{
  "best_metric": 7.306600570678711,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.026897989375294196,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00026897989375294196,
      "grad_norm": 14.062777519226074,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 9.9528,
      "step": 1
    },
    {
      "epoch": 0.00026897989375294196,
      "eval_loss": 10.383614540100098,
      "eval_runtime": 1.103,
      "eval_samples_per_second": 45.331,
      "eval_steps_per_second": 6.346,
      "step": 1
    },
    {
      "epoch": 0.0005379597875058839,
      "grad_norm": 9.013472557067871,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 10.4374,
      "step": 2
    },
    {
      "epoch": 0.0008069396812588259,
      "grad_norm": 9.113578796386719,
      "learning_rate": 8.999999999999999e-05,
      "loss": 10.5416,
      "step": 3
    },
    {
      "epoch": 0.0010759195750117679,
      "grad_norm": 9.272452354431152,
      "learning_rate": 0.00011999999999999999,
      "loss": 10.5582,
      "step": 4
    },
    {
      "epoch": 0.0013448994687647099,
      "grad_norm": 9.502043724060059,
      "learning_rate": 0.00015,
      "loss": 10.4131,
      "step": 5
    },
    {
      "epoch": 0.0016138793625176519,
      "grad_norm": 12.628140449523926,
      "learning_rate": 0.00017999999999999998,
      "loss": 9.5481,
      "step": 6
    },
    {
      "epoch": 0.0018828592562705937,
      "grad_norm": 10.771757125854492,
      "learning_rate": 0.00020999999999999998,
      "loss": 9.7362,
      "step": 7
    },
    {
      "epoch": 0.0021518391500235357,
      "grad_norm": 8.7677640914917,
      "learning_rate": 0.00023999999999999998,
      "loss": 9.394,
      "step": 8
    },
    {
      "epoch": 0.0024208190437764775,
      "grad_norm": 9.826272010803223,
      "learning_rate": 0.00027,
      "loss": 8.7301,
      "step": 9
    },
    {
      "epoch": 0.0026897989375294197,
      "grad_norm": 8.201698303222656,
      "learning_rate": 0.0003,
      "loss": 8.4353,
      "step": 10
    },
    {
      "epoch": 0.0029587788312823615,
      "grad_norm": 6.270658493041992,
      "learning_rate": 0.0002999794957488703,
      "loss": 7.7853,
      "step": 11
    },
    {
      "epoch": 0.0032277587250353038,
      "grad_norm": 5.651599884033203,
      "learning_rate": 0.0002999179886011389,
      "loss": 7.7574,
      "step": 12
    },
    {
      "epoch": 0.0034967386187882456,
      "grad_norm": 3.6305131912231445,
      "learning_rate": 0.0002998154953722457,
      "loss": 7.9822,
      "step": 13
    },
    {
      "epoch": 0.0037657185125411874,
      "grad_norm": 3.2104008197784424,
      "learning_rate": 0.00029967204408281613,
      "loss": 8.3468,
      "step": 14
    },
    {
      "epoch": 0.004034698406294129,
      "grad_norm": 2.4810068607330322,
      "learning_rate": 0.00029948767395100045,
      "loss": 8.2438,
      "step": 15
    },
    {
      "epoch": 0.004303678300047071,
      "grad_norm": 2.427516460418701,
      "learning_rate": 0.0002992624353817517,
      "loss": 8.4045,
      "step": 16
    },
    {
      "epoch": 0.004572658193800014,
      "grad_norm": 1.9261265993118286,
      "learning_rate": 0.0002989963899530457,
      "loss": 7.9577,
      "step": 17
    },
    {
      "epoch": 0.004841638087552955,
      "grad_norm": 2.021862268447876,
      "learning_rate": 0.00029868961039904624,
      "loss": 8.1164,
      "step": 18
    },
    {
      "epoch": 0.005110617981305897,
      "grad_norm": 2.315554141998291,
      "learning_rate": 0.00029834218059022024,
      "loss": 8.1393,
      "step": 19
    },
    {
      "epoch": 0.0053795978750588395,
      "grad_norm": 2.343036651611328,
      "learning_rate": 0.00029795419551040833,
