{
  "best_metric": 0.8110023736953735,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.10933442667760011,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005466721333880005,
      "grad_norm": 0.3069092035293579,
      "learning_rate": 1e-05,
      "loss": 0.5402,
      "step": 1
    },
    {
      "epoch": 0.0005466721333880005,
      "eval_loss": 1.1926336288452148,
      "eval_runtime": 96.8443,
      "eval_samples_per_second": 31.814,
      "eval_steps_per_second": 7.961,
      "step": 1
    },
    {
      "epoch": 0.001093344266776001,
      "grad_norm": 0.3607691526412964,
      "learning_rate": 2e-05,
      "loss": 0.7127,
      "step": 2
    },
    {
      "epoch": 0.0016400164001640015,
      "grad_norm": 0.394183874130249,
      "learning_rate": 3e-05,
      "loss": 0.6074,
      "step": 3
    },
    {
      "epoch": 0.002186688533552002,
      "grad_norm": 0.374828577041626,
      "learning_rate": 4e-05,
      "loss": 0.7711,
      "step": 4
    },
    {
      "epoch": 0.0027333606669400026,
      "grad_norm": 0.392012357711792,
      "learning_rate": 5e-05,
      "loss": 0.8362,
      "step": 5
    },
    {
      "epoch": 0.003280032800328003,
      "grad_norm": 0.3144543468952179,
      "learning_rate": 6e-05,
      "loss": 0.6681,
      "step": 6
    },
    {
      "epoch": 0.003826704933716004,
      "grad_norm": 0.4012846350669861,
      "learning_rate": 7e-05,
      "loss": 0.7757,
      "step": 7
    },
    {
      "epoch": 0.004373377067104004,
      "grad_norm": 0.38390469551086426,
      "learning_rate": 8e-05,
      "loss": 0.8064,
      "step": 8
    },
    {
      "epoch": 0.004920049200492005,
      "grad_norm": 0.3611810505390167,
      "learning_rate": 9e-05,
      "loss": 0.737,
      "step": 9
    },
    {
      "epoch": 0.005466721333880005,
      "grad_norm": 0.3719647526741028,
      "learning_rate": 0.0001,
      "loss": 0.8061,
      "step": 10
    },
    {
      "epoch": 0.006013393467268006,
      "grad_norm": 0.3899047374725342,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7862,
      "step": 11
    },
    {
      "epoch": 0.006560065600656006,
      "grad_norm": 0.41380685567855835,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8475,
      "step": 12
    },
    {
      "epoch": 0.007106737734044007,
      "grad_norm": 0.376996248960495,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9195,
      "step": 13
    },
    {
      "epoch": 0.007653409867432008,
      "grad_norm": 0.3617386519908905,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8514,
      "step": 14
    },
    {
      "epoch": 0.008200082000820008,
      "grad_norm": 0.4081059694290161,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8761,
      "step": 15
    },
    {
      "epoch": 0.008746754134208008,
      "grad_norm": 0.3920508027076721,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.8342,
      "step": 16
    },
    {
      "epoch": 0.00929342626759601,
      "grad_norm": 0.4705219864845276,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8478,
      "step": 17
    },
    {
      "epoch": 0.00984009840098401,
      "grad_norm": 0.40676283836364746,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8163,
      "step": 18
    },
    {
      "epoch": 0.01038677053437201,
      "grad_norm": 0.3783537447452545,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.759,
      "step": 19
    },
    {
      "epoch": 0.01093344266776001,
      "grad_norm": 0.4141082465648651,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8751,
      "step": 20
    },
    {
      "epoch": 0.011480114801148012,
      "grad_norm": 0.43635162711143494,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.8942,
      "step": 21
    },
    {
      "epoch": 0.012026786934536012,
      "grad_norm": 0.4932522475719452,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8731,
      "step": 22
    },
    {
      "epoch": 0.012573459067924012,
      "grad_norm": 0.3789720833301544,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8015,
      "step": 23
    },
    {
      "epoch": 0.013120131201312012,
      "grad_norm": 0.4504881799221039,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.0006,
      "step": 24
    },
    {
      "epoch": 0.013666803334700014,
      "grad_norm": 0.4233343005180359,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7965,
      "step": 25
    },
    {
      "epoch": 0.014213475468088014,
      "grad_norm": 0.44158434867858887,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8434,
      "step": 26
    },
    {
      "epoch": 0.014760147601476014,
      "grad_norm": 0.5280115604400635,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9236,
      "step": 27
    },
    {
      "epoch": 0.015306819734864016,
      "grad_norm": 0.48434582352638245,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.9014,
