{
  "best_metric": 0.022677214816212654,
  "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": 0.1379365772008896,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.0589,
      "step": 1
    },
    {
      "epoch": 0.002186987424822307,
      "eval_loss": 0.23621612787246704,
      "eval_runtime": 2.127,
      "eval_samples_per_second": 23.508,
      "eval_steps_per_second": 3.291,
      "step": 1
    },
    {
      "epoch": 0.004373974849644614,
      "grad_norm": 0.12105759233236313,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.0552,
      "step": 2
    },
    {
      "epoch": 0.0065609622744669215,
      "grad_norm": 0.11737111210823059,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.0608,
      "step": 3
    },
    {
      "epoch": 0.008747949699289229,
      "grad_norm": 0.11113476753234863,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.0471,
      "step": 4
    },
    {
      "epoch": 0.010934937124111536,
      "grad_norm": 0.12482555210590363,
      "learning_rate": 0.00015,
      "loss": 0.0495,
      "step": 5
    },
    {
      "epoch": 0.013121924548933843,
      "grad_norm": 0.15192073583602905,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.0574,
      "step": 6
    },
    {
      "epoch": 0.01530891197375615,
      "grad_norm": 0.15852989256381989,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.0594,
      "step": 7
    },
    {
      "epoch": 0.017495899398578457,
      "grad_norm": 0.15277495980262756,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.0651,
      "step": 8
    },
    {
      "epoch": 0.019682886823400764,
      "grad_norm": 0.1454448699951172,
      "learning_rate": 0.00027,
      "loss": 0.059,
      "step": 9
    },
    {
      "epoch": 0.02186987424822307,
      "grad_norm": 0.2372606247663498,
      "learning_rate": 0.0003,
      "loss": 0.059,
      "step": 10
    },
    {
      "epoch": 0.02405686167304538,
      "grad_norm": 0.21213853359222412,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.045,
      "step": 11
    },
    {
      "epoch": 0.026243849097867686,
      "grad_norm": 0.17461541295051575,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.0373,
      "step": 12
    },
    {
      "epoch": 0.028430836522689993,
      "grad_norm": 0.12617610394954681,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.0266,
      "step": 13
    },
    {
      "epoch": 0.0306178239475123,
      "grad_norm": 0.19508954882621765,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.031,
      "step": 14
    },
    {
      "epoch": 0.03280481137233461,
      "grad_norm": 0.21883797645568848,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.0271,
      "step": 15
    },
    {
      "epoch": 0.034991798797156914,
      "grad_norm": 0.26026102900505066,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.0303,
      "step": 16
    },
    {
      "epoch": 0.037178786221979225,
      "grad_norm": 0.21829484403133392,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.0339,
      "step": 17
    },
    {
      "epoch": 0.03936577364680153,
      "grad_norm": 0.1891174167394638,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.0267,
      "step": 18
    },
    {
      "epoch": 0.04155276107162384,
      "grad_norm": 0.1897806078195572,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.0209,
      "step": 19
    },
    {
      "epoch": 0.04373974849644614,
      "grad_norm": 0.14886467158794403,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.026,
      "step": 20
    },
    {
      "epoch": 0.045926735921268454,
      "grad_norm": 0.14559559524059296,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.025,
      "step": 21
    },
    {
      "epoch": 0.04811372334609076,
      "grad_norm": 0.19482867419719696,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.0305,
      "step": 22
    },
    {
      "epoch": 0.05030071077091307,
      "grad_norm": 0.1720445454120636,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.0329,
      "step": 23
    },
    {
      "epoch": 0.05248769819573537,
      "grad_norm": 0.158674418926239,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.0241,
      "step": 24
    },
    {
      "epoch": 0.05467468562055768,
      "grad_norm": 0.2127903699874878,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.0281,
      "step": 25
    },
    {
      "epoch": 0.05467468562055768,
      "eval_loss": 0.03313703089952469,
      "eval_runtime": 1.3445,
      "eval_samples_per_second": 37.188,
