{
  "best_metric": 0.020673463121056557,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.21869874248223073,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002186987424822307,
      "grad_norm": 0.13690724968910217,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.0589,
      "step": 1
    },
    {
      "epoch": 0.002186987424822307,
      "eval_loss": 0.23621612787246704,
      "eval_runtime": 2.119,
      "eval_samples_per_second": 23.596,
      "eval_steps_per_second": 3.303,
      "step": 1
    },
    {
      "epoch": 0.004373974849644614,
      "grad_norm": 0.12066072225570679,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.0552,
      "step": 2
    },
    {
      "epoch": 0.0065609622744669215,
      "grad_norm": 0.11652152240276337,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.0608,
      "step": 3
    },
    {
      "epoch": 0.008747949699289229,
      "grad_norm": 0.11270295083522797,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.047,
      "step": 4
    },
    {
      "epoch": 0.010934937124111536,
      "grad_norm": 0.12687504291534424,
      "learning_rate": 0.00015,
      "loss": 0.0494,
      "step": 5
    },
    {
      "epoch": 0.013121924548933843,
      "grad_norm": 0.15194256603717804,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.0574,
      "step": 6
    },
    {
      "epoch": 0.01530891197375615,
      "grad_norm": 0.1595032513141632,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.059,
      "step": 7
    },
    {
      "epoch": 0.017495899398578457,
      "grad_norm": 0.15066266059875488,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.0646,
      "step": 8
    },
    {
      "epoch": 0.019682886823400764,
      "grad_norm": 0.14444738626480103,
      "learning_rate": 0.00027,
      "loss": 0.0587,
      "step": 9
    },
    {
      "epoch": 0.02186987424822307,
      "grad_norm": 0.2381969392299652,
      "learning_rate": 0.0003,
      "loss": 0.058,
      "step": 10
    },
    {
      "epoch": 0.02405686167304538,
      "grad_norm": 0.21966710686683655,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.045,
      "step": 11
    },
    {
      "epoch": 0.026243849097867686,
      "grad_norm": 0.17246013879776,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.0374,
      "step": 12
    },
    {
      "epoch": 0.028430836522689993,
      "grad_norm": 0.12403001636266708,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.0263,
      "step": 13
    },
    {
      "epoch": 0.0306178239475123,
      "grad_norm": 0.2065289467573166,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.0323,
      "step": 14
    },
    {
      "epoch": 0.03280481137233461,
      "grad_norm": 0.2022233009338379,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.0266,
      "step": 15
    },
    {
      "epoch": 0.034991798797156914,
      "grad_norm": 0.2569928765296936,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.0297,
      "step": 16
    },
    {
      "epoch": 0.037178786221979225,
      "grad_norm": 0.218874990940094,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.035,
      "step": 17
    },
    {
      "epoch": 0.03936577364680153,
      "grad_norm": 0.19128642976284027,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.0272,
      "step": 18
    },
    {
      "epoch": 0.04155276107162384,
      "grad_norm": 0.19477908313274384,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.0209,
      "step": 19
    },
    {
      "epoch": 0.04373974849644614,
      "grad_norm": 0.15674588084220886,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.0265,
      "step": 20
    },
    {
      "epoch": 0.045926735921268454,
      "grad_norm": 0.13309833407402039,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.0253,
      "step": 21
    },
    {
      "epoch": 0.04811372334609076,
      "grad_norm": 0.2032337784767151,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.0314,
      "step": 22
    },
    {
      "epoch": 0.05030071077091307,
      "grad_norm": 0.17100787162780762,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.0331,
      "step": 23
    },
    {
      "epoch": 0.05248769819573537,
      "grad_norm": 0.14446628093719482,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.0241,
      "step": 24
    },
    {
      "epoch": 0.05467468562055768,
      "grad_norm": 0.19537991285324097,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.028,
      "step": 25
    },
    {
      "epoch": 0.05467468562055768,
      "eval_loss": 0.03276868909597397,
      "eval_runtime": 1.3382,
