{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 18.846153846153847,
  "eval_steps": 500,
  "global_step": 14040,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 3.2763532763532763e-06,
      "loss": 0.819,
      "step": 46
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.5527065527065525e-06,
      "loss": 0.8698,
      "step": 92
    },
    {
      "epoch": 0.59,
      "learning_rate": 9.82905982905983e-06,
      "loss": 0.7667,
      "step": 138
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.3105413105413105e-05,
      "loss": 0.6645,
      "step": 184
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.6381766381766382e-05,
      "loss": 0.5342,
      "step": 230
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.965811965811966e-05,
      "loss": 0.5067,
      "step": 276
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.2934472934472936e-05,
      "loss": 0.434,
      "step": 322
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.621082621082621e-05,
      "loss": 0.4473,
      "step": 368
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.948717948717949e-05,
      "loss": 0.3901,
      "step": 414
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.2763532763532764e-05,
      "loss": 0.3859,
      "step": 460
    },
    {
      "epoch": 2.16,
      "learning_rate": 3.603988603988604e-05,
      "loss": 0.3526,
      "step": 506
    },
    {
      "epoch": 2.36,
      "learning_rate": 3.931623931623932e-05,
      "loss": 0.3339,
      "step": 552
    },
    {
      "epoch": 2.56,
      "learning_rate": 4.259259259259259e-05,
      "loss": 0.343,
      "step": 598
    },
    {
      "epoch": 2.75,
      "learning_rate": 4.586894586894587e-05,
      "loss": 0.2998,
      "step": 644
    },
    {
      "epoch": 2.95,
      "learning_rate": 4.9145299145299147e-05,
      "loss": 0.2778,
      "step": 690
    },
    {
      "epoch": 3.15,
      "learning_rate": 5.242165242165242e-05,
      "loss": 0.3029,
      "step": 736
    },
    {
      "epoch": 1.06,
      "learning_rate": 5.5698005698005694e-05,
      "loss": 0.2557,
      "step": 782
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.897435897435898e-05,
      "loss": 0.2605,
      "step": 828
    },
    {
      "epoch": 1.45,
      "learning_rate": 6.225071225071225e-05,
      "loss": 0.2566,
      "step": 874
    },
    {
      "epoch": 1.65,
      "learning_rate": 6.552706552706553e-05,
      "loss": 0.2409,
      "step": 920
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.880341880341881e-05,
      "loss": 0.2518,
      "step": 966
    },
    {
      "epoch": 2.04,
      "learning_rate": 7.207977207977208e-05,
      "loss": 0.279,
      "step": 1012
    },
    {
      "epoch": 2.24,
      "learning_rate": 7.535612535612536e-05,
      "loss": 0.2421,
      "step": 1058
    },
    {
      "epoch": 2.43,
      "learning_rate": 7.863247863247864e-05,
      "loss": 0.2237,
      "step": 1104
    },
    {
      "epoch": 2.63,
      "learning_rate": 8.190883190883192e-05,
      "loss": 0.2057,
      "step": 1150
    },
    {
      "epoch": 2.82,
      "learning_rate": 8.518518518518518e-05,
      "loss": 0.2496,
      "step": 1196
    },
    {
      "epoch": 3.02,
      "learning_rate": 8.846153846153847e-05,
      "loss": 0.2397,
      "step": 1242
    },
    {
      "epoch": 3.22,
      "learning_rate": 9.173789173789175e-05,
      "loss": 0.2322,
      "step": 1288
    },
    {
      "epoch": 3.41,
      "learning_rate": 9.501424501424501e-05,
      "loss": 0.2046,
      "step": 1334
    },
    {
      "epoch": 3.61,
      "learning_rate": 9.829059829059829e-05,
      "loss": 0.2308,
      "step": 1380
    },
    {
      "epoch": 3.81,
      "learning_rate": 9.982589427033872e-05,
      "loss": 0.2052,
      "step": 1426
    },
    {
      "epoch": 4.0,
      "learning_rate": 9.946185501741058e-05,
      "loss": 0.1759,
      "step": 1472
    },
    {
      "epoch": 4.2,
      "learning_rate": 9.909781576448244e-05,
      "loss": 0.2116,
      "step": 1518
    },
    {
      "epoch": 2.11,
      "learning_rate": 9.87337765115543e-05,
      "loss": 0.1603,
      "step": 1564
    },
    {
      "epoch": 2.31,
      "learning_rate": 9.836973725862614e-05,
      "loss": 0.1892,
      "step": 1610
    },
    {
      "epoch": 2.5,
      "learning_rate": 9.800569800569801e-05,
      "loss": 0.1656,
      "step": 1656
    },
    {
      "epoch": 2.7,
      "learning_rate": 9.764165875276987e-05,
      "loss": 0.181,
      "step": 1702
    },
    {
      "epoch": 2.9,
      "learning_rate": 9.727761949984172e-05,
      "loss": 0.1727,
      "step": 1748
    },
    {
      "epoch": 3.09,
