epoch": 1.843137254901961,
      "grad_norm": 0.12922266125679016,
      "learning_rate": 4.167132867132867e-05,
      "loss": 12.4327,
      "step": 94
    },
    {
      "epoch": 1.8627450980392157,
      "grad_norm": 0.1282566338777542,
      "learning_rate": 4.096503496503496e-05,
      "loss": 12.4311,
      "step": 95
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.07856478542089462,
      "learning_rate": 4.025874125874126e-05,
      "loss": 12.4363,
      "step": 96
    },
    {
      "epoch": 1.9019607843137254,
      "grad_norm": 0.09109707176685333,
      "learning_rate": 3.955244755244755e-05,
      "loss": 12.4274,
      "step": 97
    },
    {
      "epoch": 1.9215686274509802,
      "grad_norm": 0.09043984115123749,
      "learning_rate": 3.884615384615385e-05,
      "loss": 12.4345,
      "step": 98
    },
    {
      "epoch": 1.9411764705882353,
      "grad_norm": 0.09672176837921143,
      "learning_rate": 3.8139860139860137e-05,
      "loss": 12.4294,
      "step": 99
    },
    {
      "epoch": 1.9607843137254903,
      "grad_norm": 0.104476198554039,
      "learning_rate": 3.743356643356643e-05,
      "loss": 12.4295,
      "step": 100
    },
    {
      "epoch": 1.9607843137254903,
      "eval_loss": 12.426092147827148,
      "eval_runtime": 0.7943,
      "eval_samples_per_second": 866.219,
      "eval_steps_per_second": 27.699,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 153,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3085330022400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}