{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8666183924692252,
  "eval_steps": 50,
  "global_step": 187,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004634322954380883,
      "grad_norm": 1.1059749126434326,
      "learning_rate": 7.499999999999999e-06,
      "loss": 2.7798,
      "step": 1
    },
    {
      "epoch": 0.004634322954380883,
      "eval_loss": 2.9304847717285156,
      "eval_runtime": 146.6617,
      "eval_samples_per_second": 4.957,
      "eval_steps_per_second": 2.482,
      "step": 1
    },
    {
      "epoch": 0.009268645908761766,
      "grad_norm": 1.1082885265350342,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 2.681,
      "step": 2
    },
    {
      "epoch": 0.013902968863142651,
      "grad_norm": 1.2035174369812012,
      "learning_rate": 2.2499999999999998e-05,
      "loss": 2.9068,
      "step": 3
    },
    {
      "epoch": 0.018537291817523532,
      "grad_norm": 1.1457459926605225,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 2.9637,
      "step": 4
    },
    {
      "epoch": 0.023171614771904415,
      "grad_norm": 1.1010493040084839,
      "learning_rate": 3.75e-05,
      "loss": 2.7247,
      "step": 5
    },
    {
      "epoch": 0.027805937726285302,
      "grad_norm": 1.2098731994628906,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 2.8731,
      "step": 6
    },
    {
      "epoch": 0.03244026068066618,
      "grad_norm": 1.0666383504867554,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 2.6556,
      "step": 7
    },
    {
      "epoch": 0.037074583635047065,
      "grad_norm": 0.8229893445968628,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 2.5,
      "step": 8
    },
    {
      "epoch": 0.04170890658942795,
      "grad_norm": 1.1555801630020142,
      "learning_rate": 6.75e-05,
      "loss": 2.663,
      "step": 9
    },
    {
      "epoch": 0.04634322954380883,
      "grad_norm": 1.2436870336532593,
      "learning_rate": 7.5e-05,
      "loss": 2.3639,
      "step": 10
    },
    {
      "epoch": 0.05097755249818972,
      "grad_norm": 1.1677322387695312,
      "learning_rate": 8.25e-05,
      "loss": 2.3472,
      "step": 11
    },
    {
      "epoch": 0.055611875452570604,
      "grad_norm": 1.1217212677001953,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.2676,
      "step": 12
    },
    {
      "epoch": 0.06024619840695149,
      "grad_norm": 0.7882691621780396,
      "learning_rate": 9.75e-05,
      "loss": 2.1962,
      "step": 13
    },
    {
      "epoch": 0.06488052136133236,
      "grad_norm": 0.8494845032691956,
      "learning_rate": 0.00010499999999999999,
      "loss": 2.1433,
      "step": 14
    },
    {
      "epoch": 0.06951484431571325,
      "grad_norm": 0.980268120765686,
      "learning_rate": 0.0001125,
      "loss": 2.152,
      "step": 15
    },
    {
      "epoch": 0.07414916727009413,
      "grad_norm": 0.9087497591972351,
      "learning_rate": 0.00011999999999999999,
      "loss": 2.0726,
      "step": 16
    },
    {
      "epoch": 0.07878349022447502,
      "grad_norm": 0.6476942300796509,
      "learning_rate": 0.00012749999999999998,
      "loss": 1.9891,
      "step": 17
    },
    {
      "epoch": 0.0834178131788559,
      "grad_norm": 0.7011496424674988,
      "learning_rate": 0.000135,
      "loss": 1.9417,
      "step": 18
    },
    {
      "epoch": 0.08805213613323679,
      "grad_norm": 0.7312366962432861,
      "learning_rate": 0.0001425,
      "loss": 2.0363,
      "step": 19
    },
    {
      "epoch": 0.09268645908761766,
      "grad_norm": 0.6832443475723267,
      "learning_rate": 0.00015,
      "loss": 1.9493,
      "step": 20
    },
    {
      "epoch": 0.09732078204199855,
      "grad_norm": 0.5798928737640381,
      "learning_rate": 0.00014998857713672935,
      "loss": 1.9732,
      "step": 21
    },
    {
      "epoch": 0.10195510499637944,
      "grad_norm": 0.5472275018692017,
      "learning_rate": 0.00014995431202643217,
      "loss": 1.8398,
      "step": 22
    },
    {
      "epoch": 0.10658942795076032,
      "grad_norm": 0.7329992055892944,
      "learning_rate": 0.000149897215106593,
      "loss": 1.8098,