      "loss": 7.8621,
      "step": 20
    },
    {
      "epoch": 0.005648577768811782,
      "grad_norm": 1.6685760021209717,
      "learning_rate": 0.00029752576123085736,
      "loss": 7.6249,
      "step": 21
    },
    {
      "epoch": 0.005917557662564723,
      "grad_norm": 1.617172360420227,
      "learning_rate": 0.0002970569948812214,
      "loss": 7.8443,
      "step": 22
    },
    {
      "epoch": 0.006186537556317665,
      "grad_norm": 1.611405611038208,
      "learning_rate": 0.0002965480246175399,
      "loss": 7.1947,
      "step": 23
    },
    {
      "epoch": 0.0064555174500706075,
      "grad_norm": 1.3807909488677979,
      "learning_rate": 0.0002959989895872009,
      "loss": 7.7691,
      "step": 24
    },
    {
      "epoch": 0.006724497343823549,
      "grad_norm": 1.8649704456329346,
      "learning_rate": 0.0002954100398908995,
      "loss": 7.6449,
      "step": 25
    },
    {
      "epoch": 0.006724497343823549,
      "eval_loss": 7.789085865020752,
      "eval_runtime": 1.1023,
      "eval_samples_per_second": 45.359,
      "eval_steps_per_second": 6.35,
      "step": 25
    },
    {
      "epoch": 0.006993477237576491,
      "grad_norm": 1.826485276222229,
      "learning_rate": 0.0002947813365416023,
      "loss": 7.775,
      "step": 26
    },
    {
      "epoch": 0.007262457131329433,
      "grad_norm": 2.0122640132904053,
      "learning_rate": 0.0002941130514205272,
      "loss": 7.4112,
      "step": 27
    },
    {
      "epoch": 0.007531437025082375,
      "grad_norm": 1.474570870399475,
      "learning_rate": 0.0002934053672301536,
      "loss": 7.605,
      "step": 28
    },
    {
      "epoch": 0.007800416918835317,
      "grad_norm": 1.2456080913543701,
      "learning_rate": 0.00029265847744427303,
      "loss": 7.615,
      "step": 29
    },
    {
      "epoch": 0.008069396812588258,
      "grad_norm": 1.3614413738250732,
      "learning_rate": 0.00029187258625509513,
      "loss": 7.1255,
      "step": 30
    },
    {
      "epoch": 0.0083383767063412,
      "grad_norm": 1.5178754329681396,
      "learning_rate": 0.00029104790851742417,
      "loss": 7.3523,
      "step": 31
    },
    {
      "epoch": 0.008607356600094143,
      "grad_norm": 1.0982545614242554,
      "learning_rate": 0.0002901846696899191,
      "loss": 7.2886,
      "step": 32
    },
    {
      "epoch": 0.008876336493847085,
      "grad_norm": 0.9949588775634766,
      "learning_rate": 0.00028928310577345606,
      "loss": 7.705,
      "step": 33
    },
    {
      "epoch": 0.009145316387600027,
      "grad_norm": 1.0565680265426636,
      "learning_rate": 0.0002883434632466077,
      "loss": 7.054,
      "step": 34
    },
    {
      "epoch": 0.00941429628135297,
      "grad_norm": 1.4660252332687378,
      "learning_rate": 0.00028736599899825856,
      "loss": 6.5231,
      "step": 35
    },
    {
      "epoch": 0.00968327617510591,
      "grad_norm": 1.0093355178833008,
      "learning_rate": 0.00028635098025737434,
      "loss": 7.4915,
      "step": 36
    },
    {
      "epoch": 0.009952256068858852,
      "grad_norm": 1.0597023963928223,
      "learning_rate": 0.00028529868451994384,
      "loss": 7.5809,
      "step": 37
    },
    {
      "epoch": 0.010221235962611794,
      "grad_norm": 1.0300654172897339,
      "learning_rate": 0.0002842093994731145,
      "loss": 7.4441,
      "step": 38
    },
    {
      "epoch": 0.010490215856364737,
      "grad_norm": 1.0486762523651123,
      "learning_rate": 0.00028308342291654174,
      "loss": 6.7324,
      "step": 39
    },
    {
      "epoch": 0.010759195750117679,
      "grad_norm": 0.9966297149658203,
      "learning_rate": 0.00028192106268097334,
      "loss": 7.7486,
      "step": 40
