{
  "best_metric": 11.921294212341309,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.5673758865248227,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005673758865248227,
      "grad_norm": 0.008871576748788357,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 11.9309,
      "step": 1
    },
    {
      "epoch": 0.005673758865248227,
      "eval_loss": 11.931636810302734,
      "eval_runtime": 0.0623,
      "eval_samples_per_second": 802.105,
      "eval_steps_per_second": 32.084,
      "step": 1
    },
    {
      "epoch": 0.011347517730496455,
      "grad_norm": 0.00887356884777546,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 11.9318,
      "step": 2
    },
    {
      "epoch": 0.01702127659574468,
      "grad_norm": 0.008197522722184658,
      "learning_rate": 8.999999999999999e-05,
      "loss": 11.931,
      "step": 3
    },
    {
      "epoch": 0.02269503546099291,
      "grad_norm": 0.009136962704360485,
      "learning_rate": 0.00011999999999999999,
      "loss": 11.9312,
      "step": 4
    },
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 0.00863950327038765,
      "learning_rate": 0.00015,
      "loss": 11.9313,
      "step": 5
    },
    {
      "epoch": 0.03404255319148936,
      "grad_norm": 0.010503701865673065,
      "learning_rate": 0.00017999999999999998,
      "loss": 11.9309,
      "step": 6
    },
    {
      "epoch": 0.03971631205673759,
      "grad_norm": 0.009797968901693821,
      "learning_rate": 0.00020999999999999998,
      "loss": 11.9304,
      "step": 7
    },
    {
      "epoch": 0.04539007092198582,
      "grad_norm": 0.012021354399621487,
      "learning_rate": 0.00023999999999999998,
      "loss": 11.9315,
      "step": 8
    },
    {
      "epoch": 0.05106382978723404,
      "grad_norm": 0.011232552118599415,
      "learning_rate": 0.00027,
      "loss": 11.9305,
      "step": 9
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 0.015392161905765533,
      "learning_rate": 0.0003,
      "loss": 11.9322,
      "step": 10
    },
    {
      "epoch": 0.062411347517730496,
      "grad_norm": 0.01867329329252243,
      "learning_rate": 0.0002999794957488703,
      "loss": 11.9309,
      "step": 11
    },
    {
      "epoch": 0.06808510638297872,
      "grad_norm": 0.02108246646821499,
      "learning_rate": 0.0002999179886011389,
      "loss": 11.9326,
      "step": 12
    },
    {
      "epoch": 0.07375886524822695,
      "grad_norm": 0.010044677183032036,
      "learning_rate": 0.0002998154953722457,
      "loss": 11.9306,
      "step": 13
    },
    {
      "epoch": 0.07943262411347518,
      "grad_norm": 0.011672090739011765,
      "learning_rate": 0.00029967204408281613,
      "loss": 11.9307,
      "step": 14
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 0.011708973906934261,
      "learning_rate": 0.00029948767395100045,
      "loss": 11.9316,
      "step": 15
    },
    {
      "epoch": 0.09078014184397164,
      "grad_norm": 0.015453565865755081,
      "learning_rate": 0.0002992624353817517,
      "loss": 11.9305,
      "step": 16
    },
    {
      "epoch": 0.09645390070921986,
      "grad_norm": 0.015091469511389732,
      "learning_rate": 0.0002989963899530457,
      "loss": 11.9317,
      "step": 17
    },
    {
      "epoch": 0.10212765957446808,
      "grad_norm": 0.018384767696261406,
      "learning_rate": 0.00029868961039904624,
      "loss": 11.93,
      "step": 18
    },
    {
      "epoch": 0.10780141843971631,
      "grad_norm": 0.021163498982787132,
      "learning_rate": 0.00029834218059022024,
      "loss": 11.9306,
      "step": 19
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 0.02513609640300274,
      "learning_rate": 0.00029795419551040833,
      "loss": 11.93,
