{
  "best_metric": 12.396309852600098,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.07501875468867217,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00037509377344336085,
      "grad_norm": 0.028227796778082848,
      "learning_rate": 1e-05,
      "loss": 12.4418,
      "step": 1
    },
    {
      "epoch": 0.00037509377344336085,
      "eval_loss": 12.456700325012207,
      "eval_runtime": 31.5309,
      "eval_samples_per_second": 142.4,
      "eval_steps_per_second": 35.616,
      "step": 1
    },
    {
      "epoch": 0.0007501875468867217,
      "grad_norm": 0.02150120586156845,
      "learning_rate": 2e-05,
      "loss": 12.455,
      "step": 2
    },
    {
      "epoch": 0.0011252813203300824,
      "grad_norm": 0.015428487211465836,
      "learning_rate": 3e-05,
      "loss": 12.455,
      "step": 3
    },
    {
      "epoch": 0.0015003750937734434,
      "grad_norm": 0.0164105873554945,
      "learning_rate": 4e-05,
      "loss": 12.4565,
      "step": 4
    },
    {
      "epoch": 0.0018754688672168042,
      "grad_norm": 0.017800066620111465,
      "learning_rate": 5e-05,
      "loss": 12.4605,
      "step": 5
    },
    {
      "epoch": 0.002250562640660165,
      "grad_norm": 0.015917498618364334,
      "learning_rate": 6e-05,
      "loss": 12.4521,
      "step": 6
    },
    {
      "epoch": 0.002625656414103526,
      "grad_norm": 0.01773245818912983,
      "learning_rate": 7e-05,
      "loss": 12.4578,
      "step": 7
    },
    {
      "epoch": 0.003000750187546887,
      "grad_norm": 0.015480170026421547,
      "learning_rate": 8e-05,
      "loss": 12.4671,
      "step": 8
    },
    {
      "epoch": 0.0033758439609902473,
      "grad_norm": 0.018675751984119415,
      "learning_rate": 9e-05,
      "loss": 12.457,
      "step": 9
    },
    {
      "epoch": 0.0037509377344336083,
      "grad_norm": 0.018724359571933746,
      "learning_rate": 0.0001,
      "loss": 12.4645,
      "step": 10
    },
    {
      "epoch": 0.004126031507876969,
      "grad_norm": 0.01711506024003029,
      "learning_rate": 9.999316524962345e-05,
      "loss": 12.4613,
      "step": 11
    },
    {
      "epoch": 0.00450112528132033,
      "grad_norm": 0.020380137488245964,
      "learning_rate": 9.997266286704631e-05,
      "loss": 12.4581,
      "step": 12
    },
    {
      "epoch": 0.004876219054763691,
      "grad_norm": 0.02045395039021969,
      "learning_rate": 9.993849845741524e-05,
      "loss": 12.4577,
      "step": 13
    },
    {
      "epoch": 0.005251312828207052,
      "grad_norm": 0.018522614613175392,
      "learning_rate": 9.989068136093873e-05,
      "loss": 12.463,
      "step": 14
    },
    {
      "epoch": 0.005626406601650412,
      "grad_norm": 0.019625676795840263,
      "learning_rate": 9.98292246503335e-05,
      "loss": 12.4533,
      "step": 15
    },
    {
      "epoch": 0.006001500375093774,
      "grad_norm": 0.026187023147940636,
      "learning_rate": 9.975414512725057e-05,
      "loss": 12.4512,
      "step": 16
    },
    {
      "epoch": 0.006376594148537134,
      "grad_norm": 0.02676096372306347,
      "learning_rate": 9.966546331768191e-05,
      "loss": 12.4488,
      "step": 17
    },
    {
      "epoch": 0.006751687921980495,
      "grad_norm": 0.02111980877816677,
      "learning_rate": 9.956320346634876e-05,
      "loss": 12.4491,
      "step": 18
    },
    {
      "epoch": 0.007126781695423856,
      "grad_norm": 0.028822433203458786,
      "learning_rate": 9.944739353007344e-05,
      "loss": 12.4562,
      "step": 19
    },
    {
      "epoch": 0.007501875468867217,
      "grad_norm": 0.026074018329381943,
      "learning_rate": 9.931806517013612e-05,
      "loss": 12.4552,
      "step": 20
    },
    {
      "epoch": 0.007876969242310577,
      "grad_norm": 0.032735712826251984,
      "learning_rate": 9.917525374361912e-05,
      "loss": 12.4498,
      "step": 21
    },
    {
      "epoch": 0.008252063015753939,
      "grad_norm": 0.033054810017347336,
      "learning_rate": 9.901899829374047e-05,
      "loss": 12.4539,
      "step": 22
    },
    {
      "epoch": 0.0086271567891973,
      "grad_norm": 0.033514585345983505,
      "learning_rate": 9.884934153917997e-05,
      "loss": 12.4585,
      "step": 23
    },
    {
      "epoch": 0.00900225056264066,
      "grad_norm": 0.020584290847182274,
      "learning_rate": 9.86663298624003e-05,
      "loss": 12.4505,
      "step": 24
    },
    {
      "epoch": 0.009377344336084021,
