{
  "best_metric": 1.06106698513031,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.07732456988208003,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007732456988208003,
      "grad_norm": 17.36431312561035,
      "learning_rate": 2e-05,
      "loss": 4.7994,
      "step": 1
    },
    {
      "epoch": 0.0007732456988208003,
      "eval_loss": 1.5391517877578735,
      "eval_runtime": 350.2016,
      "eval_samples_per_second": 1.556,
      "eval_steps_per_second": 0.78,
      "step": 1
    },
    {
      "epoch": 0.0015464913976416005,
      "grad_norm": 16.813636779785156,
      "learning_rate": 4e-05,
      "loss": 6.5771,
      "step": 2
    },
    {
      "epoch": 0.002319737096462401,
      "grad_norm": 15.335413932800293,
      "learning_rate": 6e-05,
      "loss": 6.3871,
      "step": 3
    },
    {
      "epoch": 0.003092982795283201,
      "grad_norm": 12.222745895385742,
      "learning_rate": 8e-05,
      "loss": 5.7415,
      "step": 4
    },
    {
      "epoch": 0.0038662284941040014,
      "grad_norm": 11.978750228881836,
      "learning_rate": 0.0001,
      "loss": 5.3726,
      "step": 5
    },
    {
      "epoch": 0.004639474192924802,
      "grad_norm": 10.958758354187012,
      "learning_rate": 9.997266286704631e-05,
      "loss": 5.7592,
      "step": 6
    },
    {
      "epoch": 0.005412719891745603,
      "grad_norm": 10.371870994567871,
      "learning_rate": 9.989068136093873e-05,
      "loss": 5.0328,
      "step": 7
    },
    {
      "epoch": 0.006185965590566402,
      "grad_norm": 15.32174301147461,
      "learning_rate": 9.975414512725057e-05,
      "loss": 4.7995,
      "step": 8
    },
    {
      "epoch": 0.0069592112893872024,
      "grad_norm": 11.446320533752441,
      "learning_rate": 9.956320346634876e-05,
      "loss": 4.8366,
      "step": 9
    },
    {
      "epoch": 0.007732456988208003,
      "grad_norm": 11.212560653686523,
      "learning_rate": 9.931806517013612e-05,
      "loss": 5.5192,
      "step": 10
    },
    {
      "epoch": 0.008505702687028804,
      "grad_norm": 11.631918907165527,
      "learning_rate": 9.901899829374047e-05,
      "loss": 5.0465,
      "step": 11
    },
    {
      "epoch": 0.009278948385849604,
      "grad_norm": 10.389140129089355,
      "learning_rate": 9.86663298624003e-05,
      "loss": 4.9063,
      "step": 12
    },
    {
      "epoch": 0.010052194084670405,
      "grad_norm": 11.703014373779297,
      "learning_rate": 9.826044551386744e-05,
      "loss": 5.2112,
      "step": 13
    },
    {
      "epoch": 0.010825439783491205,
      "grad_norm": 10.6223726272583,
      "learning_rate": 9.780178907671789e-05,
      "loss": 4.7938,
      "step": 14
    },
    {
      "epoch": 0.011598685482312004,
      "grad_norm": 9.967108726501465,
      "learning_rate": 9.729086208503174e-05,
      "loss": 4.8199,
      "step": 15
    },
    {
      "epoch": 0.012371931181132804,
      "grad_norm": 9.973040580749512,
      "learning_rate": 9.672822322997305e-05,
      "loss": 5.1272,
      "step": 16
    },
    {
      "epoch": 0.013145176879953605,
      "grad_norm": 10.061216354370117,
      "learning_rate": 9.611448774886924e-05,
      "loss": 4.5049,
      "step": 17
    },
    {
      "epoch": 0.013918422578774405,
      "grad_norm": 9.44239616394043,
      "learning_rate": 9.545032675245813e-05,
      "loss": 4.7982,
      "step": 18
    },
    {
      "epoch": 0.014691668277595205,
      "grad_norm": 9.862997055053711,
      "learning_rate": 9.473646649103818e-05,
      "loss": 4.9277,
      "step": 19
    },
    {
      "epoch": 0.015464913976416006,
      "grad_norm": 8.347469329833984,
