{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 598,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016722408026755853,
      "grad_norm": 108.1450424194336,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 23.7219,
      "step": 1
    },
    {
      "epoch": 0.008361204013377926,
      "grad_norm": 80.87652587890625,
      "learning_rate": 2.4999999999999998e-05,
      "loss": 22.4468,
      "step": 5
    },
    {
      "epoch": 0.016722408026755852,
      "grad_norm": 25.19646644592285,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 18.8421,
      "step": 10
    },
    {
      "epoch": 0.02508361204013378,
      "grad_norm": 7.7148966789245605,
      "learning_rate": 7.5e-05,
      "loss": 15.947,
      "step": 15
    },
    {
      "epoch": 0.033444816053511704,
      "grad_norm": 6.524266719818115,
      "learning_rate": 9.999999999999999e-05,
      "loss": 14.4621,
      "step": 20
    },
    {
      "epoch": 0.04180602006688963,
      "grad_norm": 3.7445762157440186,
      "learning_rate": 0.000125,
      "loss": 13.5317,
      "step": 25
    },
    {
      "epoch": 0.05016722408026756,
      "grad_norm": 2.5251731872558594,
      "learning_rate": 0.00015,
      "loss": 13.0802,
      "step": 30
    },
    {
      "epoch": 0.05852842809364549,
      "grad_norm": 3.446436882019043,
      "learning_rate": 0.000175,
      "loss": 12.5052,
      "step": 35
    },
    {
      "epoch": 0.06688963210702341,
      "grad_norm": 5.8851447105407715,
      "learning_rate": 0.00019999999999999998,
      "loss": 11.5731,
      "step": 40
    },
    {
      "epoch": 0.07525083612040134,
      "grad_norm": 11.619170188903809,
      "learning_rate": 0.000225,
      "loss": 9.873,
      "step": 45
    },
    {
      "epoch": 0.08361204013377926,
      "grad_norm": 20.056072235107422,
      "learning_rate": 0.00025,
      "loss": 7.4632,
      "step": 50
    },
    {
      "epoch": 0.09197324414715718,
      "grad_norm": 9.337392807006836,
      "learning_rate": 0.00027499999999999996,
      "loss": 3.5644,
      "step": 55
    },
    {
      "epoch": 0.10033444816053512,
      "grad_norm": 5.715840816497803,
      "learning_rate": 0.0003,
      "loss": 2.2307,
      "step": 60
    },
    {
      "epoch": 0.10869565217391304,
      "grad_norm": 3.3433170318603516,
      "learning_rate": 0.0002999360698660697,
      "loss": 1.735,
      "step": 65
    },
    {
      "epoch": 0.11705685618729098,
      "grad_norm": 1.1295098066329956,
      "learning_rate": 0.0002997443339584391,
      "loss": 1.4312,
      "step": 70
    },
    {
      "epoch": 0.1254180602006689,
      "grad_norm": 1.1192564964294434,
      "learning_rate": 0.0002994249557131383,
      "loss": 1.26,
      "step": 75
    },
    {
      "epoch": 0.13377926421404682,
      "grad_norm": 0.5016701817512512,
      "learning_rate": 0.00029897820736875393,
      "loss": 1.18,
      "step": 80
    },
    {
      "epoch": 0.14214046822742474,
      "grad_norm": 1.4025403261184692,
      "learning_rate": 0.0002984044697343724,
      "loss": 1.1377,
      "step": 85
    },
    {
      "epoch": 0.1505016722408027,
      "grad_norm": 0.6089034080505371,
      "learning_rate": 0.00029770423186497794,
      "loss": 1.0823,
      "step": 90
    },
    {
      "epoch": 0.1588628762541806,
      "grad_norm": 0.8872767090797424,
      "learning_rate": 0.0002968780906445808,
      "loss": 1.0462,
      "step": 95
    },
    {
      "epoch": 0.16722408026755853,
      "grad_norm": 1.0498641729354858,
