{
  "best_metric": 0.08705329149961472,
  "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": 0.6567320823669434,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.4071,
      "step": 1
    },
    {
      "epoch": 0.005673758865248227,
      "eval_loss": 0.22036334872245789,
      "eval_runtime": 6.6422,
      "eval_samples_per_second": 7.528,
      "eval_steps_per_second": 1.054,
      "step": 1
    },
    {
      "epoch": 0.011347517730496455,
      "grad_norm": 0.6732487678527832,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.3639,
      "step": 2
    },
    {
      "epoch": 0.01702127659574468,
      "grad_norm": 0.5613159537315369,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.3219,
      "step": 3
    },
    {
      "epoch": 0.02269503546099291,
      "grad_norm": 0.45505204796791077,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.3377,
      "step": 4
    },
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 0.4392223358154297,
      "learning_rate": 0.00015,
      "loss": 0.3325,
      "step": 5
    },
    {
      "epoch": 0.03404255319148936,
      "grad_norm": 0.4434760510921478,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.3476,
      "step": 6
    },
    {
      "epoch": 0.03971631205673759,
      "grad_norm": 0.2849961221218109,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.2592,
      "step": 7
    },
    {
      "epoch": 0.04539007092198582,
      "grad_norm": 0.22268033027648926,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.2355,
      "step": 8
    },
    {
      "epoch": 0.05106382978723404,
      "grad_norm": 0.6029117703437805,
      "learning_rate": 0.00027,
      "loss": 0.3223,
      "step": 9
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 0.543067216873169,
      "learning_rate": 0.0003,
      "loss": 0.2553,
      "step": 10
    },
    {
      "epoch": 0.062411347517730496,
      "grad_norm": 0.265033483505249,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.2578,
      "step": 11
    },
    {
      "epoch": 0.06808510638297872,
      "grad_norm": 0.14402134716510773,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.1828,
      "step": 12
    },
    {
      "epoch": 0.07375886524822695,
      "grad_norm": 0.1815207153558731,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.2784,
      "step": 13
    },
    {
      "epoch": 0.07943262411347518,
      "grad_norm": 0.17301031947135925,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.2375,
      "step": 14
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 0.1395721584558487,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.1957,
      "step": 15
    },
    {
      "epoch": 0.09078014184397164,
      "grad_norm": 0.14996208250522614,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.2279,
      "step": 16
    },
    {
      "epoch": 0.09645390070921986,
      "grad_norm": 0.1510487198829651,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.1986,
      "step": 17
    },
    {
      "epoch": 0.10212765957446808,
      "grad_norm": 0.1490045040845871,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.1931,
      "step": 18
    },
    {
      "epoch": 0.10780141843971631,
      "grad_norm": 0.17285487055778503,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.1473,
      "step": 19
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 0.13048504292964935,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.0971,
      "step": 20
    },
    {
      "epoch": 0.11914893617021277,
      "grad_norm": 0.12347353994846344,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.0713,
      "step": 21
    },
    {
      "epoch": 0.12482269503546099,
      "grad_norm": 0.07937260717153549,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.0287,
      "step": 22
    },
    {
      "epoch": 0.13049645390070921,
      "grad_norm": 0.08024411648511887,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.0298,
      "step": 23
    },
    {
      "epoch": 0.13617021276595745,
      "grad_norm": 0.09828471392393112,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.0294,
      "step": 24
    },
    {
      "epoch": 0.14184397163120568,
      "grad_norm": 0.09629218280315399,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.0208,
      "step": 25
    },
    {
      "epoch": 0.14184397163120568,
      "eval_loss": 0.10909587889909744,
      "eval_runtime": 6.7173,
      "eval_samples_per_second": 7.443,
      "eval_steps_per_second": 1.042,
