{
  "best_metric": 1.4313876628875732,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.951338199513382,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009732360097323601,
      "grad_norm": 2.561129570007324,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.2346,
      "step": 1
    },
    {
      "epoch": 0.009732360097323601,
      "eval_loss": 2.790834903717041,
      "eval_runtime": 8.4988,
      "eval_samples_per_second": 20.356,
      "eval_steps_per_second": 10.237,
      "step": 1
    },
    {
      "epoch": 0.019464720194647202,
      "grad_norm": 2.8345415592193604,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.4613,
      "step": 2
    },
    {
      "epoch": 0.029197080291970802,
      "grad_norm": 2.73110294342041,
      "learning_rate": 1e-05,
      "loss": 1.4969,
      "step": 3
    },
    {
      "epoch": 0.038929440389294405,
      "grad_norm": 3.0560357570648193,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.82,
      "step": 4
    },
    {
      "epoch": 0.04866180048661801,
      "grad_norm": 2.894944429397583,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.6151,
      "step": 5
    },
    {
      "epoch": 0.058394160583941604,
      "grad_norm": 3.1693663597106934,
      "learning_rate": 2e-05,
      "loss": 1.738,
      "step": 6
    },
    {
      "epoch": 0.0681265206812652,
      "grad_norm": 2.4796085357666016,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 1.5731,
      "step": 7
    },
    {
      "epoch": 0.07785888077858881,
      "grad_norm": 2.3419411182403564,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.8261,
      "step": 8
    },
    {
      "epoch": 0.08759124087591241,
      "grad_norm": 2.226973295211792,
      "learning_rate": 3e-05,
      "loss": 1.6176,
      "step": 9
    },
    {
      "epoch": 0.09732360097323602,
      "grad_norm": 2.4438183307647705,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.8584,
      "step": 10
    },
    {
      "epoch": 0.1070559610705596,
      "grad_norm": 2.081064462661743,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 1.5844,
      "step": 11
    },
    {
      "epoch": 0.11678832116788321,
      "grad_norm": 2.120450019836426,
      "learning_rate": 4e-05,
      "loss": 1.8517,
      "step": 12
    },
    {
      "epoch": 0.12652068126520682,
      "grad_norm": 1.9778972864151,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 1.8444,
      "step": 13
    },
    {
      "epoch": 0.1362530413625304,
      "grad_norm": 2.3344366550445557,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.8748,
      "step": 14
    },
    {
      "epoch": 0.145985401459854,
      "grad_norm": 2.5431606769561768,
      "learning_rate": 5e-05,
      "loss": 1.9008,
      "step": 15
    },
    {
      "epoch": 0.15571776155717762,
      "grad_norm": 4.447021961212158,
      "learning_rate": 5.333333333333333e-05,
      "loss": 2.1142,
      "step": 16
    },
    {
      "epoch": 0.1654501216545012,
      "grad_norm": 2.817978620529175,
      "learning_rate": 5.666666666666667e-05,
      "loss": 2.2744,
      "step": 17
    },
    {
      "epoch": 0.17518248175182483,
      "grad_norm": 2.8833377361297607,
      "learning_rate": 6e-05,
      "loss": 2.02,
      "step": 18
    },
    {
      "epoch": 0.18491484184914841,
      "grad_norm": 3.51873779296875,
      "learning_rate": 6.333333333333333e-05,
      "loss": 2.0815,
      "step": 19
    },
    {
      "epoch": 0.19464720194647203,
      "grad_norm": 3.589921236038208,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.0436,
      "step": 20
    },
    {
      "epoch": 0.20437956204379562,
      "grad_norm": 3.756092071533203,
      "learning_rate": 7e-05,
      "loss": 2.2747,
      "step": 21
    },
    {
      "epoch": 0.2141119221411192,
      "grad_norm": 4.150580883026123,
      "learning_rate": 7.333333333333333e-05,
      "loss": 2.356,
      "step": 22
    },
    {
      "epoch": 0.22384428223844283,
      "grad_norm": 4.673558235168457,
      "learning_rate": 7.666666666666667e-05,
      "loss": 2.0281,
      "step": 23
    },
    {
      "epoch": 0.23357664233576642,
      "grad_norm": 5.720743656158447,
      "learning_rate": 8e-05,
      "loss": 2.4525,
      "step": 24
    },
    {
      "epoch": 0.24330900243309003,
      "grad_norm": 6.601008415222168,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.8416,
      "step": 25
    },
    {