      "learning_rate": 9.397368756032445e-05,
      "loss": 4.4154,
      "step": 20
    },
    {
      "epoch": 0.016238159675236806,
      "grad_norm": 8.445976257324219,
      "learning_rate": 9.316282404787871e-05,
      "loss": 3.718,
      "step": 21
    },
    {
      "epoch": 0.017011405374057608,
      "grad_norm": 9.758785247802734,
      "learning_rate": 9.230476262104677e-05,
      "loss": 4.5808,
      "step": 22
    },
    {
      "epoch": 0.017784651072878407,
      "grad_norm": 11.981024742126465,
      "learning_rate": 9.140044155740101e-05,
      "loss": 6.4283,
      "step": 23
    },
    {
      "epoch": 0.01855789677169921,
      "grad_norm": 12.591474533081055,
      "learning_rate": 9.045084971874738e-05,
      "loss": 5.034,
      "step": 24
    },
    {
      "epoch": 0.019331142470520007,
      "grad_norm": 10.587797164916992,
      "learning_rate": 8.945702546981969e-05,
      "loss": 5.3043,
      "step": 25
    },
    {
      "epoch": 0.019331142470520007,
      "eval_loss": 1.1092556715011597,
      "eval_runtime": 351.8518,
      "eval_samples_per_second": 1.549,
      "eval_steps_per_second": 0.776,
      "step": 25
    },
    {
      "epoch": 0.02010438816934081,
      "grad_norm": 8.1387300491333,
      "learning_rate": 8.842005554284296e-05,
      "loss": 5.3438,
      "step": 26
    },
    {
      "epoch": 0.020877633868161608,
      "grad_norm": 8.583553314208984,
      "learning_rate": 8.73410738492077e-05,
      "loss": 3.7688,
      "step": 27
    },
    {
      "epoch": 0.02165087956698241,
      "grad_norm": 8.653087615966797,
      "learning_rate": 8.622126023955446e-05,
      "loss": 4.184,
      "step": 28
    },
    {
      "epoch": 0.02242412526580321,
      "grad_norm": 9.537445068359375,
      "learning_rate": 8.506183921362443e-05,
      "loss": 3.9987,
      "step": 29
    },
    {
      "epoch": 0.023197370964624008,
      "grad_norm": 10.528961181640625,
      "learning_rate": 8.386407858128706e-05,
      "loss": 5.8944,
      "step": 30
    },
    {
      "epoch": 0.02397061666344481,
      "grad_norm": 11.14555549621582,
      "learning_rate": 8.262928807620843e-05,
      "loss": 4.382,
      "step": 31
    },
    {
      "epoch": 0.02474386236226561,
      "grad_norm": 9.45686149597168,
      "learning_rate": 8.135881792367686e-05,
      "loss": 4.9518,
      "step": 32
    },
    {
      "epoch": 0.02551710806108641,
      "grad_norm": 8.43744945526123,
      "learning_rate": 8.005405736415126e-05,
      "loss": 4.2156,
      "step": 33
    },
    {
      "epoch": 0.02629035375990721,
      "grad_norm": 9.362334251403809,
      "learning_rate": 7.871643313414718e-05,
      "loss": 4.2592,
      "step": 34
    },
    {
      "epoch": 0.02706359945872801,
      "grad_norm": 9.237394332885742,
      "learning_rate": 7.734740790612136e-05,
      "loss": 3.7767,
      "step": 35
    },
    {
      "epoch": 0.02783684515754881,
      "grad_norm": 10.05842399597168,
      "learning_rate": 7.594847868906076e-05,
      "loss": 4.4501,
      "step": 36
    },
    {
      "epoch": 0.028610090856369612,
      "grad_norm": 10.300761222839355,
      "learning_rate": 7.452117519152542e-05,
      "loss": 4.6419,
      "step": 37
    },
    {
      "epoch": 0.02938333655519041,
      "grad_norm": 10.16982650756836,
      "learning_rate": 7.30670581489344e-05,
      "loss": 4.0752,
      "step": 38
    },
    {
      "epoch": 0.030156582254011213,
      "grad_norm": 9.05498218536377,
      "learning_rate": 7.158771761692464e-05,
      "loss": 4.7093,
      "step": 39
    },
    {
      "epoch": 0.03092982795283201,
      "grad_norm": 9.234203338623047,
