{
  "best_metric": 0.8602708578109741,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.5444015444015444,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007722007722007722,
      "grad_norm": 0.48682987689971924,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 4.6335,
      "step": 1
    },
    {
      "epoch": 0.007722007722007722,
      "eval_loss": 1.5098271369934082,
      "eval_runtime": 5.2371,
      "eval_samples_per_second": 9.547,
      "eval_steps_per_second": 1.337,
      "step": 1
    },
    {
      "epoch": 0.015444015444015444,
      "grad_norm": 0.576587975025177,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 5.2535,
      "step": 2
    },
    {
      "epoch": 0.023166023166023165,
      "grad_norm": 0.5523186326026917,
      "learning_rate": 8.999999999999999e-05,
      "loss": 5.3701,
      "step": 3
    },
    {
      "epoch": 0.03088803088803089,
      "grad_norm": 0.5980996489524841,
      "learning_rate": 0.00011999999999999999,
      "loss": 5.3462,
      "step": 4
    },
    {
      "epoch": 0.03861003861003861,
      "grad_norm": 0.7052809596061707,
      "learning_rate": 0.00015,
      "loss": 5.4412,
      "step": 5
    },
    {
      "epoch": 0.04633204633204633,
      "grad_norm": 0.8689579367637634,
      "learning_rate": 0.00017999999999999998,
      "loss": 5.494,
      "step": 6
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 0.725929319858551,
      "learning_rate": 0.00020999999999999998,
      "loss": 5.4008,
      "step": 7
    },
    {
      "epoch": 0.06177606177606178,
      "grad_norm": 0.9785446524620056,
      "learning_rate": 0.00023999999999999998,
      "loss": 5.3156,
      "step": 8
    },
    {
      "epoch": 0.0694980694980695,
      "grad_norm": 1.1441841125488281,
      "learning_rate": 0.00027,
      "loss": 5.1554,
      "step": 9
    },
    {
      "epoch": 0.07722007722007722,
      "grad_norm": 1.2562114000320435,
      "learning_rate": 0.0003,
      "loss": 5.0023,
      "step": 10
    },
    {
      "epoch": 0.08494208494208494,
      "grad_norm": 1.2354058027267456,
      "learning_rate": 0.0002999794957488703,
      "loss": 4.5674,
      "step": 11
    },
    {
      "epoch": 0.09266409266409266,
      "grad_norm": 1.0314974784851074,
      "learning_rate": 0.0002999179886011389,
      "loss": 4.9171,
      "step": 12
    },
    {
      "epoch": 0.10038610038610038,
      "grad_norm": 0.7933022975921631,
      "learning_rate": 0.0002998154953722457,
      "loss": 4.6985,
      "step": 13
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 0.7299078106880188,
      "learning_rate": 0.00029967204408281613,
      "loss": 4.4703,
      "step": 14
    },
    {
      "epoch": 0.11583011583011583,
      "grad_norm": 0.7776244878768921,
      "learning_rate": 0.00029948767395100045,
      "loss": 4.586,
      "step": 15
    },
    {
      "epoch": 0.12355212355212356,
      "grad_norm": 0.8550058007240295,
      "learning_rate": 0.0002992624353817517,
      "loss": 4.9221,
      "step": 16
    },
    {
      "epoch": 0.13127413127413126,
      "grad_norm": 0.8260884881019592,
      "learning_rate": 0.0002989963899530457,
      "loss": 4.8339,
      "step": 17
    },
    {
      "epoch": 0.138996138996139,
      "grad_norm": 0.898746132850647,
      "learning_rate": 0.00029868961039904624,
      "loss": 4.9411,
      "step": 18
    },
    {
      "epoch": 0.14671814671814673,
      "grad_norm": 0.9319860935211182,
      "learning_rate": 0.00029834218059022024,
      "loss": 5.1397,
      "step": 19
    },
    {
      "epoch": 0.15444015444015444,
      "grad_norm": 1.0337817668914795,
      "learning_rate": 0.00029795419551040833,
      "loss": 5.4067,
      "step": 20
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 1.090299129486084,
      "learning_rate": 0.00029752576123085736,
      "loss": 5.55,
      "step": 21
    },
    {
      "epoch": 0.16988416988416988,
      "grad_norm": 1.102376937866211,
      "learning_rate": 0.0002970569948812214,
      "loss": 5.0307,
      "step": 22
    },
    {
      "epoch": 0.1776061776061776,
      "grad_norm": 1.1082665920257568,
      "learning_rate": 0.0002965480246175399,
      "loss": 5.2671,
      "step": 23
    },
    {
      "epoch": 0.18532818532818532,
      "grad_norm": 1.2935750484466553,
      "learning_rate": 0.0002959989895872009,
      "loss": 5.5509,
      "step": 24
    },
    {
      "epoch": 0.19305019305019305,
      "grad_norm": 1.4439600706100464,
      "learning_rate": 0.0002954100398908995,