      "epoch": 0.25304136253041365,
      "grad_norm": 1.5111806392669678,
      "learning_rate": 8.666666666666667e-05,
      "loss": 1.4464,
      "step": 26
    },
    {
      "epoch": 0.26277372262773724,
      "grad_norm": 1.3955457210540771,
      "learning_rate": 9e-05,
      "loss": 1.2069,
      "step": 27
    },
    {
      "epoch": 0.2725060827250608,
      "grad_norm": 1.3112324476242065,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.4838,
      "step": 28
    },
    {
      "epoch": 0.2822384428223844,
      "grad_norm": 1.112937331199646,
      "learning_rate": 9.666666666666667e-05,
      "loss": 1.1667,
      "step": 29
    },
    {
      "epoch": 0.291970802919708,
      "grad_norm": 1.1505944728851318,
      "learning_rate": 0.0001,
      "loss": 1.4673,
      "step": 30
    },
    {
      "epoch": 0.30170316301703165,
      "grad_norm": 1.3048782348632812,
      "learning_rate": 9.999146252290264e-05,
      "loss": 1.7036,
      "step": 31
    },
    {
      "epoch": 0.31143552311435524,
      "grad_norm": 1.2255563735961914,
      "learning_rate": 9.996585300715116e-05,
      "loss": 1.3834,
      "step": 32
    },
    {
      "epoch": 0.32116788321167883,
      "grad_norm": 1.2667236328125,
      "learning_rate": 9.99231801983717e-05,
      "loss": 1.4415,
      "step": 33
    },
    {
      "epoch": 0.3309002433090024,
      "grad_norm": 1.4525693655014038,
      "learning_rate": 9.986345866928941e-05,
      "loss": 1.4059,
      "step": 34
    },
    {
      "epoch": 0.340632603406326,
      "grad_norm": 1.4886246919631958,
      "learning_rate": 9.978670881475172e-05,
      "loss": 1.6845,
      "step": 35
    },
    {
      "epoch": 0.35036496350364965,
      "grad_norm": 1.4919886589050293,
      "learning_rate": 9.96929568447637e-05,
      "loss": 1.5118,
      "step": 36
    },
    {
      "epoch": 0.36009732360097324,
      "grad_norm": 1.5687556266784668,
      "learning_rate": 9.958223477553714e-05,
      "loss": 1.6167,
      "step": 37
    },
    {
      "epoch": 0.36982968369829683,
      "grad_norm": 1.4886263608932495,
      "learning_rate": 9.94545804185573e-05,
      "loss": 1.6128,
      "step": 38
    },
    {
      "epoch": 0.3795620437956204,
      "grad_norm": 1.7041724920272827,
      "learning_rate": 9.931003736767013e-05,
      "loss": 1.6574,
      "step": 39
    },
    {
      "epoch": 0.38929440389294406,
      "grad_norm": 1.9276127815246582,
      "learning_rate": 9.91486549841951e-05,
      "loss": 1.7981,
      "step": 40
    },
    {
      "epoch": 0.39902676399026765,
      "grad_norm": 1.9765902757644653,
      "learning_rate": 9.89704883800683e-05,
      "loss": 1.6794,
      "step": 41
    },
    {
      "epoch": 0.40875912408759124,
      "grad_norm": 2.283078908920288,
      "learning_rate": 9.877559839902184e-05,
      "loss": 1.8731,
      "step": 42
    },
    {
      "epoch": 0.41849148418491483,
      "grad_norm": 2.033916473388672,
      "learning_rate": 9.85640515958057e-05,
      "loss": 1.7398,
      "step": 43
    },
    {
      "epoch": 0.4282238442822384,
      "grad_norm": 2.406275510787964,
      "learning_rate": 9.833592021345937e-05,
      "loss": 2.1072,
      "step": 44
    },
    {
      "epoch": 0.43795620437956206,
      "grad_norm": 2.896510601043701,
      "learning_rate": 9.809128215864097e-05,
      "loss": 1.7025,
      "step": 45
    },
    {
      "epoch": 0.44768856447688565,
      "grad_norm": 3.435720920562744,
      "learning_rate": 9.783022097502204e-05,
      "loss": 2.1374,
      "step": 46
    },
    {
      "epoch": 0.45742092457420924,
      "grad_norm": 3.6062421798706055,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.2205,
      "step": 47
    },
    {
      "epoch": 0.46715328467153283,
      "grad_norm": 4.2540764808654785,
      "learning_rate": 9.725919140804099e-05,
      "loss": 2.0222,
      "step": 48
    },
    {
      "epoch": 0.4768856447688564,
      "grad_norm": 5.007321834564209,
      "learning_rate": 9.694941803075283e-05,
      "loss": 2.4715,
      "step": 49
    },
    {
      "epoch": 0.48661800486618007,
      "grad_norm": 6.096455097198486,
      "learning_rate": 9.662361147021779e-05,
      "loss": 2.1,
      "step": 50
    },
    {
      "epoch": 0.48661800486618007,
      "eval_loss": 1.6414257287979126,
      "eval_runtime": 8.5066,
      "eval_samples_per_second": 20.337,
      "eval_steps_per_second": 10.227,
      "step": 50
