{
  "best_metric": 10.12276840209961,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.0784698381559588,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008259982963785137,
      "grad_norm": 1.8529645204544067,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.4083,
      "step": 1
    },
    {
      "epoch": 0.0008259982963785137,
      "eval_loss": 10.408509254455566,
      "eval_runtime": 0.0799,
      "eval_samples_per_second": 626.139,
      "eval_steps_per_second": 162.796,
      "step": 1
    },
    {
      "epoch": 0.0016519965927570275,
      "grad_norm": 1.9922393560409546,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.4113,
      "step": 2
    },
    {
      "epoch": 0.002477994889135541,
      "grad_norm": 1.9800035953521729,
      "learning_rate": 0.0001,
      "loss": 10.4098,
      "step": 3
    },
    {
      "epoch": 0.003303993185514055,
      "grad_norm": 2.011288642883301,
      "learning_rate": 9.997376600647783e-05,
      "loss": 10.4051,
      "step": 4
    },
    {
      "epoch": 0.004129991481892569,
      "grad_norm": 2.104647636413574,
      "learning_rate": 9.989509461357426e-05,
      "loss": 10.3894,
      "step": 5
    },
    {
      "epoch": 0.004955989778271082,
      "grad_norm": 2.0105316638946533,
      "learning_rate": 9.976407754861426e-05,
      "loss": 10.3932,
      "step": 6
    },
    {
      "epoch": 0.0057819880746495965,
      "grad_norm": 1.978432297706604,
      "learning_rate": 9.958086757163489e-05,
      "loss": 10.3872,
      "step": 7
    },
    {
      "epoch": 0.00660798637102811,
      "grad_norm": 2.0279252529144287,
      "learning_rate": 9.934567829727386e-05,
      "loss": 10.3743,
      "step": 8
    },
    {
      "epoch": 0.007433984667406623,
      "grad_norm": 1.9801558256149292,
      "learning_rate": 9.905878394570453e-05,
      "loss": 10.3722,
      "step": 9
    },
    {
      "epoch": 0.008259982963785138,
      "grad_norm": 2.0980846881866455,
      "learning_rate": 9.872051902290737e-05,
      "loss": 10.3572,
      "step": 10
    },
    {
      "epoch": 0.009085981260163651,
      "grad_norm": 2.0367014408111572,
      "learning_rate": 9.833127793065098e-05,
      "loss": 10.3547,
      "step": 11
    },
    {
      "epoch": 0.009911979556542164,
      "grad_norm": 2.1126158237457275,
      "learning_rate": 9.789151450663723e-05,
      "loss": 10.3405,
      "step": 12
    },
    {
      "epoch": 0.010737977852920678,
      "grad_norm": 1.8768205642700195,
      "learning_rate": 9.740174149534693e-05,
      "loss": 10.3356,
      "step": 13
    },
    {
      "epoch": 0.011563976149299193,
      "grad_norm": 2.0427446365356445,
      "learning_rate": 9.686252995020249e-05,
      "loss": 10.3318,
      "step": 14
    },
    {
      "epoch": 0.012389974445677706,
      "grad_norm": 2.027947425842285,
      "learning_rate": 9.627450856774539e-05,
      "loss": 10.3323,
      "step": 15
    },
    {
      "epoch": 0.01321597274205622,
      "grad_norm": 2.088620185852051,
      "learning_rate": 9.563836295460398e-05,
      "loss": 10.3158,
      "step": 16
    },
    {
      "epoch": 0.014041971038434733,
      "grad_norm": 2.0752029418945312,
      "learning_rate": 9.495483482810688e-05,
      "loss": 10.3053,
      "step": 17
    },
    {
      "epoch": 0.014867969334813247,
      "grad_norm": 1.991979956626892,
      "learning_rate": 9.422472115147382e-05,
      "loss": 10.3076,
      "step": 18
    },
    {
      "epoch": 0.01569396763119176,
      "grad_norm": 1.952653169631958,
      "learning_rate": 9.3448873204592e-05,
      "loss": 10.2969,
      "step": 19
    },
    {
      "epoch": 0.016519965927570275,
      "grad_norm": 1.9945733547210693,
      "learning_rate": 9.2628195591462e-05,
      "loss": 10.2861,
      "step": 20
    },
    {
      "epoch": 0.01734596422394879,
      "grad_norm": 1.918555498123169,
      "learning_rate": 9.176364518546989e-05,
      "loss": 10.287,
      "step": 21
    },
    {
      "epoch": 0.018171962520327302,
      "grad_norm": 1.90217125415802,
      "learning_rate": 9.08562300137157e-05,
      "loss": 10.2761,
      "step": 22
    },
    {
      "epoch": 0.018997960816705815,
      "grad_norm": 1.8743098974227905,
      "learning_rate": 8.990700808169889e-05,
      "loss": 10.2719,
      "step": 23
    },
    {