      "step": 23
    },
    {
      "epoch": 0.11122375090514121,
      "grad_norm": 0.6771075129508972,
      "learning_rate": 0.0001498173037694868,
      "loss": 1.7746,
      "step": 24
    },
    {
      "epoch": 0.11585807385952208,
      "grad_norm": 0.8174684643745422,
      "learning_rate": 0.0001497146023568809,
      "loss": 1.7504,
      "step": 25
    },
    {
      "epoch": 0.12049239681390297,
      "grad_norm": 0.6408036351203918,
      "learning_rate": 0.00014958914215262048,
      "loss": 1.7606,
      "step": 26
    },
    {
      "epoch": 0.12512671976828385,
      "grad_norm": 0.7159773111343384,
      "learning_rate": 0.00014944096137309914,
      "loss": 1.7529,
      "step": 27
    },
    {
      "epoch": 0.12976104272266473,
      "grad_norm": 0.8010567426681519,
      "learning_rate": 0.00014927010515561776,
      "loss": 1.9922,
      "step": 28
    },
    {
      "epoch": 0.13439536567704563,
      "grad_norm": 0.6913322806358337,
      "learning_rate": 0.00014907662554463532,
      "loss": 1.6162,
      "step": 29
    },
    {
      "epoch": 0.1390296886314265,
      "grad_norm": 0.6494315266609192,
      "learning_rate": 0.0001488605814759156,
      "loss": 1.6571,
      "step": 30
    },
    {
      "epoch": 0.14366401158580738,
      "grad_norm": 0.6595631241798401,
      "learning_rate": 0.00014862203875857477,
      "loss": 1.5886,
      "step": 31
    },
    {
      "epoch": 0.14829833454018826,
      "grad_norm": 0.7777145504951477,
      "learning_rate": 0.0001483610700550354,
      "loss": 1.5729,
      "step": 32
    },
    {
      "epoch": 0.15293265749456916,
      "grad_norm": 0.7189599871635437,
      "learning_rate": 0.00014807775485889264,
      "loss": 1.6492,
      "step": 33
    },
    {
      "epoch": 0.15756698044895004,
      "grad_norm": 0.7974843978881836,
      "learning_rate": 0.0001477721794706997,
      "loss": 1.5415,
      "step": 34
    },
    {
      "epoch": 0.16220130340333092,
      "grad_norm": 0.8167005181312561,
      "learning_rate": 0.0001474444369716801,
      "loss": 1.4696,
      "step": 35
    },
    {
      "epoch": 0.1668356263577118,
      "grad_norm": 0.7308511137962341,
      "learning_rate": 0.0001470946271953739,
      "loss": 1.6394,
      "step": 36
    },
    {
      "epoch": 0.1714699493120927,
      "grad_norm": 0.808505654335022,
      "learning_rate": 0.00014672285669722765,
      "loss": 1.4614,
      "step": 37
    },
    {
      "epoch": 0.17610427226647357,
      "grad_norm": 0.7852684259414673,
      "learning_rate": 0.00014632923872213652,
      "loss": 1.4592,
      "step": 38
    },
    {
      "epoch": 0.18073859522085445,
      "grad_norm": 0.7765493988990784,
      "learning_rate": 0.00014591389316994876,
      "loss": 1.3337,
      "step": 39
    },
    {
      "epoch": 0.18537291817523532,
      "grad_norm": 0.9292432069778442,
      "learning_rate": 0.0001454769465589431,
      "loss": 1.4594,
      "step": 40
    },
    {
      "epoch": 0.19000724112961623,
      "grad_norm": 0.9222384095191956,
      "learning_rate": 0.00014501853198729012,
      "loss": 1.5136,
      "step": 41
    },
    {
      "epoch": 0.1946415640839971,
      "grad_norm": 0.8896085619926453,
      "learning_rate": 0.00014453878909250904,
      "loss": 1.4321,
      "step": 42
    },
    {
      "epoch": 0.19927588703837798,
      "grad_norm": 0.9805691242218018,
      "learning_rate": 0.00014403786400893302,
      "loss": 1.2422,
      "step": 43
    },
    {
      "epoch": 0.20391020999275888,
      "grad_norm": 0.9406644701957703,
      "learning_rate": 0.00014351590932319504,
      "loss": 1.3904,
      "step": 44
    },
    {
      "epoch": 0.20854453294713976,
      "grad_norm": 1.2533518075942993,
      "learning_rate": 0.00014297308402774875,
      "loss": 1.2121,
      "step": 45
    },
    {
      "epoch": 0.21317885590152064,
      "grad_norm": 1.020983338356018,
      "learning_rate": 0.0001424095534724375,
      "loss": 1.148,
      "step": 46
    },
    {
      "epoch": 0.2178131788559015,
      "grad_norm": 0.895693302154541,
      "learning_rate": 0.00014182548931412757,
      "loss": 1.3044,