      "learning_rate": 9.691358024691359e-05,
      "loss": 0.1555,
      "step": 1794
    },
    {
      "epoch": 3.29,
      "learning_rate": 9.654954099398545e-05,
      "loss": 0.1152,
      "step": 1840
    },
    {
      "epoch": 3.49,
      "learning_rate": 9.61855017410573e-05,
      "loss": 0.1404,
      "step": 1886
    },
    {
      "epoch": 3.68,
      "learning_rate": 9.582146248812915e-05,
      "loss": 0.1635,
      "step": 1932
    },
    {
      "epoch": 3.88,
      "learning_rate": 9.545742323520101e-05,
      "loss": 0.1429,
      "step": 1978
    },
    {
      "epoch": 4.08,
      "learning_rate": 9.509338398227288e-05,
      "loss": 0.1369,
      "step": 2024
    },
    {
      "epoch": 4.27,
      "learning_rate": 9.472934472934474e-05,
      "loss": 0.1482,
      "step": 2070
    },
    {
      "epoch": 4.47,
      "learning_rate": 9.436530547641659e-05,
      "loss": 0.1388,
      "step": 2116
    },
    {
      "epoch": 4.67,
      "learning_rate": 9.400126622348845e-05,
      "loss": 0.1602,
      "step": 2162
    },
    {
      "epoch": 4.86,
      "learning_rate": 9.36372269705603e-05,
      "loss": 0.1764,
      "step": 2208
    },
    {
      "epoch": 5.06,
      "learning_rate": 9.327318771763217e-05,
      "loss": 0.16,
      "step": 2254
    },
    {
      "epoch": 5.26,
      "learning_rate": 9.290914846470402e-05,
      "loss": 0.133,
      "step": 2300
    },
    {
      "epoch": 3.17,
      "learning_rate": 9.254510921177588e-05,
      "loss": 0.1226,
      "step": 2346
    },
    {
      "epoch": 3.36,
      "learning_rate": 9.218106995884775e-05,
      "loss": 0.1062,
      "step": 2392
    },
    {
      "epoch": 3.56,
      "learning_rate": 9.181703070591961e-05,
      "loss": 0.1184,
      "step": 2438
    },
    {
      "epoch": 3.76,
      "learning_rate": 9.145299145299146e-05,
      "loss": 0.107,
      "step": 2484
    },
    {
      "epoch": 3.95,
      "learning_rate": 9.108895220006331e-05,
      "loss": 0.1113,
      "step": 2530
    },
    {
      "epoch": 4.15,
      "learning_rate": 9.072491294713517e-05,
      "loss": 0.13,
      "step": 2576
    },
    {
      "epoch": 4.35,
      "learning_rate": 9.036087369420702e-05,
      "loss": 0.1066,
      "step": 2622
    },
    {
      "epoch": 4.54,
      "learning_rate": 8.999683444127889e-05,
      "loss": 0.1131,
      "step": 2668
    },
    {
      "epoch": 4.74,
      "learning_rate": 8.963279518835075e-05,
      "loss": 0.1117,
      "step": 2714
    },
    {
      "epoch": 4.94,
      "learning_rate": 8.926875593542262e-05,
      "loss": 0.1143,
      "step": 2760
    },
    {
      "epoch": 5.13,
      "learning_rate": 8.890471668249447e-05,
      "loss": 0.1041,
      "step": 2806
    },
    {
      "epoch": 5.33,
      "learning_rate": 8.854067742956632e-05,
      "loss": 0.1041,
      "step": 2852
    },
    {
      "epoch": 5.53,
      "learning_rate": 8.817663817663818e-05,
      "loss": 0.1205,
      "step": 2898
    },
    {
      "epoch": 5.72,
      "learning_rate": 8.781259892371004e-05,
      "loss": 0.1214,
      "step": 2944
    },
    {
      "epoch": 5.92,
      "learning_rate": 8.74485596707819e-05,
      "loss": 0.117,
      "step": 2990
    },
    {
      "epoch": 6.12,
      "learning_rate": 8.708452041785376e-05,
      "loss": 0.1115,
      "step": 3036
    },
    {
      "epoch": 4.03,
      "learning_rate": 8.672048116492562e-05,
      "loss": 0.106,
      "step": 3082
    },
    {
      "epoch": 4.22,
      "learning_rate": 8.635644191199747e-05,
      "loss": 0.0876,
      "step": 3128
    },
    {
      "epoch": 4.42,
      "learning_rate": 8.599240265906932e-05,
      "loss": 0.0827,
      "step": 3174
    },
    {
      "epoch": 4.62,
      "learning_rate": 8.562836340614119e-05,
      "loss": 0.0842,
      "step": 3220
    },
    {
      "epoch": 4.81,
      "learning_rate": 8.526432415321305e-05,
      "loss": 0.0933,
      "step": 3266
    },
    {
      "epoch": 5.01,
      "learning_rate": 8.490028490028491e-05,
      "loss": 0.0908,
      "step": 3312
    },
    {
      "epoch": 5.21,
      "learning_rate": 8.453624564735676e-05,
      "loss": 0.089,
      "step": 3358
    },
    {
      "epoch": 5.4,
      "learning_rate": 8.417220639442863e-05,
      "loss": 0.084,
      "step": 3404
    },
    {
      "epoch": 5.6,
      "learning_rate": 8.380816714150048e-05,
      "loss": 0.0745,
      "step": 3450
    },
    {
      "epoch": 5.79,
      "learning_rate": 8.344412788857233e-05,
      "loss": 0.0786,
      "step": 3496
    },
    {
      "epoch": 5.99,
      "learning_rate": 8.308008863564419e-05,
      "loss": 0.077,
      "step": 3542
