{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 30.0,
  "eval_steps": 500,
  "global_step": 26250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 1.9886202812194824,
      "learning_rate": 0.00029886857142857144,
      "loss": 1.2287,
      "step": 100
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 1.3383790254592896,
      "learning_rate": 0.0002977257142857143,
      "loss": 1.0151,
      "step": 200
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 1.4753262996673584,
      "learning_rate": 0.0002965828571428571,
      "loss": 0.9255,
      "step": 300
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 1.6120792627334595,
      "learning_rate": 0.00029544,
      "loss": 0.9156,
      "step": 400
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.7478028535842896,
      "learning_rate": 0.00029429714285714284,
      "loss": 0.8849,
      "step": 500
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 1.4654852151870728,
      "learning_rate": 0.0002931542857142857,
      "loss": 0.847,
      "step": 600
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.6262428760528564,
      "learning_rate": 0.0002920114285714285,
      "loss": 0.8322,
      "step": 700
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 1.2275465726852417,
      "learning_rate": 0.0002908685714285714,
      "loss": 0.8382,
      "step": 800
    },
    {
      "epoch": 1.0285714285714285,
      "grad_norm": 0.8290926218032837,
      "learning_rate": 0.00028972571428571424,
      "loss": 0.8152,
      "step": 900
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.5321491956710815,
      "learning_rate": 0.0002885828571428571,
      "loss": 0.766,
      "step": 1000
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 1.1432169675827026,
      "learning_rate": 0.00028743999999999997,
      "loss": 0.7438,
      "step": 1100
    },
    {
      "epoch": 1.3714285714285714,
      "grad_norm": 3.4796738624572754,
      "learning_rate": 0.00028629714285714286,
      "loss": 0.7422,
      "step": 1200
    },
    {
      "epoch": 1.4857142857142858,
      "grad_norm": 0.8977236747741699,
      "learning_rate": 0.0002851542857142857,
      "loss": 0.7047,
      "step": 1300
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.8644102811813354,
      "learning_rate": 0.00028401142857142854,
      "loss": 0.7545,
      "step": 1400
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 1.1881957054138184,
      "learning_rate": 0.00028286857142857143,
      "loss": 0.7159,
      "step": 1500
    },
    {
      "epoch": 1.8285714285714287,
      "grad_norm": 1.2069973945617676,
      "learning_rate": 0.00028172571428571427,
      "loss": 0.6974,
      "step": 1600
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 1.1324719190597534,
      "learning_rate": 0.0002805828571428571,
      "loss": 0.7014,
      "step": 1700
    },
    {
      "epoch": 2.057142857142857,
      "grad_norm": 1.6258182525634766,
      "learning_rate": 0.00027944,
      "loss": 0.6531,
      "step": 1800
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 1.6277265548706055,
      "learning_rate": 0.00027829714285714283,
      "loss": 0.6167,
      "step": 1900
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 1.05016028881073,
      "learning_rate": 0.00027715428571428567,
      "loss": 0.6365,
      "step": 2000
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.4809651374816895,
      "learning_rate": 0.00027601142857142856,
      "loss": 0.64,
      "step": 2100
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.9632180333137512,
      "learning_rate": 0.0002748685714285714,
      "loss": 0.631,
      "step": 2200
    },
    {
      "epoch": 2.6285714285714286,
      "grad_norm": 1.4610211849212646,
      "learning_rate": 0.00027372571428571423,
      "loss": 0.6183,
      "step": 2300
    },
    {
      "epoch": 2.742857142857143,
      "grad_norm": 0.95488440990448,
      "learning_rate": 0.0002725828571428571,
      "loss": 0.6116,
      "step": 2400
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 1.4659332036972046,
      "learning_rate": 0.00027144,
      "loss": 0.6281,
      "step": 2500
    },
    {
      "epoch": 2.9714285714285715,
      "grad_norm": 1.0329852104187012,
      "learning_rate": 0.00027029714285714285,
      "loss": 0.6289,
      "step": 2600
    },
    {
      "epoch": 3.085714285714286,
      "grad_norm": 1.1207853555679321,
      "learning_rate": 0.0002691542857142857,