      "learning_rate": 0.00029592675027743253,
      "loss": 1.0203,
      "step": 100
    },
    {
      "epoch": 0.17558528428093645,
      "grad_norm": 1.5126526355743408,
      "learning_rate": 0.00029485102168776096,
      "loss": 1.0039,
      "step": 105
    },
    {
      "epoch": 0.18394648829431437,
      "grad_norm": 1.2154971361160278,
      "learning_rate": 0.0002936518218285368,
      "loss": 0.9897,
      "step": 110
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 0.8289320468902588,
      "learning_rate": 0.0002923301728998616,
      "loss": 0.9631,
      "step": 115
    },
    {
      "epoch": 0.20066889632107024,
      "grad_norm": 1.4787485599517822,
      "learning_rate": 0.0002908872014776423,
      "loss": 0.9517,
      "step": 120
    },
    {
      "epoch": 0.20903010033444816,
      "grad_norm": 1.2933125495910645,
      "learning_rate": 0.0002893241375532959,
      "loss": 0.9611,
      "step": 125
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 1.0930614471435547,
      "learning_rate": 0.00028764231348530267,
      "loss": 0.9246,
      "step": 130
    },
    {
      "epoch": 0.225752508361204,
      "grad_norm": 1.1177003383636475,
      "learning_rate": 0.00028584316286350164,
      "loss": 0.9513,
      "step": 135
    },
    {
      "epoch": 0.23411371237458195,
      "grad_norm": 1.164829969406128,
      "learning_rate": 0.0002839282192870955,
      "loss": 0.9224,
      "step": 140
    },
    {
      "epoch": 0.24247491638795987,
      "grad_norm": 0.5613699555397034,
      "learning_rate": 0.00028189911505740843,
      "loss": 0.9142,
      "step": 145
    },
    {
      "epoch": 0.2508361204013378,
      "grad_norm": 0.8771304488182068,
      "learning_rate": 0.0002797575797865093,
      "loss": 0.9032,
      "step": 150
    },
    {
      "epoch": 0.2591973244147157,
      "grad_norm": 1.156224250793457,
      "learning_rate": 0.0002775054389228871,
      "loss": 0.8969,
      "step": 155
    },
    {
      "epoch": 0.26755852842809363,
      "grad_norm": 1.482100486755371,
      "learning_rate": 0.0002751446121954359,
      "loss": 0.8972,
      "step": 160
    },
    {
      "epoch": 0.27591973244147155,
      "grad_norm": 1.0462350845336914,
      "learning_rate": 0.00027267711197707386,
      "loss": 0.8902,
      "step": 165
    },
    {
      "epoch": 0.2842809364548495,
      "grad_norm": 0.8120772838592529,
      "learning_rate": 0.0002701050415693934,
      "loss": 0.8766,
      "step": 170
    },
    {
      "epoch": 0.29264214046822745,
      "grad_norm": 0.8219690322875977,
      "learning_rate": 0.0002674305934098032,
      "loss": 0.8838,
      "step": 175
    },
    {
      "epoch": 0.3010033444816054,
      "grad_norm": 0.643622875213623,
      "learning_rate": 0.00026465604720269026,
      "loss": 0.882,
      "step": 180
    },
    {
      "epoch": 0.3093645484949833,
      "grad_norm": 1.0544142723083496,
      "learning_rate": 0.0002617837679761962,
      "loss": 0.8643,
      "step": 185
    },
    {
      "epoch": 0.3177257525083612,
      "grad_norm": 0.718562126159668,
      "learning_rate": 0.0002588162040662628,
      "loss": 0.8456,
      "step": 190
    },
    {
      "epoch": 0.32608695652173914,
      "grad_norm": 1.0501580238342285,
      "learning_rate": 0.0002557558850296661,
      "loss": 0.866,
      "step": 195
    },
    {
      "epoch": 0.33444816053511706,
      "grad_norm": 1.50191330909729,
      "learning_rate": 0.00025260541948781784,
      "loss": 0.8682,
      "step": 200
    },
    {
      "epoch": 0.342809364548495,
