{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7818654775176515,
  "eval_steps": 200,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014864362690449646,
      "grad_norm": 2.1816246446736707,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.5437,
      "num_input_tokens_seen": 30040,
      "step": 5,
      "train_runtime": 185.9609,
      "train_tokens_per_second": 161.539
    },
    {
      "epoch": 0.029728725380899292,
      "grad_norm": 1.297173579671946,
      "learning_rate": 3.75e-06,
      "loss": 1.3114,
      "num_input_tokens_seen": 65616,
      "step": 10,
      "train_runtime": 371.0314,
      "train_tokens_per_second": 176.848
    },
    {
      "epoch": 0.044593088071348944,
      "grad_norm": 1.3154044523767012,
      "learning_rate": 5.833333333333334e-06,
      "loss": 1.5722,
      "num_input_tokens_seen": 92696,
      "step": 15,
      "train_runtime": 537.3955,
      "train_tokens_per_second": 172.491
    },
    {
      "epoch": 0.059457450761798585,
      "grad_norm": 1.901062718640284,
      "learning_rate": 7.916666666666667e-06,
      "loss": 1.4077,
      "num_input_tokens_seen": 123944,
      "step": 20,
      "train_runtime": 720.0196,
      "train_tokens_per_second": 172.14
    },
    {
      "epoch": 0.07432181345224824,
      "grad_norm": 0.865431080037828,
      "learning_rate": 1e-05,
      "loss": 1.2642,
      "num_input_tokens_seen": 154432,
      "step": 25,
      "train_runtime": 892.3433,
      "train_tokens_per_second": 173.063
    },
    {
      "epoch": 0.08918617614269789,
      "grad_norm": 0.7781390780834406,
      "learning_rate": 1.2083333333333333e-05,
      "loss": 1.1572,
      "num_input_tokens_seen": 181960,
      "step": 30,
      "train_runtime": 1057.0334,
      "train_tokens_per_second": 172.142
    },
    {
      "epoch": 0.10405053883314754,
      "grad_norm": 0.665108652040459,
      "learning_rate": 1.4166666666666668e-05,
      "loss": 0.9421,
      "num_input_tokens_seen": 212640,
      "step": 35,
      "train_runtime": 1231.9846,
      "train_tokens_per_second": 172.6
    },
    {
      "epoch": 0.11891490152359717,
      "grad_norm": 0.2825351078495791,
      "learning_rate": 1.6250000000000002e-05,
      "loss": 0.8661,
      "num_input_tokens_seen": 245808,
      "step": 40,
      "train_runtime": 1416.5893,
      "train_tokens_per_second": 173.521
    },
    {
      "epoch": 0.13377926421404682,
      "grad_norm": 0.36334526479148993,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 0.9087,
      "num_input_tokens_seen": 272224,
      "step": 45,
      "train_runtime": 1582.5403,
      "train_tokens_per_second": 172.017
    },
    {
      "epoch": 0.14864362690449648,
      "grad_norm": 0.44642145260416205,
      "learning_rate": 2.0416666666666667e-05,
      "loss": 0.8855,
      "num_input_tokens_seen": 305560,
      "step": 50,
      "train_runtime": 1768.3526,
      "train_tokens_per_second": 172.794
    },
    {
      "epoch": 0.1635079895949461,
      "grad_norm": 0.41738282561467666,
      "learning_rate": 2.25e-05,
      "loss": 0.8737,
      "num_input_tokens_seen": 332024,
      "step": 55,
      "train_runtime": 1927.929,
      "train_tokens_per_second": 172.218
    },
    {
      "epoch": 0.17837235228539577,
      "grad_norm": 0.39634079236288305,
      "learning_rate": 2.4583333333333332e-05,
      "loss": 0.8043,
      "num_input_tokens_seen": 360856,
      "step": 60,
      "train_runtime": 2097.4995,
      "train_tokens_per_second": 172.041
    },
    {
      "epoch": 0.1932367149758454,
      "grad_norm": 0.35491219061131213,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.7943,
      "num_input_tokens_seen": 398608,
      "step": 65,
      "train_runtime": 2304.6738,
      "train_tokens_per_second": 172.956
    },
    {
      "epoch": 0.20810107766629507,
      "grad_norm": 0.35737550120310063,
      "learning_rate": 2.8749999999999997e-05,
      "loss": 0.8492,
      "num_input_tokens_seen": 425552,
      "step": 70,
      "train_runtime": 2460.8004,
      "train_tokens_per_second": 172.932
    },
    {
      "epoch": 0.2229654403567447,
      "grad_norm": 0.48693276619814596,
      "learning_rate": 3.0833333333333335e-05,
      "loss": 0.6925,
      "num_input_tokens_seen": 457392,
      "step": 75,
      "train_runtime": 2638.2785,
      "train_tokens_per_second": 173.368
    },
    {
      "epoch": 0.23782980304719434,
      "grad_norm": 0.5078391701662902,