      "learning_rate": 7.008477123264848e-05,
      "loss": 4.4179,
      "step": 40
    },
    {
      "epoch": 0.03170307365165281,
      "grad_norm": 9.255125999450684,
      "learning_rate": 6.855986244591104e-05,
      "loss": 3.5948,
      "step": 41
    },
    {
      "epoch": 0.03247631935047361,
      "grad_norm": 10.639616012573242,
      "learning_rate": 6.701465872208216e-05,
      "loss": 4.5235,
      "step": 42
    },
    {
      "epoch": 0.03324956504929441,
      "grad_norm": 8.199054718017578,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.7567,
      "step": 43
    },
    {
      "epoch": 0.034022810748115216,
      "grad_norm": 14.720418930053711,
      "learning_rate": 6.387014543809223e-05,
      "loss": 5.8634,
      "step": 44
    },
    {
      "epoch": 0.034796056446936015,
      "grad_norm": 8.992387771606445,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.7691,
      "step": 45
    },
    {
      "epoch": 0.03556930214575681,
      "grad_norm": 13.752641677856445,
      "learning_rate": 6.066498153718735e-05,
      "loss": 4.0749,
      "step": 46
    },
    {
      "epoch": 0.03634254784457761,
      "grad_norm": 9.262603759765625,
      "learning_rate": 5.90440267166055e-05,
      "loss": 3.926,
      "step": 47
    },
    {
      "epoch": 0.03711579354339842,
      "grad_norm": 8.374828338623047,
      "learning_rate": 5.74131823855921e-05,
      "loss": 3.248,
      "step": 48
    },
    {
      "epoch": 0.037889039242219216,
      "grad_norm": 10.220807075500488,
      "learning_rate": 5.577423184847932e-05,
      "loss": 4.066,
      "step": 49
    },
    {
      "epoch": 0.038662284941040015,
      "grad_norm": 13.713523864746094,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 3.6488,
      "step": 50
    },
    {
      "epoch": 0.038662284941040015,
      "eval_loss": 1.0772173404693604,
      "eval_runtime": 351.8904,
      "eval_samples_per_second": 1.549,
      "eval_steps_per_second": 0.776,
      "step": 50
    },
    {
      "epoch": 0.039435530639860814,
      "grad_norm": 10.129049301147461,
      "learning_rate": 5.247918773366112e-05,
      "loss": 4.7483,
      "step": 51
    },
    {
      "epoch": 0.04020877633868162,
      "grad_norm": 8.601277351379395,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 4.5312,
      "step": 52
    },
    {
      "epoch": 0.04098202203750242,
      "grad_norm": 11.301950454711914,
      "learning_rate": 4.917330276168208e-05,
      "loss": 4.7463,
      "step": 53
    },
    {
      "epoch": 0.041755267736323216,
      "grad_norm": 8.8668851852417,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 5.0553,
      "step": 54
    },
    {
      "epoch": 0.042528513435144015,
      "grad_norm": 9.888030052185059,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 4.5142,
      "step": 55
    },
    {
      "epoch": 0.04330175913396482,
      "grad_norm": 9.675687789916992,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 4.6986,
      "step": 56
    },
    {
      "epoch": 0.04407500483278562,
      "grad_norm": 11.324494361877441,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 5.2414,
      "step": 57
    },
    {
      "epoch": 0.04484825053160642,
      "grad_norm": 10.077937126159668,
      "learning_rate": 4.095597328339452e-05,
      "loss": 4.647,
      "step": 58
    },
    {
      "epoch": 0.045621496230427216,
      "grad_norm": 9.43274211883545,
      "learning_rate": 3.933501846281267e-05,
      "loss": 4.5543,
      "step": 59
    },
    {
      "epoch": 0.046394741929248015,
      "grad_norm": 10.41069221496582,
      "learning_rate": 3.772572564296005e-05,