      "grad_norm": 0.0395231731235981,
      "learning_rate": 9.847001329696653e-05,
      "loss": 12.4581,
      "step": 25
    },
    {
      "epoch": 0.009752438109527382,
      "grad_norm": 0.035367202013731,
      "learning_rate": 9.826044551386744e-05,
      "loss": 12.452,
      "step": 26
    },
    {
      "epoch": 0.010127531882970742,
      "grad_norm": 0.03525306284427643,
      "learning_rate": 9.803768380684242e-05,
      "loss": 12.4562,
      "step": 27
    },
    {
      "epoch": 0.010502625656414103,
      "grad_norm": 0.04686054587364197,
      "learning_rate": 9.780178907671789e-05,
      "loss": 12.4585,
      "step": 28
    },
    {
      "epoch": 0.010877719429857465,
      "grad_norm": 0.04403698444366455,
      "learning_rate": 9.755282581475769e-05,
      "loss": 12.4532,
      "step": 29
    },
    {
      "epoch": 0.011252813203300824,
      "grad_norm": 0.050271838903427124,
      "learning_rate": 9.729086208503174e-05,
      "loss": 12.4547,
      "step": 30
    },
    {
      "epoch": 0.011627906976744186,
      "grad_norm": 0.03823979198932648,
      "learning_rate": 9.701596950580806e-05,
      "loss": 12.4534,
      "step": 31
    },
    {
      "epoch": 0.012003000750187547,
      "grad_norm": 0.049024488776922226,
      "learning_rate": 9.672822322997305e-05,
      "loss": 12.4535,
      "step": 32
    },
    {
      "epoch": 0.012378094523630907,
      "grad_norm": 0.04174116998910904,
      "learning_rate": 9.642770192448536e-05,
      "loss": 12.4573,
      "step": 33
    },
    {
      "epoch": 0.012753188297074268,
      "grad_norm": 0.05679089203476906,
      "learning_rate": 9.611448774886924e-05,
      "loss": 12.4584,
      "step": 34
    },
    {
      "epoch": 0.01312828207051763,
      "grad_norm": 0.05935642123222351,
      "learning_rate": 9.578866633275288e-05,
      "loss": 12.4563,
      "step": 35
    },
    {
      "epoch": 0.01350337584396099,
      "grad_norm": 0.04450904205441475,
      "learning_rate": 9.545032675245813e-05,
      "loss": 12.4608,
      "step": 36
    },
    {
      "epoch": 0.01387846961740435,
      "grad_norm": 0.06490136682987213,
      "learning_rate": 9.509956150664796e-05,
      "loss": 12.4594,
      "step": 37
    },
    {
      "epoch": 0.014253563390847712,
      "grad_norm": 0.06130573898553848,
      "learning_rate": 9.473646649103818e-05,
      "loss": 12.4486,
      "step": 38
    },
    {
      "epoch": 0.014628657164291074,
      "grad_norm": 0.0688103511929512,
      "learning_rate": 9.43611409721806e-05,
      "loss": 12.4572,
      "step": 39
    },
    {
      "epoch": 0.015003750937734433,
      "grad_norm": 0.06818948686122894,
      "learning_rate": 9.397368756032445e-05,
      "loss": 12.4462,
      "step": 40
    },
    {
      "epoch": 0.015378844711177795,
      "grad_norm": 0.06699138879776001,
      "learning_rate": 9.357421218136386e-05,
      "loss": 12.455,
      "step": 41
    },
    {
      "epoch": 0.015753938484621154,
      "grad_norm": 0.06593026965856552,
      "learning_rate": 9.316282404787871e-05,
      "loss": 12.4519,
      "step": 42
    },
    {
      "epoch": 0.016129032258064516,
      "grad_norm": 0.06654481589794159,
      "learning_rate": 9.273963562927695e-05,
      "loss": 12.4479,
      "step": 43
    },
    {
      "epoch": 0.016504126031507877,
      "grad_norm": 0.08861877024173737,
      "learning_rate": 9.230476262104677e-05,
      "loss": 12.4527,
      "step": 44
    },
    {
      "epoch": 0.01687921980495124,
      "grad_norm": 0.08027205616235733,
      "learning_rate": 9.185832391312644e-05,
      "loss": 12.4615,
      "step": 45
    },
    {
      "epoch": 0.0172543135783946,
      "grad_norm": 0.10534841567277908,
      "learning_rate": 9.140044155740101e-05,
      "loss": 12.451,
      "step": 46
    },
    {
      "epoch": 0.017629407351837958,
      "grad_norm": 0.09641523659229279,
      "learning_rate": 9.093124073433463e-05,
      "loss": 12.4487,
      "step": 47
    },
    {
      "epoch": 0.01800450112528132,
      "grad_norm": 0.1218847930431366,
      "learning_rate": 9.045084971874738e-05,
      "loss": 12.4449,
      "step": 48
    },
    {
      "epoch": 0.01837959489872468,
      "grad_norm": 0.099039725959301,
      "learning_rate": 8.995939984474624e-05,
      "loss": 12.4529,
      "step": 49
    },
    {
      "epoch": 0.018754688672168042,
      "grad_norm": 0.10472770780324936,
      "learning_rate": 8.945702546981969e-05,
      "loss": 12.4444,
