{
  "best_metric": 0.6681632995605469,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.11302627860977678,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011302627860977678,
      "grad_norm": 793.308837890625,
      "learning_rate": 1e-05,
      "loss": 11.6478,
      "step": 1
    },
    {
      "epoch": 0.0011302627860977678,
      "eval_loss": 3.2303900718688965,
      "eval_runtime": 105.0885,
      "eval_samples_per_second": 14.179,
      "eval_steps_per_second": 3.549,
      "step": 1
    },
    {
      "epoch": 0.0022605255721955355,
      "grad_norm": 1157.48828125,
      "learning_rate": 2e-05,
      "loss": 12.4896,
      "step": 2
    },
    {
      "epoch": 0.003390788358293303,
      "grad_norm": 131.5410919189453,
      "learning_rate": 3e-05,
      "loss": 9.1943,
      "step": 3
    },
    {
      "epoch": 0.004521051144391071,
      "grad_norm": 68.70294952392578,
      "learning_rate": 4e-05,
      "loss": 5.6464,
      "step": 4
    },
    {
      "epoch": 0.005651313930488839,
      "grad_norm": 148.5250244140625,
      "learning_rate": 5e-05,
      "loss": 4.9647,
      "step": 5
    },
    {
      "epoch": 0.006781576716586606,
      "grad_norm": 39.88493728637695,
      "learning_rate": 6e-05,
      "loss": 3.6084,
      "step": 6
    },
    {
      "epoch": 0.007911839502684374,
      "grad_norm": 13.25629711151123,
      "learning_rate": 7e-05,
      "loss": 3.0777,
      "step": 7
    },
    {
      "epoch": 0.009042102288782142,
      "grad_norm": 15.91224193572998,
      "learning_rate": 8e-05,
      "loss": 2.9451,
      "step": 8
    },
    {
      "epoch": 0.010172365074879909,
      "grad_norm": 17.490968704223633,
      "learning_rate": 9e-05,
      "loss": 2.8105,
      "step": 9
    },
    {
      "epoch": 0.011302627860977677,
      "grad_norm": 9.884227752685547,
      "learning_rate": 0.0001,
      "loss": 2.7296,
      "step": 10
    },
    {
      "epoch": 0.012432890647075446,
      "grad_norm": 10.834426879882812,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.697,
      "step": 11
    },
    {
      "epoch": 0.013563153433173212,
      "grad_norm": 40.39820861816406,
      "learning_rate": 9.997266286704631e-05,
      "loss": 3.3782,
      "step": 12
    },
    {
      "epoch": 0.01469341621927098,
      "grad_norm": 10.876916885375977,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.8799,
      "step": 13
    },
    {
      "epoch": 0.015823679005368747,
      "grad_norm": 6.255303382873535,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.7307,
      "step": 14
    },
    {
      "epoch": 0.016953941791466517,
      "grad_norm": 5.4854416847229,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.6597,
      "step": 15
    },
    {
      "epoch": 0.018084204577564284,
      "grad_norm": 8.040909767150879,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.669,
      "step": 16
    },
    {
      "epoch": 0.01921446736366205,
      "grad_norm": 5.405959606170654,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.6124,
      "step": 17
    },
    {
      "epoch": 0.020344730149759818,
      "grad_norm": 6.204880237579346,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.6543,
      "step": 18
    },
    {
      "epoch": 0.021474992935857588,
      "grad_norm": 5.449324607849121,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.7599,
      "step": 19
    },
    {
      "epoch": 0.022605255721955354,
      "grad_norm": 5.886956691741943,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.7869,
      "step": 20
    },
    {
      "epoch": 0.02373551850805312,
      "grad_norm": 4.629397392272949,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.757,
      "step": 21
    },
    {
      "epoch": 0.02486578129415089,
      "grad_norm": 4.251619815826416,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.5278,
      "step": 22
    },
    {
      "epoch": 0.025996044080248658,
      "grad_norm": 5.332093715667725,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.7128,
      "step": 23
    },
    {
      "epoch": 0.027126306866346424,
      "grad_norm": 4.628209590911865,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.6893,
      "step": 24
    },
    {
      "epoch": 0.028256569652444195,
      "grad_norm": 5.050840377807617,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.873,