    },
    {
      "epoch": 0.011028175643870621,
      "grad_norm": 0.8546872735023499,
      "learning_rate": 0.00028072263654409154,
      "loss": 6.9361,
      "step": 41
    },
    {
      "epoch": 0.011297155537623563,
      "grad_norm": 0.9719182252883911,
      "learning_rate": 0.0002794884721436361,
      "loss": 7.2164,
      "step": 42
    },
    {
      "epoch": 0.011566135431376504,
      "grad_norm": 1.2323123216629028,
      "learning_rate": 0.00027821890688783083,
      "loss": 6.7995,
      "step": 43
    },
    {
      "epoch": 0.011835115325129446,
      "grad_norm": 1.016748070716858,
      "learning_rate": 0.0002769142878631403,
      "loss": 7.3677,
      "step": 44
    },
    {
      "epoch": 0.012104095218882388,
      "grad_norm": 0.9493099451065063,
      "learning_rate": 0.00027557497173937923,
      "loss": 6.8809,
      "step": 45
    },
    {
      "epoch": 0.01237307511263533,
      "grad_norm": 0.6532073020935059,
      "learning_rate": 0.000274201324672203,
      "loss": 6.9965,
      "step": 46
    },
    {
      "epoch": 0.012642055006388273,
      "grad_norm": 1.0315707921981812,
      "learning_rate": 0.00027279372220300385,
      "loss": 7.3371,
      "step": 47
    },
    {
      "epoch": 0.012911034900141215,
      "grad_norm": 0.867978036403656,
      "learning_rate": 0.0002713525491562421,
      "loss": 7.2436,
      "step": 48
    },
    {
      "epoch": 0.013180014793894156,
      "grad_norm": 0.8053029775619507,
      "learning_rate": 0.00026987819953423867,
      "loss": 6.8425,
      "step": 49
    },
    {
      "epoch": 0.013448994687647098,
      "grad_norm": 1.2040008306503296,
      "learning_rate": 0.00026837107640945905,
      "loss": 6.9863,
      "step": 50
    },
    {
      "epoch": 0.013448994687647098,
      "eval_loss": 7.4686126708984375,
      "eval_runtime": 1.1025,
      "eval_samples_per_second": 45.352,
      "eval_steps_per_second": 6.349,
      "step": 50
    },
    {
      "epoch": 0.01371797458140004,
      "grad_norm": 2.073488235473633,
      "learning_rate": 0.0002668315918143169,
      "loss": 6.6067,
      "step": 51
    },
    {
      "epoch": 0.013986954475152982,
      "grad_norm": 1.6959115266799927,
      "learning_rate": 0.00026526016662852886,
      "loss": 7.4615,
      "step": 52
    },
    {
      "epoch": 0.014255934368905925,
      "grad_norm": 1.1312484741210938,
      "learning_rate": 0.00026365723046405023,
      "loss": 7.562,
      "step": 53
    },
    {
      "epoch": 0.014524914262658867,
      "grad_norm": 0.8906031847000122,
      "learning_rate": 0.0002620232215476231,
      "loss": 7.8548,
      "step": 54
    },
    {
      "epoch": 0.014793894156411809,
      "grad_norm": 1.1955941915512085,
      "learning_rate": 0.0002603585866009697,
      "loss": 7.5388,
      "step": 55
    },
    {
      "epoch": 0.01506287405016475,
      "grad_norm": 1.6056780815124512,
      "learning_rate": 0.00025866378071866334,
      "loss": 6.7458,
      "step": 56
    },
    {
      "epoch": 0.015331853943917692,
      "grad_norm": 0.9653465151786804,
      "learning_rate": 0.00025693926724370956,
      "loss": 7.2338,
      "step": 57
    },
    {
      "epoch": 0.015600833837670634,
      "grad_norm": 1.055378794670105,
      "learning_rate": 0.00025518551764087326,
      "loss": 7.2497,
      "step": 58
    },
    {
      "epoch": 0.015869813731423574,
      "grad_norm": 0.982029378414154,
      "learning_rate": 0.00025340301136778483,
      "loss": 6.3055,
      "step": 59
    },
    {
      "epoch": 0.016138793625176517,
      "grad_norm": 1.4051647186279297,
      "learning_rate": 0.00025159223574386114,
      "loss": 6.7392,
      "step": 60
    },
    {
      "epoch": 0.01640777351892946,
