{
  "best_metric": 0.36422646045684814,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.38559107052257735,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004058853373921867,
      "grad_norm": 0.5062510967254639,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.3693,
      "step": 1
    },
    {
      "epoch": 0.004058853373921867,
      "eval_loss": 0.8792099952697754,
      "eval_runtime": 3.4344,
      "eval_samples_per_second": 14.559,
      "eval_steps_per_second": 3.785,
      "step": 1
    },
    {
      "epoch": 0.008117706747843734,
      "grad_norm": 0.9184481501579285,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.5743,
      "step": 2
    },
    {
      "epoch": 0.0121765601217656,
      "grad_norm": 0.9887821674346924,
      "learning_rate": 0.0001,
      "loss": 0.6198,
      "step": 3
    },
    {
      "epoch": 0.016235413495687467,
      "grad_norm": 0.7524212598800659,
      "learning_rate": 9.997376600647783e-05,
      "loss": 0.5442,
      "step": 4
    },
    {
      "epoch": 0.020294266869609334,
      "grad_norm": 0.6812997460365295,
      "learning_rate": 9.989509461357426e-05,
      "loss": 0.4661,
      "step": 5
    },
    {
      "epoch": 0.0243531202435312,
      "grad_norm": 0.5500982403755188,
      "learning_rate": 9.976407754861426e-05,
      "loss": 0.4792,
      "step": 6
    },
    {
      "epoch": 0.028411973617453068,
      "grad_norm": 0.48947757482528687,
      "learning_rate": 9.958086757163489e-05,
      "loss": 0.4932,
      "step": 7
    },
    {
      "epoch": 0.032470826991374935,
      "grad_norm": 0.4276084303855896,
      "learning_rate": 9.934567829727386e-05,
      "loss": 0.4636,
      "step": 8
    },
    {
      "epoch": 0.0365296803652968,
      "grad_norm": 0.3858795464038849,
      "learning_rate": 9.905878394570453e-05,
      "loss": 0.442,
      "step": 9
    },
    {
      "epoch": 0.04058853373921867,
      "grad_norm": 0.37294769287109375,
      "learning_rate": 9.872051902290737e-05,
      "loss": 0.4651,
      "step": 10
    },
    {
      "epoch": 0.044647387113140535,
      "grad_norm": 0.41522446274757385,
      "learning_rate": 9.833127793065098e-05,
      "loss": 0.4742,
      "step": 11
    },
    {
      "epoch": 0.0487062404870624,
      "grad_norm": 0.40490609407424927,
      "learning_rate": 9.789151450663723e-05,
      "loss": 0.4696,
      "step": 12
    },
    {
      "epoch": 0.05276509386098427,
      "grad_norm": 0.15065628290176392,
      "learning_rate": 9.740174149534693e-05,
      "loss": 0.1888,
      "step": 13
    },
    {
      "epoch": 0.056823947234906136,
      "grad_norm": 0.3047502934932709,
      "learning_rate": 9.686252995020249e-05,
      "loss": 0.3328,
      "step": 14
    },
    {
      "epoch": 0.060882800608828,
      "grad_norm": 0.2834240198135376,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.3549,
      "step": 15
    },
    {
      "epoch": 0.06494165398274987,
      "grad_norm": 0.2397720217704773,
      "learning_rate": 9.563836295460398e-05,
      "loss": 0.3516,
      "step": 16
    },
    {
      "epoch": 0.06900050735667174,
      "grad_norm": 0.2353983372449875,
      "learning_rate": 9.495483482810688e-05,
      "loss": 0.402,
      "step": 17
    },
    {
      "epoch": 0.0730593607305936,
      "grad_norm": 0.264461487531662,
      "learning_rate": 9.422472115147382e-05,
      "loss": 0.4114,
      "step": 18
    },
    {
      "epoch": 0.07711821410451547,
      "grad_norm": 0.3238242268562317,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.4244,
      "step": 19
    },
    {
      "epoch": 0.08117706747843734,
      "grad_norm": 0.33132946491241455,
      "learning_rate": 9.2628195591462e-05,
      "loss": 0.4197,
      "step": 20
    },
    {
      "epoch": 0.0852359208523592,
      "grad_norm": 0.31999894976615906,
      "learning_rate": 9.176364518546989e-05,
      "loss": 0.4201,
      "step": 21
    },
    {
      "epoch": 0.08929477422628107,
      "grad_norm": 0.27462199330329895,
      "learning_rate": 9.08562300137157e-05,
      "loss": 0.4323,
      "step": 22
    },
    {
      "epoch": 0.09335362760020294,
      "grad_norm": 0.28106844425201416,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.4207,
      "step": 23
    },
    {
      "epoch": 0.0974124809741248,