      "eval_steps_per_second": 5.206,
      "step": 25
    },
    {
      "epoch": 0.056861673045379986,
      "grad_norm": 0.1662108302116394,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.0259,
      "step": 26
    },
    {
      "epoch": 0.0590486604702023,
      "grad_norm": 0.14126865565776825,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.019,
      "step": 27
    },
    {
      "epoch": 0.0612356478950246,
      "grad_norm": 0.20812584459781647,
      "learning_rate": 0.0002934053672301536,
      "loss": 0.0269,
      "step": 28
    },
    {
      "epoch": 0.0634226353198469,
      "grad_norm": 0.16265930235385895,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.0166,
      "step": 29
    },
    {
      "epoch": 0.06560962274466922,
      "grad_norm": 0.1864025890827179,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.0298,
      "step": 30
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 0.2999975085258484,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.0342,
      "step": 31
    },
    {
      "epoch": 0.06998359759431383,
      "grad_norm": 0.18503515422344208,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.0305,
      "step": 32
    },
    {
      "epoch": 0.07217058501913615,
      "grad_norm": 0.2400880604982376,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.0218,
      "step": 33
    },
    {
      "epoch": 0.07435757244395845,
      "grad_norm": 0.17187494039535522,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.0238,
      "step": 34
    },
    {
      "epoch": 0.07654455986878075,
      "grad_norm": 0.17750395834445953,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.0274,
      "step": 35
    },
    {
      "epoch": 0.07873154729360306,
      "grad_norm": 0.24035736918449402,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.0327,
      "step": 36
    },
    {
      "epoch": 0.08091853471842538,
      "grad_norm": 0.17879100143909454,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.0273,
      "step": 37
    },
    {
      "epoch": 0.08310552214324768,
      "grad_norm": 0.5411270260810852,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.0349,
      "step": 38
    },
    {
      "epoch": 0.08529250956806998,
      "grad_norm": 0.21817879378795624,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.0326,
      "step": 39
    },
    {
      "epoch": 0.08747949699289229,
      "grad_norm": 1.6915651559829712,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.037,
      "step": 40
    },
    {
      "epoch": 0.0896664844177146,
      "grad_norm": 0.2748837172985077,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.0307,
      "step": 41
    },
    {
      "epoch": 0.09185347184253691,
      "grad_norm": 0.27645471692085266,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.0406,
      "step": 42
    },
    {
      "epoch": 0.09404045926735921,
      "grad_norm": 0.2864626944065094,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.0361,
      "step": 43
    },
    {
      "epoch": 0.09622744669218151,
      "grad_norm": 0.267821729183197,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.0375,
      "step": 44
    },
    {
      "epoch": 0.09841443411700383,
      "grad_norm": 0.9943220019340515,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.0658,
      "step": 45
    },
    {
      "epoch": 0.10060142154182614,
      "grad_norm": 0.37693554162979126,
      "learning_rate": 0.000274201324672203,
      "loss": 0.0562,
      "step": 46
    },
    {
      "epoch": 0.10278840896664844,
      "grad_norm": 0.4007059335708618,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.0629,
      "step": 47
    },
    {
      "epoch": 0.10497539639147074,
      "grad_norm": 0.559242308139801,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.0811,
      "step": 48
    },
    {
      "epoch": 0.10716238381629306,
      "grad_norm": 0.8317009806632996,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.1323,
      "step": 49
    },
    {
      "epoch": 0.10934937124111536,
      "grad_norm": 1.7056876420974731,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.2221,
      "step": 50
    },
    {
      "epoch": 0.10934937124111536,
      "eval_loss": 0.030457014217972755,
      "eval_runtime": 1.3502,
      "eval_samples_per_second": 37.032,
      "eval_steps_per_second": 5.185,
      "step": 50
    },
    {
      "epoch": 0.11153635866593767,
      "grad_norm": 0.49903276562690735,
      "learning_rate": 0.0002668315918143169,
