{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.993979933110368,
  "eval_steps": 100,
  "global_step": 1119,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013377926421404682,
      "grad_norm": 31.946590376675037,
      "learning_rate": 4.4642857142857147e-07,
      "loss": 1.2958,
      "step": 5
    },
    {
      "epoch": 0.026755852842809364,
      "grad_norm": 6.55244388496526,
      "learning_rate": 8.928571428571429e-07,
      "loss": 1.2627,
      "step": 10
    },
    {
      "epoch": 0.04013377926421405,
      "grad_norm": 7.5989567440091585,
      "learning_rate": 1.3392857142857143e-06,
      "loss": 1.2874,
      "step": 15
    },
    {
      "epoch": 0.05351170568561873,
      "grad_norm": 2.7362855062254225,
      "learning_rate": 1.7857142857142859e-06,
      "loss": 1.2337,
      "step": 20
    },
    {
      "epoch": 0.06688963210702341,
      "grad_norm": 2.1889352739395216,
      "learning_rate": 2.2321428571428573e-06,
      "loss": 1.2754,
      "step": 25
    },
    {
      "epoch": 0.0802675585284281,
      "grad_norm": 1.8597549946305532,
      "learning_rate": 2.6785714285714285e-06,
      "loss": 1.238,
      "step": 30
    },
    {
      "epoch": 0.09364548494983277,
      "grad_norm": 2.018444805401378,
      "learning_rate": 3.125e-06,
      "loss": 1.2122,
      "step": 35
    },
    {
      "epoch": 0.10702341137123746,
      "grad_norm": 1.937412231850121,
      "learning_rate": 3.5714285714285718e-06,
      "loss": 1.1821,
      "step": 40
    },
    {
      "epoch": 0.12040133779264214,
      "grad_norm": 2.2790127360584083,
      "learning_rate": 4.017857142857143e-06,
      "loss": 1.1503,
      "step": 45
    },
    {
      "epoch": 0.13377926421404682,
      "grad_norm": 1.6229723458044985,
      "learning_rate": 4.464285714285715e-06,
      "loss": 1.1426,
      "step": 50
    },
    {
      "epoch": 0.14715719063545152,
      "grad_norm": 1.9924287113006085,
      "learning_rate": 4.910714285714286e-06,
      "loss": 1.1012,
      "step": 55
    },
    {
      "epoch": 0.1605351170568562,
      "grad_norm": 1.832154946956557,
      "learning_rate": 5.357142857142857e-06,
      "loss": 1.1423,
      "step": 60
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 2.2835904131577256,
      "learning_rate": 5.8035714285714295e-06,
      "loss": 1.1462,
      "step": 65
    },
    {
      "epoch": 0.18729096989966554,
      "grad_norm": 1.7067435078913915,
      "learning_rate": 6.25e-06,
      "loss": 1.105,
      "step": 70
    },
    {
      "epoch": 0.20066889632107024,
      "grad_norm": 1.8499351081387354,
      "learning_rate": 6.696428571428571e-06,
      "loss": 1.0921,
      "step": 75
    },
    {
      "epoch": 0.2140468227424749,
      "grad_norm": 2.3542380670481124,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 1.109,
      "step": 80
    },
    {
      "epoch": 0.22742474916387959,
      "grad_norm": 2.55387815202157,
      "learning_rate": 7.589285714285714e-06,
      "loss": 1.0625,
      "step": 85
    },
    {
      "epoch": 0.2408026755852843,
      "grad_norm": 1.392008189059501,
      "learning_rate": 8.035714285714286e-06,
      "loss": 1.0792,
      "step": 90
    },
    {
      "epoch": 0.25418060200668896,
      "grad_norm": 1.4336889975083718,
      "learning_rate": 8.482142857142858e-06,
      "loss": 1.062,
      "step": 95
    },
    {
      "epoch": 0.26755852842809363,
      "grad_norm": 1.414284998073309,
      "learning_rate": 8.92857142857143e-06,
      "loss": 1.042,
      "step": 100
    },
    {
      "epoch": 0.26755852842809363,
      "eval_loss": 1.0254441499710083,
      "eval_runtime": 150.1041,
      "eval_samples_per_second": 35.395,
      "eval_steps_per_second": 1.113,
      "step": 100
    },
    {
      "epoch": 0.2809364548494983,
      "grad_norm": 1.517891168040724,
      "learning_rate": 9.375000000000001e-06,
      "loss": 1.0349,
      "step": 105
    },
    {
      "epoch": 0.29431438127090304,
      "grad_norm": 1.6103336966412949,
      "learning_rate": 9.821428571428573e-06,
      "loss": 1.0631,
      "step": 110
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 1.3400760919486352,
      "learning_rate": 9.99978101208322e-06,
      "loss": 1.0234,
      "step": 115
    },
    {
      "epoch": 0.3210702341137124,
      "grad_norm": 3.9922688605654546,
      "learning_rate": 9.99844282205785e-06,
      "loss": 1.0557,
      "step": 120
    },
    {
      "epoch": 0.33444816053511706,
      "grad_norm": 1.4489282467883469,
      "learning_rate": 9.995888427170226e-06,
      "loss": 1.0582,
      "step": 125
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 1.3370551994177822,
      "learning_rate": 9.992118448947408e-06,
      "loss": 1.0259,
      "step": 130
    },
    {
      "epoch": 0.3612040133779264,
      "grad_norm": 1.4251445984876532,
      "learning_rate": 9.987133804688247e-06,
      "loss": 1.0689,
      "step": 135
    },
    {
      "epoch": 0.3745819397993311,
      "grad_norm": 1.2711652329134817,
      "learning_rate": 9.98093570724018e-06,
      "loss": 1.0185,
      "step": 140
    },
    {