      "grad_norm": 0.3135908246040344,
      "learning_rate": 8.891708613973126e-05,
      "loss": 0.4172,
      "step": 24
    },
    {
      "epoch": 0.10147133434804667,
      "grad_norm": 0.39373230934143066,
      "learning_rate": 8.788761839251559e-05,
      "loss": 0.4293,
      "step": 25
    },
    {
      "epoch": 0.10147133434804667,
      "eval_loss": 0.4003879129886627,
      "eval_runtime": 3.4909,
      "eval_samples_per_second": 14.323,
      "eval_steps_per_second": 3.724,
      "step": 25
    },
    {
      "epoch": 0.10553018772196854,
      "grad_norm": 0.2560587227344513,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.2327,
      "step": 26
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.45607316493988037,
      "learning_rate": 8.571489144483944e-05,
      "loss": 0.3487,
      "step": 27
    },
    {
      "epoch": 0.11364789446981227,
      "grad_norm": 0.3606185019016266,
      "learning_rate": 8.457416554680877e-05,
      "loss": 0.3752,
      "step": 28
    },
    {
      "epoch": 0.11770674784373414,
      "grad_norm": 0.2905651330947876,
      "learning_rate": 8.339895749467238e-05,
      "loss": 0.3514,
      "step": 29
    },
    {
      "epoch": 0.121765601217656,
      "grad_norm": 0.23107478022575378,
      "learning_rate": 8.219063752844926e-05,
      "loss": 0.3738,
      "step": 30
    },
    {
      "epoch": 0.12582445459157787,
      "grad_norm": 0.1988050937652588,
      "learning_rate": 8.095061449516903e-05,
      "loss": 0.3693,
      "step": 31
    },
    {
      "epoch": 0.12988330796549974,
      "grad_norm": 0.2333528846502304,
      "learning_rate": 7.968033420621935e-05,
      "loss": 0.3971,
      "step": 32
    },
    {
      "epoch": 0.1339421613394216,
      "grad_norm": 0.3175937235355377,
      "learning_rate": 7.838127775159452e-05,
      "loss": 0.3949,
      "step": 33
    },
    {
      "epoch": 0.13800101471334347,
      "grad_norm": 0.3904169201850891,
      "learning_rate": 7.705495977301078e-05,
      "loss": 0.4436,
      "step": 34
    },
    {
      "epoch": 0.14205986808726534,
      "grad_norm": 0.3506806194782257,
      "learning_rate": 7.570292669790186e-05,
      "loss": 0.4193,
      "step": 35
    },
    {
      "epoch": 0.1461187214611872,
      "grad_norm": 0.33251529932022095,
      "learning_rate": 7.43267549363537e-05,
      "loss": 0.4313,
      "step": 36
    },
    {
      "epoch": 0.15017757483510907,
      "grad_norm": 0.3682462275028229,
      "learning_rate": 7.292804904308087e-05,
      "loss": 0.4288,
      "step": 37
    },
    {
      "epoch": 0.15423642820903094,
      "grad_norm": 0.11894040554761887,
      "learning_rate": 7.150843984658754e-05,
      "loss": 0.1897,
      "step": 38
    },
    {
      "epoch": 0.1582952815829528,
      "grad_norm": 0.19390328228473663,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.3119,
      "step": 39
    },
    {
      "epoch": 0.16235413495687467,
      "grad_norm": 0.24307291209697723,
      "learning_rate": 6.861315478964841e-05,
      "loss": 0.345,
      "step": 40
    },
    {
      "epoch": 0.16641298833079654,
      "grad_norm": 0.2972720265388489,
      "learning_rate": 6.714085470206609e-05,
      "loss": 0.3694,
      "step": 41
    },
    {
      "epoch": 0.1704718417047184,
      "grad_norm": 0.2774950861930847,
      "learning_rate": 6.56543989209901e-05,
      "loss": 0.3787,
      "step": 42
    },
    {
      "epoch": 0.17453069507864027,
      "grad_norm": 0.24689042568206787,
      "learning_rate": 6.415552058736854e-05,
      "loss": 0.3736,
      "step": 43
    },
    {
      "epoch": 0.17858954845256214,
      "grad_norm": 0.2081252783536911,
      "learning_rate": 6.264596732629e-05,
      "loss": 0.3739,
      "step": 44
    },
    {
      "epoch": 0.182648401826484,
      "grad_norm": 0.2078096568584442,
      "learning_rate": 6.112749920933111e-05,
      "loss": 0.3723,
      "step": 45
    },
    {
      "epoch": 0.18670725520040587,
      "grad_norm": 0.20248815417289734,
      "learning_rate": 5.960188670239154e-05,
      "loss": 0.3964,
      "step": 46
    },
    {
      "epoch": 0.19076610857432774,
      "grad_norm": 0.2449951171875,
      "learning_rate": 5.80709086014102e-05,
      "loss": 0.4352,
      "step": 47
    },
    {