      "step": 20
    },
    {
      "epoch": 0.11914893617021277,
      "grad_norm": 0.021745305508375168,
      "learning_rate": 0.00029752576123085736,
      "loss": 11.9316,
      "step": 21
    },
    {
      "epoch": 0.12482269503546099,
      "grad_norm": 0.027898726984858513,
      "learning_rate": 0.0002970569948812214,
      "loss": 11.9302,
      "step": 22
    },
    {
      "epoch": 0.13049645390070921,
      "grad_norm": 0.03330138325691223,
      "learning_rate": 0.0002965480246175399,
      "loss": 11.9297,
      "step": 23
    },
    {
      "epoch": 0.13617021276595745,
      "grad_norm": 0.038234010338783264,
      "learning_rate": 0.0002959989895872009,
      "loss": 11.93,
      "step": 24
    },
    {
      "epoch": 0.14184397163120568,
      "grad_norm": 0.05450105294585228,
      "learning_rate": 0.0002954100398908995,
      "loss": 11.9267,
      "step": 25
    },
    {
      "epoch": 0.14184397163120568,
      "eval_loss": 11.929553031921387,
      "eval_runtime": 0.0614,
      "eval_samples_per_second": 813.963,
      "eval_steps_per_second": 32.559,
      "step": 25
    },
    {
      "epoch": 0.1475177304964539,
      "grad_norm": 0.027311373502016068,
      "learning_rate": 0.0002947813365416023,
      "loss": 11.9293,
      "step": 26
    },
    {
      "epoch": 0.15319148936170213,
      "grad_norm": 0.03143694996833801,
      "learning_rate": 0.0002941130514205272,
      "loss": 11.9299,
      "step": 27
    },
    {
      "epoch": 0.15886524822695036,
      "grad_norm": 0.028894711285829544,
      "learning_rate": 0.0002934053672301536,
      "loss": 11.9293,
      "step": 28
    },
    {
      "epoch": 0.16453900709219857,
      "grad_norm": 0.03230096772313118,
      "learning_rate": 0.00029265847744427303,
      "loss": 11.9293,
      "step": 29
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 0.0343053974211216,
      "learning_rate": 0.00029187258625509513,
      "loss": 11.9288,
      "step": 30
    },
    {
      "epoch": 0.17588652482269504,
      "grad_norm": 0.03575234115123749,
      "learning_rate": 0.00029104790851742417,
      "loss": 11.9295,
      "step": 31
    },
    {
      "epoch": 0.18156028368794327,
      "grad_norm": 0.03856245055794716,
      "learning_rate": 0.0002901846696899191,
      "loss": 11.9281,
      "step": 32
    },
    {
      "epoch": 0.18723404255319148,
      "grad_norm": 0.046584248542785645,
      "learning_rate": 0.00028928310577345606,
      "loss": 11.9262,
      "step": 33
    },
    {
      "epoch": 0.19290780141843972,
      "grad_norm": 0.04177519306540489,
      "learning_rate": 0.0002883434632466077,
      "loss": 11.9279,
      "step": 34
    },
    {
      "epoch": 0.19858156028368795,
      "grad_norm": 0.04843081906437874,
      "learning_rate": 0.00028736599899825856,
      "loss": 11.9265,
      "step": 35
    },
    {
      "epoch": 0.20425531914893616,
      "grad_norm": 0.04884253442287445,
      "learning_rate": 0.00028635098025737434,
      "loss": 11.9265,
      "step": 36
    },
    {
      "epoch": 0.2099290780141844,
      "grad_norm": 0.05538347363471985,
      "learning_rate": 0.00028529868451994384,
      "loss": 11.923,
      "step": 37
    },
    {
      "epoch": 0.21560283687943263,
      "grad_norm": 0.043813928961753845,
      "learning_rate": 0.0002842093994731145,
      "loss": 11.9268,
      "step": 38
    },
    {
      "epoch": 0.22127659574468084,
      "grad_norm": 0.04136502370238304,
      "learning_rate": 0.00028308342291654174,
      "loss": 11.9264,
      "step": 39
    },
    {
      "epoch": 0.22695035460992907,
      "grad_norm": 0.039866868406534195,
      "learning_rate": 0.00028192106268097334,
      "loss": 11.9269,