      "epoch": 0.3879598662207358,
      "grad_norm": 1.144552453590232,
      "learning_rate": 9.973525664704137e-06,
      "loss": 1.0098,
      "step": 145
    },
    {
      "epoch": 0.4013377926421405,
      "grad_norm": 1.2055734801642233,
      "learning_rate": 9.964905480067585e-06,
      "loss": 1.0266,
      "step": 150
    },
    {
      "epoch": 0.41471571906354515,
      "grad_norm": 1.2157728777821908,
      "learning_rate": 9.955077250765833e-06,
      "loss": 1.0324,
      "step": 155
    },
    {
      "epoch": 0.4280936454849498,
      "grad_norm": 1.2067546777875673,
      "learning_rate": 9.944043368171692e-06,
      "loss": 1.0481,
      "step": 160
    },
    {
      "epoch": 0.4414715719063545,
      "grad_norm": 2.6261182971339134,
      "learning_rate": 9.931806517013612e-06,
      "loss": 1.0721,
      "step": 165
    },
    {
      "epoch": 0.45484949832775917,
      "grad_norm": 1.237982640721041,
      "learning_rate": 9.91836967472245e-06,
      "loss": 1.0181,
      "step": 170
    },
    {
      "epoch": 0.4682274247491639,
      "grad_norm": 1.188674540139363,
      "learning_rate": 9.903736110707001e-06,
      "loss": 1.0196,
      "step": 175
    },
    {
      "epoch": 0.4816053511705686,
      "grad_norm": 1.1470412076788694,
      "learning_rate": 9.8879093855585e-06,
      "loss": 1.0617,
      "step": 180
    },
    {
      "epoch": 0.49498327759197325,
      "grad_norm": 1.1834785845562295,
      "learning_rate": 9.870893350184274e-06,
      "loss": 1.0196,
      "step": 185
    },
    {
      "epoch": 0.5083612040133779,
      "grad_norm": 1.3318612284290117,
      "learning_rate": 9.852692144870746e-06,
      "loss": 1.0577,
      "step": 190
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 1.1976993059713574,
      "learning_rate": 9.833310198276037e-06,
      "loss": 1.036,
      "step": 195
    },
    {
      "epoch": 0.5351170568561873,
      "grad_norm": 1.3579484538265107,
      "learning_rate": 9.812752226352405e-06,
      "loss": 0.9872,
      "step": 200
    },
    {
      "epoch": 0.5351170568561873,
      "eval_loss": 1.0063743591308594,
      "eval_runtime": 149.7108,
      "eval_samples_per_second": 35.488,
      "eval_steps_per_second": 1.115,
      "step": 200
    },
    {
      "epoch": 0.5484949832775919,
      "grad_norm": 1.2190388188014913,
      "learning_rate": 9.791023231198757e-06,
      "loss": 1.0283,
      "step": 205
    },
    {
      "epoch": 0.5618729096989966,
      "grad_norm": 1.022418475593247,
      "learning_rate": 9.768128499843579e-06,
      "loss": 1.0278,
      "step": 210
    },
    {
      "epoch": 0.5752508361204013,
      "grad_norm": 1.2003316921360592,
      "learning_rate": 9.744073602958493e-06,
      "loss": 1.0498,
      "step": 215
    },
    {
      "epoch": 0.5886287625418061,
      "grad_norm": 1.116688252576712,
      "learning_rate": 9.718864393502828e-06,
      "loss": 1.0187,
      "step": 220
    },
    {
      "epoch": 0.6020066889632107,
      "grad_norm": 1.2888011234637655,
      "learning_rate": 9.692507005299499e-06,
      "loss": 1.0398,
      "step": 225
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.1735950690203159,
      "learning_rate": 9.665007851542541e-06,
      "loss": 1.042,
      "step": 230
    },
    {
      "epoch": 0.6287625418060201,
      "grad_norm": 1.0955355204061985,
      "learning_rate": 9.636373623236672e-06,
      "loss": 0.9689,
      "step": 235
    },
    {
      "epoch": 0.6421404682274248,
      "grad_norm": 1.217898633941405,
      "learning_rate": 9.60661128756926e-06,
      "loss": 0.9335,
      "step": 240
    },
    {
      "epoch": 0.6555183946488294,
      "grad_norm": 1.2872565874857864,
      "learning_rate": 9.575728086215093e-06,
      "loss": 1.0172,
      "step": 245
    },
    {
      "epoch": 0.6688963210702341,
      "grad_norm": 1.1483180612149577,
      "learning_rate": 9.543731533574349e-06,
      "loss": 0.9927,
      "step": 250
    },
    {
      "epoch": 0.6822742474916388,
      "grad_norm": 1.271466676847694,
      "learning_rate": 9.510629414944229e-06,
      "loss": 1.0104,
      "step": 255
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 1.3591750189647636,
      "learning_rate": 9.47642978462465e-06,
      "loss": 1.0316,
      "step": 260
    },
    {
      "epoch": 0.7090301003344481,
      "grad_norm": 1.253695733744314,
      "learning_rate": 9.441140963958515e-06,
      "loss": 1.0672,
      "step": 265
    },
    {
      "epoch": 0.7224080267558528,
      "grad_norm": 1.2962413499952996,
      "learning_rate": 9.404771539306978e-06,
      "loss": 1.0328,
      "step": 270
    },
    {
      "epoch": 0.7357859531772575,
      "grad_norm": 1.058056902161627,
      "learning_rate": 9.367330359960239e-06,
      "loss": 0.9912,
      "step": 275
    },
    {
      "epoch": 0.7491638795986622,
      "grad_norm": 1.3613124209671206,
      "learning_rate": 9.328826535984374e-06,
      "loss": 1.014,
      "step": 280
    },
    {
      "epoch": 0.7625418060200669,
      "grad_norm": 0.9916292842180835,
      "learning_rate": 9.289269436004692e-06,
      "loss": 0.9737,