      "epoch": 0.1948249619482496,
      "grad_norm": 0.2900124490261078,
      "learning_rate": 5.653634995836856e-05,
      "loss": 0.429,
      "step": 48
    },
    {
      "epoch": 0.19888381532217148,
      "grad_norm": 0.3739871680736542,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.4275,
      "step": 49
    },
    {
      "epoch": 0.20294266869609334,
      "grad_norm": 0.4056133031845093,
      "learning_rate": 5.346365004163145e-05,
      "loss": 0.4132,
      "step": 50
    },
    {
      "epoch": 0.20294266869609334,
      "eval_loss": 0.3687722384929657,
      "eval_runtime": 3.499,
      "eval_samples_per_second": 14.29,
      "eval_steps_per_second": 3.715,
      "step": 50
    },
    {
      "epoch": 0.2070015220700152,
      "grad_norm": 0.07692764699459076,
      "learning_rate": 5.192909139858981e-05,
      "loss": 0.1729,
      "step": 51
    },
    {
      "epoch": 0.21106037544393708,
      "grad_norm": 0.1375497430562973,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 0.3147,
      "step": 52
    },
    {
      "epoch": 0.21511922881785894,
      "grad_norm": 0.1671007126569748,
      "learning_rate": 4.887250079066892e-05,
      "loss": 0.3289,
      "step": 53
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.1718771904706955,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 0.3449,
      "step": 54
    },
    {
      "epoch": 0.22323693556570268,
      "grad_norm": 0.20011144876480103,
      "learning_rate": 4.584447941263149e-05,
      "loss": 0.3742,
      "step": 55
    },
    {
      "epoch": 0.22729578893962454,
      "grad_norm": 0.18110662698745728,
      "learning_rate": 4.43456010790099e-05,
      "loss": 0.4061,
      "step": 56
    },
    {
      "epoch": 0.2313546423135464,
      "grad_norm": 0.20814234018325806,
      "learning_rate": 4.285914529793391e-05,
      "loss": 0.3747,
      "step": 57
    },
    {
      "epoch": 0.23541349568746828,
      "grad_norm": 0.19282929599285126,
      "learning_rate": 4.13868452103516e-05,
      "loss": 0.3778,
      "step": 58
    },
    {
      "epoch": 0.23947234906139014,
      "grad_norm": 0.21799100935459137,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 0.3985,
      "step": 59
    },
    {
      "epoch": 0.243531202435312,
      "grad_norm": 0.21902616322040558,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 0.3939,
      "step": 60
    },
    {
      "epoch": 0.24759005580923388,
      "grad_norm": 0.2695430815219879,
      "learning_rate": 3.707195095691913e-05,
      "loss": 0.3985,
      "step": 61
    },
    {
      "epoch": 0.25164890918315574,
      "grad_norm": 0.28181904554367065,
      "learning_rate": 3.567324506364632e-05,
      "loss": 0.3966,
      "step": 62
    },
    {
      "epoch": 0.2557077625570776,
      "grad_norm": 0.09019971638917923,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 0.1922,
      "step": 63
    },
    {
      "epoch": 0.2597666159309995,
      "grad_norm": 0.13326597213745117,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 0.3133,
      "step": 64
    },
    {
      "epoch": 0.26382546930492135,
      "grad_norm": 0.16596747934818268,
      "learning_rate": 3.16187222484055e-05,
      "loss": 0.3314,
      "step": 65
    },
    {
      "epoch": 0.2678843226788432,
      "grad_norm": 0.19934867322444916,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 0.335,
      "step": 66
    },
    {
      "epoch": 0.2719431760527651,
      "grad_norm": 0.17301230132579803,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 0.3333,
      "step": 67
    },
    {
      "epoch": 0.27600202942668695,
      "grad_norm": 0.18114101886749268,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 0.3575,
      "step": 68
    },
    {
      "epoch": 0.2800608828006088,
      "grad_norm": 0.17812739312648773,
      "learning_rate": 2.660104250532764e-05,
      "loss": 0.3595,
      "step": 69
    },
    {
      "epoch": 0.2841197361745307,
      "grad_norm": 0.18535548448562622,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 0.3873,
      "step": 70
    },
    {
      "epoch": 0.28817858954845255,
      "grad_norm": 0.20128794014453888,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 0.3631,
      "step": 71
    },
    {
      "epoch": 0.2922374429223744,