      "step": 28
    },
    {
      "epoch": 0.015853491868252016,
      "grad_norm": 0.5671005845069885,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7846,
      "step": 29
    },
    {
      "epoch": 0.016400164001640016,
      "grad_norm": 0.52934730052948,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9313,
      "step": 30
    },
    {
      "epoch": 0.016946836135028016,
      "grad_norm": 0.5285961031913757,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8943,
      "step": 31
    },
    {
      "epoch": 0.017493508268416016,
      "grad_norm": 0.553436279296875,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6807,
      "step": 32
    },
    {
      "epoch": 0.018040180401804017,
      "grad_norm": 0.576675295829773,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8869,
      "step": 33
    },
    {
      "epoch": 0.01858685253519202,
      "grad_norm": 0.6142381429672241,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8837,
      "step": 34
    },
    {
      "epoch": 0.01913352466858002,
      "grad_norm": 0.6652787923812866,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8762,
      "step": 35
    },
    {
      "epoch": 0.01968019680196802,
      "grad_norm": 0.6900700926780701,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.9253,
      "step": 36
    },
    {
      "epoch": 0.02022686893535602,
      "grad_norm": 0.7439871430397034,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.9703,
      "step": 37
    },
    {
      "epoch": 0.02077354106874402,
      "grad_norm": 0.7081446647644043,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8926,
      "step": 38
    },
    {
      "epoch": 0.02132021320213202,
      "grad_norm": 0.7153584361076355,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9543,
      "step": 39
    },
    {
      "epoch": 0.02186688533552002,
      "grad_norm": 0.9375388622283936,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8955,
      "step": 40
    },
    {
      "epoch": 0.022413557468908024,
      "grad_norm": 0.8841165900230408,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8365,
      "step": 41
    },
    {
      "epoch": 0.022960229602296024,
      "grad_norm": 0.9551074504852295,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9767,
      "step": 42
    },
    {
      "epoch": 0.023506901735684024,
      "grad_norm": 0.8008959889411926,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8992,
      "step": 43
    },
    {
      "epoch": 0.024053573869072024,
      "grad_norm": 0.977232038974762,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9695,
      "step": 44
    },
    {
      "epoch": 0.024600246002460024,
      "grad_norm": 1.0420466661453247,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.9015,
      "step": 45
    },
    {
      "epoch": 0.025146918135848025,
      "grad_norm": 0.9358241558074951,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.957,
      "step": 46
    },
    {
      "epoch": 0.025693590269236025,
      "grad_norm": 1.12788724899292,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.0739,
      "step": 47
    },
    {
      "epoch": 0.026240262402624025,
      "grad_norm": 1.1769741773605347,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.85,
      "step": 48
    },
    {
      "epoch": 0.026786934536012028,
      "grad_norm": 1.4089933633804321,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0487,
      "step": 49
    },
    {
      "epoch": 0.02733360666940003,
      "grad_norm": 1.4431661367416382,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.8077,
      "step": 50
    },
    {
      "epoch": 0.02733360666940003,
      "eval_loss": 0.8743061423301697,
      "eval_runtime": 97.1126,
      "eval_samples_per_second": 31.726,
      "eval_steps_per_second": 7.939,
      "step": 50
    },
    {
      "epoch": 0.02788027880278803,
      "grad_norm": 0.29097920656204224,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4253,
      "step": 51
    },
    {
      "epoch": 0.02842695093617603,
      "grad_norm": 0.405794620513916,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.7253,
      "step": 52
    },
    {
      "epoch": 0.02897362306956403,
      "grad_norm": 0.4073840379714966,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6463,
      "step": 53
    },
    {
      "epoch": 0.02952029520295203,
      "grad_norm": 0.359628826379776,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7174,
      "step": 54
    },
    {
      "epoch": 0.03006696733634003,
      "grad_norm": 0.3805781900882721,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6539,
      "step": 55
    },
    {
      "epoch": 0.030613639469728032,
      "grad_norm": 0.3185127079486847,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.6994,
      "step": 56
    },
    {
      "epoch": 0.031160311603116032,