      "loss": 0.5658,
      "step": 2700
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.1021409034729004,
      "learning_rate": 0.00026801142857142853,
      "loss": 0.5508,
      "step": 2800
    },
    {
      "epoch": 3.314285714285714,
      "grad_norm": 1.3904248476028442,
      "learning_rate": 0.0002668685714285714,
      "loss": 0.5705,
      "step": 2900
    },
    {
      "epoch": 3.4285714285714284,
      "grad_norm": 1.0779317617416382,
      "learning_rate": 0.00026572571428571426,
      "loss": 0.5586,
      "step": 3000
    },
    {
      "epoch": 3.5428571428571427,
      "grad_norm": 1.5445743799209595,
      "learning_rate": 0.0002645828571428571,
      "loss": 0.5457,
      "step": 3100
    },
    {
      "epoch": 3.657142857142857,
      "grad_norm": 1.100846290588379,
      "learning_rate": 0.00026344,
      "loss": 0.5495,
      "step": 3200
    },
    {
      "epoch": 3.7714285714285714,
      "grad_norm": 1.7807058095932007,
      "learning_rate": 0.0002622971428571428,
      "loss": 0.5752,
      "step": 3300
    },
    {
      "epoch": 3.8857142857142857,
      "grad_norm": 1.18954336643219,
      "learning_rate": 0.00026115428571428566,
      "loss": 0.5443,
      "step": 3400
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.0324475765228271,
      "learning_rate": 0.00026001142857142855,
      "loss": 0.5344,
      "step": 3500
    },
    {
      "epoch": 4.114285714285714,
      "grad_norm": 1.2776315212249756,
      "learning_rate": 0.0002588685714285714,
      "loss": 0.4963,
      "step": 3600
    },
    {
      "epoch": 4.228571428571429,
      "grad_norm": 1.8203849792480469,
      "learning_rate": 0.0002577257142857142,
      "loss": 0.4796,
      "step": 3700
    },
    {
      "epoch": 4.3428571428571425,
      "grad_norm": 1.0043076276779175,
      "learning_rate": 0.0002565828571428571,
      "loss": 0.4828,
      "step": 3800
    },
    {
      "epoch": 4.457142857142857,
      "grad_norm": 1.506948471069336,
      "learning_rate": 0.00025544,
      "loss": 0.5112,
      "step": 3900
    },
    {
      "epoch": 4.571428571428571,
      "grad_norm": 1.1585667133331299,
      "learning_rate": 0.00025429714285714284,
      "loss": 0.4957,
      "step": 4000
    },
    {
      "epoch": 4.685714285714286,
      "grad_norm": 1.3756364583969116,
      "learning_rate": 0.0002531542857142857,
      "loss": 0.5106,
      "step": 4100
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.9732717871665955,
      "learning_rate": 0.00025201142857142857,
      "loss": 0.483,
      "step": 4200
    },
    {
      "epoch": 4.914285714285715,
      "grad_norm": 1.2413655519485474,
      "learning_rate": 0.0002508685714285714,
      "loss": 0.5,
      "step": 4300
    },
    {
      "epoch": 5.0285714285714285,
      "grad_norm": 1.0629197359085083,
      "learning_rate": 0.00024972571428571425,
      "loss": 0.4751,
      "step": 4400
    },
    {
      "epoch": 5.142857142857143,
      "grad_norm": 1.3967541456222534,
      "learning_rate": 0.00024858285714285714,
      "loss": 0.4427,
      "step": 4500
    },
    {
      "epoch": 5.257142857142857,
      "grad_norm": 1.1337262392044067,
      "learning_rate": 0.00024744,
      "loss": 0.4413,
      "step": 4600
    },
    {
      "epoch": 5.371428571428572,
      "grad_norm": 1.4365642070770264,
      "learning_rate": 0.0002462971428571428,
      "loss": 0.4342,
      "step": 4700
    },
    {
      "epoch": 5.485714285714286,
      "grad_norm": 1.1386431455612183,
      "learning_rate": 0.0002451542857142857,
      "loss": 0.4302,
      "step": 4800
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.6757099628448486,
      "learning_rate": 0.00024401142857142854,
      "loss": 0.448,
      "step": 4900
    },
    {
      "epoch": 5.714285714285714,
      "grad_norm": 1.2465338706970215,
      "learning_rate": 0.00024286857142857143,
      "loss": 0.4401,
      "step": 5000
    },
    {
      "epoch": 5.828571428571428,
      "grad_norm": 1.482226014137268,
      "learning_rate": 0.00024172571428571427,
      "loss": 0.4613,
      "step": 5100
    },
    {
      "epoch": 5.942857142857143,
      "grad_norm": 2.177501678466797,
      "learning_rate": 0.00024058285714285713,
      "loss": 0.4364,
      "step": 5200
    },
    {
      "epoch": 6.057142857142857,
      "grad_norm": 1.069575309753418,
      "learning_rate": 0.00023944,
      "loss": 0.4228,
      "step": 5300
    },
    {
      "epoch": 6.171428571428572,