      "step": 50
    },
    {
      "epoch": 0.018754688672168042,
      "eval_loss": 12.44905948638916,
      "eval_runtime": 31.5562,
      "eval_samples_per_second": 142.286,
      "eval_steps_per_second": 35.587,
      "step": 50
    },
    {
      "epoch": 0.019129782445611403,
      "grad_norm": 0.05895780399441719,
      "learning_rate": 8.894386393810563e-05,
      "loss": 12.4463,
      "step": 51
    },
    {
      "epoch": 0.019504876219054765,
      "grad_norm": 0.07146885246038437,
      "learning_rate": 8.842005554284296e-05,
      "loss": 12.4498,
      "step": 52
    },
    {
      "epoch": 0.019879969992498126,
      "grad_norm": 0.08618733286857605,
      "learning_rate": 8.788574348801675e-05,
      "loss": 12.4441,
      "step": 53
    },
    {
      "epoch": 0.020255063765941484,
      "grad_norm": 0.07748620212078094,
      "learning_rate": 8.73410738492077e-05,
      "loss": 12.4509,
      "step": 54
    },
    {
      "epoch": 0.020630157539384845,
      "grad_norm": 0.09370458871126175,
      "learning_rate": 8.678619553365659e-05,
      "loss": 12.4547,
      "step": 55
    },
    {
      "epoch": 0.021005251312828207,
      "grad_norm": 0.08380654454231262,
      "learning_rate": 8.622126023955446e-05,
      "loss": 12.4526,
      "step": 56
    },
    {
      "epoch": 0.02138034508627157,
      "grad_norm": 0.0880570337176323,
      "learning_rate": 8.564642241456986e-05,
      "loss": 12.4447,
      "step": 57
    },
    {
      "epoch": 0.02175543885971493,
      "grad_norm": 0.1042032390832901,
      "learning_rate": 8.506183921362443e-05,
      "loss": 12.4487,
      "step": 58
    },
    {
      "epoch": 0.02213053263315829,
      "grad_norm": 0.09437630325555801,
      "learning_rate": 8.44676704559283e-05,
      "loss": 12.4442,
      "step": 59
    },
    {
      "epoch": 0.02250562640660165,
      "grad_norm": 0.08716624975204468,
      "learning_rate": 8.386407858128706e-05,
      "loss": 12.449,
      "step": 60
    },
    {
      "epoch": 0.02288072018004501,
      "grad_norm": 0.12372646480798721,
      "learning_rate": 8.32512286056924e-05,
      "loss": 12.4366,
      "step": 61
    },
    {
      "epoch": 0.023255813953488372,
      "grad_norm": 0.09988711774349213,
      "learning_rate": 8.262928807620843e-05,
      "loss": 12.4503,
      "step": 62
    },
    {
      "epoch": 0.023630907726931733,
      "grad_norm": 0.12361840903759003,
      "learning_rate": 8.199842702516583e-05,
      "loss": 12.4464,
      "step": 63
    },
    {
      "epoch": 0.024006001500375095,
      "grad_norm": 0.10942015796899796,
      "learning_rate": 8.135881792367686e-05,
      "loss": 12.4522,
      "step": 64
    },
    {
      "epoch": 0.024381095273818456,
      "grad_norm": 0.13083170354366302,
      "learning_rate": 8.07106356344834e-05,
      "loss": 12.4474,
      "step": 65
    },
    {
      "epoch": 0.024756189047261814,
      "grad_norm": 0.13645674288272858,
      "learning_rate": 8.005405736415126e-05,
      "loss": 12.443,
      "step": 66
    },
    {
      "epoch": 0.025131282820705175,
      "grad_norm": 0.12455920875072479,
      "learning_rate": 7.938926261462366e-05,
      "loss": 12.4414,
      "step": 67
    },
    {
      "epoch": 0.025506376594148537,
      "grad_norm": 0.13404513895511627,
      "learning_rate": 7.871643313414718e-05,
      "loss": 12.443,
      "step": 68
    },
    {
      "epoch": 0.025881470367591898,
      "grad_norm": 0.1426197737455368,
      "learning_rate": 7.803575286758364e-05,
      "loss": 12.4312,
      "step": 69
    },
    {
      "epoch": 0.02625656414103526,
      "grad_norm": 0.14360785484313965,
      "learning_rate": 7.734740790612136e-05,
      "loss": 12.4401,
      "step": 70
    },
    {
      "epoch": 0.02663165791447862,
      "grad_norm": 0.1424376368522644,
      "learning_rate": 7.66515864363997e-05,
      "loss": 12.4432,
      "step": 71
    },
    {
      "epoch": 0.02700675168792198,
      "grad_norm": 0.11531911045312881,
      "learning_rate": 7.594847868906076e-05,
      "loss": 12.4397,
      "step": 72
    },
    {
      "epoch": 0.02738184546136534,
      "grad_norm": 0.16378456354141235,
      "learning_rate": 7.52382768867422e-05,
      "loss": 12.4424,
      "step": 73
    },
    {
      "epoch": 0.0277569392348087,
      "grad_norm": 0.1332365870475769,
      "learning_rate": 7.452117519152542e-05,
      "loss": 12.4377,
      "step": 74
    },
    {
      "epoch": 0.028132033008252063,