      "grad_norm": 2.241793394088745,
      "learning_rate": 0.00024936749290317196,
      "loss": 0.858,
      "step": 205
    },
    {
      "epoch": 0.3511705685618729,
      "grad_norm": 0.8153356313705444,
      "learning_rate": 0.00024604486529013106,
      "loss": 0.8508,
      "step": 210
    },
    {
      "epoch": 0.3595317725752508,
      "grad_norm": 1.1809695959091187,
      "learning_rate": 0.00024264036886240603,
      "loss": 0.845,
      "step": 215
    },
    {
      "epoch": 0.36789297658862874,
      "grad_norm": 0.45723193883895874,
      "learning_rate": 0.00023915690561883125,
      "loss": 0.8446,
      "step": 220
    },
    {
      "epoch": 0.3762541806020067,
      "grad_norm": 1.4294965267181396,
      "learning_rate": 0.00023559744486969622,
      "loss": 0.8342,
      "step": 225
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.41016700863838196,
      "learning_rate": 0.00023196502070569963,
      "loss": 0.8355,
      "step": 230
    },
    {
      "epoch": 0.39297658862876256,
      "grad_norm": 0.39777177572250366,
      "learning_rate": 0.00022826272941168556,
      "loss": 0.8328,
      "step": 235
    },
    {
      "epoch": 0.4013377926421405,
      "grad_norm": 0.9254685044288635,
      "learning_rate": 0.00022449372682736428,
      "loss": 0.8285,
      "step": 240
    },
    {
      "epoch": 0.4096989966555184,
      "grad_norm": 0.9923207759857178,
      "learning_rate": 0.00022066122565726914,
      "loss": 0.8205,
      "step": 245
    },
    {
      "epoch": 0.4180602006688963,
      "grad_norm": 1.5853259563446045,
      "learning_rate": 0.00021676849273224132,
      "loss": 0.8431,
      "step": 250
    },
    {
      "epoch": 0.42642140468227424,
      "grad_norm": 0.5669292211532593,
      "learning_rate": 0.00021281884622477757,
      "loss": 0.828,
      "step": 255
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.7299262285232544,
      "learning_rate": 0.00020881565282061386,
      "loss": 0.82,
      "step": 260
    },
    {
      "epoch": 0.4431438127090301,
      "grad_norm": 2.6832640171051025,
      "learning_rate": 0.00020476232484895653,
      "loss": 0.8197,
      "step": 265
    },
    {
      "epoch": 0.451505016722408,
      "grad_norm": 1.040622591972351,
      "learning_rate": 0.00020066231737380684,
      "loss": 0.8163,
      "step": 270
    },
    {
      "epoch": 0.459866220735786,
      "grad_norm": 0.9296326637268066,
      "learning_rate": 0.00019651912524885814,
      "loss": 0.8207,
      "step": 275
    },
    {
      "epoch": 0.4682274247491639,
      "grad_norm": 1.341401219367981,
      "learning_rate": 0.00019233628013847636,
      "loss": 0.7954,
      "step": 280
    },
    {
      "epoch": 0.4765886287625418,
      "grad_norm": 1.4546632766723633,
      "learning_rate": 0.00018811734750730306,
      "loss": 0.8087,
      "step": 285
    },
    {
      "epoch": 0.48494983277591974,
      "grad_norm": 2.639110803604126,
      "learning_rate": 0.000183865923581047,
      "loss": 0.82,
      "step": 290
    },
    {
      "epoch": 0.49331103678929766,
      "grad_norm": 1.9307732582092285,
      "learning_rate": 0.00017958563228105473,
      "loss": 0.8261,
      "step": 295
    },
    {
      "epoch": 0.5016722408026756,
      "grad_norm": 0.8820024132728577,
      "learning_rate": 0.000175280122135274,
      "loss": 0.8188,
      "step": 300
    },
    {
      "epoch": 0.5100334448160535,
      "grad_norm": 1.1421868801116943,
      "learning_rate": 0.00017095306316824145,
