{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 16.72936660268714,
  "eval_steps": 500,
  "global_step": 31260,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 3.326935380678183e-06,
      "loss": 0.9276,
      "step": 104
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.653870761356366e-06,
      "loss": 0.8349,
      "step": 208
    },
    {
      "epoch": 0.6,
      "learning_rate": 9.948816378758798e-06,
      "loss": 0.7345,
      "step": 312
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.3243761996161231e-05,
      "loss": 0.6139,
      "step": 416
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.657069737683941e-05,
      "loss": 0.495,
      "step": 520
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.9897632757517596e-05,
      "loss": 0.4694,
      "step": 624
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.322456813819578e-05,
      "loss": 0.4558,
      "step": 728
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.6551503518873962e-05,
      "loss": 0.402,
      "step": 832
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.9878438899552147e-05,
      "loss": 0.3865,
      "step": 936
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.320537428023033e-05,
      "loss": 0.3576,
      "step": 1040
    },
    {
      "epoch": 2.2,
      "learning_rate": 3.653230966090851e-05,
      "loss": 0.3395,
      "step": 1144
    },
    {
      "epoch": 2.4,
      "learning_rate": 3.98592450415867e-05,
      "loss": 0.355,
      "step": 1248
    },
    {
      "epoch": 2.6,
      "learning_rate": 4.318618042226488e-05,
      "loss": 0.3237,
      "step": 1352
    },
    {
      "epoch": 2.79,
      "learning_rate": 4.651311580294306e-05,
      "loss": 0.3006,
      "step": 1456
    },
    {
      "epoch": 2.99,
      "learning_rate": 4.984005118362124e-05,
      "loss": 0.3352,
      "step": 1560
    },
    {
      "epoch": 3.19,
      "learning_rate": 5.3166986564299424e-05,
      "loss": 0.2761,
      "step": 1664
    },
    {
      "epoch": 3.39,
      "learning_rate": 5.649392194497761e-05,
      "loss": 0.2918,
      "step": 1768
    },
    {
      "epoch": 3.59,
      "learning_rate": 5.982085732565579e-05,
      "loss": 0.2906,
      "step": 1872
    },
    {
      "epoch": 1.09,
      "learning_rate": 6.314779270633397e-05,
      "loss": 0.2698,
      "step": 1976
    },
    {
      "epoch": 1.29,
      "learning_rate": 6.647472808701216e-05,
      "loss": 0.2749,
      "step": 2080
    },
    {
      "epoch": 1.49,
      "learning_rate": 6.980166346769034e-05,
      "loss": 0.2739,
      "step": 2184
    },
    {
      "epoch": 1.69,
      "learning_rate": 7.312859884836853e-05,
      "loss": 0.2477,
      "step": 2288
    },
    {
      "epoch": 1.89,
      "learning_rate": 7.645553422904671e-05,
      "loss": 0.2419,
      "step": 2392
    },
    {
      "epoch": 2.09,
      "learning_rate": 7.97824696097249e-05,
      "loss": 0.2501,
      "step": 2496
    },
    {
      "epoch": 2.29,
      "learning_rate": 8.310940499040308e-05,
      "loss": 0.2325,
      "step": 2600
    },
    {
      "epoch": 2.49,
      "learning_rate": 8.643634037108127e-05,
      "loss": 0.215,
      "step": 2704
    },
    {
      "epoch": 2.69,
      "learning_rate": 8.976327575175944e-05,
      "loss": 0.2277,
      "step": 2808
    },
    {
      "epoch": 2.88,
      "learning_rate": 9.309021113243761e-05,
      "loss": 0.2002,
      "step": 2912
    },
    {
      "epoch": 3.08,
      "learning_rate": 9.638515674984006e-05,
      "loss": 0.2191,
      "step": 3016
    },
    {
      "epoch": 3.28,
      "learning_rate": 9.971209213051824e-05,
      "loss": 0.1843,
      "step": 3120
    },
    {
      "epoch": 3.48,
      "learning_rate": 9.966588469467548e-05,
      "loss": 0.2207,
      "step": 3224
    },
    {
      "epoch": 3.68,
      "learning_rate": 9.929622520793347e-05,
      "loss": 0.2072,
      "step": 3328
    },
    {
      "epoch": 3.88,
      "learning_rate": 9.892656572119144e-05,
      "loss": 0.191,
      "step": 3432
    },
    {
      "epoch": 4.08,
      "learning_rate": 9.855690623444942e-05,
      "loss": 0.2003,
      "step": 3536
    },
    {
      "epoch": 4.28,
      "learning_rate": 9.81872467477074e-05,
      "loss": 0.187,
      "step": 3640
    },
    {
      "epoch": 4.48,
      "learning_rate": 9.781758726096538e-05,
      "loss": 0.1657,
      "step": 3744
    },
    {
      "epoch": 4.68,
      "learning_rate": 9.744792777422336e-05,
      "loss": 0.185,
      "step": 3848
    },
    {
      "epoch": 2.18,
      "learning_rate": 9.707826828748135e-05,
