{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.759571209800919,
  "eval_steps": 100,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015313935681470138,
      "grad_norm": 3.8326407564846536,
      "learning_rate": 6.134969325153375e-07,
      "loss": 1.3339,
      "step": 5
    },
    {
      "epoch": 0.030627871362940276,
      "grad_norm": 3.5496788557416803,
      "learning_rate": 1.226993865030675e-06,
      "loss": 1.3517,
      "step": 10
    },
    {
      "epoch": 0.045941807044410414,
      "grad_norm": 2.292172802820395,
      "learning_rate": 1.8404907975460124e-06,
      "loss": 1.3142,
      "step": 15
    },
    {
      "epoch": 0.06125574272588055,
      "grad_norm": 1.7775340318261912,
      "learning_rate": 2.45398773006135e-06,
      "loss": 1.2477,
      "step": 20
    },
    {
      "epoch": 0.07656967840735068,
      "grad_norm": 1.4368794370978828,
      "learning_rate": 3.0674846625766875e-06,
      "loss": 1.2037,
      "step": 25
    },
    {
      "epoch": 0.09188361408882083,
      "grad_norm": 1.061354555879628,
      "learning_rate": 3.680981595092025e-06,
      "loss": 1.1505,
      "step": 30
    },
    {
      "epoch": 0.10719754977029096,
      "grad_norm": 0.8377616484610274,
      "learning_rate": 4.294478527607362e-06,
      "loss": 1.1179,
      "step": 35
    },
    {
      "epoch": 0.1225114854517611,
      "grad_norm": 0.7884987790196414,
      "learning_rate": 4.9079754601227e-06,
      "loss": 1.0735,
      "step": 40
    },
    {
      "epoch": 0.13782542113323124,
      "grad_norm": 0.7279957151761491,
      "learning_rate": 5.521472392638038e-06,
      "loss": 1.0556,
      "step": 45
    },
    {
      "epoch": 0.15313935681470137,
      "grad_norm": 0.6692858930956382,
      "learning_rate": 6.134969325153375e-06,
      "loss": 1.0294,
      "step": 50
    },
    {
      "epoch": 0.16845329249617153,
      "grad_norm": 0.6401840707040195,
      "learning_rate": 6.748466257668712e-06,
      "loss": 1.0175,
      "step": 55
    },
    {
      "epoch": 0.18376722817764166,
      "grad_norm": 0.6584204446837412,
      "learning_rate": 7.36196319018405e-06,
      "loss": 1.0283,
      "step": 60
    },
    {
      "epoch": 0.1990811638591118,
      "grad_norm": 0.6647811794468166,
      "learning_rate": 7.975460122699386e-06,
      "loss": 0.9799,
      "step": 65
    },
    {
      "epoch": 0.21439509954058192,
      "grad_norm": 0.6774675226534475,
      "learning_rate": 8.588957055214725e-06,
      "loss": 0.969,
      "step": 70
    },
    {
      "epoch": 0.22970903522205208,
      "grad_norm": 0.6918496726012217,
      "learning_rate": 9.202453987730062e-06,
      "loss": 0.9787,
      "step": 75
    },
    {
      "epoch": 0.2450229709035222,
      "grad_norm": 0.6740082248654927,
      "learning_rate": 9.8159509202454e-06,
      "loss": 0.9596,
      "step": 80
    },
    {
      "epoch": 0.26033690658499237,
      "grad_norm": 0.6791518891702232,
      "learning_rate": 1.0429447852760737e-05,
      "loss": 0.9813,
      "step": 85
    },
    {
      "epoch": 0.27565084226646247,
      "grad_norm": 0.7029695620068616,
      "learning_rate": 1.1042944785276076e-05,
      "loss": 0.9703,
      "step": 90
    },
    {
      "epoch": 0.29096477794793263,
      "grad_norm": 0.6355433423695775,
      "learning_rate": 1.1656441717791411e-05,
      "loss": 0.9375,
      "step": 95
    },
    {
      "epoch": 0.30627871362940273,
      "grad_norm": 0.6551855479751819,
      "learning_rate": 1.226993865030675e-05,
      "loss": 0.952,
      "step": 100
    },
    {
      "epoch": 0.30627871362940273,
      "eval_loss": 0.964697003364563,
      "eval_runtime": 3.4019,
      "eval_samples_per_second": 36.45,
      "eval_steps_per_second": 2.352,
      "step": 100
    },
    {
      "epoch": 0.3215926493108729,
      "grad_norm": 0.6655305965463972,
      "learning_rate": 1.2883435582822085e-05,
      "loss": 0.9237,
      "step": 105
    },
    {
      "epoch": 0.33690658499234305,
      "grad_norm": 0.7257201177401903,
      "learning_rate": 1.3496932515337424e-05,
      "loss": 0.9511,
      "step": 110
    },
    {
      "epoch": 0.35222052067381315,