      "learning_rate": 3.291666666666667e-05,
      "loss": 0.8085,
      "num_input_tokens_seen": 483824,
      "step": 80,
      "train_runtime": 2806.7407,
      "train_tokens_per_second": 172.379
    },
    {
      "epoch": 0.25269416573764397,
      "grad_norm": 0.3024390891532131,
      "learning_rate": 3.5e-05,
      "loss": 0.7564,
      "num_input_tokens_seen": 512864,
      "step": 85,
      "train_runtime": 2979.1533,
      "train_tokens_per_second": 172.151
    },
    {
      "epoch": 0.26755852842809363,
      "grad_norm": 0.37806969672351337,
      "learning_rate": 3.708333333333334e-05,
      "loss": 0.8039,
      "num_input_tokens_seen": 538720,
      "step": 90,
      "train_runtime": 3137.4212,
      "train_tokens_per_second": 171.708
    },
    {
      "epoch": 0.2824228911185433,
      "grad_norm": 0.3125837610721519,
      "learning_rate": 3.9166666666666665e-05,
      "loss": 0.7889,
      "num_input_tokens_seen": 569688,
      "step": 95,
      "train_runtime": 3317.1304,
      "train_tokens_per_second": 171.741
    },
    {
      "epoch": 0.29728725380899296,
      "grad_norm": 0.2612296186361751,
      "learning_rate": 4.125e-05,
      "loss": 0.8101,
      "num_input_tokens_seen": 603480,
      "step": 100,
      "train_runtime": 3508.249,
      "train_tokens_per_second": 172.017
    },
    {
      "epoch": 0.31215161649944256,
      "grad_norm": 0.4664200778768721,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.7587,
      "num_input_tokens_seen": 632928,
      "step": 105,
      "train_runtime": 3681.3714,
      "train_tokens_per_second": 171.927
    },
    {
      "epoch": 0.3270159791898922,
      "grad_norm": 0.4122820082467493,
      "learning_rate": 4.541666666666667e-05,
      "loss": 0.7925,
      "num_input_tokens_seen": 659840,
      "step": 110,
      "train_runtime": 3850.7584,
      "train_tokens_per_second": 171.353
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.29086455774181913,
      "learning_rate": 4.75e-05,
      "loss": 0.8142,
      "num_input_tokens_seen": 690432,
      "step": 115,
      "train_runtime": 4029.493,
      "train_tokens_per_second": 171.345
    },
    {
      "epoch": 0.35674470457079155,
      "grad_norm": 0.49406027919264844,
      "learning_rate": 4.958333333333334e-05,
      "loss": 0.7088,
      "num_input_tokens_seen": 726264,
      "step": 120,
      "train_runtime": 4222.1079,
      "train_tokens_per_second": 172.015
    },
    {
      "epoch": 0.37160906726124115,
      "grad_norm": 0.29533667352828036,
      "learning_rate": 4.9999194067399066e-05,
      "loss": 0.6237,
      "num_input_tokens_seen": 763328,
      "step": 125,
      "train_runtime": 4420.0509,
      "train_tokens_per_second": 172.697
    },
    {
      "epoch": 0.3864734299516908,
      "grad_norm": 0.554389641306832,
      "learning_rate": 4.999592005526383e-05,
      "loss": 0.6609,
      "num_input_tokens_seen": 792888,
      "step": 130,
      "train_runtime": 4590.9234,
      "train_tokens_per_second": 172.708
    },
    {
      "epoch": 0.4013377926421405,
      "grad_norm": 0.3913197863670873,
      "learning_rate": 4.999012792238118e-05,
      "loss": 0.7873,
      "num_input_tokens_seen": 830784,
      "step": 135,
      "train_runtime": 4780.7961,
      "train_tokens_per_second": 173.775
    },
    {
      "epoch": 0.41620215533259014,
      "grad_norm": 0.7292785043191194,
      "learning_rate": 4.998181825225791e-05,
      "loss": 0.7047,
      "num_input_tokens_seen": 869304,
      "step": 140,
      "train_runtime": 4979.1373,
      "train_tokens_per_second": 174.589
    },
    {
      "epoch": 0.43106651802303975,
      "grad_norm": 0.3288366913256035,
      "learning_rate": 4.997099188202077e-05,
      "loss": 0.6608,
      "num_input_tokens_seen": 903752,
      "step": 145,
      "train_runtime": 5170.5438,
      "train_tokens_per_second": 174.789
    },
    {
      "epoch": 0.4459308807134894,
      "grad_norm": 0.32850031143064623,
      "learning_rate": 4.995764990233205e-05,
      "loss": 0.7203,
      "num_input_tokens_seen": 935672,
      "step": 150,
      "train_runtime": 5350.7854,
      "train_tokens_per_second": 174.866
    },
    {
      "epoch": 0.46079524340393907,
      "grad_norm": 0.4093406468089712,
      "learning_rate": 4.994179365727973e-05,
      "loss": 0.7793,
      "num_input_tokens_seen": 967928,
      "step": 155,
      "train_runtime": 5526.3425,
      "train_tokens_per_second": 175.148