      "loss": 5.6251,
      "step": 25
    },
    {
      "epoch": 0.19305019305019305,
      "eval_loss": 1.1729116439819336,
      "eval_runtime": 5.345,
      "eval_samples_per_second": 9.354,
      "eval_steps_per_second": 1.31,
      "step": 25
    },
    {
      "epoch": 0.20077220077220076,
      "grad_norm": 1.432866096496582,
      "learning_rate": 0.0002947813365416023,
      "loss": 5.5811,
      "step": 26
    },
    {
      "epoch": 0.2084942084942085,
      "grad_norm": 1.3532747030258179,
      "learning_rate": 0.0002941130514205272,
      "loss": 5.395,
      "step": 27
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 1.4329724311828613,
      "learning_rate": 0.0002934053672301536,
      "loss": 5.0288,
      "step": 28
    },
    {
      "epoch": 0.22393822393822393,
      "grad_norm": 1.5020999908447266,
      "learning_rate": 0.00029265847744427303,
      "loss": 5.747,
      "step": 29
    },
    {
      "epoch": 0.23166023166023167,
      "grad_norm": 1.7116535902023315,
      "learning_rate": 0.00029187258625509513,
      "loss": 5.4511,
      "step": 30
    },
    {
      "epoch": 0.23938223938223938,
      "grad_norm": 1.9912713766098022,
      "learning_rate": 0.00029104790851742417,
      "loss": 5.7581,
      "step": 31
    },
    {
      "epoch": 0.2471042471042471,
      "grad_norm": 2.8238329887390137,
      "learning_rate": 0.0002901846696899191,
      "loss": 5.0392,
      "step": 32
    },
    {
      "epoch": 0.2548262548262548,
      "grad_norm": 3.7411208152770996,
      "learning_rate": 0.00028928310577345606,
      "loss": 4.6187,
      "step": 33
    },
    {
      "epoch": 0.2625482625482625,
      "grad_norm": 3.40368390083313,
      "learning_rate": 0.0002883434632466077,
      "loss": 4.6782,
      "step": 34
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 2.3785061836242676,
      "learning_rate": 0.00028736599899825856,
      "loss": 4.6217,
      "step": 35
    },
    {
      "epoch": 0.277992277992278,
      "grad_norm": 1.2492105960845947,
      "learning_rate": 0.00028635098025737434,
      "loss": 4.5761,
      "step": 36
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.98371422290802,
      "learning_rate": 0.00028529868451994384,
      "loss": 4.2969,
      "step": 37
    },
    {
      "epoch": 0.29343629343629346,
      "grad_norm": 0.8923739790916443,
      "learning_rate": 0.0002842093994731145,
      "loss": 4.1866,
      "step": 38
    },
    {
      "epoch": 0.30115830115830117,
      "grad_norm": 0.8865004181861877,
      "learning_rate": 0.00028308342291654174,
      "loss": 4.2122,
      "step": 39
    },
    {
      "epoch": 0.3088803088803089,
      "grad_norm": 0.9209084510803223,
      "learning_rate": 0.00028192106268097334,
      "loss": 4.2564,
      "step": 40
    },
    {
      "epoch": 0.3166023166023166,
      "grad_norm": 0.8480415940284729,
      "learning_rate": 0.00028072263654409154,
      "loss": 4.1739,
      "step": 41
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 0.87739098072052,
      "learning_rate": 0.0002794884721436361,
      "loss": 4.2479,
      "step": 42
    },
    {
      "epoch": 0.33204633204633205,
      "grad_norm": 1.0233778953552246,
      "learning_rate": 0.00027821890688783083,
      "loss": 4.0354,
      "step": 43
    },
    {
      "epoch": 0.33976833976833976,
      "grad_norm": 1.0052204132080078,
      "learning_rate": 0.0002769142878631403,
      "loss": 4.1265,
      "step": 44
    },
    {
      "epoch": 0.3474903474903475,
      "grad_norm": 0.9846855998039246,
      "learning_rate": 0.00027557497173937923,
      "loss": 3.8857,
      "step": 45
    },
    {
      "epoch": 0.3552123552123552,
      "grad_norm": 0.9861114621162415,
      "learning_rate": 0.000274201324672203,
      "loss": 4.034,
      "step": 46
    },
    {
      "epoch": 0.36293436293436293,
      "grad_norm": 1.1083577871322632,
      "learning_rate": 0.00027279372220300385,
      "loss": 3.9773,
      "step": 47
    },
    {
      "epoch": 0.37065637065637064,
      "grad_norm": 1.147931456565857,
      "learning_rate": 0.0002713525491562421,
      "loss": 4.3488,
      "step": 48
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 1.1465137004852295,
      "learning_rate": 0.00026987819953423867,
      "loss": 4.2694,
      "step": 49
    },
    {
      "epoch": 0.3861003861003861,
      "grad_norm": 1.1972469091415405,
      "learning_rate": 0.00026837107640945905,
      "loss": 4.4304,
      "step": 50
    },
    {
      "epoch": 0.3861003861003861,