      "eval_samples_per_second": 37.362,
      "eval_steps_per_second": 5.231,
      "step": 25
    },
    {
      "epoch": 0.056861673045379986,
      "grad_norm": 0.16063371300697327,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.0253,
      "step": 26
    },
    {
      "epoch": 0.0590486604702023,
      "grad_norm": 0.14069896936416626,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.0195,
      "step": 27
    },
    {
      "epoch": 0.0612356478950246,
      "grad_norm": 0.20457680523395538,
      "learning_rate": 0.0002934053672301536,
      "loss": 0.0272,
      "step": 28
    },
    {
      "epoch": 0.0634226353198469,
      "grad_norm": 0.16065166890621185,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.0163,
      "step": 29
    },
    {
      "epoch": 0.06560962274466922,
      "grad_norm": 0.1813274621963501,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.029,
      "step": 30
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 0.2427264302968979,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.034,
      "step": 31
    },
    {
      "epoch": 0.06998359759431383,
      "grad_norm": 0.19946575164794922,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.0327,
      "step": 32
    },
    {
      "epoch": 0.07217058501913615,
      "grad_norm": 0.2525937259197235,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.0232,
      "step": 33
    },
    {
      "epoch": 0.07435757244395845,
      "grad_norm": 0.1592988669872284,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.0247,
      "step": 34
    },
    {
      "epoch": 0.07654455986878075,
      "grad_norm": 0.1970003992319107,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.0284,
      "step": 35
    },
    {
      "epoch": 0.07873154729360306,
      "grad_norm": 0.2504012882709503,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.0326,
      "step": 36
    },
    {
      "epoch": 0.08091853471842538,
      "grad_norm": 0.1752198189496994,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.0285,
      "step": 37
    },
    {
      "epoch": 0.08310552214324768,
      "grad_norm": 0.2530890703201294,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.0327,
      "step": 38
    },
    {
      "epoch": 0.08529250956806998,
      "grad_norm": 0.28970402479171753,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.034,
      "step": 39
    },
    {
      "epoch": 0.08747949699289229,
      "grad_norm": 0.1608027219772339,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.0178,
      "step": 40
    },
    {
      "epoch": 0.0896664844177146,
      "grad_norm": 0.37331146001815796,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.0302,
      "step": 41
    },
    {
      "epoch": 0.09185347184253691,
      "grad_norm": 0.32435354590415955,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.0411,
      "step": 42
    },
    {
      "epoch": 0.09404045926735921,
      "grad_norm": 0.3027302026748657,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.0328,
      "step": 43
    },
    {
      "epoch": 0.09622744669218151,
      "grad_norm": 0.2774754762649536,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.0382,
      "step": 44
    },
    {
      "epoch": 0.09841443411700383,
      "grad_norm": 0.45914962887763977,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.0577,
      "step": 45
    },
    {
      "epoch": 0.10060142154182614,
      "grad_norm": 0.44936031103134155,
      "learning_rate": 0.000274201324672203,
      "loss": 0.0591,
      "step": 46
    },
    {
      "epoch": 0.10278840896664844,
      "grad_norm": 0.4533582627773285,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.065,
      "step": 47
    },
    {
      "epoch": 0.10497539639147074,
      "grad_norm": 0.6735382080078125,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.0823,
      "step": 48
    },
    {
      "epoch": 0.10716238381629306,
      "grad_norm": 1.1085397005081177,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.1422,
      "step": 49
    },
    {
      "epoch": 0.10934937124111536,
      "grad_norm": 1.1576088666915894,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.215,
      "step": 50
    },
    {
      "epoch": 0.10934937124111536,
      "eval_loss": 0.026529133319854736,
      "eval_runtime": 1.3407,
      "eval_samples_per_second": 37.293,
      "eval_steps_per_second": 5.221,
      "step": 50
    },
    {
      "epoch": 0.11153635866593767,
      "grad_norm": 1.0392637252807617,
      "learning_rate": 0.0002668315918143169,
      "loss": 0.0633,
