{
  "best_metric": 0.00040800104034133255,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 2.9304029304029307,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014652014652014652,
      "grad_norm": 7.171113967895508,
      "learning_rate": 1e-05,
      "loss": 5.7842,
      "step": 1
    },
    {
      "epoch": 0.014652014652014652,
      "eval_loss": 1.6904494762420654,
      "eval_runtime": 12.2974,
      "eval_samples_per_second": 9.352,
      "eval_steps_per_second": 2.358,
      "step": 1
    },
    {
      "epoch": 0.029304029304029304,
      "grad_norm": 8.249961853027344,
      "learning_rate": 2e-05,
      "loss": 5.4593,
      "step": 2
    },
    {
      "epoch": 0.04395604395604396,
      "grad_norm": 8.18285846710205,
      "learning_rate": 3e-05,
      "loss": 6.2386,
      "step": 3
    },
    {
      "epoch": 0.05860805860805861,
      "grad_norm": 7.577951431274414,
      "learning_rate": 4e-05,
      "loss": 6.139,
      "step": 4
    },
    {
      "epoch": 0.07326007326007326,
      "grad_norm": 7.315019607543945,
      "learning_rate": 5e-05,
      "loss": 6.4635,
      "step": 5
    },
    {
      "epoch": 0.08791208791208792,
      "grad_norm": 9.246410369873047,
      "learning_rate": 6e-05,
      "loss": 5.4756,
      "step": 6
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 7.5367431640625,
      "learning_rate": 7e-05,
      "loss": 5.1481,
      "step": 7
    },
    {
      "epoch": 0.11721611721611722,
      "grad_norm": 7.304732322692871,
      "learning_rate": 8e-05,
      "loss": 4.6305,
      "step": 8
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 8.40855598449707,
      "learning_rate": 9e-05,
      "loss": 4.0095,
      "step": 9
    },
    {
      "epoch": 0.14652014652014653,
      "grad_norm": 8.29879093170166,
      "learning_rate": 0.0001,
      "loss": 3.8675,
      "step": 10
    },
    {
      "epoch": 0.16117216117216118,
      "grad_norm": 9.616212844848633,
      "learning_rate": 9.999316524962345e-05,
      "loss": 3.5677,
      "step": 11
    },
    {
      "epoch": 0.17582417582417584,
      "grad_norm": 10.818434715270996,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.9394,
      "step": 12
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 7.230936527252197,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.2885,
      "step": 13
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 7.360617160797119,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.7575,
      "step": 14
    },
    {
      "epoch": 0.21978021978021978,
      "grad_norm": 8.605161666870117,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.8599,
      "step": 15
    },
    {
      "epoch": 0.23443223443223443,
      "grad_norm": 17.73501968383789,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.7667,
      "step": 16
    },
    {
      "epoch": 0.2490842490842491,
      "grad_norm": 17.304738998413086,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.2396,
      "step": 17
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 32.71799850463867,
      "learning_rate": 9.956320346634876e-05,
      "loss": 5.2437,
      "step": 18
    },
    {
      "epoch": 0.2783882783882784,
      "grad_norm": 20.27690315246582,
      "learning_rate": 9.944739353007344e-05,
      "loss": 3.6841,
      "step": 19
    },
    {
      "epoch": 0.29304029304029305,
      "grad_norm": 12.349483489990234,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.995,
      "step": 20
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 8.449111938476562,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.9495,
      "step": 21
    },
    {
      "epoch": 0.32234432234432236,
      "grad_norm": 7.5645833015441895,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.8086,
      "step": 22
    },
    {
      "epoch": 0.336996336996337,
      "grad_norm": 7.12092399597168,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.4162,
      "step": 23
    },
    {
      "epoch": 0.3516483516483517,
      "grad_norm": 7.32703971862793,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.6227,
      "step": 24
    },
    {
      "epoch": 0.3663003663003663,
      "grad_norm": 6.202816486358643,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.2803,
      "step": 25
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 3.8677966594696045,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.5428,
      "step": 26
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 4.151014804840088,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4794,
      "step": 27
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 3.6379082202911377,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4734,
      "step": 28
    },
    {
      "epoch": 0.4249084249084249,
      "grad_norm": 4.096688747406006,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2979,
      "step": 29
    },
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 8.675773620605469,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.2047,
      "step": 30
    },
    {
      "epoch": 0.4542124542124542,
      "grad_norm": 2.3221731185913086,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.1207,
      "step": 31
    },
    {
      "epoch": 0.46886446886446886,
      "grad_norm": 2.4593706130981445,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2031,
      "step": 32
    },
    {
      "epoch": 0.4835164835164835,
      "grad_norm": 4.812369346618652,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.357,