      "epoch": 0.01982395911308433,
      "grad_norm": 1.8643437623977661,
      "learning_rate": 8.891708613973126e-05,
      "loss": 10.2475,
      "step": 24
    },
    {
      "epoch": 0.020649957409462842,
      "grad_norm": 1.8139985799789429,
      "learning_rate": 8.788761839251559e-05,
      "loss": 10.2605,
      "step": 25
    },
    {
      "epoch": 0.020649957409462842,
      "eval_loss": 10.234816551208496,
      "eval_runtime": 0.08,
      "eval_samples_per_second": 625.12,
      "eval_steps_per_second": 162.531,
      "step": 25
    },
    {
      "epoch": 0.021475955705841356,
      "grad_norm": 1.7132413387298584,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.2417,
      "step": 26
    },
    {
      "epoch": 0.02230195400221987,
      "grad_norm": 1.7616883516311646,
      "learning_rate": 8.571489144483944e-05,
      "loss": 10.2424,
      "step": 27
    },
    {
      "epoch": 0.023127952298598386,
      "grad_norm": 1.7035174369812012,
      "learning_rate": 8.457416554680877e-05,
      "loss": 10.2336,
      "step": 28
    },
    {
      "epoch": 0.0239539505949769,
      "grad_norm": 1.6459009647369385,
      "learning_rate": 8.339895749467238e-05,
      "loss": 10.2207,
      "step": 29
    },
    {
      "epoch": 0.024779948891355413,
      "grad_norm": 1.6194607019424438,
      "learning_rate": 8.219063752844926e-05,
      "loss": 10.215,
      "step": 30
    },
    {
      "epoch": 0.025605947187733926,
      "grad_norm": 1.582850456237793,
      "learning_rate": 8.095061449516903e-05,
      "loss": 10.2174,
      "step": 31
    },
    {
      "epoch": 0.02643194548411244,
      "grad_norm": 1.5164111852645874,
      "learning_rate": 7.968033420621935e-05,
      "loss": 10.2114,
      "step": 32
    },
    {
      "epoch": 0.027257943780490953,
      "grad_norm": 1.5401805639266968,
      "learning_rate": 7.838127775159452e-05,
      "loss": 10.2216,
      "step": 33
    },
    {
      "epoch": 0.028083942076869466,
      "grad_norm": 1.4308018684387207,
      "learning_rate": 7.705495977301078e-05,
      "loss": 10.2051,
      "step": 34
    },
    {
      "epoch": 0.02890994037324798,
      "grad_norm": 1.4240089654922485,
      "learning_rate": 7.570292669790186e-05,
      "loss": 10.2089,
      "step": 35
    },
    {
      "epoch": 0.029735938669626493,
      "grad_norm": 1.3456974029541016,
      "learning_rate": 7.43267549363537e-05,
      "loss": 10.1928,
      "step": 36
    },
    {
      "epoch": 0.030561936966005007,
      "grad_norm": 1.3179231882095337,
      "learning_rate": 7.292804904308087e-05,
      "loss": 10.1926,
      "step": 37
    },
    {
      "epoch": 0.03138793526238352,
      "grad_norm": 1.191386103630066,
      "learning_rate": 7.150843984658754e-05,
      "loss": 10.2057,
      "step": 38
    },
    {
      "epoch": 0.03221393355876204,
      "grad_norm": 1.2104068994522095,
      "learning_rate": 7.006958254769438e-05,
      "loss": 10.1858,
      "step": 39
    },
    {
      "epoch": 0.03303993185514055,
      "grad_norm": 1.17447030544281,
      "learning_rate": 6.861315478964841e-05,
      "loss": 10.1709,
      "step": 40
    },
    {
      "epoch": 0.033865930151519064,
      "grad_norm": 1.1405586004257202,
      "learning_rate": 6.714085470206609e-05,
      "loss": 10.1776,
      "step": 41
    },
    {
      "epoch": 0.03469192844789758,
      "grad_norm": 1.1019338369369507,
      "learning_rate": 6.56543989209901e-05,
      "loss": 10.1702,
      "step": 42
    },
    {
      "epoch": 0.03551792674427609,
      "grad_norm": 1.048142910003662,
      "learning_rate": 6.415552058736854e-05,
      "loss": 10.1706,
      "step": 43
    },
    {
      "epoch": 0.036343925040654604,
      "grad_norm": 1.0173368453979492,
      "learning_rate": 6.264596732629e-05,
      "loss": 10.1657,
      "step": 44
    },
    {
      "epoch": 0.03716992333703312,
      "grad_norm": 1.0117427110671997,
      "learning_rate": 6.112749920933111e-05,
      "loss": 10.1707,
      "step": 45
    },
    {
      "epoch": 0.03799592163341163,
      "grad_norm": 0.979099690914154,
      "learning_rate": 5.960188670239154e-05,
      "loss": 10.1746,
      "step": 46
    },
    {
      "epoch": 0.038821919929790144,
      "grad_norm": 0.9135434031486511,
      "learning_rate": 5.80709086014102e-05,
      "loss": 10.1605,