      "step": 40
    },
    {
      "epoch": 0.2326241134751773,
      "grad_norm": 0.03647204488515854,
      "learning_rate": 0.00028072263654409154,
      "loss": 11.9265,
      "step": 41
    },
    {
      "epoch": 0.23829787234042554,
      "grad_norm": 0.042418453842401505,
      "learning_rate": 0.0002794884721436361,
      "loss": 11.926,
      "step": 42
    },
    {
      "epoch": 0.24397163120567375,
      "grad_norm": 0.033910833299160004,
      "learning_rate": 0.00027821890688783083,
      "loss": 11.9237,
      "step": 43
    },
    {
      "epoch": 0.24964539007092199,
      "grad_norm": 0.030534636229276657,
      "learning_rate": 0.0002769142878631403,
      "loss": 11.9243,
      "step": 44
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 0.031080015003681183,
      "learning_rate": 0.00027557497173937923,
      "loss": 11.925,
      "step": 45
    },
    {
      "epoch": 0.26099290780141843,
      "grad_norm": 0.03134627267718315,
      "learning_rate": 0.000274201324672203,
      "loss": 11.923,
      "step": 46
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.029894711449742317,
      "learning_rate": 0.00027279372220300385,
      "loss": 11.9236,
      "step": 47
    },
    {
      "epoch": 0.2723404255319149,
      "grad_norm": 0.03413419798016548,
      "learning_rate": 0.0002713525491562421,
      "loss": 11.9241,
      "step": 48
    },
    {
      "epoch": 0.27801418439716313,
      "grad_norm": 0.030735192820429802,
      "learning_rate": 0.00026987819953423867,
      "loss": 11.922,
      "step": 49
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 0.04948793351650238,
      "learning_rate": 0.00026837107640945905,
      "loss": 11.9191,
      "step": 50
    },
    {
      "epoch": 0.28368794326241137,
      "eval_loss": 11.923072814941406,
      "eval_runtime": 0.0619,
      "eval_samples_per_second": 808.129,
      "eval_steps_per_second": 32.325,
      "step": 50
    },
    {
      "epoch": 0.28936170212765955,
      "grad_norm": 0.020492788404226303,
      "learning_rate": 0.0002668315918143169,
      "loss": 11.9241,
      "step": 51
    },
    {
      "epoch": 0.2950354609929078,
      "grad_norm": 0.025100423023104668,
      "learning_rate": 0.00026526016662852886,
      "loss": 11.9241,
      "step": 52
    },
    {
      "epoch": 0.300709219858156,
      "grad_norm": 0.02257562056183815,
      "learning_rate": 0.00026365723046405023,
      "loss": 11.9241,
      "step": 53
    },
    {
      "epoch": 0.30638297872340425,
      "grad_norm": 0.0209531057626009,
      "learning_rate": 0.0002620232215476231,
      "loss": 11.9252,
      "step": 54
    },
    {
      "epoch": 0.3120567375886525,
      "grad_norm": 0.02379811555147171,
      "learning_rate": 0.0002603585866009697,
      "loss": 11.9236,
      "step": 55
    },
    {
      "epoch": 0.3177304964539007,
      "grad_norm": 0.0216002706438303,
      "learning_rate": 0.00025866378071866334,
      "loss": 11.9217,
      "step": 56
    },
    {
      "epoch": 0.32340425531914896,
      "grad_norm": 0.022563716396689415,
      "learning_rate": 0.00025693926724370956,
      "loss": 11.9229,
      "step": 57
    },
    {
      "epoch": 0.32907801418439714,
      "grad_norm": 0.01919177919626236,
      "learning_rate": 0.00025518551764087326,
      "loss": 11.922,
      "step": 58
    },
    {
      "epoch": 0.3347517730496454,
      "grad_norm": 0.0177815742790699,
      "learning_rate": 0.00025340301136778483,
      "loss": 11.9216,
      "step": 59
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 0.023311970755457878,
      "learning_rate": 0.00025159223574386114,
      "loss": 11.9206,
      "step": 60
    },
    {
      "epoch": 0.34609929078014184,
