{
  "best_metric": 11.915943145751953,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.04142609326049245,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004142609326049245,
      "grad_norm": 0.009111136198043823,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 11.9291,
      "step": 1
    },
    {
      "epoch": 0.0004142609326049245,
      "eval_loss": 11.93281364440918,
      "eval_runtime": 0.2456,
      "eval_samples_per_second": 203.617,
      "eval_steps_per_second": 28.506,
      "step": 1
    },
    {
      "epoch": 0.000828521865209849,
      "grad_norm": 0.01578676700592041,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 11.9311,
      "step": 2
    },
    {
      "epoch": 0.0012427827978147737,
      "grad_norm": 0.010788201354444027,
      "learning_rate": 8.999999999999999e-05,
      "loss": 11.9303,
      "step": 3
    },
    {
      "epoch": 0.001657043730419698,
      "grad_norm": 0.014519501477479935,
      "learning_rate": 0.00011999999999999999,
      "loss": 11.9288,
      "step": 4
    },
    {
      "epoch": 0.0020713046630246226,
      "grad_norm": 0.01510781329125166,
      "learning_rate": 0.00015,
      "loss": 11.9304,
      "step": 5
    },
    {
      "epoch": 0.0024855655956295473,
      "grad_norm": 0.013269297778606415,
      "learning_rate": 0.00017999999999999998,
      "loss": 11.9294,
      "step": 6
    },
    {
      "epoch": 0.0028998265282344717,
      "grad_norm": 0.013751151971518993,
      "learning_rate": 0.00020999999999999998,
      "loss": 11.9321,
      "step": 7
    },
    {
      "epoch": 0.003314087460839396,
      "grad_norm": 0.015573951415717602,
      "learning_rate": 0.00023999999999999998,
      "loss": 11.9287,
      "step": 8
    },
    {
      "epoch": 0.0037283483934443208,
      "grad_norm": 0.009504775516688824,
      "learning_rate": 0.00027,
      "loss": 11.9305,
      "step": 9
    },
    {
      "epoch": 0.004142609326049245,
      "grad_norm": 0.010801173746585846,
      "learning_rate": 0.0003,
      "loss": 11.9337,
      "step": 10
    },
    {
      "epoch": 0.0045568702586541695,
      "grad_norm": 0.011178042739629745,
      "learning_rate": 0.0002999794957488703,
      "loss": 11.9278,
      "step": 11
    },
    {
      "epoch": 0.004971131191259095,
      "grad_norm": 0.014659388922154903,
      "learning_rate": 0.0002999179886011389,
      "loss": 11.9297,
      "step": 12
    },
    {
      "epoch": 0.005385392123864019,
      "grad_norm": 0.013904299587011337,
      "learning_rate": 0.0002998154953722457,
      "loss": 11.9315,
      "step": 13
    },
    {
      "epoch": 0.005799653056468943,
      "grad_norm": 0.014901366084814072,
      "learning_rate": 0.00029967204408281613,
      "loss": 11.9306,
      "step": 14
    },
    {
      "epoch": 0.006213913989073868,
      "grad_norm": 0.014373673126101494,
      "learning_rate": 0.00029948767395100045,
      "loss": 11.9291,
      "step": 15
    },
    {
      "epoch": 0.006628174921678792,
      "grad_norm": 0.012232257053256035,
      "learning_rate": 0.0002992624353817517,
      "loss": 11.9292,
      "step": 16
    },
    {
      "epoch": 0.007042435854283717,
      "grad_norm": 0.011413573287427425,
      "learning_rate": 0.0002989963899530457,
      "loss": 11.9322,
      "step": 17
    },
    {
      "epoch": 0.0074566967868886416,
      "grad_norm": 0.016656706109642982,
      "learning_rate": 0.00029868961039904624,
      "loss": 11.9324,
      "step": 18
    },
    {
      "epoch": 0.007870957719493567,
      "grad_norm": 0.014373266138136387,
      "learning_rate": 0.00029834218059022024,
      "loss": 11.9318,
      "step": 19
    },
    {
      "epoch": 0.00828521865209849,
      "grad_norm": 0.015115369111299515,
      "learning_rate": 0.00029795419551040833,