    },
    {
      "epoch": 0.4756596060943887,
      "grad_norm": 0.26538290553046884,
      "learning_rate": 4.992342474424209e-05,
      "loss": 0.6941,
      "num_input_tokens_seen": 1006856,
      "step": 160,
      "train_runtime": 5732.4064,
      "train_tokens_per_second": 175.643
    },
    {
      "epoch": 0.49052396878483834,
      "grad_norm": 0.3293209375345381,
      "learning_rate": 4.990254501372677e-05,
      "loss": 0.7154,
      "num_input_tokens_seen": 1040320,
      "step": 165,
      "train_runtime": 5919.4184,
      "train_tokens_per_second": 175.747
    },
    {
      "epoch": 0.5053883314752879,
      "grad_norm": 0.37872717401082634,
      "learning_rate": 4.987915656918435e-05,
      "loss": 0.7354,
      "num_input_tokens_seen": 1071792,
      "step": 170,
      "train_runtime": 6093.1775,
      "train_tokens_per_second": 175.9
    },
    {
      "epoch": 0.5202526941657376,
      "grad_norm": 0.34111517332292757,
      "learning_rate": 4.985326176679645e-05,
      "loss": 0.7598,
      "num_input_tokens_seen": 1103216,
      "step": 175,
      "train_runtime": 6268.9044,
      "train_tokens_per_second": 175.982
    },
    {
      "epoch": 0.5351170568561873,
      "grad_norm": 0.44888012700873,
      "learning_rate": 4.9824863215238373e-05,
      "loss": 0.7502,
      "num_input_tokens_seen": 1131576,
      "step": 180,
      "train_runtime": 6435.3922,
      "train_tokens_per_second": 175.836
    },
    {
      "epoch": 0.5499814195466369,
      "grad_norm": 0.4802566147521983,
      "learning_rate": 4.979396377541628e-05,
      "loss": 0.6844,
      "num_input_tokens_seen": 1160040,
      "step": 185,
      "train_runtime": 6605.4368,
      "train_tokens_per_second": 175.619
    },
    {
      "epoch": 0.5648457822370866,
      "grad_norm": 0.4821989259826241,
      "learning_rate": 4.976056656017901e-05,
      "loss": 0.8291,
      "num_input_tokens_seen": 1190376,
      "step": 190,
      "train_runtime": 6782.0935,
      "train_tokens_per_second": 175.517
    },
    {
      "epoch": 0.5797101449275363,
      "grad_norm": 0.386641731129637,
      "learning_rate": 4.972467493400445e-05,
      "loss": 0.7762,
      "num_input_tokens_seen": 1217904,
      "step": 195,
      "train_runtime": 6948.2037,
      "train_tokens_per_second": 175.283
    },
    {
      "epoch": 0.5945745076179859,
      "grad_norm": 0.4418388818648707,
      "learning_rate": 4.968629251266064e-05,
      "loss": 0.6688,
      "num_input_tokens_seen": 1256312,
      "step": 200,
      "train_runtime": 7158.3945,
      "train_tokens_per_second": 175.502
    },
    {
      "epoch": 0.5945745076179859,
      "eval_loss": 0.8953876495361328,
      "eval_runtime": 353.0879,
      "eval_samples_per_second": 1.325,
      "eval_steps_per_second": 0.663,
      "num_input_tokens_seen": 1256312,
      "step": 200
    },
    {
      "epoch": 0.6094388703084356,
      "grad_norm": 0.5521465457074078,
      "learning_rate": 4.964542316284147e-05,
      "loss": 0.7398,
      "num_input_tokens_seen": 1290880,
      "step": 205,
      "train_runtime": 7728.2908,
      "train_tokens_per_second": 167.033
    },
    {
      "epoch": 0.6243032329988851,
      "grad_norm": 0.4773991938686689,
      "learning_rate": 4.960207100177716e-05,
      "loss": 0.7169,
      "num_input_tokens_seen": 1320288,
      "step": 210,
      "train_runtime": 7894.6486,
      "train_tokens_per_second": 167.238
    },
    {
      "epoch": 0.6391675956893348,
      "grad_norm": 0.51804635767658,
      "learning_rate": 4.955624039681952e-05,
      "loss": 0.7618,
      "num_input_tokens_seen": 1346816,
      "step": 215,
      "train_runtime": 8060.6928,
      "train_tokens_per_second": 167.084
    },
    {
      "epoch": 0.6540319583797845,
      "grad_norm": 0.5900793472953364,
      "learning_rate": 4.950793596500192e-05,
      "loss": 0.7563,
      "num_input_tokens_seen": 1382472,
      "step": 220,
      "train_runtime": 8252.4478,
      "train_tokens_per_second": 167.523
    },
    {
      "epoch": 0.6688963210702341,
      "grad_norm": 0.39058107426349015,
      "learning_rate": 4.94571625725742e-05,
      "loss": 0.6626,
      "num_input_tokens_seen": 1420832,
      "step": 225,
      "train_runtime": 8450.5909,
      "train_tokens_per_second": 168.134
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.5663525201259818,
      "learning_rate": 4.940392533451244e-05,
      "loss": 0.7741,