      "grad_norm": 0.02824515849351883,
      "learning_rate": 0.0002497536858170772,
      "loss": 11.9201,
      "step": 61
    },
    {
      "epoch": 0.3517730496453901,
      "grad_norm": 0.026084575802087784,
      "learning_rate": 0.00024788786422862526,
      "loss": 11.9212,
      "step": 62
    },
    {
      "epoch": 0.3574468085106383,
      "grad_norm": 0.010427826084196568,
      "learning_rate": 0.00024599528107549745,
      "loss": 11.9232,
      "step": 63
    },
    {
      "epoch": 0.36312056737588655,
      "grad_norm": 0.02153744362294674,
      "learning_rate": 0.00024407645377103054,
      "loss": 11.9236,
      "step": 64
    },
    {
      "epoch": 0.36879432624113473,
      "grad_norm": 0.015608604997396469,
      "learning_rate": 0.00024213190690345018,
      "loss": 11.9228,
      "step": 65
    },
    {
      "epoch": 0.37446808510638296,
      "grad_norm": 0.014669565483927727,
      "learning_rate": 0.00024016217209245374,
      "loss": 11.9234,
      "step": 66
    },
    {
      "epoch": 0.3801418439716312,
      "grad_norm": 0.014809111133217812,
      "learning_rate": 0.00023816778784387094,
      "loss": 11.9224,
      "step": 67
    },
    {
      "epoch": 0.38581560283687943,
      "grad_norm": 0.014629780314862728,
      "learning_rate": 0.0002361492994024415,
      "loss": 11.9226,
      "step": 68
    },
    {
      "epoch": 0.39148936170212767,
      "grad_norm": 0.014726509340107441,
      "learning_rate": 0.0002341072586027509,
      "loss": 11.9223,
      "step": 69
    },
    {
      "epoch": 0.3971631205673759,
      "grad_norm": 0.012833105400204659,
      "learning_rate": 0.00023204222371836405,
      "loss": 11.9205,
      "step": 70
    },
    {
      "epoch": 0.40283687943262414,
      "grad_norm": 0.008062456734478474,
      "learning_rate": 0.00022995475930919905,
      "loss": 11.9225,
      "step": 71
    },
    {
      "epoch": 0.4085106382978723,
      "grad_norm": 0.014799988828599453,
      "learning_rate": 0.00022784543606718227,
      "loss": 11.9216,
      "step": 72
    },
    {
      "epoch": 0.41418439716312055,
      "grad_norm": 0.020988009870052338,
      "learning_rate": 0.00022571483066022657,
      "loss": 11.9207,
      "step": 73
    },
    {
      "epoch": 0.4198581560283688,
      "grad_norm": 0.018813014030456543,
      "learning_rate": 0.0002235635255745762,
      "loss": 11.9195,
      "step": 74
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.04026465490460396,
      "learning_rate": 0.00022139210895556104,
      "loss": 11.9166,
      "step": 75
    },
    {
      "epoch": 0.425531914893617,
      "eval_loss": 11.921867370605469,
      "eval_runtime": 0.0609,
      "eval_samples_per_second": 821.063,
      "eval_steps_per_second": 32.843,
      "step": 75
    },
    {
      "epoch": 0.43120567375886526,
      "grad_norm": 0.01442672498524189,
      "learning_rate": 0.00021920117444680317,
      "loss": 11.9233,
      "step": 76
    },
    {
      "epoch": 0.4368794326241135,
      "grad_norm": 0.015003877691924572,
      "learning_rate": 0.00021699132102792097,
      "loss": 11.9237,
      "step": 77
    },
    {
      "epoch": 0.4425531914893617,
      "grad_norm": 0.016231343150138855,
      "learning_rate": 0.0002147631528507739,
      "loss": 11.9233,
      "step": 78
    },
    {
      "epoch": 0.4482269503546099,
      "grad_norm": 0.01320897787809372,
      "learning_rate": 0.00021251727907429355,
      "loss": 11.9232,
      "step": 79
    },
    {
      "epoch": 0.45390070921985815,
      "grad_norm": 0.011513592675328255,
      "learning_rate": 0.0002102543136979454,
      "loss": 11.923,
      "step": 80
    },
    {
      "epoch": 0.4595744680851064,
