{
  "best_metric": 0.8465943932533264,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.031203682034480068,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003120368203448007,
      "grad_norm": 9.957253456115723,
      "learning_rate": 1e-05,
      "loss": 2.6627,
      "step": 1
    },
    {
      "epoch": 0.0003120368203448007,
      "eval_loss": 2.7949066162109375,
      "eval_runtime": 575.1453,
      "eval_samples_per_second": 9.385,
      "eval_steps_per_second": 2.347,
      "step": 1
    },
    {
      "epoch": 0.0006240736406896014,
      "grad_norm": 11.108814239501953,
      "learning_rate": 2e-05,
      "loss": 2.6689,
      "step": 2
    },
    {
      "epoch": 0.000936110461034402,
      "grad_norm": 10.682526588439941,
      "learning_rate": 3e-05,
      "loss": 2.4337,
      "step": 3
    },
    {
      "epoch": 0.0012481472813792027,
      "grad_norm": 7.091076374053955,
      "learning_rate": 4e-05,
      "loss": 1.7918,
      "step": 4
    },
    {
      "epoch": 0.0015601841017240034,
      "grad_norm": 3.724902391433716,
      "learning_rate": 5e-05,
      "loss": 1.3859,
      "step": 5
    },
    {
      "epoch": 0.001872220922068804,
      "grad_norm": 2.5286026000976562,
      "learning_rate": 6e-05,
      "loss": 1.1309,
      "step": 6
    },
    {
      "epoch": 0.0021842577424136048,
      "grad_norm": 2.7851521968841553,
      "learning_rate": 7e-05,
      "loss": 1.1048,
      "step": 7
    },
    {
      "epoch": 0.0024962945627584054,
      "grad_norm": 1.8212271928787231,
      "learning_rate": 8e-05,
      "loss": 0.8491,
      "step": 8
    },
    {
      "epoch": 0.002808331383103206,
      "grad_norm": 1.6948728561401367,
      "learning_rate": 9e-05,
      "loss": 0.928,
      "step": 9
    },
    {
      "epoch": 0.003120368203448007,
      "grad_norm": 1.5595484972000122,
      "learning_rate": 0.0001,
      "loss": 0.8576,
      "step": 10
    },
    {
      "epoch": 0.0034324050237928075,
      "grad_norm": 1.3692195415496826,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8588,
      "step": 11
    },
    {
      "epoch": 0.003744441844137608,
      "grad_norm": 1.4032466411590576,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7998,
      "step": 12
    },
    {
      "epoch": 0.004056478664482409,
      "grad_norm": 1.3274507522583008,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8097,
      "step": 13
    },
    {
      "epoch": 0.0043685154848272095,
      "grad_norm": 1.175102710723877,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7696,
      "step": 14
    },
    {
      "epoch": 0.00468055230517201,
      "grad_norm": 1.281258225440979,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8471,
      "step": 15
    },
    {
      "epoch": 0.004992589125516811,
      "grad_norm": 1.2209652662277222,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.8182,
      "step": 16
    },
    {
      "epoch": 0.005304625945861612,
      "grad_norm": 1.277958869934082,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.7592,
      "step": 17
    },
    {
      "epoch": 0.005616662766206412,
      "grad_norm": 1.2684087753295898,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8921,
      "step": 18
    },
    {
      "epoch": 0.005928699586551213,
      "grad_norm": 2.5076284408569336,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7431,
      "step": 19
    },
    {
      "epoch": 0.006240736406896014,
      "grad_norm": 1.1840873956680298,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8956,
      "step": 20
    },
    {
      "epoch": 0.006552773227240814,
      "grad_norm": 1.0883880853652954,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7756,
      "step": 21
    },
    {
      "epoch": 0.006864810047585615,
      "grad_norm": 1.2152539491653442,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8632,
      "step": 22
    },
    {
      "epoch": 0.007176846867930416,
      "grad_norm": 1.468305230140686,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7961,
      "step": 23
    },
    {
      "epoch": 0.007488883688275216,
      "grad_norm": 1.2167303562164307,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7196,
      "step": 24
    },
    {
      "epoch": 0.007800920508620017,
      "grad_norm": 1.2322477102279663,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7526,
      "step": 25
    },
    {
      "epoch": 0.008112957328964818,
      "grad_norm": 1.1364251375198364,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7615,
      "step": 26
    },
    {
      "epoch": 0.008424994149309618,
      "grad_norm": 1.0931193828582764,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7886,
      "step": 27
    },
    {
      "epoch": 0.008737030969654419,
      "grad_norm": 1.1731034517288208,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7239,
      "step": 28
    },
    {
      "epoch": 0.00904906778999922,
      "grad_norm": 1.1136339902877808,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8517,
      "step": 29
    },
    {
      "epoch": 0.00936110461034402,
      "grad_norm": 1.1435471773147583,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.8485,
      "step": 30
    },
    {
      "epoch": 0.009673141430688821,
      "grad_norm": 1.1177922487258911,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8377,
      "step": 31
    },
    {
      "epoch": 0.009985178251033622,
      "grad_norm": 1.0039643049240112,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.8118,
      "step": 32
    },
    {
      "epoch": 0.010297215071378422,
      "grad_norm": 0.9791098833084106,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8896,
      "step": 33
    },
    {
      "epoch": 0.010609251891723223,