      "loss": 0.166,
      "step": 3952
    },
    {
      "epoch": 2.38,
      "learning_rate": 9.670860880073932e-05,
      "loss": 0.1557,
      "step": 4056
    },
    {
      "epoch": 2.58,
      "learning_rate": 9.633894931399731e-05,
      "loss": 0.1519,
      "step": 4160
    },
    {
      "epoch": 2.78,
      "learning_rate": 9.596928982725528e-05,
      "loss": 0.1572,
      "step": 4264
    },
    {
      "epoch": 2.98,
      "learning_rate": 9.559963034051326e-05,
      "loss": 0.1578,
      "step": 4368
    },
    {
      "epoch": 3.17,
      "learning_rate": 9.522997085377124e-05,
      "loss": 0.1465,
      "step": 4472
    },
    {
      "epoch": 3.37,
      "learning_rate": 9.486031136702922e-05,
      "loss": 0.1508,
      "step": 4576
    },
    {
      "epoch": 3.57,
      "learning_rate": 9.44906518802872e-05,
      "loss": 0.154,
      "step": 4680
    },
    {
      "epoch": 3.77,
      "learning_rate": 9.412099239354518e-05,
      "loss": 0.1574,
      "step": 4784
    },
    {
      "epoch": 3.97,
      "learning_rate": 9.375133290680316e-05,
      "loss": 0.1455,
      "step": 4888
    },
    {
      "epoch": 4.17,
      "learning_rate": 9.338167342006115e-05,
      "loss": 0.1587,
      "step": 4992
    },
    {
      "epoch": 4.37,
      "learning_rate": 9.301201393331912e-05,
      "loss": 0.1352,
      "step": 5096
    },
    {
      "epoch": 4.57,
      "learning_rate": 9.26423544465771e-05,
      "loss": 0.119,
      "step": 5200
    },
    {
      "epoch": 4.77,
      "learning_rate": 9.227269495983508e-05,
      "loss": 0.1299,
      "step": 5304
    },
    {
      "epoch": 4.97,
      "learning_rate": 9.190303547309305e-05,
      "loss": 0.1246,
      "step": 5408
    },
    {
      "epoch": 5.17,
      "learning_rate": 9.153337598635103e-05,
      "loss": 0.1273,
      "step": 5512
    },
    {
      "epoch": 5.37,
      "learning_rate": 9.116371649960901e-05,
      "loss": 0.1236,
      "step": 5616
    },
    {
      "epoch": 5.57,
      "learning_rate": 9.0794057012867e-05,
      "loss": 0.1307,
      "step": 5720
    },
    {
      "epoch": 3.07,
      "learning_rate": 9.042439752612499e-05,
      "loss": 0.1286,
      "step": 5824
    },
    {
      "epoch": 3.26,
      "learning_rate": 9.005473803938296e-05,
      "loss": 0.1071,
      "step": 5928
    },
    {
      "epoch": 3.46,
      "learning_rate": 8.968507855264093e-05,
      "loss": 0.111,
      "step": 6032
    },
    {
      "epoch": 3.66,
      "learning_rate": 8.931541906589892e-05,
      "loss": 0.109,
      "step": 6136
    },
    {
      "epoch": 3.86,
      "learning_rate": 8.894575957915689e-05,
      "loss": 0.1136,
      "step": 6240
    },
    {
      "epoch": 4.06,
      "learning_rate": 8.857610009241487e-05,
      "loss": 0.1069,
      "step": 6344
    },
    {
      "epoch": 4.26,
      "learning_rate": 8.820644060567285e-05,
      "loss": 0.1136,
      "step": 6448
    },
    {
      "epoch": 4.46,
      "learning_rate": 8.783678111893084e-05,
      "loss": 0.1115,
      "step": 6552
    },
    {
      "epoch": 4.66,
      "learning_rate": 8.746712163218883e-05,
      "loss": 0.0999,
      "step": 6656
    },
    {
      "epoch": 4.86,
      "learning_rate": 8.70974621454468e-05,
      "loss": 0.0966,
      "step": 6760
    },
    {
      "epoch": 5.06,
      "learning_rate": 8.672780265870477e-05,
      "loss": 0.1099,
      "step": 6864
    },
    {
      "epoch": 5.26,
      "learning_rate": 8.635814317196276e-05,
      "loss": 0.1033,
      "step": 6968
    },
    {
      "epoch": 5.46,
      "learning_rate": 8.598848368522073e-05,
      "loss": 0.1022,
      "step": 7072
    },
    {
      "epoch": 5.66,
      "learning_rate": 8.56188241984787e-05,
      "loss": 0.0991,
      "step": 7176
    },
    {
      "epoch": 5.86,
      "learning_rate": 8.524916471173669e-05,
      "loss": 0.1082,
      "step": 7280
    },
    {
      "epoch": 6.06,
      "learning_rate": 8.487950522499466e-05,
      "loss": 0.0936,
      "step": 7384
    },
    {
      "epoch": 6.26,
      "learning_rate": 8.450984573825265e-05,
      "loss": 0.094,
      "step": 7488
    },
    {
      "epoch": 6.46,
      "learning_rate": 8.414018625151064e-05,
      "loss": 0.096,
      "step": 7592
    },
    {
      "epoch": 6.66,
      "learning_rate": 8.377052676476861e-05,
      "loss": 0.0836,
      "step": 7696
    },
    {
      "epoch": 4.15,
      "learning_rate": 8.340442169616834e-05,
      "loss": 0.0918,
      "step": 7800
    },
    {
      "epoch": 4.35,
      "learning_rate": 8.303476220942632e-05,
      "loss": 0.078,