      "grad_norm": 0.7424667090609683,
      "learning_rate": 1.4110429447852763e-05,
      "loss": 0.9323,
      "step": 115
    },
    {
      "epoch": 0.3675344563552833,
      "grad_norm": 0.7336582339806711,
      "learning_rate": 1.47239263803681e-05,
      "loss": 0.9449,
      "step": 120
    },
    {
      "epoch": 0.38284839203675347,
      "grad_norm": 0.6851538651091853,
      "learning_rate": 1.5337423312883436e-05,
      "loss": 0.9133,
      "step": 125
    },
    {
      "epoch": 0.3981623277182236,
      "grad_norm": 0.7424313941044212,
      "learning_rate": 1.5950920245398772e-05,
      "loss": 0.9173,
      "step": 130
    },
    {
      "epoch": 0.41347626339969373,
      "grad_norm": 0.7937170928985942,
      "learning_rate": 1.656441717791411e-05,
      "loss": 0.9348,
      "step": 135
    },
    {
      "epoch": 0.42879019908116384,
      "grad_norm": 0.7668730085289572,
      "learning_rate": 1.717791411042945e-05,
      "loss": 0.9091,
      "step": 140
    },
    {
      "epoch": 0.444104134762634,
      "grad_norm": 0.713212902268727,
      "learning_rate": 1.7791411042944788e-05,
      "loss": 0.9054,
      "step": 145
    },
    {
      "epoch": 0.45941807044410415,
      "grad_norm": 0.8266274957992115,
      "learning_rate": 1.8404907975460123e-05,
      "loss": 0.9165,
      "step": 150
    },
    {
      "epoch": 0.47473200612557426,
      "grad_norm": 0.7773849012810377,
      "learning_rate": 1.9018404907975462e-05,
      "loss": 0.9261,
      "step": 155
    },
    {
      "epoch": 0.4900459418070444,
      "grad_norm": 0.7698543962501324,
      "learning_rate": 1.96319018404908e-05,
      "loss": 0.8848,
      "step": 160
    },
    {
      "epoch": 0.5053598774885145,
      "grad_norm": 0.7326492641075325,
      "learning_rate": 1.9999908278985548e-05,
      "loss": 0.9002,
      "step": 165
    },
    {
      "epoch": 0.5206738131699847,
      "grad_norm": 0.725915155149828,
      "learning_rate": 1.9998876436895888e-05,
      "loss": 0.9064,
      "step": 170
    },
    {
      "epoch": 0.5359877488514548,
      "grad_norm": 0.7137681931522117,
      "learning_rate": 1.99966982201439e-05,
      "loss": 0.9083,
      "step": 175
    },
    {
      "epoch": 0.5513016845329249,
      "grad_norm": 0.8244990854189328,
      "learning_rate": 1.9993373878462894e-05,
      "loss": 0.8988,
      "step": 180
    },
    {
      "epoch": 0.5666156202143952,
      "grad_norm": 0.7883005110592801,
      "learning_rate": 1.99889037929898e-05,
      "loss": 0.9021,
      "step": 185
    },
    {
      "epoch": 0.5819295558958653,
      "grad_norm": 0.7224060026030372,
      "learning_rate": 1.9983288476221482e-05,
      "loss": 0.8881,
      "step": 190
    },
    {
      "epoch": 0.5972434915773354,
      "grad_norm": 0.7010662098507998,
      "learning_rate": 1.9976528571955946e-05,
      "loss": 0.8889,
      "step": 195
    },
    {
      "epoch": 0.6125574272588055,
      "grad_norm": 0.7154815490781321,
      "learning_rate": 1.9968624855218578e-05,
      "loss": 0.8884,
      "step": 200
    },
    {
      "epoch": 0.6125574272588055,
      "eval_loss": 0.9119902849197388,
      "eval_runtime": 3.4604,
      "eval_samples_per_second": 35.834,
      "eval_steps_per_second": 2.312,
      "step": 200
    },
    {
      "epoch": 0.6278713629402757,
      "grad_norm": 0.6984184509316927,
      "learning_rate": 1.995957823217325e-05,
      "loss": 0.9033,
      "step": 205
    },
    {
      "epoch": 0.6431852986217458,
      "grad_norm": 0.7120998555383481,
      "learning_rate": 1.9949389740018438e-05,
      "loss": 0.8988,
      "step": 210
    },
    {
      "epoch": 0.6584992343032159,
      "grad_norm": 0.66696186884436,
      "learning_rate": 1.993806054686832e-05,
      "loss": 0.8735,
      "step": 215
    },
    {
      "epoch": 0.6738131699846861,
      "grad_norm": 0.7395425655626215,
      "learning_rate": 1.9925591951618822e-05,
      "loss": 0.9127,
      "step": 220
    },
    {
      "epoch": 0.6891271056661562,
      "grad_norm": 0.6960401538019414,
      "learning_rate": 1.9911985383798737e-05,
      "loss": 0.875,
      "step": 225
    },