      "num_input_tokens_seen": 1451496,
      "step": 230,
      "train_runtime": 8624.0331,
      "train_tokens_per_second": 168.308
    },
    {
      "epoch": 0.6986250464511334,
      "grad_norm": 0.3852996317746423,
      "learning_rate": 4.9348229614003615e-05,
      "loss": 0.7749,
      "num_input_tokens_seen": 1483136,
      "step": 235,
      "train_runtime": 8805.4306,
      "train_tokens_per_second": 168.434
    },
    {
      "epoch": 0.7134894091415831,
      "grad_norm": 0.4546419228429511,
      "learning_rate": 4.9290081021905416e-05,
      "loss": 0.7186,
      "num_input_tokens_seen": 1522176,
      "step": 240,
      "train_runtime": 9011.7223,
      "train_tokens_per_second": 168.911
    },
    {
      "epoch": 0.7283537718320326,
      "grad_norm": 0.27319864084916956,
      "learning_rate": 4.9229485416180876e-05,
      "loss": 0.659,
      "num_input_tokens_seen": 1562400,
      "step": 245,
      "train_runtime": 9221.6215,
      "train_tokens_per_second": 169.428
    },
    {
      "epoch": 0.7432181345224823,
      "grad_norm": 0.5971581275751557,
      "learning_rate": 4.916644890130831e-05,
      "loss": 0.747,
      "num_input_tokens_seen": 1587136,
      "step": 250,
      "train_runtime": 9378.073,
      "train_tokens_per_second": 169.239
    },
    {
      "epoch": 0.758082497212932,
      "grad_norm": 0.3725130213516166,
      "learning_rate": 4.9100977827666345e-05,
      "loss": 0.698,
      "num_input_tokens_seen": 1614920,
      "step": 255,
      "train_runtime": 9541.7299,
      "train_tokens_per_second": 169.248
    },
    {
      "epoch": 0.7729468599033816,
      "grad_norm": 0.4907840552388026,
      "learning_rate": 4.903307879089411e-05,
      "loss": 0.6477,
      "num_input_tokens_seen": 1645688,
      "step": 260,
      "train_runtime": 9716.0007,
      "train_tokens_per_second": 169.379
    },
    {
      "epoch": 0.7878112225938313,
      "grad_norm": 0.5241784073891005,
      "learning_rate": 4.896275863122685e-05,
      "loss": 0.7262,
      "num_input_tokens_seen": 1681888,
      "step": 265,
      "train_runtime": 9905.9233,
      "train_tokens_per_second": 169.786
    },
    {
      "epoch": 0.802675585284281,
      "grad_norm": 0.4747498444810908,
      "learning_rate": 4.8890024432806806e-05,
      "loss": 0.7729,
      "num_input_tokens_seen": 1709480,
      "step": 270,
      "train_runtime": 10078.2583,
      "train_tokens_per_second": 169.621
    },
    {
      "epoch": 0.8175399479747306,
      "grad_norm": 0.40268303548713125,
      "learning_rate": 4.8814883522969545e-05,
      "loss": 0.653,
      "num_input_tokens_seen": 1744560,
      "step": 275,
      "train_runtime": 10262.7966,
      "train_tokens_per_second": 169.989
    },
    {
      "epoch": 0.8324043106651803,
      "grad_norm": 0.5361180434189863,
      "learning_rate": 4.8737343471505806e-05,
      "loss": 0.75,
      "num_input_tokens_seen": 1773576,
      "step": 280,
      "train_runtime": 10433.1959,
      "train_tokens_per_second": 169.994
    },
    {
      "epoch": 0.8472686733556298,
      "grad_norm": 0.4150141248761779,
      "learning_rate": 4.865741208989888e-05,
      "loss": 0.6366,
      "num_input_tokens_seen": 1807248,
      "step": 285,
      "train_runtime": 10621.0739,
      "train_tokens_per_second": 170.157
    },
    {
      "epoch": 0.8621330360460795,
      "grad_norm": 0.557076443271248,
      "learning_rate": 4.857509743053774e-05,
      "loss": 0.7992,
      "num_input_tokens_seen": 1836512,
      "step": 290,
      "train_runtime": 10790.2552,
      "train_tokens_per_second": 170.201
    },
    {
      "epoch": 0.8769973987365292,
      "grad_norm": 0.622394894811983,
      "learning_rate": 4.8490407785905756e-05,
      "loss": 0.7259,
      "num_input_tokens_seen": 1864768,
      "step": 295,
      "train_runtime": 10958.7213,
      "train_tokens_per_second": 170.163
    },
    {
      "epoch": 0.8918617614269788,
      "grad_norm": 0.32132112389269674,
      "learning_rate": 4.840335168774532e-05,
      "loss": 0.6569,
      "num_input_tokens_seen": 1897416,
      "step": 300,
      "train_runtime": 11132.0894,
      "train_tokens_per_second": 170.446
    },
    {
      "epoch": 0.9067261241174285,
      "grad_norm": 0.5699931721537229,
      "learning_rate": 4.8313937906198415e-05,
      "loss": 0.7109,
      "num_input_tokens_seen": 1925464,
      "step": 305,
      "train_runtime": 11302.0412,
      "train_tokens_per_second": 170.364
