{
  "best_metric": 0.22028179466724396,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.8830022075055187,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008830022075055188,
      "grad_norm": 0.5267917513847351,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.7436,
      "step": 1
    },
    {
      "epoch": 0.008830022075055188,
      "eval_loss": 0.7710736989974976,
      "eval_runtime": 8.9645,
      "eval_samples_per_second": 5.578,
      "eval_steps_per_second": 0.781,
      "step": 1
    },
    {
      "epoch": 0.017660044150110375,
      "grad_norm": 0.6040651202201843,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.8066,
      "step": 2
    },
    {
      "epoch": 0.026490066225165563,
      "grad_norm": 0.6579259634017944,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.8391,
      "step": 3
    },
    {
      "epoch": 0.03532008830022075,
      "grad_norm": 0.6005827784538269,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.7884,
      "step": 4
    },
    {
      "epoch": 0.04415011037527594,
      "grad_norm": 0.5310338735580444,
      "learning_rate": 0.00015,
      "loss": 0.5849,
      "step": 5
    },
    {
      "epoch": 0.052980132450331126,
      "grad_norm": 0.4925440847873688,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.5388,
      "step": 6
    },
    {
      "epoch": 0.06181015452538632,
      "grad_norm": 0.6406821012496948,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.4683,
      "step": 7
    },
    {
      "epoch": 0.0706401766004415,
      "grad_norm": 0.9326793551445007,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.5396,
      "step": 8
    },
    {
      "epoch": 0.07947019867549669,
      "grad_norm": 0.5024523138999939,
      "learning_rate": 0.00027,
      "loss": 0.4557,
      "step": 9
    },
    {
      "epoch": 0.08830022075055188,
      "grad_norm": 0.5244933366775513,
      "learning_rate": 0.0003,
      "loss": 0.4242,
      "step": 10
    },
    {
      "epoch": 0.09713024282560706,
      "grad_norm": 0.5493826866149902,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.3902,
      "step": 11
    },
    {
      "epoch": 0.10596026490066225,
      "grad_norm": 0.5801348686218262,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.4015,
      "step": 12
    },
    {
      "epoch": 0.11479028697571744,
      "grad_norm": 0.48916712403297424,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.3983,
      "step": 13
    },
    {
      "epoch": 0.12362030905077263,
      "grad_norm": 0.3941458761692047,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.3628,
      "step": 14
    },
    {
      "epoch": 0.13245033112582782,
      "grad_norm": 0.4000348746776581,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.3254,
      "step": 15
    },
    {
      "epoch": 0.141280353200883,
      "grad_norm": 0.39534318447113037,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.3563,
      "step": 16
    },
    {
      "epoch": 0.15011037527593818,
      "grad_norm": 0.3745306134223938,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.3458,
      "step": 17
    },
    {
      "epoch": 0.15894039735099338,
      "grad_norm": 0.3725316822528839,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.3429,
      "step": 18
    },
    {
      "epoch": 0.16777041942604856,
      "grad_norm": 0.3427765965461731,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.3101,
      "step": 19
    },
    {
      "epoch": 0.17660044150110377,
      "grad_norm": 0.3185417056083679,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.2583,
      "step": 20
    },
    {
      "epoch": 0.18543046357615894,
      "grad_norm": 0.3798052668571472,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.2997,
      "step": 21
    },
    {
      "epoch": 0.19426048565121412,
      "grad_norm": 0.4568968713283539,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.2729,
      "step": 22
    },
    {
      "epoch": 0.20309050772626933,
      "grad_norm": 0.3697591722011566,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.2551,
      "step": 23
    },
    {
      "epoch": 0.2119205298013245,
      "grad_norm": 0.36315158009529114,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.2292,
      "step": 24
    },
    {
      "epoch": 0.22075055187637968,
      "grad_norm": 0.4563204050064087,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.2202,
      "step": 25
    },
    {
      "epoch": 0.22075055187637968,
      "eval_loss": 0.3227197527885437,
      "eval_runtime": 8.5814,