      "loss": 4.8732,
      "step": 60
    },
    {
      "epoch": 0.04716798762806882,
      "grad_norm": 9.759603500366211,
      "learning_rate": 3.612985456190778e-05,
      "loss": 4.7214,
      "step": 61
    },
    {
      "epoch": 0.04794123332688962,
      "grad_norm": 11.823719024658203,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 5.5216,
      "step": 62
    },
    {
      "epoch": 0.04871447902571042,
      "grad_norm": 9.14537239074707,
      "learning_rate": 3.298534127791785e-05,
      "loss": 3.9145,
      "step": 63
    },
    {
      "epoch": 0.04948772472453122,
      "grad_norm": 10.29529094696045,
      "learning_rate": 3.144013755408895e-05,
      "loss": 5.2241,
      "step": 64
    },
    {
      "epoch": 0.05026097042335202,
      "grad_norm": 8.020105361938477,
      "learning_rate": 2.991522876735154e-05,
      "loss": 4.4175,
      "step": 65
    },
    {
      "epoch": 0.05103421612217282,
      "grad_norm": 7.962001323699951,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 3.8547,
      "step": 66
    },
    {
      "epoch": 0.05180746182099362,
      "grad_norm": 7.753868579864502,
      "learning_rate": 2.693294185106562e-05,
      "loss": 3.7267,
      "step": 67
    },
    {
      "epoch": 0.05258070751981442,
      "grad_norm": 8.525618553161621,
      "learning_rate": 2.547882480847461e-05,
      "loss": 4.6899,
      "step": 68
    },
    {
      "epoch": 0.053353953218635224,
      "grad_norm": 8.045459747314453,
      "learning_rate": 2.405152131093926e-05,
      "loss": 4.1387,
      "step": 69
    },
    {
      "epoch": 0.05412719891745602,
      "grad_norm": 7.087581634521484,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 4.1212,
      "step": 70
    },
    {
      "epoch": 0.05490044461627682,
      "grad_norm": 7.834628582000732,
      "learning_rate": 2.128356686585282e-05,
      "loss": 3.7453,
      "step": 71
    },
    {
      "epoch": 0.05567369031509762,
      "grad_norm": 8.538744926452637,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 4.6089,
      "step": 72
    },
    {
      "epoch": 0.056446936013918425,
      "grad_norm": 7.815285682678223,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 3.8365,
      "step": 73
    },
    {
      "epoch": 0.057220181712739224,
      "grad_norm": 7.645932674407959,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 2.5073,
      "step": 74
    },
    {
      "epoch": 0.05799342741156002,
      "grad_norm": 8.115581512451172,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 4.0698,
      "step": 75
    },
    {
      "epoch": 0.05799342741156002,
      "eval_loss": 1.0642553567886353,
      "eval_runtime": 352.0611,
      "eval_samples_per_second": 1.548,
      "eval_steps_per_second": 0.775,
      "step": 75
    },
    {
      "epoch": 0.05876667311038082,
      "grad_norm": 7.514301776885986,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 3.9285,
      "step": 76
    },
    {
      "epoch": 0.05953991880920163,
      "grad_norm": 11.112171173095703,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 4.9558,
      "step": 77
    },
    {
      "epoch": 0.060313164508022425,
      "grad_norm": 7.495338439941406,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 3.9271,
      "step": 78
    },
    {
      "epoch": 0.061086410206843224,
      "grad_norm": 9.140981674194336,
      "learning_rate": 1.157994445715706e-05,
      "loss": 3.571,
      "step": 79
    },
    {
      "epoch": 0.06185965590566402,
      "grad_norm": 9.3052978515625,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 4.5799,
      "step": 80
    },
    {
      "epoch": 0.06263290160448483,