      "step": 285
    },
    {
      "epoch": 0.7759197324414716,
      "grad_norm": 1.199932466102474,
      "learning_rate": 9.248668684926199e-06,
      "loss": 0.9971,
      "step": 290
    },
    {
      "epoch": 0.7892976588628763,
      "grad_norm": 1.2020222255226058,
      "learning_rate": 9.207034161591689e-06,
      "loss": 1.0176,
      "step": 295
    },
    {
      "epoch": 0.802675585284281,
      "grad_norm": 0.9386029912207539,
      "learning_rate": 9.16437599637807e-06,
      "loss": 1.008,
      "step": 300
    },
    {
      "epoch": 0.802675585284281,
      "eval_loss": 0.993434488773346,
      "eval_runtime": 150.5269,
      "eval_samples_per_second": 35.296,
      "eval_steps_per_second": 1.109,
      "step": 300
    },
    {
      "epoch": 0.8160535117056856,
      "grad_norm": 1.0269697222310779,
      "learning_rate": 9.120704568731455e-06,
      "loss": 1.0055,
      "step": 305
    },
    {
      "epoch": 0.8294314381270903,
      "grad_norm": 1.1921850873424837,
      "learning_rate": 9.07603050464169e-06,
      "loss": 0.9808,
      "step": 310
    },
    {
      "epoch": 0.842809364548495,
      "grad_norm": 1.4150961151993176,
      "learning_rate": 9.030364674056853e-06,
      "loss": 1.0094,
      "step": 315
    },
    {
      "epoch": 0.8561872909698997,
      "grad_norm": 1.1824752842844202,
      "learning_rate": 8.983718188238428e-06,
      "loss": 0.9978,
      "step": 320
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.9474487837144705,
      "learning_rate": 8.936102397057737e-06,
      "loss": 0.9654,
      "step": 325
    },
    {
      "epoch": 0.882943143812709,
      "grad_norm": 1.3116449529301724,
      "learning_rate": 8.88752888623434e-06,
      "loss": 0.9949,
      "step": 330
    },
    {
      "epoch": 0.8963210702341137,
      "grad_norm": 1.2357926812300235,
      "learning_rate": 8.838009474517022e-06,
      "loss": 1.0466,
      "step": 335
    },
    {
      "epoch": 0.9096989966555183,
      "grad_norm": 1.21136665171992,
      "learning_rate": 8.787556210808101e-06,
      "loss": 1.0075,
      "step": 340
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 1.1046034738865587,
      "learning_rate": 8.736181371231728e-06,
      "loss": 1.0351,
      "step": 345
    },
    {
      "epoch": 0.9364548494983278,
      "grad_norm": 1.0160775318780402,
      "learning_rate": 8.683897456146897e-06,
      "loss": 1.0235,
      "step": 350
    },
    {
      "epoch": 0.9498327759197325,
      "grad_norm": 1.1967451568920842,
      "learning_rate": 8.630717187105902e-06,
      "loss": 0.9868,
      "step": 355
    },
    {
      "epoch": 0.9632107023411371,
      "grad_norm": 1.0723467089474863,
      "learning_rate": 8.576653503758964e-06,
      "loss": 1.0067,
      "step": 360
    },
    {
      "epoch": 0.9765886287625418,
      "grad_norm": 1.246858371531942,
      "learning_rate": 8.52171956070581e-06,
      "loss": 0.9743,
      "step": 365
    },
    {
      "epoch": 0.9899665551839465,
      "grad_norm": 1.0275971223118703,
      "learning_rate": 8.465928724294923e-06,
      "loss": 0.96,
      "step": 370
    },
    {
      "epoch": 1.0033444816053512,
      "grad_norm": 0.9382551654479478,
      "learning_rate": 8.409294569371293e-06,
      "loss": 0.9897,
      "step": 375
    },
    {
      "epoch": 1.0167224080267558,
      "grad_norm": 1.162719556520577,
      "learning_rate": 8.351830875973436e-06,
      "loss": 0.7912,
      "step": 380
    },
    {
      "epoch": 1.0301003344481605,
      "grad_norm": 1.2039432672032517,
      "learning_rate": 8.293551625980468e-06,
      "loss": 0.7677,
      "step": 385
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 1.0218121146847778,
      "learning_rate": 8.234470999710086e-06,
      "loss": 0.7457,
      "step": 390
    },
    {
      "epoch": 1.0568561872909699,
      "grad_norm": 1.2407699947992628,
      "learning_rate": 8.174603372468259e-06,
      "loss": 0.7489,
      "step": 395
    },
    {
      "epoch": 1.0702341137123745,
      "grad_norm": 1.3082306318602033,
      "learning_rate": 8.113963311051474e-06,
      "loss": 0.7473,
      "step": 400
    },
    {
      "epoch": 1.0702341137123745,
      "eval_loss": 1.0105931758880615,
      "eval_runtime": 149.7077,
      "eval_samples_per_second": 35.489,
      "eval_steps_per_second": 1.116,
      "step": 400
    },
    {
      "epoch": 1.0836120401337792,
      "grad_norm": 1.056246079397668,
      "learning_rate": 8.052565570202394e-06,
      "loss": 0.78,
      "step": 405
    },
    {
      "epoch": 1.0969899665551839,
      "grad_norm": 1.0671946804584624,
      "learning_rate": 7.990425089019774e-06,
      "loss": 0.7339,
      "step": 410
    },
    {
      "epoch": 1.1103678929765886,
      "grad_norm": 1.288275985516129,
      "learning_rate": 7.927556987323534e-06,
      "loss": 0.775,
      "step": 415
    },
    {
      "epoch": 1.1237458193979932,
      "grad_norm": 1.1249043744252742,
      "learning_rate": 7.86397656197586e-06,
      "loss": 0.7532,
      "step": 420
    },
    {
      "epoch": 1.137123745819398,
      "grad_norm": 1.0933149663805157,