      "eval_samples_per_second": 5.827,
      "eval_steps_per_second": 0.816,
      "step": 25
    },
    {
      "epoch": 0.22958057395143489,
      "grad_norm": 0.3887939155101776,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.2462,
      "step": 26
    },
    {
      "epoch": 0.23841059602649006,
      "grad_norm": 0.5520837903022766,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.4752,
      "step": 27
    },
    {
      "epoch": 0.24724061810154527,
      "grad_norm": 4.037907123565674,
      "learning_rate": 0.0002934053672301536,
      "loss": 1.4451,
      "step": 28
    },
    {
      "epoch": 0.2560706401766004,
      "grad_norm": 0.38813430070877075,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.4314,
      "step": 29
    },
    {
      "epoch": 0.26490066225165565,
      "grad_norm": 0.34112170338630676,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.4137,
      "step": 30
    },
    {
      "epoch": 0.2737306843267108,
      "grad_norm": 0.3160345256328583,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.3477,
      "step": 31
    },
    {
      "epoch": 0.282560706401766,
      "grad_norm": 0.33565646409988403,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.3028,
      "step": 32
    },
    {
      "epoch": 0.2913907284768212,
      "grad_norm": 0.26487964391708374,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.2279,
      "step": 33
    },
    {
      "epoch": 0.30022075055187636,
      "grad_norm": 0.28182142972946167,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.2752,
      "step": 34
    },
    {
      "epoch": 0.3090507726269316,
      "grad_norm": 0.3119100034236908,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.2873,
      "step": 35
    },
    {
      "epoch": 0.31788079470198677,
      "grad_norm": 0.280179500579834,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.2633,
      "step": 36
    },
    {
      "epoch": 0.32671081677704195,
      "grad_norm": 0.27022480964660645,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.2684,
      "step": 37
    },
    {
      "epoch": 0.3355408388520971,
      "grad_norm": 0.31984391808509827,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.2911,
      "step": 38
    },
    {
      "epoch": 0.3443708609271523,
      "grad_norm": 0.2874024212360382,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.2726,
      "step": 39
    },
    {
      "epoch": 0.35320088300220753,
      "grad_norm": 0.2740573287010193,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.2663,
      "step": 40
    },
    {
      "epoch": 0.3620309050772627,
      "grad_norm": 0.2838146686553955,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.2439,
      "step": 41
    },
    {
      "epoch": 0.3708609271523179,
      "grad_norm": 0.2758471369743347,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.2644,
      "step": 42
    },
    {
      "epoch": 0.37969094922737306,
      "grad_norm": 0.265119343996048,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.2497,
      "step": 43
    },
    {
      "epoch": 0.38852097130242824,
      "grad_norm": 0.28861644864082336,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.2751,
      "step": 44
    },
    {
      "epoch": 0.3973509933774834,
      "grad_norm": 0.2569108307361603,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.2488,
      "step": 45
    },
    {
      "epoch": 0.40618101545253865,
      "grad_norm": 0.24016250669956207,
      "learning_rate": 0.000274201324672203,
      "loss": 0.2178,
      "step": 46
    },
    {
      "epoch": 0.41501103752759383,
      "grad_norm": 0.2832198143005371,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.2597,
      "step": 47
    },
    {
      "epoch": 0.423841059602649,
      "grad_norm": 0.2444036304950714,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.195,
      "step": 48
    },
    {
      "epoch": 0.4326710816777042,
      "grad_norm": 0.24414511024951935,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.1861,
      "step": 49
    },
    {
      "epoch": 0.44150110375275936,
      "grad_norm": 0.27019017934799194,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.2333,
      "step": 50
    },
    {
      "epoch": 0.44150110375275936,
      "eval_loss": 0.26030516624450684,
      "eval_runtime": 8.5711,
      "eval_samples_per_second": 5.834,
      "eval_steps_per_second": 0.817,
      "step": 50
    },
    {
      "epoch": 0.4503311258278146,
      "grad_norm": 0.26158371567726135,