      "grad_norm": 0.15533415973186493,
      "learning_rate": 7.379736965185368e-05,
      "loss": 12.4295,
      "step": 75
    },
    {
      "epoch": 0.028507126781695424,
      "grad_norm": 0.17212828993797302,
      "learning_rate": 7.30670581489344e-05,
      "loss": 12.4319,
      "step": 76
    },
    {
      "epoch": 0.028882220555138786,
      "grad_norm": 0.16506913304328918,
      "learning_rate": 7.233044034264034e-05,
      "loss": 12.4369,
      "step": 77
    },
    {
      "epoch": 0.029257314328582147,
      "grad_norm": 0.12321052700281143,
      "learning_rate": 7.158771761692464e-05,
      "loss": 12.4334,
      "step": 78
    },
    {
      "epoch": 0.029632408102025505,
      "grad_norm": 0.1749526709318161,
      "learning_rate": 7.083909302476453e-05,
      "loss": 12.4301,
      "step": 79
    },
    {
      "epoch": 0.030007501875468866,
      "grad_norm": 0.21545860171318054,
      "learning_rate": 7.008477123264848e-05,
      "loss": 12.4339,
      "step": 80
    },
    {
      "epoch": 0.030382595648912228,
      "grad_norm": 0.13776488602161407,
      "learning_rate": 6.932495846462261e-05,
      "loss": 12.4443,
      "step": 81
    },
    {
      "epoch": 0.03075768942235559,
      "grad_norm": 0.17230091989040375,
      "learning_rate": 6.855986244591104e-05,
      "loss": 12.4262,
      "step": 82
    },
    {
      "epoch": 0.03113278319579895,
      "grad_norm": 0.1966809630393982,
      "learning_rate": 6.778969234612584e-05,
      "loss": 12.4308,
      "step": 83
    },
    {
      "epoch": 0.03150787696924231,
      "grad_norm": 0.17156358063220978,
      "learning_rate": 6.701465872208216e-05,
      "loss": 12.4272,
      "step": 84
    },
    {
      "epoch": 0.03188297074268567,
      "grad_norm": 0.17334824800491333,
      "learning_rate": 6.623497346023418e-05,
      "loss": 12.432,
      "step": 85
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 0.2051803469657898,
      "learning_rate": 6.545084971874738e-05,
      "loss": 12.4184,
      "step": 86
    },
    {
      "epoch": 0.032633158289572396,
      "grad_norm": 0.2344592660665512,
      "learning_rate": 6.466250186922325e-05,
      "loss": 12.4215,
      "step": 87
    },
    {
      "epoch": 0.033008252063015754,
      "grad_norm": 0.17081362009048462,
      "learning_rate": 6.387014543809223e-05,
      "loss": 12.4222,
      "step": 88
    },
    {
      "epoch": 0.03338334583645911,
      "grad_norm": 0.1841144561767578,
      "learning_rate": 6.307399704769099e-05,
      "loss": 12.4281,
      "step": 89
    },
    {
      "epoch": 0.03375843960990248,
      "grad_norm": 0.21089807152748108,
      "learning_rate": 6.227427435703997e-05,
      "loss": 12.4144,
      "step": 90
    },
    {
      "epoch": 0.034133533383345835,
      "grad_norm": 0.17784003913402557,
      "learning_rate": 6.147119600233758e-05,
      "loss": 12.4224,
      "step": 91
    },
    {
      "epoch": 0.0345086271567892,
      "grad_norm": 0.16964246332645416,
      "learning_rate": 6.066498153718735e-05,
      "loss": 12.4225,
      "step": 92
    },
    {
      "epoch": 0.03488372093023256,
      "grad_norm": 0.1785283386707306,
      "learning_rate": 5.985585137257401e-05,
      "loss": 12.4296,
      "step": 93
    },
    {
      "epoch": 0.035258814703675916,
      "grad_norm": 0.23231767117977142,
      "learning_rate": 5.90440267166055e-05,
      "loss": 12.4255,
      "step": 94
    },
    {
      "epoch": 0.03563390847711928,
      "grad_norm": 0.25896158814430237,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 12.4,
      "step": 95
    },
    {
      "epoch": 0.03600900225056264,
      "grad_norm": 0.2535313665866852,
      "learning_rate": 5.74131823855921e-05,
      "loss": 12.4118,
      "step": 96
    },
    {
      "epoch": 0.036384096024006,
      "grad_norm": 0.23708033561706543,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 12.4108,
      "step": 97
    },
    {
      "epoch": 0.03675918979744936,
      "grad_norm": 0.2405415028333664,
      "learning_rate": 5.577423184847932e-05,
      "loss": 12.4137,
      "step": 98
    },
    {
      "epoch": 0.037134283570892726,
      "grad_norm": 0.22012895345687866,
      "learning_rate": 5.495227651252315e-05,
      "loss": 12.4154,
      "step": 99
    },
    {
      "epoch": 0.037509377344336084,
      "grad_norm": 0.21927011013031006,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 12.4005,
      "step": 100
    },
    {