      "step": 25
    },
    {
      "epoch": 0.1475177304964539,
      "grad_norm": 0.0800151377916336,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.0173,
      "step": 26
    },
    {
      "epoch": 0.15319148936170213,
      "grad_norm": 0.08075784146785736,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.018,
      "step": 27
    },
    {
      "epoch": 0.15886524822695036,
      "grad_norm": 0.10134506225585938,
      "learning_rate": 0.0002934053672301536,
      "loss": 0.0199,
      "step": 28
    },
    {
      "epoch": 0.16453900709219857,
      "grad_norm": 0.07547775655984879,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.0122,
      "step": 29
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 0.10290510952472687,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.0143,
      "step": 30
    },
    {
      "epoch": 0.17588652482269504,
      "grad_norm": 0.1462346613407135,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.0203,
      "step": 31
    },
    {
      "epoch": 0.18156028368794327,
      "grad_norm": 0.08281629532575607,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.0166,
      "step": 32
    },
    {
      "epoch": 0.18723404255319148,
      "grad_norm": 0.09583016484975815,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.0207,
      "step": 33
    },
    {
      "epoch": 0.19290780141843972,
      "grad_norm": 0.08298071473836899,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.0135,
      "step": 34
    },
    {
      "epoch": 0.19858156028368795,
      "grad_norm": 0.12078027427196503,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.014,
      "step": 35
    },
    {
      "epoch": 0.20425531914893616,
      "grad_norm": 0.07853731513023376,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.0129,
      "step": 36
    },
    {
      "epoch": 0.2099290780141844,
      "grad_norm": 0.08032602816820145,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.0125,
      "step": 37
    },
    {
      "epoch": 0.21560283687943263,
      "grad_norm": 0.07942873239517212,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.0127,
      "step": 38
    },
    {
      "epoch": 0.22127659574468084,
      "grad_norm": 0.11203460395336151,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.015,
      "step": 39
    },
    {
      "epoch": 0.22695035460992907,
      "grad_norm": 0.10632278770208359,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.0168,
      "step": 40
    },
    {
      "epoch": 0.2326241134751773,
      "grad_norm": 0.12105297297239304,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.0148,
      "step": 41
    },
    {
      "epoch": 0.23829787234042554,
      "grad_norm": 0.16477319598197937,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.0224,
      "step": 42
    },
    {
      "epoch": 0.24397163120567375,
      "grad_norm": 0.20291352272033691,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.0339,
      "step": 43
    },
    {
      "epoch": 0.24964539007092199,
      "grad_norm": 0.5795202851295471,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.0607,
      "step": 44
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 0.3015036880970001,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.2348,
      "step": 45
    },
    {
      "epoch": 0.26099290780141843,
      "grad_norm": 0.21086736023426056,
      "learning_rate": 0.000274201324672203,
      "loss": 0.1987,
      "step": 46
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.1581435650587082,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.1761,
      "step": 47
    },
    {
      "epoch": 0.2723404255319149,
      "grad_norm": 0.17156659066677094,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.2314,
      "step": 48
    },
    {
      "epoch": 0.27801418439716313,
      "grad_norm": 0.15111802518367767,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.1813,
      "step": 49
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 0.1316436380147934,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.1325,
      "step": 50
    },
    {
      "epoch": 0.28368794326241137,
      "eval_loss": 0.09500084072351456,
      "eval_runtime": 6.6628,
      "eval_samples_per_second": 7.504,
      "eval_steps_per_second": 1.051,
      "step": 50
    },
    {
      "epoch": 0.28936170212765955,
      "grad_norm": 0.15596741437911987,
      "learning_rate": 0.0002668315918143169,
      "loss": 0.2319,
      "step": 51