      "grad_norm": 0.3456040918827057,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7239,
      "step": 57
    },
    {
      "epoch": 0.03170698373650403,
      "grad_norm": 0.34060031175613403,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.8351,
      "step": 58
    },
    {
      "epoch": 0.03225365586989203,
      "grad_norm": 0.28398457169532776,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.739,
      "step": 59
    },
    {
      "epoch": 0.03280032800328003,
      "grad_norm": 0.3257451355457306,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8343,
      "step": 60
    },
    {
      "epoch": 0.03334700013666803,
      "grad_norm": 0.3267151117324829,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6755,
      "step": 61
    },
    {
      "epoch": 0.03389367227005603,
      "grad_norm": 0.36094099283218384,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8584,
      "step": 62
    },
    {
      "epoch": 0.03444034440344403,
      "grad_norm": 0.3773055076599121,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.8732,
      "step": 63
    },
    {
      "epoch": 0.03498701653683203,
      "grad_norm": 0.34619849920272827,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6814,
      "step": 64
    },
    {
      "epoch": 0.03553368867022003,
      "grad_norm": 0.4096669554710388,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7999,
      "step": 65
    },
    {
      "epoch": 0.03608036080360803,
      "grad_norm": 0.35697975754737854,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7619,
      "step": 66
    },
    {
      "epoch": 0.03662703293699603,
      "grad_norm": 0.3736931085586548,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8721,
      "step": 67
    },
    {
      "epoch": 0.03717370507038404,
      "grad_norm": 0.3895150125026703,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.8932,
      "step": 68
    },
    {
      "epoch": 0.03772037720377204,
      "grad_norm": 0.3509528338909149,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7938,
      "step": 69
    },
    {
      "epoch": 0.03826704933716004,
      "grad_norm": 0.3806791305541992,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8325,
      "step": 70
    },
    {
      "epoch": 0.03881372147054804,
      "grad_norm": 0.39087459444999695,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.8545,
      "step": 71
    },
    {
      "epoch": 0.03936039360393604,
      "grad_norm": 0.4205693304538727,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.8172,
      "step": 72
    },
    {
      "epoch": 0.03990706573732404,
      "grad_norm": 0.4108438789844513,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.8648,
      "step": 73
    },
    {
      "epoch": 0.04045373787071204,
      "grad_norm": 0.3966136872768402,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.8309,
      "step": 74
    },
    {
      "epoch": 0.04100041000410004,
      "grad_norm": 0.40907979011535645,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.8192,
      "step": 75
    },
    {
      "epoch": 0.04154708213748804,
      "grad_norm": 0.4363439083099365,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.9368,
      "step": 76
    },
    {
      "epoch": 0.04209375427087604,
      "grad_norm": 0.491629958152771,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.9145,
      "step": 77
    },
    {
      "epoch": 0.04264042640426404,
      "grad_norm": 0.4541201889514923,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8231,
      "step": 78
    },
    {
      "epoch": 0.04318709853765204,
      "grad_norm": 0.4886787533760071,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.938,
      "step": 79
    },
    {
      "epoch": 0.04373377067104004,
      "grad_norm": 0.5285751819610596,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7741,
      "step": 80
    },
    {
      "epoch": 0.04428044280442804,
      "grad_norm": 0.5779556632041931,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7631,
      "step": 81
    },
    {
      "epoch": 0.04482711493781605,
      "grad_norm": 0.48515424132347107,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.8665,
      "step": 82
    },
    {
      "epoch": 0.04537378707120405,
      "grad_norm": 0.574564516544342,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8031,
      "step": 83
    },
    {
      "epoch": 0.04592045920459205,
      "grad_norm": 0.7102771997451782,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.9174,
      "step": 84
    },
    {
      "epoch": 0.04646713133798005,
      "grad_norm": 0.5967442989349365,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6952,
      "step": 85
    },
    {
      "epoch": 0.04701380347136805,
      "grad_norm": 0.6809207797050476,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9056,
      "step": 86
    },
    {