      "step": 47
    },
    {
      "epoch": 0.22244750181028242,
      "grad_norm": 1.1574026346206665,
      "learning_rate": 0.0001412210694644195,
      "loss": 1.2857,
      "step": 48
    },
    {
      "epoch": 0.2270818247646633,
      "grad_norm": 1.032139539718628,
      "learning_rate": 0.00014059647803545467,
      "loss": 1.2987,
      "step": 49
    },
    {
      "epoch": 0.23171614771904417,
      "grad_norm": 0.9623427391052246,
      "learning_rate": 0.0001399519052838329,
      "loss": 1.1087,
      "step": 50
    },
    {
      "epoch": 0.23171614771904417,
      "eval_loss": 1.1839566230773926,
      "eval_runtime": 146.108,
      "eval_samples_per_second": 4.976,
      "eval_steps_per_second": 2.491,
      "step": 50
    },
    {
      "epoch": 0.23635047067342504,
      "grad_norm": 1.263940691947937,
      "learning_rate": 0.00013928754755265842,
      "loss": 1.0973,
      "step": 51
    },
    {
      "epoch": 0.24098479362780595,
      "grad_norm": 1.0416457653045654,
      "learning_rate": 0.00013860360721173193,
      "loss": 1.1655,
      "step": 52
    },
    {
      "epoch": 0.24561911658218682,
      "grad_norm": 1.1260313987731934,
      "learning_rate": 0.0001379002925959068,
      "loss": 1.0404,
      "step": 53
    },
    {
      "epoch": 0.2502534395365677,
      "grad_norm": 0.9762699604034424,
      "learning_rate": 0.0001371778179416281,
      "loss": 1.0744,
      "step": 54
    },
    {
      "epoch": 0.2548877624909486,
      "grad_norm": 1.2078801393508911,
      "learning_rate": 0.00013643640332167438,
      "loss": 1.0079,
      "step": 55
    },
    {
      "epoch": 0.25952208544532945,
      "grad_norm": 1.075649380683899,
      "learning_rate": 0.00013567627457812106,
      "loss": 1.0864,
      "step": 56
    },
    {
      "epoch": 0.26415640839971033,
      "grad_norm": 1.1446782350540161,
      "learning_rate": 0.00013489766325354695,
      "loss": 1.0853,
      "step": 57
    },
    {
      "epoch": 0.26879073135409126,
      "grad_norm": 1.1303826570510864,
      "learning_rate": 0.00013410080652050412,
      "loss": 1.0711,
      "step": 58
    },
    {
      "epoch": 0.27342505430847214,
      "grad_norm": 1.216537356376648,
      "learning_rate": 0.0001332859471092728,
      "loss": 0.9193,
      "step": 59
    },
    {
      "epoch": 0.278059377262853,
      "grad_norm": 1.4602874517440796,
      "learning_rate": 0.00013245333323392333,
      "loss": 0.9987,
      "step": 60
    },
    {
      "epoch": 0.2826937002172339,
      "grad_norm": 1.0730090141296387,
      "learning_rate": 0.0001316032185167079,
      "loss": 1.0272,
      "step": 61
    },
    {
      "epoch": 0.28732802317161477,
      "grad_norm": 1.0437711477279663,
      "learning_rate": 0.00013073586191080457,
      "loss": 1.0511,
      "step": 62
    },
    {
      "epoch": 0.29196234612599564,
      "grad_norm": 1.0983786582946777,
      "learning_rate": 0.00012985152762143778,
      "loss": 0.9506,
      "step": 63
    },
    {
      "epoch": 0.2965966690803765,
      "grad_norm": 1.3723191022872925,
      "learning_rate": 0.00012895048502539882,
      "loss": 1.0643,
      "step": 64
    },
    {
      "epoch": 0.30123099203475745,
      "grad_norm": 1.2514058351516724,
      "learning_rate": 0.00012803300858899104,
      "loss": 1.0204,
      "step": 65
    },
    {
      "epoch": 0.3058653149891383,
      "grad_norm": 1.038238525390625,
      "learning_rate": 0.0001270993777844248,
      "loss": 0.7876,
      "step": 66
    },
    {
      "epoch": 0.3104996379435192,
      "grad_norm": 1.313706874847412,
      "learning_rate": 0.0001261498770046874,
      "loss": 1.0337,
      "step": 67
    },
    {
      "epoch": 0.3151339608979001,
      "grad_norm": 1.1323295831680298,
      "learning_rate": 0.00012518479547691435,
      "loss": 0.8007,
      "step": 68
    },
    {
      "epoch": 0.31976828385228095,
      "grad_norm": 1.0297540426254272,
      "learning_rate": 0.00012420442717428804,
      "loss": 0.9792,
      "step": 69
    },
    {
      "epoch": 0.32440260680666183,
      "grad_norm": 1.201749563217163,
      "learning_rate": 0.00012320907072649044,
