{
  "best_metric": 0.6185301542282104,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.2271436683702442,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001135718341851221,
      "grad_norm": 0.28587621450424194,
      "learning_rate": 1e-05,
      "loss": 0.5342,
      "step": 1
    },
    {
      "epoch": 0.001135718341851221,
      "eval_loss": 0.9649807810783386,
      "eval_runtime": 45.1782,
      "eval_samples_per_second": 32.826,
      "eval_steps_per_second": 8.212,
      "step": 1
    },
    {
      "epoch": 0.002271436683702442,
      "grad_norm": 0.2883836030960083,
      "learning_rate": 2e-05,
      "loss": 0.6004,
      "step": 2
    },
    {
      "epoch": 0.0034071550255536627,
      "grad_norm": 0.2831919193267822,
      "learning_rate": 3e-05,
      "loss": 0.5044,
      "step": 3
    },
    {
      "epoch": 0.004542873367404884,
      "grad_norm": 0.2778588533401489,
      "learning_rate": 4e-05,
      "loss": 0.6686,
      "step": 4
    },
    {
      "epoch": 0.0056785917092561046,
      "grad_norm": 0.2853076159954071,
      "learning_rate": 5e-05,
      "loss": 0.713,
      "step": 5
    },
    {
      "epoch": 0.0068143100511073255,
      "grad_norm": 0.3056105971336365,
      "learning_rate": 6e-05,
      "loss": 0.7237,
      "step": 6
    },
    {
      "epoch": 0.007950028392958546,
      "grad_norm": 0.28540077805519104,
      "learning_rate": 7e-05,
      "loss": 0.5959,
      "step": 7
    },
    {
      "epoch": 0.009085746734809767,
      "grad_norm": 0.304429829120636,
      "learning_rate": 8e-05,
      "loss": 0.6697,
      "step": 8
    },
    {
      "epoch": 0.010221465076660987,
      "grad_norm": 0.31493642926216125,
      "learning_rate": 9e-05,
      "loss": 0.7212,
      "step": 9
    },
    {
      "epoch": 0.011357183418512209,
      "grad_norm": 0.3360876739025116,
      "learning_rate": 0.0001,
      "loss": 0.7119,
      "step": 10
    },
    {
      "epoch": 0.01249290176036343,
      "grad_norm": 0.33844152092933655,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8433,
      "step": 11
    },
    {
      "epoch": 0.013628620102214651,
      "grad_norm": 0.30477261543273926,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.6937,
      "step": 12
    },
    {
      "epoch": 0.014764338444065871,
      "grad_norm": 0.4441061019897461,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.6255,
      "step": 13
    },
    {
      "epoch": 0.01590005678591709,
      "grad_norm": 0.3593422770500183,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.6035,
      "step": 14
    },
    {
      "epoch": 0.017035775127768313,
      "grad_norm": 0.3784604072570801,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5875,
      "step": 15
    },
    {
      "epoch": 0.018171493469619535,
      "grad_norm": 0.32449987530708313,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.5847,
      "step": 16
    },
    {
      "epoch": 0.019307211811470756,
      "grad_norm": 0.3020523190498352,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6235,
      "step": 17
    },
    {
      "epoch": 0.020442930153321975,
      "grad_norm": 0.325476735830307,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.7309,
      "step": 18
    },
    {
      "epoch": 0.021578648495173196,
      "grad_norm": 0.2985352575778961,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.5713,
      "step": 19
    },
    {
      "epoch": 0.022714366837024418,
      "grad_norm": 0.5520193576812744,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6346,
      "step": 20
    },
    {
      "epoch": 0.02385008517887564,
      "grad_norm": 0.3754502534866333,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.5562,
      "step": 21
    },
    {
      "epoch": 0.02498580352072686,
      "grad_norm": 0.35194963216781616,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.5782,
      "step": 22
    },
    {
      "epoch": 0.02612152186257808,
      "grad_norm": 0.34777048230171204,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6927,
      "step": 23
    },
    {
      "epoch": 0.027257240204429302,
      "grad_norm": 0.3555465340614319,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.6566,
      "step": 24
    },
    {
      "epoch": 0.028392958546280524,
      "grad_norm": 0.3510722517967224,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5784,
      "step": 25
    },
    {
      "epoch": 0.029528676888131742,
      "grad_norm": 0.3669740855693817,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.572,
      "step": 26
    },
    {
      "epoch": 0.030664395229982964,
      "grad_norm": 0.3677334189414978,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.478,
      "step": 27
    },
    {
      "epoch": 0.03180011357183418,
      "grad_norm": 0.3556850254535675,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.5437,