      "loss": 0.808,
      "step": 305
    },
    {
      "epoch": 0.5183946488294314,
      "grad_norm": 1.443213701248169,
      "learning_rate": 0.00016660814377274764,
      "loss": 0.8246,
      "step": 310
    },
    {
      "epoch": 0.5267558528428093,
      "grad_norm": 1.0917268991470337,
      "learning_rate": 0.00016224906756584414,
      "loss": 0.8132,
      "step": 315
    },
    {
      "epoch": 0.5351170568561873,
      "grad_norm": 1.4697446823120117,
      "learning_rate": 0.00015787955023187394,
      "loss": 0.7961,
      "step": 320
    },
    {
      "epoch": 0.5434782608695652,
      "grad_norm": 0.5695840716362,
      "learning_rate": 0.00015350331635521528,
      "loss": 0.8022,
      "step": 325
    },
    {
      "epoch": 0.5518394648829431,
      "grad_norm": 0.5283718705177307,
      "learning_rate": 0.00014912409624543942,
      "loss": 0.8126,
      "step": 330
    },
    {
      "epoch": 0.560200668896321,
      "grad_norm": 0.604545533657074,
      "learning_rate": 0.000144745622757588,
      "loss": 0.8025,
      "step": 335
    },
    {
      "epoch": 0.568561872909699,
      "grad_norm": 0.5798037648200989,
      "learning_rate": 0.00014037162811028105,
      "loss": 0.7849,
      "step": 340
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 0.8034297227859497,
      "learning_rate": 0.00013600584070436663,
      "loss": 0.7902,
      "step": 345
    },
    {
      "epoch": 0.5852842809364549,
      "grad_norm": 0.454662948846817,
      "learning_rate": 0.0001316519819448257,
      "loss": 0.79,
      "step": 350
    },
    {
      "epoch": 0.5936454849498328,
      "grad_norm": 0.8804046511650085,
      "learning_rate": 0.0001273137630686397,
      "loss": 0.7963,
      "step": 355
    },
    {
      "epoch": 0.6020066889632107,
      "grad_norm": 0.7838584780693054,
      "learning_rate": 0.0001229948819813257,
      "loss": 0.7967,
      "step": 360
    },
    {
      "epoch": 0.6103678929765887,
      "grad_norm": 1.194453477859497,
      "learning_rate": 0.00011869902010483487,
      "loss": 0.7879,
      "step": 365
    },
    {
      "epoch": 0.6187290969899666,
      "grad_norm": 0.972303032875061,
      "learning_rate": 0.00011442983923950197,
      "loss": 0.8019,
      "step": 370
    },
    {
      "epoch": 0.6270903010033445,
      "grad_norm": 0.7446233034133911,
      "learning_rate": 0.00011019097844272025,
      "loss": 0.7786,
      "step": 375
    },
    {
      "epoch": 0.6354515050167224,
      "grad_norm": 0.754374086856842,
      "learning_rate": 0.00010598605092700247,
      "loss": 0.792,
      "step": 380
    },
    {
      "epoch": 0.6438127090301003,
      "grad_norm": 1.5724862813949585,
      "learning_rate": 0.00010181864098007187,
      "loss": 0.7877,
      "step": 385
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.7619232535362244,
      "learning_rate": 9.76923009096091e-05,
      "loss": 0.7795,
      "step": 390
    },
    {
      "epoch": 0.6605351170568562,
      "grad_norm": 0.7642078995704651,
      "learning_rate": 9.361054801525882e-05,
      "loss": 0.7811,
      "step": 395
    },
    {
      "epoch": 0.6688963210702341,
      "grad_norm": 0.6380756497383118,
      "learning_rate": 8.9576861590477e-05,
      "loss": 0.7793,
      "step": 400
    },
    {
      "epoch": 0.677257525083612,
      "grad_norm": 1.0837666988372803,
      "learning_rate": 8.559467995677535e-05,
      "loss": 0.7833,
      "step": 405
    },
    {
      "epoch": 0.68561872909699,
      "grad_norm": 0.4329131245613098,