    {
      "epoch": 0.7044410413476263,
      "grad_norm": 0.7195874036136765,
      "learning_rate": 1.9897242403405792e-05,
      "loss": 0.8782,
      "step": 230
    },
    {
      "epoch": 0.7197549770290965,
      "grad_norm": 0.7129931764921758,
      "learning_rate": 1.9881364700727827e-05,
      "loss": 0.8943,
      "step": 235
    },
    {
      "epoch": 0.7350689127105666,
      "grad_norm": 0.690645634714852,
      "learning_rate": 1.9864354096148966e-05,
      "loss": 0.8782,
      "step": 240
    },
    {
      "epoch": 0.7503828483920367,
      "grad_norm": 0.7055958514936376,
      "learning_rate": 1.9846212539940955e-05,
      "loss": 0.8867,
      "step": 245
    },
    {
      "epoch": 0.7656967840735069,
      "grad_norm": 0.7517885221069497,
      "learning_rate": 1.982694211203952e-05,
      "loss": 0.8843,
      "step": 250
    },
    {
      "epoch": 0.781010719754977,
      "grad_norm": 0.7270711746255435,
      "learning_rate": 1.9806545021805922e-05,
      "loss": 0.8757,
      "step": 255
    },
    {
      "epoch": 0.7963246554364471,
      "grad_norm": 0.707252502344583,
      "learning_rate": 1.9785023607773655e-05,
      "loss": 0.8842,
      "step": 260
    },
    {
      "epoch": 0.8116385911179173,
      "grad_norm": 0.8083132789219781,
      "learning_rate": 1.976238033738033e-05,
      "loss": 0.8578,
      "step": 265
    },
    {
      "epoch": 0.8269525267993875,
      "grad_norm": 0.7287731737231247,
      "learning_rate": 1.9738617806684767e-05,
      "loss": 0.911,
      "step": 270
    },
    {
      "epoch": 0.8422664624808576,
      "grad_norm": 0.7683997901360534,
      "learning_rate": 1.9713738740069384e-05,
      "loss": 0.8607,
      "step": 275
    },
    {
      "epoch": 0.8575803981623277,
      "grad_norm": 0.6883196631913017,
      "learning_rate": 1.9687745989927823e-05,
      "loss": 0.8781,
      "step": 280
    },
    {
      "epoch": 0.8728943338437979,
      "grad_norm": 0.7137416791751114,
      "learning_rate": 1.966064253633793e-05,
      "loss": 0.8675,
      "step": 285
    },
    {
      "epoch": 0.888208269525268,
      "grad_norm": 0.800711538711323,
      "learning_rate": 1.963243148672009e-05,
      "loss": 0.8696,
      "step": 290
    },
    {
      "epoch": 0.9035222052067381,
      "grad_norm": 0.7017619169785259,
      "learning_rate": 1.960311607548096e-05,
      "loss": 0.8724,
      "step": 295
    },
    {
      "epoch": 0.9188361408882083,
      "grad_norm": 0.7347091076360852,
      "learning_rate": 1.957269966364263e-05,
      "loss": 0.8753,
      "step": 300
    },
    {
      "epoch": 0.9188361408882083,
      "eval_loss": 0.8846515417098999,
      "eval_runtime": 3.4431,
      "eval_samples_per_second": 36.014,
      "eval_steps_per_second": 2.323,
      "step": 300
    },
    {
      "epoch": 0.9341500765696784,
      "grad_norm": 0.6840257399223311,
      "learning_rate": 1.9541185738457304e-05,
      "loss": 0.8661,
      "step": 305
    },
    {
      "epoch": 0.9494640122511485,
      "grad_norm": 0.6350789314835292,
      "learning_rate": 1.9508577913007475e-05,
      "loss": 0.866,
      "step": 310
    },
    {
      "epoch": 0.9647779479326187,
      "grad_norm": 0.742666392443459,
      "learning_rate": 1.9474879925791665e-05,
      "loss": 0.8712,
      "step": 315
    },
    {
      "epoch": 0.9800918836140888,
      "grad_norm": 0.7707700113231902,
      "learning_rate": 1.944009564029584e-05,
      "loss": 0.8656,
      "step": 320
    },
    {
      "epoch": 0.9954058192955589,
      "grad_norm": 0.7026681496550549,
      "learning_rate": 1.9404229044550432e-05,
      "loss": 0.8707,
      "step": 325
    },
    {
      "epoch": 1.0122511485451762,
      "grad_norm": 0.8698658929763603,
      "learning_rate": 1.9367284250673126e-05,
      "loss": 1.0103,
      "step": 330
    },
    {
      "epoch": 1.0275650842266462,
      "grad_norm": 0.7696705674515646,
      "learning_rate": 1.9329265494397386e-05,
      "loss": 0.8254,
      "step": 335
    },
    {
      "epoch": 1.0428790199081164,
      "grad_norm": 0.703085270940529,
      "learning_rate": 1.929017713458685e-05,
      "loss": 0.7994,