      "step": 7904
    },
    {
      "epoch": 4.55,
      "learning_rate": 8.266865714082605e-05,
      "loss": 0.0866,
      "step": 8008
    },
    {
      "epoch": 4.75,
      "learning_rate": 8.229899765408404e-05,
      "loss": 0.0716,
      "step": 8112
    },
    {
      "epoch": 4.95,
      "learning_rate": 8.192933816734201e-05,
      "loss": 0.0783,
      "step": 8216
    },
    {
      "epoch": 5.15,
      "learning_rate": 8.15596786806e-05,
      "loss": 0.0864,
      "step": 8320
    },
    {
      "epoch": 5.35,
      "learning_rate": 8.119001919385797e-05,
      "loss": 0.0801,
      "step": 8424
    },
    {
      "epoch": 5.55,
      "learning_rate": 8.082035970711594e-05,
      "loss": 0.0801,
      "step": 8528
    },
    {
      "epoch": 5.75,
      "learning_rate": 8.045070022037393e-05,
      "loss": 0.0787,
      "step": 8632
    },
    {
      "epoch": 5.95,
      "learning_rate": 8.00810407336319e-05,
      "loss": 0.082,
      "step": 8736
    },
    {
      "epoch": 6.15,
      "learning_rate": 7.971138124688989e-05,
      "loss": 0.0783,
      "step": 8840
    },
    {
      "epoch": 6.35,
      "learning_rate": 7.934172176014788e-05,
      "loss": 0.0823,
      "step": 8944
    },
    {
      "epoch": 6.55,
      "learning_rate": 7.897206227340585e-05,
      "loss": 0.0796,
      "step": 9048
    },
    {
      "epoch": 6.75,
      "learning_rate": 7.860240278666384e-05,
      "loss": 0.0835,
      "step": 9152
    },
    {
      "epoch": 6.95,
      "learning_rate": 7.823274329992181e-05,
      "loss": 0.085,
      "step": 9256
    },
    {
      "epoch": 7.15,
      "learning_rate": 7.786308381317978e-05,
      "loss": 0.071,
      "step": 9360
    },
    {
      "epoch": 7.35,
      "learning_rate": 7.749342432643777e-05,
      "loss": 0.0662,
      "step": 9464
    },
    {
      "epoch": 7.55,
      "learning_rate": 7.712376483969574e-05,
      "loss": 0.0635,
      "step": 9568
    },
    {
      "epoch": 5.04,
      "learning_rate": 7.675410535295371e-05,
      "loss": 0.075,
      "step": 9672
    },
    {
      "epoch": 5.24,
      "learning_rate": 7.63844458662117e-05,
      "loss": 0.0587,
      "step": 9776
    },
    {
      "epoch": 5.44,
      "learning_rate": 7.601478637946969e-05,
      "loss": 0.0631,
      "step": 9880
    },
    {
      "epoch": 5.64,
      "learning_rate": 7.564868131086942e-05,
      "loss": 0.0626,
      "step": 9984
    },
    {
      "epoch": 5.84,
      "learning_rate": 7.528257624226914e-05,
      "loss": 0.0741,
      "step": 10088
    },
    {
      "epoch": 6.04,
      "learning_rate": 7.491291675552711e-05,
      "loss": 0.0522,
      "step": 10192
    },
    {
      "epoch": 6.24,
      "learning_rate": 7.45432572687851e-05,
      "loss": 0.0622,
      "step": 10296
    },
    {
      "epoch": 6.44,
      "learning_rate": 7.417359778204309e-05,
      "loss": 0.0602,
      "step": 10400
    },
    {
      "epoch": 6.64,
      "learning_rate": 7.380393829530107e-05,
      "loss": 0.0639,
      "step": 10504
    },
    {
      "epoch": 6.84,
      "learning_rate": 7.343427880855905e-05,
      "loss": 0.0723,
      "step": 10608
    },
    {
      "epoch": 7.04,
      "learning_rate": 7.306461932181702e-05,
      "loss": 0.0607,
      "step": 10712
    },
    {
      "epoch": 7.24,
      "learning_rate": 7.2694959835075e-05,
      "loss": 0.0655,
      "step": 10816
    },
    {
      "epoch": 7.44,
      "learning_rate": 7.232530034833298e-05,
      "loss": 0.069,
      "step": 10920
    },
    {
      "epoch": 7.64,
      "learning_rate": 7.195564086159095e-05,
      "loss": 0.0664,
      "step": 11024
    },
    {
      "epoch": 7.84,
      "learning_rate": 7.158598137484894e-05,
      "loss": 0.0568,
      "step": 11128
    },
    {
      "epoch": 8.04,
      "learning_rate": 7.121632188810691e-05,
      "loss": 0.0612,
      "step": 11232
    },
    {
      "epoch": 8.24,
      "learning_rate": 7.08466624013649e-05,
      "loss": 0.055,
      "step": 11336
    },
    {
      "epoch": 8.44,
      "learning_rate": 7.047700291462288e-05,
      "loss": 0.0501,
      "step": 11440
    },
    {
      "epoch": 8.64,
      "learning_rate": 7.010734342788086e-05,
      "loss": 0.057,
      "step": 11544
    },
    {
      "epoch": 6.13,
      "learning_rate": 6.973768394113884e-05,
      "loss": 0.0502,
      "step": 11648
    },
    {
      "epoch": 6.33,
      "learning_rate": 6.936802445439682e-05,
      "loss": 0.0539,
      "step": 11752
    },
    {
      "epoch": 6.53,
      "learning_rate": 6.899836496765479e-05,
      "loss": 0.0491,
      "step": 11856