      "epoch": 0.037509377344336084,
      "eval_loss": 12.415033340454102,
      "eval_runtime": 31.5735,
      "eval_samples_per_second": 142.208,
      "eval_steps_per_second": 35.568,
      "step": 100
    },
    {
      "epoch": 0.03788447111777944,
      "grad_norm": 0.15709909796714783,
      "learning_rate": 5.330452921628497e-05,
      "loss": 12.4302,
      "step": 101
    },
    {
      "epoch": 0.03825956489122281,
      "grad_norm": 0.17682993412017822,
      "learning_rate": 5.247918773366112e-05,
      "loss": 12.4186,
      "step": 102
    },
    {
      "epoch": 0.038634658664666165,
      "grad_norm": 0.18583868443965912,
      "learning_rate": 5.165316846586541e-05,
      "loss": 12.4125,
      "step": 103
    },
    {
      "epoch": 0.03900975243810953,
      "grad_norm": 0.19769588112831116,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 12.4085,
      "step": 104
    },
    {
      "epoch": 0.03938484621155289,
      "grad_norm": 0.20496231317520142,
      "learning_rate": 5e-05,
      "loss": 12.4132,
      "step": 105
    },
    {
      "epoch": 0.03975993998499625,
      "grad_norm": 0.19453130662441254,
      "learning_rate": 4.917330276168208e-05,
      "loss": 12.4091,
      "step": 106
    },
    {
      "epoch": 0.04013503375843961,
      "grad_norm": 0.16093809902668,
      "learning_rate": 4.834683153413459e-05,
      "loss": 12.4309,
      "step": 107
    },
    {
      "epoch": 0.04051012753188297,
      "grad_norm": 0.1725478619337082,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 12.4166,
      "step": 108
    },
    {
      "epoch": 0.04088522130532633,
      "grad_norm": 0.1555778682231903,
      "learning_rate": 4.669547078371504e-05,
      "loss": 12.4231,
      "step": 109
    },
    {
      "epoch": 0.04126031507876969,
      "grad_norm": 0.15406446158885956,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 12.4061,
      "step": 110
    },
    {
      "epoch": 0.041635408852213056,
      "grad_norm": 0.1694355607032776,
      "learning_rate": 4.504772348747687e-05,
      "loss": 12.4145,
      "step": 111
    },
    {
      "epoch": 0.042010502625656414,
      "grad_norm": 0.19442622363567352,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 12.4043,
      "step": 112
    },
    {
      "epoch": 0.04238559639909977,
      "grad_norm": 0.1768011897802353,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 12.403,
      "step": 113
    },
    {
      "epoch": 0.04276069017254314,
      "grad_norm": 0.1964731067419052,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 12.4091,
      "step": 114
    },
    {
      "epoch": 0.043135783945986494,
      "grad_norm": 0.17676453292369843,
      "learning_rate": 4.17702704859633e-05,
      "loss": 12.402,
      "step": 115
    },
    {
      "epoch": 0.04351087771942986,
      "grad_norm": 0.19306358695030212,
      "learning_rate": 4.095597328339452e-05,
      "loss": 12.4084,
      "step": 116
    },
    {
      "epoch": 0.04388597149287322,
      "grad_norm": 0.1834443211555481,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 12.4116,
      "step": 117
    },
    {
      "epoch": 0.04426106526631658,
      "grad_norm": 0.20726795494556427,
      "learning_rate": 3.933501846281267e-05,
      "loss": 12.3981,
      "step": 118
    },
    {
      "epoch": 0.04463615903975994,
      "grad_norm": 0.12804187834262848,
      "learning_rate": 3.852880399766243e-05,
      "loss": 12.4136,
      "step": 119
    },
    {
      "epoch": 0.0450112528132033,
      "grad_norm": 0.1477503776550293,
      "learning_rate": 3.772572564296005e-05,
      "loss": 12.4162,
      "step": 120
    },
    {
      "epoch": 0.04538634658664666,
      "grad_norm": 0.20745225250720978,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 12.3971,
      "step": 121
    },
    {
      "epoch": 0.04576144036009002,
      "grad_norm": 0.17155945301055908,
      "learning_rate": 3.612985456190778e-05,
      "loss": 12.3973,
      "step": 122
    },
    {
      "epoch": 0.046136534133533386,
      "grad_norm": 0.12994982302188873,
      "learning_rate": 3.533749813077677e-05,
      "loss": 12.3985,
      "step": 123
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 0.20189839601516724,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 12.4053,
      "step": 124
    },
    {
      "epoch": 0.04688672168042011,
      "grad_norm": 0.17578479647636414,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 12.4054,
      "step": 125