      "step": 340
    },
    {
      "epoch": 1.0581929555895866,
      "grad_norm": 0.7281489106195598,
      "learning_rate": 1.9250023652735573e-05,
      "loss": 0.7997,
      "step": 345
    },
    {
      "epoch": 1.0735068912710566,
      "grad_norm": 0.6721859356177987,
      "learning_rate": 1.920880965245422e-05,
      "loss": 0.8028,
      "step": 350
    },
    {
      "epoch": 1.0888208269525268,
      "grad_norm": 0.6999456629939552,
      "learning_rate": 1.9166539858942258e-05,
      "loss": 0.7923,
      "step": 355
    },
    {
      "epoch": 1.104134762633997,
      "grad_norm": 0.761057382772568,
      "learning_rate": 1.912321911844622e-05,
      "loss": 0.8023,
      "step": 360
    },
    {
      "epoch": 1.119448698315467,
      "grad_norm": 0.7613985157569584,
      "learning_rate": 1.907885239770408e-05,
      "loss": 0.8171,
      "step": 365
    },
    {
      "epoch": 1.1347626339969372,
      "grad_norm": 0.7130602486133167,
      "learning_rate": 1.9033444783375806e-05,
      "loss": 0.8136,
      "step": 370
    },
    {
      "epoch": 1.1500765696784074,
      "grad_norm": 0.7290477717213912,
      "learning_rate": 1.8987001481460177e-05,
      "loss": 0.7956,
      "step": 375
    },
    {
      "epoch": 1.1653905053598774,
      "grad_norm": 0.6942113670274667,
      "learning_rate": 1.8939527816697917e-05,
      "loss": 0.795,
      "step": 380
    },
    {
      "epoch": 1.1807044410413476,
      "grad_norm": 0.7278550945084655,
      "learning_rate": 1.8891029231961208e-05,
      "loss": 0.8038,
      "step": 385
    },
    {
      "epoch": 1.1960183767228179,
      "grad_norm": 0.7637922924754829,
      "learning_rate": 1.8841511287629667e-05,
      "loss": 0.7941,
      "step": 390
    },
    {
      "epoch": 1.2113323124042878,
      "grad_norm": 0.7227667767094055,
      "learning_rate": 1.8790979660952832e-05,
      "loss": 0.7899,
      "step": 395
    },
    {
      "epoch": 1.226646248085758,
      "grad_norm": 0.6856723635729023,
      "learning_rate": 1.8739440145399295e-05,
      "loss": 0.8037,
      "step": 400
    },
    {
      "epoch": 1.226646248085758,
      "eval_loss": 0.8724085092544556,
      "eval_runtime": 3.6883,
      "eval_samples_per_second": 33.619,
      "eval_steps_per_second": 2.169,
      "step": 400
    },
    {
      "epoch": 1.2419601837672283,
      "grad_norm": 0.6585093868236329,
      "learning_rate": 1.8686898649992437e-05,
      "loss": 0.7969,
      "step": 405
    },
    {
      "epoch": 1.2572741194486983,
      "grad_norm": 0.6787675213944868,
      "learning_rate": 1.8633361198632987e-05,
      "loss": 0.8077,
      "step": 410
    },
    {
      "epoch": 1.2725880551301685,
      "grad_norm": 0.6808724401749536,
      "learning_rate": 1.857883392940837e-05,
      "loss": 0.8077,
      "step": 415
    },
    {
      "epoch": 1.2879019908116387,
      "grad_norm": 0.6824672080638723,
      "learning_rate": 1.8523323093888983e-05,
      "loss": 0.8025,
      "step": 420
    },
    {
      "epoch": 1.3032159264931087,
      "grad_norm": 0.6611632916751219,
      "learning_rate": 1.8466835056411422e-05,
      "loss": 0.7875,
      "step": 425
    },
    {
      "epoch": 1.318529862174579,
      "grad_norm": 0.701746007873801,
      "learning_rate": 1.8409376293348836e-05,
      "loss": 0.794,
      "step": 430
    },
    {
      "epoch": 1.3338437978560491,
      "grad_norm": 0.6668057827943388,
      "learning_rate": 1.8350953392368408e-05,
      "loss": 0.797,
      "step": 435
    },
    {
      "epoch": 1.349157733537519,
      "grad_norm": 0.7077024335619939,
      "learning_rate": 1.8291573051676063e-05,
      "loss": 0.8257,
      "step": 440
    },
    {
      "epoch": 1.3644716692189893,
      "grad_norm": 0.7168213984013295,
      "learning_rate": 1.8231242079248512e-05,
      "loss": 0.7934,
      "step": 445
    },
    {
      "epoch": 1.3797856049004595,
      "grad_norm": 0.7308258264034365,
      "learning_rate": 1.816996739205274e-05,
      "loss": 0.8078,
      "step": 450
    },
    {
      "epoch": 1.3950995405819295,
      "grad_norm": 0.7935757091141241,
      "learning_rate": 1.810775601525296e-05,