    },
    {
      "epoch": 0.9215904868078781,
      "grad_norm": 0.49216652434145286,
      "learning_rate": 4.822217544892298e-05,
      "loss": 0.6374,
      "num_input_tokens_seen": 1956064,
      "step": 310,
      "train_runtime": 11477.605,
      "train_tokens_per_second": 170.424
    },
    {
      "epoch": 0.9364548494983278,
      "grad_norm": 0.289252551788521,
      "learning_rate": 4.812807356018556e-05,
      "loss": 0.7321,
      "num_input_tokens_seen": 1986504,
      "step": 315,
      "train_runtime": 11660.7035,
      "train_tokens_per_second": 170.359
    },
    {
      "epoch": 0.9513192121887774,
      "grad_norm": 0.4471738070997589,
      "learning_rate": 4.803164171993001e-05,
      "loss": 0.6904,
      "num_input_tokens_seen": 2012976,
      "step": 320,
      "train_runtime": 11819.4269,
      "train_tokens_per_second": 170.311
    },
    {
      "epoch": 0.966183574879227,
      "grad_norm": 0.4988862477404023,
      "learning_rate": 4.793288964282244e-05,
      "loss": 0.8029,
      "num_input_tokens_seen": 2041512,
      "step": 325,
      "train_runtime": 11993.4775,
      "train_tokens_per_second": 170.219
    },
    {
      "epoch": 0.9810479375696767,
      "grad_norm": 0.4455586736978044,
      "learning_rate": 4.783182727727258e-05,
      "loss": 0.7208,
      "num_input_tokens_seen": 2065864,
      "step": 330,
      "train_runtime": 12150.1754,
      "train_tokens_per_second": 170.028
    },
    {
      "epoch": 0.9959123002601263,
      "grad_norm": 0.45313304199376386,
      "learning_rate": 4.772846480443154e-05,
      "loss": 0.6892,
      "num_input_tokens_seen": 2099192,
      "step": 335,
      "train_runtime": 12332.4171,
      "train_tokens_per_second": 170.217
    },
    {
      "epoch": 1.0089186176142697,
      "grad_norm": 0.34932689166112835,
      "learning_rate": 4.762281263716619e-05,
      "loss": 0.7558,
      "num_input_tokens_seen": 2125816,
      "step": 340,
      "train_runtime": 12484.2733,
      "train_tokens_per_second": 170.28
    },
    {
      "epoch": 1.0237829803047194,
      "grad_norm": 0.4092397826706536,
      "learning_rate": 4.751488141901009e-05,
      "loss": 0.5846,
      "num_input_tokens_seen": 2160160,
      "step": 345,
      "train_runtime": 12674.5489,
      "train_tokens_per_second": 170.433
    },
    {
      "epoch": 1.038647342995169,
      "grad_norm": 0.31168294599405477,
      "learning_rate": 4.740468202309132e-05,
      "loss": 0.5396,
      "num_input_tokens_seen": 2202880,
      "step": 350,
      "train_runtime": 12878.5359,
      "train_tokens_per_second": 171.05
    },
    {
      "epoch": 1.0535117056856187,
      "grad_norm": 0.4562243418713546,
      "learning_rate": 4.729222555103703e-05,
      "loss": 0.6491,
      "num_input_tokens_seen": 2232216,
      "step": 355,
      "train_runtime": 13048.5779,
      "train_tokens_per_second": 171.07
    },
    {
      "epoch": 1.0683760683760684,
      "grad_norm": 0.37853300240110366,
      "learning_rate": 4.717752333185511e-05,
      "loss": 0.5624,
      "num_input_tokens_seen": 2255520,
      "step": 360,
      "train_runtime": 13200.2201,
      "train_tokens_per_second": 170.87
    },
    {
      "epoch": 1.083240431066518,
      "grad_norm": 0.505365165589364,
      "learning_rate": 4.706058692079288e-05,
      "loss": 0.5882,
      "num_input_tokens_seen": 2295400,
      "step": 365,
      "train_runtime": 13416.4241,
      "train_tokens_per_second": 171.089
    },
    {
      "epoch": 1.0981047937569677,
      "grad_norm": 0.7984507974057846,
      "learning_rate": 4.6941428098172956e-05,
      "loss": 0.6382,
      "num_input_tokens_seen": 2322496,
      "step": 370,
      "train_runtime": 13576.7515,
      "train_tokens_per_second": 171.064
    },
    {
      "epoch": 1.1129691564474173,
      "grad_norm": 0.5722349779883125,
      "learning_rate": 4.682005886820656e-05,
      "loss": 0.6791,
      "num_input_tokens_seen": 2353904,
      "step": 375,
      "train_runtime": 13756.8344,
      "train_tokens_per_second": 171.108
    },
    {
      "epoch": 1.127833519137867,
      "grad_norm": 0.826155965272619,
      "learning_rate": 4.669649145778412e-05,
      "loss": 0.6277,
      "num_input_tokens_seen": 2389640,
      "step": 380,
      "train_runtime": 13955.4804,
      "train_tokens_per_second": 171.233
    },
    {
      "epoch": 1.1426978818283167,
      "grad_norm": 0.48208601176965793,