    },
    {
      "epoch": 0.49635036496350365,
      "grad_norm": 1.1391383409500122,
      "learning_rate": 9.628188298907782e-05,
      "loss": 1.2541,
      "step": 51
    },
    {
      "epoch": 0.5060827250608273,
      "grad_norm": 1.1661523580551147,
      "learning_rate": 9.592434928729616e-05,
      "loss": 1.2535,
      "step": 52
    },
    {
      "epoch": 0.5158150851581509,
      "grad_norm": 1.1368708610534668,
      "learning_rate": 9.555113246230442e-05,
      "loss": 1.3312,
      "step": 53
    },
    {
      "epoch": 0.5255474452554745,
      "grad_norm": 1.2222440242767334,
      "learning_rate": 9.516235996730645e-05,
      "loss": 1.4968,
      "step": 54
    },
    {
      "epoch": 0.5352798053527981,
      "grad_norm": 1.0211539268493652,
      "learning_rate": 9.475816456775313e-05,
      "loss": 1.2689,
      "step": 55
    },
    {
      "epoch": 0.5450121654501217,
      "grad_norm": 1.1477605104446411,
      "learning_rate": 9.43386842960031e-05,
      "loss": 1.3366,
      "step": 56
    },
    {
      "epoch": 0.5547445255474452,
      "grad_norm": 1.2544337511062622,
      "learning_rate": 9.39040624041849e-05,
      "loss": 1.3807,
      "step": 57
    },
    {
      "epoch": 0.5644768856447688,
      "grad_norm": 1.1475023031234741,
      "learning_rate": 9.345444731527642e-05,
      "loss": 1.4254,
      "step": 58
    },
    {
      "epoch": 0.5742092457420924,
      "grad_norm": 1.4840086698532104,
      "learning_rate": 9.298999257241863e-05,
      "loss": 1.5814,
      "step": 59
    },
    {
      "epoch": 0.583941605839416,
      "grad_norm": 1.42258882522583,
      "learning_rate": 9.251085678648072e-05,
      "loss": 1.5854,
      "step": 60
    },
    {
      "epoch": 0.5936739659367397,
      "grad_norm": 1.4192280769348145,
      "learning_rate": 9.201720358189464e-05,
      "loss": 1.3861,
      "step": 61
    },
    {
      "epoch": 0.6034063260340633,
      "grad_norm": 1.545946717262268,
      "learning_rate": 9.150920154077754e-05,
      "loss": 1.6667,
      "step": 62
    },
    {
      "epoch": 0.6131386861313869,
      "grad_norm": 1.5429267883300781,
      "learning_rate": 9.098702414536107e-05,
      "loss": 1.6165,
      "step": 63
    },
    {
      "epoch": 0.6228710462287105,
      "grad_norm": 1.6278637647628784,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6723,
      "step": 64
    },
    {
      "epoch": 0.6326034063260341,
      "grad_norm": 1.791162371635437,
      "learning_rate": 8.9900861364012e-05,
      "loss": 1.5965,
      "step": 65
    },
    {
      "epoch": 0.6423357664233577,
      "grad_norm": 1.8076893091201782,
      "learning_rate": 8.933724690167417e-05,
      "loss": 1.411,
      "step": 66
    },
    {
      "epoch": 0.6520681265206812,
      "grad_norm": 1.8186296224594116,
      "learning_rate": 8.876019880555649e-05,
      "loss": 1.7853,
      "step": 67
    },
    {
      "epoch": 0.6618004866180048,
      "grad_norm": 2.107891321182251,
      "learning_rate": 8.816991413705516e-05,
      "loss": 2.0107,
      "step": 68
    },
    {
      "epoch": 0.6715328467153284,
      "grad_norm": 2.3741533756256104,
      "learning_rate": 8.756659447784368e-05,
      "loss": 1.7998,
      "step": 69
    },
    {
      "epoch": 0.681265206812652,
      "grad_norm": 2.356527328491211,
      "learning_rate": 8.695044586103296e-05,
      "loss": 1.6174,
      "step": 70
    },
    {
      "epoch": 0.6909975669099757,
      "grad_norm": 2.934279203414917,
      "learning_rate": 8.632167870081121e-05,
      "loss": 1.718,
      "step": 71
    },
    {
      "epoch": 0.7007299270072993,
      "grad_norm": 2.9609880447387695,
      "learning_rate": 8.568050772058762e-05,
      "loss": 2.0726,
      "step": 72
    },
    {
      "epoch": 0.7104622871046229,
      "grad_norm": 3.2685890197753906,
      "learning_rate": 8.502715187966455e-05,
      "loss": 1.755,
      "step": 73
    },
    {
      "epoch": 0.7201946472019465,
      "grad_norm": 4.2150726318359375,
      "learning_rate": 8.436183429846313e-05,
      "loss": 2.178,
      "step": 74
    },
    {
      "epoch": 0.7299270072992701,
      "grad_norm": 4.920742511749268,
      "learning_rate": 8.368478218232787e-05,
      "loss": 2.1087,
      "step": 75
    },
    {
      "epoch": 0.7396593673965937,
      "grad_norm": 0.9526451826095581,
      "learning_rate": 8.299622674393614e-05,
      "loss": 1.5099,
