{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 119,
  "global_step": 475,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.434104859828949,
      "learning_rate": 2e-05,
      "loss": 0.8629,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 0.9369699358940125,
      "eval_runtime": 61.2717,
      "eval_samples_per_second": 1.632,
      "eval_steps_per_second": 1.632,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.517804741859436,
      "learning_rate": 4e-05,
      "loss": 0.9794,
      "step": 2
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.3174158334732056,
      "learning_rate": 6e-05,
      "loss": 1.5473,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.6236504912376404,
      "learning_rate": 8e-05,
      "loss": 0.6592,
      "step": 4
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.49080607295036316,
      "learning_rate": 0.0001,
      "loss": 1.1104,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.43938764929771423,
      "learning_rate": 0.00012,
      "loss": 0.9446,
      "step": 6
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.8905380368232727,
      "learning_rate": 0.00014,
      "loss": 0.6719,
      "step": 7
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.9044575095176697,
      "learning_rate": 0.00016,
      "loss": 0.6471,
      "step": 8
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.541214108467102,
      "learning_rate": 0.00018,
      "loss": 0.8339,
      "step": 9
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.075484275817871,
      "learning_rate": 0.0002,
      "loss": 0.9616,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.3413633406162262,
      "learning_rate": 0.0001999998618515421,
      "loss": 0.8251,
      "step": 11
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.7642049193382263,
      "learning_rate": 0.00019999944740655014,
      "loss": 1.3883,
      "step": 12
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.5759286284446716,
      "learning_rate": 0.00019999875666616918,
      "loss": 0.9162,
      "step": 13
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.16646409034729,
      "learning_rate": 0.00019999778963230775,
      "loss": 1.1735,
      "step": 14
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.5447037220001221,
      "learning_rate": 0.0001999965463076377,
      "loss": 1.2769,
      "step": 15
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.510498046875,
      "learning_rate": 0.00019999502669559432,
      "loss": 1.1439,
      "step": 16
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.514502227306366,
      "learning_rate": 0.00019999323080037624,
      "loss": 0.9929,
      "step": 17
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.2014903873205185,
      "learning_rate": 0.00019999115862694546,
      "loss": 0.6706,
      "step": 18
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.6941856741905212,
      "learning_rate": 0.00019998881018102737,
      "loss": 0.7576,
      "step": 19
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.29424500465393066,
      "learning_rate": 0.00019998618546911056,
      "loss": 1.5048,
      "step": 20
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.431168556213379,
      "learning_rate": 0.00019998328449844714,
      "loss": 0.761,
      "step": 21
    },
    {
      "epoch": 0.05,
      "grad_norm": 2.672117233276367,
      "learning_rate": 0.00019998010727705236,
      "loss": 0.9434,
      "step": 22
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.40351876616477966,
      "learning_rate": 0.00019997665381370477,
      "loss": 1.2708,
      "step": 23
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.36313024163246155,
      "learning_rate": 0.00019997292411794618,
      "loss": 0.6931,
      "step": 24
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.7412884831428528,
      "learning_rate": 0.00019996891820008164,
      "loss": 0.827,
      "step": 25
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.7299063205718994,
      "learning_rate": 0.00019996463607117935,
      "loss": 0.7135,
      "step": 26
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.5188469290733337,
      "learning_rate": 0.00019996007774307075,
      "loss": 0.574,
      "step": 27
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.23084047436714172,
      "learning_rate": 0.00019995524322835034,
      "loss": 1.0736,
      "step": 28
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.7209138870239258,
      "learning_rate": 0.00019995013254037574,
      "loss": 0.9087,
      "step": 29
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.2266876697540283,
      "learning_rate": 0.00019994474569326757,
      "loss": 1.2464,
      "step": 30
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.6613232493400574,
      "learning_rate": 0.0001999390827019096,
      "loss": 0.9568,
      "step": 31
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.0048911571502686,
      "learning_rate": 0.00019993314358194843,
      "loss": 1.1935,
      "step": 32
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.9797032475471497,
      "learning_rate": 0.00019992692834979372,
      "loss": 1.1969,
      "step": 33
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.4784688353538513,
      "learning_rate": 0.00019992043702261793,
      "loss": 0.8674,
      "step": 34
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.863600015640259,
      "learning_rate": 0.00019991366961835642,
      "loss": 1.3276,
      "step": 35
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.4809297025203705,
      "learning_rate": 0.0001999066261557073,
      "loss": 1.0116,
      "step": 36
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.6229730844497681,
      "learning_rate": 0.00019989930665413147,
      "loss": 1.2794,
      "step": 37
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.5807106494903564,
      "learning_rate": 0.0001998917111338525,
      "loss": 1.0074,
      "step": 38
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.5811257362365723,
      "learning_rate": 0.00019988383961585645,
      "loss": 1.2491,
      "step": 39
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.46693727374076843,
      "learning_rate": 0.00019987569212189224,
      "loss": 0.8432,
      "step": 40
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.9792713522911072,
      "learning_rate": 0.00019986726867447107,
      "loss": 0.8716,
      "step": 41
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.3240562081336975,
      "learning_rate": 0.00019985856929686667,
      "loss": 0.9934,
      "step": 42
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.7358172535896301,
      "learning_rate": 0.0001998495940131152,
      "loss": 0.7247,
      "step": 43
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.40497535467147827,
      "learning_rate": 0.00019984034284801502,
      "loss": 0.8262,
      "step": 44
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.36835265159606934,
      "learning_rate": 0.00019983081582712685,
      "loss": 1.0898,
      "step": 45
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.7027626633644104,
      "learning_rate": 0.0001998210129767735,
      "loss": 1.2949,
      "step": 46
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.35624387860298157,
      "learning_rate": 0.00019981093432404006,
      "loss": 0.9734,
      "step": 47
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.4896808862686157,
      "learning_rate": 0.00019980057989677345,
      "loss": 1.2297,
      "step": 48
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.9656649827957153,
      "learning_rate": 0.00019978994972358265,
      "loss": 0.8358,
      "step": 49
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.644644021987915,
      "learning_rate": 0.0001997790438338385,
      "loss": 0.7373,
      "step": 50
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.0634011030197144,
      "learning_rate": 0.00019976786225767365,
      "loss": 1.3792,
      "step": 51
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.9041422605514526,
      "learning_rate": 0.00019975640502598244,
      "loss": 0.856,
      "step": 52
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.5682844519615173,
      "learning_rate": 0.00019974467217042085,
      "loss": 0.6686,
      "step": 53
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.7197520136833191,
      "learning_rate": 0.00019973266372340639,
      "loss": 0.6806,
      "step": 54
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.2542258501052856,
      "learning_rate": 0.00019972037971811802,
      "loss": 1.353,
      "step": 55
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.6802650094032288,
      "learning_rate": 0.0001997078201884961,
      "loss": 1.0014,
      "step": 56
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.4886693060398102,
      "learning_rate": 0.0001996949851692422,
      "loss": 0.8613,
      "step": 57
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.0226856470108032,
      "learning_rate": 0.0001996818746958191,
      "loss": 1.0443,
      "step": 58
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.5514834523200989,
      "learning_rate": 0.00019966848880445062,
      "loss": 0.8816,
      "step": 59
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.4890052378177643,
      "learning_rate": 0.00019965482753212156,
      "loss": 0.8541,
      "step": 60