      "learning_rate": 4.657073831524358e-05,
      "loss": 0.5038,
      "num_input_tokens_seen": 2427872,
      "step": 385,
      "train_runtime": 14154.7296,
      "train_tokens_per_second": 171.524
    },
    {
      "epoch": 1.1575622445187663,
      "grad_norm": 0.862951567640207,
      "learning_rate": 4.644281210911631e-05,
      "loss": 0.6581,
      "num_input_tokens_seen": 2453984,
      "step": 390,
      "train_runtime": 14320.9438,
      "train_tokens_per_second": 171.356
    },
    {
      "epoch": 1.172426607209216,
      "grad_norm": 0.6446091778736193,
      "learning_rate": 4.631272572685086e-05,
      "loss": 0.5966,
      "num_input_tokens_seen": 2482696,
      "step": 395,
      "train_runtime": 14484.582,
      "train_tokens_per_second": 171.403
    },
    {
      "epoch": 1.1872909698996654,
      "grad_norm": 0.5940985307805492,
      "learning_rate": 4.618049227351467e-05,
      "loss": 0.6238,
      "num_input_tokens_seen": 2515024,
      "step": 400,
      "train_runtime": 14670.3277,
      "train_tokens_per_second": 171.436
    },
    {
      "epoch": 1.1872909698996654,
      "eval_loss": 0.8729309439659119,
      "eval_runtime": 355.7054,
      "eval_samples_per_second": 1.316,
      "eval_steps_per_second": 0.658,
      "num_input_tokens_seen": 2515024,
      "step": 400
    },
    {
      "epoch": 1.2021553325901153,
      "grad_norm": 0.42070342961969176,
      "learning_rate": 4.6046125070473854e-05,
      "loss": 0.6013,
      "num_input_tokens_seen": 2544048,
      "step": 405,
      "train_runtime": 15222.6559,
      "train_tokens_per_second": 167.122
    },
    {
      "epoch": 1.2170196952805648,
      "grad_norm": 0.5065404783086159,
      "learning_rate": 4.5909637654051194e-05,
      "loss": 0.6597,
      "num_input_tokens_seen": 2577080,
      "step": 410,
      "train_runtime": 15412.9664,
      "train_tokens_per_second": 167.202
    },
    {
      "epoch": 1.2318840579710144,
      "grad_norm": 0.7043622561243575,
      "learning_rate": 4.577104377416243e-05,
      "loss": 0.6459,
      "num_input_tokens_seen": 2605240,
      "step": 415,
      "train_runtime": 15585.0317,
      "train_tokens_per_second": 167.163
    },
    {
      "epoch": 1.246748420661464,
      "grad_norm": 0.5815684563195597,
      "learning_rate": 4.5630357392931136e-05,
      "loss": 0.5973,
      "num_input_tokens_seen": 2634016,
      "step": 420,
      "train_runtime": 15757.2057,
      "train_tokens_per_second": 167.163
    },
    {
      "epoch": 1.2616127833519137,
      "grad_norm": 0.5571563336020446,
      "learning_rate": 4.548759268328211e-05,
      "loss": 0.6341,
      "num_input_tokens_seen": 2663784,
      "step": 425,
      "train_runtime": 15930.8715,
      "train_tokens_per_second": 167.209
    },
    {
      "epoch": 1.2764771460423634,
      "grad_norm": 0.6460743117704272,
      "learning_rate": 4.534276402751361e-05,
      "loss": 0.651,
      "num_input_tokens_seen": 2697024,
      "step": 430,
      "train_runtime": 16122.3767,
      "train_tokens_per_second": 167.285
    },
    {
      "epoch": 1.291341508732813,
      "grad_norm": 0.6482175581649149,
      "learning_rate": 4.5195886015848454e-05,
      "loss": 0.6475,
      "num_input_tokens_seen": 2719400,
      "step": 435,
      "train_runtime": 16266.13,
      "train_tokens_per_second": 167.182
    },
    {
      "epoch": 1.3062058714232627,
      "grad_norm": 0.6094464333253732,
      "learning_rate": 4.5046973444964165e-05,
      "loss": 0.6373,
      "num_input_tokens_seen": 2751744,
      "step": 440,
      "train_runtime": 16434.9886,
      "train_tokens_per_second": 167.432
    },
    {
      "epoch": 1.3210702341137124,
      "grad_norm": 0.8126749512005293,
      "learning_rate": 4.4896041316502335e-05,
      "loss": 0.6434,
      "num_input_tokens_seen": 2791080,
      "step": 445,
      "train_runtime": 16641.4496,
      "train_tokens_per_second": 167.719
    },
    {
      "epoch": 1.335934596804162,
      "grad_norm": 0.5026965778291799,
      "learning_rate": 4.474310483555739e-05,
      "loss": 0.5877,
      "num_input_tokens_seen": 2823104,
      "step": 450,
      "train_runtime": 16826.3481,
      "train_tokens_per_second": 167.779
    },
    {
      "epoch": 1.3507989594946117,
      "grad_norm": 0.824948158879483,
      "learning_rate": 4.4588179409144734e-05,
      "loss": 0.6944,
      "num_input_tokens_seen": 2850480,
      "step": 455,
      "train_runtime": 16993.1957,