      "loss": 11.9287,
      "step": 20
    },
    {
      "epoch": 0.008699479584703415,
      "grad_norm": 0.01734703592956066,
      "learning_rate": 0.00029752576123085736,
      "loss": 11.9309,
      "step": 21
    },
    {
      "epoch": 0.009113740517308339,
      "grad_norm": 0.014644989743828773,
      "learning_rate": 0.0002970569948812214,
      "loss": 11.9254,
      "step": 22
    },
    {
      "epoch": 0.009528001449913264,
      "grad_norm": 0.021497027948498726,
      "learning_rate": 0.0002965480246175399,
      "loss": 11.9302,
      "step": 23
    },
    {
      "epoch": 0.00994226238251819,
      "grad_norm": 0.01817285642027855,
      "learning_rate": 0.0002959989895872009,
      "loss": 11.9312,
      "step": 24
    },
    {
      "epoch": 0.010356523315123113,
      "grad_norm": 0.02207845263183117,
      "learning_rate": 0.0002954100398908995,
      "loss": 11.9284,
      "step": 25
    },
    {
      "epoch": 0.010356523315123113,
      "eval_loss": 11.93165397644043,
      "eval_runtime": 0.2441,
      "eval_samples_per_second": 204.847,
      "eval_steps_per_second": 28.679,
      "step": 25
    },
    {
      "epoch": 0.010770784247728038,
      "grad_norm": 0.017103340476751328,
      "learning_rate": 0.0002947813365416023,
      "loss": 11.9297,
      "step": 26
    },
    {
      "epoch": 0.011185045180332961,
      "grad_norm": 0.0265261959284544,
      "learning_rate": 0.0002941130514205272,
      "loss": 11.9303,
      "step": 27
    },
    {
      "epoch": 0.011599306112937887,
      "grad_norm": 0.031121160835027695,
      "learning_rate": 0.0002934053672301536,
      "loss": 11.9264,
      "step": 28
    },
    {
      "epoch": 0.012013567045542812,
      "grad_norm": 0.020733291283249855,
      "learning_rate": 0.00029265847744427303,
      "loss": 11.9311,
      "step": 29
    },
    {
      "epoch": 0.012427827978147735,
      "grad_norm": 0.019345130771398544,
      "learning_rate": 0.00029187258625509513,
      "loss": 11.9295,
      "step": 30
    },
    {
      "epoch": 0.01284208891075266,
      "grad_norm": 0.025070849806070328,
      "learning_rate": 0.00029104790851742417,
      "loss": 11.9307,
      "step": 31
    },
    {
      "epoch": 0.013256349843357584,
      "grad_norm": 0.02109096758067608,
      "learning_rate": 0.0002901846696899191,
      "loss": 11.927,
      "step": 32
    },
    {
      "epoch": 0.01367061077596251,
      "grad_norm": 0.027676530182361603,
      "learning_rate": 0.00028928310577345606,
      "loss": 11.9296,
      "step": 33
    },
    {
      "epoch": 0.014084871708567434,
      "grad_norm": 0.02774973399937153,
      "learning_rate": 0.0002883434632466077,
      "loss": 11.9294,
      "step": 34
    },
    {
      "epoch": 0.014499132641172358,
      "grad_norm": 0.026240255683660507,
      "learning_rate": 0.00028736599899825856,
      "loss": 11.9283,
      "step": 35
    },
    {
      "epoch": 0.014913393573777283,
      "grad_norm": 0.03300342708826065,
      "learning_rate": 0.00028635098025737434,
      "loss": 11.9277,
      "step": 36
    },
    {
      "epoch": 0.015327654506382208,
      "grad_norm": 0.03084516152739525,
      "learning_rate": 0.00028529868451994384,
      "loss": 11.9284,
      "step": 37
    },
    {
      "epoch": 0.015741915438987134,
      "grad_norm": 0.03772755712270737,
      "learning_rate": 0.0002842093994731145,
      "loss": 11.9301,
      "step": 38
    },
    {
      "epoch": 0.016156176371592057,
      "grad_norm": 0.044647328555583954,
      "learning_rate": 0.00028308342291654174,
      "loss": 11.929,
      "step": 39
    },
    {
      "epoch": 0.01657043730419698,
      "grad_norm": 0.0458788201212883,
      "learning_rate": 0.00028192106268097334,
      "loss": 11.9261,