      "learning_rate": 7.799699283159199e-06,
      "loss": 0.792,
      "step": 425
    },
    {
      "epoch": 1.1505016722408028,
      "grad_norm": 0.997956490849396,
      "learning_rate": 7.734740790612137e-06,
      "loss": 0.7748,
      "step": 430
    },
    {
      "epoch": 1.1638795986622075,
      "grad_norm": 0.8427898442243963,
      "learning_rate": 7.669116889823955e-06,
      "loss": 0.7524,
      "step": 435
    },
    {
      "epoch": 1.1772575250836121,
      "grad_norm": 1.181226726720212,
      "learning_rate": 7.602843548188915e-06,
      "loss": 0.7835,
      "step": 440
    },
    {
      "epoch": 1.1906354515050168,
      "grad_norm": 1.2669045285704714,
      "learning_rate": 7.5359368911211115e-06,
      "loss": 0.7696,
      "step": 445
    },
    {
      "epoch": 1.2040133779264215,
      "grad_norm": 0.9050504465278061,
      "learning_rate": 7.468413198130891e-06,
      "loss": 0.7652,
      "step": 450
    },
    {
      "epoch": 1.2173913043478262,
      "grad_norm": 1.179211905798687,
      "learning_rate": 7.400288898863779e-06,
      "loss": 0.7223,
      "step": 455
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 1.0441122444048954,
      "learning_rate": 7.3315805691028615e-06,
      "loss": 0.7756,
      "step": 460
    },
    {
      "epoch": 1.2441471571906355,
      "grad_norm": 1.3279168455135049,
      "learning_rate": 7.262304926735633e-06,
      "loss": 0.8294,
      "step": 465
    },
    {
      "epoch": 1.2575250836120402,
      "grad_norm": 0.959241708442744,
      "learning_rate": 7.192478827686242e-06,
      "loss": 0.7392,
      "step": 470
    },
    {
      "epoch": 1.2709030100334449,
      "grad_norm": 1.1289301016174298,
      "learning_rate": 7.122119261814175e-06,
      "loss": 0.7595,
      "step": 475
    },
    {
      "epoch": 1.2842809364548495,
      "grad_norm": 1.087208477220754,
      "learning_rate": 7.0512433487803245e-06,
      "loss": 0.7432,
      "step": 480
    },
    {
      "epoch": 1.2976588628762542,
      "grad_norm": 1.0789795463274745,
      "learning_rate": 6.979868333881499e-06,
      "loss": 0.7664,
      "step": 485
    },
    {
      "epoch": 1.3110367892976589,
      "grad_norm": 1.3380304539387544,
      "learning_rate": 6.908011583854353e-06,
      "loss": 0.7236,
      "step": 490
    },
    {
      "epoch": 1.3244147157190636,
      "grad_norm": 1.0055939295359189,
      "learning_rate": 6.835690582649762e-06,
      "loss": 0.762,
      "step": 495
    },
    {
      "epoch": 1.3377926421404682,
      "grad_norm": 1.5847854902361571,
      "learning_rate": 6.762922927178696e-06,
      "loss": 0.7788,
      "step": 500
    },
    {
      "epoch": 1.3377926421404682,
      "eval_loss": 1.0046015977859497,
      "eval_runtime": 149.6682,
      "eval_samples_per_second": 35.499,
      "eval_steps_per_second": 1.116,
      "step": 500
    },
    {
      "epoch": 1.351170568561873,
      "grad_norm": 1.1518010042974471,
      "learning_rate": 6.689726323030582e-06,
      "loss": 0.7847,
      "step": 505
    },
    {
      "epoch": 1.3645484949832776,
      "grad_norm": 1.0172541085747402,
      "learning_rate": 6.6161185801652495e-06,
      "loss": 0.7676,
      "step": 510
    },
    {
      "epoch": 1.3779264214046822,
      "grad_norm": 0.9656720368153764,
      "learning_rate": 6.5421176085794645e-06,
      "loss": 0.7217,
      "step": 515
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.9939195607529424,
      "learning_rate": 6.467741413949124e-06,
      "loss": 0.7707,
      "step": 520
    },
    {
      "epoch": 1.4046822742474916,
      "grad_norm": 1.0058019218908654,
      "learning_rate": 6.39300809324818e-06,
      "loss": 0.7755,
      "step": 525
    },
    {
      "epoch": 1.4180602006688963,
      "grad_norm": 1.030206779995328,
      "learning_rate": 6.3179358303453386e-06,
      "loss": 0.7635,
      "step": 530
    },
    {
      "epoch": 1.431438127090301,
      "grad_norm": 1.023059488522412,
      "learning_rate": 6.242542891579619e-06,
      "loss": 0.7505,
      "step": 535
    },
    {
      "epoch": 1.4448160535117056,
      "grad_norm": 1.021326179356742,
      "learning_rate": 6.1668476213158525e-06,
      "loss": 0.7029,
      "step": 540
    },
    {
      "epoch": 1.4581939799331103,
      "grad_norm": 0.9174722380364886,
      "learning_rate": 6.090868437481185e-06,
      "loss": 0.7637,
      "step": 545
    },
    {
      "epoch": 1.471571906354515,
      "grad_norm": 0.9740471001361392,
      "learning_rate": 6.0146238270836895e-06,
      "loss": 0.8025,
      "step": 550
    },
    {
      "epoch": 1.4849498327759196,
      "grad_norm": 0.9534933933758712,
      "learning_rate": 5.938132341714173e-06,
      "loss": 0.7436,
      "step": 555
    },
    {
      "epoch": 1.4983277591973243,
      "grad_norm": 1.091666803054282,
      "learning_rate": 5.861412593032247e-06,
      "loss": 0.7566,
      "step": 560
    },
    {
      "epoch": 1.511705685618729,
      "grad_norm": 1.136903874541745,
      "learning_rate": 5.7844832482378245e-06,
      "loss": 0.7137,
      "step": 565
    },
    {
      "epoch": 1.5250836120401337,
