{
  "best_metric": 0.409039705991745,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.16611295681063123,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016611295681063123,
      "grad_norm": 1.2991793155670166,
      "learning_rate": 1e-05,
      "loss": 0.6513,
      "step": 1
    },
    {
      "epoch": 0.0016611295681063123,
      "eval_loss": 0.8317100405693054,
      "eval_runtime": 132.9593,
      "eval_samples_per_second": 7.626,
      "eval_steps_per_second": 1.91,
      "step": 1
    },
    {
      "epoch": 0.0033222591362126247,
      "grad_norm": 1.2579532861709595,
      "learning_rate": 2e-05,
      "loss": 0.6749,
      "step": 2
    },
    {
      "epoch": 0.0049833887043189366,
      "grad_norm": 1.0699290037155151,
      "learning_rate": 3e-05,
      "loss": 0.6399,
      "step": 3
    },
    {
      "epoch": 0.006644518272425249,
      "grad_norm": 0.7915657162666321,
      "learning_rate": 4e-05,
      "loss": 0.6214,
      "step": 4
    },
    {
      "epoch": 0.008305647840531562,
      "grad_norm": 0.5864650011062622,
      "learning_rate": 5e-05,
      "loss": 0.5893,
      "step": 5
    },
    {
      "epoch": 0.009966777408637873,
      "grad_norm": 0.4930439591407776,
      "learning_rate": 6e-05,
      "loss": 0.5539,
      "step": 6
    },
    {
      "epoch": 0.011627906976744186,
      "grad_norm": 0.8789781928062439,
      "learning_rate": 7e-05,
      "loss": 0.5859,
      "step": 7
    },
    {
      "epoch": 0.013289036544850499,
      "grad_norm": 0.6858446598052979,
      "learning_rate": 8e-05,
      "loss": 0.5161,
      "step": 8
    },
    {
      "epoch": 0.014950166112956811,
      "grad_norm": 0.4820753037929535,
      "learning_rate": 9e-05,
      "loss": 0.4945,
      "step": 9
    },
    {
      "epoch": 0.016611295681063124,
      "grad_norm": 0.35846245288848877,
      "learning_rate": 0.0001,
      "loss": 0.4702,
      "step": 10
    },
    {
      "epoch": 0.018272425249169437,
      "grad_norm": 0.3399806022644043,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.4192,
      "step": 11
    },
    {
      "epoch": 0.019933554817275746,
      "grad_norm": 0.32994091510772705,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.4455,
      "step": 12
    },
    {
      "epoch": 0.02159468438538206,
      "grad_norm": 0.2916202247142792,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.4491,
      "step": 13
    },
    {
      "epoch": 0.023255813953488372,
      "grad_norm": 0.2513728439807892,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4192,
      "step": 14
    },
    {
      "epoch": 0.024916943521594685,
      "grad_norm": 0.20601803064346313,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4135,
      "step": 15
    },
    {
      "epoch": 0.026578073089700997,
      "grad_norm": 0.20515939593315125,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4149,
      "step": 16
    },
    {
      "epoch": 0.02823920265780731,
      "grad_norm": 0.24935221672058105,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.4144,
      "step": 17
    },
    {
      "epoch": 0.029900332225913623,
      "grad_norm": 0.22809065878391266,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.4117,
      "step": 18
    },
    {
      "epoch": 0.03156146179401993,
      "grad_norm": 0.2064090371131897,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.3975,
      "step": 19
    },
    {
      "epoch": 0.03322259136212625,
      "grad_norm": 0.20076528191566467,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.3937,
      "step": 20
    },
    {
      "epoch": 0.03488372093023256,
      "grad_norm": 0.20907463133335114,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.3936,
      "step": 21
    },
    {
      "epoch": 0.036544850498338874,
      "grad_norm": 0.20472639799118042,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.3875,
      "step": 22
    },
    {
      "epoch": 0.03820598006644518,
      "grad_norm": 0.17747552692890167,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.3996,
      "step": 23
    },
    {
      "epoch": 0.03986710963455149,
      "grad_norm": 0.18577048182487488,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.4622,
      "step": 24
    },
    {
      "epoch": 0.04152823920265781,
      "grad_norm": 0.18465018272399902,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4465,
      "step": 25
    },
    {
      "epoch": 0.04318936877076412,
      "grad_norm": 0.36926233768463135,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.6891,
      "step": 26
    },
    {
      "epoch": 0.044850498338870434,
      "grad_norm": 0.3326234817504883,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.6926,
      "step": 27
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 0.24597014486789703,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6492,
      "step": 28
    },
    {
      "epoch": 0.04817275747508306,
      "grad_norm": 0.22998689115047455,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6338,
      "step": 29
    },
    {
      "epoch": 0.04983388704318937,
      "grad_norm": 0.2597779631614685,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.6451,
      "step": 30
    },
    {
      "epoch": 0.05149501661129568,
      "grad_norm": 0.30236122012138367,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.622,
      "step": 31
    },
    {
      "epoch": 0.053156146179401995,
      "grad_norm": 0.2684450149536133,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6151,
      "step": 32
    },
    {
      "epoch": 0.054817275747508304,
      "grad_norm": 0.25038909912109375,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.593,
      "step": 33
    },
    {