      "learning_rate": 0.0002668315918143169,
      "loss": 0.1915,
      "step": 51
    },
    {
      "epoch": 0.45916114790286977,
      "grad_norm": 0.3106990456581116,
      "learning_rate": 0.00026526016662852886,
      "loss": 0.2188,
      "step": 52
    },
    {
      "epoch": 0.46799116997792495,
      "grad_norm": 0.35014471411705017,
      "learning_rate": 0.00026365723046405023,
      "loss": 0.2459,
      "step": 53
    },
    {
      "epoch": 0.4768211920529801,
      "grad_norm": 0.37680375576019287,
      "learning_rate": 0.0002620232215476231,
      "loss": 0.29,
      "step": 54
    },
    {
      "epoch": 0.4856512141280353,
      "grad_norm": 0.4499601423740387,
      "learning_rate": 0.0002603585866009697,
      "loss": 0.3253,
      "step": 55
    },
    {
      "epoch": 0.49448123620309054,
      "grad_norm": 1.3646451234817505,
      "learning_rate": 0.00025866378071866334,
      "loss": 0.635,
      "step": 56
    },
    {
      "epoch": 0.5033112582781457,
      "grad_norm": 0.3264712691307068,
      "learning_rate": 0.00025693926724370956,
      "loss": 0.3822,
      "step": 57
    },
    {
      "epoch": 0.5121412803532008,
      "grad_norm": 0.3070512115955353,
      "learning_rate": 0.00025518551764087326,
      "loss": 0.3222,
      "step": 58
    },
    {
      "epoch": 0.5209713024282561,
      "grad_norm": 0.27624809741973877,
      "learning_rate": 0.00025340301136778483,
      "loss": 0.3353,
      "step": 59
    },
    {
      "epoch": 0.5298013245033113,
      "grad_norm": 0.2753635048866272,
      "learning_rate": 0.00025159223574386114,
      "loss": 0.3167,
      "step": 60
    },
    {
      "epoch": 0.5386313465783664,
      "grad_norm": 0.2416149228811264,
      "learning_rate": 0.0002497536858170772,
      "loss": 0.2327,
      "step": 61
    },
    {
      "epoch": 0.5474613686534217,
      "grad_norm": 0.2498352825641632,
      "learning_rate": 0.00024788786422862526,
      "loss": 0.2401,
      "step": 62
    },
    {
      "epoch": 0.5562913907284768,
      "grad_norm": 0.24006612598896027,
      "learning_rate": 0.00024599528107549745,
      "loss": 0.2362,
      "step": 63
    },
    {
      "epoch": 0.565121412803532,
      "grad_norm": 0.23591412603855133,
      "learning_rate": 0.00024407645377103054,
      "loss": 0.2181,
      "step": 64
    },
    {
      "epoch": 0.5739514348785872,
      "grad_norm": 0.26131555438041687,
      "learning_rate": 0.00024213190690345018,
      "loss": 0.2303,
      "step": 65
    },
    {
      "epoch": 0.5827814569536424,
      "grad_norm": 0.23474238812923431,
      "learning_rate": 0.00024016217209245374,
      "loss": 0.2231,
      "step": 66
    },
    {
      "epoch": 0.5916114790286976,
      "grad_norm": 0.26084139943122864,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.2424,
      "step": 67
    },
    {
      "epoch": 0.6004415011037527,
      "grad_norm": 0.28198346495628357,
      "learning_rate": 0.0002361492994024415,
      "loss": 0.2714,
      "step": 68
    },
    {
      "epoch": 0.609271523178808,
      "grad_norm": 0.26249727606773376,
      "learning_rate": 0.0002341072586027509,
      "loss": 0.2478,
      "step": 69
    },
    {
      "epoch": 0.6181015452538632,
      "grad_norm": 0.2686706781387329,
      "learning_rate": 0.00023204222371836405,
      "loss": 0.2649,
      "step": 70
    },
    {
      "epoch": 0.6269315673289183,
      "grad_norm": 0.2589472234249115,
      "learning_rate": 0.00022995475930919905,
      "loss": 0.247,
      "step": 71
    },
    {
      "epoch": 0.6357615894039735,
      "grad_norm": 0.24519923329353333,
      "learning_rate": 0.00022784543606718227,
      "loss": 0.233,
      "step": 72
    },
    {
      "epoch": 0.6445916114790287,
      "grad_norm": 0.25989893078804016,
      "learning_rate": 0.00022571483066022657,
      "loss": 0.2705,
      "step": 73
    },
    {
      "epoch": 0.6534216335540839,
      "grad_norm": 0.2571690082550049,
      "learning_rate": 0.0002235635255745762,
      "loss": 0.2456,
      "step": 74
    },
    {
      "epoch": 0.6622516556291391,
      "grad_norm": 0.253063440322876,
      "learning_rate": 0.00022139210895556104,
      "loss": 0.182,
      "step": 75
    },
    {
      "epoch": 0.6622516556291391,
      "eval_loss": 0.23765632510185242,
      "eval_runtime": 8.9718,
      "eval_samples_per_second": 5.573,
      "eval_steps_per_second": 0.78,
      "step": 75
    },
    {
      "epoch": 0.6710816777041942,
      "grad_norm": 0.26982638239860535,