      "loss": 0.8172,
      "step": 455
    },
    {
      "epoch": 1.4104134762633997,
      "grad_norm": 0.7960723044086886,
      "learning_rate": 1.8044615081405153e-05,
      "loss": 0.7973,
      "step": 460
    },
    {
      "epoch": 1.42572741194487,
      "grad_norm": 0.7013219126306894,
      "learning_rate": 1.7980551829639357e-05,
      "loss": 0.7928,
      "step": 465
    },
    {
      "epoch": 1.44104134762634,
      "grad_norm": 0.7030096980783208,
      "learning_rate": 1.7915573604829684e-05,
      "loss": 0.7891,
      "step": 470
    },
    {
      "epoch": 1.4563552833078102,
      "grad_norm": 0.7129952798275541,
      "learning_rate": 1.784968785675221e-05,
      "loss": 0.7964,
      "step": 475
    },
    {
      "epoch": 1.4716692189892804,
      "grad_norm": 0.7042351661303197,
      "learning_rate": 1.7782902139230876e-05,
      "loss": 0.7821,
      "step": 480
    },
    {
      "epoch": 1.4869831546707504,
      "grad_norm": 0.7412846210916867,
      "learning_rate": 1.7715224109271426e-05,
      "loss": 0.7983,
      "step": 485
    },
    {
      "epoch": 1.5022970903522204,
      "grad_norm": 0.7586380261564012,
      "learning_rate": 1.764666152618355e-05,
      "loss": 0.8167,
      "step": 490
    },
    {
      "epoch": 1.5176110260336908,
      "grad_norm": 0.784243612804958,
      "learning_rate": 1.7577222250691254e-05,
      "loss": 0.8086,
      "step": 495
    },
    {
      "epoch": 1.5329249617151608,
      "grad_norm": 0.6901397300587065,
      "learning_rate": 1.7506914244031627e-05,
      "loss": 0.7966,
      "step": 500
    },
    {
      "epoch": 1.5329249617151608,
      "eval_loss": 0.8608717918395996,
      "eval_runtime": 4.0604,
      "eval_samples_per_second": 30.539,
      "eval_steps_per_second": 1.97,
      "step": 500
    },
    {
      "epoch": 1.5482388973966308,
      "grad_norm": 0.6826627810241662,
      "learning_rate": 1.7435745567042096e-05,
      "loss": 0.7871,
      "step": 505
    },
    {
      "epoch": 1.5635528330781012,
      "grad_norm": 0.7329202799692207,
      "learning_rate": 1.7363724379236237e-05,
      "loss": 0.806,
      "step": 510
    },
    {
      "epoch": 1.5788667687595712,
      "grad_norm": 0.8605855369920612,
      "learning_rate": 1.7290858937868296e-05,
      "loss": 0.8134,
      "step": 515
    },
    {
      "epoch": 1.5941807044410412,
      "grad_norm": 0.6963610579257828,
      "learning_rate": 1.7217157596986474e-05,
      "loss": 0.8057,
      "step": 520
    },
    {
      "epoch": 1.6094946401225116,
      "grad_norm": 0.715201778907277,
      "learning_rate": 1.7142628806475144e-05,
      "loss": 0.806,
      "step": 525
    },
    {
      "epoch": 1.6248085758039816,
      "grad_norm": 0.7191782284781755,
      "learning_rate": 1.706728111108607e-05,
      "loss": 0.8027,
      "step": 530
    },
    {
      "epoch": 1.6401225114854516,
      "grad_norm": 0.6872215034145709,
      "learning_rate": 1.699112314945874e-05,
      "loss": 0.7953,
      "step": 535
    },
    {
      "epoch": 1.655436447166922,
      "grad_norm": 0.7008995671254957,
      "learning_rate": 1.691416365312996e-05,
      "loss": 0.8096,
      "step": 540
    },
    {
      "epoch": 1.670750382848392,
      "grad_norm": 0.6521306963395784,
      "learning_rate": 1.683641144553275e-05,
      "loss": 0.7921,
      "step": 545
    },
    {
      "epoch": 1.686064318529862,
      "grad_norm": 0.6632532080286483,
      "learning_rate": 1.675787544098477e-05,
      "loss": 0.8056,
      "step": 550
    },
    {
      "epoch": 1.7013782542113323,
      "grad_norm": 0.6547969582532698,
      "learning_rate": 1.667856464366626e-05,
      "loss": 0.7819,
      "step": 555
    },
    {
      "epoch": 1.7166921898928025,
      "grad_norm": 0.7046901763937415,
      "learning_rate": 1.6598488146587733e-05,
      "loss": 0.8061,
      "step": 560
    },
    {
      "epoch": 1.7320061255742725,
      "grad_norm": 0.6788820639858653,
      "learning_rate": 1.6517655130547435e-05,
      "loss": 0.7997,
      "step": 565
    },
    {
      "epoch": 1.7473200612557427,
      "grad_norm": 0.6894021837769623,