      "step": 33
    },
    {
      "epoch": 0.4981684981684982,
      "grad_norm": 3.705998659133911,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.2637,
      "step": 34
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 22.32494354248047,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.2922,
      "step": 35
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 16.230104446411133,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.0214,
      "step": 36
    },
    {
      "epoch": 0.5421245421245421,
      "grad_norm": 11.69698429107666,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.2805,
      "step": 37
    },
    {
      "epoch": 0.5567765567765568,
      "grad_norm": 7.815195083618164,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.214,
      "step": 38
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 4.955883502960205,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7645,
      "step": 39
    },
    {
      "epoch": 0.5860805860805861,
      "grad_norm": 7.214204788208008,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.6162,
      "step": 40
    },
    {
      "epoch": 0.6007326007326007,
      "grad_norm": 4.006315231323242,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.3474,
      "step": 41
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 2.4061203002929688,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.226,
      "step": 42
    },
    {
      "epoch": 0.63003663003663,
      "grad_norm": 2.47221302986145,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.1974,
      "step": 43
    },
    {
      "epoch": 0.6446886446886447,
      "grad_norm": 2.361098527908325,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.227,
      "step": 44
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 1.537760853767395,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.1373,
      "step": 45
    },
    {
      "epoch": 0.673992673992674,
      "grad_norm": 1.766296148300171,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.1352,
      "step": 46
    },
    {
      "epoch": 0.6886446886446886,
      "grad_norm": 1.1294655799865723,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0913,
      "step": 47
    },
    {
      "epoch": 0.7032967032967034,
      "grad_norm": 0.9794086813926697,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0357,
      "step": 48
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 2.3417065143585205,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.0325,
      "step": 49
    },
    {
      "epoch": 0.7326007326007326,
      "grad_norm": 5.738649368286133,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0837,
      "step": 50
    },
    {
      "epoch": 0.7326007326007326,
      "eval_loss": 0.15919870138168335,
      "eval_runtime": 12.4815,
      "eval_samples_per_second": 9.214,
      "eval_steps_per_second": 2.323,
      "step": 50
    },
    {
      "epoch": 0.7472527472527473,
      "grad_norm": 2.0001914501190186,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.0272,
      "step": 51
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 10.208358764648438,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.8891,
      "step": 52
    },
    {
      "epoch": 0.7765567765567766,
      "grad_norm": 8.16737174987793,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0669,
      "step": 53
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 8.048969268798828,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.6473,
      "step": 54
    },
    {
      "epoch": 0.8058608058608059,
      "grad_norm": 5.047337055206299,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.3801,
      "step": 55
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 3.1520726680755615,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.1758,
      "step": 56
    },
    {
      "epoch": 0.8351648351648352,
      "grad_norm": 5.624608516693115,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.3011,
      "step": 57
    },
    {
      "epoch": 0.8498168498168498,
      "grad_norm": 6.7333807945251465,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.1641,
      "step": 58
    },
    {
      "epoch": 0.8644688644688645,
      "grad_norm": 2.139389991760254,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.087,
      "step": 59
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 2.7562003135681152,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.174,
      "step": 60
    },
    {
      "epoch": 0.8937728937728938,
      "grad_norm": 2.383864402770996,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.163,
      "step": 61
    },
    {
      "epoch": 0.9084249084249084,
      "grad_norm": 3.657308578491211,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.0653,
      "step": 62
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 1.1119287014007568,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.0532,
      "step": 63
    },
    {
      "epoch": 0.9377289377289377,
      "grad_norm": 0.31136569380760193,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.0164,
      "step": 64
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.4584847390651703,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.018,
      "step": 65
    },
    {
      "epoch": 0.967032967032967,
      "grad_norm": 0.49475133419036865,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.0154,
      "step": 66
    },
    {
      "epoch": 0.9816849816849816,
      "grad_norm": 0.5075758099555969,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0151,