      "epoch": 0.04756047560475605,
      "grad_norm": 0.7411814332008362,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.8733,
      "step": 87
    },
    {
      "epoch": 0.04810714773814405,
      "grad_norm": 0.738089382648468,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7369,
      "step": 88
    },
    {
      "epoch": 0.04865381987153205,
      "grad_norm": 0.7281075716018677,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7636,
      "step": 89
    },
    {
      "epoch": 0.04920049200492005,
      "grad_norm": 0.8782175779342651,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.9889,
      "step": 90
    },
    {
      "epoch": 0.04974716413830805,
      "grad_norm": 0.9165307283401489,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7913,
      "step": 91
    },
    {
      "epoch": 0.05029383627169605,
      "grad_norm": 0.8662875294685364,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.9658,
      "step": 92
    },
    {
      "epoch": 0.05084050840508405,
      "grad_norm": 0.8678541779518127,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.9923,
      "step": 93
    },
    {
      "epoch": 0.05138718053847205,
      "grad_norm": 0.9310894012451172,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.9293,
      "step": 94
    },
    {
      "epoch": 0.05193385267186005,
      "grad_norm": 0.9479677677154541,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.9141,
      "step": 95
    },
    {
      "epoch": 0.05248052480524805,
      "grad_norm": 0.9137459397315979,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.9577,
      "step": 96
    },
    {
      "epoch": 0.053027196938636056,
      "grad_norm": 0.9934679269790649,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.9613,
      "step": 97
    },
    {
      "epoch": 0.053573869072024057,
      "grad_norm": 1.1777949333190918,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0094,
      "step": 98
    },
    {
      "epoch": 0.05412054120541206,
      "grad_norm": 1.270877718925476,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.9323,
      "step": 99
    },
    {
      "epoch": 0.05466721333880006,
      "grad_norm": 1.4865914583206177,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8477,
      "step": 100
    },
    {
      "epoch": 0.05466721333880006,
      "eval_loss": 0.8316740393638611,
      "eval_runtime": 97.3339,
      "eval_samples_per_second": 31.654,
      "eval_steps_per_second": 7.921,
      "step": 100
    },
    {
      "epoch": 0.05521388547218806,
      "grad_norm": 0.22655868530273438,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4252,
      "step": 101
    },
    {
      "epoch": 0.05576055760557606,
      "grad_norm": 0.23559735715389252,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5393,
      "step": 102
    },
    {
      "epoch": 0.05630722973896406,
      "grad_norm": 0.303044855594635,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.6636,
      "step": 103
    },
    {
      "epoch": 0.05685390187235206,
      "grad_norm": 0.3049126863479614,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7799,
      "step": 104
    },
    {
      "epoch": 0.05740057400574006,
      "grad_norm": 0.30967023968696594,
      "learning_rate": 5e-05,
      "loss": 0.7729,
      "step": 105
    },
    {
      "epoch": 0.05794724613912806,
      "grad_norm": 0.3273995816707611,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.7487,
      "step": 106
    },
    {
      "epoch": 0.05849391827251606,
      "grad_norm": 0.35926833748817444,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.8707,
      "step": 107
    },
    {
      "epoch": 0.05904059040590406,
      "grad_norm": 0.3108914792537689,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.7284,
      "step": 108
    },
    {
      "epoch": 0.05958726253929206,
      "grad_norm": 0.31308290362358093,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.7675,
      "step": 109
    },
    {
      "epoch": 0.06013393467268006,
      "grad_norm": 0.32868656516075134,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.7792,
      "step": 110
    },
    {
      "epoch": 0.06068060680606806,
      "grad_norm": 0.3666906952857971,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.7261,
      "step": 111
    },
    {
      "epoch": 0.061227278939456065,
      "grad_norm": 0.3456765413284302,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.6404,
      "step": 112
    },
    {
      "epoch": 0.061773951072844065,
      "grad_norm": 0.35511282086372375,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7718,
      "step": 113
    },
    {
      "epoch": 0.062320623206232065,
      "grad_norm": 0.3306672275066376,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.7311,
      "step": 114
    },
    {
      "epoch": 0.06286729533962006,