    },
    {
      "epoch": 0.047261815453863466,
      "grad_norm": 0.12535934150218964,
      "learning_rate": 3.298534127791785e-05,
      "loss": 12.4023,
      "step": 126
    },
    {
      "epoch": 0.047636909227306824,
      "grad_norm": 0.15147213637828827,
      "learning_rate": 3.221030765387417e-05,
      "loss": 12.4079,
      "step": 127
    },
    {
      "epoch": 0.04801200300075019,
      "grad_norm": 0.1409454494714737,
      "learning_rate": 3.144013755408895e-05,
      "loss": 12.4,
      "step": 128
    },
    {
      "epoch": 0.04838709677419355,
      "grad_norm": 0.1726028025150299,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 12.4012,
      "step": 129
    },
    {
      "epoch": 0.04876219054763691,
      "grad_norm": 0.16818451881408691,
      "learning_rate": 2.991522876735154e-05,
      "loss": 12.4042,
      "step": 130
    },
    {
      "epoch": 0.04913728432108027,
      "grad_norm": 0.15247759222984314,
      "learning_rate": 2.916090697523549e-05,
      "loss": 12.4033,
      "step": 131
    },
    {
      "epoch": 0.04951237809452363,
      "grad_norm": 0.14745765924453735,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 12.4,
      "step": 132
    },
    {
      "epoch": 0.04988747186796699,
      "grad_norm": 0.18994639813899994,
      "learning_rate": 2.766955965735968e-05,
      "loss": 12.3933,
      "step": 133
    },
    {
      "epoch": 0.05026256564141035,
      "grad_norm": 0.14111657440662384,
      "learning_rate": 2.693294185106562e-05,
      "loss": 12.3997,
      "step": 134
    },
    {
      "epoch": 0.050637659414853715,
      "grad_norm": 0.17824867367744446,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 12.4169,
      "step": 135
    },
    {
      "epoch": 0.05101275318829707,
      "grad_norm": 0.14255212247371674,
      "learning_rate": 2.547882480847461e-05,
      "loss": 12.3961,
      "step": 136
    },
    {
      "epoch": 0.05138784696174044,
      "grad_norm": 0.13047799468040466,
      "learning_rate": 2.476172311325783e-05,
      "loss": 12.4034,
      "step": 137
    },
    {
      "epoch": 0.051762940735183796,
      "grad_norm": 0.16238361597061157,
      "learning_rate": 2.405152131093926e-05,
      "loss": 12.3969,
      "step": 138
    },
    {
      "epoch": 0.052138034508627154,
      "grad_norm": 0.17070843279361725,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 12.4012,
      "step": 139
    },
    {
      "epoch": 0.05251312828207052,
      "grad_norm": 0.17022596299648285,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 12.3876,
      "step": 140
    },
    {
      "epoch": 0.05288822205551388,
      "grad_norm": 0.18745656311511993,
      "learning_rate": 2.196424713241637e-05,
      "loss": 12.3994,
      "step": 141
    },
    {
      "epoch": 0.05326331582895724,
      "grad_norm": 0.1485593616962433,
      "learning_rate": 2.128356686585282e-05,
      "loss": 12.3831,
      "step": 142
    },
    {
      "epoch": 0.0536384096024006,
      "grad_norm": 0.1549435406923294,
      "learning_rate": 2.061073738537635e-05,
      "loss": 12.3945,
      "step": 143
    },
    {
      "epoch": 0.05401350337584396,
      "grad_norm": 0.17713989317417145,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 12.4051,
      "step": 144
    },
    {
      "epoch": 0.05438859714928732,
      "grad_norm": 0.12847283482551575,
      "learning_rate": 1.928936436551661e-05,
      "loss": 12.3975,
      "step": 145
    },
    {
      "epoch": 0.05476369092273068,
      "grad_norm": 0.1436091512441635,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 12.3934,
      "step": 146
    },
    {
      "epoch": 0.055138784696174045,
      "grad_norm": 0.15440858900547028,
      "learning_rate": 1.800157297483417e-05,
      "loss": 12.3992,
      "step": 147
    },
    {
      "epoch": 0.0555138784696174,
      "grad_norm": 0.15569362044334412,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 12.4044,
      "step": 148
    },
    {
      "epoch": 0.05588897224306077,
      "grad_norm": 0.1933399885892868,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 12.3897,
      "step": 149
    },
    {
      "epoch": 0.056264066016504126,
      "grad_norm": 0.22875584661960602,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 12.3968,
      "step": 150
    },
    {
      "epoch": 0.056264066016504126,
      "eval_loss": 12.39761734008789,
      "eval_runtime": 31.5345,
      "eval_samples_per_second": 142.384,