      "step": 76
    },
    {
      "epoch": 0.7493917274939172,
      "grad_norm": 0.8414137363433838,
      "learning_rate": 8.229640312433937e-05,
      "loss": 1.2436,
      "step": 77
    },
    {
      "epoch": 0.7591240875912408,
      "grad_norm": 0.8733347058296204,
      "learning_rate": 8.158555031266254e-05,
      "loss": 1.1234,
      "step": 78
    },
    {
      "epoch": 0.7688564476885644,
      "grad_norm": 1.00202214717865,
      "learning_rate": 8.086391106448965e-05,
      "loss": 1.3466,
      "step": 79
    },
    {
      "epoch": 0.7785888077858881,
      "grad_norm": 1.0467771291732788,
      "learning_rate": 8.013173181896283e-05,
      "loss": 1.3533,
      "step": 80
    },
    {
      "epoch": 0.7883211678832117,
      "grad_norm": 1.020969271659851,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.1149,
      "step": 81
    },
    {
      "epoch": 0.7980535279805353,
      "grad_norm": 1.2848833799362183,
      "learning_rate": 7.863675700402526e-05,
      "loss": 1.5418,
      "step": 82
    },
    {
      "epoch": 0.8077858880778589,
      "grad_norm": 1.0578773021697998,
      "learning_rate": 7.787447196714427e-05,
      "loss": 1.2322,
      "step": 83
    },
    {
      "epoch": 0.8175182481751825,
      "grad_norm": 1.1764395236968994,
      "learning_rate": 7.710266782362247e-05,
      "loss": 1.4151,
      "step": 84
    },
    {
      "epoch": 0.8272506082725061,
      "grad_norm": 1.1490318775177002,
      "learning_rate": 7.63216081438678e-05,
      "loss": 1.3977,
      "step": 85
    },
    {
      "epoch": 0.8369829683698297,
      "grad_norm": 1.2954095602035522,
      "learning_rate": 7.553155965904535e-05,
      "loss": 1.5416,
      "step": 86
    },
    {
      "epoch": 0.8467153284671532,
      "grad_norm": 1.3160747289657593,
      "learning_rate": 7.473279216998895e-05,
      "loss": 1.5042,
      "step": 87
    },
    {
      "epoch": 0.8564476885644768,
      "grad_norm": 1.409975528717041,
      "learning_rate": 7.392557845506432e-05,
      "loss": 1.4701,
      "step": 88
    },
    {
      "epoch": 0.8661800486618005,
      "grad_norm": 1.3988336324691772,
      "learning_rate": 7.311019417701566e-05,
      "loss": 1.45,
      "step": 89
    },
    {
      "epoch": 0.8759124087591241,
      "grad_norm": 1.5642749071121216,
      "learning_rate": 7.228691778882693e-05,
      "loss": 1.3627,
      "step": 90
    },
    {
      "epoch": 0.8856447688564477,
      "grad_norm": 1.7261797189712524,
      "learning_rate": 7.145603043863045e-05,
      "loss": 1.6223,
      "step": 91
    },
    {
      "epoch": 0.8953771289537713,
      "grad_norm": 1.9605493545532227,
      "learning_rate": 7.061781587369519e-05,
      "loss": 1.6284,
      "step": 92
    },
    {
      "epoch": 0.9051094890510949,
      "grad_norm": 2.0385546684265137,
      "learning_rate": 6.977256034352712e-05,
      "loss": 1.8184,
      "step": 93
    },
    {
      "epoch": 0.9148418491484185,
      "grad_norm": 2.2109363079071045,
      "learning_rate": 6.892055250211552e-05,
      "loss": 2.017,
      "step": 94
    },
    {
      "epoch": 0.9245742092457421,
      "grad_norm": 2.3940110206604004,
      "learning_rate": 6.806208330935766e-05,
      "loss": 1.8573,
      "step": 95
    },
    {
      "epoch": 0.9343065693430657,
      "grad_norm": 3.0049099922180176,
      "learning_rate": 6.719744593169641e-05,
      "loss": 1.8005,
      "step": 96
    },
    {
      "epoch": 0.9440389294403893,
      "grad_norm": 3.1753697395324707,
      "learning_rate": 6.632693564200416e-05,
      "loss": 1.9637,
      "step": 97
    },
    {
      "epoch": 0.9537712895377128,
      "grad_norm": 3.117792844772339,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7955,
      "step": 98
    },
    {
      "epoch": 0.9635036496350365,
      "grad_norm": 3.933270215988159,
      "learning_rate": 6.456948734446624e-05,
      "loss": 1.7495,
      "step": 99
    },
    {
      "epoch": 0.9732360097323601,
      "grad_norm": 4.156220436096191,
      "learning_rate": 6.368314950360415e-05,
      "loss": 1.9626,
      "step": 100
    },
    {
      "epoch": 0.9732360097323601,
      "eval_loss": 1.4313876628875732,
      "eval_runtime": 8.544,
      "eval_samples_per_second": 20.248,
      "eval_steps_per_second": 10.183,
      "step": 100
    },
    {
      "epoch": 0.9829683698296837,
      "grad_norm": 0.8358758687973022,