      "grad_norm": 0.3338456451892853,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7137,
      "step": 115
    },
    {
      "epoch": 0.06341396747300806,
      "grad_norm": 0.4029041826725006,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.839,
      "step": 116
    },
    {
      "epoch": 0.06396063960639606,
      "grad_norm": 0.3924928903579712,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.8505,
      "step": 117
    },
    {
      "epoch": 0.06450731173978407,
      "grad_norm": 0.3895188868045807,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7668,
      "step": 118
    },
    {
      "epoch": 0.06505398387317206,
      "grad_norm": 0.36792147159576416,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.765,
      "step": 119
    },
    {
      "epoch": 0.06560065600656007,
      "grad_norm": 0.3897154629230499,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8566,
      "step": 120
    },
    {
      "epoch": 0.06614732813994807,
      "grad_norm": 0.34125691652297974,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7822,
      "step": 121
    },
    {
      "epoch": 0.06669400027333607,
      "grad_norm": 0.4398977756500244,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.9144,
      "step": 122
    },
    {
      "epoch": 0.06724067240672407,
      "grad_norm": 0.40511661767959595,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.8572,
      "step": 123
    },
    {
      "epoch": 0.06778734454011207,
      "grad_norm": 0.3971826136112213,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8615,
      "step": 124
    },
    {
      "epoch": 0.06833401667350007,
      "grad_norm": 0.4220927655696869,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.8308,
      "step": 125
    },
    {
      "epoch": 0.06888068880688807,
      "grad_norm": 0.4385756850242615,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.853,
      "step": 126
    },
    {
      "epoch": 0.06942736094027607,
      "grad_norm": 0.48937928676605225,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7775,
      "step": 127
    },
    {
      "epoch": 0.06997403307366407,
      "grad_norm": 0.4303417205810547,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.6566,
      "step": 128
    },
    {
      "epoch": 0.07052070520705207,
      "grad_norm": 0.5215846300125122,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.8281,
      "step": 129
    },
    {
      "epoch": 0.07106737734044007,
      "grad_norm": 0.4792439341545105,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7626,
      "step": 130
    },
    {
      "epoch": 0.07161404947382807,
      "grad_norm": 0.4871768653392792,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.8331,
      "step": 131
    },
    {
      "epoch": 0.07216072160721607,
      "grad_norm": 0.6033509373664856,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.8205,
      "step": 132
    },
    {
      "epoch": 0.07270739374060407,
      "grad_norm": 0.5285858511924744,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7063,
      "step": 133
    },
    {
      "epoch": 0.07325406587399207,
      "grad_norm": 0.7049718499183655,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7961,
      "step": 134
    },
    {
      "epoch": 0.07380073800738007,
      "grad_norm": 0.7140984535217285,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.9019,
      "step": 135
    },
    {
      "epoch": 0.07434741014076808,
      "grad_norm": 0.6189845204353333,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.9155,
      "step": 136
    },
    {
      "epoch": 0.07489408227415607,
      "grad_norm": 0.7536526322364807,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8957,
      "step": 137
    },
    {
      "epoch": 0.07544075440754408,
      "grad_norm": 0.6665773391723633,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.8459,
      "step": 138
    },
    {
      "epoch": 0.07598742654093207,
      "grad_norm": 0.7366706132888794,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.9508,
      "step": 139
    },
    {
      "epoch": 0.07653409867432008,
      "grad_norm": 0.835137128829956,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.081,
      "step": 140
    },
    {
      "epoch": 0.07708077080770807,
      "grad_norm": 0.7635148763656616,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.0036,
      "step": 141
    },
    {
      "epoch": 0.07762744294109608,
      "grad_norm": 0.865788996219635,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.919,
      "step": 142
    },
    {
      "epoch": 0.07817411507448407,
      "grad_norm": 0.858587384223938,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8688,
      "step": 143
    },
    {
      "epoch": 0.07872078720787208,
      "grad_norm": 0.9220221638679504,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.0861,
      "step": 144