      "grad_norm": 1.0944264729530682,
      "learning_rate": 5.7073630255290515e-06,
      "loss": 0.7716,
      "step": 570
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 1.1213292333748575,
      "learning_rate": 5.630070689547875e-06,
      "loss": 0.7631,
      "step": 575
    },
    {
      "epoch": 1.551839464882943,
      "grad_norm": 1.0512016732048837,
      "learning_rate": 5.552625046814283e-06,
      "loss": 0.7737,
      "step": 580
    },
    {
      "epoch": 1.5652173913043477,
      "grad_norm": 0.9851716844060948,
      "learning_rate": 5.475044941150361e-06,
      "loss": 0.7399,
      "step": 585
    },
    {
      "epoch": 1.5785953177257523,
      "grad_norm": 1.0580186713020379,
      "learning_rate": 5.397349249095279e-06,
      "loss": 0.7521,
      "step": 590
    },
    {
      "epoch": 1.5919732441471572,
      "grad_norm": 1.0741202044360585,
      "learning_rate": 5.319556875312313e-06,
      "loss": 0.7779,
      "step": 595
    },
    {
      "epoch": 1.605351170568562,
      "grad_norm": 1.2559630227035101,
      "learning_rate": 5.241686747989023e-06,
      "loss": 0.7246,
      "step": 600
    },
    {
      "epoch": 1.605351170568562,
      "eval_loss": 1.00019371509552,
      "eval_runtime": 150.3942,
      "eval_samples_per_second": 35.327,
      "eval_steps_per_second": 1.11,
      "step": 600
    },
    {
      "epoch": 1.6187290969899666,
      "grad_norm": 0.9665058472664697,
      "learning_rate": 5.163757814231708e-06,
      "loss": 0.7553,
      "step": 605
    },
    {
      "epoch": 1.6321070234113713,
      "grad_norm": 1.0298616708170112,
      "learning_rate": 5.085789035455256e-06,
      "loss": 0.7372,
      "step": 610
    },
    {
      "epoch": 1.645484949832776,
      "grad_norm": 1.1440770710719401,
      "learning_rate": 5.007799382769516e-06,
      "loss": 0.7422,
      "step": 615
    },
    {
      "epoch": 1.6588628762541806,
      "grad_norm": 1.0233808186087545,
      "learning_rate": 4.929807832363308e-06,
      "loss": 0.7515,
      "step": 620
    },
    {
      "epoch": 1.6722408026755853,
      "grad_norm": 1.178015294752791,
      "learning_rate": 4.8518333608872015e-06,
      "loss": 0.758,
      "step": 625
    },
    {
      "epoch": 1.68561872909699,
      "grad_norm": 1.0131920406972836,
      "learning_rate": 4.773894940836174e-06,
      "loss": 0.749,
      "step": 630
    },
    {
      "epoch": 1.6989966555183946,
      "grad_norm": 1.1643352193905245,
      "learning_rate": 4.69601153593329e-06,
      "loss": 0.7784,
      "step": 635
    },
    {
      "epoch": 1.7123745819397993,
      "grad_norm": 1.2241373501480923,
      "learning_rate": 4.618202096515505e-06,
      "loss": 0.7553,
      "step": 640
    },
    {
      "epoch": 1.725752508361204,
      "grad_norm": 1.0198134391959597,
      "learning_rate": 4.540485554922729e-06,
      "loss": 0.7655,
      "step": 645
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 1.0507444811075115,
      "learning_rate": 4.462880820891284e-06,
      "loss": 0.7506,
      "step": 650
    },
    {
      "epoch": 1.7525083612040135,
      "grad_norm": 1.0689187605834707,
      "learning_rate": 4.385406776952833e-06,
      "loss": 0.7681,
      "step": 655
    },
    {
      "epoch": 1.7658862876254182,
      "grad_norm": 1.023967031835118,
      "learning_rate": 4.308082273839953e-06,
      "loss": 0.7859,
      "step": 660
    },
    {
      "epoch": 1.779264214046823,
      "grad_norm": 2.7354167382822037,
      "learning_rate": 4.230926125899432e-06,
      "loss": 0.7677,
      "step": 665
    },
    {
      "epoch": 1.7926421404682276,
      "grad_norm": 1.2533171109574939,
      "learning_rate": 4.153957106514428e-06,
      "loss": 0.7224,
      "step": 670
    },
    {
      "epoch": 1.8060200668896322,
      "grad_norm": 1.1666059608649366,
      "learning_rate": 4.0771939435365795e-06,
      "loss": 0.7286,
      "step": 675
    },
    {
      "epoch": 1.819397993311037,
      "grad_norm": 1.0827920835385718,
      "learning_rate": 4.000655314729222e-06,
      "loss": 0.7939,
      "step": 680
    },
    {
      "epoch": 1.8327759197324416,
      "grad_norm": 1.05022651820567,
      "learning_rate": 3.924359843222758e-06,
      "loss": 0.7843,
      "step": 685
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 1.093474005640841,
      "learning_rate": 3.848326092983356e-06,
      "loss": 0.732,
      "step": 690
    },
    {
      "epoch": 1.859531772575251,
      "grad_norm": 1.0137348368542876,
      "learning_rate": 3.7725725642960047e-06,
      "loss": 0.7317,
      "step": 695
    },
    {
      "epoch": 1.8729096989966556,
      "grad_norm": 1.0331644505317576,
      "learning_rate": 3.6971176892631048e-06,
      "loss": 0.7525,
      "step": 700
    },
    {
      "epoch": 1.8729096989966556,
      "eval_loss": 0.9970734119415283,
      "eval_runtime": 149.7659,
      "eval_samples_per_second": 35.475,
      "eval_steps_per_second": 1.115,
      "step": 700
    },
    {
      "epoch": 1.8862876254180603,
      "grad_norm": 1.0320209327878382,
      "learning_rate": 3.6219798273196147e-06,