      "eval_steps_per_second": 35.612,
      "step": 150
    },
    {
      "epoch": 0.056639159789947484,
      "grad_norm": 0.12880399823188782,
      "learning_rate": 1.553232954407171e-05,
      "loss": 12.4149,
      "step": 151
    },
    {
      "epoch": 0.05701425356339085,
      "grad_norm": 0.12402915209531784,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 12.4003,
      "step": 152
    },
    {
      "epoch": 0.05738934733683421,
      "grad_norm": 0.1705862581729889,
      "learning_rate": 1.435357758543015e-05,
      "loss": 12.4128,
      "step": 153
    },
    {
      "epoch": 0.05776444111027757,
      "grad_norm": 0.1499006450176239,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 12.3956,
      "step": 154
    },
    {
      "epoch": 0.05813953488372093,
      "grad_norm": 0.1119084283709526,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 12.3997,
      "step": 155
    },
    {
      "epoch": 0.058514628657164294,
      "grad_norm": 0.11400716751813889,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 12.4023,
      "step": 156
    },
    {
      "epoch": 0.05888972243060765,
      "grad_norm": 0.15442615747451782,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 12.3995,
      "step": 157
    },
    {
      "epoch": 0.05926481620405101,
      "grad_norm": 0.12590335309505463,
      "learning_rate": 1.157994445715706e-05,
      "loss": 12.399,
      "step": 158
    },
    {
      "epoch": 0.059639909977494375,
      "grad_norm": 0.12511345744132996,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 12.3968,
      "step": 159
    },
    {
      "epoch": 0.06001500375093773,
      "grad_norm": 0.11674850434064865,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 12.3987,
      "step": 160
    },
    {
      "epoch": 0.0603900975243811,
      "grad_norm": 0.11702191084623337,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 12.399,
      "step": 161
    },
    {
      "epoch": 0.060765191297824456,
      "grad_norm": 0.13874897360801697,
      "learning_rate": 9.549150281252633e-06,
      "loss": 12.412,
      "step": 162
    },
    {
      "epoch": 0.061140285071267814,
      "grad_norm": 0.1664118766784668,
      "learning_rate": 9.068759265665384e-06,
      "loss": 12.402,
      "step": 163
    },
    {
      "epoch": 0.06151537884471118,
      "grad_norm": 0.15710681676864624,
      "learning_rate": 8.599558442598998e-06,
      "loss": 12.4037,
      "step": 164
    },
    {
      "epoch": 0.061890472618154536,
      "grad_norm": 0.12185448408126831,
      "learning_rate": 8.141676086873572e-06,
      "loss": 12.4065,
      "step": 165
    },
    {
      "epoch": 0.0622655663915979,
      "grad_norm": 0.14105747640132904,
      "learning_rate": 7.695237378953223e-06,
      "loss": 12.3988,
      "step": 166
    },
    {
      "epoch": 0.06264066016504126,
      "grad_norm": 0.12631039321422577,
      "learning_rate": 7.260364370723044e-06,
      "loss": 12.4128,
      "step": 167
    },
    {
      "epoch": 0.06301575393848462,
      "grad_norm": 0.11355233937501907,
      "learning_rate": 6.837175952121306e-06,
      "loss": 12.4008,
      "step": 168
    },
    {
      "epoch": 0.06339084771192798,
      "grad_norm": 0.14496929943561554,
      "learning_rate": 6.425787818636131e-06,
      "loss": 12.3943,
      "step": 169
    },
    {
      "epoch": 0.06376594148537135,
      "grad_norm": 0.12267716974020004,
      "learning_rate": 6.026312439675552e-06,
      "loss": 12.3954,
      "step": 170
    },
    {
      "epoch": 0.0641410352588147,
      "grad_norm": 0.13069912791252136,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 12.4037,
      "step": 171
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 0.16758450865745544,
      "learning_rate": 5.263533508961827e-06,
      "loss": 12.3909,
      "step": 172
    },
    {
      "epoch": 0.06489122280570142,
      "grad_norm": 0.11563099175691605,
      "learning_rate": 4.900438493352055e-06,
      "loss": 12.3995,
      "step": 173
    },
    {
      "epoch": 0.06526631657914479,
      "grad_norm": 0.12327788770198822,
      "learning_rate": 4.549673247541875e-06,
      "loss": 12.4022,
      "step": 174
    },
    {
      "epoch": 0.06564141035258815,
      "grad_norm": 0.11180421710014343,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 12.4013,
      "step": 175
    },
    {
      "epoch": 0.06601650412603151,
      "grad_norm": 0.15724514424800873,