      "grad_norm": 0.9517635107040405,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8058,
      "step": 34
    },
    {
      "epoch": 0.010921288712068024,
      "grad_norm": 1.0164357423782349,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8149,
      "step": 35
    },
    {
      "epoch": 0.011233325532412824,
      "grad_norm": 0.9662339091300964,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8988,
      "step": 36
    },
    {
      "epoch": 0.011545362352757625,
      "grad_norm": 0.9611389636993408,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.766,
      "step": 37
    },
    {
      "epoch": 0.011857399173102426,
      "grad_norm": 1.1109344959259033,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.9435,
      "step": 38
    },
    {
      "epoch": 0.012169435993447227,
      "grad_norm": 1.1274558305740356,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9347,
      "step": 39
    },
    {
      "epoch": 0.012481472813792027,
      "grad_norm": 1.0689157247543335,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8265,
      "step": 40
    },
    {
      "epoch": 0.012793509634136828,
      "grad_norm": 1.0937086343765259,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8571,
      "step": 41
    },
    {
      "epoch": 0.013105546454481629,
      "grad_norm": 1.0644176006317139,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7975,
      "step": 42
    },
    {
      "epoch": 0.01341758327482643,
      "grad_norm": 1.2639864683151245,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.9379,
      "step": 43
    },
    {
      "epoch": 0.01372962009517123,
      "grad_norm": 2.6970744132995605,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.5578,
      "step": 44
    },
    {
      "epoch": 0.01404165691551603,
      "grad_norm": 2.194770574569702,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.682,
      "step": 45
    },
    {
      "epoch": 0.014353693735860831,
      "grad_norm": 1.9200794696807861,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.7524,
      "step": 46
    },
    {
      "epoch": 0.014665730556205632,
      "grad_norm": 1.6025694608688354,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.6386,
      "step": 47
    },
    {
      "epoch": 0.014977767376550433,
      "grad_norm": 1.3628052473068237,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6543,
      "step": 48
    },
    {
      "epoch": 0.015289804196895233,
      "grad_norm": 1.1497654914855957,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.4452,
      "step": 49
    },
    {
      "epoch": 0.015601841017240034,
      "grad_norm": 1.199021816253662,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.6019,
      "step": 50
    },
    {
      "epoch": 0.015601841017240034,
      "eval_loss": 0.963438868522644,
      "eval_runtime": 576.2596,
      "eval_samples_per_second": 9.367,
      "eval_steps_per_second": 2.343,
      "step": 50
    },
    {
      "epoch": 0.015913877837584835,
      "grad_norm": 1.680629014968872,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.9826,
      "step": 51
    },
    {
      "epoch": 0.016225914657929635,
      "grad_norm": 1.1629451513290405,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.8711,
      "step": 52
    },
    {
      "epoch": 0.016537951478274436,
      "grad_norm": 0.999272346496582,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.9047,
      "step": 53
    },
    {
      "epoch": 0.016849988298619237,
      "grad_norm": 1.0136737823486328,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7953,
      "step": 54
    },
    {
      "epoch": 0.017162025118964037,
      "grad_norm": 0.951803982257843,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6757,
      "step": 55
    },
    {
      "epoch": 0.017474061939308838,
      "grad_norm": 1.0217398405075073,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.822,
      "step": 56
    },
    {
      "epoch": 0.01778609875965364,
      "grad_norm": 0.9405883550643921,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7946,
      "step": 57
    },
    {
      "epoch": 0.01809813557999844,
      "grad_norm": 0.9246597290039062,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7408,
      "step": 58
    },
    {
      "epoch": 0.01841017240034324,
      "grad_norm": 1.0739665031433105,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8104,
      "step": 59
    },
    {
      "epoch": 0.01872220922068804,
      "grad_norm": 1.036548376083374,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.7561,
      "step": 60
    },
    {
      "epoch": 0.01903424604103284,
      "grad_norm": 0.9185912013053894,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7367,
      "step": 61
    },
    {
      "epoch": 0.019346282861377642,
      "grad_norm": 0.9082395434379578,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8553,
      "step": 62
    },
    {
      "epoch": 0.019658319681722443,
      "grad_norm": 0.9209671020507812,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7051,
      "step": 63
    },
    {
      "epoch": 0.019970356502067244,
      "grad_norm": 0.8518406748771667,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6811,
      "step": 64
    },
    {
      "epoch": 0.020282393322412044,
      "grad_norm": 0.8296268582344055,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.6696,
      "step": 65
    },
    {
      "epoch": 0.020594430142756845,
      "grad_norm": 0.8943758606910706,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6595,
      "step": 66
    },
    {
      "epoch": 0.020906466963101646,
      "grad_norm": 0.9089400172233582,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8329,
      "step": 67