      "train_tokens_per_second": 167.742
    },
    {
      "epoch": 1.3656633221850614,
      "grad_norm": 0.6935578787290407,
      "learning_rate": 4.4431280644648676e-05,
      "loss": 0.6677,
      "num_input_tokens_seen": 2877920,
      "step": 460,
      "train_runtime": 17162.7566,
      "train_tokens_per_second": 167.684
    },
    {
      "epoch": 1.380527684875511,
      "grad_norm": 0.775256808439057,
      "learning_rate": 4.427242434825013e-05,
      "loss": 0.6185,
      "num_input_tokens_seen": 2910104,
      "step": 465,
      "train_runtime": 17349.4341,
      "train_tokens_per_second": 167.735
    },
    {
      "epoch": 1.3953920475659607,
      "grad_norm": 0.5290136444612117,
      "learning_rate": 4.4111626523334235e-05,
      "loss": 0.4792,
      "num_input_tokens_seen": 2943600,
      "step": 470,
      "train_runtime": 17535.2111,
      "train_tokens_per_second": 167.868
    },
    {
      "epoch": 1.4102564102564101,
      "grad_norm": 0.431851575535354,
      "learning_rate": 4.394890336887819e-05,
      "loss": 0.5479,
      "num_input_tokens_seen": 2983616,
      "step": 475,
      "train_runtime": 17735.6146,
      "train_tokens_per_second": 168.227
    },
    {
      "epoch": 1.42512077294686,
      "grad_norm": 0.707234404224925,
      "learning_rate": 4.378427127781935e-05,
      "loss": 0.6563,
      "num_input_tokens_seen": 3010896,
      "step": 480,
      "train_runtime": 17897.1321,
      "train_tokens_per_second": 168.233
    },
    {
      "epoch": 1.4399851356373095,
      "grad_norm": 0.5496990766753803,
      "learning_rate": 4.361774683540375e-05,
      "loss": 0.5839,
      "num_input_tokens_seen": 3040128,
      "step": 485,
      "train_runtime": 18074.4912,
      "train_tokens_per_second": 168.2
    },
    {
      "epoch": 1.4548494983277591,
      "grad_norm": 0.40637808524319596,
      "learning_rate": 4.34493468175153e-05,
      "loss": 0.5499,
      "num_input_tokens_seen": 3070192,
      "step": 490,
      "train_runtime": 18243.0065,
      "train_tokens_per_second": 168.294
    },
    {
      "epoch": 1.4697138610182088,
      "grad_norm": 0.5939003521421573,
      "learning_rate": 4.327908818898581e-05,
      "loss": 0.6602,
      "num_input_tokens_seen": 3100544,
      "step": 495,
      "train_runtime": 18419.7661,
      "train_tokens_per_second": 168.327
    },
    {
      "epoch": 1.4845782237086584,
      "grad_norm": 0.5699315589577931,
      "learning_rate": 4.3106988101885825e-05,
      "loss": 0.6172,
      "num_input_tokens_seen": 3134864,
      "step": 500,
      "train_runtime": 18605.4997,
      "train_tokens_per_second": 168.491
    },
    {
      "epoch": 1.499442586399108,
      "grad_norm": 0.5176180044018102,
      "learning_rate": 4.293306389379682e-05,
      "loss": 0.6932,
      "num_input_tokens_seen": 3164496,
      "step": 505,
      "train_runtime": 18782.3882,
      "train_tokens_per_second": 168.482
    },
    {
      "epoch": 1.5143069490895578,
      "grad_norm": 0.8125909060302873,
      "learning_rate": 4.275733308606452e-05,
      "loss": 0.6075,
      "num_input_tokens_seen": 3201592,
      "step": 510,
      "train_runtime": 18974.7401,
      "train_tokens_per_second": 168.729
    },
    {
      "epoch": 1.5291713117800074,
      "grad_norm": 0.4238803109744304,
      "learning_rate": 4.2579813382033764e-05,
      "loss": 0.6465,
      "num_input_tokens_seen": 3242824,
      "step": 515,
      "train_runtime": 19182.5699,
      "train_tokens_per_second": 169.051
    },
    {
      "epoch": 1.544035674470457,
      "grad_norm": 0.5568097005839904,
      "learning_rate": 4.240052266526512e-05,
      "loss": 0.6159,
      "num_input_tokens_seen": 3273600,
      "step": 520,
      "train_runtime": 19367.6233,
      "train_tokens_per_second": 169.024
    },
    {
      "epoch": 1.5589000371609067,
      "grad_norm": 0.5943741262587303,
      "learning_rate": 4.22194789977332e-05,
      "loss": 0.6439,
      "num_input_tokens_seen": 3308472,
      "step": 525,
      "train_runtime": 19562.3706,
      "train_tokens_per_second": 169.124
    },
    {
      "epoch": 1.5737643998513564,
      "grad_norm": 0.8079971411544303,
      "learning_rate": 4.203670061800712e-05,
      "loss": 0.6874,
      "num_input_tokens_seen": 3332568,
      "step": 530,
      "train_runtime": 19717.9765,
      "train_tokens_per_second": 169.012
    },
    {
      "epoch": 1.588628762541806,
      "grad_norm": 0.551762199364396,