    },
    {
      "epoch": 6.19,
      "learning_rate": 8.271604938271605e-05,
      "loss": 0.0882,
      "step": 3588
    },
    {
      "epoch": 6.38,
      "learning_rate": 8.235201012978792e-05,
      "loss": 0.0902,
      "step": 3634
    },
    {
      "epoch": 6.58,
      "learning_rate": 8.198797087685977e-05,
      "loss": 0.0879,
      "step": 3680
    },
    {
      "epoch": 6.78,
      "learning_rate": 8.162393162393163e-05,
      "loss": 0.0881,
      "step": 3726
    },
    {
      "epoch": 6.97,
      "learning_rate": 8.125989237100348e-05,
      "loss": 0.0955,
      "step": 3772
    },
    {
      "epoch": 7.17,
      "learning_rate": 8.089585311807535e-05,
      "loss": 0.0917,
      "step": 3818
    },
    {
      "epoch": 5.08,
      "learning_rate": 8.05318138651472e-05,
      "loss": 0.0851,
      "step": 3864
    },
    {
      "epoch": 5.28,
      "learning_rate": 8.016777461221906e-05,
      "loss": 0.0638,
      "step": 3910
    },
    {
      "epoch": 5.47,
      "learning_rate": 7.980373535929092e-05,
      "loss": 0.0795,
      "step": 3956
    },
    {
      "epoch": 5.67,
      "learning_rate": 7.943969610636279e-05,
      "loss": 0.0671,
      "step": 4002
    },
    {
      "epoch": 5.87,
      "learning_rate": 7.907565685343464e-05,
      "loss": 0.0779,
      "step": 4048
    },
    {
      "epoch": 6.06,
      "learning_rate": 7.871161760050649e-05,
      "loss": 0.0722,
      "step": 4094
    },
    {
      "epoch": 6.26,
      "learning_rate": 7.834757834757835e-05,
      "loss": 0.0594,
      "step": 4140
    },
    {
      "epoch": 6.46,
      "learning_rate": 7.79835390946502e-05,
      "loss": 0.0774,
      "step": 4186
    },
    {
      "epoch": 6.65,
      "learning_rate": 7.761949984172207e-05,
      "loss": 0.0727,
      "step": 4232
    },
    {
      "epoch": 6.85,
      "learning_rate": 7.725546058879393e-05,
      "loss": 0.0621,
      "step": 4278
    },
    {
      "epoch": 7.05,
      "learning_rate": 7.68914213358658e-05,
      "loss": 0.0619,
      "step": 4324
    },
    {
      "epoch": 7.24,
      "learning_rate": 7.652738208293764e-05,
      "loss": 0.0633,
      "step": 4370
    },
    {
      "epoch": 7.44,
      "learning_rate": 7.61633428300095e-05,
      "loss": 0.0585,
      "step": 4416
    },
    {
      "epoch": 7.64,
      "learning_rate": 7.579930357708136e-05,
      "loss": 0.0743,
      "step": 4462
    },
    {
      "epoch": 7.83,
      "learning_rate": 7.543526432415322e-05,
      "loss": 0.0751,
      "step": 4508
    },
    {
      "epoch": 8.03,
      "learning_rate": 7.507122507122507e-05,
      "loss": 0.0597,
      "step": 4554
    },
    {
      "epoch": 8.23,
      "learning_rate": 7.470718581829694e-05,
      "loss": 0.0692,
      "step": 4600
    },
    {
      "epoch": 6.14,
      "learning_rate": 7.43431465653688e-05,
      "loss": 0.0595,
      "step": 4646
    },
    {
      "epoch": 6.33,
      "learning_rate": 7.397910731244065e-05,
      "loss": 0.0505,
      "step": 4692
    },
    {
      "epoch": 6.53,
      "learning_rate": 7.36150680595125e-05,
      "loss": 0.0516,
      "step": 4738
    },
    {
      "epoch": 6.73,
      "learning_rate": 7.325102880658436e-05,
      "loss": 0.0577,
      "step": 4784
    },
    {
      "epoch": 6.92,
      "learning_rate": 7.288698955365623e-05,
      "loss": 0.0546,
      "step": 4830
    },
    {
      "epoch": 7.12,
      "learning_rate": 7.252295030072809e-05,
      "loss": 0.0472,
      "step": 4876
    },
    {
      "epoch": 7.32,
      "learning_rate": 7.215891104779994e-05,
      "loss": 0.0565,
      "step": 4922
    },
    {
      "epoch": 7.51,
      "learning_rate": 7.17948717948718e-05,
      "loss": 0.0545,
      "step": 4968
    },
    {
      "epoch": 7.71,
      "learning_rate": 7.143083254194365e-05,
      "loss": 0.0399,
      "step": 5014
    },
    {
      "epoch": 7.91,
      "learning_rate": 7.10667932890155e-05,
      "loss": 0.0536,
      "step": 5060
    },
    {
      "epoch": 8.1,
      "learning_rate": 7.070275403608737e-05,
      "loss": 0.0567,
      "step": 5106
    },
    {
      "epoch": 8.3,
      "learning_rate": 7.033871478315923e-05,
      "loss": 0.0608,
      "step": 5152
    },
    {
      "epoch": 8.5,
      "learning_rate": 6.99746755302311e-05,
      "loss": 0.0517,
      "step": 5198
    },
    {
      "epoch": 8.69,
      "learning_rate": 6.961063627730295e-05,
      "loss": 0.0514,
      "step": 5244
    },
    {
      "epoch": 8.89,
      "learning_rate": 6.924659702437481e-05,
      "loss": 0.0525,
      "step": 5290
    },
    {
      "epoch": 9.09,
      "learning_rate": 6.888255777144666e-05,