      "learning_rate": 3.885512251130763e-06,
      "loss": 12.4021,
      "step": 176
    },
    {
      "epoch": 0.06639159789947487,
      "grad_norm": 0.143633171916008,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 12.4002,
      "step": 177
    },
    {
      "epoch": 0.06676669167291822,
      "grad_norm": 0.11034294217824936,
      "learning_rate": 3.271776770026963e-06,
      "loss": 12.3917,
      "step": 178
    },
    {
      "epoch": 0.0671417854463616,
      "grad_norm": 0.15341949462890625,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 12.3967,
      "step": 179
    },
    {
      "epoch": 0.06751687921980495,
      "grad_norm": 0.10005737841129303,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 12.4042,
      "step": 180
    },
    {
      "epoch": 0.06789197299324831,
      "grad_norm": 0.13085509836673737,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 12.3949,
      "step": 181
    },
    {
      "epoch": 0.06826706676669167,
      "grad_norm": 0.10891951620578766,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 12.4011,
      "step": 182
    },
    {
      "epoch": 0.06864216054013503,
      "grad_norm": 0.12164262682199478,
      "learning_rate": 1.962316193157593e-06,
      "loss": 12.3917,
      "step": 183
    },
    {
      "epoch": 0.0690172543135784,
      "grad_norm": 0.09939981251955032,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 12.4022,
      "step": 184
    },
    {
      "epoch": 0.06939234808702176,
      "grad_norm": 0.1242922693490982,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 12.3914,
      "step": 185
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 0.11778715252876282,
      "learning_rate": 1.333670137599713e-06,
      "loss": 12.3901,
      "step": 186
    },
    {
      "epoch": 0.07014253563390847,
      "grad_norm": 0.15849320590496063,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 12.3847,
      "step": 187
    },
    {
      "epoch": 0.07051762940735183,
      "grad_norm": 0.13588441908359528,
      "learning_rate": 9.810017062595322e-07,
      "loss": 12.3784,
      "step": 188
    },
    {
      "epoch": 0.0708927231807952,
      "grad_norm": 0.1551114022731781,
      "learning_rate": 8.247462563808817e-07,
      "loss": 12.4063,
      "step": 189
    },
    {
      "epoch": 0.07126781695423856,
      "grad_norm": 0.11420614272356033,
      "learning_rate": 6.819348298638839e-07,
      "loss": 12.3947,
      "step": 190
    },
    {
      "epoch": 0.07164291072768192,
      "grad_norm": 0.10785336047410965,
      "learning_rate": 5.526064699265753e-07,
      "loss": 12.4054,
      "step": 191
    },
    {
      "epoch": 0.07201800450112528,
      "grad_norm": 0.15972203016281128,
      "learning_rate": 4.367965336512403e-07,
      "loss": 12.393,
      "step": 192
    },
    {
      "epoch": 0.07239309827456865,
      "grad_norm": 0.14436322450637817,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 12.392,
      "step": 193
    },
    {
      "epoch": 0.072768192048012,
      "grad_norm": 0.1813633292913437,
      "learning_rate": 2.458548727494292e-07,
      "loss": 12.3865,
      "step": 194
    },
    {
      "epoch": 0.07314328582145536,
      "grad_norm": 0.14993774890899658,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 12.3762,
      "step": 195
    },
    {
      "epoch": 0.07351837959489872,
      "grad_norm": 0.16768528521060944,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 12.4146,
      "step": 196
    },
    {
      "epoch": 0.07389347336834208,
      "grad_norm": 0.15012212097644806,
      "learning_rate": 6.150154258476315e-08,
      "loss": 12.3854,
      "step": 197
    },
    {
      "epoch": 0.07426856714178545,
      "grad_norm": 0.15772943198680878,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 12.4011,
      "step": 198
    },
    {
      "epoch": 0.07464366091522881,
      "grad_norm": 0.13127177953720093,
      "learning_rate": 6.834750376549792e-09,
      "loss": 12.3747,
      "step": 199
    },
    {
      "epoch": 0.07501875468867217,
      "grad_norm": 0.2327679842710495,
      "learning_rate": 0.0,
      "loss": 12.3892,
      "step": 200
    },
    {
      "epoch": 0.07501875468867217,
      "eval_loss": 12.396309852600098,
      "eval_runtime": 31.4805,
      "eval_samples_per_second": 142.628,
      "eval_steps_per_second": 35.673,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 775189168128.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}