      "step": 40
    },
    {
      "epoch": 0.016984698236801904,
      "grad_norm": 0.062342319637537,
      "learning_rate": 0.00028072263654409154,
      "loss": 11.9292,
      "step": 41
    },
    {
      "epoch": 0.01739895916940683,
      "grad_norm": 0.04045253247022629,
      "learning_rate": 0.0002794884721436361,
      "loss": 11.9276,
      "step": 42
    },
    {
      "epoch": 0.017813220102011754,
      "grad_norm": 0.05095702409744263,
      "learning_rate": 0.00027821890688783083,
      "loss": 11.9244,
      "step": 43
    },
    {
      "epoch": 0.018227481034616678,
      "grad_norm": 0.04911315068602562,
      "learning_rate": 0.0002769142878631403,
      "loss": 11.9264,
      "step": 44
    },
    {
      "epoch": 0.018641741967221605,
      "grad_norm": 0.04607488214969635,
      "learning_rate": 0.00027557497173937923,
      "loss": 11.9244,
      "step": 45
    },
    {
      "epoch": 0.019056002899826528,
      "grad_norm": 0.05658293142914772,
      "learning_rate": 0.000274201324672203,
      "loss": 11.9224,
      "step": 46
    },
    {
      "epoch": 0.01947026383243145,
      "grad_norm": 0.050977252423763275,
      "learning_rate": 0.00027279372220300385,
      "loss": 11.9255,
      "step": 47
    },
    {
      "epoch": 0.01988452476503638,
      "grad_norm": 0.06175487861037254,
      "learning_rate": 0.0002713525491562421,
      "loss": 11.9218,
      "step": 48
    },
    {
      "epoch": 0.020298785697641302,
      "grad_norm": 0.049341753125190735,
      "learning_rate": 0.00026987819953423867,
      "loss": 11.927,
      "step": 49
    },
    {
      "epoch": 0.020713046630246226,
      "grad_norm": 0.0748741626739502,
      "learning_rate": 0.00026837107640945905,
      "loss": 11.9258,
      "step": 50
    },
    {
      "epoch": 0.020713046630246226,
      "eval_loss": 11.926169395446777,
      "eval_runtime": 0.2445,
      "eval_samples_per_second": 204.526,
      "eval_steps_per_second": 28.634,
      "step": 50
    },
    {
      "epoch": 0.021127307562851153,
      "grad_norm": 0.06076189503073692,
      "learning_rate": 0.0002668315918143169,
      "loss": 11.9242,
      "step": 51
    },
    {
      "epoch": 0.021541568495456076,
      "grad_norm": 0.0622175894677639,
      "learning_rate": 0.00026526016662852886,
      "loss": 11.9228,
      "step": 52
    },
    {
      "epoch": 0.021955829428061,
      "grad_norm": 0.05812002345919609,
      "learning_rate": 0.00026365723046405023,
      "loss": 11.9241,
      "step": 53
    },
    {
      "epoch": 0.022370090360665923,
      "grad_norm": 0.05627156049013138,
      "learning_rate": 0.0002620232215476231,
      "loss": 11.9206,
      "step": 54
    },
    {
      "epoch": 0.02278435129327085,
      "grad_norm": 0.04959167540073395,
      "learning_rate": 0.0002603585866009697,
      "loss": 11.9216,
      "step": 55
    },
    {
      "epoch": 0.023198612225875773,
      "grad_norm": 0.05402550846338272,
      "learning_rate": 0.00025866378071866334,
      "loss": 11.9216,
      "step": 56
    },
    {
      "epoch": 0.023612873158480697,
      "grad_norm": 0.049663037061691284,
      "learning_rate": 0.00025693926724370956,
      "loss": 11.9207,
      "step": 57
    },
    {
      "epoch": 0.024027134091085624,
      "grad_norm": 0.045585885643959045,
      "learning_rate": 0.00025518551764087326,
      "loss": 11.9232,
      "step": 58
    },
    {
      "epoch": 0.024441395023690547,
      "grad_norm": 0.05635461211204529,
      "learning_rate": 0.00025340301136778483,
      "loss": 11.922,
      "step": 59
    },
    {
      "epoch": 0.02485565595629547,
      "grad_norm": 0.05952185392379761,
      "learning_rate": 0.00025159223574386114,
      "loss": 11.9209,
      "step": 60
    },
    {