      "loss": 0.0554,
      "step": 5336
    },
    {
      "epoch": 9.28,
      "learning_rate": 6.851851851851852e-05,
      "loss": 0.0696,
      "step": 5382
    },
    {
      "epoch": 7.19,
      "learning_rate": 6.815447926559037e-05,
      "loss": 0.0358,
      "step": 5428
    },
    {
      "epoch": 7.39,
      "learning_rate": 6.779044001266224e-05,
      "loss": 0.0413,
      "step": 5474
    },
    {
      "epoch": 7.59,
      "learning_rate": 6.74264007597341e-05,
      "loss": 0.0358,
      "step": 5520
    },
    {
      "epoch": 7.78,
      "learning_rate": 6.706236150680597e-05,
      "loss": 0.0483,
      "step": 5566
    },
    {
      "epoch": 7.98,
      "learning_rate": 6.669832225387782e-05,
      "loss": 0.039,
      "step": 5612
    },
    {
      "epoch": 8.18,
      "learning_rate": 6.633428300094967e-05,
      "loss": 0.0381,
      "step": 5658
    },
    {
      "epoch": 8.37,
      "learning_rate": 6.597024374802153e-05,
      "loss": 0.0502,
      "step": 5704
    },
    {
      "epoch": 8.57,
      "learning_rate": 6.560620449509338e-05,
      "loss": 0.0421,
      "step": 5750
    },
    {
      "epoch": 8.76,
      "learning_rate": 6.524216524216524e-05,
      "loss": 0.0447,
      "step": 5796
    },
    {
      "epoch": 8.96,
      "learning_rate": 6.487812598923711e-05,
      "loss": 0.0406,
      "step": 5842
    },
    {
      "epoch": 9.16,
      "learning_rate": 6.451408673630897e-05,
      "loss": 0.0446,
      "step": 5888
    },
    {
      "epoch": 9.35,
      "learning_rate": 6.415004748338082e-05,
      "loss": 0.0483,
      "step": 5934
    },
    {
      "epoch": 9.55,
      "learning_rate": 6.378600823045267e-05,
      "loss": 0.0432,
      "step": 5980
    },
    {
      "epoch": 9.75,
      "learning_rate": 6.342196897752454e-05,
      "loss": 0.0483,
      "step": 6026
    },
    {
      "epoch": 9.94,
      "learning_rate": 6.30579297245964e-05,
      "loss": 0.0493,
      "step": 6072
    },
    {
      "epoch": 10.14,
      "learning_rate": 6.269389047166825e-05,
      "loss": 0.0448,
      "step": 6118
    },
    {
      "epoch": 8.05,
      "learning_rate": 6.232985121874011e-05,
      "loss": 0.037,
      "step": 6164
    },
    {
      "epoch": 8.25,
      "learning_rate": 6.196581196581198e-05,
      "loss": 0.0319,
      "step": 6210
    },
    {
      "epoch": 8.44,
      "learning_rate": 6.160177271288383e-05,
      "loss": 0.0341,
      "step": 6256
    },
    {
      "epoch": 8.64,
      "learning_rate": 6.123773345995568e-05,
      "loss": 0.0322,
      "step": 6302
    },
    {
      "epoch": 8.84,
      "learning_rate": 6.087369420702754e-05,
      "loss": 0.0375,
      "step": 6348
    },
    {
      "epoch": 9.03,
      "learning_rate": 6.0509654954099404e-05,
      "loss": 0.0291,
      "step": 6394
    },
    {
      "epoch": 9.23,
      "learning_rate": 6.014561570117127e-05,
      "loss": 0.0322,
      "step": 6440
    },
    {
      "epoch": 9.43,
      "learning_rate": 5.978157644824312e-05,
      "loss": 0.0315,
      "step": 6486
    },
    {
      "epoch": 9.62,
      "learning_rate": 5.9417537195314975e-05,
      "loss": 0.0341,
      "step": 6532
    },
    {
      "epoch": 9.82,
      "learning_rate": 5.905349794238684e-05,
      "loss": 0.0314,
      "step": 6578
    },
    {
      "epoch": 10.02,
      "learning_rate": 5.868945868945869e-05,
      "loss": 0.0338,
      "step": 6624
    },
    {
      "epoch": 10.21,
      "learning_rate": 5.8325419436530546e-05,
      "loss": 0.0311,
      "step": 6670
    },
    {
      "epoch": 10.41,
      "learning_rate": 5.796138018360241e-05,
      "loss": 0.0335,
      "step": 6716
    },
    {
      "epoch": 10.61,
      "learning_rate": 5.7597340930674274e-05,
      "loss": 0.0409,
      "step": 6762
    },
    {
      "epoch": 10.8,
      "learning_rate": 5.7233301677746124e-05,
      "loss": 0.0332,
      "step": 6808
    },
    {
      "epoch": 11.0,
      "learning_rate": 5.686926242481798e-05,
      "loss": 0.0456,
      "step": 6854
    },
    {
      "epoch": 11.2,
      "learning_rate": 5.6505223171889845e-05,
      "loss": 0.0311,
      "step": 6900
    },
    {
      "epoch": 9.11,
      "learning_rate": 5.61411839189617e-05,
      "loss": 0.0331,
      "step": 6946
    },
    {
      "epoch": 9.3,
      "learning_rate": 5.577714466603355e-05,
      "loss": 0.0234,
      "step": 6992
    },
    {
      "epoch": 9.5,
      "learning_rate": 5.5413105413105416e-05,
      "loss": 0.0214,
      "step": 7038
    },
    {
      "epoch": 9.7,
      "learning_rate": 5.504906616017728e-05,
      "loss": 0.0266,
      "step": 7084
    },
    {
      "epoch": 9.89,