    },
    {
      "epoch": 6.73,
      "learning_rate": 6.862870548091278e-05,
      "loss": 0.0473,
      "step": 11960
    },
    {
      "epoch": 6.93,
      "learning_rate": 6.825904599417075e-05,
      "loss": 0.0467,
      "step": 12064
    },
    {
      "epoch": 7.13,
      "learning_rate": 6.788938650742874e-05,
      "loss": 0.0492,
      "step": 12168
    },
    {
      "epoch": 7.33,
      "learning_rate": 6.751972702068672e-05,
      "loss": 0.0519,
      "step": 12272
    },
    {
      "epoch": 7.53,
      "learning_rate": 6.71500675339447e-05,
      "loss": 0.0505,
      "step": 12376
    },
    {
      "epoch": 7.73,
      "learning_rate": 6.678040804720268e-05,
      "loss": 0.0478,
      "step": 12480
    },
    {
      "epoch": 7.93,
      "learning_rate": 6.641074856046066e-05,
      "loss": 0.0516,
      "step": 12584
    },
    {
      "epoch": 8.13,
      "learning_rate": 6.604108907371863e-05,
      "loss": 0.052,
      "step": 12688
    },
    {
      "epoch": 8.33,
      "learning_rate": 6.567142958697662e-05,
      "loss": 0.0523,
      "step": 12792
    },
    {
      "epoch": 8.53,
      "learning_rate": 6.530177010023459e-05,
      "loss": 0.0516,
      "step": 12896
    },
    {
      "epoch": 8.73,
      "learning_rate": 6.493211061349258e-05,
      "loss": 0.0435,
      "step": 13000
    },
    {
      "epoch": 8.93,
      "learning_rate": 6.456245112675056e-05,
      "loss": 0.0503,
      "step": 13104
    },
    {
      "epoch": 9.12,
      "learning_rate": 6.419279164000854e-05,
      "loss": 0.043,
      "step": 13208
    },
    {
      "epoch": 9.32,
      "learning_rate": 6.382313215326652e-05,
      "loss": 0.0433,
      "step": 13312
    },
    {
      "epoch": 9.52,
      "learning_rate": 6.34534726665245e-05,
      "loss": 0.0432,
      "step": 13416
    },
    {
      "epoch": 7.02,
      "learning_rate": 6.308381317978247e-05,
      "loss": 0.0423,
      "step": 13520
    },
    {
      "epoch": 7.22,
      "learning_rate": 6.271415369304045e-05,
      "loss": 0.0416,
      "step": 13624
    },
    {
      "epoch": 7.42,
      "learning_rate": 6.234449420629843e-05,
      "loss": 0.0363,
      "step": 13728
    },
    {
      "epoch": 7.62,
      "learning_rate": 6.19748347195564e-05,
      "loss": 0.0335,
      "step": 13832
    },
    {
      "epoch": 7.82,
      "learning_rate": 6.160517523281439e-05,
      "loss": 0.0395,
      "step": 13936
    },
    {
      "epoch": 8.02,
      "learning_rate": 6.123551574607237e-05,
      "loss": 0.0358,
      "step": 14040
    },
    {
      "epoch": 8.22,
      "learning_rate": 6.0865856259330354e-05,
      "loss": 0.0397,
      "step": 14144
    },
    {
      "epoch": 8.42,
      "learning_rate": 6.0496196772588334e-05,
      "loss": 0.0441,
      "step": 14248
    },
    {
      "epoch": 8.62,
      "learning_rate": 6.012653728584631e-05,
      "loss": 0.0408,
      "step": 14352
    },
    {
      "epoch": 8.82,
      "learning_rate": 5.9756877799104293e-05,
      "loss": 0.0403,
      "step": 14456
    },
    {
      "epoch": 9.02,
      "learning_rate": 5.9387218312362267e-05,
      "loss": 0.0379,
      "step": 14560
    },
    {
      "epoch": 9.21,
      "learning_rate": 5.9017558825620246e-05,
      "loss": 0.0383,
      "step": 14664
    },
    {
      "epoch": 9.41,
      "learning_rate": 5.864789933887823e-05,
      "loss": 0.0457,
      "step": 14768
    },
    {
      "epoch": 9.61,
      "learning_rate": 5.8278239852136206e-05,
      "loss": 0.039,
      "step": 14872
    },
    {
      "epoch": 9.81,
      "learning_rate": 5.7912134783535946e-05,
      "loss": 0.0396,
      "step": 14976
    },
    {
      "epoch": 10.01,
      "learning_rate": 5.754247529679392e-05,
      "loss": 0.0379,
      "step": 15080
    },
    {
      "epoch": 10.21,
      "learning_rate": 5.717281581005189e-05,
      "loss": 0.034,
      "step": 15184
    },
    {
      "epoch": 10.41,
      "learning_rate": 5.680315632330988e-05,
      "loss": 0.0363,
      "step": 15288
    },
    {
      "epoch": 10.61,
      "learning_rate": 5.643349683656786e-05,
      "loss": 0.0302,
      "step": 15392
    },
    {
      "epoch": 8.11,
      "learning_rate": 5.606383734982583e-05,
      "loss": 0.0325,
      "step": 15496
    },
    {
      "epoch": 8.31,
      "learning_rate": 5.569417786308382e-05,
      "loss": 0.0307,
      "step": 15600
    },
    {
      "epoch": 8.51,
      "learning_rate": 5.532451837634179e-05,
      "loss": 0.0345,
      "step": 15704
    },
    {
      "epoch": 8.71,
      "learning_rate": 5.495485888959978e-05,