      "learning_rate": 6.279213887972179e-05,
      "loss": 1.1099,
      "step": 101
    },
    {
      "epoch": 0.9927007299270073,
      "grad_norm": 1.8137092590332031,
      "learning_rate": 6.189675975213094e-05,
      "loss": 1.5814,
      "step": 102
    },
    {
      "epoch": 1.0072992700729928,
      "grad_norm": 5.907174110412598,
      "learning_rate": 6.099731789198344e-05,
      "loss": 2.7366,
      "step": 103
    },
    {
      "epoch": 1.0170316301703164,
      "grad_norm": 0.7866008281707764,
      "learning_rate": 6.009412045785051e-05,
      "loss": 1.1892,
      "step": 104
    },
    {
      "epoch": 1.02676399026764,
      "grad_norm": 0.7891255021095276,
      "learning_rate": 5.918747589082853e-05,
      "loss": 1.0516,
      "step": 105
    },
    {
      "epoch": 1.0364963503649636,
      "grad_norm": 0.8564149737358093,
      "learning_rate": 5.82776938092065e-05,
      "loss": 1.2148,
      "step": 106
    },
    {
      "epoch": 1.0462287104622872,
      "grad_norm": 0.8796920776367188,
      "learning_rate": 5.736508490273188e-05,
      "loss": 1.1409,
      "step": 107
    },
    {
      "epoch": 1.0559610705596107,
      "grad_norm": 0.8622186183929443,
      "learning_rate": 5.644996082651017e-05,
      "loss": 0.992,
      "step": 108
    },
    {
      "epoch": 1.0656934306569343,
      "grad_norm": 0.9955086708068848,
      "learning_rate": 5.553263409457504e-05,
      "loss": 0.9974,
      "step": 109
    },
    {
      "epoch": 1.075425790754258,
      "grad_norm": 1.0158140659332275,
      "learning_rate": 5.4613417973165106e-05,
      "loss": 1.1488,
      "step": 110
    },
    {
      "epoch": 1.0851581508515815,
      "grad_norm": 0.9220258593559265,
      "learning_rate": 5.3692626373743706e-05,
      "loss": 0.8071,
      "step": 111
    },
    {
      "epoch": 1.094890510948905,
      "grad_norm": 1.199191927909851,
      "learning_rate": 5.27705737457985e-05,
      "loss": 1.231,
      "step": 112
    },
    {
      "epoch": 1.1046228710462287,
      "grad_norm": 1.2195113897323608,
      "learning_rate": 5.184757496945726e-05,
      "loss": 1.1174,
      "step": 113
    },
    {
      "epoch": 1.1143552311435523,
      "grad_norm": 1.2885240316390991,
      "learning_rate": 5.092394524795649e-05,
      "loss": 0.9545,
      "step": 114
    },
    {
      "epoch": 1.1240875912408759,
      "grad_norm": 1.7053508758544922,
      "learning_rate": 5e-05,
      "loss": 1.4258,
      "step": 115
    },
    {
      "epoch": 1.1338199513381995,
      "grad_norm": 1.5056861639022827,
      "learning_rate": 4.907605475204352e-05,
      "loss": 1.1604,
      "step": 116
    },
    {
      "epoch": 1.143552311435523,
      "grad_norm": 1.7398154735565186,
      "learning_rate": 4.8152425030542766e-05,
      "loss": 0.9835,
      "step": 117
    },
    {
      "epoch": 1.1532846715328466,
      "grad_norm": 1.9436665773391724,
      "learning_rate": 4.72294262542015e-05,
      "loss": 1.1363,
      "step": 118
    },
    {
      "epoch": 1.1630170316301702,
      "grad_norm": 1.9951790571212769,
      "learning_rate": 4.6307373626256306e-05,
      "loss": 1.1854,
      "step": 119
    },
    {
      "epoch": 1.172749391727494,
      "grad_norm": 2.1532411575317383,
      "learning_rate": 4.5386582026834906e-05,
      "loss": 1.2723,
      "step": 120
    },
    {
      "epoch": 1.1824817518248176,
      "grad_norm": 2.4043993949890137,
      "learning_rate": 4.446736590542497e-05,
      "loss": 1.0575,
      "step": 121
    },
    {
      "epoch": 1.1922141119221412,
      "grad_norm": 4.176510334014893,
      "learning_rate": 4.3550039173489845e-05,
      "loss": 1.182,
      "step": 122
    },
    {
      "epoch": 1.2019464720194648,
      "grad_norm": 3.3336949348449707,
      "learning_rate": 4.2634915097268115e-05,
      "loss": 1.3804,
      "step": 123
    },
    {
      "epoch": 1.2116788321167884,
      "grad_norm": 3.177910804748535,
      "learning_rate": 4.1722306190793495e-05,
      "loss": 0.9483,
      "step": 124
    },
    {
      "epoch": 1.221411192214112,
      "grad_norm": 3.3130061626434326,
      "learning_rate": 4.0812524109171476e-05,
      "loss": 0.9993,
      "step": 125
    },
    {
      "epoch": 1.2311435523114356,
      "grad_norm": 3.794668197631836,
      "learning_rate": 3.99058795421495e-05,
      "loss": 1.0756,
      "step": 126
    },
    {
      "epoch": 1.2408759124087592,