      "learning_rate": 5.4685026907249136e-05,
      "loss": 0.0279,
      "step": 7130
    },
    {
      "epoch": 10.09,
      "learning_rate": 5.4320987654320986e-05,
      "loss": 0.0256,
      "step": 7176
    },
    {
      "epoch": 10.29,
      "learning_rate": 5.395694840139285e-05,
      "loss": 0.0256,
      "step": 7222
    },
    {
      "epoch": 10.48,
      "learning_rate": 5.359290914846471e-05,
      "loss": 0.0277,
      "step": 7268
    },
    {
      "epoch": 10.68,
      "learning_rate": 5.322886989553656e-05,
      "loss": 0.0237,
      "step": 7314
    },
    {
      "epoch": 10.88,
      "learning_rate": 5.286483064260842e-05,
      "loss": 0.0286,
      "step": 7360
    },
    {
      "epoch": 11.07,
      "learning_rate": 5.2500791389680285e-05,
      "loss": 0.0285,
      "step": 7406
    },
    {
      "epoch": 11.27,
      "learning_rate": 5.213675213675214e-05,
      "loss": 0.0325,
      "step": 7452
    },
    {
      "epoch": 11.47,
      "learning_rate": 5.177271288382399e-05,
      "loss": 0.0345,
      "step": 7498
    },
    {
      "epoch": 11.66,
      "learning_rate": 5.1408673630895856e-05,
      "loss": 0.0254,
      "step": 7544
    },
    {
      "epoch": 11.86,
      "learning_rate": 5.104463437796771e-05,
      "loss": 0.0277,
      "step": 7590
    },
    {
      "epoch": 12.06,
      "learning_rate": 5.0680595125039577e-05,
      "loss": 0.0242,
      "step": 7636
    },
    {
      "epoch": 12.25,
      "learning_rate": 5.031655587211143e-05,
      "loss": 0.0277,
      "step": 7682
    },
    {
      "epoch": 10.16,
      "learning_rate": 4.995251661918329e-05,
      "loss": 0.0188,
      "step": 7728
    },
    {
      "epoch": 10.36,
      "learning_rate": 4.958847736625515e-05,
      "loss": 0.0218,
      "step": 7774
    },
    {
      "epoch": 10.56,
      "learning_rate": 4.9224438113327004e-05,
      "loss": 0.0244,
      "step": 7820
    },
    {
      "epoch": 10.75,
      "learning_rate": 4.886039886039887e-05,
      "loss": 0.0204,
      "step": 7866
    },
    {
      "epoch": 10.95,
      "learning_rate": 4.849635960747072e-05,
      "loss": 0.0224,
      "step": 7912
    },
    {
      "epoch": 11.15,
      "learning_rate": 4.813232035454258e-05,
      "loss": 0.0205,
      "step": 7958
    },
    {
      "epoch": 11.34,
      "learning_rate": 4.776828110161444e-05,
      "loss": 0.027,
      "step": 8004
    },
    {
      "epoch": 11.54,
      "learning_rate": 4.7404241848686296e-05,
      "loss": 0.0183,
      "step": 8050
    },
    {
      "epoch": 11.74,
      "learning_rate": 4.704020259575815e-05,
      "loss": 0.0199,
      "step": 8096
    },
    {
      "epoch": 11.93,
      "learning_rate": 4.667616334283001e-05,
      "loss": 0.0227,
      "step": 8142
    },
    {
      "epoch": 12.13,
      "learning_rate": 4.6312124089901874e-05,
      "loss": 0.0232,
      "step": 8188
    },
    {
      "epoch": 12.32,
      "learning_rate": 4.5948084836973724e-05,
      "loss": 0.0221,
      "step": 8234
    },
    {
      "epoch": 12.52,
      "learning_rate": 4.558404558404559e-05,
      "loss": 0.0207,
      "step": 8280
    },
    {
      "epoch": 12.72,
      "learning_rate": 4.5220006331117445e-05,
      "loss": 0.0213,
      "step": 8326
    },
    {
      "epoch": 12.91,
      "learning_rate": 4.48559670781893e-05,
      "loss": 0.0201,
      "step": 8372
    },
    {
      "epoch": 13.11,
      "learning_rate": 4.449192782526116e-05,
      "loss": 0.0196,
      "step": 8418
    },
    {
      "epoch": 11.02,
      "learning_rate": 4.412788857233302e-05,
      "loss": 0.0197,
      "step": 8464
    },
    {
      "epoch": 11.22,
      "learning_rate": 4.376384931940488e-05,
      "loss": 0.0154,
      "step": 8510
    },
    {
      "epoch": 11.41,
      "learning_rate": 4.3399810066476736e-05,
      "loss": 0.0177,
      "step": 8556
    },
    {
      "epoch": 11.61,
      "learning_rate": 4.303577081354859e-05,
      "loss": 0.0158,
      "step": 8602
    },
    {
      "epoch": 11.81,
      "learning_rate": 4.267173156062046e-05,
      "loss": 0.0158,
      "step": 8648
    },
    {
      "epoch": 12.0,
      "learning_rate": 4.230769230769231e-05,
      "loss": 0.0163,
      "step": 8694
    },
    {
      "epoch": 12.2,
      "learning_rate": 4.194365305476417e-05,
      "loss": 0.0184,
      "step": 8740
    },
    {
      "epoch": 12.4,
      "learning_rate": 4.157961380183603e-05,
      "loss": 0.016,
      "step": 8786
    },
    {
      "epoch": 12.59,
      "learning_rate": 4.1215574548907885e-05,
      "loss": 0.0154,
      "step": 8832
    },
    {
      "epoch": 12.79,
      "learning_rate": 4.085153529597974e-05,