    },
    {
      "epoch": 0.2950354609929078,
      "grad_norm": 0.15342959761619568,
      "learning_rate": 0.00026526016662852886,
      "loss": 0.2409,
      "step": 52
    },
    {
      "epoch": 0.300709219858156,
      "grad_norm": 0.5929403901100159,
      "learning_rate": 0.00026365723046405023,
      "loss": 0.1871,
      "step": 53
    },
    {
      "epoch": 0.30638297872340425,
      "grad_norm": 0.1430080085992813,
      "learning_rate": 0.0002620232215476231,
      "loss": 0.2278,
      "step": 54
    },
    {
      "epoch": 0.3120567375886525,
      "grad_norm": 0.2504333555698395,
      "learning_rate": 0.0002603585866009697,
      "loss": 0.2109,
      "step": 55
    },
    {
      "epoch": 0.3177304964539007,
      "grad_norm": 0.36393240094184875,
      "learning_rate": 0.00025866378071866334,
      "loss": 0.1844,
      "step": 56
    },
    {
      "epoch": 0.32340425531914896,
      "grad_norm": 0.13066324591636658,
      "learning_rate": 0.00025693926724370956,
      "loss": 0.2173,
      "step": 57
    },
    {
      "epoch": 0.32907801418439714,
      "grad_norm": 0.13164402544498444,
      "learning_rate": 0.00025518551764087326,
      "loss": 0.2108,
      "step": 58
    },
    {
      "epoch": 0.3347517730496454,
      "grad_norm": 0.14740315079689026,
      "learning_rate": 0.00025340301136778483,
      "loss": 0.2271,
      "step": 59
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 0.15507878363132477,
      "learning_rate": 0.00025159223574386114,
      "loss": 0.2442,
      "step": 60
    },
    {
      "epoch": 0.34609929078014184,
      "grad_norm": 0.13118167221546173,
      "learning_rate": 0.0002497536858170772,
      "loss": 0.1877,
      "step": 61
    },
    {
      "epoch": 0.3517730496453901,
      "grad_norm": 0.14413724839687347,
      "learning_rate": 0.00024788786422862526,
      "loss": 0.214,
      "step": 62
    },
    {
      "epoch": 0.3574468085106383,
      "grad_norm": 0.11405673623085022,
      "learning_rate": 0.00024599528107549745,
      "loss": 0.0906,
      "step": 63
    },
    {
      "epoch": 0.36312056737588655,
      "grad_norm": 0.10695318877696991,
      "learning_rate": 0.00024407645377103054,
      "loss": 0.0675,
      "step": 64
    },
    {
      "epoch": 0.36879432624113473,
      "grad_norm": 0.09675230830907822,
      "learning_rate": 0.00024213190690345018,
      "loss": 0.0587,
      "step": 65
    },
    {
      "epoch": 0.37446808510638296,
      "grad_norm": 0.09902877360582352,
      "learning_rate": 0.00024016217209245374,
      "loss": 0.0707,
      "step": 66
    },
    {
      "epoch": 0.3801418439716312,
      "grad_norm": 0.0778760313987732,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.0319,
      "step": 67
    },
    {
      "epoch": 0.38581560283687943,
      "grad_norm": 0.06342566013336182,
      "learning_rate": 0.0002361492994024415,
      "loss": 0.0235,
      "step": 68
    },
    {
      "epoch": 0.39148936170212767,
      "grad_norm": 0.0666981041431427,
      "learning_rate": 0.0002341072586027509,
      "loss": 0.0202,
      "step": 69
    },
    {
      "epoch": 0.3971631205673759,
      "grad_norm": 0.08664432168006897,
      "learning_rate": 0.00023204222371836405,
      "loss": 0.017,
      "step": 70
    },
    {
      "epoch": 0.40283687943262414,
      "grad_norm": 0.09265201538801193,
      "learning_rate": 0.00022995475930919905,
      "loss": 0.0091,
      "step": 71
    },
    {
      "epoch": 0.4085106382978723,
      "grad_norm": 0.06965811550617218,
      "learning_rate": 0.00022784543606718227,
      "loss": 0.0098,
      "step": 72
    },
    {
      "epoch": 0.41418439716312055,
      "grad_norm": 0.0695430338382721,
      "learning_rate": 0.00022571483066022657,
      "loss": 0.0092,
      "step": 73
    },
    {
      "epoch": 0.4198581560283688,
      "grad_norm": 0.08358810096979141,
      "learning_rate": 0.0002235635255745762,
      "loss": 0.0121,
      "step": 74
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.059993814677000046,
      "learning_rate": 0.00022139210895556104,
      "loss": 0.0082,
      "step": 75
    },
    {
      "epoch": 0.425531914893617,
      "eval_loss": 0.09436039626598358,
      "eval_runtime": 6.6489,
      "eval_samples_per_second": 7.52,
      "eval_steps_per_second": 1.053,
      "step": 75
    },
    {
      "epoch": 0.43120567375886526,
      "grad_norm": 0.09175027161836624,
      "learning_rate": 0.00021920117444680317,