      "eval_loss": 1.040252685546875,
      "eval_runtime": 5.3531,
      "eval_samples_per_second": 9.34,
      "eval_steps_per_second": 1.308,
      "step": 50
    },
    {
      "epoch": 0.3938223938223938,
      "grad_norm": 1.1470128297805786,
      "learning_rate": 0.0002668315918143169,
      "loss": 4.643,
      "step": 51
    },
    {
      "epoch": 0.4015444015444015,
      "grad_norm": 1.1371747255325317,
      "learning_rate": 0.00026526016662852886,
      "loss": 4.2,
      "step": 52
    },
    {
      "epoch": 0.4092664092664093,
      "grad_norm": 1.2832008600234985,
      "learning_rate": 0.00026365723046405023,
      "loss": 4.8526,
      "step": 53
    },
    {
      "epoch": 0.416988416988417,
      "grad_norm": 1.2690390348434448,
      "learning_rate": 0.0002620232215476231,
      "loss": 5.1477,
      "step": 54
    },
    {
      "epoch": 0.4247104247104247,
      "grad_norm": 1.2886794805526733,
      "learning_rate": 0.0002603585866009697,
      "loss": 4.5254,
      "step": 55
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 1.4495960474014282,
      "learning_rate": 0.00025866378071866334,
      "loss": 4.7262,
      "step": 56
    },
    {
      "epoch": 0.44015444015444016,
      "grad_norm": 1.5323647260665894,
      "learning_rate": 0.00025693926724370956,
      "loss": 5.6915,
      "step": 57
    },
    {
      "epoch": 0.44787644787644787,
      "grad_norm": 1.6446021795272827,
      "learning_rate": 0.00025518551764087326,
      "loss": 5.4946,
      "step": 58
    },
    {
      "epoch": 0.4555984555984556,
      "grad_norm": 1.501075029373169,
      "learning_rate": 0.00025340301136778483,
      "loss": 4.8464,
      "step": 59
    },
    {
      "epoch": 0.46332046332046334,
      "grad_norm": 1.6051170825958252,
      "learning_rate": 0.00025159223574386114,
      "loss": 5.3962,
      "step": 60
    },
    {
      "epoch": 0.47104247104247104,
      "grad_norm": 1.7223901748657227,
      "learning_rate": 0.0002497536858170772,
      "loss": 5.3883,
      "step": 61
    },
    {
      "epoch": 0.47876447876447875,
      "grad_norm": 1.845331072807312,
      "learning_rate": 0.00024788786422862526,
      "loss": 5.2666,
      "step": 62
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 1.9371899366378784,
      "learning_rate": 0.00024599528107549745,
      "loss": 4.9756,
      "step": 63
    },
    {
      "epoch": 0.4942084942084942,
      "grad_norm": 2.5107109546661377,
      "learning_rate": 0.00024407645377103054,
      "loss": 4.1281,
      "step": 64
    },
    {
      "epoch": 0.5019305019305019,
      "grad_norm": 1.3052512407302856,
      "learning_rate": 0.00024213190690345018,
      "loss": 3.7595,
      "step": 65
    },
    {
      "epoch": 0.5096525096525096,
      "grad_norm": 1.4003005027770996,
      "learning_rate": 0.00024016217209245374,
      "loss": 4.1023,
      "step": 66
    },
    {
      "epoch": 0.5173745173745173,
      "grad_norm": 1.176680564880371,
      "learning_rate": 0.00023816778784387094,
      "loss": 3.8911,
      "step": 67
    },
    {
      "epoch": 0.525096525096525,
      "grad_norm": 0.9517709016799927,
      "learning_rate": 0.0002361492994024415,
      "loss": 3.8995,
      "step": 68
    },
    {
      "epoch": 0.5328185328185329,
      "grad_norm": 0.9139338731765747,
      "learning_rate": 0.0002341072586027509,
      "loss": 3.8387,
      "step": 69
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.9844569563865662,
      "learning_rate": 0.00023204222371836405,
      "loss": 3.6323,
      "step": 70
    },
    {
      "epoch": 0.5482625482625483,
      "grad_norm": 1.0444170236587524,
      "learning_rate": 0.00022995475930919905,
      "loss": 3.672,
      "step": 71
    },
    {
      "epoch": 0.555984555984556,
      "grad_norm": 1.0720690488815308,
      "learning_rate": 0.00022784543606718227,
      "loss": 3.6361,
      "step": 72
    },
    {
      "epoch": 0.5637065637065637,
      "grad_norm": 1.1444705724716187,
      "learning_rate": 0.00022571483066022657,
      "loss": 3.6604,
      "step": 73
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.0103129148483276,
      "learning_rate": 0.0002235635255745762,
      "loss": 3.7358,
      "step": 74
    },
    {
      "epoch": 0.5791505791505791,
      "grad_norm": 0.934658944606781,
      "learning_rate": 0.00022139210895556104,
      "loss": 3.5276,
      "step": 75
    },
    {
      "epoch": 0.5791505791505791,
      "eval_loss": 0.9763892292976379,
      "eval_runtime": 5.3528,