      "loss": 0.0569,
      "step": 51
    },
    {
      "epoch": 0.11372334609075997,
      "grad_norm": 0.2299562394618988,
      "learning_rate": 0.00026526016662852886,
      "loss": 0.0467,
      "step": 52
    },
    {
      "epoch": 0.11591033351558229,
      "grad_norm": 0.16393032670021057,
      "learning_rate": 0.00026365723046405023,
      "loss": 0.0423,
      "step": 53
    },
    {
      "epoch": 0.1180973209404046,
      "grad_norm": 0.17008137702941895,
      "learning_rate": 0.0002620232215476231,
      "loss": 0.022,
      "step": 54
    },
    {
      "epoch": 0.1202843083652269,
      "grad_norm": 0.19242006540298462,
      "learning_rate": 0.0002603585866009697,
      "loss": 0.02,
      "step": 55
    },
    {
      "epoch": 0.1224712957900492,
      "grad_norm": 0.11400814354419708,
      "learning_rate": 0.00025866378071866334,
      "loss": 0.015,
      "step": 56
    },
    {
      "epoch": 0.12465828321487152,
      "grad_norm": 0.15946003794670105,
      "learning_rate": 0.00025693926724370956,
      "loss": 0.0188,
      "step": 57
    },
    {
      "epoch": 0.1268452706396938,
      "grad_norm": 0.12168512493371964,
      "learning_rate": 0.00025518551764087326,
      "loss": 0.0162,
      "step": 58
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 0.11870243400335312,
      "learning_rate": 0.00025340301136778483,
      "loss": 0.0179,
      "step": 59
    },
    {
      "epoch": 0.13121924548933844,
      "grad_norm": 0.10031919181346893,
      "learning_rate": 0.00025159223574386114,
      "loss": 0.0136,
      "step": 60
    },
    {
      "epoch": 0.13340623291416073,
      "grad_norm": 0.11089091747999191,
      "learning_rate": 0.0002497536858170772,
      "loss": 0.0211,
      "step": 61
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 0.15215983986854553,
      "learning_rate": 0.00024788786422862526,
      "loss": 0.0225,
      "step": 62
    },
    {
      "epoch": 0.13778020776380537,
      "grad_norm": 0.13198548555374146,
      "learning_rate": 0.00024599528107549745,
      "loss": 0.0165,
      "step": 63
    },
    {
      "epoch": 0.13996719518862766,
      "grad_norm": 0.10001133382320404,
      "learning_rate": 0.00024407645377103054,
      "loss": 0.019,
      "step": 64
    },
    {
      "epoch": 0.14215418261344998,
      "grad_norm": 0.10065522789955139,
      "learning_rate": 0.00024213190690345018,
      "loss": 0.0183,
      "step": 65
    },
    {
      "epoch": 0.1443411700382723,
      "grad_norm": 0.09749165922403336,
      "learning_rate": 0.00024016217209245374,
      "loss": 0.0146,
      "step": 66
    },
    {
      "epoch": 0.14652815746309458,
      "grad_norm": 0.11730261147022247,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.0168,
      "step": 67
    },
    {
      "epoch": 0.1487151448879169,
      "grad_norm": 0.0950559601187706,
      "learning_rate": 0.0002361492994024415,
      "loss": 0.0151,
      "step": 68
    },
    {
      "epoch": 0.1509021323127392,
      "grad_norm": 0.12146329879760742,
      "learning_rate": 0.0002341072586027509,
      "loss": 0.0205,
      "step": 69
    },
    {
      "epoch": 0.1530891197375615,
      "grad_norm": 0.10607416927814484,
      "learning_rate": 0.00023204222371836405,
      "loss": 0.0173,
      "step": 70
    },
    {
      "epoch": 0.15527610716238383,
      "grad_norm": 0.10930145531892776,
      "learning_rate": 0.00022995475930919905,
      "loss": 0.0218,
      "step": 71
    },
    {
      "epoch": 0.15746309458720611,
      "grad_norm": 0.10130448639392853,
      "learning_rate": 0.00022784543606718227,
      "loss": 0.0146,
      "step": 72
    },
    {
      "epoch": 0.15965008201202843,
      "grad_norm": 0.15067188441753387,
      "learning_rate": 0.00022571483066022657,
      "loss": 0.0173,
      "step": 73
    },
    {
      "epoch": 0.16183706943685075,
      "grad_norm": 0.192259281873703,
      "learning_rate": 0.0002235635255745762,
      "loss": 0.0159,
      "step": 74
    },
    {
      "epoch": 0.16402405686167304,
      "grad_norm": 0.17025741934776306,
      "learning_rate": 0.00022139210895556104,
      "loss": 0.0218,
      "step": 75
    },
    {
      "epoch": 0.16402405686167304,
      "eval_loss": 0.02335500717163086,
      "eval_runtime": 1.35,
      "eval_samples_per_second": 37.037,
      "eval_steps_per_second": 5.185,
      "step": 75
    },
    {
      "epoch": 0.16621104428649536,
      "grad_norm": 0.12429143488407135,