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.9011398553848267,
      "learning_rate": 0.0001996408909165776,
      "loss": 1.1158,
      "step": 61
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.7809276580810547,
      "learning_rate": 0.00019962667899632518,
      "loss": 0.6702,
      "step": 62
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.604097843170166,
      "learning_rate": 0.00019961219181063142,
      "loss": 1.1875,
      "step": 63
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.9003333449363708,
      "learning_rate": 0.00019959742939952392,
      "loss": 1.2126,
      "step": 64
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.59239661693573,
      "learning_rate": 0.0001995823918037908,
      "loss": 1.1083,
      "step": 65
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.6981655955314636,
      "learning_rate": 0.00019956707906498044,
      "loss": 0.9634,
      "step": 66
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.4635857045650482,
      "learning_rate": 0.00019955149122540152,
      "loss": 1.0345,
      "step": 67
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.35098958015441895,
      "learning_rate": 0.00019953562832812272,
      "loss": 0.8871,
      "step": 68
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.4510989189147949,
      "learning_rate": 0.00019951949041697274,
      "loss": 0.6967,
      "step": 69
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.39661434292793274,
      "learning_rate": 0.00019950307753654017,
      "loss": 1.0786,
      "step": 70
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.5836047530174255,
      "learning_rate": 0.00019948638973217323,
      "loss": 0.9265,
      "step": 71
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.4589115381240845,
      "learning_rate": 0.00019946942704997982,
      "loss": 0.6476,
      "step": 72
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.4495834410190582,
      "learning_rate": 0.00019945218953682734,
      "loss": 0.8693,
      "step": 73
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.35905730724334717,
      "learning_rate": 0.00019943467724034252,
      "loss": 1.0325,
      "step": 74
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.235016345977783,
      "learning_rate": 0.0001994168902089112,
      "loss": 1.3103,
      "step": 75
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.36725524067878723,
      "learning_rate": 0.00019939882849167852,
      "loss": 0.908,
      "step": 76
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.66635662317276,
      "learning_rate": 0.0001993804921385484,
      "loss": 0.682,
      "step": 77
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.121004819869995,
      "learning_rate": 0.0001993618812001836,
      "loss": 0.8462,
      "step": 78
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.44895172119140625,
      "learning_rate": 0.00019934299572800556,
      "loss": 0.9625,
      "step": 79
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.5769445300102234,
      "learning_rate": 0.00019932383577419432,
      "loss": 0.7278,
      "step": 80
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.3807710111141205,
      "learning_rate": 0.00019930440139168817,
      "loss": 0.657,
      "step": 81
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.212838813662529,
      "learning_rate": 0.00019928469263418374,
      "loss": 0.3094,
      "step": 82
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.8039274215698242,
      "learning_rate": 0.0001992647095561357,
      "loss": 0.8898,
      "step": 83
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.7184070348739624,
      "learning_rate": 0.00019924445221275675,
      "loss": 0.8613,
      "step": 84
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.4697589874267578,
      "learning_rate": 0.00019922392066001722,
      "loss": 0.9533,
      "step": 85
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.7024903297424316,
      "learning_rate": 0.00019920311495464518,
      "loss": 0.7188,
      "step": 86
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.5008754730224609,
      "learning_rate": 0.00019918203515412617,
      "loss": 0.8329,
      "step": 87
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.6406499743461609,
      "learning_rate": 0.00019916068131670302,
      "loss": 1.4259,
      "step": 88
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.39489614963531494,
      "learning_rate": 0.00019913905350137573,
      "loss": 0.5831,
      "step": 89
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.7018424272537231,
      "learning_rate": 0.0001991171517679013,
      "loss": 0.9808,
      "step": 90
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.5011338591575623,
      "learning_rate": 0.00019909497617679348,
      "loss": 0.6806,
      "step": 91
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.2412053793668747,
      "learning_rate": 0.0001990725267893228,
      "loss": 1.0299,
      "step": 92
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.4145759046077728,
      "learning_rate": 0.00019904980366751624,
      "loss": 1.4344,
      "step": 93
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.5789082050323486,
      "learning_rate": 0.00019902680687415705,
      "loss": 0.4662,
      "step": 94
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.28986847400665283,
      "learning_rate": 0.00019900353647278466,
      "loss": 1.296,
      "step": 95
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.33722007274627686,
      "learning_rate": 0.00019897999252769448,
      "loss": 0.8011,
      "step": 96
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.6796722412109375,
      "learning_rate": 0.00019895617510393772,
      "loss": 0.972,
      "step": 97
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.5858548879623413,
      "learning_rate": 0.00019893208426732115,
      "loss": 1.0073,
      "step": 98
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.5766484141349792,
      "learning_rate": 0.00019890772008440704,
      "loss": 0.7884,
      "step": 99
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.37647876143455505,
      "learning_rate": 0.00019888308262251285,
      "loss": 0.6407,
      "step": 100
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.5475112199783325,
      "learning_rate": 0.00019885817194971117,
      "loss": 1.1401,
      "step": 101
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.1082801818847656,
      "learning_rate": 0.00019883298813482938,
      "loss": 1.392,
      "step": 102
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.3952051103115082,
      "learning_rate": 0.00019880753124744963,
      "loss": 1.0498,
      "step": 103
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.19289755821228027,
      "learning_rate": 0.00019878180135790845,
      "loss": 0.4145,
      "step": 104
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.5658400654792786,
      "learning_rate": 0.00019875579853729676,
      "loss": 1.0984,
      "step": 105
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.8976437449455261,
      "learning_rate": 0.00019872952285745959,
      "loss": 0.6919,
      "step": 106
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.5265024900436401,
      "learning_rate": 0.00019870297439099577,
      "loss": 1.2932,
      "step": 107
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.8367021083831787,
      "learning_rate": 0.00019867615321125795,
      "loss": 1.4497,
      "step": 108
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.5223955512046814,
      "learning_rate": 0.00019864905939235214,
      "loss": 1.0325,
      "step": 109
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.408779501914978,
      "learning_rate": 0.00019862169300913785,
      "loss": 0.9026,
      "step": 110
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.24817530810832977,
      "learning_rate": 0.00019859405413722746,
      "loss": 0.826,
      "step": 111
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.450430154800415,
      "learning_rate": 0.0001985661428529863,
      "loss": 0.9791,
      "step": 112
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.4882315993309021,
      "learning_rate": 0.0001985379592335325,
      "loss": 0.7889,
      "step": 113
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.42783451080322266,
      "learning_rate": 0.00019850950335673643,
      "loss": 1.1608,
      "step": 114
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.0337790250778198,
      "learning_rate": 0.00019848077530122083,
      "loss": 1.045,
      "step": 115
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.3064819872379303,
      "learning_rate": 0.00019845177514636042,
      "loss": 0.6474,
      "step": 116
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.29662173986434937,
      "learning_rate": 0.00019842250297228176,
      "loss": 0.9493,
      "step": 117
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.515562891960144,
      "learning_rate": 0.00019839295885986296,
      "loss": 1.0605,
      "step": 118
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.4514832496643066,
      "learning_rate": 0.0001983631428907335,
      "loss": 0.6917,
      "step": 119
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.8804921507835388,
      "eval_runtime": 61.5233,
      "eval_samples_per_second": 1.625,
      "eval_steps_per_second": 1.625,
      "step": 119