      "eval_samples_per_second": 9.341,
      "eval_steps_per_second": 1.308,
      "step": 75
    },
    {
      "epoch": 0.5868725868725869,
      "grad_norm": 1.0414830446243286,
      "learning_rate": 0.00021920117444680317,
      "loss": 3.3979,
      "step": 76
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 1.0259995460510254,
      "learning_rate": 0.00021699132102792097,
      "loss": 3.9118,
      "step": 77
    },
    {
      "epoch": 0.6023166023166023,
      "grad_norm": 0.9699999690055847,
      "learning_rate": 0.0002147631528507739,
      "loss": 3.4132,
      "step": 78
    },
    {
      "epoch": 0.61003861003861,
      "grad_norm": 0.9405478239059448,
      "learning_rate": 0.00021251727907429355,
      "loss": 3.6127,
      "step": 79
    },
    {
      "epoch": 0.6177606177606177,
      "grad_norm": 1.0241910219192505,
      "learning_rate": 0.0002102543136979454,
      "loss": 3.5856,
      "step": 80
    },
    {
      "epoch": 0.6254826254826255,
      "grad_norm": 1.178605556488037,
      "learning_rate": 0.0002079748753938678,
      "loss": 4.0102,
      "step": 81
    },
    {
      "epoch": 0.6332046332046332,
      "grad_norm": 1.2604138851165771,
      "learning_rate": 0.0002056795873377331,
      "loss": 4.081,
      "step": 82
    },
    {
      "epoch": 0.640926640926641,
      "grad_norm": 1.2290773391723633,
      "learning_rate": 0.00020336907703837748,
      "loss": 4.1918,
      "step": 83
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 1.2991111278533936,
      "learning_rate": 0.00020104397616624645,
      "loss": 4.4876,
      "step": 84
    },
    {
      "epoch": 0.6563706563706564,
      "grad_norm": 1.2828688621520996,
      "learning_rate": 0.00019870492038070252,
      "loss": 4.7199,
      "step": 85
    },
    {
      "epoch": 0.6640926640926641,
      "grad_norm": 1.3234930038452148,
      "learning_rate": 0.0001963525491562421,
      "loss": 4.5667,
      "step": 86
    },
    {
      "epoch": 0.6718146718146718,
      "grad_norm": 1.3188049793243408,
      "learning_rate": 0.0001939875056076697,
      "loss": 4.4543,
      "step": 87
    },
    {
      "epoch": 0.6795366795366795,
      "grad_norm": 1.5290600061416626,
      "learning_rate": 0.00019161043631427666,
      "loss": 5.0645,
      "step": 88
    },
    {
      "epoch": 0.6872586872586872,
      "grad_norm": 1.4858952760696411,
      "learning_rate": 0.00018922199114307294,
      "loss": 4.5925,
      "step": 89
    },
    {
      "epoch": 0.694980694980695,
      "grad_norm": 1.3900132179260254,
      "learning_rate": 0.00018682282307111987,
      "loss": 4.954,
      "step": 90
    },
    {
      "epoch": 0.7027027027027027,
      "grad_norm": 1.5378596782684326,
      "learning_rate": 0.00018441358800701273,
      "loss": 4.843,
      "step": 91
    },
    {
      "epoch": 0.7104247104247104,
      "grad_norm": 1.5774720907211304,
      "learning_rate": 0.00018199494461156203,
      "loss": 5.1157,
      "step": 92
    },
    {
      "epoch": 0.7181467181467182,
      "grad_norm": 1.6517233848571777,
      "learning_rate": 0.000179567554117722,
      "loss": 5.4105,
      "step": 93
    },
    {
      "epoch": 0.7258687258687259,
      "grad_norm": 1.7554528713226318,
      "learning_rate": 0.00017713208014981648,
      "loss": 5.1654,
      "step": 94
    },
    {
      "epoch": 0.7335907335907336,
      "grad_norm": 2.210441827774048,
      "learning_rate": 0.00017468918854211007,
      "loss": 4.4223,
      "step": 95
    },
    {
      "epoch": 0.7413127413127413,
      "grad_norm": 2.504167079925537,
      "learning_rate": 0.00017223954715677627,
      "loss": 4.0045,
      "step": 96
    },
    {
      "epoch": 0.749034749034749,
      "grad_norm": 0.911471962928772,
      "learning_rate": 0.00016978382570131034,
      "loss": 3.5021,
      "step": 97
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 1.0775392055511475,
      "learning_rate": 0.00016732269554543794,
      "loss": 3.7632,
      "step": 98
    },
    {
      "epoch": 0.7644787644787645,
      "grad_norm": 1.1211020946502686,
      "learning_rate": 0.00016485682953756942,
      "loss": 3.7639,
      "step": 99
    },
    {
      "epoch": 0.7722007722007722,
      "grad_norm": 1.113716721534729,
      "learning_rate": 0.00016238690182084986,
      "loss": 3.6035,
      "step": 100
    },
    {
      "epoch": 0.7722007722007722,
      "eval_loss": 0.9697064161300659,
      "eval_runtime": 5.3491,
      "eval_samples_per_second": 9.347,