      "step": 28
    },
    {
      "epoch": 0.032935831913685404,
      "grad_norm": 0.3665291666984558,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4554,
      "step": 29
    },
    {
      "epoch": 0.034071550255536626,
      "grad_norm": 0.44375571608543396,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.5728,
      "step": 30
    },
    {
      "epoch": 0.03520726859738785,
      "grad_norm": 0.5056313276290894,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6432,
      "step": 31
    },
    {
      "epoch": 0.03634298693923907,
      "grad_norm": 0.47293323278427124,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.657,
      "step": 32
    },
    {
      "epoch": 0.03747870528109029,
      "grad_norm": 0.49744749069213867,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7089,
      "step": 33
    },
    {
      "epoch": 0.03861442362294151,
      "grad_norm": 0.4489412009716034,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6226,
      "step": 34
    },
    {
      "epoch": 0.039750141964792735,
      "grad_norm": 0.5018207430839539,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7271,
      "step": 35
    },
    {
      "epoch": 0.04088586030664395,
      "grad_norm": 0.5215710401535034,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.6084,
      "step": 36
    },
    {
      "epoch": 0.04202157864849517,
      "grad_norm": 0.5685145854949951,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.5973,
      "step": 37
    },
    {
      "epoch": 0.04315729699034639,
      "grad_norm": 0.617323637008667,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.6381,
      "step": 38
    },
    {
      "epoch": 0.044293015332197615,
      "grad_norm": 0.5867332220077515,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.5594,
      "step": 39
    },
    {
      "epoch": 0.045428733674048836,
      "grad_norm": 0.6086481809616089,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8105,
      "step": 40
    },
    {
      "epoch": 0.04656445201590006,
      "grad_norm": 0.6420219540596008,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6315,
      "step": 41
    },
    {
      "epoch": 0.04770017035775128,
      "grad_norm": 0.5783979892730713,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7278,
      "step": 42
    },
    {
      "epoch": 0.0488358886996025,
      "grad_norm": 0.551679790019989,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6533,
      "step": 43
    },
    {
      "epoch": 0.04997160704145372,
      "grad_norm": 0.5775166153907776,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7946,
      "step": 44
    },
    {
      "epoch": 0.05110732538330494,
      "grad_norm": 0.5262088775634766,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.833,
      "step": 45
    },
    {
      "epoch": 0.05224304372515616,
      "grad_norm": 0.5546041131019592,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6032,
      "step": 46
    },
    {
      "epoch": 0.05337876206700738,
      "grad_norm": 0.7229691743850708,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8234,
      "step": 47
    },
    {
      "epoch": 0.054514480408858604,
      "grad_norm": 0.6842191815376282,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8742,
      "step": 48
    },
    {
      "epoch": 0.055650198750709826,
      "grad_norm": 1.1393651962280273,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0264,
      "step": 49
    },
    {
      "epoch": 0.05678591709256105,
      "grad_norm": 1.6334478855133057,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.8657,
      "step": 50
    },
    {
      "epoch": 0.05678591709256105,
      "eval_loss": 0.6582953333854675,
      "eval_runtime": 45.174,
      "eval_samples_per_second": 32.829,
      "eval_steps_per_second": 8.213,
      "step": 50
    },
    {
      "epoch": 0.05792163543441227,
      "grad_norm": 0.1891520470380783,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4388,
      "step": 51
    },
    {
      "epoch": 0.059057353776263484,
      "grad_norm": 0.24352461099624634,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.5765,
      "step": 52
    },
    {
      "epoch": 0.060193072118114706,
      "grad_norm": 0.2556052803993225,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.4889,
      "step": 53
    },
    {
      "epoch": 0.06132879045996593,
      "grad_norm": 0.27673864364624023,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.612,
      "step": 54
    },
    {
      "epoch": 0.06246450880181715,
      "grad_norm": 0.2975902557373047,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6353,
      "step": 55
    },
    {
      "epoch": 0.06360022714366836,
      "grad_norm": 0.27071166038513184,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7141,
      "step": 56
    },
    {
      "epoch": 0.06473594548551959,