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.30757004022598267,
      "learning_rate": 0.00019833305514727395,
      "loss": 0.9722,
      "step": 120
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.5162855386734009,
      "learning_rate": 0.00019830269571261583,
      "loss": 1.2197,
      "step": 121
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.5095639824867249,
      "learning_rate": 0.00019827206467064133,
      "loss": 0.8676,
      "step": 122
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.4804045557975769,
      "learning_rate": 0.00019824116210598306,
      "loss": 0.8565,
      "step": 123
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.28008362650871277,
      "learning_rate": 0.0001982099881040239,
      "loss": 0.9001,
      "step": 124
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.6209085583686829,
      "learning_rate": 0.0001981785427508966,
      "loss": 0.7188,
      "step": 125
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.32877278327941895,
      "learning_rate": 0.0001981468261334837,
      "loss": 0.6749,
      "step": 126
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.4256601631641388,
      "learning_rate": 0.00019811483833941728,
      "loss": 0.8086,
      "step": 127
    },
    {
      "epoch": 0.27,
      "grad_norm": 1.1572288274765015,
      "learning_rate": 0.0001980825794570786,
      "loss": 0.8554,
      "step": 128
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.4987819194793701,
      "learning_rate": 0.00019805004957559793,
      "loss": 0.6999,
      "step": 129
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.6852537393569946,
      "learning_rate": 0.00019801724878485438,
      "loss": 0.8759,
      "step": 130
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.7970736622810364,
      "learning_rate": 0.00019798417717547552,
      "loss": 0.7471,
      "step": 131
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5638220310211182,
      "learning_rate": 0.00019795083483883715,
      "loss": 1.0391,
      "step": 132
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5482009649276733,
      "learning_rate": 0.00019791722186706317,
      "loss": 0.8363,
      "step": 133
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.23791633546352386,
      "learning_rate": 0.0001978833383530251,
      "loss": 0.725,
      "step": 134
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5339345335960388,
      "learning_rate": 0.00019784918439034216,
      "loss": 0.9828,
      "step": 135
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.24769064784049988,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.9496,
      "step": 136
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.46634215116500854,
      "learning_rate": 0.00019778006549725375,
      "loss": 1.0973,
      "step": 137
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.8007522821426392,
      "learning_rate": 0.00019774510075782172,
      "loss": 0.6847,
      "step": 138
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.5393804907798767,
      "learning_rate": 0.00019770986595169096,
      "loss": 0.6461,
      "step": 139
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.2891620695590973,
      "learning_rate": 0.00019767436117621413,
      "loss": 0.2937,
      "step": 140
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.9463545680046082,
      "learning_rate": 0.0001976385865294899,
      "loss": 0.4934,
      "step": 141
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.25647807121276855,
      "learning_rate": 0.00019760254211036244,
      "loss": 0.7446,
      "step": 142
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.49435535073280334,
      "learning_rate": 0.00019756622801842143,
      "loss": 0.3544,
      "step": 143
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.7826042175292969,
      "learning_rate": 0.00019752964435400155,
      "loss": 0.6972,
      "step": 144
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.7160178422927856,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.9655,
      "step": 145
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.3925221264362335,
      "learning_rate": 0.00019745566871278794,
      "loss": 0.9041,
      "step": 146
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.5669321417808533,
      "learning_rate": 0.0001974182769403866,
      "loss": 0.9093,
      "step": 147
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.5025343298912048,
      "learning_rate": 0.00019738061600429064,
      "loss": 0.6226,
      "step": 148
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.1127972602844238,
      "learning_rate": 0.0001973426860085561,
      "loss": 0.7431,
      "step": 149
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.4064362049102783,
      "learning_rate": 0.00019730448705798239,
      "loss": 0.8444,
      "step": 150
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.9272475242614746,
      "learning_rate": 0.00019726601925811204,
      "loss": 0.836,
      "step": 151
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.6594715118408203,
      "learning_rate": 0.00019722728271523034,
      "loss": 0.9031,
      "step": 152
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.9399688839912415,
      "learning_rate": 0.00019718827753636522,
      "loss": 0.7959,
      "step": 153
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.4452652633190155,
      "learning_rate": 0.00019714900382928675,
      "loss": 0.5638,
      "step": 154
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.47481146454811096,
      "learning_rate": 0.000197109461702507,
      "loss": 0.8291,
      "step": 155
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.1962246149778366,
      "learning_rate": 0.00019706965126527963,
      "loss": 0.7894,
      "step": 156
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.366571307182312,
      "learning_rate": 0.00019702957262759965,
      "loss": 1.1808,
      "step": 157
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.3261445760726929,
      "learning_rate": 0.00019698922590020312,
      "loss": 0.8769,
      "step": 158
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.5637160539627075,
      "learning_rate": 0.00019694861119456679,
      "loss": 0.882,
      "step": 159
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.4508800208568573,
      "learning_rate": 0.0001969077286229078,
      "loss": 1.2723,
      "step": 160
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.41292956471443176,
      "learning_rate": 0.0001968665782981835,
      "loss": 0.7919,
      "step": 161
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.6105634570121765,
      "learning_rate": 0.00019682516033409092,
      "loss": 1.0901,
      "step": 162
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.6460319757461548,
      "learning_rate": 0.00019678347484506669,
      "loss": 1.0425,
      "step": 163
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.8627430200576782,
      "learning_rate": 0.00019674152194628638,
      "loss": 0.8019,
      "step": 164
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.3218872547149658,
      "learning_rate": 0.00019669930175366472,
      "loss": 0.8345,
      "step": 165
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.6773053407669067,
      "learning_rate": 0.00019665681438385473,
      "loss": 1.3567,
      "step": 166
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.3802971839904785,
      "learning_rate": 0.0001966140599542477,
      "loss": 0.7315,
      "step": 167
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.9038891196250916,
      "learning_rate": 0.0001965710385829728,
      "loss": 0.6807,
      "step": 168
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.7831525802612305,
      "learning_rate": 0.00019652775038889674,
      "loss": 1.2796,
      "step": 169
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.3705346882343292,
      "learning_rate": 0.00019648419549162348,
      "loss": 0.8275,
      "step": 170
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.7794845104217529,
      "learning_rate": 0.0001964403740114939,
      "loss": 0.7539,
      "step": 171
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.2621815800666809,
      "learning_rate": 0.00019639628606958533,
      "loss": 0.976,
      "step": 172
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.6929745674133301,
      "learning_rate": 0.00019635193178771143,
      "loss": 0.6198,
      "step": 173
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.543230414390564,
      "learning_rate": 0.0001963073112884217,
      "loss": 0.9319,
      "step": 174
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.6732174158096313,
      "learning_rate": 0.0001962624246950012,
      "loss": 0.804,
      "step": 175
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.25452062487602234,
      "learning_rate": 0.00019621727213147027,
      "loss": 0.7632,
      "step": 176
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.6591973304748535,
      "learning_rate": 0.00019617185372258392,
      "loss": 0.9745,
      "step": 177
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.6275454163551331,
      "learning_rate": 0.0001961261695938319,
      "loss": 0.3411,
      "step": 178
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.6691128611564636,
      "learning_rate": 0.00019608021987143804,
      "loss": 0.9564,
      "step": 179
