{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 153,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0196078431372549,
      "grad_norm": 3.726946670212783e-05,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0196078431372549,
      "eval_loss": 11.5,
      "eval_runtime": 1.0786,
      "eval_samples_per_second": 637.837,
      "eval_steps_per_second": 20.396,
      "step": 1
    },
    {
      "epoch": 0.0392156862745098,
      "grad_norm": 2.546375799283851e-05,
      "learning_rate": 2.0200000000000003e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 2.7978725483990274e-05,
      "learning_rate": 3.0299999999999998e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 2.6746447474579327e-05,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.09803921568627451,
      "grad_norm": 3.7722737033618614e-05,
      "learning_rate": 5.05e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 4.788485239259899e-05,
      "learning_rate": 6.0599999999999996e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.13725490196078433,
      "grad_norm": 4.837014421354979e-05,
      "learning_rate": 7.07e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 3.2393749279435724e-05,
      "learning_rate": 8.080000000000001e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.17647058823529413,
      "grad_norm": 2.726590719248634e-05,
      "learning_rate": 9.09e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 2.6114654247066937e-05,
      "learning_rate": 0.000101,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.21568627450980393,
      "grad_norm": 4.485388126340695e-05,
      "learning_rate": 0.0001002937062937063,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 3.979922257713042e-05,
      "learning_rate": 9.958741258741259e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.2549019607843137,
      "grad_norm": 5.8709450968308374e-05,
      "learning_rate": 9.888111888111889e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.27450980392156865,
      "grad_norm": 3.613016087911092e-05,
      "learning_rate": 9.817482517482517e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.29411764705882354,
      "grad_norm": 3.2821957574924454e-05,
      "learning_rate": 9.746853146853147e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.3137254901960784,
      "grad_norm": 4.67407880933024e-05,
      "learning_rate": 9.676223776223776e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 4.4002754293615e-05,
      "learning_rate": 9.605594405594406e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 6.495012348750606e-05,
      "learning_rate": 9.534965034965035e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.37254901960784315,
      "grad_norm": 5.5453569075325504e-05,
      "learning_rate": 9.464335664335665e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 4.442952558747493e-05,
      "learning_rate": 9.393706293706294e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.4117647058823529,
      "grad_norm": 5.454928395920433e-05,
      "learning_rate": 9.323076923076924e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.43137254901960786,
      "grad_norm": 6.270724406931549e-05,
      "learning_rate": 9.252447552447552e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.45098039215686275,
      "grad_norm": 7.197450031526387e-05,
      "learning_rate": 9.181818181818182e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 8.590270590502769e-05,
      "learning_rate": 9.111188811188811e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.49019607843137253,
      "grad_norm": 9.847155888564885e-05,
      "learning_rate": 9.04055944055944e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.5098039215686274,
      "grad_norm": 8.442815305897966e-05,
      "learning_rate": 8.96993006993007e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.5294117647058824,
      "grad_norm": 5.8915611589327455e-05,
      "learning_rate": 8.8993006993007e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.5490196078431373,
      "grad_norm": 8.398713544011116e-05,
      "learning_rate": 8.828671328671329e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.5686274509803921,
      "grad_norm": 7.030486449366435e-05,
      "learning_rate": 8.758041958041957e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 7.76613742345944e-05,
      "learning_rate": 8.687412587412587e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.6078431372549019,
      "grad_norm": 0.00013637992378789932,
      "learning_rate": 8.616783216783216e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.6274509803921569,
      "grad_norm": 0.00010595240019029006,
      "learning_rate": 8.546153846153846e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.6470588235294118,
      "grad_norm": 7.119768270058557e-05,
      "learning_rate": 8.475524475524476e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 9.644283272791654e-05,
      "learning_rate": 8.404895104895105e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.6862745098039216,
      "grad_norm": 0.00010261753050144762,
      "learning_rate": 8.334265734265735e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.00011962924327235669,
      "learning_rate": 8.263636363636364e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.7254901960784313,
      "grad_norm": 0.00013324664905667305,
      "learning_rate": 8.193006993006992e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.7450980392156863,
      "grad_norm": 0.00013165611017029732,
      "learning_rate": 8.122377622377622e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.7647058823529411,
      "grad_norm": 0.00011035199713660404,
      "learning_rate": 8.051748251748251e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 8.712222916074097e-05,
      "learning_rate": 7.981118881118881e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.803921568627451,