    },
    {
      "epoch": 0.07926745934126007,
      "grad_norm": 0.8511350154876709,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.8834,
      "step": 145
    },
    {
      "epoch": 0.07981413147464808,
      "grad_norm": 0.9338250160217285,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.0603,
      "step": 146
    },
    {
      "epoch": 0.08036080360803607,
      "grad_norm": 0.8890387415885925,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.887,
      "step": 147
    },
    {
      "epoch": 0.08090747574142408,
      "grad_norm": 1.3564544916152954,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.9562,
      "step": 148
    },
    {
      "epoch": 0.08145414787481207,
      "grad_norm": 1.1206952333450317,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.843,
      "step": 149
    },
    {
      "epoch": 0.08200082000820008,
      "grad_norm": 1.4429903030395508,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.933,
      "step": 150
    },
    {
      "epoch": 0.08200082000820008,
      "eval_loss": 0.8216313719749451,
      "eval_runtime": 97.4704,
      "eval_samples_per_second": 31.61,
      "eval_steps_per_second": 7.91,
      "step": 150
    },
    {
      "epoch": 0.08254749214158809,
      "grad_norm": 0.24565434455871582,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.5379,
      "step": 151
    },
    {
      "epoch": 0.08309416427497608,
      "grad_norm": 0.2382674217224121,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.4801,
      "step": 152
    },
    {
      "epoch": 0.08364083640836409,
      "grad_norm": 0.3419133126735687,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7045,
      "step": 153
    },
    {
      "epoch": 0.08418750854175208,
      "grad_norm": 0.2874261736869812,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.7787,
      "step": 154
    },
    {
      "epoch": 0.08473418067514009,
      "grad_norm": 0.27888223528862,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.696,
      "step": 155
    },
    {
      "epoch": 0.08528085280852808,
      "grad_norm": 0.26107171177864075,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5702,
      "step": 156
    },
    {
      "epoch": 0.08582752494191609,
      "grad_norm": 0.31347405910491943,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.7934,
      "step": 157
    },
    {
      "epoch": 0.08637419707530408,
      "grad_norm": 0.32900470495224,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.8004,
      "step": 158
    },
    {
      "epoch": 0.08692086920869209,
      "grad_norm": 0.31359201669692993,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.7957,
      "step": 159
    },
    {
      "epoch": 0.08746754134208008,
      "grad_norm": 0.2995634377002716,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7908,
      "step": 160
    },
    {
      "epoch": 0.08801421347546809,
      "grad_norm": 0.3189164400100708,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.6818,
      "step": 161
    },
    {
      "epoch": 0.08856088560885608,
      "grad_norm": 0.32028207182884216,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7752,
      "step": 162
    },
    {
      "epoch": 0.08910755774224409,
      "grad_norm": 0.31895431876182556,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.7536,
      "step": 163
    },
    {
      "epoch": 0.0896542298756321,
      "grad_norm": 0.40144073963165283,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.8963,
      "step": 164
    },
    {
      "epoch": 0.09020090200902009,
      "grad_norm": 0.3307654559612274,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.8065,
      "step": 165
    },
    {
      "epoch": 0.0907475741424081,
      "grad_norm": 0.3702203929424286,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.81,
      "step": 166
    },
    {
      "epoch": 0.09129424627579609,
      "grad_norm": 0.3444533944129944,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.8369,
      "step": 167
    },
    {
      "epoch": 0.0918409184091841,
      "grad_norm": 0.3747360408306122,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.8286,
      "step": 168
    },
    {
      "epoch": 0.09238759054257209,
      "grad_norm": 0.33142971992492676,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.7242,
      "step": 169
    },
    {
      "epoch": 0.0929342626759601,
      "grad_norm": 0.3446040749549866,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.8383,
      "step": 170
    },
    {
      "epoch": 0.09348093480934809,
      "grad_norm": 0.3630118668079376,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.8188,
      "step": 171
    },
    {
      "epoch": 0.0940276069427361,
      "grad_norm": 0.370663046836853,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.8025,
      "step": 172
    },
    {
      "epoch": 0.09457427907612409,