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.3190310299396515,
      "learning_rate": 0.00019603400468235998,
      "loss": 1.3002,
      "step": 180
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.4648153781890869,
      "learning_rate": 0.0001959875241542889,
      "loss": 0.9507,
      "step": 181
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.5921639800071716,
      "learning_rate": 0.00019594077841564907,
      "loss": 0.9397,
      "step": 182
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.5769446492195129,
      "learning_rate": 0.00019589376759559745,
      "loss": 0.9958,
      "step": 183
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.8454503417015076,
      "learning_rate": 0.00019584649182402357,
      "loss": 1.189,
      "step": 184
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.2865101099014282,
      "learning_rate": 0.0001957989512315489,
      "loss": 0.6747,
      "step": 185
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.3642055094242096,
      "learning_rate": 0.0001957511459495266,
      "loss": 0.5196,
      "step": 186
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.4965610206127167,
      "learning_rate": 0.00019570307611004124,
      "loss": 0.9448,
      "step": 187
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.5694214105606079,
      "learning_rate": 0.00019565474184590826,
      "loss": 0.868,
      "step": 188
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.6402484774589539,
      "learning_rate": 0.00019560614329067378,
      "loss": 0.8872,
      "step": 189
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.37722048163414,
      "learning_rate": 0.0001955572805786141,
      "loss": 0.9253,
      "step": 190
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.9157966375350952,
      "learning_rate": 0.00019550815384473534,
      "loss": 1.6508,
      "step": 191
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.33376675844192505,
      "learning_rate": 0.0001954587632247732,
      "loss": 0.9109,
      "step": 192
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.2680880129337311,
      "learning_rate": 0.00019540910885519242,
      "loss": 1.0693,
      "step": 193
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.7726811766624451,
      "learning_rate": 0.00019535919087318652,
      "loss": 0.9574,
      "step": 194
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.8604207634925842,
      "learning_rate": 0.0001953090094166773,
      "loss": 0.9475,
      "step": 195
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.3954675197601318,
      "learning_rate": 0.0001952585646243146,
      "loss": 1.5094,
      "step": 196
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.39931145310401917,
      "learning_rate": 0.00019520785663547586,
      "loss": 0.9915,
      "step": 197
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.772156298160553,
      "learning_rate": 0.00019515688559026563,
      "loss": 1.4155,
      "step": 198
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.48633861541748047,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.9607,
      "step": 199
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.4661516845226288,
      "learning_rate": 0.0001950541548947829,
      "loss": 1.0283,
      "step": 200
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.8846752047538757,
      "learning_rate": 0.00019500239552835215,
      "loss": 0.756,
      "step": 201
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.9870714545249939,
      "learning_rate": 0.00019495037367323262,
      "loss": 0.7688,
      "step": 202
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.7435501217842102,
      "learning_rate": 0.00019489808947315915,
      "loss": 0.4752,
      "step": 203
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.6509325504302979,
      "learning_rate": 0.0001948455430725913,
      "loss": 0.9053,
      "step": 204
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.30190637707710266,
      "learning_rate": 0.0001947927346167132,
      "loss": 0.9323,
      "step": 205
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.420055627822876,
      "learning_rate": 0.00019473966425143292,
      "loss": 0.6446,
      "step": 206
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.49513018131256104,
      "learning_rate": 0.00019468633212338233,
      "loss": 0.9022,
      "step": 207
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.4812709391117096,
      "learning_rate": 0.00019463273837991643,
      "loss": 0.6835,
      "step": 208
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.2101246416568756,
      "learning_rate": 0.00019457888316911306,
      "loss": 0.5991,
      "step": 209
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.3539298176765442,
      "learning_rate": 0.00019452476663977248,
      "loss": 0.7323,
      "step": 210
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.29954612255096436,
      "learning_rate": 0.00019447038894141705,
      "loss": 0.6868,
      "step": 211
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.4053567349910736,
      "learning_rate": 0.00019441575022429065,
      "loss": 1.0805,
      "step": 212
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.7733739614486694,
      "learning_rate": 0.00019436085063935835,
      "loss": 1.3524,
      "step": 213
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.6096423864364624,
      "learning_rate": 0.00019430569033830605,
      "loss": 1.0183,
      "step": 214
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.1940584182739258,
      "learning_rate": 0.00019425026947353992,
      "loss": 1.0919,
      "step": 215
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.4030895233154297,
      "learning_rate": 0.00019419458819818614,
      "loss": 0.7642,
      "step": 216
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.4116997718811035,
      "learning_rate": 0.00019413864666609034,
      "loss": 0.6112,
      "step": 217
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.4545953869819641,
      "learning_rate": 0.00019408244503181724,
      "loss": 0.7328,
      "step": 218
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.9334838390350342,
      "learning_rate": 0.0001940259834506502,
      "loss": 1.0518,
      "step": 219
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.2695348858833313,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.987,
      "step": 220
    },
    {
      "epoch": 0.47,
      "grad_norm": 1.3967281579971313,
      "learning_rate": 0.00019391228107235858,
      "loss": 1.0819,
      "step": 221
    },
    {
      "epoch": 0.47,
      "grad_norm": 1.0220236778259277,
      "learning_rate": 0.00019385504058939024,
      "loss": 0.9621,
      "step": 222
    },
    {
      "epoch": 0.47,
      "grad_norm": 2.5694682598114014,
      "learning_rate": 0.00019379754078783937,
      "loss": 1.0647,
      "step": 223
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.6181725263595581,
      "learning_rate": 0.00019373978182657625,
      "loss": 1.0991,
      "step": 224
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.508532702922821,
      "learning_rate": 0.0001936817638651871,
      "loss": 1.0276,
      "step": 225
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.3763074278831482,
      "learning_rate": 0.00019362348706397373,
      "loss": 0.7447,
      "step": 226
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.9533042311668396,
      "learning_rate": 0.00019356495158395315,
      "loss": 1.1979,
      "step": 227
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.43593689799308777,
      "learning_rate": 0.00019350615758685708,
      "loss": 1.0028,
      "step": 228
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.7646205425262451,
      "learning_rate": 0.00019344710523513156,
      "loss": 1.463,
      "step": 229
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.29402196407318115,
      "learning_rate": 0.00019338779469193639,
      "loss": 1.2726,
      "step": 230
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.5773300528526306,
      "learning_rate": 0.00019332822612114475,
      "loss": 0.4847,
      "step": 231
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.0580178499221802,
      "learning_rate": 0.00019326839968734279,
      "loss": 1.0639,
      "step": 232
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.6212771534919739,
      "learning_rate": 0.00019320831555582908,
      "loss": 0.7302,
      "step": 233
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.1953450441360474,
      "learning_rate": 0.00019314797389261424,
      "loss": 0.9873,
      "step": 234
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.856995940208435,
      "learning_rate": 0.00019308737486442045,
      "loss": 0.9573,
      "step": 235
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.36539939045906067,
      "learning_rate": 0.00019302651863868092,
      "loss": 0.6884,
      "step": 236
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.3269266188144684,
      "learning_rate": 0.0001929654053835395,
      "loss": 0.9445,
      "step": 237
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.46403074264526367,
      "learning_rate": 0.00019290403526785025,
      "loss": 0.9783,
      "step": 238
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.8782849311828613,
      "eval_runtime": 61.3598,
      "eval_samples_per_second": 1.63,