      "grad_norm": 0.00012872941442765296,
      "learning_rate": 7.91048951048951e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 0.0001236675016116351,
      "learning_rate": 7.83986013986014e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.8431372549019608,
      "grad_norm": 0.00017374215531162918,
      "learning_rate": 7.76923076923077e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.8627450980392157,
      "grad_norm": 0.00016970356227830052,
      "learning_rate": 7.698601398601398e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.8823529411764706,
      "grad_norm": 0.00013173974002711475,
      "learning_rate": 7.627972027972027e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.9019607843137255,
      "grad_norm": 0.00014211614325176924,
      "learning_rate": 7.557342657342657e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.9215686274509803,
      "grad_norm": 0.00012073171092197299,
      "learning_rate": 7.486713286713286e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.0001576584909344092,
      "learning_rate": 7.416083916083916e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.9607843137254902,
      "grad_norm": 0.00013290104106999934,
      "learning_rate": 7.345454545454545e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.9803921568627451,
      "grad_norm": 0.00020503792620729655,
      "learning_rate": 7.274825174825175e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.9803921568627451,
      "eval_loss": 11.5,
      "eval_runtime": 0.6466,
      "eval_samples_per_second": 1064.006,
      "eval_steps_per_second": 34.023,
      "step": 50
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.0001408671378158033,
      "learning_rate": 7.204195804195805e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 1.0196078431372548,
      "grad_norm": 0.00018512530368752778,
      "learning_rate": 7.133566433566433e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 1.0392156862745099,
      "grad_norm": 0.00012292621249798685,
      "learning_rate": 7.062937062937062e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 0.00018587136582937092,
      "learning_rate": 6.992307692307692e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 1.0784313725490196,
      "grad_norm": 0.00020599419076461345,
      "learning_rate": 6.921678321678321e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 1.0980392156862746,
      "grad_norm": 0.00018194003496319056,
      "learning_rate": 6.851048951048951e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 1.1176470588235294,
      "grad_norm": 0.00020641495939344168,
      "learning_rate": 6.78041958041958e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 1.1372549019607843,
      "grad_norm": 0.00022939956397749484,
      "learning_rate": 6.70979020979021e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 1.156862745098039,
      "grad_norm": 0.00016353426326531917,
      "learning_rate": 6.639160839160838e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.000171757405041717,
      "learning_rate": 6.568531468531468e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 1.196078431372549,
      "grad_norm": 0.00018360056856181473,
      "learning_rate": 6.497902097902097e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 1.215686274509804,
      "grad_norm": 0.00025392137467861176,
      "learning_rate": 6.427272727272727e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 1.2352941176470589,
      "grad_norm": 0.0002807354903779924,
      "learning_rate": 6.356643356643356e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 1.2549019607843137,
      "grad_norm": 0.00026548118330538273,
      "learning_rate": 6.286013986013986e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 1.2745098039215685,
      "grad_norm": 0.00016954861348494887,
      "learning_rate": 6.215384615384615e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 0.0002116493706125766,
      "learning_rate": 6.144755244755245e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 1.3137254901960784,
      "grad_norm": 0.00016135629266500473,
      "learning_rate": 6.074125874125874e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.00022329531202558428,
      "learning_rate": 6.0034965034965033e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 1.3529411764705883,
      "grad_norm": 0.00028010981623083353,
      "learning_rate": 5.932867132867133e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 1.3725490196078431,
      "grad_norm": 0.00031517096795141697,
      "learning_rate": 5.8622377622377624e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 1.392156862745098,
      "grad_norm": 0.00030739433714188635,
      "learning_rate": 5.791608391608392e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.00018070408259518445,
      "learning_rate": 5.7209790209790215e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 1.4313725490196079,
      "grad_norm": 0.00026431979495100677,
      "learning_rate": 5.650349650349651e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 1.4509803921568627,
      "grad_norm": 0.00020367998513393104,
      "learning_rate": 5.579720279720279e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 0.00026323492056690156,
      "learning_rate": 5.509090909090909e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 1.4901960784313726,
      "grad_norm": 0.00034865838824771345,
      "learning_rate": 5.438461538461538e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 1.5098039215686274,
      "grad_norm": 0.00023557976237498224,
      "learning_rate": 5.367832167832168e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 0.00021717116760555655,
      "learning_rate": 5.2972027972027974e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 1.5490196078431373,