      "loss": 0.7621,
      "step": 705
    },
    {
      "epoch": 1.899665551839465,
      "grad_norm": 1.3023198090948238,
      "learning_rate": 3.547177260765904e-06,
      "loss": 0.7473,
      "step": 710
    },
    {
      "epoch": 1.9130434782608696,
      "grad_norm": 1.0442173127014935,
      "learning_rate": 3.47272819031935e-06,
      "loss": 0.7279,
      "step": 715
    },
    {
      "epoch": 1.9264214046822743,
      "grad_norm": 1.1980268226658213,
      "learning_rate": 3.398650730685813e-06,
      "loss": 0.7681,
      "step": 720
    },
    {
      "epoch": 1.939799331103679,
      "grad_norm": 1.0904891997215738,
      "learning_rate": 3.3249629061520126e-06,
      "loss": 0.7551,
      "step": 725
    },
    {
      "epoch": 1.9531772575250836,
      "grad_norm": 0.9747796170841941,
      "learning_rate": 3.2516826461999287e-06,
      "loss": 0.7567,
      "step": 730
    },
    {
      "epoch": 1.9665551839464883,
      "grad_norm": 0.9766080320866084,
      "learning_rate": 3.1788277811442436e-06,
      "loss": 0.7621,
      "step": 735
    },
    {
      "epoch": 1.979933110367893,
      "grad_norm": 0.9932850189281304,
      "learning_rate": 3.1064160377939457e-06,
      "loss": 0.7707,
      "step": 740
    },
    {
      "epoch": 1.9933110367892977,
      "grad_norm": 1.4307674678624753,
      "learning_rate": 3.0344650351390797e-06,
      "loss": 0.7902,
      "step": 745
    },
    {
      "epoch": 2.0066889632107023,
      "grad_norm": 1.0374602352029385,
      "learning_rate": 2.962992280063771e-06,
      "loss": 0.6413,
      "step": 750
    },
    {
      "epoch": 2.020066889632107,
      "grad_norm": 1.0251714475763039,
      "learning_rate": 2.8920151630864906e-06,
      "loss": 0.5334,
      "step": 755
    },
    {
      "epoch": 2.0334448160535117,
      "grad_norm": 1.0474079542961143,
      "learning_rate": 2.821550954128667e-06,
      "loss": 0.5353,
      "step": 760
    },
    {
      "epoch": 2.0468227424749164,
      "grad_norm": 1.0781379123388604,
      "learning_rate": 2.7516167983126053e-06,
      "loss": 0.5371,
      "step": 765
    },
    {
      "epoch": 2.060200668896321,
      "grad_norm": 0.9379537943202282,
      "learning_rate": 2.6822297117898144e-06,
      "loss": 0.535,
      "step": 770
    },
    {
      "epoch": 2.0735785953177257,
      "grad_norm": 1.343473723166369,
      "learning_rate": 2.61340657760067e-06,
      "loss": 0.5595,
      "step": 775
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.8716267946589176,
      "learning_rate": 2.5451641415665097e-06,
      "loss": 0.5129,
      "step": 780
    },
    {
      "epoch": 2.100334448160535,
      "grad_norm": 1.083594982127184,
      "learning_rate": 2.4775190082150747e-06,
      "loss": 0.5391,
      "step": 785
    },
    {
      "epoch": 2.1137123745819397,
      "grad_norm": 0.9685617426495453,
      "learning_rate": 2.4104876367403602e-06,
      "loss": 0.5462,
      "step": 790
    },
    {
      "epoch": 2.1270903010033444,
      "grad_norm": 1.1798547706895686,
      "learning_rate": 2.344086336997819e-06,
      "loss": 0.5001,
      "step": 795
    },
    {
      "epoch": 2.140468227424749,
      "grad_norm": 0.9742855432807195,
      "learning_rate": 2.278331265535898e-06,
      "loss": 0.529,
      "step": 800
    },
    {
      "epoch": 2.140468227424749,
      "eval_loss": 1.0470257997512817,
      "eval_runtime": 149.7094,
      "eval_samples_per_second": 35.489,
      "eval_steps_per_second": 1.115,
      "step": 800
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.976201736501433,
      "learning_rate": 2.2132384216648783e-06,
      "loss": 0.5773,
      "step": 805
    },
    {
      "epoch": 2.1672240802675584,
      "grad_norm": 0.9423763960170988,
      "learning_rate": 2.148823643563973e-06,
      "loss": 0.5209,
      "step": 810
    },
    {
      "epoch": 2.180602006688963,
      "grad_norm": 0.950162661211813,
      "learning_rate": 2.0851026044276405e-06,
      "loss": 0.5338,
      "step": 815
    },
    {
      "epoch": 2.1939799331103678,
      "grad_norm": 1.004119449417975,
      "learning_rate": 2.022090808652024e-06,
      "loss": 0.5502,
      "step": 820
    },
    {
      "epoch": 2.2073578595317724,
      "grad_norm": 1.147565589764388,
      "learning_rate": 1.9598035880624832e-06,
      "loss": 0.5352,
      "step": 825
    },
    {
      "epoch": 2.220735785953177,
      "grad_norm": 0.9031033821480767,
      "learning_rate": 1.8982560981830911e-06,
      "loss": 0.5474,
      "step": 830
    },
    {
      "epoch": 2.234113712374582,
      "grad_norm": 1.0009392979799976,
      "learning_rate": 1.8374633145490566e-06,
      "loss": 0.4991,
      "step": 835
    },
    {
      "epoch": 2.2474916387959865,
      "grad_norm": 0.9582618373764454,
      "learning_rate": 1.7774400290629095e-06,
      "loss": 0.532,
      "step": 840
    },
    {
      "epoch": 2.260869565217391,
      "grad_norm": 1.0009695871449187,
      "learning_rate": 1.7182008463953986e-06,
      "loss": 0.5582,
      "step": 845
    },
    {
      "epoch": 2.274247491638796,
      "grad_norm": 0.9316164669727046,