      "loss": 0.0084,
      "step": 76
    },
    {
      "epoch": 0.4368794326241135,
      "grad_norm": 0.06123727932572365,
      "learning_rate": 0.00021699132102792097,
      "loss": 0.0094,
      "step": 77
    },
    {
      "epoch": 0.4425531914893617,
      "grad_norm": 0.11089751869440079,
      "learning_rate": 0.0002147631528507739,
      "loss": 0.0071,
      "step": 78
    },
    {
      "epoch": 0.4482269503546099,
      "grad_norm": 0.06789694726467133,
      "learning_rate": 0.00021251727907429355,
      "loss": 0.0073,
      "step": 79
    },
    {
      "epoch": 0.45390070921985815,
      "grad_norm": 0.06642229110002518,
      "learning_rate": 0.0002102543136979454,
      "loss": 0.0068,
      "step": 80
    },
    {
      "epoch": 0.4595744680851064,
      "grad_norm": 0.0795132964849472,
      "learning_rate": 0.0002079748753938678,
      "loss": 0.0051,
      "step": 81
    },
    {
      "epoch": 0.4652482269503546,
      "grad_norm": 0.11351794749498367,
      "learning_rate": 0.0002056795873377331,
      "loss": 0.0108,
      "step": 82
    },
    {
      "epoch": 0.47092198581560285,
      "grad_norm": 0.07391192764043808,
      "learning_rate": 0.00020336907703837748,
      "loss": 0.0102,
      "step": 83
    },
    {
      "epoch": 0.4765957446808511,
      "grad_norm": 0.08752062171697617,
      "learning_rate": 0.00020104397616624645,
      "loss": 0.0074,
      "step": 84
    },
    {
      "epoch": 0.48226950354609927,
      "grad_norm": 0.10944165289402008,
      "learning_rate": 0.00019870492038070252,
      "loss": 0.01,
      "step": 85
    },
    {
      "epoch": 0.4879432624113475,
      "grad_norm": 0.13292644917964935,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.0152,
      "step": 86
    },
    {
      "epoch": 0.49361702127659574,
      "grad_norm": 0.16543662548065186,
      "learning_rate": 0.0001939875056076697,
      "loss": 0.0175,
      "step": 87
    },
    {
      "epoch": 0.49929078014184397,
      "grad_norm": 0.4206661880016327,
      "learning_rate": 0.00019161043631427666,
      "loss": 0.0632,
      "step": 88
    },
    {
      "epoch": 0.5049645390070922,
      "grad_norm": 0.2616719901561737,
      "learning_rate": 0.00018922199114307294,
      "loss": 0.1991,
      "step": 89
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 0.2395102083683014,
      "learning_rate": 0.00018682282307111987,
      "loss": 0.2178,
      "step": 90
    },
    {
      "epoch": 0.5163120567375886,
      "grad_norm": 0.16154062747955322,
      "learning_rate": 0.00018441358800701273,
      "loss": 0.1978,
      "step": 91
    },
    {
      "epoch": 0.5219858156028369,
      "grad_norm": 0.13820257782936096,
      "learning_rate": 0.00018199494461156203,
      "loss": 0.1875,
      "step": 92
    },
    {
      "epoch": 0.5276595744680851,
      "grad_norm": 0.15515460073947906,
      "learning_rate": 0.000179567554117722,
      "loss": 0.2294,
      "step": 93
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.14044955372810364,
      "learning_rate": 0.00017713208014981648,
      "loss": 0.1898,
      "step": 94
    },
    {
      "epoch": 0.5390070921985816,
      "grad_norm": 0.1499217450618744,
      "learning_rate": 0.00017468918854211007,
      "loss": 0.208,
      "step": 95
    },
    {
      "epoch": 0.5446808510638298,
      "grad_norm": 0.1417035013437271,
      "learning_rate": 0.00017223954715677627,
      "loss": 0.2009,
      "step": 96
    },
    {
      "epoch": 0.550354609929078,
      "grad_norm": 0.12359917163848877,
      "learning_rate": 0.00016978382570131034,
      "loss": 0.1748,
      "step": 97
    },
    {
      "epoch": 0.5560283687943263,
      "grad_norm": 0.1188841164112091,
      "learning_rate": 0.00016732269554543794,
      "loss": 0.1583,
      "step": 98
    },
    {
      "epoch": 0.5617021276595745,
      "grad_norm": 0.1371552050113678,
      "learning_rate": 0.00016485682953756942,
      "loss": 0.1704,
      "step": 99
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 0.14197076857089996,
      "learning_rate": 0.00016238690182084986,
      "loss": 0.1849,
      "step": 100
    },
    {
      "epoch": 0.5673758865248227,
      "eval_loss": 0.08705329149961472,
      "eval_runtime": 6.6626,
      "eval_samples_per_second": 7.505,
      "eval_steps_per_second": 1.051,
      "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": 7.60950229649326e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}