      "step": 51
    },
    {
      "epoch": 0.11372334609075997,
      "grad_norm": 0.15875579416751862,
      "learning_rate": 0.00026526016662852886,
      "loss": 0.0412,
      "step": 52
    },
    {
      "epoch": 0.11591033351558229,
      "grad_norm": 0.1337694674730301,
      "learning_rate": 0.00026365723046405023,
      "loss": 0.0385,
      "step": 53
    },
    {
      "epoch": 0.1180973209404046,
      "grad_norm": 0.05959850922226906,
      "learning_rate": 0.0002620232215476231,
      "loss": 0.0177,
      "step": 54
    },
    {
      "epoch": 0.1202843083652269,
      "grad_norm": 0.1247549057006836,
      "learning_rate": 0.0002603585866009697,
      "loss": 0.0184,
      "step": 55
    },
    {
      "epoch": 0.1224712957900492,
      "grad_norm": 0.20971360802650452,
      "learning_rate": 0.00025866378071866334,
      "loss": 0.0167,
      "step": 56
    },
    {
      "epoch": 0.12465828321487152,
      "grad_norm": 0.14267611503601074,
      "learning_rate": 0.00025693926724370956,
      "loss": 0.0161,
      "step": 57
    },
    {
      "epoch": 0.1268452706396938,
      "grad_norm": 0.10089556872844696,
      "learning_rate": 0.00025518551764087326,
      "loss": 0.0161,
      "step": 58
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 0.10070645809173584,
      "learning_rate": 0.00025340301136778483,
      "loss": 0.0188,
      "step": 59
    },
    {
      "epoch": 0.13121924548933844,
      "grad_norm": 0.1393732726573944,
      "learning_rate": 0.00025159223574386114,
      "loss": 0.0142,
      "step": 60
    },
    {
      "epoch": 0.13340623291416073,
      "grad_norm": 0.09585541486740112,
      "learning_rate": 0.0002497536858170772,
      "loss": 0.0211,
      "step": 61
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 0.22409416735172272,
      "learning_rate": 0.00024788786422862526,
      "loss": 0.0246,
      "step": 62
    },
    {
      "epoch": 0.13778020776380537,
      "grad_norm": 0.11945615708827972,
      "learning_rate": 0.00024599528107549745,
      "loss": 0.016,
      "step": 63
    },
    {
      "epoch": 0.13996719518862766,
      "grad_norm": 0.0991947129368782,
      "learning_rate": 0.00024407645377103054,
      "loss": 0.019,
      "step": 64
    },
    {
      "epoch": 0.14215418261344998,
      "grad_norm": 0.09855477511882782,
      "learning_rate": 0.00024213190690345018,
      "loss": 0.0175,
      "step": 65
    },
    {
      "epoch": 0.1443411700382723,
      "grad_norm": 0.09625185281038284,
      "learning_rate": 0.00024016217209245374,
      "loss": 0.0144,
      "step": 66
    },
    {
      "epoch": 0.14652815746309458,
      "grad_norm": 0.12816566228866577,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.0161,
      "step": 67
    },
    {
      "epoch": 0.1487151448879169,
      "grad_norm": 0.08715605735778809,
      "learning_rate": 0.0002361492994024415,
      "loss": 0.0139,
      "step": 68
    },
    {
      "epoch": 0.1509021323127392,
      "grad_norm": 0.2528409957885742,
      "learning_rate": 0.0002341072586027509,
      "loss": 0.0218,
      "step": 69
    },
    {
      "epoch": 0.1530891197375615,
      "grad_norm": 0.12442867457866669,
      "learning_rate": 0.00023204222371836405,
      "loss": 0.0198,
      "step": 70
    },
    {
      "epoch": 0.15527610716238383,
      "grad_norm": 0.1194726973772049,
      "learning_rate": 0.00022995475930919905,
      "loss": 0.023,
      "step": 71
    },
    {
      "epoch": 0.15746309458720611,
      "grad_norm": 0.09626832604408264,
      "learning_rate": 0.00022784543606718227,
      "loss": 0.0138,
      "step": 72
    },
    {
      "epoch": 0.15965008201202843,
      "grad_norm": 0.12682025134563446,
      "learning_rate": 0.00022571483066022657,
      "loss": 0.0157,
      "step": 73
    },
    {
      "epoch": 0.16183706943685075,
      "grad_norm": 0.2088419646024704,
      "learning_rate": 0.0002235635255745762,
      "loss": 0.0157,
      "step": 74
    },
    {
      "epoch": 0.16402405686167304,
      "grad_norm": 0.13500891625881195,
      "learning_rate": 0.00022139210895556104,
      "loss": 0.0222,
      "step": 75
    },
    {
      "epoch": 0.16402405686167304,
      "eval_loss": 0.022737087681889534,
      "eval_runtime": 1.3392,
      "eval_samples_per_second": 37.336,
      "eval_steps_per_second": 5.227,
      "step": 75
    },
    {
      "epoch": 0.16621104428649536,
      "grad_norm": 0.15281231701374054,
      "learning_rate": 0.00021920117444680317,
      "loss": 0.019,
      "step": 76
    },
    {