      "eval_steps_per_second": 1.63,
      "step": 238
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.6627680659294128,
      "learning_rate": 0.00019284240846117697,
      "loss": 0.9527,
      "step": 239
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.866802990436554,
      "learning_rate": 0.00019278052513379255,
      "loss": 0.6096,
      "step": 240
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.5304962396621704,
      "learning_rate": 0.00019271838545667876,
      "loss": 0.8335,
      "step": 241
    },
    {
      "epoch": 0.51,
      "grad_norm": 1.076063632965088,
      "learning_rate": 0.00019265598960152555,
      "loss": 1.3308,
      "step": 242
    },
    {
      "epoch": 0.51,
      "grad_norm": 2.491516351699829,
      "learning_rate": 0.00019259333774073083,
      "loss": 1.4458,
      "step": 243
    },
    {
      "epoch": 0.51,
      "grad_norm": 1.3771064281463623,
      "learning_rate": 0.00019253043004739968,
      "loss": 1.4581,
      "step": 244
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.24413131177425385,
      "learning_rate": 0.00019246726669534415,
      "loss": 0.7537,
      "step": 245
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.02517831325531,
      "learning_rate": 0.00019240384785908265,
      "loss": 1.0646,
      "step": 246
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.4848421514034271,
      "learning_rate": 0.00019234017371383945,
      "loss": 0.6972,
      "step": 247
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.8870792388916016,
      "learning_rate": 0.00019227624443554425,
      "loss": 1.2114,
      "step": 248
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.5171313285827637,
      "learning_rate": 0.00019221206020083166,
      "loss": 0.7243,
      "step": 249
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.5975112915039062,
      "learning_rate": 0.00019214762118704076,
      "loss": 0.964,
      "step": 250
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.0921701192855835,
      "learning_rate": 0.0001920829275722146,
      "loss": 1.1413,
      "step": 251
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.6540035009384155,
      "learning_rate": 0.00019201797953509955,
      "loss": 0.9732,
      "step": 252
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.137863278388977,
      "learning_rate": 0.0001919527772551451,
      "loss": 1.3374,
      "step": 253
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.4139158725738525,
      "learning_rate": 0.00019188732091250307,
      "loss": 1.1147,
      "step": 254
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.5039550065994263,
      "learning_rate": 0.00019182161068802741,
      "loss": 0.7832,
      "step": 255
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.567670464515686,
      "learning_rate": 0.00019175564676327339,
      "loss": 0.6684,
      "step": 256
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.4372114837169647,
      "learning_rate": 0.0001916894293204973,
      "loss": 0.7285,
      "step": 257
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.4466225206851959,
      "learning_rate": 0.00019162295854265594,
      "loss": 0.5705,
      "step": 258
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.7975250482559204,
      "learning_rate": 0.00019155623461340594,
      "loss": 1.4155,
      "step": 259
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.6310514211654663,
      "learning_rate": 0.00019148925771710347,
      "loss": 0.7388,
      "step": 260
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5273220539093018,
      "learning_rate": 0.0001914220280388037,
      "loss": 0.9241,
      "step": 261
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.8354101181030273,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.8085,
      "step": 262
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.7362698316574097,
      "learning_rate": 0.00019128681107992415,
      "loss": 0.953,
      "step": 263
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.5334580540657043,
      "learning_rate": 0.00019121882417294462,
      "loss": 0.4416,
      "step": 264
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.6351854205131531,
      "learning_rate": 0.00019115058523116733,
      "loss": 0.6414,
      "step": 265
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.28386977314949036,
      "learning_rate": 0.00019108209444313433,
      "loss": 1.0273,
      "step": 266
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.5504246354103088,
      "learning_rate": 0.00019101335199808354,
      "loss": 1.1191,
      "step": 267
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.7449864149093628,
      "learning_rate": 0.00019094435808594823,
      "loss": 1.1073,
      "step": 268
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.6302490830421448,
      "learning_rate": 0.00019087511289735644,
      "loss": 1.2092,
      "step": 269
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.5618910789489746,
      "learning_rate": 0.0001908056166236305,
      "loss": 1.1966,
      "step": 270
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.46393775939941406,
      "learning_rate": 0.0001907358694567865,
      "loss": 0.7148,
      "step": 271
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.34640607237815857,
      "learning_rate": 0.00019066587158953366,
      "loss": 1.1297,
      "step": 272
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.3277580738067627,
      "learning_rate": 0.00019059562321527396,
      "loss": 1.0978,
      "step": 273
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.8730579018592834,
      "learning_rate": 0.0001905251245281015,
      "loss": 0.9732,
      "step": 274
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.32950034737586975,
      "learning_rate": 0.00019045437572280194,
      "loss": 1.0795,
      "step": 275
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.48170116543769836,
      "learning_rate": 0.00019038337699485208,
      "loss": 0.8124,
      "step": 276
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.858323335647583,
      "learning_rate": 0.00019031212854041918,
      "loss": 0.813,
      "step": 277
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.9366027116775513,
      "learning_rate": 0.00019024063055636057,
      "loss": 1.5074,
      "step": 278
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.4378308653831482,
      "learning_rate": 0.00019016888324022296,
      "loss": 0.8387,
      "step": 279
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.5781106948852539,
      "learning_rate": 0.0001900968867902419,
      "loss": 1.0496,
      "step": 280
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.834186851978302,
      "learning_rate": 0.00019002464140534147,
      "loss": 1.2684,
      "step": 281
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.752008855342865,
      "learning_rate": 0.00018995214728513343,
      "loss": 1.069,
      "step": 282
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3941871225833893,
      "learning_rate": 0.0001898794046299167,
      "loss": 0.942,
      "step": 283
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.4069131314754486,
      "learning_rate": 0.0001898064136406771,
      "loss": 0.7116,
      "step": 284
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.6478765606880188,
      "learning_rate": 0.00018973317451908642,
      "loss": 0.9494,
      "step": 285
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.8658535480499268,
      "learning_rate": 0.0001896596874675021,
      "loss": 0.7592,
      "step": 286
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.8622011542320251,
      "learning_rate": 0.0001895859526889666,
      "loss": 0.9392,
      "step": 287
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.8127020001411438,
      "learning_rate": 0.00018951197038720688,
      "loss": 1.3309,
      "step": 288
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.5042945146560669,
      "learning_rate": 0.0001894377407666337,
      "loss": 0.7607,
      "step": 289
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.7252426743507385,
      "learning_rate": 0.00018936326403234125,
      "loss": 1.1221,
      "step": 290
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.7334456443786621,
      "learning_rate": 0.0001892885403901064,
      "loss": 0.4738,
      "step": 291
    },
    {
      "epoch": 0.61,
      "grad_norm": 2.6204662322998047,
      "learning_rate": 0.00018921357004638835,
      "loss": 1.2511,
      "step": 292
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.5708286762237549,
      "learning_rate": 0.00018913835320832778,
      "loss": 1.0887,
      "step": 293
    },
    {
      "epoch": 0.62,
      "grad_norm": 1.0324314832687378,
      "learning_rate": 0.00018906289008374655,
      "loss": 1.1019,
      "step": 294
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.3663407862186432,
      "learning_rate": 0.0001889871808811469,
      "loss": 1.0333,
      "step": 295
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.7219849824905396,
      "learning_rate": 0.00018891122580971098,
      "loss": 0.858,
      "step": 296
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.7850363850593567,
      "learning_rate": 0.00018883502507930042,
      "loss": 0.9503,
      "step": 297
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.28012195229530334,
      "learning_rate": 0.00018875857890045543,