      "step": 25
    },
    {
      "epoch": 0.02938683243854196,
      "grad_norm": 15.831549644470215,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.764,
      "step": 26
    },
    {
      "epoch": 0.030517095224639728,
      "grad_norm": 5.640730857849121,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.8243,
      "step": 27
    },
    {
      "epoch": 0.031647358010737495,
      "grad_norm": 4.622921943664551,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.8895,
      "step": 28
    },
    {
      "epoch": 0.032777620796835265,
      "grad_norm": 3.4673752784729004,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.6753,
      "step": 29
    },
    {
      "epoch": 0.033907883582933035,
      "grad_norm": 4.400412559509277,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.918,
      "step": 30
    },
    {
      "epoch": 0.0350381463690308,
      "grad_norm": 30.6713809967041,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.8105,
      "step": 31
    },
    {
      "epoch": 0.03616840915512857,
      "grad_norm": 4.252901077270508,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.8125,
      "step": 32
    },
    {
      "epoch": 0.03729867194122634,
      "grad_norm": 4.446712970733643,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.7987,
      "step": 33
    },
    {
      "epoch": 0.0384289347273241,
      "grad_norm": 4.5988688468933105,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.8463,
      "step": 34
    },
    {
      "epoch": 0.03955919751342187,
      "grad_norm": 3.57090163230896,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.8395,
      "step": 35
    },
    {
      "epoch": 0.040689460299519635,
      "grad_norm": 5.003127574920654,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.8054,
      "step": 36
    },
    {
      "epoch": 0.041819723085617405,
      "grad_norm": 4.430306911468506,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.9095,
      "step": 37
    },
    {
      "epoch": 0.042949985871715175,
      "grad_norm": 3.776151180267334,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.7794,
      "step": 38
    },
    {
      "epoch": 0.04408024865781294,
      "grad_norm": 4.0163373947143555,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.8656,
      "step": 39
    },
    {
      "epoch": 0.04521051144391071,
      "grad_norm": 3.8399384021759033,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.8012,
      "step": 40
    },
    {
      "epoch": 0.04634077423000848,
      "grad_norm": 3.859337568283081,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.9344,
      "step": 41
    },
    {
      "epoch": 0.04747103701610624,
      "grad_norm": 3.8300116062164307,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.8931,
      "step": 42
    },
    {
      "epoch": 0.04860129980220401,
      "grad_norm": 3.786048412322998,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.8088,
      "step": 43
    },
    {
      "epoch": 0.04973156258830178,
      "grad_norm": 3.4179418087005615,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.8516,
      "step": 44
    },
    {
      "epoch": 0.050861825374399545,
      "grad_norm": 3.5727052688598633,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.7993,
      "step": 45
    },
    {
      "epoch": 0.051992088160497316,
      "grad_norm": 3.7449238300323486,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.1631,
      "step": 46
    },
    {
      "epoch": 0.053122350946595086,
      "grad_norm": 3.2603912353515625,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.8704,
      "step": 47
    },
    {
      "epoch": 0.05425261373269285,
      "grad_norm": 2.6630172729492188,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6844,
      "step": 48
    },
    {
      "epoch": 0.05538287651879062,
      "grad_norm": 3.6026859283447266,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.0858,
      "step": 49
    },
    {
      "epoch": 0.05651313930488839,
      "grad_norm": 3.2763783931732178,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.8216,
      "step": 50
    },
    {
      "epoch": 0.05651313930488839,
      "eval_loss": 0.6686553955078125,
      "eval_runtime": 106.943,
      "eval_samples_per_second": 13.933,