      "loss": 1.0579,
      "step": 70
    },
    {
      "epoch": 0.3290369297610427,
      "grad_norm": 1.0487987995147705,
      "learning_rate": 0.0001221990293287378,
      "loss": 0.8679,
      "step": 71
    },
    {
      "epoch": 0.3336712527154236,
      "grad_norm": 0.9669104814529419,
      "learning_rate": 0.00012117461064942435,
      "loss": 0.9195,
      "step": 72
    },
    {
      "epoch": 0.3383055756698045,
      "grad_norm": 1.1065351963043213,
      "learning_rate": 0.00012013612673640363,
      "loss": 0.9479,
      "step": 73
    },
    {
      "epoch": 0.3429398986241854,
      "grad_norm": 1.1072312593460083,
      "learning_rate": 0.00011908389392193547,
      "loss": 0.8467,
      "step": 74
    },
    {
      "epoch": 0.34757422157856627,
      "grad_norm": 1.1270943880081177,
      "learning_rate": 0.00011801823272632844,
      "loss": 0.7588,
      "step": 75
    },
    {
      "epoch": 0.35220854453294714,
      "grad_norm": 1.2270523309707642,
      "learning_rate": 0.00011693946776030599,
      "loss": 0.9326,
      "step": 76
    },
    {
      "epoch": 0.356842867487328,
      "grad_norm": 1.2635189294815063,
      "learning_rate": 0.00011584792762612703,
      "loss": 0.9417,
      "step": 77
    },
    {
      "epoch": 0.3614771904417089,
      "grad_norm": 1.3055872917175293,
      "learning_rate": 0.00011474394481749035,
      "loss": 0.9683,
      "step": 78
    },
    {
      "epoch": 0.36611151339608977,
      "grad_norm": 1.0037323236465454,
      "learning_rate": 0.00011362785561825406,
      "loss": 0.6438,
      "step": 79
    },
    {
      "epoch": 0.37074583635047065,
      "grad_norm": 1.0581717491149902,
      "learning_rate": 0.0001125,
      "loss": 0.8729,
      "step": 80
    },
    {
      "epoch": 0.3753801593048516,
      "grad_norm": 1.194458246231079,
      "learning_rate": 0.00011136072151847529,
      "loss": 0.7414,
      "step": 81
    },
    {
      "epoch": 0.38001448225923246,
      "grad_norm": 1.3376874923706055,
      "learning_rate": 0.00011021036720894179,
      "loss": 0.7101,
      "step": 82
    },
    {
      "epoch": 0.38464880521361333,
      "grad_norm": 1.5701568126678467,
      "learning_rate": 0.00010904928748046599,
      "loss": 0.6721,
      "step": 83
    },
    {
      "epoch": 0.3892831281679942,
      "grad_norm": 1.53782057762146,
      "learning_rate": 0.0001078778360091808,
      "loss": 0.7689,
      "step": 84
    },
    {
      "epoch": 0.3939174511223751,
      "grad_norm": 1.1315703392028809,
      "learning_rate": 0.00010669636963055245,
      "loss": 0.6933,
      "step": 85
    },
    {
      "epoch": 0.39855177407675596,
      "grad_norm": 1.1853336095809937,
      "learning_rate": 0.00010550524823068502,
      "loss": 0.7163,
      "step": 86
    },
    {
      "epoch": 0.40318609703113684,
      "grad_norm": 1.1081809997558594,
      "learning_rate": 0.00010430483463669551,
      "loss": 0.8206,
      "step": 87
    },
    {
      "epoch": 0.40782041998551777,
      "grad_norm": 1.1602833271026611,
      "learning_rate": 0.0001030954945061934,
      "loss": 0.632,
      "step": 88
    },
    {
      "epoch": 0.41245474293989864,
      "grad_norm": 1.3947807550430298,
      "learning_rate": 0.0001018775962158975,
      "loss": 0.668,
      "step": 89
    },
    {
      "epoch": 0.4170890658942795,
      "grad_norm": 1.2622536420822144,
      "learning_rate": 0.00010065151074942516,
      "loss": 0.5766,
      "step": 90
    },
    {
      "epoch": 0.4217233888486604,
      "grad_norm": 1.39005708694458,
      "learning_rate": 9.941761158428674e-05,
      "loss": 0.5234,
      "step": 91
    },
    {
      "epoch": 0.4263577118030413,
      "grad_norm": 1.3181982040405273,
      "learning_rate": 9.817627457812105e-05,
      "loss": 0.575,
      "step": 92
    },
    {
      "epoch": 0.43099203475742215,
      "grad_norm": 1.385236144065857,
      "learning_rate": 9.692787785420525e-05,
      "loss": 0.7406,
      "step": 93
    },
    {
      "epoch": 0.435626357711803,
      "grad_norm": 1.2025413513183594,
      "learning_rate": 9.567280168627493e-05,
      "loss": 0.565,