      "grad_norm": 0.2838987112045288,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8059,
      "step": 57
    },
    {
      "epoch": 0.06587166382737081,
      "grad_norm": 0.3135128915309906,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.9673,
      "step": 58
    },
    {
      "epoch": 0.06700738216922203,
      "grad_norm": 0.30168676376342773,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.5871,
      "step": 59
    },
    {
      "epoch": 0.06814310051107325,
      "grad_norm": 0.29614490270614624,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6503,
      "step": 60
    },
    {
      "epoch": 0.06927881885292447,
      "grad_norm": 0.2764257490634918,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6762,
      "step": 61
    },
    {
      "epoch": 0.0704145371947757,
      "grad_norm": 0.29700255393981934,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8599,
      "step": 62
    },
    {
      "epoch": 0.07155025553662692,
      "grad_norm": 0.2648394703865051,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5471,
      "step": 63
    },
    {
      "epoch": 0.07268597387847814,
      "grad_norm": 0.3043407201766968,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6099,
      "step": 64
    },
    {
      "epoch": 0.07382169222032936,
      "grad_norm": 0.2747691571712494,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5428,
      "step": 65
    },
    {
      "epoch": 0.07495741056218058,
      "grad_norm": 0.33190101385116577,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6866,
      "step": 66
    },
    {
      "epoch": 0.0760931289040318,
      "grad_norm": 0.3031877875328064,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.587,
      "step": 67
    },
    {
      "epoch": 0.07722884724588303,
      "grad_norm": 0.2695032060146332,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.5381,
      "step": 68
    },
    {
      "epoch": 0.07836456558773425,
      "grad_norm": 0.266230970621109,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.4978,
      "step": 69
    },
    {
      "epoch": 0.07950028392958547,
      "grad_norm": 0.27955299615859985,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5467,
      "step": 70
    },
    {
      "epoch": 0.08063600227143668,
      "grad_norm": 0.2760303020477295,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.5855,
      "step": 71
    },
    {
      "epoch": 0.0817717206132879,
      "grad_norm": 0.2622968852519989,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5038,
      "step": 72
    },
    {
      "epoch": 0.08290743895513912,
      "grad_norm": 0.27819812297821045,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5153,
      "step": 73
    },
    {
      "epoch": 0.08404315729699034,
      "grad_norm": 0.3057125210762024,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.5795,
      "step": 74
    },
    {
      "epoch": 0.08517887563884156,
      "grad_norm": 0.3000001609325409,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.5289,
      "step": 75
    },
    {
      "epoch": 0.08631459398069279,
      "grad_norm": 0.31792858242988586,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6631,
      "step": 76
    },
    {
      "epoch": 0.08745031232254401,
      "grad_norm": 0.34289002418518066,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.674,
      "step": 77
    },
    {
      "epoch": 0.08858603066439523,
      "grad_norm": 0.33311328291893005,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.5904,
      "step": 78
    },
    {
      "epoch": 0.08972174900624645,
      "grad_norm": 0.5390769243240356,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.5572,
      "step": 79
    },
    {
      "epoch": 0.09085746734809767,
      "grad_norm": 0.3349092900753021,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.5724,
      "step": 80
    },
    {
      "epoch": 0.0919931856899489,
      "grad_norm": 0.32684823870658875,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.4915,
      "step": 81
    },
    {
      "epoch": 0.09312890403180012,
      "grad_norm": 0.3935104310512543,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.4288,
      "step": 82
    },
    {
      "epoch": 0.09426462237365134,
      "grad_norm": 0.3680626451969147,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.5688,
      "step": 83
    },
    {
      "epoch": 0.09540034071550256,
      "grad_norm": 0.4408837854862213,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.5658,
      "step": 84
    },
    {
      "epoch": 0.09653605905735378,
      "grad_norm": 0.6107640266418457,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6462,
      "step": 85
    },
    {
      "epoch": 0.097671777399205,
      "grad_norm": 0.4316844940185547,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6678,
      "step": 86
    },
    {
