{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.3784295175023652,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003784295175023652,
      "grad_norm": 0.00011392086162231863,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.003784295175023652,
      "eval_loss": 11.5,
      "eval_runtime": 1.99,
      "eval_samples_per_second": 223.614,
      "eval_steps_per_second": 56.28,
      "step": 1
    },
    {
      "epoch": 0.007568590350047304,
      "grad_norm": 0.00011392626765882596,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.011352885525070956,
      "grad_norm": 9.126810618909076e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.015137180700094607,
      "grad_norm": 0.00012079317093594,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.01892147587511826,
      "grad_norm": 0.00013068151019979268,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.02270577105014191,
      "grad_norm": 0.00013781298184767365,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.026490066225165563,
      "grad_norm": 0.00011931403423659503,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.030274361400189215,
      "grad_norm": 7.444625225616619e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.03405865657521287,
      "grad_norm": 9.970557584892958e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.03784295175023652,
      "grad_norm": 0.00011921407713089138,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.041627246925260174,
      "grad_norm": 0.00015253745368681848,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.04541154210028382,
      "grad_norm": 0.00014556266251020133,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.04919583727530748,
      "grad_norm": 0.00014760822523385286,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.052980132450331126,
      "grad_norm": 0.00011346988321747631,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.05676442762535478,
      "grad_norm": 0.00017548487812746316,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.06054872280037843,
      "grad_norm": 0.00017099750402849168,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.06433301797540208,
      "grad_norm": 0.00018018046102952212,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.06811731315042574,
      "grad_norm": 0.00019239389803260565,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.07190160832544938,
      "grad_norm": 0.00023869199503678828,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.07568590350047304,
      "grad_norm": 0.00018224233645014465,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.07947019867549669,
      "grad_norm": 0.0001689050259301439,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.08325449385052035,
      "grad_norm": 0.0002421535609755665,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.08703878902554399,
      "grad_norm": 0.00020825379760935903,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.09082308420056764,
      "grad_norm": 0.0002500048722140491,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.0946073793755913,
      "grad_norm": 0.000246277340920642,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.09839167455061495,
      "grad_norm": 0.00019197013170924038,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.1021759697256386,
      "grad_norm": 0.0002337003534194082,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.10596026490066225,
      "grad_norm": 0.000294659985229373,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.1097445600756859,
      "grad_norm": 0.00020803308871109039,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.11352885525070956,
      "grad_norm": 0.00033990509109571576,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.1173131504257332,
      "grad_norm": 0.00024411026970483363,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.12109744560075686,
      "grad_norm": 0.0003257458156440407,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.12488174077578051,
      "grad_norm": 0.0003640092327259481,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.12866603595080417,
      "grad_norm": 0.0003347630554344505,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.13245033112582782,
      "grad_norm": 0.0002442197874188423,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.13623462630085148,
      "grad_norm": 0.0003589051484595984,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.1400189214758751,
      "grad_norm": 0.00033283705124631524,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.14380321665089876,
      "grad_norm": 0.0002927516179624945,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.14758751182592242,
      "grad_norm": 0.00028098642360419035,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.15137180700094607,
      "grad_norm": 0.00034260371467098594,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.15515610217596973,
      "grad_norm": 0.00041411619167774916,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.15894039735099338,
      "grad_norm": 0.000367051106877625,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.16272469252601704,
      "grad_norm": 0.00041485161636956036,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.1665089877010407,
      "grad_norm": 0.00043028229265473783,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.17029328287606432,
      "grad_norm": 0.00033999388688243926,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.17407757805108798,
      "grad_norm": 0.00034981509088538587,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.17786187322611163,
      "grad_norm": 0.00041490880539640784,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.1816461684011353,
      "grad_norm": 0.0004471220017876476,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.18543046357615894,
      "grad_norm": 0.00047907637781463563,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.1892147587511826,
      "grad_norm": 0.00046024954644963145,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.1892147587511826,
      "eval_loss": 11.5,