      "eval_steps_per_second": 3.488,
      "step": 50
    },
    {
      "epoch": 0.05764340209098615,
      "grad_norm": 7.047059535980225,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.3943,
      "step": 51
    },
    {
      "epoch": 0.05877366487708392,
      "grad_norm": 3.35186767578125,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.1352,
      "step": 52
    },
    {
      "epoch": 0.05990392766318169,
      "grad_norm": 3.5137863159179688,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.2424,
      "step": 53
    },
    {
      "epoch": 0.061034190449279456,
      "grad_norm": 3.1273257732391357,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.1845,
      "step": 54
    },
    {
      "epoch": 0.062164453235377226,
      "grad_norm": 3.170482635498047,
      "learning_rate": 8.678619553365659e-05,
      "loss": 2.2313,
      "step": 55
    },
    {
      "epoch": 0.06329471602147499,
      "grad_norm": 2.9466161727905273,
      "learning_rate": 8.622126023955446e-05,
      "loss": 2.2675,
      "step": 56
    },
    {
      "epoch": 0.06442497880757277,
      "grad_norm": 3.1644484996795654,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.277,
      "step": 57
    },
    {
      "epoch": 0.06555524159367053,
      "grad_norm": 2.9599294662475586,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.2118,
      "step": 58
    },
    {
      "epoch": 0.06668550437976829,
      "grad_norm": 4.45035982131958,
      "learning_rate": 8.44676704559283e-05,
      "loss": 2.45,
      "step": 59
    },
    {
      "epoch": 0.06781576716586607,
      "grad_norm": 3.307894468307495,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.4022,
      "step": 60
    },
    {
      "epoch": 0.06894602995196383,
      "grad_norm": 3.315178155899048,
      "learning_rate": 8.32512286056924e-05,
      "loss": 2.3148,
      "step": 61
    },
    {
      "epoch": 0.0700762927380616,
      "grad_norm": 3.3259332180023193,
      "learning_rate": 8.262928807620843e-05,
      "loss": 2.3667,
      "step": 62
    },
    {
      "epoch": 0.07120655552415937,
      "grad_norm": 3.088707208633423,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.2734,
      "step": 63
    },
    {
      "epoch": 0.07233681831025714,
      "grad_norm": 4.132589340209961,
      "learning_rate": 8.135881792367686e-05,
      "loss": 2.4403,
      "step": 64
    },
    {
      "epoch": 0.0734670810963549,
      "grad_norm": 4.20663595199585,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.4266,
      "step": 65
    },
    {
      "epoch": 0.07459734388245268,
      "grad_norm": 3.900576114654541,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.4775,
      "step": 66
    },
    {
      "epoch": 0.07572760666855044,
      "grad_norm": 3.7162678241729736,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.4847,
      "step": 67
    },
    {
      "epoch": 0.0768578694546482,
      "grad_norm": 3.464790105819702,
      "learning_rate": 7.871643313414718e-05,
      "loss": 2.3735,
      "step": 68
    },
    {
      "epoch": 0.07798813224074597,
      "grad_norm": 3.6781411170959473,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.4899,
      "step": 69
    },
    {
      "epoch": 0.07911839502684374,
      "grad_norm": 3.7448372840881348,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.4988,
      "step": 70
    },
    {
      "epoch": 0.0802486578129415,
      "grad_norm": 3.722891330718994,
      "learning_rate": 7.66515864363997e-05,
      "loss": 2.5031,
      "step": 71
    },
    {
      "epoch": 0.08137892059903927,
      "grad_norm": 3.3679347038269043,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.4905,
      "step": 72
    },
    {
      "epoch": 0.08250918338513705,
      "grad_norm": 3.2018232345581055,
      "learning_rate": 7.52382768867422e-05,
      "loss": 2.5374,
      "step": 73
    },
    {
      "epoch": 0.08363944617123481,
      "grad_norm": 4.144588470458984,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.5555,
      "step": 74
    },
    {
      "epoch": 0.08476970895733257,
      "grad_norm": 3.0146422386169434,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.5006,
      "step": 75
    },
    {
      "epoch": 0.08589997174343035,
      "grad_norm": 3.384679079055786,
      "learning_rate": 7.30670581489344e-05,