      "eval_steps_per_second": 1.309,
      "step": 100
    },
    {
      "epoch": 0.7799227799227799,
      "grad_norm": 1.0814489126205444,
      "learning_rate": 0.0001599135876488549,
      "loss": 3.5405,
      "step": 101
    },
    {
      "epoch": 0.7876447876447876,
      "grad_norm": 0.9852569699287415,
      "learning_rate": 0.00015743756320098332,
      "loss": 3.675,
      "step": 102
    },
    {
      "epoch": 0.7953667953667953,
      "grad_norm": 0.8714922070503235,
      "learning_rate": 0.0001549595053975962,
      "loss": 3.4446,
      "step": 103
    },
    {
      "epoch": 0.803088803088803,
      "grad_norm": 0.8799896836280823,
      "learning_rate": 0.00015248009171495378,
      "loss": 3.6148,
      "step": 104
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 1.293359398841858,
      "learning_rate": 0.00015,
      "loss": 3.3241,
      "step": 105
    },
    {
      "epoch": 0.8185328185328186,
      "grad_norm": 0.9777370691299438,
      "learning_rate": 0.00014751990828504622,
      "loss": 3.6845,
      "step": 106
    },
    {
      "epoch": 0.8262548262548263,
      "grad_norm": 0.9750072956085205,
      "learning_rate": 0.00014504049460240375,
      "loss": 3.4494,
      "step": 107
    },
    {
      "epoch": 0.833976833976834,
      "grad_norm": 1.0229166746139526,
      "learning_rate": 0.00014256243679901663,
      "loss": 3.2735,
      "step": 108
    },
    {
      "epoch": 0.8416988416988417,
      "grad_norm": 1.066885232925415,
      "learning_rate": 0.00014008641235114508,
      "loss": 3.4985,
      "step": 109
    },
    {
      "epoch": 0.8494208494208494,
      "grad_norm": 1.0786669254302979,
      "learning_rate": 0.00013761309817915014,
      "loss": 3.3593,
      "step": 110
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.026157259941101,
      "learning_rate": 0.00013514317046243058,
      "loss": 3.3279,
      "step": 111
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 1.2047860622406006,
      "learning_rate": 0.00013267730445456208,
      "loss": 3.2932,
      "step": 112
    },
    {
      "epoch": 0.8725868725868726,
      "grad_norm": 1.2109214067459106,
      "learning_rate": 0.00013021617429868963,
      "loss": 3.5373,
      "step": 113
    },
    {
      "epoch": 0.8803088803088803,
      "grad_norm": 1.4360451698303223,
      "learning_rate": 0.00012776045284322368,
      "loss": 4.342,
      "step": 114
    },
    {
      "epoch": 0.888030888030888,
      "grad_norm": 1.5244028568267822,
      "learning_rate": 0.00012531081145788987,
      "loss": 4.2701,
      "step": 115
    },
    {
      "epoch": 0.8957528957528957,
      "grad_norm": 1.4067096710205078,
      "learning_rate": 0.00012286791985018355,
      "loss": 4.2046,
      "step": 116
    },
    {
      "epoch": 0.9034749034749034,
      "grad_norm": 1.6591242551803589,
      "learning_rate": 0.00012043244588227796,
      "loss": 4.6911,
      "step": 117
    },
    {
      "epoch": 0.9111969111969112,
      "grad_norm": 1.7317063808441162,
      "learning_rate": 0.00011800505538843798,
      "loss": 5.2398,
      "step": 118
    },
    {
      "epoch": 0.918918918918919,
      "grad_norm": 1.7341680526733398,
      "learning_rate": 0.00011558641199298727,
      "loss": 4.8259,
      "step": 119
    },
    {
      "epoch": 0.9266409266409267,
      "grad_norm": 1.5798319578170776,
      "learning_rate": 0.00011317717692888012,
      "loss": 4.5209,
      "step": 120
    },
    {
      "epoch": 0.9343629343629344,
      "grad_norm": 1.6763194799423218,
      "learning_rate": 0.00011077800885692702,
      "loss": 4.6994,
      "step": 121
    },
    {
      "epoch": 0.9420849420849421,
      "grad_norm": 1.6097149848937988,
      "learning_rate": 0.00010838956368572334,
      "loss": 5.0794,
      "step": 122
    },
    {
      "epoch": 0.9498069498069498,
      "grad_norm": 2.604187250137329,
      "learning_rate": 0.0001060124943923303,
      "loss": 4.6673,
      "step": 123
    },
    {
      "epoch": 0.9575289575289575,
      "grad_norm": 1.969926118850708,
      "learning_rate": 0.0001036474508437579,
      "loss": 4.7072,
      "step": 124
    },
    {
      "epoch": 0.9652509652509652,
      "grad_norm": 1.6438111066818237,
      "learning_rate": 0.00010129507961929748,
      "loss": 5.2833,
      "step": 125
    },
    {
      "epoch": 0.9652509652509652,
      "eval_loss": 0.9461151361465454,
      "eval_runtime": 5.3437,
      "eval_samples_per_second": 9.357,
      "eval_steps_per_second": 1.31,
      "step": 125