      "step": 67
    },
    {
      "epoch": 0.9963369963369964,
      "grad_norm": 0.4408712685108185,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.0177,
      "step": 68
    },
    {
      "epoch": 1.010989010989011,
      "grad_norm": 5.486754417419434,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7785,
      "step": 69
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 4.421342372894287,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6265,
      "step": 70
    },
    {
      "epoch": 1.0402930402930404,
      "grad_norm": 3.824197769165039,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.4132,
      "step": 71
    },
    {
      "epoch": 1.054945054945055,
      "grad_norm": 3.349147081375122,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.2662,
      "step": 72
    },
    {
      "epoch": 1.0695970695970696,
      "grad_norm": 1.882283329963684,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.1482,
      "step": 73
    },
    {
      "epoch": 1.0842490842490842,
      "grad_norm": 5.016214847564697,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.2292,
      "step": 74
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 3.190034866333008,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.1483,
      "step": 75
    },
    {
      "epoch": 1.1135531135531136,
      "grad_norm": 2.186093330383301,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.1412,
      "step": 76
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 2.1952931880950928,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.0725,
      "step": 77
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.4728530645370483,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0392,
      "step": 78
    },
    {
      "epoch": 1.1575091575091574,
      "grad_norm": 2.180964708328247,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.0234,
      "step": 79
    },
    {
      "epoch": 1.1721611721611722,
      "grad_norm": 5.380253791809082,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0168,
      "step": 80
    },
    {
      "epoch": 1.1868131868131868,
      "grad_norm": 1.3068042993545532,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0065,
      "step": 81
    },
    {
      "epoch": 1.2014652014652014,
      "grad_norm": 0.17705301940441132,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0028,
      "step": 82
    },
    {
      "epoch": 1.2161172161172162,
      "grad_norm": 0.6389381885528564,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0035,
      "step": 83
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.1175999790430069,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.002,
      "step": 84
    },
    {
      "epoch": 1.2454212454212454,
      "grad_norm": 0.5508256554603577,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0035,
      "step": 85
    },
    {
      "epoch": 1.26007326007326,
      "grad_norm": 6.405404567718506,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5281,
      "step": 86
    },
    {
      "epoch": 1.2747252747252746,
      "grad_norm": 6.507776260375977,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3845,
      "step": 87
    },
    {
      "epoch": 1.2893772893772895,
      "grad_norm": 9.523035049438477,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.5877,
      "step": 88
    },
    {
      "epoch": 1.304029304029304,
      "grad_norm": 3.862123489379883,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.176,
      "step": 89
    },
    {
      "epoch": 1.3186813186813187,
      "grad_norm": 2.078538179397583,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1199,
      "step": 90
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.530057668685913,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.082,
      "step": 91
    },
    {
      "epoch": 1.347985347985348,
      "grad_norm": 2.7264068126678467,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0613,
      "step": 92
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.5741703510284424,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0192,
      "step": 93
    },
    {
      "epoch": 1.3772893772893773,
      "grad_norm": 0.3630363345146179,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0101,
      "step": 94
    },
    {
      "epoch": 1.3919413919413919,
      "grad_norm": 1.366981029510498,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0193,
      "step": 95
    },
    {
      "epoch": 1.4065934065934065,
      "grad_norm": 1.431036114692688,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.005,
      "step": 96
    },
    {
      "epoch": 1.4212454212454213,
      "grad_norm": 1.2951421737670898,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0047,
      "step": 97
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 0.13851676881313324,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0019,
      "step": 98
    },
    {
      "epoch": 1.4505494505494505,
      "grad_norm": 2.1086246967315674,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0044,
      "step": 99
    },
    {
      "epoch": 1.4652014652014653,
      "grad_norm": 1.2437102794647217,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0196,
      "step": 100
    },
    {
      "epoch": 1.4652014652014653,
      "eval_loss": 0.028146879747509956,
      "eval_runtime": 12.4855,
      "eval_samples_per_second": 9.211,
      "eval_steps_per_second": 2.323,
      "step": 100
    },
    {
      "epoch": 1.47985347985348,