      "learning_rate": 1.6436074863078783e-05,
      "loss": 0.803,
      "step": 570
    },
    {
      "epoch": 1.762633996937213,
      "grad_norm": 0.7360294460315284,
      "learning_rate": 1.635375669738782e-05,
      "loss": 0.7975,
      "step": 575
    },
    {
      "epoch": 1.777947932618683,
      "grad_norm": 0.6850098881910617,
      "learning_rate": 1.627071007128089e-05,
      "loss": 0.7825,
      "step": 580
    },
    {
      "epoch": 1.793261868300153,
      "grad_norm": 0.7278655150611072,
      "learning_rate": 1.618694450608256e-05,
      "loss": 0.7955,
      "step": 585
    },
    {
      "epoch": 1.8085758039816233,
      "grad_norm": 0.7122173514963583,
      "learning_rate": 1.6102469605544036e-05,
      "loss": 0.808,
      "step": 590
    },
    {
      "epoch": 1.8238897396630933,
      "grad_norm": 0.6925118679066572,
      "learning_rate": 1.6017295054742045e-05,
      "loss": 0.7875,
      "step": 595
    },
    {
      "epoch": 1.8392036753445635,
      "grad_norm": 0.6857769438421079,
      "learning_rate": 1.5931430618968476e-05,
      "loss": 0.7884,
      "step": 600
    },
    {
      "epoch": 1.8392036753445635,
      "eval_loss": 0.8516013622283936,
      "eval_runtime": 4.2451,
      "eval_samples_per_second": 29.21,
      "eval_steps_per_second": 1.885,
      "step": 600
    },
    {
      "epoch": 1.8545176110260337,
      "grad_norm": 0.6326947636704211,
      "learning_rate": 1.5844886142610763e-05,
      "loss": 0.7819,
      "step": 605
    },
    {
      "epoch": 1.8698315467075037,
      "grad_norm": 0.666694114425699,
      "learning_rate": 1.575767154802323e-05,
      "loss": 0.7777,
      "step": 610
    },
    {
      "epoch": 1.885145482388974,
      "grad_norm": 0.6182711467351976,
      "learning_rate": 1.5669796834389496e-05,
      "loss": 0.7889,
      "step": 615
    },
    {
      "epoch": 1.9004594180704442,
      "grad_norm": 0.6402744830423595,
      "learning_rate": 1.5581272076576047e-05,
      "loss": 0.7839,
      "step": 620
    },
    {
      "epoch": 1.9157733537519142,
      "grad_norm": 0.6612456968952057,
      "learning_rate": 1.5492107423977167e-05,
      "loss": 0.7884,
      "step": 625
    },
    {
      "epoch": 1.9310872894333844,
      "grad_norm": 0.6757984187665057,
      "learning_rate": 1.5402313099351302e-05,
      "loss": 0.7784,
      "step": 630
    },
    {
      "epoch": 1.9464012251148546,
      "grad_norm": 0.6707442527908725,
      "learning_rate": 1.5311899397649e-05,
      "loss": 0.7935,
      "step": 635
    },
    {
      "epoch": 1.9617151607963246,
      "grad_norm": 0.787792189502549,
      "learning_rate": 1.522087668483264e-05,
      "loss": 0.779,
      "step": 640
    },
    {
      "epoch": 1.9770290964777948,
      "grad_norm": 0.6925473058613637,
      "learning_rate": 1.5129255396687899e-05,
      "loss": 0.7891,
      "step": 645
    },
    {
      "epoch": 1.992343032159265,
      "grad_norm": 0.6890667970589922,
      "learning_rate": 1.503704603762734e-05,
      "loss": 0.7693,
      "step": 650
    },
    {
      "epoch": 2.009188361408882,
      "grad_norm": 0.8106643045129424,
      "learning_rate": 1.4944259179486068e-05,
      "loss": 0.9039,
      "step": 655
    },
    {
      "epoch": 2.0245022970903523,
      "grad_norm": 0.7728005094053498,
      "learning_rate": 1.4850905460309648e-05,
      "loss": 0.7116,
      "step": 660
    },
    {
      "epoch": 2.0398162327718223,
      "grad_norm": 0.7301328106464207,
      "learning_rate": 1.4756995583134463e-05,
      "loss": 0.7313,
      "step": 665
    },
    {
      "epoch": 2.0551301684532923,
      "grad_norm": 0.702048383564715,
      "learning_rate": 1.4662540314760608e-05,
      "loss": 0.7222,
      "step": 670
    },
    {
      "epoch": 2.0704441041347628,
      "grad_norm": 0.7081084536553046,
      "learning_rate": 1.4567550484517456e-05,
      "loss": 0.7214,
      "step": 675
    },
    {
      "epoch": 2.0857580398162328,
      "grad_norm": 0.7492389283409402,
      "learning_rate": 1.4472036983022106e-05,
      "loss": 0.7251,
      "step": 680
    },
    {
      "epoch": 2.1010719754977027,
      "grad_norm": 0.7183839129962212,