      "loss": 2.6001,
      "step": 76
    },
    {
      "epoch": 0.08703023452952811,
      "grad_norm": 3.17840576171875,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.5854,
      "step": 77
    },
    {
      "epoch": 0.08816049731562588,
      "grad_norm": 3.397296905517578,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.5631,
      "step": 78
    },
    {
      "epoch": 0.08929076010172365,
      "grad_norm": 3.4653842449188232,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.6416,
      "step": 79
    },
    {
      "epoch": 0.09042102288782142,
      "grad_norm": 3.1254074573516846,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.5894,
      "step": 80
    },
    {
      "epoch": 0.09155128567391918,
      "grad_norm": 3.4320321083068848,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.68,
      "step": 81
    },
    {
      "epoch": 0.09268154846001696,
      "grad_norm": 3.4371142387390137,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.544,
      "step": 82
    },
    {
      "epoch": 0.09381181124611472,
      "grad_norm": 3.5839908123016357,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.7267,
      "step": 83
    },
    {
      "epoch": 0.09494207403221248,
      "grad_norm": 3.330444097518921,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.6227,
      "step": 84
    },
    {
      "epoch": 0.09607233681831026,
      "grad_norm": 3.0069053173065186,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.6964,
      "step": 85
    },
    {
      "epoch": 0.09720259960440802,
      "grad_norm": 3.130023956298828,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.7333,
      "step": 86
    },
    {
      "epoch": 0.09833286239050579,
      "grad_norm": 3.0710136890411377,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.6722,
      "step": 87
    },
    {
      "epoch": 0.09946312517660356,
      "grad_norm": 2.988614320755005,
      "learning_rate": 6.387014543809223e-05,
      "loss": 2.5794,
      "step": 88
    },
    {
      "epoch": 0.10059338796270133,
      "grad_norm": 3.1522057056427,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.6536,
      "step": 89
    },
    {
      "epoch": 0.10172365074879909,
      "grad_norm": 3.2672934532165527,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.6735,
      "step": 90
    },
    {
      "epoch": 0.10285391353489687,
      "grad_norm": 3.3788697719573975,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.6591,
      "step": 91
    },
    {
      "epoch": 0.10398417632099463,
      "grad_norm": 4.3577046394348145,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.6826,
      "step": 92
    },
    {
      "epoch": 0.1051144391070924,
      "grad_norm": 3.8894002437591553,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.7146,
      "step": 93
    },
    {
      "epoch": 0.10624470189319017,
      "grad_norm": 3.9112329483032227,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.4512,
      "step": 94
    },
    {
      "epoch": 0.10737496467928793,
      "grad_norm": 3.968187093734741,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.336,
      "step": 95
    },
    {
      "epoch": 0.1085052274653857,
      "grad_norm": 3.755615234375,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.8332,
      "step": 96
    },
    {
      "epoch": 0.10963549025148348,
      "grad_norm": 3.6911725997924805,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.0493,
      "step": 97
    },
    {
      "epoch": 0.11076575303758124,
      "grad_norm": 4.834873199462891,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.0833,
      "step": 98
    },
    {
      "epoch": 0.111896015823679,
      "grad_norm": 3.7316572666168213,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.7376,
      "step": 99
    },
    {
      "epoch": 0.11302627860977678,
      "grad_norm": 3.422861099243164,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.6723,
      "step": 100
    },
    {
      "epoch": 0.11302627860977678,
      "eval_loss": 0.6681632995605469,
      "eval_runtime": 106.9564,
      "eval_samples_per_second": 13.931,
      "eval_steps_per_second": 3.487,
      "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": 1.431616484278272e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}