      "loss": 0.0268,
      "step": 15808
    },
    {
      "epoch": 8.91,
      "learning_rate": 5.458519940285776e-05,
      "loss": 0.0356,
      "step": 15912
    },
    {
      "epoch": 9.11,
      "learning_rate": 5.421553991611573e-05,
      "loss": 0.0308,
      "step": 16016
    },
    {
      "epoch": 9.31,
      "learning_rate": 5.384588042937372e-05,
      "loss": 0.0311,
      "step": 16120
    },
    {
      "epoch": 9.5,
      "learning_rate": 5.34762209426317e-05,
      "loss": 0.0314,
      "step": 16224
    },
    {
      "epoch": 9.7,
      "learning_rate": 5.310656145588967e-05,
      "loss": 0.0316,
      "step": 16328
    },
    {
      "epoch": 9.9,
      "learning_rate": 5.273690196914766e-05,
      "loss": 0.0322,
      "step": 16432
    },
    {
      "epoch": 10.1,
      "learning_rate": 5.236724248240563e-05,
      "loss": 0.0348,
      "step": 16536
    },
    {
      "epoch": 10.3,
      "learning_rate": 5.199758299566361e-05,
      "loss": 0.031,
      "step": 16640
    },
    {
      "epoch": 10.5,
      "learning_rate": 5.1627923508921597e-05,
      "loss": 0.0308,
      "step": 16744
    },
    {
      "epoch": 10.7,
      "learning_rate": 5.125826402217957e-05,
      "loss": 0.0317,
      "step": 16848
    },
    {
      "epoch": 10.9,
      "learning_rate": 5.0888604535437556e-05,
      "loss": 0.0298,
      "step": 16952
    },
    {
      "epoch": 11.1,
      "learning_rate": 5.051894504869553e-05,
      "loss": 0.0278,
      "step": 17056
    },
    {
      "epoch": 11.3,
      "learning_rate": 5.014928556195351e-05,
      "loss": 0.0255,
      "step": 17160
    },
    {
      "epoch": 11.5,
      "learning_rate": 4.977962607521149e-05,
      "loss": 0.0287,
      "step": 17264
    },
    {
      "epoch": 11.7,
      "learning_rate": 4.940996658846947e-05,
      "loss": 0.0286,
      "step": 17368
    },
    {
      "epoch": 9.2,
      "learning_rate": 4.904030710172745e-05,
      "loss": 0.027,
      "step": 17472
    },
    {
      "epoch": 9.4,
      "learning_rate": 4.867064761498543e-05,
      "loss": 0.0227,
      "step": 17576
    },
    {
      "epoch": 9.6,
      "learning_rate": 4.830098812824341e-05,
      "loss": 0.026,
      "step": 17680
    },
    {
      "epoch": 9.79,
      "learning_rate": 4.793132864150139e-05,
      "loss": 0.0228,
      "step": 17784
    },
    {
      "epoch": 9.99,
      "learning_rate": 4.756166915475937e-05,
      "loss": 0.025,
      "step": 17888
    },
    {
      "epoch": 10.19,
      "learning_rate": 4.719200966801735e-05,
      "loss": 0.0258,
      "step": 17992
    },
    {
      "epoch": 10.39,
      "learning_rate": 4.6825904599417074e-05,
      "loss": 0.0276,
      "step": 18096
    },
    {
      "epoch": 10.59,
      "learning_rate": 4.6456245112675054e-05,
      "loss": 0.0278,
      "step": 18200
    },
    {
      "epoch": 10.79,
      "learning_rate": 4.608658562593304e-05,
      "loss": 0.0224,
      "step": 18304
    },
    {
      "epoch": 10.99,
      "learning_rate": 4.571692613919102e-05,
      "loss": 0.0267,
      "step": 18408
    },
    {
      "epoch": 11.19,
      "learning_rate": 4.5347266652448994e-05,
      "loss": 0.026,
      "step": 18512
    },
    {
      "epoch": 11.39,
      "learning_rate": 4.4977607165706973e-05,
      "loss": 0.0268,
      "step": 18616
    },
    {
      "epoch": 11.59,
      "learning_rate": 4.460794767896495e-05,
      "loss": 0.0237,
      "step": 18720
    },
    {
      "epoch": 11.79,
      "learning_rate": 4.423828819222294e-05,
      "loss": 0.0257,
      "step": 18824
    },
    {
      "epoch": 11.99,
      "learning_rate": 4.386862870548091e-05,
      "loss": 0.0243,
      "step": 18928
    },
    {
      "epoch": 12.19,
      "learning_rate": 4.349896921873889e-05,
      "loss": 0.0241,
      "step": 19032
    },
    {
      "epoch": 12.39,
      "learning_rate": 4.312930973199687e-05,
      "loss": 0.0209,
      "step": 19136
    },
    {
      "epoch": 12.59,
      "learning_rate": 4.275965024525486e-05,
      "loss": 0.0205,
      "step": 19240
    },
    {
      "epoch": 10.08,
      "learning_rate": 4.238999075851283e-05,
      "loss": 0.0226,
      "step": 19344
    },
    {
      "epoch": 10.28,
      "learning_rate": 4.202033127177081e-05,
      "loss": 0.0193,
      "step": 19448
    },
    {
      "epoch": 10.48,
      "learning_rate": 4.165067178502879e-05,
      "loss": 0.0199,
      "step": 19552
    },
    {
      "epoch": 10.68,
      "learning_rate": 4.128101229828677e-05,
      "loss": 0.0203,
      "step": 19656
    },
    {
      "epoch": 10.88,