      "learning_rate": 1.437601076093073e-05,
      "loss": 0.71,
      "step": 685
    },
    {
      "epoch": 2.116385911179173,
      "grad_norm": 0.6904647110507196,
      "learning_rate": 1.4279482827683095e-05,
      "loss": 0.724,
      "step": 690
    },
    {
      "epoch": 2.131699846860643,
      "grad_norm": 0.6745352346306862,
      "learning_rate": 1.4182464250240341e-05,
      "loss": 0.7127,
      "step": 695
    },
    {
      "epoch": 2.147013782542113,
      "grad_norm": 0.7254396412798532,
      "learning_rate": 1.4084966151816124e-05,
      "loss": 0.7071,
      "step": 700
    },
    {
      "epoch": 2.147013782542113,
      "eval_loss": 0.8550077676773071,
      "eval_runtime": 3.8848,
      "eval_samples_per_second": 31.919,
      "eval_steps_per_second": 2.059,
      "step": 700
    },
    {
      "epoch": 2.1623277182235836,
      "grad_norm": 0.73349139216254,
      "learning_rate": 1.3986999710601348e-05,
      "loss": 0.7298,
      "step": 705
    },
    {
      "epoch": 2.1776416539050536,
      "grad_norm": 0.6655753573647281,
      "learning_rate": 1.3888576158482586e-05,
      "loss": 0.7124,
      "step": 710
    },
    {
      "epoch": 2.1929555895865236,
      "grad_norm": 0.6987464871327375,
      "learning_rate": 1.3789706779754326e-05,
      "loss": 0.712,
      "step": 715
    },
    {
      "epoch": 2.208269525267994,
      "grad_norm": 0.7104463485359258,
      "learning_rate": 1.3690402909825245e-05,
      "loss": 0.7256,
      "step": 720
    },
    {
      "epoch": 2.223583460949464,
      "grad_norm": 0.786597658435966,
      "learning_rate": 1.3590675933918578e-05,
      "loss": 0.7265,
      "step": 725
    },
    {
      "epoch": 2.238897396630934,
      "grad_norm": 0.7359585689347169,
      "learning_rate": 1.3490537285766809e-05,
      "loss": 0.7167,
      "step": 730
    },
    {
      "epoch": 2.2542113323124044,
      "grad_norm": 0.6905264840508457,
      "learning_rate": 1.3389998446300791e-05,
      "loss": 0.7046,
      "step": 735
    },
    {
      "epoch": 2.2695252679938744,
      "grad_norm": 0.7110824744193723,
      "learning_rate": 1.3289070942333448e-05,
      "loss": 0.7113,
      "step": 740
    },
    {
      "epoch": 2.2848392036753444,
      "grad_norm": 0.774570053362907,
      "learning_rate": 1.3187766345238222e-05,
      "loss": 0.7097,
      "step": 745
    },
    {
      "epoch": 2.300153139356815,
      "grad_norm": 0.7178949231829396,
      "learning_rate": 1.308609626962242e-05,
      "loss": 0.6951,
      "step": 750
    },
    {
      "epoch": 2.315467075038285,
      "grad_norm": 0.6778307950742112,
      "learning_rate": 1.2984072371995581e-05,
      "loss": 0.7119,
      "step": 755
    },
    {
      "epoch": 2.330781010719755,
      "grad_norm": 0.7381317901698428,
      "learning_rate": 1.288170634943307e-05,
      "loss": 0.7179,
      "step": 760
    },
    {
      "epoch": 2.3460949464012253,
      "grad_norm": 0.688339196574423,
      "learning_rate": 1.2779009938234986e-05,
      "loss": 0.7372,
      "step": 765
    },
    {
      "epoch": 2.3614088820826953,
      "grad_norm": 0.7309911889901869,
      "learning_rate": 1.2675994912580601e-05,
      "loss": 0.7217,
      "step": 770
    },
    {
      "epoch": 2.3767228177641653,
      "grad_norm": 2.627453466768546,
      "learning_rate": 1.2572673083178448e-05,
      "loss": 0.7208,
      "step": 775
    },
    {
      "epoch": 2.3920367534456357,
      "grad_norm": 0.6825595176377366,
      "learning_rate": 1.2469056295912216e-05,
      "loss": 0.7173,
      "step": 780
    },
    {
      "epoch": 2.4073506891271057,
      "grad_norm": 0.681764187496552,
      "learning_rate": 1.2365156430482621e-05,
      "loss": 0.7172,
      "step": 785
    },
    {
      "epoch": 2.4226646248085757,
      "grad_norm": 0.6957949104606218,
      "learning_rate": 1.2260985399045379e-05,
      "loss": 0.7144,
      "step": 790
    },
    {
      "epoch": 2.437978560490046,
      "grad_norm": 0.6810069800053375,
      "learning_rate": 1.2156555144845489e-05,
      "loss": 0.7153,
      "step": 795
    },
    {
      "epoch": 2.453292496171516,