      "grad_norm": 0.21520088613033295,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.3809,
      "step": 72
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.2530140280723572,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 0.4191,
      "step": 73
    },
    {
      "epoch": 0.30035514967021815,
      "grad_norm": 0.2900885343551636,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 0.4096,
      "step": 74
    },
    {
      "epoch": 0.30441400304414,
      "grad_norm": 0.37200847268104553,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 0.3949,
      "step": 75
    },
    {
      "epoch": 0.30441400304414,
      "eval_loss": 0.36422646045684814,
      "eval_runtime": 3.5086,
      "eval_samples_per_second": 14.251,
      "eval_steps_per_second": 3.705,
      "step": 75
    },
    {
      "epoch": 0.3084728564180619,
      "grad_norm": 0.09115864336490631,
      "learning_rate": 1.91437699862843e-05,
      "loss": 0.2235,
      "step": 76
    },
    {
      "epoch": 0.31253170979198375,
      "grad_norm": 0.1393779069185257,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 0.3149,
      "step": 77
    },
    {
      "epoch": 0.3165905631659056,
      "grad_norm": 0.14699040353298187,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 0.3251,
      "step": 78
    },
    {
      "epoch": 0.3206494165398275,
      "grad_norm": 0.1531774252653122,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 0.3349,
      "step": 79
    },
    {
      "epoch": 0.32470826991374935,
      "grad_norm": 0.1625107377767563,
      "learning_rate": 1.577527884852619e-05,
      "loss": 0.3474,
      "step": 80
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 0.1845567524433136,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 0.3567,
      "step": 81
    },
    {
      "epoch": 0.3328259766615931,
      "grad_norm": 0.18067772686481476,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 0.3791,
      "step": 82
    },
    {
      "epoch": 0.33688483003551495,
      "grad_norm": 0.20357079803943634,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 0.3848,
      "step": 83
    },
    {
      "epoch": 0.3409436834094368,
      "grad_norm": 0.20797663927078247,
      "learning_rate": 1.313747004979751e-05,
      "loss": 0.3734,
      "step": 84
    },
    {
      "epoch": 0.3450025367833587,
      "grad_norm": 0.23876087367534637,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 0.4123,
      "step": 85
    },
    {
      "epoch": 0.34906139015728055,
      "grad_norm": 0.2859575152397156,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 0.4115,
      "step": 86
    },
    {
      "epoch": 0.3531202435312024,
      "grad_norm": 0.3142327666282654,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 0.3819,
      "step": 87
    },
    {
      "epoch": 0.3571790969051243,
      "grad_norm": 0.10286320745944977,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 0.179,
      "step": 88
    },
    {
      "epoch": 0.36123795027904615,
      "grad_norm": 0.1432906836271286,
      "learning_rate": 1.094121605429547e-05,
      "loss": 0.3092,
      "step": 89
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 0.15591755509376526,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 0.3168,
      "step": 90
    },
    {
      "epoch": 0.3693556570268899,
      "grad_norm": 0.16477596759796143,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 0.3352,
      "step": 91
    },
    {
      "epoch": 0.37341451040081175,
      "grad_norm": 0.16704893112182617,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 0.3432,
      "step": 92
    },
    {
      "epoch": 0.3774733637747336,
      "grad_norm": 0.1805972009897232,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 0.3548,
      "step": 93
    },
    {
      "epoch": 0.3815322171486555,
      "grad_norm": 0.1912754327058792,
      "learning_rate": 1.002623399352217e-05,
      "loss": 0.3728,
      "step": 94
    },
    {
      "epoch": 0.38559107052257735,
      "grad_norm": 0.1889467090368271,
      "learning_rate": 1e-05,
      "loss": 0.3875,
      "step": 95
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "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": 1.1352414048768492e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}