      "grad_norm": 4.657321453094482,
      "learning_rate": 3.9002682108016585e-05,
      "loss": 1.2689,
      "step": 127
    },
    {
      "epoch": 1.2506082725060828,
      "grad_norm": 2.611271858215332,
      "learning_rate": 3.8103240247869075e-05,
      "loss": 1.172,
      "step": 128
    },
    {
      "epoch": 1.2603406326034063,
      "grad_norm": 1.1134867668151855,
      "learning_rate": 3.720786112027822e-05,
      "loss": 1.1583,
      "step": 129
    },
    {
      "epoch": 1.27007299270073,
      "grad_norm": 0.9907546043395996,
      "learning_rate": 3.631685049639586e-05,
      "loss": 0.7971,
      "step": 130
    },
    {
      "epoch": 1.2798053527980535,
      "grad_norm": 1.003038763999939,
      "learning_rate": 3.543051265553377e-05,
      "loss": 0.9214,
      "step": 131
    },
    {
      "epoch": 1.289537712895377,
      "grad_norm": 1.0400054454803467,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.93,
      "step": 132
    },
    {
      "epoch": 1.2992700729927007,
      "grad_norm": 1.040252685546875,
      "learning_rate": 3.367306435799584e-05,
      "loss": 1.0214,
      "step": 133
    },
    {
      "epoch": 1.3090024330900243,
      "grad_norm": 1.131703495979309,
      "learning_rate": 3.2802554068303596e-05,
      "loss": 0.9794,
      "step": 134
    },
    {
      "epoch": 1.3187347931873479,
      "grad_norm": 1.1634037494659424,
      "learning_rate": 3.1937916690642356e-05,
      "loss": 1.0565,
      "step": 135
    },
    {
      "epoch": 1.3284671532846715,
      "grad_norm": 1.099692940711975,
      "learning_rate": 3.107944749788449e-05,
      "loss": 1.0702,
      "step": 136
    },
    {
      "epoch": 1.338199513381995,
      "grad_norm": 1.1738554239273071,
      "learning_rate": 3.0227439656472877e-05,
      "loss": 1.1693,
      "step": 137
    },
    {
      "epoch": 1.3479318734793186,
      "grad_norm": 1.3135583400726318,
      "learning_rate": 2.9382184126304834e-05,
      "loss": 1.1786,
      "step": 138
    },
    {
      "epoch": 1.3576642335766422,
      "grad_norm": 1.372623324394226,
      "learning_rate": 2.8543969561369556e-05,
      "loss": 1.1273,
      "step": 139
    },
    {
      "epoch": 1.3673965936739658,
      "grad_norm": 1.3669289350509644,
      "learning_rate": 2.771308221117309e-05,
      "loss": 1.1737,
      "step": 140
    },
    {
      "epoch": 1.3771289537712894,
      "grad_norm": 1.3666361570358276,
      "learning_rate": 2.688980582298435e-05,
      "loss": 1.0974,
      "step": 141
    },
    {
      "epoch": 1.3868613138686132,
      "grad_norm": 1.604569911956787,
      "learning_rate": 2.607442154493568e-05,
      "loss": 1.2102,
      "step": 142
    },
    {
      "epoch": 1.3965936739659368,
      "grad_norm": 1.736600637435913,
      "learning_rate": 2.5267207830011068e-05,
      "loss": 1.2063,
      "step": 143
    },
    {
      "epoch": 1.4063260340632604,
      "grad_norm": 1.6941345930099487,
      "learning_rate": 2.446844034095466e-05,
      "loss": 1.1358,
      "step": 144
    },
    {
      "epoch": 1.416058394160584,
      "grad_norm": 2.2099905014038086,
      "learning_rate": 2.3678391856132204e-05,
      "loss": 1.4332,
      "step": 145
    },
    {
      "epoch": 1.4257907542579076,
      "grad_norm": 1.9193940162658691,
      "learning_rate": 2.2897332176377528e-05,
      "loss": 1.0148,
      "step": 146
    },
    {
      "epoch": 1.4355231143552312,
      "grad_norm": 2.477287769317627,
      "learning_rate": 2.2125528032855724e-05,
      "loss": 1.2941,
      "step": 147
    },
    {
      "epoch": 1.4452554744525548,
      "grad_norm": 2.3540828227996826,
      "learning_rate": 2.136324299597474e-05,
      "loss": 1.0426,
      "step": 148
    },
    {
      "epoch": 1.4549878345498783,
      "grad_norm": 2.6681060791015625,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.2108,
      "step": 149
    },
    {
      "epoch": 1.464720194647202,
      "grad_norm": 2.8821654319763184,
      "learning_rate": 1.9868268181037185e-05,
      "loss": 1.0689,
      "step": 150
    },
    {
      "epoch": 1.464720194647202,
      "eval_loss": 1.4939614534378052,
      "eval_runtime": 8.5285,
      "eval_samples_per_second": 20.285,
      "eval_steps_per_second": 10.201,
      "step": 150
    },
    {
      "epoch": 1.4744525547445255,
      "grad_norm": 3.5771002769470215,
      "learning_rate": 1.9136088935510362e-05,