      "loss": 0.8068,
      "step": 298
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.7574068307876587,
      "learning_rate": 0.00018868188748439444,
      "loss": 0.7557,
      "step": 299
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.9131019711494446,
      "learning_rate": 0.00018860495104301345,
      "loss": 1.1462,
      "step": 300
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.24085545539855957,
      "learning_rate": 0.00018852776978888551,
      "loss": 0.8286,
      "step": 301
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.4502617418766022,
      "learning_rate": 0.00018845034393526005,
      "loss": 1.0052,
      "step": 302
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.7258254289627075,
      "learning_rate": 0.00018837267369606228,
      "loss": 0.9703,
      "step": 303
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.6078888773918152,
      "learning_rate": 0.00018829475928589271,
      "loss": 0.8479,
      "step": 304
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.5912296772003174,
      "learning_rate": 0.00018821660092002641,
      "loss": 1.0336,
      "step": 305
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.3440995216369629,
      "learning_rate": 0.0001881381988144126,
      "loss": 0.7629,
      "step": 306
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5613306164741516,
      "learning_rate": 0.0001880595531856738,
      "loss": 1.0355,
      "step": 307
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5265874862670898,
      "learning_rate": 0.0001879806642511055,
      "loss": 0.9046,
      "step": 308
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.37300053238868713,
      "learning_rate": 0.0001879015322286754,
      "loss": 0.578,
      "step": 309
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.7948945164680481,
      "learning_rate": 0.00018782215733702286,
      "loss": 0.5693,
      "step": 310
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5222792625427246,
      "learning_rate": 0.0001877425397954582,
      "loss": 0.812,
      "step": 311
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.6407319903373718,
      "learning_rate": 0.00018766267982396224,
      "loss": 0.7317,
      "step": 312
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.36041396856307983,
      "learning_rate": 0.00018758257764318567,
      "loss": 0.3617,
      "step": 313
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.6465966105461121,
      "learning_rate": 0.00018750223347444828,
      "loss": 0.6037,
      "step": 314
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.4281207025051117,
      "learning_rate": 0.00018742164753973855,
      "loss": 0.5269,
      "step": 315
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.3671799898147583,
      "learning_rate": 0.00018734082006171299,
      "loss": 0.66,
      "step": 316
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.4369129240512848,
      "learning_rate": 0.00018725975126369535,
      "loss": 1.1395,
      "step": 317
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.4631548523902893,
      "learning_rate": 0.00018717844136967624,
      "loss": 0.7871,
      "step": 318
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.4736942946910858,
      "learning_rate": 0.00018709689060431242,
      "loss": 1.2983,
      "step": 319
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.7346480488777161,
      "learning_rate": 0.00018701509919292613,
      "loss": 0.9507,
      "step": 320
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.5298660397529602,
      "learning_rate": 0.00018693306736150444,
      "loss": 0.6621,
      "step": 321
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.5501769781112671,
      "learning_rate": 0.0001868507953366989,
      "loss": 0.6954,
      "step": 322
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.565510630607605,
      "learning_rate": 0.0001867682833458245,
      "loss": 1.2279,
      "step": 323
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.2679019570350647,
      "learning_rate": 0.00018668553161685933,
      "loss": 0.6207,
      "step": 324
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.0185893774032593,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.1179,
      "step": 325
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.400493323802948,
      "learning_rate": 0.00018651930985988036,
      "loss": 0.5947,
      "step": 326
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.7746186256408691,
      "learning_rate": 0.00018643584029113215,
      "loss": 1.0365,
      "step": 327
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.5792235136032104,
      "learning_rate": 0.0001863521319028231,
      "loss": 0.7102,
      "step": 328
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.35895833373069763,
      "learning_rate": 0.00018626818492623688,
      "loss": 0.5571,
      "step": 329
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.41158926486968994,
      "learning_rate": 0.0001861839995933164,
      "loss": 0.9009,
      "step": 330
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.5845640301704407,
      "learning_rate": 0.00018609957613666315,
      "loss": 0.3317,
      "step": 331
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.4458400309085846,
      "learning_rate": 0.00018601491478953657,
      "loss": 1.0094,
      "step": 332
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.6415822505950928,
      "learning_rate": 0.00018593001578585326,
      "loss": 0.9772,
      "step": 333
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.616220474243164,
      "learning_rate": 0.00018584487936018661,
      "loss": 0.6879,
      "step": 334
    },
    {
      "epoch": 0.71,
      "grad_norm": 1.4885902404785156,
      "learning_rate": 0.00018575950574776595,
      "loss": 0.9627,
      "step": 335
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.2818461060523987,
      "learning_rate": 0.0001856738951844759,
      "loss": 0.9156,
      "step": 336
    },
    {
      "epoch": 0.71,
      "grad_norm": 1.2286068201065063,
      "learning_rate": 0.00018558804790685588,
      "loss": 2.6577,
      "step": 337
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.7086435556411743,
      "learning_rate": 0.00018550196415209914,
      "loss": 0.8172,
      "step": 338
    },
    {
      "epoch": 0.71,
      "grad_norm": 1.0317937135696411,
      "learning_rate": 0.00018541564415805258,
      "loss": 1.3381,
      "step": 339
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.693418562412262,
      "learning_rate": 0.00018532908816321558,
      "loss": 1.1259,
      "step": 340
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.25714910030365,
      "learning_rate": 0.00018524229640673974,
      "loss": 0.7892,
      "step": 341
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.6042699813842773,
      "learning_rate": 0.00018515526912842796,
      "loss": 0.8982,
      "step": 342
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.3453720211982727,
      "learning_rate": 0.00018506800656873398,
      "loss": 0.9424,
      "step": 343
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.7436335682868958,
      "learning_rate": 0.0001849805089687615,
      "loss": 0.7121,
      "step": 344
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.8308970928192139,
      "learning_rate": 0.00018489277657026375,
      "loss": 1.1099,
      "step": 345
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.6892271637916565,
      "learning_rate": 0.0001848048096156426,
      "loss": 0.6814,
      "step": 346
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.30851200222969055,
      "learning_rate": 0.00018471660834794805,
      "loss": 0.283,
      "step": 347
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.2706887722015381,
      "learning_rate": 0.00018462817301087748,
      "loss": 0.6258,
      "step": 348
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.9876924157142639,
      "learning_rate": 0.00018453950384877504,
      "loss": 0.6983,
      "step": 349
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.3037252128124237,
      "learning_rate": 0.0001844506011066308,
      "loss": 0.9854,
      "step": 350
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.0091379880905151,
      "learning_rate": 0.00018436146503008035,
      "loss": 0.9871,
      "step": 351
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.5219744443893433,
      "learning_rate": 0.0001842720958654039,
      "loss": 0.3771,
      "step": 352
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.49409008026123047,
      "learning_rate": 0.00018418249385952575,
      "loss": 1.0838,
      "step": 353
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.29014095664024353,
      "learning_rate": 0.00018409265926001343,
      "loss": 0.9922,
      "step": 354
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3307441771030426,
      "learning_rate": 0.00018400259231507717,
      "loss": 1.0458,
      "step": 355
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3356322646141052,
      "learning_rate": 0.00018391229327356916,
      "loss": 0.9891,
      "step": 356
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3707556426525116,
      "learning_rate": 0.00018382176238498286,
      "loss": 0.9578,
      "step": 357
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.8826732635498047,
      "eval_runtime": 61.8974,