      "grad_norm": 0.3147693872451782,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.0016,
      "step": 101
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.563218355178833,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0191,
      "step": 102
    },
    {
      "epoch": 1.5091575091575091,
      "grad_norm": 3.387148380279541,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.3576,
      "step": 103
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 4.037352561950684,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.3353,
      "step": 104
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 4.494482517242432,
      "learning_rate": 5e-05,
      "loss": 0.2089,
      "step": 105
    },
    {
      "epoch": 1.5531135531135531,
      "grad_norm": 2.983988046646118,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.0788,
      "step": 106
    },
    {
      "epoch": 1.5677655677655677,
      "grad_norm": 2.5249171257019043,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.034,
      "step": 107
    },
    {
      "epoch": 1.5824175824175826,
      "grad_norm": 2.030799627304077,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0645,
      "step": 108
    },
    {
      "epoch": 1.5970695970695972,
      "grad_norm": 0.3472387492656708,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.011,
      "step": 109
    },
    {
      "epoch": 1.6117216117216118,
      "grad_norm": 0.7935450077056885,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.0325,
      "step": 110
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.5581241846084595,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.0086,
      "step": 111
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 0.3660702109336853,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.0033,
      "step": 112
    },
    {
      "epoch": 1.6556776556776556,
      "grad_norm": 0.160755455493927,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.0021,
      "step": 113
    },
    {
      "epoch": 1.6703296703296702,
      "grad_norm": 0.3223567306995392,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.0025,
      "step": 114
    },
    {
      "epoch": 1.684981684981685,
      "grad_norm": 0.051478661596775055,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.0011,
      "step": 115
    },
    {
      "epoch": 1.6996336996336996,
      "grad_norm": 0.030928069725632668,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.0009,
      "step": 116
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.05390363559126854,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.0011,
      "step": 117
    },
    {
      "epoch": 1.728937728937729,
      "grad_norm": 0.1354142725467682,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.0019,
      "step": 118
    },
    {
      "epoch": 1.7435897435897436,
      "grad_norm": 0.16326498985290527,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.0021,
      "step": 119
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 1.7877599000930786,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.1456,
      "step": 120
    },
    {
      "epoch": 1.7728937728937728,
      "grad_norm": 1.529577612876892,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.1205,
      "step": 121
    },
    {
      "epoch": 1.7875457875457874,
      "grad_norm": 2.127880334854126,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.0538,
      "step": 122
    },
    {
      "epoch": 1.8021978021978022,
      "grad_norm": 1.0004794597625732,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0451,
      "step": 123
    },
    {
      "epoch": 1.8168498168498168,
      "grad_norm": 1.099411129951477,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0245,
      "step": 124
    },
    {
      "epoch": 1.8315018315018317,
      "grad_norm": 0.34262022376060486,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.0185,
      "step": 125
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 1.1417449712753296,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0356,
      "step": 126
    },
    {
      "epoch": 1.8608058608058609,
      "grad_norm": 0.5071332454681396,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.0063,
      "step": 127
    },
    {
      "epoch": 1.8754578754578755,
      "grad_norm": 0.15192635357379913,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0021,
      "step": 128
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.12583224475383759,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0032,
      "step": 129
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.005871925503015518,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0004,
      "step": 130
    },
    {
      "epoch": 1.9194139194139193,
      "grad_norm": 0.005865914281457663,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.0004,
      "step": 131
    },
    {
      "epoch": 1.934065934065934,
      "grad_norm": 0.005555153824388981,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0004,
      "step": 132
    },
    {
      "epoch": 1.9487179487179487,
      "grad_norm": 0.005144666414707899,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.0003,
      "step": 133
    },
    {
      "epoch": 1.9633699633699635,
      "grad_norm": 0.011223836801946163,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.0004,
      "step": 134
    },
    {
      "epoch": 1.978021978021978,
      "grad_norm": 0.11967798322439194,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.0011,