      "epoch": 0.09880749574105621,
      "grad_norm": 0.469474732875824,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6106,
      "step": 87
    },
    {
      "epoch": 0.09994321408290743,
      "grad_norm": 0.46427488327026367,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7108,
      "step": 88
    },
    {
      "epoch": 0.10107893242475866,
      "grad_norm": 0.5984750390052795,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7294,
      "step": 89
    },
    {
      "epoch": 0.10221465076660988,
      "grad_norm": 0.5776738524436951,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5364,
      "step": 90
    },
    {
      "epoch": 0.1033503691084611,
      "grad_norm": 0.480001300573349,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6483,
      "step": 91
    },
    {
      "epoch": 0.10448608745031232,
      "grad_norm": 0.4645431935787201,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.5624,
      "step": 92
    },
    {
      "epoch": 0.10562180579216354,
      "grad_norm": 0.45610418915748596,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.554,
      "step": 93
    },
    {
      "epoch": 0.10675752413401476,
      "grad_norm": 0.4992101490497589,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7384,
      "step": 94
    },
    {
      "epoch": 0.10789324247586599,
      "grad_norm": 0.5353257656097412,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.809,
      "step": 95
    },
    {
      "epoch": 0.10902896081771721,
      "grad_norm": 0.5114256143569946,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5357,
      "step": 96
    },
    {
      "epoch": 0.11016467915956843,
      "grad_norm": 0.6297036409378052,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7608,
      "step": 97
    },
    {
      "epoch": 0.11130039750141965,
      "grad_norm": 0.6160755753517151,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7081,
      "step": 98
    },
    {
      "epoch": 0.11243611584327087,
      "grad_norm": 0.8610752820968628,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7427,
      "step": 99
    },
    {
      "epoch": 0.1135718341851221,
      "grad_norm": 1.1927225589752197,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8926,
      "step": 100
    },
    {
      "epoch": 0.1135718341851221,
      "eval_loss": 0.6406848430633545,
      "eval_runtime": 45.3409,
      "eval_samples_per_second": 32.708,
      "eval_steps_per_second": 8.182,
      "step": 100
    },
    {
      "epoch": 0.11470755252697332,
      "grad_norm": 0.20554471015930176,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.6411,
      "step": 101
    },
    {
      "epoch": 0.11584327086882454,
      "grad_norm": 0.18406450748443604,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5401,
      "step": 102
    },
    {
      "epoch": 0.11697898921067575,
      "grad_norm": 0.2107355296611786,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.6546,
      "step": 103
    },
    {
      "epoch": 0.11811470755252697,
      "grad_norm": 0.2293836921453476,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.6375,
      "step": 104
    },
    {
      "epoch": 0.11925042589437819,
      "grad_norm": 0.22309936583042145,
      "learning_rate": 5e-05,
      "loss": 0.6583,
      "step": 105
    },
    {
      "epoch": 0.12038614423622941,
      "grad_norm": 0.25468921661376953,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.6559,
      "step": 106
    },
    {
      "epoch": 0.12152186257808063,
      "grad_norm": 0.22292295098304749,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.7567,
      "step": 107
    },
    {
      "epoch": 0.12265758091993186,
      "grad_norm": 0.22964225709438324,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.7859,
      "step": 108
    },
    {
      "epoch": 0.12379329926178308,
      "grad_norm": 0.2538079023361206,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6493,
      "step": 109
    },
    {
      "epoch": 0.1249290176036343,
      "grad_norm": 0.25034886598587036,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.6773,
      "step": 110
    },
    {
      "epoch": 0.1260647359454855,
      "grad_norm": 0.2586336135864258,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.5549,
      "step": 111
    },
    {
      "epoch": 0.12720045428733673,
      "grad_norm": 0.2829302251338959,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.717,
      "step": 112
    },
    {
      "epoch": 0.12833617262918795,
      "grad_norm": 0.2507753074169159,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.6245,
      "step": 113
    },
    {
      "epoch": 0.12947189097103917,
      "grad_norm": 0.24705368280410767,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6405,
      "step": 114
    },
    {
      "epoch": 0.1306076093128904,