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 1.9076019525527954,
      "learning_rate": 9.895602383375353e-05,
      "loss": 5.2664,
      "step": 126
    },
    {
      "epoch": 0.9806949806949807,
      "grad_norm": 1.8879812955856323,
      "learning_rate": 9.663092296162251e-05,
      "loss": 4.3967,
      "step": 127
    },
    {
      "epoch": 0.9884169884169884,
      "grad_norm": 2.473862886428833,
      "learning_rate": 9.432041266226686e-05,
      "loss": 4.1485,
      "step": 128
    },
    {
      "epoch": 0.9961389961389961,
      "grad_norm": 1.1409136056900024,
      "learning_rate": 9.202512460613219e-05,
      "loss": 3.8003,
      "step": 129
    },
    {
      "epoch": 1.0038610038610039,
      "grad_norm": 1.3350063562393188,
      "learning_rate": 8.97456863020546e-05,
      "loss": 4.0067,
      "step": 130
    },
    {
      "epoch": 1.0115830115830116,
      "grad_norm": 0.9195145964622498,
      "learning_rate": 8.748272092570646e-05,
      "loss": 3.2715,
      "step": 131
    },
    {
      "epoch": 1.0193050193050193,
      "grad_norm": 0.9917705655097961,
      "learning_rate": 8.523684714922608e-05,
      "loss": 3.3658,
      "step": 132
    },
    {
      "epoch": 1.027027027027027,
      "grad_norm": 0.9408825635910034,
      "learning_rate": 8.300867897207903e-05,
      "loss": 3.4766,
      "step": 133
    },
    {
      "epoch": 1.0347490347490347,
      "grad_norm": 0.9783669710159302,
      "learning_rate": 8.079882555319684e-05,
      "loss": 3.313,
      "step": 134
    },
    {
      "epoch": 1.0424710424710424,
      "grad_norm": 1.037092685699463,
      "learning_rate": 7.860789104443896e-05,
      "loss": 3.1864,
      "step": 135
    },
    {
      "epoch": 1.05019305019305,
      "grad_norm": 1.0254372358322144,
      "learning_rate": 7.643647442542382e-05,
      "loss": 3.1248,
      "step": 136
    },
    {
      "epoch": 1.057915057915058,
      "grad_norm": 0.9661920070648193,
      "learning_rate": 7.428516933977347e-05,
      "loss": 3.2942,
      "step": 137
    },
    {
      "epoch": 1.0656370656370657,
      "grad_norm": 0.9666591286659241,
      "learning_rate": 7.215456393281776e-05,
      "loss": 3.0228,
      "step": 138
    },
    {
      "epoch": 1.0733590733590734,
      "grad_norm": 0.9560402631759644,
      "learning_rate": 7.004524069080096e-05,
      "loss": 3.1348,
      "step": 139
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.9567746520042419,
      "learning_rate": 6.795777628163599e-05,
      "loss": 2.9588,
      "step": 140
    },
    {
      "epoch": 1.0888030888030888,
      "grad_norm": 1.0468031167984009,
      "learning_rate": 6.58927413972491e-05,
      "loss": 3.0136,
      "step": 141
    },
    {
      "epoch": 1.0965250965250966,
      "grad_norm": 1.105804443359375,
      "learning_rate": 6.385070059755846e-05,
      "loss": 2.9526,
      "step": 142
    },
    {
      "epoch": 1.1042471042471043,
      "grad_norm": 1.1531401872634888,
      "learning_rate": 6.183221215612904e-05,
      "loss": 2.9225,
      "step": 143
    },
    {
      "epoch": 1.111969111969112,
      "grad_norm": 1.205812692642212,
      "learning_rate": 5.983782790754623e-05,
      "loss": 3.1323,
      "step": 144
    },
    {
      "epoch": 1.1196911196911197,
      "grad_norm": 1.1785130500793457,
      "learning_rate": 5.786809309654982e-05,
      "loss": 2.7042,
      "step": 145
    },
    {
      "epoch": 1.1274131274131274,
      "grad_norm": 1.4720457792282104,
      "learning_rate": 5.592354622896944e-05,
      "loss": 3.406,
      "step": 146
    },
    {
      "epoch": 1.135135135135135,
      "grad_norm": 1.4923970699310303,
      "learning_rate": 5.40047189245025e-05,
      "loss": 3.3196,
      "step": 147
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.756646752357483,
      "learning_rate": 5.211213577137469e-05,
      "loss": 3.5537,
      "step": 148
    },
    {
      "epoch": 1.1505791505791505,
      "grad_norm": 1.7553679943084717,
      "learning_rate": 5.024631418292274e-05,
      "loss": 3.627,
      "step": 149
    },
    {
      "epoch": 1.1583011583011582,
      "grad_norm": 1.7934798002243042,
      "learning_rate": 4.840776425613886e-05,
      "loss": 3.9637,
      "step": 150
    },
    {
      "epoch": 1.1583011583011582,
      "eval_loss": 0.8916868567466736,
      "eval_runtime": 5.3655,
      "eval_samples_per_second": 9.319,
      "eval_steps_per_second": 1.305,
      "step": 150
    },
    {
      "epoch": 1.166023166023166,