      "step": 47
    },
    {
      "epoch": 0.03964791822616866,
      "grad_norm": 0.8850502371788025,
      "learning_rate": 5.653634995836856e-05,
      "loss": 10.1635,
      "step": 48
    },
    {
      "epoch": 0.04047391652254717,
      "grad_norm": 0.8332787156105042,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.1517,
      "step": 49
    },
    {
      "epoch": 0.041299914818925684,
      "grad_norm": 0.8061609864234924,
      "learning_rate": 5.346365004163145e-05,
      "loss": 10.1519,
      "step": 50
    },
    {
      "epoch": 0.041299914818925684,
      "eval_loss": 10.1450777053833,
      "eval_runtime": 0.0797,
      "eval_samples_per_second": 627.657,
      "eval_steps_per_second": 163.191,
      "step": 50
    },
    {
      "epoch": 0.0421259131153042,
      "grad_norm": 0.7433369755744934,
      "learning_rate": 5.192909139858981e-05,
      "loss": 10.1678,
      "step": 51
    },
    {
      "epoch": 0.04295191141168271,
      "grad_norm": 0.7525593042373657,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 10.153,
      "step": 52
    },
    {
      "epoch": 0.043777909708061225,
      "grad_norm": 0.7264389991760254,
      "learning_rate": 4.887250079066892e-05,
      "loss": 10.1436,
      "step": 53
    },
    {
      "epoch": 0.04460390800443974,
      "grad_norm": 0.6619519591331482,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 10.1484,
      "step": 54
    },
    {
      "epoch": 0.04542990630081825,
      "grad_norm": 0.6890254616737366,
      "learning_rate": 4.584447941263149e-05,
      "loss": 10.1523,
      "step": 55
    },
    {
      "epoch": 0.04625590459719677,
      "grad_norm": 0.6508134007453918,
      "learning_rate": 4.43456010790099e-05,
      "loss": 10.1471,
      "step": 56
    },
    {
      "epoch": 0.047081902893575285,
      "grad_norm": 0.6366608738899231,
      "learning_rate": 4.285914529793391e-05,
      "loss": 10.1436,
      "step": 57
    },
    {
      "epoch": 0.0479079011899538,
      "grad_norm": 0.6206996440887451,
      "learning_rate": 4.13868452103516e-05,
      "loss": 10.1471,
      "step": 58
    },
    {
      "epoch": 0.04873389948633231,
      "grad_norm": 0.6083361506462097,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 10.1518,
      "step": 59
    },
    {
      "epoch": 0.049559897782710825,
      "grad_norm": 0.6109912991523743,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 10.1513,
      "step": 60
    },
    {
      "epoch": 0.05038589607908934,
      "grad_norm": 0.5825498104095459,
      "learning_rate": 3.707195095691913e-05,
      "loss": 10.1439,
      "step": 61
    },
    {
      "epoch": 0.05121189437546785,
      "grad_norm": 0.5695679187774658,
      "learning_rate": 3.567324506364632e-05,
      "loss": 10.1357,
      "step": 62
    },
    {
      "epoch": 0.052037892671846366,
      "grad_norm": 0.5250859260559082,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 10.149,
      "step": 63
    },
    {
      "epoch": 0.05286389096822488,
      "grad_norm": 0.5382351279258728,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 10.137,
      "step": 64
    },
    {
      "epoch": 0.05368988926460339,
      "grad_norm": 0.5617210268974304,
      "learning_rate": 3.16187222484055e-05,
      "loss": 10.1362,
      "step": 65
    },
    {
      "epoch": 0.054515887560981906,
      "grad_norm": 0.5113865733146667,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 10.1428,
      "step": 66
    },
    {
      "epoch": 0.05534188585736042,
      "grad_norm": 0.548232913017273,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 10.1417,
      "step": 67
    },
    {
      "epoch": 0.05616788415373893,
      "grad_norm": 0.5503516793251038,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 10.1364,
      "step": 68
    },
    {
      "epoch": 0.056993882450117446,
      "grad_norm": 0.6043108701705933,
      "learning_rate": 2.660104250532764e-05,
      "loss": 10.1383,
      "step": 69
    },
    {
      "epoch": 0.05781988074649596,
      "grad_norm": 0.5401960015296936,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 10.1353,
      "step": 70
    },
    {
      "epoch": 0.05864587904287447,
      "grad_norm": 0.5547022819519043,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 10.1326,
      "step": 71
    },
    {