      "learning_rate": 1.6597601804319186e-06,
      "loss": 0.508,
      "step": 850
    },
    {
      "epoch": 2.2876254180602005,
      "grad_norm": 1.1628160696804308,
      "learning_rate": 1.602132250765378e-06,
      "loss": 0.5539,
      "step": 855
    },
    {
      "epoch": 2.3010033444816056,
      "grad_norm": 0.9951585058908428,
      "learning_rate": 1.5453310792363275e-06,
      "loss": 0.545,
      "step": 860
    },
    {
      "epoch": 2.3143812709030103,
      "grad_norm": 0.9609133074764106,
      "learning_rate": 1.489370486521219e-06,
      "loss": 0.5266,
      "step": 865
    },
    {
      "epoch": 2.327759197324415,
      "grad_norm": 0.9987936738623786,
      "learning_rate": 1.4342640887695935e-06,
      "loss": 0.5175,
      "step": 870
    },
    {
      "epoch": 2.3411371237458196,
      "grad_norm": 0.945306998480509,
      "learning_rate": 1.380025294291057e-06,
      "loss": 0.5132,
      "step": 875
    },
    {
      "epoch": 2.3545150501672243,
      "grad_norm": 1.0723405116543199,
      "learning_rate": 1.3266673002927993e-06,
      "loss": 0.5381,
      "step": 880
    },
    {
      "epoch": 2.367892976588629,
      "grad_norm": 1.0166089482172302,
      "learning_rate": 1.2742030896685075e-06,
      "loss": 0.5151,
      "step": 885
    },
    {
      "epoch": 2.3812709030100336,
      "grad_norm": 1.110135707052159,
      "learning_rate": 1.2226454278393956e-06,
      "loss": 0.5314,
      "step": 890
    },
    {
      "epoch": 2.3946488294314383,
      "grad_norm": 0.9125170499901653,
      "learning_rate": 1.1720068596481765e-06,
      "loss": 0.5083,
      "step": 895
    },
    {
      "epoch": 2.408026755852843,
      "grad_norm": 0.8662645128241546,
      "learning_rate": 1.1222997063066855e-06,
      "loss": 0.5365,
      "step": 900
    },
    {
      "epoch": 2.408026755852843,
      "eval_loss": 1.0517374277114868,
      "eval_runtime": 149.9889,
      "eval_samples_per_second": 35.423,
      "eval_steps_per_second": 1.113,
      "step": 900
    },
    {
      "epoch": 2.4214046822742477,
      "grad_norm": 1.030613777960971,
      "learning_rate": 1.0735360623979201e-06,
      "loss": 0.5308,
      "step": 905
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 1.0048676206192078,
      "learning_rate": 1.0257277929332332e-06,
      "loss": 0.5204,
      "step": 910
    },
    {
      "epoch": 2.448160535117057,
      "grad_norm": 0.9609476114160428,
      "learning_rate": 9.788865304653727e-07,
      "loss": 0.5391,
      "step": 915
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.9640556560352546,
      "learning_rate": 9.330236722580832e-07,
      "loss": 0.5106,
      "step": 920
    },
    {
      "epoch": 2.4749163879598663,
      "grad_norm": 0.9899691141087767,
      "learning_rate": 8.881503775129696e-07,
      "loss": 0.5413,
      "step": 925
    },
    {
      "epoch": 2.488294314381271,
      "grad_norm": 1.0571419947794767,
      "learning_rate": 8.442775646542656e-07,
      "loss": 0.5388,
      "step": 930
    },
    {
      "epoch": 2.5016722408026757,
      "grad_norm": 0.9680901349582856,
      "learning_rate": 8.014159086722101e-07,
      "loss": 0.5242,
      "step": 935
    },
    {
      "epoch": 2.5150501672240804,
      "grad_norm": 1.0704814253502815,
      "learning_rate": 7.595758385256325e-07,
      "loss": 0.5477,
      "step": 940
    },
    {
      "epoch": 2.528428093645485,
      "grad_norm": 0.9880390697232635,
      "learning_rate": 7.187675346044165e-07,
      "loss": 0.5078,
      "step": 945
    },
    {
      "epoch": 2.5418060200668897,
      "grad_norm": 0.9815512843065104,
      "learning_rate": 6.790009262524455e-07,
      "loss": 0.5414,
      "step": 950
    },
    {
      "epoch": 2.5551839464882944,
      "grad_norm": 0.978897636667664,
      "learning_rate": 6.40285689351619e-07,
      "loss": 0.5165,
      "step": 955
    },
    {
      "epoch": 2.568561872909699,
      "grad_norm": 1.0210817819839888,
      "learning_rate": 6.026312439675553e-07,
      "loss": 0.5129,
      "step": 960
    },
    {
      "epoch": 2.5819397993311037,
      "grad_norm": 1.0090720244525628,
      "learning_rate": 5.66046752057523e-07,
      "loss": 0.503,
      "step": 965
    },
    {
      "epoch": 2.5953177257525084,
      "grad_norm": 1.1825668438151073,
      "learning_rate": 5.305411152411943e-07,
      "loss": 0.5241,
      "step": 970
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 1.1589618219400188,
      "learning_rate": 4.961229726347233e-07,
      "loss": 0.5176,
      "step": 975
    },
    {
      "epoch": 2.6220735785953178,
      "grad_norm": 1.1916794312531742,
      "learning_rate": 4.628006987487088e-07,
      "loss": 0.4961,
      "step": 980
    },
    {
      "epoch": 2.6354515050167224,
      "grad_norm": 0.9842745180406584,
      "learning_rate": 4.3058240145053223e-07,
      "loss": 0.5436,
      "step": 985
    },
    {
      "epoch": 2.648829431438127,
      "grad_norm": 0.9987938748419682,
      "learning_rate": 3.994759199915821e-07,
      "loss": 0.5004,
      "step": 990
    },
    {
      "epoch": 2.6622073578595318,