      "grad_norm": 0.2499982863664627,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.6437,
      "step": 115
    },
    {
      "epoch": 0.13174332765474162,
      "grad_norm": 0.2599751949310303,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.5369,
      "step": 116
    },
    {
      "epoch": 0.13287904599659284,
      "grad_norm": 0.2495185136795044,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.4994,
      "step": 117
    },
    {
      "epoch": 0.13401476433844406,
      "grad_norm": 0.29191693663597107,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7,
      "step": 118
    },
    {
      "epoch": 0.13515048268029528,
      "grad_norm": 0.2529820501804352,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.5028,
      "step": 119
    },
    {
      "epoch": 0.1362862010221465,
      "grad_norm": 0.30688759684562683,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.5004,
      "step": 120
    },
    {
      "epoch": 0.13742191936399772,
      "grad_norm": 0.25404050946235657,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5795,
      "step": 121
    },
    {
      "epoch": 0.13855763770584895,
      "grad_norm": 0.2841479778289795,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6493,
      "step": 122
    },
    {
      "epoch": 0.13969335604770017,
      "grad_norm": 0.28411149978637695,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.6535,
      "step": 123
    },
    {
      "epoch": 0.1408290743895514,
      "grad_norm": 0.27034473419189453,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5072,
      "step": 124
    },
    {
      "epoch": 0.1419647927314026,
      "grad_norm": 0.30387383699417114,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.5385,
      "step": 125
    },
    {
      "epoch": 0.14310051107325383,
      "grad_norm": 0.3213527798652649,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6015,
      "step": 126
    },
    {
      "epoch": 0.14423622941510506,
      "grad_norm": 0.3365834951400757,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.5615,
      "step": 127
    },
    {
      "epoch": 0.14537194775695628,
      "grad_norm": 0.32947126030921936,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.6012,
      "step": 128
    },
    {
      "epoch": 0.1465076660988075,
      "grad_norm": 0.3885734975337982,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.6578,
      "step": 129
    },
    {
      "epoch": 0.14764338444065872,
      "grad_norm": 0.3276621103286743,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.4654,
      "step": 130
    },
    {
      "epoch": 0.14877910278250994,
      "grad_norm": 0.3912336230278015,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6163,
      "step": 131
    },
    {
      "epoch": 0.14991482112436116,
      "grad_norm": 0.3491542637348175,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.4827,
      "step": 132
    },
    {
      "epoch": 0.15105053946621239,
      "grad_norm": 0.37011754512786865,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.4593,
      "step": 133
    },
    {
      "epoch": 0.1521862578080636,
      "grad_norm": 0.4029077887535095,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6057,
      "step": 134
    },
    {
      "epoch": 0.15332197614991483,
      "grad_norm": 0.4404357373714447,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6726,
      "step": 135
    },
    {
      "epoch": 0.15445769449176605,
      "grad_norm": 0.5280731320381165,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.5016,
      "step": 136
    },
    {
      "epoch": 0.15559341283361727,
      "grad_norm": 0.4749316871166229,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.5482,
      "step": 137
    },
    {
      "epoch": 0.1567291311754685,
      "grad_norm": 0.5895432233810425,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6207,
      "step": 138
    },
    {
      "epoch": 0.15786484951731972,
      "grad_norm": 0.4824456572532654,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.64,
      "step": 139
    },
    {
      "epoch": 0.15900056785917094,
      "grad_norm": 0.5339910387992859,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.5273,
      "step": 140
    },
    {
      "epoch": 0.16013628620102216,
      "grad_norm": 0.5747649669647217,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.662,
      "step": 141
    },
    {
      "epoch": 0.16127200454287335,
      "grad_norm": 0.5866848230361938,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6057,
      "step": 142
    },
    {
      "epoch": 0.16240772288472458,
      "grad_norm": 0.5015600919723511,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6192,
      "step": 143
    },
    {
      "epoch": 0.1635434412265758,
      "grad_norm": 0.5512033700942993,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7593,
      "step": 144
    },
    {