      "learning_rate": 4.091135281154475e-05,
      "loss": 0.0204,
      "step": 19760
    },
    {
      "epoch": 11.08,
      "learning_rate": 4.054169332480273e-05,
      "loss": 0.0201,
      "step": 19864
    },
    {
      "epoch": 11.28,
      "learning_rate": 4.017203383806071e-05,
      "loss": 0.0231,
      "step": 19968
    },
    {
      "epoch": 11.48,
      "learning_rate": 3.980237435131869e-05,
      "loss": 0.0207,
      "step": 20072
    },
    {
      "epoch": 11.68,
      "learning_rate": 3.943271486457667e-05,
      "loss": 0.0184,
      "step": 20176
    },
    {
      "epoch": 11.88,
      "learning_rate": 3.906305537783465e-05,
      "loss": 0.0206,
      "step": 20280
    },
    {
      "epoch": 12.08,
      "learning_rate": 3.869339589109263e-05,
      "loss": 0.0219,
      "step": 20384
    },
    {
      "epoch": 12.28,
      "learning_rate": 3.832373640435061e-05,
      "loss": 0.0206,
      "step": 20488
    },
    {
      "epoch": 12.48,
      "learning_rate": 3.795407691760859e-05,
      "loss": 0.0242,
      "step": 20592
    },
    {
      "epoch": 12.68,
      "learning_rate": 3.758441743086657e-05,
      "loss": 0.0198,
      "step": 20696
    },
    {
      "epoch": 12.88,
      "learning_rate": 3.721475794412455e-05,
      "loss": 0.0207,
      "step": 20800
    },
    {
      "epoch": 13.08,
      "learning_rate": 3.684509845738252e-05,
      "loss": 0.0183,
      "step": 20904
    },
    {
      "epoch": 13.28,
      "learning_rate": 3.647543897064051e-05,
      "loss": 0.0171,
      "step": 21008
    },
    {
      "epoch": 13.48,
      "learning_rate": 3.610577948389849e-05,
      "loss": 0.0174,
      "step": 21112
    },
    {
      "epoch": 13.68,
      "learning_rate": 3.573611999715647e-05,
      "loss": 0.0182,
      "step": 21216
    },
    {
      "epoch": 11.17,
      "learning_rate": 3.536646051041444e-05,
      "loss": 0.0178,
      "step": 21320
    },
    {
      "epoch": 11.37,
      "learning_rate": 3.499680102367243e-05,
      "loss": 0.0156,
      "step": 21424
    },
    {
      "epoch": 11.57,
      "learning_rate": 3.462714153693041e-05,
      "loss": 0.0171,
      "step": 21528
    },
    {
      "epoch": 11.77,
      "learning_rate": 3.425748205018838e-05,
      "loss": 0.0156,
      "step": 21632
    },
    {
      "epoch": 11.97,
      "learning_rate": 3.388782256344636e-05,
      "loss": 0.0171,
      "step": 21736
    },
    {
      "epoch": 12.17,
      "learning_rate": 3.351816307670435e-05,
      "loss": 0.0145,
      "step": 21840
    },
    {
      "epoch": 12.37,
      "learning_rate": 3.314850358996233e-05,
      "loss": 0.0153,
      "step": 21944
    },
    {
      "epoch": 12.57,
      "learning_rate": 3.27788441032203e-05,
      "loss": 0.0157,
      "step": 22048
    },
    {
      "epoch": 12.77,
      "learning_rate": 3.240918461647828e-05,
      "loss": 0.0176,
      "step": 22152
    },
    {
      "epoch": 12.97,
      "learning_rate": 3.203952512973626e-05,
      "loss": 0.0152,
      "step": 22256
    },
    {
      "epoch": 13.17,
      "learning_rate": 3.166986564299425e-05,
      "loss": 0.0196,
      "step": 22360
    },
    {
      "epoch": 13.37,
      "learning_rate": 3.130020615625222e-05,
      "loss": 0.0171,
      "step": 22464
    },
    {
      "epoch": 13.57,
      "learning_rate": 3.0934101087651954e-05,
      "loss": 0.0182,
      "step": 22568
    },
    {
      "epoch": 13.77,
      "learning_rate": 3.0564441600909934e-05,
      "loss": 0.0194,
      "step": 22672
    },
    {
      "epoch": 13.97,
      "learning_rate": 3.0194782114167914e-05,
      "loss": 0.0163,
      "step": 22776
    },
    {
      "epoch": 14.17,
      "learning_rate": 2.9825122627425893e-05,
      "loss": 0.0136,
      "step": 22880
    },
    {
      "epoch": 14.37,
      "learning_rate": 2.945546314068387e-05,
      "loss": 0.0136,
      "step": 22984
    },
    {
      "epoch": 14.57,
      "learning_rate": 2.908580365394185e-05,
      "loss": 0.014,
      "step": 23088
    },
    {
      "epoch": 12.06,
      "learning_rate": 2.8716144167199833e-05,
      "loss": 0.0154,
      "step": 23192
    },
    {
      "epoch": 12.26,
      "learning_rate": 2.834648468045781e-05,
      "loss": 0.0134,
      "step": 23296
    },
    {
      "epoch": 12.46,
      "learning_rate": 2.797682519371579e-05,
      "loss": 0.0124,
      "step": 23400
    },
    {
      "epoch": 12.66,
      "learning_rate": 2.760716570697377e-05,
      "loss": 0.0127,
      "step": 23504
    },
    {
      "epoch": 12.86,
      "learning_rate": 2.7237506220231752e-05,
      "loss": 0.0127,