      "step": 94
    },
    {
      "epoch": 0.4402606806661839,
      "grad_norm": 1.1163705587387085,
      "learning_rate": 9.441142838268905e-05,
      "loss": 0.5613,
      "step": 95
    },
    {
      "epoch": 0.44489500362056483,
      "grad_norm": 1.2544317245483398,
      "learning_rate": 9.314414216997507e-05,
      "loss": 0.7618,
      "step": 96
    },
    {
      "epoch": 0.4495293265749457,
      "grad_norm": 1.1881450414657593,
      "learning_rate": 9.187132907578987e-05,
      "loss": 0.7518,
      "step": 97
    },
    {
      "epoch": 0.4541636495293266,
      "grad_norm": 1.1118865013122559,
      "learning_rate": 9.059337681133192e-05,
      "loss": 0.5474,
      "step": 98
    },
    {
      "epoch": 0.45879797248370746,
      "grad_norm": 1.0739349126815796,
      "learning_rate": 8.931067465324085e-05,
      "loss": 0.5227,
      "step": 99
    },
    {
      "epoch": 0.46343229543808834,
      "grad_norm": 1.2055435180664062,
      "learning_rate": 8.802361332501978e-05,
      "loss": 0.6742,
      "step": 100
    },
    {
      "epoch": 0.46343229543808834,
      "eval_loss": 0.6104360818862915,
      "eval_runtime": 135.03,
      "eval_samples_per_second": 5.384,
      "eval_steps_per_second": 2.696,
      "step": 100
    },
    {
      "epoch": 0.4680666183924692,
      "grad_norm": 1.332160472869873,
      "learning_rate": 8.673258487801731e-05,
      "loss": 0.5866,
      "step": 101
    },
    {
      "epoch": 0.4727009413468501,
      "grad_norm": 1.0405492782592773,
      "learning_rate": 8.54379825720049e-05,
      "loss": 0.5656,
      "step": 102
    },
    {
      "epoch": 0.47733526430123097,
      "grad_norm": 1.373766303062439,
      "learning_rate": 8.414020075538605e-05,
      "loss": 0.5363,
      "step": 103
    },
    {
      "epoch": 0.4819695872556119,
      "grad_norm": 1.1279383897781372,
      "learning_rate": 8.2839634745074e-05,
      "loss": 0.474,
      "step": 104
    },
    {
      "epoch": 0.4866039102099928,
      "grad_norm": 1.3224053382873535,
      "learning_rate": 8.153668070607437e-05,
      "loss": 0.7299,
      "step": 105
    },
    {
      "epoch": 0.49123823316437365,
      "grad_norm": 1.1764270067214966,
      "learning_rate": 8.023173553080938e-05,
      "loss": 0.5553,
      "step": 106
    },
    {
      "epoch": 0.4958725561187545,
      "grad_norm": 1.3858931064605713,
      "learning_rate": 7.89251967182208e-05,
      "loss": 0.6029,
      "step": 107
    },
    {
      "epoch": 0.5005068790731354,
      "grad_norm": 1.2218059301376343,
      "learning_rate": 7.761746225268758e-05,
      "loss": 0.5179,
      "step": 108
    },
    {
      "epoch": 0.5051412020275163,
      "grad_norm": 1.186583399772644,
      "learning_rate": 7.630893048279627e-05,
      "loss": 0.592,
      "step": 109
    },
    {
      "epoch": 0.5097755249818972,
      "grad_norm": 1.1901055574417114,
      "learning_rate": 7.5e-05,
      "loss": 0.4786,
      "step": 110
    },
    {
      "epoch": 0.5144098479362781,
      "grad_norm": 1.2109345197677612,
      "learning_rate": 7.369106951720373e-05,
      "loss": 0.4874,
      "step": 111
    },
    {
      "epoch": 0.5190441708906589,
      "grad_norm": 1.2095303535461426,
      "learning_rate": 7.238253774731244e-05,
      "loss": 0.5826,
      "step": 112
    },
    {
      "epoch": 0.5236784938450398,
      "grad_norm": 1.4487143754959106,
      "learning_rate": 7.10748032817792e-05,
      "loss": 0.6947,
      "step": 113
    },
    {
      "epoch": 0.5283128167994207,
      "grad_norm": 1.4283783435821533,
      "learning_rate": 6.976826446919059e-05,
      "loss": 0.6258,
      "step": 114
    },
    {
      "epoch": 0.5329471397538016,
      "grad_norm": 1.387428879737854,
      "learning_rate": 6.846331929392562e-05,
      "loss": 0.5088,
      "step": 115
    },
    {
      "epoch": 0.5375814627081825,
      "grad_norm": 1.3152918815612793,
      "learning_rate": 6.7160365254926e-05,
      "loss": 0.4329,
      "step": 116
    },
    {
      "epoch": 0.5422157856625633,
      "grad_norm": 1.493445873260498,
      "learning_rate": 6.585979924461394e-05,
      "loss": 0.5035,