      "grad_norm": 0.00027765179402194917,
      "learning_rate": 5.226573426573427e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": 0.00025422070757485926,
      "learning_rate": 5.1559440559440565e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 1.5882352941176472,
      "grad_norm": 0.0003297334478702396,
      "learning_rate": 5.085314685314686e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 1.607843137254902,
      "grad_norm": 0.0004201807314530015,
      "learning_rate": 5.014685314685315e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 1.6274509803921569,
      "grad_norm": 0.0003534739080350846,
      "learning_rate": 4.9440559440559444e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.00024288770509883761,
      "learning_rate": 4.873426573426573e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.0002575070830062032,
      "learning_rate": 4.802797202797203e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 1.6862745098039216,
      "grad_norm": 0.00034273709752596915,
      "learning_rate": 4.7321678321678324e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 1.7058823529411766,
      "grad_norm": 0.0003354206564836204,
      "learning_rate": 4.661538461538462e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 1.7254901960784315,
      "grad_norm": 0.0002988223859574646,
      "learning_rate": 4.590909090909091e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 1.7450980392156863,
      "grad_norm": 0.0003722968394868076,
      "learning_rate": 4.52027972027972e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.00026949227321892977,
      "learning_rate": 4.44965034965035e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 1.784313725490196,
      "grad_norm": 0.0003130983968731016,
      "learning_rate": 4.379020979020979e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 1.803921568627451,
      "grad_norm": 0.00026243989123031497,
      "learning_rate": 4.308391608391608e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 1.8235294117647058,
      "grad_norm": 0.00027229124680161476,
      "learning_rate": 4.237762237762238e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 1.843137254901961,
      "grad_norm": 0.00035372612182982266,
      "learning_rate": 4.167132867132867e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 1.8627450980392157,
      "grad_norm": 0.00039300689240917563,
      "learning_rate": 4.096503496503496e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.0002876557700801641,
      "learning_rate": 4.025874125874126e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 1.9019607843137254,
      "grad_norm": 0.00022314459783956409,
      "learning_rate": 3.955244755244755e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 1.9215686274509802,
      "grad_norm": 0.00026848912239074707,
      "learning_rate": 3.884615384615385e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 1.9411764705882353,
      "grad_norm": 0.00027283094823360443,
      "learning_rate": 3.8139860139860137e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 1.9607843137254903,
      "grad_norm": 0.0004197805537842214,
      "learning_rate": 3.743356643356643e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 1.9607843137254903,
      "eval_loss": 11.5,
      "eval_runtime": 0.4631,
      "eval_samples_per_second": 1485.776,
      "eval_steps_per_second": 47.51,
      "step": 100
    },
    {
      "epoch": 1.9803921568627452,
      "grad_norm": 0.0004091408336535096,
      "learning_rate": 3.672727272727273e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.00023171439534053206,
      "learning_rate": 3.602097902097902e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 2.019607843137255,
      "grad_norm": 0.00039071572246029973,
      "learning_rate": 3.531468531468531e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 2.0392156862745097,
      "grad_norm": 0.00026147387688979506,
      "learning_rate": 3.460839160839161e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 2.0588235294117645,
      "grad_norm": 0.0003073408151976764,
      "learning_rate": 3.39020979020979e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 2.0784313725490198,
      "grad_norm": 0.00033114402322098613,
      "learning_rate": 3.319580419580419e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 2.0980392156862746,
      "grad_norm": 0.00034095364389941096,
      "learning_rate": 3.2489510489510486e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.0003768288588616997,
      "learning_rate": 3.178321678321678e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 2.1372549019607843,
      "grad_norm": 0.00041196009260602295,
      "learning_rate": 3.107692307692308e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 2.156862745098039,
      "grad_norm": 0.0002800294605549425,
      "learning_rate": 3.037062937062937e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 2.176470588235294,
      "grad_norm": 0.000317448255373165,
      "learning_rate": 2.9664335664335664e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 2.196078431372549,
      "grad_norm": 0.0003218978818040341,
      "learning_rate": 2.895804195804196e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 2.215686274509804,
      "grad_norm": 0.00034446208155713975,
      "learning_rate": 2.8251748251748255e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.0004481629002839327,
      "learning_rate": 2.7545454545454544e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 2.2549019607843137,
      "grad_norm": 0.000561642344109714,
      "learning_rate": 2.683916083916084e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 2.2745098039215685,
      "grad_norm": 0.0004017452010884881,
      "learning_rate": 2.6132867132867135e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 2.2941176470588234,