      "grad_norm": 1.1090522864890544,
      "learning_rate": 3.694888230998289e-07,
      "loss": 0.5275,
      "step": 995
    },
    {
      "epoch": 2.6755852842809364,
      "grad_norm": 0.9438148481041575,
      "learning_rate": 3.406284071382288e-07,
      "loss": 0.5256,
      "step": 1000
    },
    {
      "epoch": 2.6755852842809364,
      "eval_loss": 1.0514318943023682,
      "eval_runtime": 149.7744,
      "eval_samples_per_second": 35.473,
      "eval_steps_per_second": 1.115,
      "step": 1000
    },
    {
      "epoch": 2.688963210702341,
      "grad_norm": 1.0051570371927316,
      "learning_rate": 3.1290169432939556e-07,
      "loss": 0.5022,
      "step": 1005
    },
    {
      "epoch": 2.702341137123746,
      "grad_norm": 1.0655831780347378,
      "learning_rate": 2.863154310469768e-07,
      "loss": 0.5397,
      "step": 1010
    },
    {
      "epoch": 2.7157190635451505,
      "grad_norm": 0.9818283546277681,
      "learning_rate": 2.6087608617414715e-07,
      "loss": 0.5359,
      "step": 1015
    },
    {
      "epoch": 2.729096989966555,
      "grad_norm": 1.0318807241047394,
      "learning_rate": 2.365898495296226e-07,
      "loss": 0.5013,
      "step": 1020
    },
    {
      "epoch": 2.74247491638796,
      "grad_norm": 1.0460771356529457,
      "learning_rate": 2.1346263036157112e-07,
      "loss": 0.5468,
      "step": 1025
    },
    {
      "epoch": 2.7558528428093645,
      "grad_norm": 1.0837948922809177,
      "learning_rate": 1.9150005590979682e-07,
      "loss": 0.52,
      "step": 1030
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 1.0353066956181127,
      "learning_rate": 1.707074700365341e-07,
      "loss": 0.4959,
      "step": 1035
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.9986043986688646,
      "learning_rate": 1.5108993192620268e-07,
      "loss": 0.5014,
      "step": 1040
    },
    {
      "epoch": 2.7959866220735785,
      "grad_norm": 0.9948563482546479,
      "learning_rate": 1.326522148544157e-07,
      "loss": 0.5043,
      "step": 1045
    },
    {
      "epoch": 2.809364548494983,
      "grad_norm": 1.1025325621449409,
      "learning_rate": 1.153988050265692e-07,
      "loss": 0.5492,
      "step": 1050
    },
    {
      "epoch": 2.822742474916388,
      "grad_norm": 0.9369588676729006,
      "learning_rate": 9.933390048626645e-08,
      "loss": 0.5247,
      "step": 1055
    },
    {
      "epoch": 2.8361204013377925,
      "grad_norm": 0.9364006205818028,
      "learning_rate": 8.446141009386955e-08,
      "loss": 0.52,
      "step": 1060
    },
    {
      "epoch": 2.849498327759197,
      "grad_norm": 1.1077929391413845,
      "learning_rate": 7.078495257540341e-08,
      "loss": 0.5146,
      "step": 1065
    },
    {
      "epoch": 2.862876254180602,
      "grad_norm": 0.990932574232909,
      "learning_rate": 5.830785564206298e-08,
      "loss": 0.5674,
      "step": 1070
    },
    {
      "epoch": 2.8762541806020065,
      "grad_norm": 1.0941649208541484,
      "learning_rate": 4.7033155180522535e-08,
      "loss": 0.544,
      "step": 1075
    },
    {
      "epoch": 2.8896321070234112,
      "grad_norm": 0.8230619670119865,
      "learning_rate": 3.696359451425491e-08,
      "loss": 0.5008,
      "step": 1080
    },
    {
      "epoch": 2.903010033444816,
      "grad_norm": 0.9924164565453516,
      "learning_rate": 2.8101623736035422e-08,
      "loss": 0.5273,
      "step": 1085
    },
    {
      "epoch": 2.9163879598662206,
      "grad_norm": 1.000233223489882,
      "learning_rate": 2.0449399111791003e-08,
      "loss": 0.5461,
      "step": 1090
    },
    {
      "epoch": 2.9297658862876252,
      "grad_norm": 1.048907180597167,
      "learning_rate": 1.400878255594762e-08,
      "loss": 0.5118,
      "step": 1095
    },
    {
      "epoch": 2.94314381270903,
      "grad_norm": 1.0344098154390242,
      "learning_rate": 8.781341178393244e-09,
      "loss": 0.518,
      "step": 1100
    },
    {
      "epoch": 2.94314381270903,
      "eval_loss": 1.0516117811203003,
      "eval_runtime": 151.5953,
      "eval_samples_per_second": 35.047,
      "eval_steps_per_second": 1.102,
      "step": 1100
    },
    {
      "epoch": 2.9565217391304346,
      "grad_norm": 0.9510584400959354,
      "learning_rate": 4.76834690317396e-09,
      "loss": 0.5003,
      "step": 1105
    },
    {
      "epoch": 2.9698996655518393,
      "grad_norm": 0.93864893822128,
      "learning_rate": 1.9707761590148642e-09,
      "loss": 0.5345,
      "step": 1110
    },
    {
      "epoch": 2.983277591973244,
      "grad_norm": 0.9885959787002001,
      "learning_rate": 3.8930964173733434e-10,
      "loss": 0.5564,
      "step": 1115
    },
    {
      "epoch": 2.993979933110368,
      "step": 1119,
      "total_flos": 594922701717504.0,
      "train_loss": 0.7812928989383128,
      "train_runtime": 15592.0429,
      "train_samples_per_second": 9.2,
      "train_steps_per_second": 0.072
    }
  ],
  "logging_steps": 5,
  "max_steps": 1119,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 594922701717504.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}