      "step": 117
    },
    {
      "epoch": 0.5468501086169443,
      "grad_norm": 1.2388755083084106,
      "learning_rate": 6.45620174279951e-05,
      "loss": 0.4064,
      "step": 118
    },
    {
      "epoch": 0.5514844315713251,
      "grad_norm": 1.163062572479248,
      "learning_rate": 6.326741512198266e-05,
      "loss": 0.3774,
      "step": 119
    },
    {
      "epoch": 0.556118754525706,
      "grad_norm": 1.305509328842163,
      "learning_rate": 6.197638667498022e-05,
      "loss": 0.4626,
      "step": 120
    },
    {
      "epoch": 0.5607530774800868,
      "grad_norm": 1.2311328649520874,
      "learning_rate": 6.068932534675913e-05,
      "loss": 0.4069,
      "step": 121
    },
    {
      "epoch": 0.5653874004344678,
      "grad_norm": 1.3704758882522583,
      "learning_rate": 5.9406623188668055e-05,
      "loss": 0.5308,
      "step": 122
    },
    {
      "epoch": 0.5700217233888487,
      "grad_norm": 1.2310731410980225,
      "learning_rate": 5.812867092421013e-05,
      "loss": 0.4324,
      "step": 123
    },
    {
      "epoch": 0.5746560463432295,
      "grad_norm": 1.2407798767089844,
      "learning_rate": 5.685585783002493e-05,
      "loss": 0.4992,
      "step": 124
    },
    {
      "epoch": 0.5792903692976105,
      "grad_norm": 1.2309188842773438,
      "learning_rate": 5.558857161731093e-05,
      "loss": 0.3967,
      "step": 125
    },
    {
      "epoch": 0.5839246922519913,
      "grad_norm": 1.2751799821853638,
      "learning_rate": 5.4327198313725064e-05,
      "loss": 0.4109,
      "step": 126
    },
    {
      "epoch": 0.5885590152063722,
      "grad_norm": 1.3883857727050781,
      "learning_rate": 5.307212214579474e-05,
      "loss": 0.3867,
      "step": 127
    },
    {
      "epoch": 0.593193338160753,
      "grad_norm": 1.410216212272644,
      "learning_rate": 5.182372542187895e-05,
      "loss": 0.3541,
      "step": 128
    },
    {
      "epoch": 0.597827661115134,
      "grad_norm": 1.3435072898864746,
      "learning_rate": 5.058238841571326e-05,
      "loss": 0.4067,
      "step": 129
    },
    {
      "epoch": 0.6024619840695149,
      "grad_norm": 1.3180471658706665,
      "learning_rate": 4.934848925057484e-05,
      "loss": 0.3048,
      "step": 130
    },
    {
      "epoch": 0.6070963070238957,
      "grad_norm": 1.1778309345245361,
      "learning_rate": 4.812240378410248e-05,
      "loss": 0.3317,
      "step": 131
    },
    {
      "epoch": 0.6117306299782767,
      "grad_norm": 1.2751339673995972,
      "learning_rate": 4.690450549380659e-05,
      "loss": 0.3,
      "step": 132
    },
    {
      "epoch": 0.6163649529326575,
      "grad_norm": 1.1635668277740479,
      "learning_rate": 4.569516536330447e-05,
      "loss": 0.2464,
      "step": 133
    },
    {
      "epoch": 0.6209992758870384,
      "grad_norm": 1.4394093751907349,
      "learning_rate": 4.449475176931499e-05,
      "loss": 0.3776,
      "step": 134
    },
    {
      "epoch": 0.6256335988414192,
      "grad_norm": 1.3860478401184082,
      "learning_rate": 4.3303630369447554e-05,
      "loss": 0.3414,
      "step": 135
    },
    {
      "epoch": 0.6302679217958002,
      "grad_norm": 0.9536806344985962,
      "learning_rate": 4.212216399081918e-05,
      "loss": 0.2116,
      "step": 136
    },
    {
      "epoch": 0.634902244750181,
      "grad_norm": 1.092250943183899,
      "learning_rate": 4.095071251953399e-05,
      "loss": 0.2411,
      "step": 137
    },
    {
      "epoch": 0.6395365677045619,
      "grad_norm": 1.3056756258010864,
      "learning_rate": 3.978963279105821e-05,
      "loss": 0.3435,
      "step": 138
    },
    {
      "epoch": 0.6441708906589428,
      "grad_norm": 1.1005077362060547,
      "learning_rate": 3.863927848152472e-05,
      "loss": 0.2612,
      "step": 139
    },
    {
      "epoch": 0.6488052136133237,
      "grad_norm": 1.237870454788208,
      "learning_rate": 3.750000000000001e-05,
      "loss": 0.3284,
      "step": 140
    },
    {
      "epoch": 0.6534395365677046,
      "grad_norm": 1.3307782411575317,
      "learning_rate": 3.637214438174593e-05,
      "loss": 0.2536,