      "eval_samples_per_second": 1.616,
      "eval_steps_per_second": 1.616,
      "step": 357
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.7507327198982239,
      "learning_rate": 0.00018373099989945236,
      "loss": 0.8916,
      "step": 358
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.3686985373497009,
      "learning_rate": 0.00018364000606775155,
      "loss": 0.9855,
      "step": 359
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.34240958094596863,
      "learning_rate": 0.00018354878114129367,
      "loss": 1.0874,
      "step": 360
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.2911188304424286,
      "learning_rate": 0.00018345732537213027,
      "loss": 1.2217,
      "step": 361
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.5415646433830261,
      "learning_rate": 0.0001833656390129509,
      "loss": 0.6675,
      "step": 362
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.36682239174842834,
      "learning_rate": 0.00018327372231708212,
      "loss": 0.8702,
      "step": 363
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.5462591648101807,
      "learning_rate": 0.0001831815755384869,
      "loss": 0.9005,
      "step": 364
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.5059930682182312,
      "learning_rate": 0.00018308919893176396,
      "loss": 0.8994,
      "step": 365
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.6344266533851624,
      "learning_rate": 0.00018299659275214706,
      "loss": 1.1571,
      "step": 366
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.2552272081375122,
      "learning_rate": 0.00018290375725550417,
      "loss": 1.2492,
      "step": 367
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.5543289184570312,
      "learning_rate": 0.00018281069269833692,
      "loss": 1.0141,
      "step": 368
    },
    {
      "epoch": 0.78,
      "grad_norm": 1.3686586618423462,
      "learning_rate": 0.0001827173993377798,
      "loss": 0.8264,
      "step": 369
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.5549390912055969,
      "learning_rate": 0.0001826238774315995,
      "loss": 1.0753,
      "step": 370
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.8563418388366699,
      "learning_rate": 0.00018253012723819416,
      "loss": 0.4458,
      "step": 371
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.4292491376399994,
      "learning_rate": 0.00018243614901659264,
      "loss": 1.1994,
      "step": 372
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.37186571955680847,
      "learning_rate": 0.00018234194302645394,
      "loss": 0.9811,
      "step": 373
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.6655788421630859,
      "learning_rate": 0.00018224750952806624,
      "loss": 0.5048,
      "step": 374
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.7731723785400391,
      "learning_rate": 0.00018215284878234642,
      "loss": 0.9481,
      "step": 375
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.36243554949760437,
      "learning_rate": 0.00018205796105083915,
      "loss": 1.0048,
      "step": 376
    },
    {
      "epoch": 0.79,
      "grad_norm": 1.08484947681427,
      "learning_rate": 0.00018196284659571639,
      "loss": 1.0245,
      "step": 377
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.128653883934021,
      "learning_rate": 0.00018186750567977637,
      "loss": 0.9997,
      "step": 378
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6685619950294495,
      "learning_rate": 0.00018177193856644316,
      "loss": 1.3555,
      "step": 379
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.30426543951034546,
      "learning_rate": 0.00018167614551976567,
      "loss": 1.1209,
      "step": 380
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6189528107643127,
      "learning_rate": 0.00018158012680441723,
      "loss": 1.0321,
      "step": 381
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6775807738304138,
      "learning_rate": 0.00018148388268569453,
      "loss": 0.7826,
      "step": 382
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.4594517946243286,
      "learning_rate": 0.00018138741342951705,
      "loss": 0.6422,
      "step": 383
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.537011444568634,
      "learning_rate": 0.00018129071930242648,
      "loss": 0.9219,
      "step": 384
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.43772855401039124,
      "learning_rate": 0.00018119380057158568,
      "loss": 1.1737,
      "step": 385
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.7221130132675171,
      "learning_rate": 0.00018109665750477806,
      "loss": 0.8636,
      "step": 386
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.3437989354133606,
      "learning_rate": 0.00018099929037040694,
      "loss": 0.9238,
      "step": 387
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.47244492173194885,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.7715,
      "step": 388
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.7109631299972534,
      "learning_rate": 0.0001808038849756822,
      "loss": 0.4109,
      "step": 389
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.27005669474601746,
      "learning_rate": 0.00018070584725522762,
      "loss": 0.7158,
      "step": 390
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.4006590247154236,
      "learning_rate": 0.00018060758654700622,
      "loss": 1.0167,
      "step": 391
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.5627204179763794,
      "learning_rate": 0.00018050910312250931,
      "loss": 0.8679,
      "step": 392
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.5019241571426392,
      "learning_rate": 0.00018041039725384352,
      "loss": 0.9163,
      "step": 393
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.00431227684021,
      "learning_rate": 0.00018031146921373018,
      "loss": 0.676,
      "step": 394
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.7062071561813354,
      "learning_rate": 0.0001802123192755044,
      "loss": 1.2407,
      "step": 395
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.6554285287857056,
      "learning_rate": 0.00018011294771311435,
      "loss": 1.1187,
      "step": 396
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.08072829246521,
      "learning_rate": 0.00018001335480112064,
      "loss": 0.4878,
      "step": 397
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.3923906981945038,
      "learning_rate": 0.00017991354081469538,
      "loss": 0.7836,
      "step": 398
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.20446747541427612,
      "learning_rate": 0.0001798135060296216,
      "loss": 0.4597,
      "step": 399
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.5178759098052979,
      "learning_rate": 0.00017971325072229226,
      "loss": 1.7021,
      "step": 400
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.5159180164337158,
      "learning_rate": 0.0001796127751697097,
      "loss": 0.6037,
      "step": 401
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.9448319673538208,
      "learning_rate": 0.0001795120796494848,
      "loss": 0.8965,
      "step": 402
    },
    {
      "epoch": 0.85,
      "grad_norm": 1.0035223960876465,
      "learning_rate": 0.00017941116443983613,
      "loss": 0.9786,
      "step": 403
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.26040011644363403,
      "learning_rate": 0.00017931002981958933,
      "loss": 0.8624,
      "step": 404
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.518144965171814,
      "learning_rate": 0.00017920867606817625,
      "loss": 1.0095,
      "step": 405
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.5256940722465515,
      "learning_rate": 0.00017910710346563416,
      "loss": 0.7392,
      "step": 406
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.8347258567810059,
      "learning_rate": 0.000179005312292605,
      "loss": 0.8081,
      "step": 407
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.8221095204353333,
      "learning_rate": 0.00017890330283033468,
      "loss": 1.1406,
      "step": 408
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.8048923015594482,
      "learning_rate": 0.00017880107536067218,
      "loss": 1.4362,
      "step": 409
    },
    {
      "epoch": 0.86,
      "grad_norm": 1.9037342071533203,
      "learning_rate": 0.0001786986301660689,
      "loss": 1.2935,
      "step": 410
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.5521582961082458,
      "learning_rate": 0.00017859596752957768,
      "loss": 1.0742,
      "step": 411
    },
    {
      "epoch": 0.87,
      "grad_norm": 1.052284598350525,
      "learning_rate": 0.00017849308773485226,
      "loss": 0.7661,
      "step": 412
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.43000859022140503,
      "learning_rate": 0.00017838999106614632,
      "loss": 0.812,
      "step": 413
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.7804751396179199,
      "learning_rate": 0.00017828667780831278,
      "loss": 0.7995,
      "step": 414
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.5827552080154419,
      "learning_rate": 0.000178183148246803,
      "loss": 0.6489,
      "step": 415
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.3453142642974854,
      "learning_rate": 0.00017807940266766593,
      "loss": 0.7154,
      "step": 416
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.24924832582473755,