      "eval_runtime": 2.1802,
      "eval_samples_per_second": 204.113,
      "eval_steps_per_second": 51.372,
      "step": 50
    },
    {
      "epoch": 0.19299905392620625,
      "grad_norm": 0.0004713274829555303,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.1967833491012299,
      "grad_norm": 0.0004975659539923072,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.20056764427625354,
      "grad_norm": 0.0004585021233651787,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.2043519394512772,
      "grad_norm": 0.0004932769224978983,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.20813623462630085,
      "grad_norm": 0.0005532164941541851,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.2119205298013245,
      "grad_norm": 0.0006865657051093876,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.21570482497634816,
      "grad_norm": 0.000607673660852015,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.2194891201513718,
      "grad_norm": 0.0004795949498657137,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.22327341532639547,
      "grad_norm": 0.0004354627162683755,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.22705771050141912,
      "grad_norm": 0.00038716112612746656,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.23084200567644275,
      "grad_norm": 0.0005533443763852119,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.2346263008514664,
      "grad_norm": 0.0006522368639707565,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.23841059602649006,
      "grad_norm": 0.000798935885541141,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.24219489120151372,
      "grad_norm": 0.000743313052225858,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.24597918637653737,
      "grad_norm": 0.0006881129229441285,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.24976348155156103,
      "grad_norm": 0.0007528004352934659,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.2535477767265847,
      "grad_norm": 0.0008783751400187612,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.25733207190160834,
      "grad_norm": 0.0008143247105181217,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.261116367076632,
      "grad_norm": 0.0007597034564241767,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.26490066225165565,
      "grad_norm": 0.0007723828312009573,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.2686849574266793,
      "grad_norm": 0.0007239784463308752,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.27246925260170296,
      "grad_norm": 0.0007658087415620685,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.27625354777672656,
      "grad_norm": 0.000722269993275404,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.2800378429517502,
      "grad_norm": 0.0006466319900937378,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.28382213812677387,
      "grad_norm": 0.0009249902796000242,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.2876064333017975,
      "grad_norm": 0.00094453408382833,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.2913907284768212,
      "grad_norm": 0.0008264336502179503,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.29517502365184484,
      "grad_norm": 0.0007132226601243019,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.2989593188268685,
      "grad_norm": 0.0007830658578313887,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.30274361400189215,
      "grad_norm": 0.0007697652326896787,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.3065279091769158,
      "grad_norm": 0.0007296271505765617,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.31031220435193946,
      "grad_norm": 0.000670959590934217,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.3140964995269631,
      "grad_norm": 0.0007570139714516699,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.31788079470198677,
      "grad_norm": 0.0008836815250106156,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.3216650898770104,
      "grad_norm": 0.0005664569907821715,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.3254493850520341,
      "grad_norm": 0.0007803346961736679,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.32923368022705773,
      "grad_norm": 0.0007202856941148639,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.3330179754020814,
      "grad_norm": 0.0007384041673503816,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.336802270577105,
      "grad_norm": 0.0007600896060466766,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.34058656575212864,
      "grad_norm": 0.000748415186535567,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.3443708609271523,
      "grad_norm": 0.000808786484412849,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.34815515610217596,
      "grad_norm": 0.0007418069872073829,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.3519394512771996,
      "grad_norm": 0.0009046116610988975,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.35572374645222327,
      "grad_norm": 0.000740163610316813,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.3595080416272469,
      "grad_norm": 0.00096157006919384,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.3632923368022706,
      "grad_norm": 0.000863321649376303,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.36707663197729423,
      "grad_norm": 0.0008699059835635126,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.3708609271523179,
      "grad_norm": 0.0009290840243920684,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.37464522232734154,
      "grad_norm": 0.000926476321183145,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.3784295175023652,
      "grad_norm": 0.001019977848045528,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.3784295175023652,
      "eval_loss": 11.5,
      "eval_runtime": 1.9856,
      "eval_samples_per_second": 224.114,
      "eval_steps_per_second": 56.406,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 16079231385600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}