      "learning_rate": 8.166739753288954e-05,
      "loss": 0.7889,
      "step": 410
    },
    {
      "epoch": 0.6939799331103679,
      "grad_norm": 0.6933662295341492,
      "learning_rate": 7.77983619413708e-05,
      "loss": 0.7903,
      "step": 415
    },
    {
      "epoch": 0.7023411371237458,
      "grad_norm": 0.7759296298027039,
      "learning_rate": 7.399087115506633e-05,
      "loss": 0.7835,
      "step": 420
    },
    {
      "epoch": 0.7107023411371237,
      "grad_norm": 0.7649604082107544,
      "learning_rate": 7.024817068592166e-05,
      "loss": 0.7865,
      "step": 425
    },
    {
      "epoch": 0.7190635451505016,
      "grad_norm": 0.4624633193016052,
      "learning_rate": 6.657345081850015e-05,
      "loss": 0.788,
      "step": 430
    },
    {
      "epoch": 0.7274247491638796,
      "grad_norm": 1.3198479413986206,
      "learning_rate": 6.296984389057886e-05,
      "loss": 0.7813,
      "step": 435
    },
    {
      "epoch": 0.7357859531772575,
      "grad_norm": 0.5763963460922241,
      "learning_rate": 5.944042162313818e-05,
      "loss": 0.7887,
      "step": 440
    },
    {
      "epoch": 0.7441471571906354,
      "grad_norm": 0.595403254032135,
      "learning_rate": 5.59881925020216e-05,
      "loss": 0.7767,
      "step": 445
    },
    {
      "epoch": 0.7525083612040134,
      "grad_norm": 0.9068358540534973,
      "learning_rate": 5.2616099213496704e-05,
      "loss": 0.7774,
      "step": 450
    },
    {
      "epoch": 0.7608695652173914,
      "grad_norm": 0.6962704658508301,
      "learning_rate": 4.93270161359043e-05,
      "loss": 0.7844,
      "step": 455
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.6204519271850586,
      "learning_rate": 4.612374688953315e-05,
      "loss": 0.7835,
      "step": 460
    },
    {
      "epoch": 0.7775919732441472,
      "grad_norm": 0.4705691635608673,
      "learning_rate": 4.300902194680902e-05,
      "loss": 0.7796,
      "step": 465
    },
    {
      "epoch": 0.7859531772575251,
      "grad_norm": 0.7778177857398987,
      "learning_rate": 3.998549630483525e-05,
      "loss": 0.7864,
      "step": 470
    },
    {
      "epoch": 0.794314381270903,
      "grad_norm": 0.7931321859359741,
      "learning_rate": 3.7055747222268256e-05,
      "loss": 0.7733,
      "step": 475
    },
    {
      "epoch": 0.802675585284281,
      "grad_norm": 0.5870620012283325,
      "learning_rate": 3.422227202245778e-05,
      "loss": 0.7615,
      "step": 480
    },
    {
      "epoch": 0.8110367892976589,
      "grad_norm": 0.9947313666343689,
      "learning_rate": 3.1487485964723966e-05,
      "loss": 0.7693,
      "step": 485
    },
    {
      "epoch": 0.8193979933110368,
      "grad_norm": 0.5786251425743103,
      "learning_rate": 2.885372018558604e-05,
      "loss": 0.7859,
      "step": 490
    },
    {
      "epoch": 0.8277591973244147,
      "grad_norm": 0.5991637110710144,
      "learning_rate": 2.6323219711697368e-05,
      "loss": 0.7781,
      "step": 495
    },
    {
      "epoch": 0.8361204013377926,
      "grad_norm": 0.7340580821037292,
      "learning_rate": 2.3898141546180678e-05,
      "loss": 0.7689,
      "step": 500
    },
    {
      "epoch": 0.8444816053511706,
      "grad_norm": 0.4942578971385956,
      "learning_rate": 2.1580552829994785e-05,
      "loss": 0.7829,
      "step": 505
    },
    {
      "epoch": 0.8528428093645485,
      "grad_norm": 0.4644772708415985,
      "learning_rate": 1.9372429079900052e-05,
      "loss": 0.7672,
      "step": 510