      "epoch": 0.05647840531561462,
      "grad_norm": 0.25587284564971924,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5875,
      "step": 34
    },
    {
      "epoch": 0.05813953488372093,
      "grad_norm": 0.19960953295230865,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5488,
      "step": 35
    },
    {
      "epoch": 0.059800664451827246,
      "grad_norm": 0.19124135375022888,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.5632,
      "step": 36
    },
    {
      "epoch": 0.061461794019933555,
      "grad_norm": 0.1789243221282959,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.5588,
      "step": 37
    },
    {
      "epoch": 0.06312292358803986,
      "grad_norm": 0.17890439927577972,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.5598,
      "step": 38
    },
    {
      "epoch": 0.06478405315614617,
      "grad_norm": 0.1927339732646942,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.5882,
      "step": 39
    },
    {
      "epoch": 0.0664451827242525,
      "grad_norm": 0.20116066932678223,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.5741,
      "step": 40
    },
    {
      "epoch": 0.0681063122923588,
      "grad_norm": 0.17227494716644287,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.5436,
      "step": 41
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 0.18728812038898468,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.5824,
      "step": 42
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.1641688197851181,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.5773,
      "step": 43
    },
    {
      "epoch": 0.07308970099667775,
      "grad_norm": 0.16669844090938568,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.5692,
      "step": 44
    },
    {
      "epoch": 0.07475083056478406,
      "grad_norm": 0.16173191368579865,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.5706,
      "step": 45
    },
    {
      "epoch": 0.07641196013289037,
      "grad_norm": 0.16865822672843933,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.5794,
      "step": 46
    },
    {
      "epoch": 0.07807308970099668,
      "grad_norm": 0.1681707352399826,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.5831,
      "step": 47
    },
    {
      "epoch": 0.07973421926910298,
      "grad_norm": 0.18740896880626678,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.5991,
      "step": 48
    },
    {
      "epoch": 0.08139534883720931,
      "grad_norm": 0.18814262747764587,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6662,
      "step": 49
    },
    {
      "epoch": 0.08305647840531562,
      "grad_norm": 0.24064107239246368,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7061,
      "step": 50
    },
    {
      "epoch": 0.08305647840531562,
      "eval_loss": 0.45007362961769104,
      "eval_runtime": 134.6502,
      "eval_samples_per_second": 7.531,
      "eval_steps_per_second": 1.886,
      "step": 50
    },
    {
      "epoch": 0.08471760797342193,
      "grad_norm": 0.18804551661014557,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.3224,
      "step": 51
    },
    {
      "epoch": 0.08637873754152824,
      "grad_norm": 0.16869483888149261,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.3237,
      "step": 52
    },
    {
      "epoch": 0.08803986710963455,
      "grad_norm": 0.16511651873588562,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.353,
      "step": 53
    },
    {
      "epoch": 0.08970099667774087,
      "grad_norm": 0.1492200344800949,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.3538,
      "step": 54
    },
    {
      "epoch": 0.09136212624584718,
      "grad_norm": 0.13702312111854553,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.3423,
      "step": 55
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 0.14534348249435425,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.331,
      "step": 56
    },
    {
      "epoch": 0.0946843853820598,
      "grad_norm": 0.1291942298412323,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.3115,
      "step": 57
    },
    {
      "epoch": 0.09634551495016612,
      "grad_norm": 0.13093352317810059,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3066,
      "step": 58
    },
    {
      "epoch": 0.09800664451827243,
      "grad_norm": 0.1452917754650116,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.3485,
      "step": 59
    },
    {
      "epoch": 0.09966777408637874,
      "grad_norm": 0.13886800408363342,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3127,
      "step": 60
    },
    {
      "epoch": 0.10132890365448505,
      "grad_norm": 0.14664413034915924,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.3349,
      "step": 61
    },
    {
      "epoch": 0.10299003322259136,
      "grad_norm": 0.13130126893520355,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.3031,
      "step": 62
    },
    {
      "epoch": 0.10465116279069768,
      "grad_norm": 0.13619501888751984,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.3359,
      "step": 63
    },
    {
      "epoch": 0.10631229235880399,
      "grad_norm": 0.14423972368240356,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.3169,
      "step": 64
    },
    {
      "epoch": 0.1079734219269103,
      "grad_norm": 0.13670726120471954,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.3358,
      "step": 65
    },
    {
      "epoch": 0.10963455149501661,
      "grad_norm": 0.13185586035251617,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.3096,
      "step": 66
    },
    {
      "epoch": 0.11129568106312292,
      "grad_norm": 0.13396374881267548,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3091,