      "grad_norm": 0.0003688019060064107,
      "learning_rate": 2.542657342657343e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 2.313725490196078,
      "grad_norm": 0.0004349400696810335,
      "learning_rate": 2.4720279720279722e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.00039143659523688257,
      "learning_rate": 2.4013986013986014e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.0004510066064540297,
      "learning_rate": 2.330769230769231e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 2.372549019607843,
      "grad_norm": 0.0004265211464371532,
      "learning_rate": 2.26013986013986e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 2.392156862745098,
      "grad_norm": 0.00033641376649029553,
      "learning_rate": 2.1895104895104893e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 2.411764705882353,
      "grad_norm": 0.00030129088554531336,
      "learning_rate": 2.118881118881119e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 2.431372549019608,
      "grad_norm": 0.0003684493131004274,
      "learning_rate": 2.048251748251748e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 2.450980392156863,
      "grad_norm": 0.00033330111182294786,
      "learning_rate": 1.9776223776223776e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 0.0004395820142235607,
      "learning_rate": 1.9069930069930068e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 2.4901960784313726,
      "grad_norm": 0.00040403471211902797,
      "learning_rate": 1.8363636363636364e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 2.5098039215686274,
      "grad_norm": 0.00036949978675693274,
      "learning_rate": 1.7657342657342656e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 2.5294117647058822,
      "grad_norm": 0.0002842578978743404,
      "learning_rate": 1.695104895104895e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 2.549019607843137,
      "grad_norm": 0.00042267926619388163,
      "learning_rate": 1.6244755244755243e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 2.568627450980392,
      "grad_norm": 0.0003992296988144517,
      "learning_rate": 1.553846153846154e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.0004117234202567488,
      "learning_rate": 1.4832167832167832e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 2.607843137254902,
      "grad_norm": 0.00047374825226143,
      "learning_rate": 1.4125874125874128e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 2.627450980392157,
      "grad_norm": 0.0004487686383072287,
      "learning_rate": 1.341958041958042e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 2.6470588235294117,
      "grad_norm": 0.000370257708709687,
      "learning_rate": 1.2713286713286715e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.00045377013157121837,
      "learning_rate": 1.2006993006993007e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 2.686274509803922,
      "grad_norm": 0.00031919433968141675,
      "learning_rate": 1.13006993006993e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 0.0004188633756712079,
      "learning_rate": 1.0594405594405594e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 2.7254901960784315,
      "grad_norm": 0.0004712211084552109,
      "learning_rate": 9.888111888111888e-06,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 2.7450980392156863,
      "grad_norm": 0.00039058204856701195,
      "learning_rate": 9.181818181818182e-06,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 2.764705882352941,
      "grad_norm": 0.0003306346479803324,
      "learning_rate": 8.475524475524476e-06,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 2.784313725490196,
      "grad_norm": 0.000356231932528317,
      "learning_rate": 7.76923076923077e-06,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 2.803921568627451,
      "grad_norm": 0.0004590142925735563,
      "learning_rate": 7.062937062937064e-06,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.0003684695693664253,
      "learning_rate": 6.3566433566433575e-06,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 2.843137254901961,
      "grad_norm": 0.0005272235721349716,
      "learning_rate": 5.65034965034965e-06,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 2.8627450980392157,
      "grad_norm": 0.0006201413343660533,
      "learning_rate": 4.944055944055944e-06,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 2.8823529411764706,
      "grad_norm": 0.0004487824044190347,
      "learning_rate": 4.237762237762238e-06,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 2.9019607843137254,
      "grad_norm": 0.00032599197584204376,
      "learning_rate": 3.531468531468532e-06,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 2.9215686274509802,
      "grad_norm": 0.00035970291355624795,
      "learning_rate": 2.825174825174825e-06,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.0003452469245530665,
      "learning_rate": 2.118881118881119e-06,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 2.9411764705882355,
      "eval_loss": 11.5,
      "eval_runtime": 1.0845,
      "eval_samples_per_second": 634.42,
      "eval_steps_per_second": 20.287,
      "step": 150
    },
    {
      "epoch": 2.9607843137254903,
      "grad_norm": 0.00048230637912638485,
      "learning_rate": 1.4125874125874126e-06,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 2.980392156862745,
      "grad_norm": 0.0005095683154650033,
      "learning_rate": 7.062937062937063e-07,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.00042812549509108067,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 153
    }
  ],
  "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": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 196809792159744.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}