      "step": 135
    },
    {
      "epoch": 1.9926739926739927,
      "grad_norm": 0.04005035012960434,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0006,
      "step": 136
    },
    {
      "epoch": 2.0073260073260073,
      "grad_norm": 1.9251799583435059,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0316,
      "step": 137
    },
    {
      "epoch": 2.021978021978022,
      "grad_norm": 6.871854305267334,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.1656,
      "step": 138
    },
    {
      "epoch": 2.0366300366300365,
      "grad_norm": 0.7605661153793335,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0212,
      "step": 139
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 0.46010249853134155,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0068,
      "step": 140
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.3990759551525116,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0049,
      "step": 141
    },
    {
      "epoch": 2.0805860805860807,
      "grad_norm": 0.12303099781274796,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0027,
      "step": 142
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.10300181806087494,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0018,
      "step": 143
    },
    {
      "epoch": 2.10989010989011,
      "grad_norm": 0.0634176954627037,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0013,
      "step": 144
    },
    {
      "epoch": 2.1245421245421245,
      "grad_norm": 0.06438025087118149,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0009,
      "step": 145
    },
    {
      "epoch": 2.139194139194139,
      "grad_norm": 0.23805208504199982,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0014,
      "step": 146
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.005752360913902521,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0004,
      "step": 147
    },
    {
      "epoch": 2.1684981684981683,
      "grad_norm": 0.0045188963413238525,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0004,
      "step": 148
    },
    {
      "epoch": 2.183150183150183,
      "grad_norm": 0.004888174124062061,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0004,
      "step": 149
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.004351768642663956,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0003,
      "step": 150
    },
    {
      "epoch": 2.197802197802198,
      "eval_loss": 0.002366294851526618,
      "eval_runtime": 12.4843,
      "eval_samples_per_second": 9.212,
      "eval_steps_per_second": 2.323,
      "step": 150
    },
    {
      "epoch": 2.2124542124542126,
      "grad_norm": 0.004610234871506691,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.0003,
      "step": 151
    },
    {
      "epoch": 2.227106227106227,
      "grad_norm": 0.005967860575765371,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.0003,
      "step": 152
    },
    {
      "epoch": 2.241758241758242,
      "grad_norm": 0.2738629877567291,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.0044,
      "step": 153
    },
    {
      "epoch": 2.2564102564102564,
      "grad_norm": 2.27718448638916,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0157,
      "step": 154
    },
    {
      "epoch": 2.271062271062271,
      "grad_norm": 3.549816608428955,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.1068,
      "step": 155
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.4325025677680969,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0076,
      "step": 156
    },
    {
      "epoch": 2.3003663003663,
      "grad_norm": 0.11416045576334,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.0016,
      "step": 157
    },
    {
      "epoch": 2.315018315018315,
      "grad_norm": 0.021142257377505302,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0013,
      "step": 158
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.025679556652903557,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0013,
      "step": 159
    },
    {
      "epoch": 2.3443223443223444,
      "grad_norm": 0.15294696390628815,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0019,
      "step": 160
    },
    {
      "epoch": 2.358974358974359,
      "grad_norm": 0.015616877004504204,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.0008,
      "step": 161
    },
    {
      "epoch": 2.3736263736263736,
      "grad_norm": 0.037164390087127686,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0009,
      "step": 162
    },
    {
      "epoch": 2.3882783882783882,
      "grad_norm": 0.026139285415410995,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.0007,
      "step": 163
    },
    {
      "epoch": 2.402930402930403,
      "grad_norm": 0.004933775402605534,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0004,
      "step": 164
    },
    {
      "epoch": 2.4175824175824174,
      "grad_norm": 0.004545349627733231,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0004,
      "step": 165
    },
    {
      "epoch": 2.4322344322344325,
      "grad_norm": 0.004212342668324709,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0003,
      "step": 166
    },
    {
      "epoch": 2.446886446886447,
      "grad_norm": 0.006587883923202753,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0003,
      "step": 167
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.0037000991869717836,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0003,