      "loss": 0.0168,
      "step": 8878
    },
    {
      "epoch": 12.99,
      "learning_rate": 4.04874960430516e-05,
      "loss": 0.0165,
      "step": 8924
    },
    {
      "epoch": 13.18,
      "learning_rate": 4.012345679012346e-05,
      "loss": 0.0143,
      "step": 8970
    },
    {
      "epoch": 13.38,
      "learning_rate": 3.975941753719531e-05,
      "loss": 0.0188,
      "step": 9016
    },
    {
      "epoch": 13.58,
      "learning_rate": 3.9395378284267176e-05,
      "loss": 0.0159,
      "step": 9062
    },
    {
      "epoch": 13.77,
      "learning_rate": 3.903133903133903e-05,
      "loss": 0.0192,
      "step": 9108
    },
    {
      "epoch": 13.97,
      "learning_rate": 3.866729977841089e-05,
      "loss": 0.018,
      "step": 9154
    },
    {
      "epoch": 14.17,
      "learning_rate": 3.830326052548275e-05,
      "loss": 0.0194,
      "step": 9200
    },
    {
      "epoch": 12.08,
      "learning_rate": 3.793922127255461e-05,
      "loss": 0.0139,
      "step": 9246
    },
    {
      "epoch": 12.27,
      "learning_rate": 3.757518201962647e-05,
      "loss": 0.0122,
      "step": 9292
    },
    {
      "epoch": 12.47,
      "learning_rate": 3.7211142766698325e-05,
      "loss": 0.015,
      "step": 9338
    },
    {
      "epoch": 12.67,
      "learning_rate": 3.684710351377018e-05,
      "loss": 0.0112,
      "step": 9384
    },
    {
      "epoch": 12.86,
      "learning_rate": 3.6483064260842046e-05,
      "loss": 0.0134,
      "step": 9430
    },
    {
      "epoch": 13.06,
      "learning_rate": 3.6119025007913896e-05,
      "loss": 0.0139,
      "step": 9476
    },
    {
      "epoch": 13.26,
      "learning_rate": 3.575498575498576e-05,
      "loss": 0.0129,
      "step": 9522
    },
    {
      "epoch": 13.45,
      "learning_rate": 3.539094650205762e-05,
      "loss": 0.0147,
      "step": 9568
    },
    {
      "epoch": 13.65,
      "learning_rate": 3.5026907249129474e-05,
      "loss": 0.0133,
      "step": 9614
    },
    {
      "epoch": 13.85,
      "learning_rate": 3.466286799620133e-05,
      "loss": 0.0135,
      "step": 9660
    },
    {
      "epoch": 14.04,
      "learning_rate": 3.429882874327319e-05,
      "loss": 0.015,
      "step": 9706
    },
    {
      "epoch": 14.24,
      "learning_rate": 3.393478949034505e-05,
      "loss": 0.0128,
      "step": 9752
    },
    {
      "epoch": 14.44,
      "learning_rate": 3.35707502374169e-05,
      "loss": 0.0135,
      "step": 9798
    },
    {
      "epoch": 14.63,
      "learning_rate": 3.3206710984488765e-05,
      "loss": 0.0137,
      "step": 9844
    },
    {
      "epoch": 14.83,
      "learning_rate": 3.284267173156062e-05,
      "loss": 0.013,
      "step": 9890
    },
    {
      "epoch": 15.03,
      "learning_rate": 3.247863247863248e-05,
      "loss": 0.0157,
      "step": 9936
    },
    {
      "epoch": 15.22,
      "learning_rate": 3.2114593225704336e-05,
      "loss": 0.0139,
      "step": 9982
    },
    {
      "epoch": 13.13,
      "learning_rate": 3.17505539727762e-05,
      "loss": 0.0103,
      "step": 10028
    },
    {
      "epoch": 13.33,
      "learning_rate": 3.138651471984806e-05,
      "loss": 0.0095,
      "step": 10074
    },
    {
      "epoch": 13.53,
      "learning_rate": 3.1022475466919914e-05,
      "loss": 0.0114,
      "step": 10120
    },
    {
      "epoch": 13.72,
      "learning_rate": 3.065843621399177e-05,
      "loss": 0.0114,
      "step": 10166
    },
    {
      "epoch": 13.92,
      "learning_rate": 3.029439696106363e-05,
      "loss": 0.0097,
      "step": 10212
    },
    {
      "epoch": 14.12,
      "learning_rate": 2.9930357708135488e-05,
      "loss": 0.0094,
      "step": 10258
    },
    {
      "epoch": 14.31,
      "learning_rate": 2.956631845520735e-05,
      "loss": 0.0109,
      "step": 10304
    },
    {
      "epoch": 14.51,
      "learning_rate": 2.9202279202279202e-05,
      "loss": 0.0105,
      "step": 10350
    },
    {
      "epoch": 14.71,
      "learning_rate": 2.883823994935106e-05,
      "loss": 0.0103,
      "step": 10396
    },
    {
      "epoch": 14.9,
      "learning_rate": 2.847420069642292e-05,
      "loss": 0.0111,
      "step": 10442
    },
    {
      "epoch": 15.1,
      "learning_rate": 2.8110161443494776e-05,
      "loss": 0.012,
      "step": 10488
    },
    {
      "epoch": 15.29,
      "learning_rate": 2.7746122190566637e-05,
      "loss": 0.0104,
      "step": 10534
    },
    {
      "epoch": 15.49,
      "learning_rate": 2.7382082937638494e-05,
      "loss": 0.0105,
      "step": 10580
    },
    {
      "epoch": 15.69,
      "learning_rate": 2.7018043684710354e-05,