      "learning_rate": 0.00017797544135754744,
      "loss": 0.8061,
      "step": 417
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.4459979236125946,
      "learning_rate": 0.0001778712646036894,
      "loss": 1.1167,
      "step": 418
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.6095878481864929,
      "learning_rate": 0.000177766872693929,
      "loss": 0.8344,
      "step": 419
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.43662723898887634,
      "learning_rate": 0.00017766226591669785,
      "loss": 1.0373,
      "step": 420
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.8759774565696716,
      "learning_rate": 0.00017755744456102122,
      "loss": 1.0988,
      "step": 421
    },
    {
      "epoch": 0.89,
      "grad_norm": 1.1800742149353027,
      "learning_rate": 0.00017745240891651735,
      "loss": 0.7385,
      "step": 422
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.5820197463035583,
      "learning_rate": 0.0001773471592733964,
      "loss": 0.9363,
      "step": 423
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.6128491759300232,
      "learning_rate": 0.00017724169592245995,
      "loss": 0.7762,
      "step": 424
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.5693449378013611,
      "learning_rate": 0.0001771360191551,
      "loss": 0.7526,
      "step": 425
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.7725418210029602,
      "learning_rate": 0.00017703012926329815,
      "loss": 0.7019,
      "step": 426
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.5068923234939575,
      "learning_rate": 0.0001769240265396249,
      "loss": 0.8308,
      "step": 427
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.34859699010849,
      "learning_rate": 0.0001768177112772388,
      "loss": 0.9593,
      "step": 428
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.34673023223876953,
      "learning_rate": 0.00017671118376988573,
      "loss": 1.0334,
      "step": 429
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.5354735851287842,
      "learning_rate": 0.0001766044443118978,
      "loss": 1.2355,
      "step": 430
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.2567592859268188,
      "learning_rate": 0.0001764974931981929,
      "loss": 0.8935,
      "step": 431
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.4151657521724701,
      "learning_rate": 0.00017639033072427366,
      "loss": 1.1042,
      "step": 432
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.4307219386100769,
      "learning_rate": 0.00017628295718622665,
      "loss": 1.2273,
      "step": 433
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.6330164074897766,
      "learning_rate": 0.0001761753728807217,
      "loss": 1.2027,
      "step": 434
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.47434625029563904,
      "learning_rate": 0.00017606757810501088,
      "loss": 0.9242,
      "step": 435
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.0463887453079224,
      "learning_rate": 0.00017595957315692782,
      "loss": 1.151,
      "step": 436
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.7210713028907776,
      "learning_rate": 0.00017585135833488692,
      "loss": 0.8223,
      "step": 437
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.5121049284934998,
      "learning_rate": 0.00017574293393788235,
      "loss": 0.6994,
      "step": 438
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.8933761119842529,
      "learning_rate": 0.00017563430026548734,
      "loss": 0.846,
      "step": 439
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.5270050764083862,
      "learning_rate": 0.0001755254576178535,
      "loss": 0.7119,
      "step": 440
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.37028369307518005,
      "learning_rate": 0.0001754164062957096,
      "loss": 0.8623,
      "step": 441
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.6245588660240173,
      "learning_rate": 0.00017530714660036112,
      "loss": 1.0409,
      "step": 442
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.878105640411377,
      "learning_rate": 0.0001751976788336892,
      "loss": 0.6867,
      "step": 443
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.3765283226966858,
      "learning_rate": 0.00017508800329814995,
      "loss": 1.2251,
      "step": 444
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.4110933840274811,
      "learning_rate": 0.00017497812029677344,
      "loss": 0.8676,
      "step": 445
    },
    {
      "epoch": 0.94,
      "grad_norm": 1.3986817598342896,
      "learning_rate": 0.000174868030133163,
      "loss": 1.6298,
      "step": 446
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.4310443103313446,
      "learning_rate": 0.0001747577331114945,
      "loss": 0.7328,
      "step": 447
    },
    {
      "epoch": 0.94,
      "grad_norm": 1.5922423601150513,
      "learning_rate": 0.00017464722953651504,
      "loss": 0.6629,
      "step": 448
    },
    {
      "epoch": 0.95,
      "grad_norm": 2.27004075050354,
      "learning_rate": 0.00017453651971354264,
      "loss": 1.4748,
      "step": 449
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.31181880831718445,
      "learning_rate": 0.00017442560394846516,
      "loss": 1.0477,
      "step": 450
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.1180263757705688,
      "learning_rate": 0.00017431448254773944,
      "loss": 0.9225,
      "step": 451
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.7490403056144714,
      "learning_rate": 0.00017420315581839044,
      "loss": 0.7847,
      "step": 452
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.138551115989685,
      "learning_rate": 0.0001740916240680105,
      "loss": 1.2782,
      "step": 453
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.9375423789024353,
      "learning_rate": 0.0001739798876047584,
      "loss": 0.8316,
      "step": 454
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.0941681861877441,
      "learning_rate": 0.0001738679467373586,
      "loss": 0.9702,
      "step": 455
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.2845444083213806,
      "learning_rate": 0.00017375580177510016,
      "loss": 0.8563,
      "step": 456
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.7341310381889343,
      "learning_rate": 0.0001736434530278362,
      "loss": 0.7102,
      "step": 457
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.886854350566864,
      "learning_rate": 0.0001735309008059829,
      "loss": 1.4872,
      "step": 458
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.44623202085494995,
      "learning_rate": 0.00017341814542051845,
      "loss": 0.8142,
      "step": 459
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.8813387155532837,
      "learning_rate": 0.00017330518718298264,
      "loss": 1.0869,
      "step": 460
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.8468006253242493,
      "learning_rate": 0.0001731920264054755,
      "loss": 1.2859,
      "step": 461
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.6797575354576111,
      "learning_rate": 0.00017307866340065685,
      "loss": 1.0288,
      "step": 462
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.25991517305374146,
      "learning_rate": 0.00017296509848174508,
      "loss": 0.7996,
      "step": 463
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.557244598865509,
      "learning_rate": 0.00017285133196251663,
      "loss": 0.6877,
      "step": 464
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.49986258149147034,
      "learning_rate": 0.00017273736415730488,
      "loss": 0.8285,
      "step": 465
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.5839115977287292,
      "learning_rate": 0.0001726231953809993,
      "loss": 0.8617,
      "step": 466
    },
    {
      "epoch": 0.98,
      "grad_norm": 1.1967806816101074,
      "learning_rate": 0.0001725088259490448,
      "loss": 0.719,
      "step": 467
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.7830839157104492,
      "learning_rate": 0.00017239425617744048,
      "loss": 0.623,
      "step": 468
    },
    {
      "epoch": 0.99,
      "grad_norm": 2.0930089950561523,
      "learning_rate": 0.00017227948638273916,
      "loss": 1.1768,
      "step": 469
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.562641441822052,
      "learning_rate": 0.0001721645168820462,
      "loss": 0.5235,
      "step": 470
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.5656068325042725,
      "learning_rate": 0.00017204934799301883,
      "loss": 0.9211,
      "step": 471
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.934866726398468,
      "learning_rate": 0.0001719339800338651,
      "loss": 0.7897,
      "step": 472
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.30100950598716736,
      "learning_rate": 0.00017181841332334318,
      "loss": 1.0436,
      "step": 473
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5494408011436462,
      "learning_rate": 0.00017170264818076026,
      "loss": 0.6412,
      "step": 474
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6607212424278259,
      "learning_rate": 0.00017158668492597186,
      "loss": 1.3501,
      "step": 475
    }
  ],
  "logging_steps": 1,
  "max_steps": 1900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 475,
  "total_flos": 3.489377344094208e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}