      "grad_norm": 1.7999972105026245,
      "learning_rate": 4.659698863221513e-05,
      "loss": 4.194,
      "step": 151
    },
    {
      "epoch": 1.1737451737451738,
      "grad_norm": 2.0590758323669434,
      "learning_rate": 4.481448235912671e-05,
      "loss": 4.3798,
      "step": 152
    },
    {
      "epoch": 1.1814671814671815,
      "grad_norm": 1.7075778245925903,
      "learning_rate": 4.306073275629044e-05,
      "loss": 3.6218,
      "step": 153
    },
    {
      "epoch": 1.1891891891891893,
      "grad_norm": 1.822914481163025,
      "learning_rate": 4.133621928133665e-05,
      "loss": 4.1097,
      "step": 154
    },
    {
      "epoch": 1.196911196911197,
      "grad_norm": 1.7491306066513062,
      "learning_rate": 3.964141339903026e-05,
      "loss": 3.969,
      "step": 155
    },
    {
      "epoch": 1.2046332046332047,
      "grad_norm": 1.8288490772247314,
      "learning_rate": 3.797677845237696e-05,
      "loss": 4.5371,
      "step": 156
    },
    {
      "epoch": 1.2123552123552124,
      "grad_norm": 1.784482717514038,
      "learning_rate": 3.634276953594982e-05,
      "loss": 3.7527,
      "step": 157
    },
    {
      "epoch": 1.22007722007722,
      "grad_norm": 1.966124176979065,
      "learning_rate": 3.473983337147118e-05,
      "loss": 4.3173,
      "step": 158
    },
    {
      "epoch": 1.2277992277992278,
      "grad_norm": 1.9975626468658447,
      "learning_rate": 3.316840818568315e-05,
      "loss": 4.6156,
      "step": 159
    },
    {
      "epoch": 1.2355212355212355,
      "grad_norm": 2.316918134689331,
      "learning_rate": 3.162892359054098e-05,
      "loss": 4.0331,
      "step": 160
    },
    {
      "epoch": 1.2432432432432432,
      "grad_norm": 2.4572503566741943,
      "learning_rate": 3.0121800465761293e-05,
      "loss": 3.5958,
      "step": 161
    },
    {
      "epoch": 1.250965250965251,
      "grad_norm": 2.1423158645629883,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 3.1944,
      "step": 162
    },
    {
      "epoch": 1.2586872586872586,
      "grad_norm": 1.1138101816177368,
      "learning_rate": 2.7206277796996144e-05,
      "loss": 3.0913,
      "step": 163
    },
    {
      "epoch": 1.2664092664092665,
      "grad_norm": 0.9798049926757812,
      "learning_rate": 2.5798675327796993e-05,
      "loss": 3.2327,
      "step": 164
    },
    {
      "epoch": 1.2741312741312742,
      "grad_norm": 0.974193274974823,
      "learning_rate": 2.4425028260620715e-05,
      "loss": 3.1556,
      "step": 165
    },
    {
      "epoch": 1.281853281853282,
      "grad_norm": 1.0049970149993896,
      "learning_rate": 2.3085712136859668e-05,
      "loss": 2.9129,
      "step": 166
    },
    {
      "epoch": 1.2895752895752897,
      "grad_norm": 0.9587703347206116,
      "learning_rate": 2.178109311216913e-05,
      "loss": 3.1648,
      "step": 167
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": 0.9530733227729797,
      "learning_rate": 2.0511527856363912e-05,
      "loss": 2.9332,
      "step": 168
    },
    {
      "epoch": 1.305019305019305,
      "grad_norm": 0.9956369400024414,
      "learning_rate": 1.927736345590839e-05,
      "loss": 3.1722,
      "step": 169
    },
    {
      "epoch": 1.3127413127413128,
      "grad_norm": 1.0111753940582275,
      "learning_rate": 1.8078937319026654e-05,
      "loss": 3.1122,
      "step": 170
    },
    {
      "epoch": 1.3204633204633205,
      "grad_norm": 1.0399214029312134,
      "learning_rate": 1.6916577083458228e-05,
      "loss": 3.141,
      "step": 171
    },
    {
      "epoch": 1.3281853281853282,
      "grad_norm": 1.0311812162399292,
      "learning_rate": 1.579060052688548e-05,
      "loss": 3.0995,
      "step": 172
    },
    {
      "epoch": 1.335907335907336,
      "grad_norm": 1.0047649145126343,
      "learning_rate": 1.4701315480056164e-05,
      "loss": 2.8465,
      "step": 173
    },
    {
      "epoch": 1.3436293436293436,
      "grad_norm": 1.0682458877563477,
      "learning_rate": 1.3649019742625623e-05,
      "loss": 2.9523,
      "step": 174
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 1.0513615608215332,
      "learning_rate": 1.2634001001741373e-05,
      "loss": 3.0281,
      "step": 175
    },
    {
      "epoch": 1.3513513513513513,
      "eval_loss": 0.8898646831512451,
      "eval_runtime": 5.3569,
      "eval_samples_per_second": 9.334,
      "eval_steps_per_second": 1.307,
      "step": 175
    },
    {
      "epoch": 1.359073359073359,
      "grad_norm": 1.0834391117095947,