      "epoch": 0.025269916888900398,
      "grad_norm": 0.04048493504524231,
      "learning_rate": 0.0002497536858170772,
      "loss": 11.9213,
      "step": 61
    },
    {
      "epoch": 0.02568417782150532,
      "grad_norm": 0.050521329045295715,
      "learning_rate": 0.00024788786422862526,
      "loss": 11.9192,
      "step": 62
    },
    {
      "epoch": 0.026098438754110245,
      "grad_norm": 0.043353911489248276,
      "learning_rate": 0.00024599528107549745,
      "loss": 11.9202,
      "step": 63
    },
    {
      "epoch": 0.026512699686715168,
      "grad_norm": 0.0434187576174736,
      "learning_rate": 0.00024407645377103054,
      "loss": 11.9171,
      "step": 64
    },
    {
      "epoch": 0.026926960619320095,
      "grad_norm": 0.0419292189180851,
      "learning_rate": 0.00024213190690345018,
      "loss": 11.9196,
      "step": 65
    },
    {
      "epoch": 0.02734122155192502,
      "grad_norm": 0.04601728916168213,
      "learning_rate": 0.00024016217209245374,
      "loss": 11.9174,
      "step": 66
    },
    {
      "epoch": 0.027755482484529942,
      "grad_norm": 0.047061558812856674,
      "learning_rate": 0.00023816778784387094,
      "loss": 11.9189,
      "step": 67
    },
    {
      "epoch": 0.02816974341713487,
      "grad_norm": 0.039436087012290955,
      "learning_rate": 0.0002361492994024415,
      "loss": 11.9178,
      "step": 68
    },
    {
      "epoch": 0.028584004349739792,
      "grad_norm": 0.03027687780559063,
      "learning_rate": 0.0002341072586027509,
      "loss": 11.9175,
      "step": 69
    },
    {
      "epoch": 0.028998265282344716,
      "grad_norm": 0.03565209358930588,
      "learning_rate": 0.00023204222371836405,
      "loss": 11.9168,
      "step": 70
    },
    {
      "epoch": 0.029412526214949643,
      "grad_norm": 0.02530493400990963,
      "learning_rate": 0.00022995475930919905,
      "loss": 11.9163,
      "step": 71
    },
    {
      "epoch": 0.029826787147554566,
      "grad_norm": 0.0354970321059227,
      "learning_rate": 0.00022784543606718227,
      "loss": 11.9154,
      "step": 72
    },
    {
      "epoch": 0.03024104808015949,
      "grad_norm": 0.018435046076774597,
      "learning_rate": 0.00022571483066022657,
      "loss": 11.9158,
      "step": 73
    },
    {
      "epoch": 0.030655309012764417,
      "grad_norm": 0.02600877545773983,
      "learning_rate": 0.0002235635255745762,
      "loss": 11.9121,
      "step": 74
    },
    {
      "epoch": 0.03106956994536934,
      "grad_norm": 0.032639019191265106,
      "learning_rate": 0.00022139210895556104,
      "loss": 11.9143,
      "step": 75
    },
    {
      "epoch": 0.03106956994536934,
      "eval_loss": 11.916912078857422,
      "eval_runtime": 0.2447,
      "eval_samples_per_second": 204.352,
      "eval_steps_per_second": 28.609,
      "step": 75
    },
    {
      "epoch": 0.03148383087797427,
      "grad_norm": 0.026764797046780586,
      "learning_rate": 0.00021920117444680317,
      "loss": 11.9196,
      "step": 76
    },
    {
      "epoch": 0.03189809181057919,
      "grad_norm": 0.0315483957529068,
      "learning_rate": 0.00021699132102792097,
      "loss": 11.9159,
      "step": 77
    },
    {
      "epoch": 0.032312352743184114,
      "grad_norm": 0.029291000217199326,
      "learning_rate": 0.0002147631528507739,
      "loss": 11.9156,
      "step": 78
    },
    {
      "epoch": 0.03272661367578904,
      "grad_norm": 0.02186393365263939,
      "learning_rate": 0.00021251727907429355,
      "loss": 11.9126,
      "step": 79
    },
    {
      "epoch": 0.03314087460839396,
      "grad_norm": 0.02193310484290123,
      "learning_rate": 0.0002102543136979454,
      "loss": 11.9144,
      "step": 80
    },
    {
      "epoch": 0.033555135540998884,
      "grad_norm": 0.027057521045207977,