      "step": 67
    },
    {
      "epoch": 0.11295681063122924,
      "grad_norm": 0.1417226344347,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.3102,
      "step": 68
    },
    {
      "epoch": 0.11461794019933555,
      "grad_norm": 0.1466892659664154,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3403,
      "step": 69
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 0.1433144360780716,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.324,
      "step": 70
    },
    {
      "epoch": 0.11794019933554817,
      "grad_norm": 0.1436891257762909,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.3434,
      "step": 71
    },
    {
      "epoch": 0.11960132890365449,
      "grad_norm": 0.15285548567771912,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.3344,
      "step": 72
    },
    {
      "epoch": 0.1212624584717608,
      "grad_norm": 0.14362435042858124,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.3191,
      "step": 73
    },
    {
      "epoch": 0.12292358803986711,
      "grad_norm": 0.15305458009243011,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.3776,
      "step": 74
    },
    {
      "epoch": 0.12458471760797342,
      "grad_norm": 0.1848021298646927,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4502,
      "step": 75
    },
    {
      "epoch": 0.12624584717607973,
      "grad_norm": 0.18864738941192627,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5257,
      "step": 76
    },
    {
      "epoch": 0.12790697674418605,
      "grad_norm": 0.16458578407764435,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.526,
      "step": 77
    },
    {
      "epoch": 0.12956810631229235,
      "grad_norm": 0.14648108184337616,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.5084,
      "step": 78
    },
    {
      "epoch": 0.13122923588039867,
      "grad_norm": 0.13501055538654327,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.4777,
      "step": 79
    },
    {
      "epoch": 0.132890365448505,
      "grad_norm": 0.15276943147182465,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.5236,
      "step": 80
    },
    {
      "epoch": 0.1345514950166113,
      "grad_norm": 0.1511184722185135,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.5364,
      "step": 81
    },
    {
      "epoch": 0.1362126245847176,
      "grad_norm": 0.14624027907848358,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.5027,
      "step": 82
    },
    {
      "epoch": 0.1378737541528239,
      "grad_norm": 0.13957354426383972,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.4793,
      "step": 83
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.13981389999389648,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.4919,
      "step": 84
    },
    {
      "epoch": 0.14119601328903655,
      "grad_norm": 0.15372055768966675,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.5226,
      "step": 85
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.1438971310853958,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5232,
      "step": 86
    },
    {
      "epoch": 0.14451827242524917,
      "grad_norm": 0.1383737474679947,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.5007,
      "step": 87
    },
    {
      "epoch": 0.1461794019933555,
      "grad_norm": 0.14018723368644714,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.5328,
      "step": 88
    },
    {
      "epoch": 0.1478405315614618,
      "grad_norm": 0.1336921900510788,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.5123,
      "step": 89
    },
    {
      "epoch": 0.14950166112956811,
      "grad_norm": 0.14490532875061035,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.4996,
      "step": 90
    },
    {
      "epoch": 0.1511627906976744,
      "grad_norm": 0.14218592643737793,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.5103,
      "step": 91
    },
    {
      "epoch": 0.15282392026578073,
      "grad_norm": 0.13371700048446655,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.4695,
      "step": 92
    },
    {
      "epoch": 0.15448504983388706,
      "grad_norm": 0.14268216490745544,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4996,
      "step": 93
    },
    {
      "epoch": 0.15614617940199335,
      "grad_norm": 0.15761351585388184,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.5142,
      "step": 94
    },
    {
      "epoch": 0.15780730897009967,
      "grad_norm": 0.14862477779388428,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.4953,
      "step": 95
    },
    {
      "epoch": 0.15946843853820597,
      "grad_norm": 0.15104886889457703,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5656,
      "step": 96
    },
    {
      "epoch": 0.1611295681063123,
      "grad_norm": 0.1583997756242752,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.538,
      "step": 97
    },
    {
      "epoch": 0.16279069767441862,
      "grad_norm": 0.16727805137634277,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5618,
      "step": 98
    },
    {
      "epoch": 0.1644518272425249,
      "grad_norm": 0.18140842020511627,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.5916,
      "step": 99
    },
    {
      "epoch": 0.16611295681063123,
      "grad_norm": 0.2026122659444809,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.677,
      "step": 100
    },
    {
      "epoch": 0.16611295681063123,
      "eval_loss": 0.409039705991745,
      "eval_runtime": 134.7555,
      "eval_samples_per_second": 7.525,
      "eval_steps_per_second": 1.885,
      "step": 100
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.46948355375104e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}