      "loss": 1.0849,
      "step": 151
    },
    {
      "epoch": 1.4841849148418491,
      "grad_norm": 4.78915548324585,
      "learning_rate": 1.8414449687337464e-05,
      "loss": 1.4458,
      "step": 152
    },
    {
      "epoch": 1.4939172749391727,
      "grad_norm": 1.8771905899047852,
      "learning_rate": 1.7703596875660645e-05,
      "loss": 0.9596,
      "step": 153
    },
    {
      "epoch": 1.5036496350364965,
      "grad_norm": 0.879431962966919,
      "learning_rate": 1.700377325606388e-05,
      "loss": 0.936,
      "step": 154
    },
    {
      "epoch": 1.51338199513382,
      "grad_norm": 1.074074149131775,
      "learning_rate": 1.631521781767214e-05,
      "loss": 0.9387,
      "step": 155
    },
    {
      "epoch": 1.5231143552311437,
      "grad_norm": 1.0957303047180176,
      "learning_rate": 1.5638165701536868e-05,
      "loss": 0.9823,
      "step": 156
    },
    {
      "epoch": 1.5328467153284673,
      "grad_norm": 1.0464794635772705,
      "learning_rate": 1.4972848120335453e-05,
      "loss": 0.8914,
      "step": 157
    },
    {
      "epoch": 1.5425790754257909,
      "grad_norm": 1.1688803434371948,
      "learning_rate": 1.4319492279412388e-05,
      "loss": 1.1249,
      "step": 158
    },
    {
      "epoch": 1.5523114355231145,
      "grad_norm": 1.119362235069275,
      "learning_rate": 1.3678321299188801e-05,
      "loss": 0.8808,
      "step": 159
    },
    {
      "epoch": 1.562043795620438,
      "grad_norm": 1.0953980684280396,
      "learning_rate": 1.3049554138967051e-05,
      "loss": 0.9477,
      "step": 160
    },
    {
      "epoch": 1.5717761557177616,
      "grad_norm": 1.2464313507080078,
      "learning_rate": 1.2433405522156332e-05,
      "loss": 1.0658,
      "step": 161
    },
    {
      "epoch": 1.5815085158150852,
      "grad_norm": 1.2577733993530273,
      "learning_rate": 1.183008586294485e-05,
      "loss": 0.9974,
      "step": 162
    },
    {
      "epoch": 1.5912408759124088,
      "grad_norm": 1.2358986139297485,
      "learning_rate": 1.1239801194443506e-05,
      "loss": 0.9851,
      "step": 163
    },
    {
      "epoch": 1.6009732360097324,
      "grad_norm": 1.3200774192810059,
      "learning_rate": 1.066275309832584e-05,
      "loss": 1.0438,
      "step": 164
    },
    {
      "epoch": 1.610705596107056,
      "grad_norm": 1.3694344758987427,
      "learning_rate": 1.0099138635988026e-05,
      "loss": 1.0153,
      "step": 165
    },
    {
      "epoch": 1.6204379562043796,
      "grad_norm": 1.3594578504562378,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.9559,
      "step": 166
    },
    {
      "epoch": 1.6301703163017032,
      "grad_norm": 1.4179956912994385,
      "learning_rate": 9.012975854638949e-06,
      "loss": 0.9414,
      "step": 167
    },
    {
      "epoch": 1.6399026763990268,
      "grad_norm": 1.6792409420013428,
      "learning_rate": 8.490798459222476e-06,
      "loss": 1.1743,
      "step": 168
    },
    {
      "epoch": 1.6496350364963503,
      "grad_norm": 1.860835313796997,
      "learning_rate": 7.982796418105371e-06,
      "loss": 1.1659,
      "step": 169
    },
    {
      "epoch": 1.659367396593674,
      "grad_norm": 2.025655508041382,
      "learning_rate": 7.489143213519301e-06,
      "loss": 1.4175,
      "step": 170
    },
    {
      "epoch": 1.6690997566909975,
      "grad_norm": 2.0176472663879395,
      "learning_rate": 7.010007427581378e-06,
      "loss": 1.2406,
      "step": 171
    },
    {
      "epoch": 1.6788321167883211,
      "grad_norm": 2.086479663848877,
      "learning_rate": 6.5455526847235825e-06,
      "loss": 1.0616,
      "step": 172
    },
    {
      "epoch": 1.6885644768856447,
      "grad_norm": 2.938669443130493,
      "learning_rate": 6.0959375958151045e-06,
      "loss": 1.0773,
      "step": 173
    },
    {
      "epoch": 1.6982968369829683,
      "grad_norm": 3.0539605617523193,
      "learning_rate": 5.6613157039969055e-06,
      "loss": 1.3783,
      "step": 174
    },
    {
      "epoch": 1.7080291970802919,
      "grad_norm": 3.0834596157073975,
      "learning_rate": 5.241835432246889e-06,
      "loss": 1.3831,
      "step": 175
    },
    {
      "epoch": 1.7177615571776155,
      "grad_norm": 3.338949203491211,
      "learning_rate": 4.837640032693558e-06,
      "loss": 0.8342,
      "step": 176
    },
    {
      "epoch": 1.727493917274939,
      "grad_norm": 4.424727916717529,