      "step": 23608
    },
    {
      "epoch": 13.06,
      "learning_rate": 2.6867846733489725e-05,
      "loss": 0.0126,
      "step": 23712
    },
    {
      "epoch": 13.26,
      "learning_rate": 2.649818724674771e-05,
      "loss": 0.0143,
      "step": 23816
    },
    {
      "epoch": 13.46,
      "learning_rate": 2.612852776000569e-05,
      "loss": 0.0133,
      "step": 23920
    },
    {
      "epoch": 13.66,
      "learning_rate": 2.575886827326367e-05,
      "loss": 0.0127,
      "step": 24024
    },
    {
      "epoch": 13.86,
      "learning_rate": 2.5389208786521645e-05,
      "loss": 0.0131,
      "step": 24128
    },
    {
      "epoch": 14.06,
      "learning_rate": 2.5019549299779628e-05,
      "loss": 0.0135,
      "step": 24232
    },
    {
      "epoch": 14.26,
      "learning_rate": 2.4649889813037608e-05,
      "loss": 0.0161,
      "step": 24336
    },
    {
      "epoch": 14.46,
      "learning_rate": 2.4280230326295588e-05,
      "loss": 0.0143,
      "step": 24440
    },
    {
      "epoch": 14.66,
      "learning_rate": 2.3910570839553567e-05,
      "loss": 0.0172,
      "step": 24544
    },
    {
      "epoch": 14.86,
      "learning_rate": 2.3540911352811544e-05,
      "loss": 0.0129,
      "step": 24648
    },
    {
      "epoch": 15.06,
      "learning_rate": 2.3171251866069527e-05,
      "loss": 0.0127,
      "step": 24752
    },
    {
      "epoch": 15.26,
      "learning_rate": 2.2801592379327504e-05,
      "loss": 0.0112,
      "step": 24856
    },
    {
      "epoch": 15.45,
      "learning_rate": 2.2431932892585487e-05,
      "loss": 0.0128,
      "step": 24960
    },
    {
      "epoch": 15.65,
      "learning_rate": 2.2065827823985213e-05,
      "loss": 0.0114,
      "step": 25064
    },
    {
      "epoch": 13.15,
      "learning_rate": 2.1696168337243193e-05,
      "loss": 0.0112,
      "step": 25168
    },
    {
      "epoch": 13.35,
      "learning_rate": 2.1326508850501173e-05,
      "loss": 0.0109,
      "step": 25272
    },
    {
      "epoch": 13.55,
      "learning_rate": 2.0956849363759153e-05,
      "loss": 0.0105,
      "step": 25376
    },
    {
      "epoch": 13.75,
      "learning_rate": 2.0587189877017133e-05,
      "loss": 0.0116,
      "step": 25480
    },
    {
      "epoch": 13.95,
      "learning_rate": 2.0217530390275112e-05,
      "loss": 0.0136,
      "step": 25584
    },
    {
      "epoch": 14.15,
      "learning_rate": 1.9847870903533092e-05,
      "loss": 0.0113,
      "step": 25688
    },
    {
      "epoch": 14.35,
      "learning_rate": 1.9478211416791072e-05,
      "loss": 0.0106,
      "step": 25792
    },
    {
      "epoch": 14.55,
      "learning_rate": 1.9108551930049052e-05,
      "loss": 0.0109,
      "step": 25896
    },
    {
      "epoch": 14.75,
      "learning_rate": 1.8738892443307032e-05,
      "loss": 0.011,
      "step": 26000
    },
    {
      "epoch": 14.95,
      "learning_rate": 1.836923295656501e-05,
      "loss": 0.0106,
      "step": 26104
    },
    {
      "epoch": 15.15,
      "learning_rate": 1.799957346982299e-05,
      "loss": 0.0134,
      "step": 26208
    },
    {
      "epoch": 15.35,
      "learning_rate": 1.762991398308097e-05,
      "loss": 0.0111,
      "step": 26312
    },
    {
      "epoch": 15.55,
      "learning_rate": 1.726025449633895e-05,
      "loss": 0.0102,
      "step": 26416
    },
    {
      "epoch": 15.74,
      "learning_rate": 1.689059500959693e-05,
      "loss": 0.0104,
      "step": 26520
    },
    {
      "epoch": 15.94,
      "learning_rate": 1.652093552285491e-05,
      "loss": 0.0095,
      "step": 26624
    },
    {
      "epoch": 16.14,
      "learning_rate": 1.615127603611289e-05,
      "loss": 0.0105,
      "step": 26728
    },
    {
      "epoch": 16.34,
      "learning_rate": 1.578161654937087e-05,
      "loss": 0.0096,
      "step": 26832
    },
    {
      "epoch": 16.54,
      "learning_rate": 1.5411957062628847e-05,
      "loss": 0.0095,
      "step": 26936
    },
    {
      "epoch": 14.04,
      "learning_rate": 1.5042297575886827e-05,
      "loss": 0.009,
      "step": 27040
    },
    {
      "epoch": 14.24,
      "learning_rate": 1.4672638089144808e-05,
      "loss": 0.0083,
      "step": 27144
    },
    {
      "epoch": 14.44,
      "learning_rate": 1.4302978602402786e-05,
      "loss": 0.0091,
      "step": 27248
    },
    {
      "epoch": 14.64,
      "learning_rate": 1.3933319115660768e-05,
      "loss": 0.0121,
      "step": 27352
    },
    {
      "epoch": 14.84,
      "learning_rate": 1.3563659628918746e-05,
      "loss": 0.0105,
      "step": 27456
    },
    {