      "learning_rate": 0.00021920117444680317,
      "loss": 0.0178,
      "step": 76
    },
    {
      "epoch": 0.16839803171131765,
      "grad_norm": 0.12413789331912994,
      "learning_rate": 0.00021699132102792097,
      "loss": 0.014,
      "step": 77
    },
    {
      "epoch": 0.17058501913613996,
      "grad_norm": 0.13945256173610687,
      "learning_rate": 0.0002147631528507739,
      "loss": 0.0167,
      "step": 78
    },
    {
      "epoch": 0.17277200656096228,
      "grad_norm": 0.15853500366210938,
      "learning_rate": 0.00021251727907429355,
      "loss": 0.0146,
      "step": 79
    },
    {
      "epoch": 0.17495899398578457,
      "grad_norm": 0.19164036214351654,
      "learning_rate": 0.0002102543136979454,
      "loss": 0.022,
      "step": 80
    },
    {
      "epoch": 0.1771459814106069,
      "grad_norm": 0.18565410375595093,
      "learning_rate": 0.0002079748753938678,
      "loss": 0.0211,
      "step": 81
    },
    {
      "epoch": 0.1793329688354292,
      "grad_norm": 0.12104719877243042,
      "learning_rate": 0.0002056795873377331,
      "loss": 0.0176,
      "step": 82
    },
    {
      "epoch": 0.1815199562602515,
      "grad_norm": 0.17440539598464966,
      "learning_rate": 0.00020336907703837748,
      "loss": 0.0172,
      "step": 83
    },
    {
      "epoch": 0.18370694368507381,
      "grad_norm": 0.2185378223657608,
      "learning_rate": 0.00020104397616624645,
      "loss": 0.027,
      "step": 84
    },
    {
      "epoch": 0.1858939311098961,
      "grad_norm": 0.18021249771118164,
      "learning_rate": 0.00019870492038070252,
      "loss": 0.0156,
      "step": 85
    },
    {
      "epoch": 0.18808091853471842,
      "grad_norm": 0.20465314388275146,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.023,
      "step": 86
    },
    {
      "epoch": 0.19026790595954074,
      "grad_norm": 0.21064847707748413,
      "learning_rate": 0.0001939875056076697,
      "loss": 0.0298,
      "step": 87
    },
    {
      "epoch": 0.19245489338436303,
      "grad_norm": 0.2056667059659958,
      "learning_rate": 0.00019161043631427666,
      "loss": 0.0271,
      "step": 88
    },
    {
      "epoch": 0.19464188080918535,
      "grad_norm": 0.2719489634037018,
      "learning_rate": 0.00018922199114307294,
      "loss": 0.0378,
      "step": 89
    },
    {
      "epoch": 0.19682886823400766,
      "grad_norm": 0.28450775146484375,
      "learning_rate": 0.00018682282307111987,
      "loss": 0.0288,
      "step": 90
    },
    {
      "epoch": 0.19901585565882995,
      "grad_norm": 0.34577643871307373,
      "learning_rate": 0.00018441358800701273,
      "loss": 0.0342,
      "step": 91
    },
    {
      "epoch": 0.20120284308365227,
      "grad_norm": 0.2987297475337982,
      "learning_rate": 0.00018199494461156203,
      "loss": 0.0447,
      "step": 92
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": 0.38449111580848694,
      "learning_rate": 0.000179567554117722,
      "loss": 0.0479,
      "step": 93
    },
    {
      "epoch": 0.20557681793329688,
      "grad_norm": 0.2054828554391861,
      "learning_rate": 0.00017713208014981648,
      "loss": 0.0173,
      "step": 94
    },
    {
      "epoch": 0.2077638053581192,
      "grad_norm": 0.3865654766559601,
      "learning_rate": 0.00017468918854211007,
      "loss": 0.0519,
      "step": 95
    },
    {
      "epoch": 0.2099507927829415,
      "grad_norm": 0.3918894827365875,
      "learning_rate": 0.00017223954715677627,
      "loss": 0.0704,
      "step": 96
    },
    {
      "epoch": 0.2121377802077638,
      "grad_norm": 0.39511775970458984,
      "learning_rate": 0.00016978382570131034,
      "loss": 0.0546,
      "step": 97
    },
    {
      "epoch": 0.21432476763258612,
      "grad_norm": 0.44580182433128357,
      "learning_rate": 0.00016732269554543794,
      "loss": 0.0807,
      "step": 98
    },
    {
      "epoch": 0.2165117550574084,
      "grad_norm": 0.6511839032173157,
      "learning_rate": 0.00016485682953756942,
      "loss": 0.1271,
      "step": 99
    },
    {
      "epoch": 0.21869874248223073,
      "grad_norm": 1.4915711879730225,
      "learning_rate": 0.00016238690182084986,
      "loss": 0.2898,
      "step": 100
    },
    {
      "epoch": 0.21869874248223073,
      "eval_loss": 0.022677214816212654,
      "eval_runtime": 1.3454,
      "eval_samples_per_second": 37.163,
      "eval_steps_per_second": 5.203,
      "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
}