      "step": 168
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.0037556381430476904,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0003,
      "step": 169
    },
    {
      "epoch": 2.490842490842491,
      "grad_norm": 0.005149703472852707,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0003,
      "step": 170
    },
    {
      "epoch": 2.5054945054945055,
      "grad_norm": 0.0907173827290535,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0037,
      "step": 171
    },
    {
      "epoch": 2.52014652014652,
      "grad_norm": 0.22464261949062347,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0075,
      "step": 172
    },
    {
      "epoch": 2.5347985347985347,
      "grad_norm": 0.15038616955280304,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.0039,
      "step": 173
    },
    {
      "epoch": 2.5494505494505493,
      "grad_norm": 0.01993418298661709,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0013,
      "step": 174
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 0.02634168602526188,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.0013,
      "step": 175
    },
    {
      "epoch": 2.578754578754579,
      "grad_norm": 0.01802430860698223,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0011,
      "step": 176
    },
    {
      "epoch": 2.5934065934065935,
      "grad_norm": 0.01721012219786644,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0008,
      "step": 177
    },
    {
      "epoch": 2.608058608058608,
      "grad_norm": 0.012717255391180515,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.0007,
      "step": 178
    },
    {
      "epoch": 2.6227106227106227,
      "grad_norm": 0.012749647721648216,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.0005,
      "step": 179
    },
    {
      "epoch": 2.6373626373626373,
      "grad_norm": 0.006188936997205019,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0004,
      "step": 180
    },
    {
      "epoch": 2.652014652014652,
      "grad_norm": 0.0052911401726305485,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0004,
      "step": 181
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.004062323365360498,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0003,
      "step": 182
    },
    {
      "epoch": 2.6813186813186816,
      "grad_norm": 0.0036065669264644384,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0003,
      "step": 183
    },
    {
      "epoch": 2.695970695970696,
      "grad_norm": 0.0035708709619939327,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0003,
      "step": 184
    },
    {
      "epoch": 2.7106227106227108,
      "grad_norm": 0.004761743824928999,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.0003,
      "step": 185
    },
    {
      "epoch": 2.7252747252747254,
      "grad_norm": 0.005422662943601608,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0003,
      "step": 186
    },
    {
      "epoch": 2.73992673992674,
      "grad_norm": 0.004277673549950123,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0003,
      "step": 187
    },
    {
      "epoch": 2.7545787545787546,
      "grad_norm": 0.0628623515367508,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.003,
      "step": 188
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.12090010195970535,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0053,
      "step": 189
    },
    {
      "epoch": 2.7838827838827838,
      "grad_norm": 0.1661021113395691,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.0044,
      "step": 190
    },
    {
      "epoch": 2.7985347985347984,
      "grad_norm": 0.01576969027519226,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0012,
      "step": 191
    },
    {
      "epoch": 2.813186813186813,
      "grad_norm": 0.017313839867711067,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0012,
      "step": 192
    },
    {
      "epoch": 2.8278388278388276,
      "grad_norm": 0.014690273441374302,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.001,
      "step": 193
    },
    {
      "epoch": 2.8424908424908426,
      "grad_norm": 0.013772205449640751,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0007,
      "step": 194
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.015179033391177654,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0007,
      "step": 195
    },
    {
      "epoch": 2.871794871794872,
      "grad_norm": 0.007945886813104153,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0005,
      "step": 196
    },
    {
      "epoch": 2.8864468864468864,
      "grad_norm": 0.004826374351978302,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0004,
      "step": 197
    },
    {
      "epoch": 2.901098901098901,
      "grad_norm": 0.004543941002339125,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0003,
      "step": 198
    },
    {
      "epoch": 2.9157509157509156,
      "grad_norm": 0.003825519233942032,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0003,
      "step": 199
    },
    {
      "epoch": 2.9304029304029307,
      "grad_norm": 0.004957566969096661,
      "learning_rate": 0.0,
      "loss": 0.0003,
      "step": 200
    },
    {
      "epoch": 2.9304029304029307,
      "eval_loss": 0.00040800104034133255,
      "eval_runtime": 12.4899,
      "eval_samples_per_second": 9.207,
      "eval_steps_per_second": 2.322,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.6316661491367936e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}