      "loss": 0.0096,
      "step": 10626
    },
    {
      "epoch": 15.88,
      "learning_rate": 2.6654004431782208e-05,
      "loss": 0.0126,
      "step": 10672
    },
    {
      "epoch": 16.08,
      "learning_rate": 2.628996517885407e-05,
      "loss": 0.012,
      "step": 10718
    },
    {
      "epoch": 16.28,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.0091,
      "step": 10764
    },
    {
      "epoch": 14.19,
      "learning_rate": 2.5561886672997785e-05,
      "loss": 0.0086,
      "step": 10810
    },
    {
      "epoch": 14.38,
      "learning_rate": 2.5197847420069642e-05,
      "loss": 0.0095,
      "step": 10856
    },
    {
      "epoch": 14.58,
      "learning_rate": 2.48338081671415e-05,
      "loss": 0.0074,
      "step": 10902
    },
    {
      "epoch": 14.78,
      "learning_rate": 2.446976891421336e-05,
      "loss": 0.0085,
      "step": 10948
    },
    {
      "epoch": 14.97,
      "learning_rate": 2.4105729661285217e-05,
      "loss": 0.0092,
      "step": 10994
    },
    {
      "epoch": 15.17,
      "learning_rate": 2.3741690408357077e-05,
      "loss": 0.0078,
      "step": 11040
    },
    {
      "epoch": 15.37,
      "learning_rate": 2.3377651155428934e-05,
      "loss": 0.0089,
      "step": 11086
    },
    {
      "epoch": 15.56,
      "learning_rate": 2.301361190250079e-05,
      "loss": 0.0083,
      "step": 11132
    },
    {
      "epoch": 15.76,
      "learning_rate": 2.264957264957265e-05,
      "loss": 0.0079,
      "step": 11178
    },
    {
      "epoch": 15.96,
      "learning_rate": 2.2285533396644508e-05,
      "loss": 0.0091,
      "step": 11224
    },
    {
      "epoch": 16.15,
      "learning_rate": 2.192149414371637e-05,
      "loss": 0.0082,
      "step": 11270
    },
    {
      "epoch": 16.35,
      "learning_rate": 2.1557454890788225e-05,
      "loss": 0.0084,
      "step": 11316
    },
    {
      "epoch": 16.55,
      "learning_rate": 2.1193415637860082e-05,
      "loss": 0.0087,
      "step": 11362
    },
    {
      "epoch": 16.74,
      "learning_rate": 2.0829376384931943e-05,
      "loss": 0.0088,
      "step": 11408
    },
    {
      "epoch": 16.94,
      "learning_rate": 2.04653371320038e-05,
      "loss": 0.0098,
      "step": 11454
    },
    {
      "epoch": 17.14,
      "learning_rate": 2.010129787907566e-05,
      "loss": 0.0087,
      "step": 11500
    },
    {
      "epoch": 15.05,
      "learning_rate": 1.9737258626147517e-05,
      "loss": 0.0087,
      "step": 11546
    },
    {
      "epoch": 15.24,
      "learning_rate": 1.9373219373219374e-05,
      "loss": 0.0066,
      "step": 11592
    },
    {
      "epoch": 15.44,
      "learning_rate": 1.900918012029123e-05,
      "loss": 0.0071,
      "step": 11638
    },
    {
      "epoch": 15.64,
      "learning_rate": 1.8645140867363088e-05,
      "loss": 0.0079,
      "step": 11684
    },
    {
      "epoch": 15.83,
      "learning_rate": 1.828110161443495e-05,
      "loss": 0.0074,
      "step": 11730
    },
    {
      "epoch": 16.03,
      "learning_rate": 1.7917062361506805e-05,
      "loss": 0.0069,
      "step": 11776
    },
    {
      "epoch": 16.23,
      "learning_rate": 1.7553023108578666e-05,
      "loss": 0.0063,
      "step": 11822
    },
    {
      "epoch": 16.42,
      "learning_rate": 1.7188983855650523e-05,
      "loss": 0.0075,
      "step": 11868
    },
    {
      "epoch": 16.62,
      "learning_rate": 1.682494460272238e-05,
      "loss": 0.0074,
      "step": 11914
    },
    {
      "epoch": 16.82,
      "learning_rate": 1.646090534979424e-05,
      "loss": 0.0067,
      "step": 11960
    },
    {
      "epoch": 17.01,
      "learning_rate": 1.6096866096866097e-05,
      "loss": 0.0064,
      "step": 12006
    },
    {
      "epoch": 17.21,
      "learning_rate": 1.5732826843937957e-05,
      "loss": 0.0068,
      "step": 12052
    },
    {
      "epoch": 17.41,
      "learning_rate": 1.5368787591009814e-05,
      "loss": 0.0076,
      "step": 12098
    },
    {
      "epoch": 17.6,
      "learning_rate": 1.5004748338081673e-05,
      "loss": 0.0069,
      "step": 12144
    },
    {
      "epoch": 17.8,
      "learning_rate": 1.4640709085153532e-05,
      "loss": 0.0075,
      "step": 12190
    },
    {
      "epoch": 18.0,
      "learning_rate": 1.427666983222539e-05,
      "loss": 0.0072,
      "step": 12236
    },
    {
      "epoch": 18.19,
      "learning_rate": 1.3912630579297247e-05,
      "loss": 0.0066,
      "step": 12282
    },
    {
      "epoch": 16.1,
      "learning_rate": 1.3548591326369106e-05,
      "loss": 0.0069,
      "step": 12328
    },
    {
      "epoch": 16.3,
      "learning_rate": 1.3184552073440961e-05,