      "step": 141
    },
    {
      "epoch": 0.6580738595220854,
      "grad_norm": 1.4346413612365723,
      "learning_rate": 3.525605518250964e-05,
      "loss": 0.2911,
      "step": 142
    },
    {
      "epoch": 0.6627081824764663,
      "grad_norm": 1.2083615064620972,
      "learning_rate": 3.415207237387297e-05,
      "loss": 0.233,
      "step": 143
    },
    {
      "epoch": 0.6673425054308472,
      "grad_norm": 1.4748581647872925,
      "learning_rate": 3.3060532239693994e-05,
      "loss": 0.319,
      "step": 144
    },
    {
      "epoch": 0.6719768283852281,
      "grad_norm": 1.2144207954406738,
      "learning_rate": 3.198176727367156e-05,
      "loss": 0.1959,
      "step": 145
    },
    {
      "epoch": 0.676611151339609,
      "grad_norm": 1.5745162963867188,
      "learning_rate": 3.091610607806452e-05,
      "loss": 0.3077,
      "step": 146
    },
    {
      "epoch": 0.6812454742939898,
      "grad_norm": 1.1295483112335205,
      "learning_rate": 2.986387326359637e-05,
      "loss": 0.2328,
      "step": 147
    },
    {
      "epoch": 0.6858797972483708,
      "grad_norm": 1.218430757522583,
      "learning_rate": 2.8825389350575624e-05,
      "loss": 0.2504,
      "step": 148
    },
    {
      "epoch": 0.6905141202027516,
      "grad_norm": 1.1782724857330322,
      "learning_rate": 2.78009706712622e-05,
      "loss": 0.2519,
      "step": 149
    },
    {
      "epoch": 0.6951484431571325,
      "grad_norm": 1.3294053077697754,
      "learning_rate": 2.6790929273509545e-05,
      "loss": 0.249,
      "step": 150
    },
    {
      "epoch": 0.6951484431571325,
      "eval_loss": 0.25855064392089844,
      "eval_runtime": 135.0303,
      "eval_samples_per_second": 5.384,
      "eval_steps_per_second": 2.696,
      "step": 150
    },
    {
      "epoch": 0.6997827661115134,
      "grad_norm": 0.8559562563896179,
      "learning_rate": 2.579557282571196e-05,
      "loss": 0.1331,
      "step": 151
    },
    {
      "epoch": 0.7044170890658943,
      "grad_norm": 1.5178470611572266,
      "learning_rate": 2.4815204523085654e-05,
      "loss": 0.3093,
      "step": 152
    },
    {
      "epoch": 0.7090514120202752,
      "grad_norm": 1.3319201469421387,
      "learning_rate": 2.385012299531262e-05,
      "loss": 0.3123,
      "step": 153
    },
    {
      "epoch": 0.713685734974656,
      "grad_norm": 1.3699779510498047,
      "learning_rate": 2.2900622215575197e-05,
      "loss": 0.2744,
      "step": 154
    },
    {
      "epoch": 0.718320057929037,
      "grad_norm": 1.4394081830978394,
      "learning_rate": 2.1966991411008938e-05,
      "loss": 0.2854,
      "step": 155
    },
    {
      "epoch": 0.7229543808834178,
      "grad_norm": 1.1516926288604736,
      "learning_rate": 2.1049514974601175e-05,
      "loss": 0.232,
      "step": 156
    },
    {
      "epoch": 0.7275887038377987,
      "grad_norm": 1.226991891860962,
      "learning_rate": 2.0148472378562215e-05,
      "loss": 0.2174,
      "step": 157
    },
    {
      "epoch": 0.7322230267921795,
      "grad_norm": 1.3236987590789795,
      "learning_rate": 1.926413808919542e-05,
      "loss": 0.2859,
      "step": 158
    },
    {
      "epoch": 0.7368573497465605,
      "grad_norm": 1.3909859657287598,
      "learning_rate": 1.8396781483292098e-05,
      "loss": 0.1741,
      "step": 159
    },
    {
      "epoch": 0.7414916727009413,
      "grad_norm": 1.3062829971313477,
      "learning_rate": 1.7546666766076655e-05,
      "loss": 0.2003,
      "step": 160
    },
    {
      "epoch": 0.7461259956553222,
      "grad_norm": 1.4208601713180542,
      "learning_rate": 1.671405289072718e-05,
      "loss": 0.2306,
      "step": 161
    },
    {
      "epoch": 0.7507603186097032,
      "grad_norm": 1.130900502204895,
      "learning_rate": 1.5899193479495857e-05,
      "loss": 0.1712,
      "step": 162
    },
    {
      "epoch": 0.755394641564084,
      "grad_norm": 1.3274939060211182,
      "learning_rate": 1.5102336746453053e-05,
      "loss": 0.2057,
      "step": 163
    },
    {
      "epoch": 0.7600289645184649,
      "grad_norm": 1.5153155326843262,
      "learning_rate": 1.4323725421878949e-05,