      "grad_norm": 0.6879227501131829,
      "learning_rate": 1.2051877640847929e-05,
      "loss": 0.7208,
      "step": 800
    },
    {
      "epoch": 2.453292496171516,
      "eval_loss": 0.8501381278038025,
      "eval_runtime": 3.7489,
      "eval_samples_per_second": 33.076,
      "eval_steps_per_second": 2.134,
      "step": 800
    },
    {
      "epoch": 2.468606431852986,
      "grad_norm": 0.7074177591745171,
      "learning_rate": 1.1946964888364949e-05,
      "loss": 0.7293,
      "step": 805
    },
    {
      "epoch": 2.4839203675344566,
      "grad_norm": 0.7100957198483567,
      "learning_rate": 1.1841828915680127e-05,
      "loss": 0.7088,
      "step": 810
    },
    {
      "epoch": 2.4992343032159265,
      "grad_norm": 0.7065376294005609,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.7083,
      "step": 815
    },
    {
      "epoch": 2.5145482388973965,
      "grad_norm": 0.699699294689246,
      "learning_rate": 1.1630935549418627e-05,
      "loss": 0.7239,
      "step": 820
    },
    {
      "epoch": 2.5298621745788665,
      "grad_norm": 0.6931742613638052,
      "learning_rate": 1.1525202334839771e-05,
      "loss": 0.7257,
      "step": 825
    },
    {
      "epoch": 2.545176110260337,
      "grad_norm": 0.6626821835687099,
      "learning_rate": 1.1419294255282574e-05,
      "loss": 0.7158,
      "step": 830
    },
    {
      "epoch": 2.560490045941807,
      "grad_norm": 0.7476424454423357,
      "learning_rate": 1.1313223453145202e-05,
      "loss": 0.7231,
      "step": 835
    },
    {
      "epoch": 2.5758039816232774,
      "grad_norm": 0.7121987313639168,
      "learning_rate": 1.1207002089482026e-05,
      "loss": 0.7272,
      "step": 840
    },
    {
      "epoch": 2.5911179173047474,
      "grad_norm": 0.6842806839970864,
      "learning_rate": 1.1100642342609352e-05,
      "loss": 0.7215,
      "step": 845
    },
    {
      "epoch": 2.6064318529862174,
      "grad_norm": 0.671282856198737,
      "learning_rate": 1.0994156406709155e-05,
      "loss": 0.7086,
      "step": 850
    },
    {
      "epoch": 2.6217457886676874,
      "grad_norm": 0.7127796423271462,
      "learning_rate": 1.088755649043104e-05,
      "loss": 0.7113,
      "step": 855
    },
    {
      "epoch": 2.637059724349158,
      "grad_norm": 0.6642491628332302,
      "learning_rate": 1.0780854815492496e-05,
      "loss": 0.7247,
      "step": 860
    },
    {
      "epoch": 2.652373660030628,
      "grad_norm": 0.6698942933482407,
      "learning_rate": 1.0674063615277681e-05,
      "loss": 0.7301,
      "step": 865
    },
    {
      "epoch": 2.6676875957120982,
      "grad_norm": 0.6690575090698347,
      "learning_rate": 1.0567195133434851e-05,
      "loss": 0.7318,
      "step": 870
    },
    {
      "epoch": 2.6830015313935682,
      "grad_norm": 0.6647266330654462,
      "learning_rate": 1.0460261622472631e-05,
      "loss": 0.7143,
      "step": 875
    },
    {
      "epoch": 2.698315467075038,
      "grad_norm": 0.6879144621587469,
      "learning_rate": 1.0353275342355262e-05,
      "loss": 0.7227,
      "step": 880
    },
    {
      "epoch": 2.713629402756508,
      "grad_norm": 0.6775051673571305,
      "learning_rate": 1.024624855909698e-05,
      "loss": 0.715,
      "step": 885
    },
    {
      "epoch": 2.7289433384379786,
      "grad_norm": 0.6785052740842338,
      "learning_rate": 1.013919354335572e-05,
      "loss": 0.7224,
      "step": 890
    },
    {
      "epoch": 2.7442572741194486,
      "grad_norm": 0.6852717568024729,
      "learning_rate": 1.0032122569026284e-05,
      "loss": 0.7181,
      "step": 895
    },
    {
      "epoch": 2.759571209800919,
      "grad_norm": 0.6966758449578118,
      "learning_rate": 9.925047911833137e-06,
      "loss": 0.726,
      "step": 900
    },
    {
      "epoch": 2.759571209800919,
      "eval_loss": 0.8449206352233887,
      "eval_runtime": 3.7457,
      "eval_samples_per_second": 33.104,
      "eval_steps_per_second": 2.136,
      "step": 900
    }
  ],
  "logging_steps": 5,
  "max_steps": 1630,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 95696971628544.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}