      "grad_norm": 0.006751392036676407,
      "learning_rate": 0.0002079748753938678,
      "loss": 11.923,
      "step": 81
    },
    {
      "epoch": 0.4652482269503546,
      "grad_norm": 0.013094574213027954,
      "learning_rate": 0.0002056795873377331,
      "loss": 11.923,
      "step": 82
    },
    {
      "epoch": 0.47092198581560285,
      "grad_norm": 0.009502195753157139,
      "learning_rate": 0.00020336907703837748,
      "loss": 11.9221,
      "step": 83
    },
    {
      "epoch": 0.4765957446808511,
      "grad_norm": 0.014381026849150658,
      "learning_rate": 0.00020104397616624645,
      "loss": 11.9215,
      "step": 84
    },
    {
      "epoch": 0.48226950354609927,
      "grad_norm": 0.010836280882358551,
      "learning_rate": 0.00019870492038070252,
      "loss": 11.9211,
      "step": 85
    },
    {
      "epoch": 0.4879432624113475,
      "grad_norm": 0.023126577958464622,
      "learning_rate": 0.0001963525491562421,
      "loss": 11.9188,
      "step": 86
    },
    {
      "epoch": 0.49361702127659574,
      "grad_norm": 0.03279098868370056,
      "learning_rate": 0.0001939875056076697,
      "loss": 11.9176,
      "step": 87
    },
    {
      "epoch": 0.49929078014184397,
      "grad_norm": 0.01929604262113571,
      "learning_rate": 0.00019161043631427666,
      "loss": 11.9227,
      "step": 88
    },
    {
      "epoch": 0.5049645390070922,
      "grad_norm": 0.017098471522331238,
      "learning_rate": 0.00018922199114307294,
      "loss": 11.9232,
      "step": 89
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 0.01761694811284542,
      "learning_rate": 0.00018682282307111987,
      "loss": 11.9227,
      "step": 90
    },
    {
      "epoch": 0.5163120567375886,
      "grad_norm": 0.01521000824868679,
      "learning_rate": 0.00018441358800701273,
      "loss": 11.9226,
      "step": 91
    },
    {
      "epoch": 0.5219858156028369,
      "grad_norm": 0.015890169888734818,
      "learning_rate": 0.00018199494461156203,
      "loss": 11.9224,
      "step": 92
    },
    {
      "epoch": 0.5276595744680851,
      "grad_norm": 0.013760216534137726,
      "learning_rate": 0.000179567554117722,
      "loss": 11.9226,
      "step": 93
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.005599765572696924,
      "learning_rate": 0.00017713208014981648,
      "loss": 11.9215,
      "step": 94
    },
    {
      "epoch": 0.5390070921985816,
      "grad_norm": 0.012645565904676914,
      "learning_rate": 0.00017468918854211007,
      "loss": 11.922,
      "step": 95
    },
    {
      "epoch": 0.5446808510638298,
      "grad_norm": 0.012626095674932003,
      "learning_rate": 0.00017223954715677627,
      "loss": 11.9197,
      "step": 96
    },
    {
      "epoch": 0.550354609929078,
      "grad_norm": 0.019928378984332085,
      "learning_rate": 0.00016978382570131034,
      "loss": 11.9208,
      "step": 97
    },
    {
      "epoch": 0.5560283687943263,
      "grad_norm": 0.013066703453660011,
      "learning_rate": 0.00016732269554543794,
      "loss": 11.9212,
      "step": 98
    },
    {
      "epoch": 0.5617021276595745,
      "grad_norm": 0.023204414173960686,
      "learning_rate": 0.00016485682953756942,
      "loss": 11.9188,
      "step": 99
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 0.037473615258932114,
      "learning_rate": 0.00016238690182084986,
      "loss": 11.9168,
      "step": 100
    },
    {
      "epoch": 0.5673758865248227,
      "eval_loss": 11.921294212341309,
      "eval_runtime": 0.0612,
      "eval_samples_per_second": 816.479,
      "eval_steps_per_second": 32.659,
      "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": 639040020480.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}