      "epoch": 0.16467915956842702,
      "grad_norm": 0.5022100806236267,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6241,
      "step": 145
    },
    {
      "epoch": 0.16581487791027824,
      "grad_norm": 0.5983948707580566,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7052,
      "step": 146
    },
    {
      "epoch": 0.16695059625212946,
      "grad_norm": 0.5650132298469543,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.695,
      "step": 147
    },
    {
      "epoch": 0.16808631459398068,
      "grad_norm": 0.7842047214508057,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.8074,
      "step": 148
    },
    {
      "epoch": 0.1692220329358319,
      "grad_norm": 0.8918259739875793,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.7603,
      "step": 149
    },
    {
      "epoch": 0.17035775127768313,
      "grad_norm": 1.3061697483062744,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.8332,
      "step": 150
    },
    {
      "epoch": 0.17035775127768313,
      "eval_loss": 0.6185301542282104,
      "eval_runtime": 45.4234,
      "eval_samples_per_second": 32.648,
      "eval_steps_per_second": 8.168,
      "step": 150
    },
    {
      "epoch": 0.17149346961953435,
      "grad_norm": 0.18895012140274048,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.5797,
      "step": 151
    },
    {
      "epoch": 0.17262918796138557,
      "grad_norm": 0.190827876329422,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.5819,
      "step": 152
    },
    {
      "epoch": 0.1737649063032368,
      "grad_norm": 0.19933661818504333,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.6377,
      "step": 153
    },
    {
      "epoch": 0.17490062464508802,
      "grad_norm": 0.21571186184883118,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.6887,
      "step": 154
    },
    {
      "epoch": 0.17603634298693924,
      "grad_norm": 0.19433721899986267,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.6778,
      "step": 155
    },
    {
      "epoch": 0.17717206132879046,
      "grad_norm": 0.22213636338710785,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5793,
      "step": 156
    },
    {
      "epoch": 0.17830777967064168,
      "grad_norm": 0.2186320424079895,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6682,
      "step": 157
    },
    {
      "epoch": 0.1794434980124929,
      "grad_norm": 0.2361341267824173,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.9224,
      "step": 158
    },
    {
      "epoch": 0.18057921635434412,
      "grad_norm": 0.20890240371227264,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.5749,
      "step": 159
    },
    {
      "epoch": 0.18171493469619535,
      "grad_norm": 0.24336326122283936,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.8155,
      "step": 160
    },
    {
      "epoch": 0.18285065303804657,
      "grad_norm": 0.23212853074073792,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.638,
      "step": 161
    },
    {
      "epoch": 0.1839863713798978,
      "grad_norm": 0.27072280645370483,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8677,
      "step": 162
    },
    {
      "epoch": 0.185122089721749,
      "grad_norm": 0.26696622371673584,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.6614,
      "step": 163
    },
    {
      "epoch": 0.18625780806360023,
      "grad_norm": 0.24532826244831085,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.5563,
      "step": 164
    },
    {
      "epoch": 0.18739352640545145,
      "grad_norm": 0.24894382059574127,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.6388,
      "step": 165
    },
    {
      "epoch": 0.18852924474730268,
      "grad_norm": 0.2568185329437256,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.5704,
      "step": 166
    },
    {
      "epoch": 0.1896649630891539,
      "grad_norm": 0.24981267750263214,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6179,
      "step": 167
    },
    {
      "epoch": 0.19080068143100512,
      "grad_norm": 0.2671128511428833,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.6103,
      "step": 168
    },
    {
      "epoch": 0.19193639977285634,
      "grad_norm": 0.2506977617740631,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.6122,
      "step": 169
    },
    {
      "epoch": 0.19307211811470756,
      "grad_norm": 0.26179465651512146,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.5909,
      "step": 170
    },
    {
      "epoch": 0.19420783645655879,
      "grad_norm": 0.26549869775772095,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.5224,
      "step": 171
    },
    {
      "epoch": 0.19534355479841,
      "grad_norm": 0.24327601492404938,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.5397,
      "step": 172
    },
    {
      "epoch": 0.1964792731402612,