      "epoch": 0.16839803171131765,
      "grad_norm": 0.11248669028282166,
      "learning_rate": 0.00021699132102792097,
      "loss": 0.0132,
      "step": 77
    },
    {
      "epoch": 0.17058501913613996,
      "grad_norm": 0.15063031017780304,
      "learning_rate": 0.0002147631528507739,
      "loss": 0.017,
      "step": 78
    },
    {
      "epoch": 0.17277200656096228,
      "grad_norm": 0.15281358361244202,
      "learning_rate": 0.00021251727907429355,
      "loss": 0.0141,
      "step": 79
    },
    {
      "epoch": 0.17495899398578457,
      "grad_norm": 0.1836492121219635,
      "learning_rate": 0.0002102543136979454,
      "loss": 0.0197,
      "step": 80
    },
    {
      "epoch": 0.1771459814106069,
      "grad_norm": 0.1414135992527008,
      "learning_rate": 0.0002079748753938678,
      "loss": 0.0205,
      "step": 81
    },
    {
      "epoch": 0.1793329688354292,
      "grad_norm": 0.14938773214817047,
      "learning_rate": 0.0002056795873377331,
      "loss": 0.0185,
      "step": 82
    },
    {
      "epoch": 0.1815199562602515,
      "grad_norm": 0.2255454659461975,
      "learning_rate": 0.00020336907703837748,
      "loss": 0.0198,
      "step": 83
    },
    {
      "epoch": 0.18370694368507381,
      "grad_norm": 0.21891963481903076,
      "learning_rate": 0.00020104397616624645,
      "loss": 0.025,
      "step": 84
    },
    {
      "epoch": 0.1858939311098961,
      "grad_norm": 0.1948690116405487,
      "learning_rate": 0.00019870492038070252,
      "loss": 0.0162,
      "step": 85
    },
    {
      "epoch": 0.18808091853471842,
      "grad_norm": 0.21625962853431702,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.0263,
      "step": 86
    },
    {
      "epoch": 0.19026790595954074,
      "grad_norm": 0.2148241251707077,
      "learning_rate": 0.0001939875056076697,
      "loss": 0.0301,
      "step": 87
    },
    {
      "epoch": 0.19245489338436303,
      "grad_norm": 0.20526079833507538,
      "learning_rate": 0.00019161043631427666,
      "loss": 0.0284,
      "step": 88
    },
    {
      "epoch": 0.19464188080918535,
      "grad_norm": 0.25726714730262756,
      "learning_rate": 0.00018922199114307294,
      "loss": 0.0387,
      "step": 89
    },
    {
      "epoch": 0.19682886823400766,
      "grad_norm": 0.23738834261894226,
      "learning_rate": 0.00018682282307111987,
      "loss": 0.0268,
      "step": 90
    },
    {
      "epoch": 0.19901585565882995,
      "grad_norm": 0.24734491109848022,
      "learning_rate": 0.00018441358800701273,
      "loss": 0.0326,
      "step": 91
    },
    {
      "epoch": 0.20120284308365227,
      "grad_norm": 0.24052025377750397,
      "learning_rate": 0.00018199494461156203,
      "loss": 0.0434,
      "step": 92
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": 0.27265802025794983,
      "learning_rate": 0.000179567554117722,
      "loss": 0.045,
      "step": 93
    },
    {
      "epoch": 0.20557681793329688,
      "grad_norm": 0.21144987642765045,
      "learning_rate": 0.00017713208014981648,
      "loss": 0.0181,
      "step": 94
    },
    {
      "epoch": 0.2077638053581192,
      "grad_norm": 0.3239058554172516,
      "learning_rate": 0.00017468918854211007,
      "loss": 0.0487,
      "step": 95
    },
    {
      "epoch": 0.2099507927829415,
      "grad_norm": 0.3763501048088074,
      "learning_rate": 0.00017223954715677627,
      "loss": 0.0731,
      "step": 96
    },
    {
      "epoch": 0.2121377802077638,
      "grad_norm": 0.38792726397514343,
      "learning_rate": 0.00016978382570131034,
      "loss": 0.0556,
      "step": 97
    },
    {
      "epoch": 0.21432476763258612,
      "grad_norm": 0.4279646873474121,
      "learning_rate": 0.00016732269554543794,
      "loss": 0.08,
      "step": 98
    },
    {
      "epoch": 0.2165117550574084,
      "grad_norm": 0.6510411500930786,
      "learning_rate": 0.00016485682953756942,
      "loss": 0.1366,
      "step": 99
    },
    {
      "epoch": 0.21869874248223073,
      "grad_norm": 1.3243879079818726,
      "learning_rate": 0.00016238690182084986,
      "loss": 0.2728,
      "step": 100
    },
    {
      "epoch": 0.21869874248223073,
      "eval_loss": 0.020673463121056557,
      "eval_runtime": 1.3447,
      "eval_samples_per_second": 37.182,
      "eval_steps_per_second": 5.206,
      "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": 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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2928976632610816e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}