      "learning_rate": 1.1656536753392287e-05,
      "loss": 2.8727,
      "step": 176
    },
    {
      "epoch": 1.3667953667953667,
      "grad_norm": 1.0857892036437988,
      "learning_rate": 1.0716894226543953e-05,
      "loss": 2.9288,
      "step": 177
    },
    {
      "epoch": 1.3745173745173744,
      "grad_norm": 1.1154727935791016,
      "learning_rate": 9.815330310080887e-06,
      "loss": 3.056,
      "step": 178
    },
    {
      "epoch": 1.3822393822393821,
      "grad_norm": 1.1769471168518066,
      "learning_rate": 8.952091482575824e-06,
      "loss": 3.2476,
      "step": 179
    },
    {
      "epoch": 1.3899613899613898,
      "grad_norm": 1.2554057836532593,
      "learning_rate": 8.127413744904804e-06,
      "loss": 3.6617,
      "step": 180
    },
    {
      "epoch": 1.3976833976833976,
      "grad_norm": 1.3026721477508545,
      "learning_rate": 7.34152255572697e-06,
      "loss": 3.8659,
      "step": 181
    },
    {
      "epoch": 1.4054054054054055,
      "grad_norm": 1.4275637865066528,
      "learning_rate": 6.594632769846353e-06,
      "loss": 3.8521,
      "step": 182
    },
    {
      "epoch": 1.4131274131274132,
      "grad_norm": 1.5288902521133423,
      "learning_rate": 5.886948579472778e-06,
      "loss": 4.0976,
      "step": 183
    },
    {
      "epoch": 1.420849420849421,
      "grad_norm": 1.5545921325683594,
      "learning_rate": 5.218663458397715e-06,
      "loss": 3.9859,
      "step": 184
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.745778203010559,
      "learning_rate": 4.589960109100444e-06,
      "loss": 4.0148,
      "step": 185
    },
    {
      "epoch": 1.4362934362934363,
      "grad_norm": 1.7549493312835693,
      "learning_rate": 4.001010412799138e-06,
      "loss": 4.2167,
      "step": 186
    },
    {
      "epoch": 1.444015444015444,
      "grad_norm": 1.7042094469070435,
      "learning_rate": 3.451975382460109e-06,
      "loss": 3.9454,
      "step": 187
    },
    {
      "epoch": 1.4517374517374517,
      "grad_norm": 1.8767509460449219,
      "learning_rate": 2.9430051187785962e-06,
      "loss": 3.8077,
      "step": 188
    },
    {
      "epoch": 1.4594594594594594,
      "grad_norm": 1.7444730997085571,
      "learning_rate": 2.4742387691426445e-06,
      "loss": 3.3349,
      "step": 189
    },
    {
      "epoch": 1.4671814671814671,
      "grad_norm": 1.981868863105774,
      "learning_rate": 2.0458044895916513e-06,
      "loss": 4.0558,
      "step": 190
    },
    {
      "epoch": 1.4749034749034748,
      "grad_norm": 2.037660837173462,
      "learning_rate": 1.6578194097797258e-06,
      "loss": 3.9423,
      "step": 191
    },
    {
      "epoch": 1.4826254826254825,
      "grad_norm": 2.352879524230957,
      "learning_rate": 1.3103896009537207e-06,
      "loss": 4.1185,
      "step": 192
    },
    {
      "epoch": 1.4903474903474905,
      "grad_norm": 2.6159369945526123,
      "learning_rate": 1.0036100469542786e-06,
      "loss": 3.4655,
      "step": 193
    },
    {
      "epoch": 1.4980694980694982,
      "grad_norm": 2.1394124031066895,
      "learning_rate": 7.375646182482875e-07,
      "loss": 2.7503,
      "step": 194
    },
    {
      "epoch": 1.505791505791506,
      "grad_norm": 0.937629759311676,
      "learning_rate": 5.123260489995229e-07,
      "loss": 2.9738,
      "step": 195
    },
    {
      "epoch": 1.5135135135135136,
      "grad_norm": 0.8871747255325317,
      "learning_rate": 3.2795591718381975e-07,
      "loss": 3.104,
      "step": 196
    },
    {
      "epoch": 1.5212355212355213,
      "grad_norm": 0.9106766581535339,
      "learning_rate": 1.8450462775428942e-07,
      "loss": 3.083,
      "step": 197
    },
    {
      "epoch": 1.528957528957529,
      "grad_norm": 0.8707587718963623,
      "learning_rate": 8.201139886109264e-08,
      "loss": 2.8924,
      "step": 198
    },
    {
      "epoch": 1.5366795366795367,
      "grad_norm": 0.8944032788276672,
      "learning_rate": 2.0504251129649374e-08,
      "loss": 2.991,
      "step": 199
    },
    {
      "epoch": 1.5444015444015444,
      "grad_norm": 0.9251424670219421,
      "learning_rate": 0.0,
      "loss": 2.9376,
      "step": 200
    },
    {
      "epoch": 1.5444015444015444,
      "eval_loss": 0.8602708578109741,
      "eval_runtime": 5.3475,
      "eval_samples_per_second": 9.35,
      "eval_steps_per_second": 1.309,
      "step": 200
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.804996985889751e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}