      "grad_norm": 0.30363285541534424,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7488,
      "step": 173
    },
    {
      "epoch": 0.19761499148211242,
      "grad_norm": 0.2855435311794281,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.5755,
      "step": 174
    },
    {
      "epoch": 0.19875070982396364,
      "grad_norm": 0.2625669538974762,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.5558,
      "step": 175
    },
    {
      "epoch": 0.19988642816581487,
      "grad_norm": 0.3195722699165344,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.4974,
      "step": 176
    },
    {
      "epoch": 0.2010221465076661,
      "grad_norm": 0.32558995485305786,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6323,
      "step": 177
    },
    {
      "epoch": 0.2021578648495173,
      "grad_norm": 0.3191676139831543,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.5321,
      "step": 178
    },
    {
      "epoch": 0.20329358319136853,
      "grad_norm": 0.3231245279312134,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.4733,
      "step": 179
    },
    {
      "epoch": 0.20442930153321975,
      "grad_norm": 0.3315020501613617,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.5208,
      "step": 180
    },
    {
      "epoch": 0.20556501987507098,
      "grad_norm": 0.34713083505630493,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5754,
      "step": 181
    },
    {
      "epoch": 0.2067007382169222,
      "grad_norm": 0.3770761489868164,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.4128,
      "step": 182
    },
    {
      "epoch": 0.20783645655877342,
      "grad_norm": 0.38760489225387573,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.4062,
      "step": 183
    },
    {
      "epoch": 0.20897217490062464,
      "grad_norm": 0.4150284230709076,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7007,
      "step": 184
    },
    {
      "epoch": 0.21010789324247586,
      "grad_norm": 0.4335708022117615,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.5506,
      "step": 185
    },
    {
      "epoch": 0.21124361158432708,
      "grad_norm": 0.4963037073612213,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.7326,
      "step": 186
    },
    {
      "epoch": 0.2123793299261783,
      "grad_norm": 0.47023719549179077,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.5702,
      "step": 187
    },
    {
      "epoch": 0.21351504826802953,
      "grad_norm": 0.5179142355918884,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.5191,
      "step": 188
    },
    {
      "epoch": 0.21465076660988075,
      "grad_norm": 0.569351077079773,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.6699,
      "step": 189
    },
    {
      "epoch": 0.21578648495173197,
      "grad_norm": 0.5384606122970581,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.4858,
      "step": 190
    },
    {
      "epoch": 0.2169222032935832,
      "grad_norm": 0.49438852071762085,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.579,
      "step": 191
    },
    {
      "epoch": 0.21805792163543442,
      "grad_norm": 0.5486657023429871,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7633,
      "step": 192
    },
    {
      "epoch": 0.21919363997728564,
      "grad_norm": 0.5459057092666626,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7972,
      "step": 193
    },
    {
      "epoch": 0.22032935831913686,
      "grad_norm": 0.5266168713569641,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6087,
      "step": 194
    },
    {
      "epoch": 0.22146507666098808,
      "grad_norm": 0.45195409655570984,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.4778,
      "step": 195
    },
    {
      "epoch": 0.2226007950028393,
      "grad_norm": 0.4909007251262665,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.6842,
      "step": 196
    },
    {
      "epoch": 0.22373651334469052,
      "grad_norm": 0.7380678653717041,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6674,
      "step": 197
    },
    {
      "epoch": 0.22487223168654175,
      "grad_norm": 0.7934592366218567,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.9338,
      "step": 198
    },
    {
      "epoch": 0.22600795002839297,
      "grad_norm": 0.7410150170326233,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.6846,
      "step": 199
    },
    {
      "epoch": 0.2271436683702442,
      "grad_norm": 1.516480803489685,
      "learning_rate": 0.0,
      "loss": 0.763,
      "step": 200
    },
    {
      "epoch": 0.2271436683702442,
      "eval_loss": 0.6213229894638062,
      "eval_runtime": 45.2745,
      "eval_samples_per_second": 32.756,
      "eval_steps_per_second": 8.194,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.565359742517248e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}