      "loss": 0.2792,
      "step": 164
    },
    {
      "epoch": 0.7646632874728457,
      "grad_norm": 1.2106071710586548,
      "learning_rate": 1.3563596678325606e-05,
      "loss": 0.213,
      "step": 165
    },
    {
      "epoch": 0.7692976104272267,
      "grad_norm": 1.3996082544326782,
      "learning_rate": 1.2822182058371878e-05,
      "loss": 0.2113,
      "step": 166
    },
    {
      "epoch": 0.7739319333816075,
      "grad_norm": 1.1402256488800049,
      "learning_rate": 1.2099707404093203e-05,
      "loss": 0.1599,
      "step": 167
    },
    {
      "epoch": 0.7785662563359884,
      "grad_norm": 1.6671884059906006,
      "learning_rate": 1.1396392788268052e-05,
      "loss": 0.301,
      "step": 168
    },
    {
      "epoch": 0.7832005792903693,
      "grad_norm": 1.1182959079742432,
      "learning_rate": 1.0712452447341582e-05,
      "loss": 0.1367,
      "step": 169
    },
    {
      "epoch": 0.7878349022447502,
      "grad_norm": 1.0370293855667114,
      "learning_rate": 1.0048094716167095e-05,
      "loss": 0.1441,
      "step": 170
    },
    {
      "epoch": 0.7924692251991311,
      "grad_norm": 1.155311942100525,
      "learning_rate": 9.40352196454532e-06,
      "loss": 0.1666,
      "step": 171
    },
    {
      "epoch": 0.7971035481535119,
      "grad_norm": 1.0911647081375122,
      "learning_rate": 8.778930535580474e-06,
      "loss": 0.185,
      "step": 172
    },
    {
      "epoch": 0.8017378711078929,
      "grad_norm": 0.9174829721450806,
      "learning_rate": 8.174510685872415e-06,
      "loss": 0.1147,
      "step": 173
    },
    {
      "epoch": 0.8063721940622737,
      "grad_norm": 1.362585425376892,
      "learning_rate": 7.5904465275624884e-06,
      "loss": 0.2452,
      "step": 174
    },
    {
      "epoch": 0.8110065170166546,
      "grad_norm": 1.197021722793579,
      "learning_rate": 7.026915972251254e-06,
      "loss": 0.2385,
      "step": 175
    },
    {
      "epoch": 0.8156408399710355,
      "grad_norm": 1.0614386796951294,
      "learning_rate": 6.484090676804926e-06,
      "loss": 0.1824,
      "step": 176
    },
    {
      "epoch": 0.8202751629254164,
      "grad_norm": 1.1456388235092163,
      "learning_rate": 5.962135991066971e-06,
      "loss": 0.1921,
      "step": 177
    },
    {
      "epoch": 0.8249094858797973,
      "grad_norm": 1.2095783948898315,
      "learning_rate": 5.461210907490951e-06,
      "loss": 0.1803,
      "step": 178
    },
    {
      "epoch": 0.8295438088341781,
      "grad_norm": 1.2167255878448486,
      "learning_rate": 4.981468012709877e-06,
      "loss": 0.1777,
      "step": 179
    },
    {
      "epoch": 0.834178131788559,
      "grad_norm": 1.2779210805892944,
      "learning_rate": 4.523053441056876e-06,
      "loss": 0.2648,
      "step": 180
    },
    {
      "epoch": 0.8388124547429399,
      "grad_norm": 1.1896816492080688,
      "learning_rate": 4.086106830051236e-06,
      "loss": 0.1531,
      "step": 181
    },
    {
      "epoch": 0.8434467776973208,
      "grad_norm": 1.0845763683319092,
      "learning_rate": 3.670761277863485e-06,
      "loss": 0.1953,
      "step": 182
    },
    {
      "epoch": 0.8480811006517016,
      "grad_norm": 1.338794231414795,
      "learning_rate": 3.277143302772342e-06,
      "loss": 0.1878,
      "step": 183
    },
    {
      "epoch": 0.8527154236060825,
      "grad_norm": 1.036252737045288,
      "learning_rate": 2.9053728046260825e-06,
      "loss": 0.1352,
      "step": 184
    },
    {
      "epoch": 0.8573497465604635,
      "grad_norm": 1.3027642965316772,
      "learning_rate": 2.555563028319885e-06,
      "loss": 0.2213,
      "step": 185
    },
    {
      "epoch": 0.8619840695148443,
      "grad_norm": 1.0671361684799194,
      "learning_rate": 2.227820529300264e-06,
      "loss": 0.2172,
      "step": 186
    },
    {
      "epoch": 0.8666183924692252,
      "grad_norm": 1.0457696914672852,
      "learning_rate": 1.9222451411073645e-06,
      "loss": 0.1704,
      "step": 187
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1160316364382536e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}