      "learning_rate": 0.00021920117444680317,
      "loss": 0.2228,
      "step": 76
    },
    {
      "epoch": 0.6799116997792495,
      "grad_norm": 0.2407388687133789,
      "learning_rate": 0.00021699132102792097,
      "loss": 0.1981,
      "step": 77
    },
    {
      "epoch": 0.6887417218543046,
      "grad_norm": 0.2429220825433731,
      "learning_rate": 0.0002147631528507739,
      "loss": 0.2099,
      "step": 78
    },
    {
      "epoch": 0.6975717439293598,
      "grad_norm": 0.2709774672985077,
      "learning_rate": 0.00021251727907429355,
      "loss": 0.208,
      "step": 79
    },
    {
      "epoch": 0.7064017660044151,
      "grad_norm": 0.2707652747631073,
      "learning_rate": 0.0002102543136979454,
      "loss": 0.2074,
      "step": 80
    },
    {
      "epoch": 0.7152317880794702,
      "grad_norm": 0.34875017404556274,
      "learning_rate": 0.0002079748753938678,
      "loss": 0.2687,
      "step": 81
    },
    {
      "epoch": 0.7240618101545254,
      "grad_norm": 0.3415201008319855,
      "learning_rate": 0.0002056795873377331,
      "loss": 0.2631,
      "step": 82
    },
    {
      "epoch": 0.7328918322295805,
      "grad_norm": 0.40681779384613037,
      "learning_rate": 0.00020336907703837748,
      "loss": 0.2692,
      "step": 83
    },
    {
      "epoch": 0.7417218543046358,
      "grad_norm": 1.7035514116287231,
      "learning_rate": 0.00020104397616624645,
      "loss": 0.6545,
      "step": 84
    },
    {
      "epoch": 0.7505518763796909,
      "grad_norm": 0.29007866978645325,
      "learning_rate": 0.00019870492038070252,
      "loss": 0.3436,
      "step": 85
    },
    {
      "epoch": 0.7593818984547461,
      "grad_norm": 0.28065428137779236,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.299,
      "step": 86
    },
    {
      "epoch": 0.7682119205298014,
      "grad_norm": 0.2473965883255005,
      "learning_rate": 0.0001939875056076697,
      "loss": 0.3076,
      "step": 87
    },
    {
      "epoch": 0.7770419426048565,
      "grad_norm": 0.2542283535003662,
      "learning_rate": 0.00019161043631427666,
      "loss": 0.2815,
      "step": 88
    },
    {
      "epoch": 0.7858719646799117,
      "grad_norm": 0.22185376286506653,
      "learning_rate": 0.00018922199114307294,
      "loss": 0.2297,
      "step": 89
    },
    {
      "epoch": 0.7947019867549668,
      "grad_norm": 0.20742599666118622,
      "learning_rate": 0.00018682282307111987,
      "loss": 0.1853,
      "step": 90
    },
    {
      "epoch": 0.8035320088300221,
      "grad_norm": 0.23171746730804443,
      "learning_rate": 0.00018441358800701273,
      "loss": 0.2454,
      "step": 91
    },
    {
      "epoch": 0.8123620309050773,
      "grad_norm": 0.2426079958677292,
      "learning_rate": 0.00018199494461156203,
      "loss": 0.1993,
      "step": 92
    },
    {
      "epoch": 0.8211920529801324,
      "grad_norm": 0.26155412197113037,
      "learning_rate": 0.000179567554117722,
      "loss": 0.2489,
      "step": 93
    },
    {
      "epoch": 0.8300220750551877,
      "grad_norm": 0.25975102186203003,
      "learning_rate": 0.00017713208014981648,
      "loss": 0.2235,
      "step": 94
    },
    {
      "epoch": 0.8388520971302428,
      "grad_norm": 0.2326008379459381,
      "learning_rate": 0.00017468918854211007,
      "loss": 0.2288,
      "step": 95
    },
    {
      "epoch": 0.847682119205298,
      "grad_norm": 0.24007712304592133,
      "learning_rate": 0.00017223954715677627,
      "loss": 0.2236,
      "step": 96
    },
    {
      "epoch": 0.8565121412803532,
      "grad_norm": 0.24881809949874878,
      "learning_rate": 0.00016978382570131034,
      "loss": 0.2407,
      "step": 97
    },
    {
      "epoch": 0.8653421633554084,
      "grad_norm": 0.25319480895996094,
      "learning_rate": 0.00016732269554543794,
      "loss": 0.2066,
      "step": 98
    },
    {
      "epoch": 0.8741721854304636,
      "grad_norm": 0.24012450873851776,
      "learning_rate": 0.00016485682953756942,
      "loss": 0.2191,
      "step": 99
    },
    {
      "epoch": 0.8830022075055187,
      "grad_norm": 0.23768042027950287,
      "learning_rate": 0.00016238690182084986,
      "loss": 0.2296,
      "step": 100
    },
    {
      "epoch": 0.8830022075055187,
      "eval_loss": 0.22028179466724396,
      "eval_runtime": 8.4215,
      "eval_samples_per_second": 5.937,
      "eval_steps_per_second": 0.831,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2.2189384971740774e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}