      "learning_rate": 4.448867537695578e-06,
      "loss": 1.1993,
      "step": 177
    },
    {
      "epoch": 1.7372262773722627,
      "grad_norm": 2.2702529430389404,
      "learning_rate": 4.075650712703849e-06,
      "loss": 0.8172,
      "step": 178
    },
    {
      "epoch": 1.7469586374695862,
      "grad_norm": 1.0071195363998413,
      "learning_rate": 3.71811701092219e-06,
      "loss": 0.9896,
      "step": 179
    },
    {
      "epoch": 1.7566909975669098,
      "grad_norm": 0.8740869164466858,
      "learning_rate": 3.376388529782215e-06,
      "loss": 0.7871,
      "step": 180
    },
    {
      "epoch": 1.7664233576642334,
      "grad_norm": 1.0121991634368896,
      "learning_rate": 3.0505819692471792e-06,
      "loss": 0.963,
      "step": 181
    },
    {
      "epoch": 1.7761557177615572,
      "grad_norm": 1.048115849494934,
      "learning_rate": 2.7408085919590264e-06,
      "loss": 1.0336,
      "step": 182
    },
    {
      "epoch": 1.7858880778588808,
      "grad_norm": 1.1694386005401611,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.9065,
      "step": 183
    },
    {
      "epoch": 1.7956204379562044,
      "grad_norm": 1.0909321308135986,
      "learning_rate": 2.1697790249779636e-06,
      "loss": 0.928,
      "step": 184
    },
    {
      "epoch": 1.805352798053528,
      "grad_norm": 1.1170390844345093,
      "learning_rate": 1.908717841359048e-06,
      "loss": 0.9702,
      "step": 185
    },
    {
      "epoch": 1.8150851581508516,
      "grad_norm": 1.2209182977676392,
      "learning_rate": 1.6640797865406288e-06,
      "loss": 1.0042,
      "step": 186
    },
    {
      "epoch": 1.8248175182481752,
      "grad_norm": 1.3357527256011963,
      "learning_rate": 1.4359484041943038e-06,
      "loss": 1.1156,
      "step": 187
    },
    {
      "epoch": 1.8345498783454988,
      "grad_norm": 1.23755943775177,
      "learning_rate": 1.2244016009781701e-06,
      "loss": 0.8536,
      "step": 188
    },
    {
      "epoch": 1.8442822384428224,
      "grad_norm": 1.3244162797927856,
      "learning_rate": 1.0295116199317057e-06,
      "loss": 1.1103,
      "step": 189
    },
    {
      "epoch": 1.854014598540146,
      "grad_norm": 1.5124642848968506,
      "learning_rate": 8.513450158049108e-07,
      "loss": 1.1423,
      "step": 190
    },
    {
      "epoch": 1.8637469586374698,
      "grad_norm": 1.6476125717163086,
      "learning_rate": 6.899626323298713e-07,
      "loss": 1.2435,
      "step": 191
    },
    {
      "epoch": 1.8734793187347933,
      "grad_norm": 1.5479832887649536,
      "learning_rate": 5.454195814427021e-07,
      "loss": 0.796,
      "step": 192
    },
    {
      "epoch": 1.883211678832117,
      "grad_norm": 1.950077772140503,
      "learning_rate": 4.177652244628627e-07,
      "loss": 1.0447,
      "step": 193
    },
    {
      "epoch": 1.8929440389294405,
      "grad_norm": 1.9293968677520752,
      "learning_rate": 3.0704315523631953e-07,
      "loss": 1.0662,
      "step": 194
    },
    {
      "epoch": 1.902676399026764,
      "grad_norm": 2.0130317211151123,
      "learning_rate": 2.1329118524827662e-07,
      "loss": 1.4686,
      "step": 195
    },
    {
      "epoch": 1.9124087591240877,
      "grad_norm": 2.3589720726013184,
      "learning_rate": 1.3654133071059893e-07,
      "loss": 1.3103,
      "step": 196
    },
    {
      "epoch": 1.9221411192214113,
      "grad_norm": 2.2165637016296387,
      "learning_rate": 7.681980162830282e-08,
      "loss": 1.1324,
      "step": 197
    },
    {
      "epoch": 1.9318734793187349,
      "grad_norm": 2.438457489013672,
      "learning_rate": 3.4146992848854695e-08,
      "loss": 1.1513,
      "step": 198
    },
    {
      "epoch": 1.9416058394160585,
      "grad_norm": 2.7616829872131348,
      "learning_rate": 8.537477097364522e-09,
      "loss": 1.2593,
      "step": 199
    },
    {
      "epoch": 1.951338199513382,
      "grad_norm": 2.911860466003418,
      "learning_rate": 0.0,
      "loss": 1.1348,
      "step": 200
    },
    {
      "epoch": 1.951338199513382,
      "eval_loss": 1.4932652711868286,
      "eval_runtime": 8.5241,
      "eval_samples_per_second": 20.295,
      "eval_steps_per_second": 10.206,
      "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": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.349515725248922e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}