      "epoch": 15.04,
      "learning_rate": 1.3194000142176728e-05,
      "loss": 0.0083,
      "step": 27560
    },
    {
      "epoch": 15.24,
      "learning_rate": 1.2824340655434706e-05,
      "loss": 0.0089,
      "step": 27664
    },
    {
      "epoch": 15.44,
      "learning_rate": 1.2454681168692686e-05,
      "loss": 0.0093,
      "step": 27768
    },
    {
      "epoch": 15.64,
      "learning_rate": 1.2085021681950665e-05,
      "loss": 0.0087,
      "step": 27872
    },
    {
      "epoch": 15.83,
      "learning_rate": 1.1715362195208644e-05,
      "loss": 0.0087,
      "step": 27976
    },
    {
      "epoch": 16.03,
      "learning_rate": 1.1345702708466623e-05,
      "loss": 0.009,
      "step": 28080
    },
    {
      "epoch": 16.23,
      "learning_rate": 1.0976043221724603e-05,
      "loss": 0.0093,
      "step": 28184
    },
    {
      "epoch": 16.43,
      "learning_rate": 1.0606383734982583e-05,
      "loss": 0.0086,
      "step": 28288
    },
    {
      "epoch": 16.63,
      "learning_rate": 1.0236724248240563e-05,
      "loss": 0.0092,
      "step": 28392
    },
    {
      "epoch": 16.83,
      "learning_rate": 9.867064761498543e-06,
      "loss": 0.0098,
      "step": 28496
    },
    {
      "epoch": 17.03,
      "learning_rate": 9.497405274756523e-06,
      "loss": 0.0088,
      "step": 28600
    },
    {
      "epoch": 17.23,
      "learning_rate": 9.127745788014502e-06,
      "loss": 0.0081,
      "step": 28704
    },
    {
      "epoch": 17.43,
      "learning_rate": 8.758086301272482e-06,
      "loss": 0.0086,
      "step": 28808
    },
    {
      "epoch": 17.63,
      "learning_rate": 8.388426814530462e-06,
      "loss": 0.0075,
      "step": 28912
    },
    {
      "epoch": 15.13,
      "learning_rate": 8.018767327788442e-06,
      "loss": 0.0086,
      "step": 29016
    },
    {
      "epoch": 15.33,
      "learning_rate": 7.649107841046422e-06,
      "loss": 0.0071,
      "step": 29120
    },
    {
      "epoch": 15.53,
      "learning_rate": 7.279448354304401e-06,
      "loss": 0.0077,
      "step": 29224
    },
    {
      "epoch": 15.73,
      "learning_rate": 6.9133432857041314e-06,
      "loss": 0.0104,
      "step": 29328
    },
    {
      "epoch": 15.93,
      "learning_rate": 6.5436837989621104e-06,
      "loss": 0.0077,
      "step": 29432
    },
    {
      "epoch": 16.12,
      "learning_rate": 6.1740243122200894e-06,
      "loss": 0.0077,
      "step": 29536
    },
    {
      "epoch": 16.32,
      "learning_rate": 5.804364825478069e-06,
      "loss": 0.0072,
      "step": 29640
    },
    {
      "epoch": 16.52,
      "learning_rate": 5.434705338736049e-06,
      "loss": 0.0079,
      "step": 29744
    },
    {
      "epoch": 16.72,
      "learning_rate": 5.065045851994029e-06,
      "loss": 0.0076,
      "step": 29848
    },
    {
      "epoch": 16.92,
      "learning_rate": 4.698940783393759e-06,
      "loss": 0.0074,
      "step": 29952
    },
    {
      "epoch": 17.12,
      "learning_rate": 4.329281296651739e-06,
      "loss": 0.0099,
      "step": 30056
    },
    {
      "epoch": 17.32,
      "learning_rate": 3.9631762280514684e-06,
      "loss": 0.0078,
      "step": 30160
    },
    {
      "epoch": 17.52,
      "learning_rate": 3.5935167413094483e-06,
      "loss": 0.0071,
      "step": 30264
    },
    {
      "epoch": 17.72,
      "learning_rate": 3.2238572545674273e-06,
      "loss": 0.0076,
      "step": 30368
    },
    {
      "epoch": 17.92,
      "learning_rate": 2.854197767825407e-06,
      "loss": 0.0076,
      "step": 30472
    },
    {
      "epoch": 18.12,
      "learning_rate": 2.484538281083387e-06,
      "loss": 0.007,
      "step": 30576
    },
    {
      "epoch": 18.32,
      "learning_rate": 2.1148787943413664e-06,
      "loss": 0.0069,
      "step": 30680
    },
    {
      "epoch": 18.52,
      "learning_rate": 1.745219307599346e-06,
      "loss": 0.0073,
      "step": 30784
    },
    {
      "epoch": 16.02,
      "learning_rate": 1.3755598208573258e-06,
      "loss": 0.0069,
      "step": 30888
    },
    {
      "epoch": 16.21,
      "learning_rate": 1.0059003341153055e-06,
      "loss": 0.007,
      "step": 30992
    },
    {
      "epoch": 16.41,
      "learning_rate": 6.36240847373285e-07,
      "loss": 0.0092,
      "step": 31096
    },
    {
      "epoch": 16.61,
      "learning_rate": 2.665813606312647e-07,
      "loss": 0.0068,
      "step": 31200
    }
  ],
  "logging_steps": 104,
  "max_steps": 31260,
  "num_train_epochs": 60,
  "save_steps": 500,
  "total_flos": 1.3669926589956096e+18,
  "trial_name": null,
  "trial_params": null
}