    },
    {
      "epoch": 0.8612040133779264,
      "grad_norm": 0.36809882521629333,
      "learning_rate": 1.727565250452414e-05,
      "loss": 0.754,
      "step": 515
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.4026561379432678,
      "learning_rate": 1.52920103999642e-05,
      "loss": 0.7628,
      "step": 520
    },
    {
      "epoch": 0.8779264214046822,
      "grad_norm": 0.45631930232048035,
      "learning_rate": 1.3423193626292405e-05,
      "loss": 0.7838,
      "step": 525
    },
    {
      "epoch": 0.8862876254180602,
      "grad_norm": 0.4896789789199829,
      "learning_rate": 1.1670795166263846e-05,
      "loss": 0.7797,
      "step": 530
    },
    {
      "epoch": 0.8946488294314381,
      "grad_norm": 0.4223991334438324,
      "learning_rate": 1.003630876745522e-05,
      "loss": 0.7747,
      "step": 535
    },
    {
      "epoch": 0.903010033444816,
      "grad_norm": 0.4364998936653137,
      "learning_rate": 8.521127668991612e-06,
      "loss": 0.7628,
      "step": 540
    },
    {
      "epoch": 0.9113712374581939,
      "grad_norm": 0.4812104403972626,
      "learning_rate": 7.126543413947045e-06,
      "loss": 0.7615,
      "step": 545
    },
    {
      "epoch": 0.919732441471572,
      "grad_norm": 0.4221721291542053,
      "learning_rate": 5.853744748430883e-06,
      "loss": 0.7692,
      "step": 550
    },
    {
      "epoch": 0.9280936454849499,
      "grad_norm": 0.42621150612831116,
      "learning_rate": 4.703816608298533e-06,
      "loss": 0.7862,
      "step": 555
    },
    {
      "epoch": 0.9364548494983278,
      "grad_norm": 0.3731984794139862,
      "learning_rate": 3.6777391943500877e-06,
      "loss": 0.7716,
      "step": 560
    },
    {
      "epoch": 0.9448160535117057,
      "grad_norm": 0.409588485956192,
      "learning_rate": 2.7763871368055137e-06,
      "loss": 0.7705,
      "step": 565
    },
    {
      "epoch": 0.9531772575250836,
      "grad_norm": 0.45919135212898254,
      "learning_rate": 2.000528749768199e-06,
      "loss": 0.7648,
      "step": 570
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 0.4654495120048523,
      "learning_rate": 1.3508253763127974e-06,
      "loss": 0.7715,
      "step": 575
    },
    {
      "epoch": 0.9698996655518395,
      "grad_norm": 0.37038466334342957,
      "learning_rate": 8.278308247549992e-07,
      "loss": 0.7731,
      "step": 580
    },
    {
      "epoch": 0.9782608695652174,
      "grad_norm": 0.40466973185539246,
      "learning_rate": 4.3199089658449425e-07,
      "loss": 0.7629,
      "step": 585
    },
    {
      "epoch": 0.9866220735785953,
      "grad_norm": 0.4049622118473053,
      "learning_rate": 1.6364300646291018e-07,
      "loss": 0.7578,
      "step": 590
    },
    {
      "epoch": 0.9949832775919732,
      "grad_norm": 0.37162256240844727,
      "learning_rate": 2.30158946110115e-08,
      "loss": 0.7674,
      "step": 595
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.468013048171997,
      "eval_runtime": 1.3394,
      "eval_samples_per_second": 3.733,
      "eval_steps_per_second": 0.747,
      "step": 598
    },
    {
      "epoch": 1.0,
      "step": 598,
      "total_flos": 9.117045735743816e+17,
      "train_loss": 1.9824217689475885,
      "train_runtime": 7933.7629,
      "train_samples_per_second": 2.411,
      "train_steps_per_second": 0.075
    }
  ],
  "logging_steps": 5,
  "max_steps": 598,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.117045735743816e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}