      "epoch": 0.059471877339252986,
      "grad_norm": 0.5565068125724792,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.1383,
      "step": 72
    },
    {
      "epoch": 0.0602978756356315,
      "grad_norm": 0.5781975388526917,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 10.1381,
      "step": 73
    },
    {
      "epoch": 0.06112387393201001,
      "grad_norm": 0.5462612509727478,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 10.1321,
      "step": 74
    },
    {
      "epoch": 0.061949872228388526,
      "grad_norm": 0.5515443682670593,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 10.1368,
      "step": 75
    },
    {
      "epoch": 0.061949872228388526,
      "eval_loss": 10.12276840209961,
      "eval_runtime": 0.08,
      "eval_samples_per_second": 624.742,
      "eval_steps_per_second": 162.433,
      "step": 75
    },
    {
      "epoch": 0.06277587052476705,
      "grad_norm": 0.5765253901481628,
      "learning_rate": 1.91437699862843e-05,
      "loss": 10.1609,
      "step": 76
    },
    {
      "epoch": 0.06360186882114556,
      "grad_norm": 0.5583258271217346,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 10.1337,
      "step": 77
    },
    {
      "epoch": 0.06442786711752407,
      "grad_norm": 0.5325179696083069,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 10.1365,
      "step": 78
    },
    {
      "epoch": 0.06525386541390259,
      "grad_norm": 0.5995349884033203,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 10.1319,
      "step": 79
    },
    {
      "epoch": 0.0660798637102811,
      "grad_norm": 0.596726655960083,
      "learning_rate": 1.577527884852619e-05,
      "loss": 10.1265,
      "step": 80
    },
    {
      "epoch": 0.06690586200665961,
      "grad_norm": 0.574684202671051,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 10.1292,
      "step": 81
    },
    {
      "epoch": 0.06773186030303813,
      "grad_norm": 0.5674662590026855,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 10.1308,
      "step": 82
    },
    {
      "epoch": 0.06855785859941664,
      "grad_norm": 0.6809078454971313,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 10.12,
      "step": 83
    },
    {
      "epoch": 0.06938385689579515,
      "grad_norm": 0.5955153703689575,
      "learning_rate": 1.313747004979751e-05,
      "loss": 10.1294,
      "step": 84
    },
    {
      "epoch": 0.07020985519217367,
      "grad_norm": 0.6445745825767517,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 10.1313,
      "step": 85
    },
    {
      "epoch": 0.07103585348855218,
      "grad_norm": 0.611798107624054,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 10.1273,
      "step": 86
    },
    {
      "epoch": 0.0718618517849307,
      "grad_norm": 0.5751798152923584,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 10.1307,
      "step": 87
    },
    {
      "epoch": 0.07268785008130921,
      "grad_norm": 0.5628722310066223,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 10.1329,
      "step": 88
    },
    {
      "epoch": 0.07351384837768772,
      "grad_norm": 0.6203532814979553,
      "learning_rate": 1.094121605429547e-05,
      "loss": 10.125,
      "step": 89
    },
    {
      "epoch": 0.07433984667406623,
      "grad_norm": 0.6454430818557739,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 10.1345,
      "step": 90
    },
    {
      "epoch": 0.07516584497044475,
      "grad_norm": 0.6020610928535461,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 10.1286,
      "step": 91
    },
    {
      "epoch": 0.07599184326682326,
      "grad_norm": 0.6609290242195129,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 10.1331,
      "step": 92
    },
    {
      "epoch": 0.07681784156320177,
      "grad_norm": 0.6074327230453491,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 10.1268,
      "step": 93
    },
    {
      "epoch": 0.07764383985958029,
      "grad_norm": 0.5935200452804565,
      "learning_rate": 1.002623399352217e-05,
      "loss": 10.1335,
      "step": 94
    },
    {
      "epoch": 0.0784698381559588,
      "grad_norm": 0.6691338419914246,
      "learning_rate": 1e-05,
      "loss": 10.1336,
      "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": 81259313233920.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}