    },
    {
      "epoch": 0.021218503783446446,
      "grad_norm": 0.9639408588409424,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7802,
      "step": 68
    },
    {
      "epoch": 0.021530540603791247,
      "grad_norm": 0.9582761526107788,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7514,
      "step": 69
    },
    {
      "epoch": 0.021842577424136048,
      "grad_norm": 0.8935718536376953,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7832,
      "step": 70
    },
    {
      "epoch": 0.02215461424448085,
      "grad_norm": 0.8567960262298584,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7493,
      "step": 71
    },
    {
      "epoch": 0.02246665106482565,
      "grad_norm": 0.9141445755958557,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.8103,
      "step": 72
    },
    {
      "epoch": 0.02277868788517045,
      "grad_norm": 0.8256440162658691,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7201,
      "step": 73
    },
    {
      "epoch": 0.02309072470551525,
      "grad_norm": 0.9923111796379089,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7621,
      "step": 74
    },
    {
      "epoch": 0.02340276152586005,
      "grad_norm": 0.8481928706169128,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.8073,
      "step": 75
    },
    {
      "epoch": 0.02371479834620485,
      "grad_norm": 0.882407546043396,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7526,
      "step": 76
    },
    {
      "epoch": 0.024026835166549652,
      "grad_norm": 0.8140597939491272,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6825,
      "step": 77
    },
    {
      "epoch": 0.024338871986894453,
      "grad_norm": 0.8657062649726868,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7353,
      "step": 78
    },
    {
      "epoch": 0.024650908807239254,
      "grad_norm": 0.8869200944900513,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7921,
      "step": 79
    },
    {
      "epoch": 0.024962945627584054,
      "grad_norm": 0.9941065311431885,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.8222,
      "step": 80
    },
    {
      "epoch": 0.025274982447928855,
      "grad_norm": 0.9149479269981384,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7853,
      "step": 81
    },
    {
      "epoch": 0.025587019268273656,
      "grad_norm": 0.9197757244110107,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7227,
      "step": 82
    },
    {
      "epoch": 0.025899056088618456,
      "grad_norm": 0.9976024031639099,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8561,
      "step": 83
    },
    {
      "epoch": 0.026211092908963257,
      "grad_norm": 0.8757933974266052,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7793,
      "step": 84
    },
    {
      "epoch": 0.026523129729308058,
      "grad_norm": 1.0709153413772583,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.8835,
      "step": 85
    },
    {
      "epoch": 0.02683516654965286,
      "grad_norm": 0.8737066388130188,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8136,
      "step": 86
    },
    {
      "epoch": 0.02714720336999766,
      "grad_norm": 0.9159258604049683,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.9143,
      "step": 87
    },
    {
      "epoch": 0.02745924019034246,
      "grad_norm": 0.9400917887687683,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.8458,
      "step": 88
    },
    {
      "epoch": 0.02777127701068726,
      "grad_norm": 0.8912694454193115,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7847,
      "step": 89
    },
    {
      "epoch": 0.02808331383103206,
      "grad_norm": 0.8344074487686157,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7255,
      "step": 90
    },
    {
      "epoch": 0.028395350651376862,
      "grad_norm": 0.9551566243171692,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7822,
      "step": 91
    },
    {
      "epoch": 0.028707387471721663,
      "grad_norm": 0.8455932140350342,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7324,
      "step": 92
    },
    {
      "epoch": 0.029019424292066463,
      "grad_norm": 0.7846436500549316,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7129,
      "step": 93
    },
    {
      "epoch": 0.029331461112411264,
      "grad_norm": 1.35532546043396,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.2972,
      "step": 94
    },
    {
      "epoch": 0.029643497932756065,
      "grad_norm": 1.1400768756866455,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.112,
      "step": 95
    },
    {
      "epoch": 0.029955534753100865,
      "grad_norm": 1.5415581464767456,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.441,
      "step": 96
    },
    {
      "epoch": 0.030267571573445666,
      "grad_norm": 1.1367700099945068,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.3925,
      "step": 97
    },
    {
      "epoch": 0.030579608393790467,
      "grad_norm": 0.9753825664520264,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.5174,
      "step": 98
    },
    {
      "epoch": 0.030891645214135267,
      "grad_norm": 0.905869722366333,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.334,
      "step": 99
    },
    {
      "epoch": 0.031203682034480068,
      "grad_norm": 0.930263876914978,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.4637,
      "step": 100
    },
    {
      "epoch": 0.031203682034480068,
      "eval_loss": 0.8465943932533264,
      "eval_runtime": 576.3777,
      "eval_samples_per_second": 9.365,
      "eval_steps_per_second": 2.342,
      "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": 1.679086225195008e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}