      "grad_norm": 8.143803596496582,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.5652,
      "step": 81
    },
    {
      "epoch": 0.06340614730330563,
      "grad_norm": 10.234214782714844,
      "learning_rate": 8.599558442598998e-06,
      "loss": 4.2623,
      "step": 82
    },
    {
      "epoch": 0.06417939300212643,
      "grad_norm": 8.836921691894531,
      "learning_rate": 7.695237378953223e-06,
      "loss": 3.5661,
      "step": 83
    },
    {
      "epoch": 0.06495263870094722,
      "grad_norm": 10.0997953414917,
      "learning_rate": 6.837175952121306e-06,
      "loss": 4.2513,
      "step": 84
    },
    {
      "epoch": 0.06572588439976802,
      "grad_norm": 9.577383995056152,
      "learning_rate": 6.026312439675552e-06,
      "loss": 4.6833,
      "step": 85
    },
    {
      "epoch": 0.06649913009858882,
      "grad_norm": 10.211189270019531,
      "learning_rate": 5.263533508961827e-06,
      "loss": 4.5139,
      "step": 86
    },
    {
      "epoch": 0.06727237579740963,
      "grad_norm": 9.4320068359375,
      "learning_rate": 4.549673247541875e-06,
      "loss": 4.1881,
      "step": 87
    },
    {
      "epoch": 0.06804562149623043,
      "grad_norm": 9.295085906982422,
      "learning_rate": 3.885512251130763e-06,
      "loss": 4.5596,
      "step": 88
    },
    {
      "epoch": 0.06881886719505123,
      "grad_norm": 7.192505836486816,
      "learning_rate": 3.271776770026963e-06,
      "loss": 3.1656,
      "step": 89
    },
    {
      "epoch": 0.06959211289387203,
      "grad_norm": 8.369428634643555,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 4.5796,
      "step": 90
    },
    {
      "epoch": 0.07036535859269283,
      "grad_norm": 7.142214298248291,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 3.4252,
      "step": 91
    },
    {
      "epoch": 0.07113860429151363,
      "grad_norm": 9.0031099319458,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 4.4111,
      "step": 92
    },
    {
      "epoch": 0.07191184999033443,
      "grad_norm": 8.895259857177734,
      "learning_rate": 1.333670137599713e-06,
      "loss": 3.6634,
      "step": 93
    },
    {
      "epoch": 0.07268509568915522,
      "grad_norm": 8.90333080291748,
      "learning_rate": 9.810017062595322e-07,
      "loss": 4.1098,
      "step": 94
    },
    {
      "epoch": 0.07345834138797602,
      "grad_norm": 10.424738883972168,
      "learning_rate": 6.819348298638839e-07,
      "loss": 4.9226,
      "step": 95
    },
    {
      "epoch": 0.07423158708679684,
      "grad_norm": 10.640342712402344,
      "learning_rate": 4.367965336512403e-07,
      "loss": 4.4209,
      "step": 96
    },
    {
      "epoch": 0.07500483278561763,
      "grad_norm": 11.282198905944824,
      "learning_rate": 2.458548727494292e-07,
      "loss": 4.0654,
      "step": 97
    },
    {
      "epoch": 0.07577807848443843,
      "grad_norm": 9.29175853729248,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 4.4543,
      "step": 98
    },
    {
      "epoch": 0.07655132418325923,
      "grad_norm": 9.734441757202148,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 3.6864,
      "step": 99
    },
    {
      "epoch": 0.07732456988208003,
      "grad_norm": 9.622171401977539,
      "learning_rate": 0.0,
      "loss": 3.4783,
      "step": 100
    },
    {
      "epoch": 0.07732456988208003,
      "eval_loss": 1.06106698513031,
      "eval_runtime": 351.8934,
      "eval_samples_per_second": 1.549,
      "eval_steps_per_second": 0.776,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 1.406258997362688e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}