      "grad_norm": 0.4290924072265625,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.855,
      "step": 173
    },
    {
      "epoch": 0.0951209512095121,
      "grad_norm": 0.3850495219230652,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7834,
      "step": 174
    },
    {
      "epoch": 0.09566762334290009,
      "grad_norm": 0.36990657448768616,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.7968,
      "step": 175
    },
    {
      "epoch": 0.0962142954762881,
      "grad_norm": 0.4475378692150116,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.9111,
      "step": 176
    },
    {
      "epoch": 0.09676096760967609,
      "grad_norm": 0.4499093294143677,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7477,
      "step": 177
    },
    {
      "epoch": 0.0973076397430641,
      "grad_norm": 0.5280972719192505,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.8695,
      "step": 178
    },
    {
      "epoch": 0.0978543118764521,
      "grad_norm": 0.5211724042892456,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.953,
      "step": 179
    },
    {
      "epoch": 0.0984009840098401,
      "grad_norm": 0.5142869353294373,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.8843,
      "step": 180
    },
    {
      "epoch": 0.0989476561432281,
      "grad_norm": 0.5148847699165344,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.8872,
      "step": 181
    },
    {
      "epoch": 0.0994943282766161,
      "grad_norm": 0.6282923221588135,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.9643,
      "step": 182
    },
    {
      "epoch": 0.1000410004100041,
      "grad_norm": 0.526904284954071,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7796,
      "step": 183
    },
    {
      "epoch": 0.1005876725433921,
      "grad_norm": 0.5684937834739685,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.9298,
      "step": 184
    },
    {
      "epoch": 0.1011343446767801,
      "grad_norm": 0.6490432620048523,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.8171,
      "step": 185
    },
    {
      "epoch": 0.1016810168101681,
      "grad_norm": 0.6962558627128601,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.8411,
      "step": 186
    },
    {
      "epoch": 0.1022276889435561,
      "grad_norm": 0.613287627696991,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.8406,
      "step": 187
    },
    {
      "epoch": 0.1027743610769441,
      "grad_norm": 0.7226855158805847,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.9352,
      "step": 188
    },
    {
      "epoch": 0.1033210332103321,
      "grad_norm": 0.8014253377914429,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.9098,
      "step": 189
    },
    {
      "epoch": 0.1038677053437201,
      "grad_norm": 0.7776386737823486,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.8603,
      "step": 190
    },
    {
      "epoch": 0.1044143774771081,
      "grad_norm": 0.7920184135437012,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.9921,
      "step": 191
    },
    {
      "epoch": 0.1049610496104961,
      "grad_norm": 0.7594107985496521,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7962,
      "step": 192
    },
    {
      "epoch": 0.1055077217438841,
      "grad_norm": 0.9584674835205078,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.9878,
      "step": 193
    },
    {
      "epoch": 0.10605439387727211,
      "grad_norm": 0.9975190758705139,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.9401,
      "step": 194
    },
    {
      "epoch": 0.1066010660106601,
      "grad_norm": 0.8227145075798035,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.9677,
      "step": 195
    },
    {
      "epoch": 0.10714773814404811,
      "grad_norm": 1.0568969249725342,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.8377,
      "step": 196
    },
    {
      "epoch": 0.1076944102774361,
      "grad_norm": 1.0103193521499634,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.9803,
      "step": 197
    },
    {
      "epoch": 0.10824108241082411,
      "grad_norm": 0.9891074299812317,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.0398,
      "step": 198
    },
    {
      "epoch": 0.1087877545442121,
      "grad_norm": 1.0939799547195435,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.698,
      "step": 199
    },
    {
      "epoch": 0.10933442667760011,
      "grad_norm": 1.4613440036773682,
      "learning_rate": 0.0,
      "loss": 0.7824,
      "step": 200
    },
    {
      "epoch": 0.10933442667760011,
      "eval_loss": 0.8110023736953735,
      "eval_runtime": 97.3761,
      "eval_samples_per_second": 31.64,
      "eval_steps_per_second": 7.918,
      "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": 5.776271908798464e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}