      "grad_norm": 1.224535346031189,
      "learning_rate": 0.0002497536858170772,
      "loss": 6.2815,
      "step": 61
    },
    {
      "epoch": 0.0166767534126824,
      "grad_norm": 0.9965676069259644,
      "learning_rate": 0.00024788786422862526,
      "loss": 6.5987,
      "step": 62
    },
    {
      "epoch": 0.016945733306435343,
      "grad_norm": 0.7063784599304199,
      "learning_rate": 0.00024599528107549745,
      "loss": 6.5176,
      "step": 63
    },
    {
      "epoch": 0.017214713200188286,
      "grad_norm": 1.3905584812164307,
      "learning_rate": 0.00024407645377103054,
      "loss": 7.3527,
      "step": 64
    },
    {
      "epoch": 0.017483693093941228,
      "grad_norm": 0.6794236898422241,
      "learning_rate": 0.00024213190690345018,
      "loss": 7.1635,
      "step": 65
    },
    {
      "epoch": 0.01775267298769417,
      "grad_norm": 0.85134357213974,
      "learning_rate": 0.00024016217209245374,
      "loss": 6.9162,
      "step": 66
    },
    {
      "epoch": 0.018021652881447112,
      "grad_norm": 1.1831365823745728,
      "learning_rate": 0.00023816778784387094,
      "loss": 7.4826,
      "step": 67
    },
    {
      "epoch": 0.018290632775200055,
      "grad_norm": 0.7540268301963806,
      "learning_rate": 0.0002361492994024415,
      "loss": 7.5541,
      "step": 68
    },
    {
      "epoch": 0.018559612668952997,
      "grad_norm": 0.8305040597915649,
      "learning_rate": 0.0002341072586027509,
      "loss": 7.0236,
      "step": 69
    },
    {
      "epoch": 0.01882859256270594,
      "grad_norm": 0.8232185244560242,
      "learning_rate": 0.00023204222371836405,
      "loss": 7.256,
      "step": 70
    },
    {
      "epoch": 0.01909757245645888,
      "grad_norm": 0.8017435669898987,
      "learning_rate": 0.00022995475930919905,
      "loss": 7.2468,
      "step": 71
    },
    {
      "epoch": 0.01936655235021182,
      "grad_norm": 0.7299101948738098,
      "learning_rate": 0.00022784543606718227,
      "loss": 6.8815,
      "step": 72
    },
    {
      "epoch": 0.019635532243964762,
      "grad_norm": 0.9603165984153748,
      "learning_rate": 0.00022571483066022657,
      "loss": 7.1806,
      "step": 73
    },
    {
      "epoch": 0.019904512137717705,
      "grad_norm": 0.7412318587303162,
      "learning_rate": 0.0002235635255745762,
      "loss": 6.8687,
      "step": 74
    },
    {
      "epoch": 0.020173492031470647,
      "grad_norm": 1.5883235931396484,
      "learning_rate": 0.00022139210895556104,
      "loss": 6.6477,
      "step": 75
    },
    {
      "epoch": 0.020173492031470647,
      "eval_loss": 7.266612529754639,
      "eval_runtime": 1.1026,
      "eval_samples_per_second": 45.347,
      "eval_steps_per_second": 6.349,
      "step": 75
    },
    {
      "epoch": 0.02044247192522359,
      "grad_norm": 0.874472975730896,
      "learning_rate": 0.00021920117444680317,
      "loss": 6.5988,
      "step": 76
    },
    {
      "epoch": 0.02071145181897653,
      "grad_norm": 1.0724687576293945,
      "learning_rate": 0.00021699132102792097,
      "loss": 7.0543,
      "step": 77
    },
    {
      "epoch": 0.020980431712729473,
      "grad_norm": 0.7699567079544067,
      "learning_rate": 0.0002147631528507739,
      "loss": 7.1625,
      "step": 78
    },
    {
      "epoch": 0.021249411606482416,
      "grad_norm": 0.622986912727356,
      "learning_rate": 0.00021251727907429355,
      "loss": 7.4872,
      "step": 79
    },
    {
      "epoch": 0.021518391500235358,
      "grad_norm": 0.9322075843811035,
      "learning_rate": 0.0002102543136979454,
      "loss": 7.0894,
      "step": 80
    },
    {
      "epoch": 0.0217873713939883,
      "grad_norm": 0.6225010752677917,