      "loss": 0.0052,
      "step": 12374
    },
    {
      "epoch": 16.5,
      "learning_rate": 1.282051282051282e-05,
      "loss": 0.0064,
      "step": 12420
    },
    {
      "epoch": 16.69,
      "learning_rate": 1.245647356758468e-05,
      "loss": 0.0063,
      "step": 12466
    },
    {
      "epoch": 16.89,
      "learning_rate": 1.2092434314656539e-05,
      "loss": 0.006,
      "step": 12512
    },
    {
      "epoch": 17.09,
      "learning_rate": 1.1728395061728396e-05,
      "loss": 0.0057,
      "step": 12558
    },
    {
      "epoch": 17.28,
      "learning_rate": 1.1364355808800253e-05,
      "loss": 0.0061,
      "step": 12604
    },
    {
      "epoch": 17.48,
      "learning_rate": 1.1000316555872111e-05,
      "loss": 0.0055,
      "step": 12650
    },
    {
      "epoch": 17.68,
      "learning_rate": 1.063627730294397e-05,
      "loss": 0.0053,
      "step": 12696
    },
    {
      "epoch": 17.87,
      "learning_rate": 1.0272238050015829e-05,
      "loss": 0.0051,
      "step": 12742
    },
    {
      "epoch": 18.07,
      "learning_rate": 9.908198797087687e-06,
      "loss": 0.0064,
      "step": 12788
    },
    {
      "epoch": 18.26,
      "learning_rate": 9.544159544159544e-06,
      "loss": 0.0056,
      "step": 12834
    },
    {
      "epoch": 18.46,
      "learning_rate": 9.180120291231403e-06,
      "loss": 0.0062,
      "step": 12880
    },
    {
      "epoch": 18.66,
      "learning_rate": 8.816081038303262e-06,
      "loss": 0.0065,
      "step": 12926
    },
    {
      "epoch": 18.85,
      "learning_rate": 8.452041785375119e-06,
      "loss": 0.0065,
      "step": 12972
    },
    {
      "epoch": 19.05,
      "learning_rate": 8.088002532446977e-06,
      "loss": 0.0064,
      "step": 13018
    },
    {
      "epoch": 19.25,
      "learning_rate": 7.723963279518836e-06,
      "loss": 0.0062,
      "step": 13064
    },
    {
      "epoch": 17.16,
      "learning_rate": 7.359924026590694e-06,
      "loss": 0.0055,
      "step": 13110
    },
    {
      "epoch": 17.35,
      "learning_rate": 6.995884773662552e-06,
      "loss": 0.0046,
      "step": 13156
    },
    {
      "epoch": 17.55,
      "learning_rate": 6.63184552073441e-06,
      "loss": 0.0049,
      "step": 13202
    },
    {
      "epoch": 17.75,
      "learning_rate": 6.267806267806268e-06,
      "loss": 0.0044,
      "step": 13248
    },
    {
      "epoch": 17.94,
      "learning_rate": 5.903767014878126e-06,
      "loss": 0.0057,
      "step": 13294
    },
    {
      "epoch": 18.14,
      "learning_rate": 5.539727761949985e-06,
      "loss": 0.0047,
      "step": 13340
    },
    {
      "epoch": 18.34,
      "learning_rate": 5.175688509021842e-06,
      "loss": 0.0048,
      "step": 13386
    },
    {
      "epoch": 18.53,
      "learning_rate": 4.8116492560937e-06,
      "loss": 0.0051,
      "step": 13432
    },
    {
      "epoch": 18.73,
      "learning_rate": 4.447610003165559e-06,
      "loss": 0.0056,
      "step": 13478
    },
    {
      "epoch": 18.93,
      "learning_rate": 4.083570750237417e-06,
      "loss": 0.0051,
      "step": 13524
    },
    {
      "epoch": 19.12,
      "learning_rate": 3.7195314973092754e-06,
      "loss": 0.0052,
      "step": 13570
    },
    {
      "epoch": 19.32,
      "learning_rate": 3.3554922443811336e-06,
      "loss": 0.0068,
      "step": 13616
    },
    {
      "epoch": 19.52,
      "learning_rate": 2.991452991452992e-06,
      "loss": 0.0064,
      "step": 13662
    },
    {
      "epoch": 19.71,
      "learning_rate": 2.6274137385248497e-06,
      "loss": 0.0055,
      "step": 13708
    },
    {
      "epoch": 19.91,
      "learning_rate": 2.263374485596708e-06,
      "loss": 0.0056,
      "step": 13754
    },
    {
      "epoch": 20.11,
      "learning_rate": 1.899335232668566e-06,
      "loss": 0.0052,
      "step": 13800
    },
    {
      "epoch": 18.02,
      "learning_rate": 1.5352959797404244e-06,
      "loss": 0.0051,
      "step": 13846
    },
    {
      "epoch": 18.21,
      "learning_rate": 1.1712567268122824e-06,
      "loss": 0.0052,
      "step": 13892
    },
    {
      "epoch": 18.41,
      "learning_rate": 8.072174738841407e-07,
      "loss": 0.0053,
      "step": 13938
    },
    {
      "epoch": 18.61,
      "learning_rate": 4.4317822095599874e-07,
      "loss": 0.0043,
      "step": 13984
    },
    {
      "epoch": 18.8,
      "learning_rate": 7.913896802785692e-08,
      "loss": 0.0046,
      "step": 14030
    }
  ],
  "logging_steps": 46,
  "max_steps": 14040,
  "num_train_epochs": 60,
  "save_steps": 500,
  "total_flos": 6.139659927158784e+17,
  "trial_name": null,
  "trial_params": null
}