      "learning_rate": 0.0002079748753938678,
      "loss": 11.9136,
      "step": 81
    },
    {
      "epoch": 0.03396939647360381,
      "grad_norm": 0.028718745335936546,
      "learning_rate": 0.0002056795873377331,
      "loss": 11.9155,
      "step": 82
    },
    {
      "epoch": 0.03438365740620874,
      "grad_norm": 0.03541611507534981,
      "learning_rate": 0.00020336907703837748,
      "loss": 11.9161,
      "step": 83
    },
    {
      "epoch": 0.03479791833881366,
      "grad_norm": 0.027952907606959343,
      "learning_rate": 0.00020104397616624645,
      "loss": 11.9165,
      "step": 84
    },
    {
      "epoch": 0.035212179271418585,
      "grad_norm": 0.02944616600871086,
      "learning_rate": 0.00019870492038070252,
      "loss": 11.9162,
      "step": 85
    },
    {
      "epoch": 0.03562644020402351,
      "grad_norm": 0.028091363608837128,
      "learning_rate": 0.0001963525491562421,
      "loss": 11.9145,
      "step": 86
    },
    {
      "epoch": 0.03604070113662843,
      "grad_norm": 0.01949743553996086,
      "learning_rate": 0.0001939875056076697,
      "loss": 11.9126,
      "step": 87
    },
    {
      "epoch": 0.036454962069233356,
      "grad_norm": 0.03287213295698166,
      "learning_rate": 0.00019161043631427666,
      "loss": 11.9162,
      "step": 88
    },
    {
      "epoch": 0.036869223001838286,
      "grad_norm": 0.024355346336960793,
      "learning_rate": 0.00018922199114307294,
      "loss": 11.9142,
      "step": 89
    },
    {
      "epoch": 0.03728348393444321,
      "grad_norm": 0.02432161383330822,
      "learning_rate": 0.00018682282307111987,
      "loss": 11.9123,
      "step": 90
    },
    {
      "epoch": 0.03769774486704813,
      "grad_norm": 0.02186986431479454,
      "learning_rate": 0.00018441358800701273,
      "loss": 11.9155,
      "step": 91
    },
    {
      "epoch": 0.038112005799653056,
      "grad_norm": 0.02595347724854946,
      "learning_rate": 0.00018199494461156203,
      "loss": 11.9145,
      "step": 92
    },
    {
      "epoch": 0.03852626673225798,
      "grad_norm": 0.01945437304675579,
      "learning_rate": 0.000179567554117722,
      "loss": 11.9142,
      "step": 93
    },
    {
      "epoch": 0.0389405276648629,
      "grad_norm": 0.034285496920347214,
      "learning_rate": 0.00017713208014981648,
      "loss": 11.9142,
      "step": 94
    },
    {
      "epoch": 0.03935478859746783,
      "grad_norm": 0.019000215455889702,
      "learning_rate": 0.00017468918854211007,
      "loss": 11.9144,
      "step": 95
    },
    {
      "epoch": 0.03976904953007276,
      "grad_norm": 0.027748456224799156,
      "learning_rate": 0.00017223954715677627,
      "loss": 11.9086,
      "step": 96
    },
    {
      "epoch": 0.04018331046267768,
      "grad_norm": 0.02137632481753826,
      "learning_rate": 0.00016978382570131034,
      "loss": 11.9144,
      "step": 97
    },
    {
      "epoch": 0.040597571395282604,
      "grad_norm": 0.02740846946835518,
      "learning_rate": 0.00016732269554543794,
      "loss": 11.9143,
      "step": 98
    },
    {
      "epoch": 0.04101183232788753,
      "grad_norm": 0.02057352475821972,
      "learning_rate": 0.00016485682953756942,
      "loss": 11.912,
      "step": 99
    },
    {
      "epoch": 0.04142609326049245,
      "grad_norm": 0.036128297448158264,
      "learning_rate": 0.00016238690182084986,
      "loss": 11.9097,
      "step": 100
    },
    {
      "epoch": 0.04142609326049245,
      "eval_loss": 11.915943145751953,
      "eval_runtime": 0.2452,
      "eval_samples_per_second": 203.942,
      "eval_steps_per_second": 28.552,
      "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": 159262310400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}