      "learning_rate": 0.0002079748753938678,
      "loss": 6.9691,
      "step": 81
    },
    {
      "epoch": 0.022056351287741242,
      "grad_norm": 0.9002844095230103,
      "learning_rate": 0.0002056795873377331,
      "loss": 6.5822,
      "step": 82
    },
    {
      "epoch": 0.022325331181494185,
      "grad_norm": 0.6348511576652527,
      "learning_rate": 0.00020336907703837748,
      "loss": 6.8699,
      "step": 83
    },
    {
      "epoch": 0.022594311075247127,
      "grad_norm": 0.5231301188468933,
      "learning_rate": 0.00020104397616624645,
      "loss": 6.8725,
      "step": 84
    },
    {
      "epoch": 0.022863290969000066,
      "grad_norm": 0.68709397315979,
      "learning_rate": 0.00019870492038070252,
      "loss": 6.7312,
      "step": 85
    },
    {
      "epoch": 0.023132270862753008,
      "grad_norm": 0.47030457854270935,
      "learning_rate": 0.0001963525491562421,
      "loss": 6.7572,
      "step": 86
    },
    {
      "epoch": 0.02340125075650595,
      "grad_norm": 0.7477748394012451,
      "learning_rate": 0.0001939875056076697,
      "loss": 7.014,
      "step": 87
    },
    {
      "epoch": 0.023670230650258892,
      "grad_norm": 0.9135372638702393,
      "learning_rate": 0.00019161043631427666,
      "loss": 6.8656,
      "step": 88
    },
    {
      "epoch": 0.023939210544011835,
      "grad_norm": 0.7729247212409973,
      "learning_rate": 0.00018922199114307294,
      "loss": 6.8811,
      "step": 89
    },
    {
      "epoch": 0.024208190437764777,
      "grad_norm": 0.8843768835067749,
      "learning_rate": 0.00018682282307111987,
      "loss": 6.8623,
      "step": 90
    },
    {
      "epoch": 0.02447717033151772,
      "grad_norm": 0.5804451107978821,
      "learning_rate": 0.00018441358800701273,
      "loss": 6.8921,
      "step": 91
    },
    {
      "epoch": 0.02474615022527066,
      "grad_norm": 0.9439037442207336,
      "learning_rate": 0.00018199494461156203,
      "loss": 7.4667,
      "step": 92
    },
    {
      "epoch": 0.025015130119023603,
      "grad_norm": 0.6652296185493469,
      "learning_rate": 0.000179567554117722,
      "loss": 7.1213,
      "step": 93
    },
    {
      "epoch": 0.025284110012776546,
      "grad_norm": 0.9313641786575317,
      "learning_rate": 0.00017713208014981648,
      "loss": 6.9055,
      "step": 94
    },
    {
      "epoch": 0.025553089906529488,
      "grad_norm": 0.5718141198158264,
      "learning_rate": 0.00017468918854211007,
      "loss": 7.4156,
      "step": 95
    },
    {
      "epoch": 0.02582206980028243,
      "grad_norm": 0.90057772397995,
      "learning_rate": 0.00017223954715677627,
      "loss": 7.0547,
      "step": 96
    },
    {
      "epoch": 0.026091049694035372,
      "grad_norm": 0.8088359236717224,
      "learning_rate": 0.00016978382570131034,
      "loss": 6.8638,
      "step": 97
    },
    {
      "epoch": 0.02636002958778831,
      "grad_norm": 0.7129319310188293,
      "learning_rate": 0.00016732269554543794,
      "loss": 7.0757,
      "step": 98
    },
    {
      "epoch": 0.026629009481541253,
      "grad_norm": 0.7212324142456055,
      "learning_rate": 0.00016485682953756942,
      "loss": 7.3563,
      "step": 99
    },
    {
      "epoch": 0.026897989375294196,
      "grad_norm": 1.3920371532440186,
      "learning_rate": 0.00016238690182084986,
      "loss": 7.3419,
      "step": 100
    },
    {
      "epoch": 0.026897989375294196,
      "eval_loss": 7.306600570678711,
      "eval_runtime": 1.1005,
      "eval_samples_per_second": 45.435,
      "eval_steps_per_second": 6.361,
      "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": 87404486197248.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}