      "learning_rate": 4.1852205939413104e-05,
      "loss": 0.6013,
      "num_input_tokens_seen": 3366712,
      "step": 535,
      "train_runtime": 19903.6186,
      "train_tokens_per_second": 169.151
    },
    {
      "epoch": 1.6034931252322555,
      "grad_norm": 0.5068985496527462,
      "learning_rate": 4.1666013548179496e-05,
      "loss": 0.6359,
      "num_input_tokens_seen": 3391608,
      "step": 540,
      "train_runtime": 20057.39,
      "train_tokens_per_second": 169.095
    },
    {
      "epoch": 1.6183574879227054,
      "grad_norm": 0.6855669469937492,
      "learning_rate": 4.147814220156437e-05,
      "loss": 0.6127,
      "num_input_tokens_seen": 3421400,
      "step": 545,
      "train_runtime": 20228.9847,
      "train_tokens_per_second": 169.134
    },
    {
      "epoch": 1.6332218506131548,
      "grad_norm": 0.4879299108867579,
      "learning_rate": 4.128861082596592e-05,
      "loss": 0.5612,
      "num_input_tokens_seen": 3455584,
      "step": 550,
      "train_runtime": 20414.7402,
      "train_tokens_per_second": 169.269
    },
    {
      "epoch": 1.6480862133036047,
      "grad_norm": 0.8129316983564234,
      "learning_rate": 4.109743851501573e-05,
      "loss": 0.6068,
      "num_input_tokens_seen": 3480392,
      "step": 555,
      "train_runtime": 20570.2335,
      "train_tokens_per_second": 169.196
    },
    {
      "epoch": 1.6629505759940542,
      "grad_norm": 0.5732379522903723,
      "learning_rate": 4.090464452765535e-05,
      "loss": 0.6331,
      "num_input_tokens_seen": 3515664,
      "step": 560,
      "train_runtime": 20754.2066,
      "train_tokens_per_second": 169.395
    },
    {
      "epoch": 1.677814938684504,
      "grad_norm": 0.8129257440384582,
      "learning_rate": 4.0710248286195994e-05,
      "loss": 0.6944,
      "num_input_tokens_seen": 3538880,
      "step": 565,
      "train_runtime": 20901.2916,
      "train_tokens_per_second": 169.314
    },
    {
      "epoch": 1.6926793013749535,
      "grad_norm": 0.5743351437424525,
      "learning_rate": 4.051426937436207e-05,
      "loss": 0.6007,
      "num_input_tokens_seen": 3576168,
      "step": 570,
      "train_runtime": 21091.5246,
      "train_tokens_per_second": 169.555
    },
    {
      "epoch": 1.7075436640654031,
      "grad_norm": 1.7481870694933204,
      "learning_rate": 4.0316727535318175e-05,
      "loss": 0.6374,
      "num_input_tokens_seen": 3606944,
      "step": 575,
      "train_runtime": 21266.3906,
      "train_tokens_per_second": 169.608
    },
    {
      "epoch": 1.7224080267558528,
      "grad_norm": 0.5813131410466363,
      "learning_rate": 4.0117642669680164e-05,
      "loss": 0.5499,
      "num_input_tokens_seen": 3637888,
      "step": 580,
      "train_runtime": 21440.8922,
      "train_tokens_per_second": 169.671
    },
    {
      "epoch": 1.7372723894463025,
      "grad_norm": 0.8484268316277586,
      "learning_rate": 3.991703483351039e-05,
      "loss": 0.6668,
      "num_input_tokens_seen": 3661216,
      "step": 585,
      "train_runtime": 21594.0452,
      "train_tokens_per_second": 169.547
    },
    {
      "epoch": 1.7521367521367521,
      "grad_norm": 0.34272148077746284,
      "learning_rate": 3.9714924236297155e-05,
      "loss": 0.6033,
      "num_input_tokens_seen": 3700064,
      "step": 590,
      "train_runtime": 21798.0768,
      "train_tokens_per_second": 169.743
    },
    {
      "epoch": 1.7670011148272018,
      "grad_norm": 0.588668446023156,
      "learning_rate": 3.9511331238918837e-05,
      "loss": 0.5136,
      "num_input_tokens_seen": 3730992,
      "step": 595,
      "train_runtime": 21979.8348,
      "train_tokens_per_second": 169.746
    },
    {
      "epoch": 1.7818654775176515,
      "grad_norm": 0.5461111827190066,
      "learning_rate": 3.9306276351592685e-05,
      "loss": 0.5867,
      "num_input_tokens_seen": 3766176,
      "step": 600,
      "train_runtime": 22165.8728,
      "train_tokens_per_second": 169.909
    },
    {
      "epoch": 1.7818654775176515,
      "eval_loss": 0.8493290543556213,
      "eval_runtime": 354.1156,
      "eval_samples_per_second": 1.322,
      "eval_steps_per_second": 0.661,
      "num_input_tokens_seen": 3766176,
      "step": 600
    }
  ],
  "logging_steps": 5,
  "max_steps": 1685,
  "num_input_tokens_seen": 3766176,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 166671066071040.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}