      "grad_norm": 1.0357013940811157,
      "learning_rate": 0.00023829714285714283,
      "loss": 0.3895,
      "step": 5400
    },
    {
      "epoch": 6.285714285714286,
      "grad_norm": 1.3480335474014282,
      "learning_rate": 0.0002371542857142857,
      "loss": 0.4087,
      "step": 5500
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.4253255128860474,
      "learning_rate": 0.00023601142857142856,
      "loss": 0.4058,
      "step": 5600
    },
    {
      "epoch": 6.514285714285714,
      "grad_norm": 1.293028712272644,
      "learning_rate": 0.0002348685714285714,
      "loss": 0.4066,
      "step": 5700
    },
    {
      "epoch": 6.628571428571428,
      "grad_norm": 1.0373749732971191,
      "learning_rate": 0.00023372571428571426,
      "loss": 0.4091,
      "step": 5800
    },
    {
      "epoch": 6.742857142857143,
      "grad_norm": 1.2542062997817993,
      "learning_rate": 0.0002325828571428571,
      "loss": 0.3926,
      "step": 5900
    },
    {
      "epoch": 6.857142857142857,
      "grad_norm": 1.4273713827133179,
      "learning_rate": 0.00023143999999999997,
      "loss": 0.3899,
      "step": 6000
    },
    {
      "epoch": 6.9714285714285715,
      "grad_norm": 1.169870376586914,
      "learning_rate": 0.00023029714285714283,
      "loss": 0.4092,
      "step": 6100
    },
    {
      "epoch": 7.085714285714285,
      "grad_norm": 1.1924947500228882,
      "learning_rate": 0.00022915428571428567,
      "loss": 0.3754,
      "step": 6200
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.349892497062683,
      "learning_rate": 0.00022801142857142856,
      "loss": 0.3537,
      "step": 6300
    },
    {
      "epoch": 7.314285714285714,
      "grad_norm": 1.2282274961471558,
      "learning_rate": 0.00022686857142857142,
      "loss": 0.3639,
      "step": 6400
    },
    {
      "epoch": 7.428571428571429,
      "grad_norm": 1.1712229251861572,
      "learning_rate": 0.0002257257142857143,
      "loss": 0.3688,
      "step": 6500
    },
    {
      "epoch": 7.542857142857143,
      "grad_norm": 2.2879111766815186,
      "learning_rate": 0.00022458285714285712,
      "loss": 0.3559,
      "step": 6600
    },
    {
      "epoch": 7.6571428571428575,
      "grad_norm": 1.1137748956680298,
      "learning_rate": 0.00022344,
      "loss": 0.3574,
      "step": 6700
    },
    {
      "epoch": 7.771428571428571,
      "grad_norm": 1.289184808731079,
      "learning_rate": 0.00022229714285714285,
      "loss": 0.3653,
      "step": 6800
    },
    {
      "epoch": 7.885714285714286,
      "grad_norm": 1.6281535625457764,
      "learning_rate": 0.0002211542857142857,
      "loss": 0.3476,
      "step": 6900
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.3460326194763184,
      "learning_rate": 0.00022001142857142855,
      "loss": 0.3606,
      "step": 7000
    },
    {
      "epoch": 8.114285714285714,
      "grad_norm": 1.2988694906234741,
      "learning_rate": 0.0002188685714285714,
      "loss": 0.3064,
      "step": 7100
    },
    {
      "epoch": 8.228571428571428,
      "grad_norm": 1.059658408164978,
      "learning_rate": 0.00021772571428571426,
      "loss": 0.333,
      "step": 7200
    },
    {
      "epoch": 8.342857142857143,
      "grad_norm": 1.6318204402923584,
      "learning_rate": 0.00021658285714285712,
      "loss": 0.3313,
      "step": 7300
    },
    {
      "epoch": 8.457142857142857,
      "grad_norm": 1.5393931865692139,
      "learning_rate": 0.00021543999999999996,
      "loss": 0.3133,
      "step": 7400
    },
    {
      "epoch": 8.571428571428571,
      "grad_norm": 1.6614785194396973,
      "learning_rate": 0.00021429714285714282,
      "loss": 0.3393,
      "step": 7500
    },
    {
      "epoch": 8.685714285714285,
      "grad_norm": 1.206910490989685,
      "learning_rate": 0.0002131542857142857,
      "loss": 0.3279,
      "step": 7600
    },
    {
      "epoch": 8.8,
      "grad_norm": 1.3397912979125977,
      "learning_rate": 0.00021201142857142858,
      "loss": 0.3342,
      "step": 7700
    },
    {
      "epoch": 8.914285714285715,
      "grad_norm": 1.1242660284042358,
      "learning_rate": 0.0002108685714285714,
      "loss": 0.3237,
      "step": 7800
    },
    {
      "epoch": 9.028571428571428,
      "grad_norm": 1.088550329208374,
      "learning_rate": 0.00020972571428571428,
      "loss": 0.3128,
      "step": 7900
    },
    {
      "epoch": 9.142857142857142,
      "grad_norm": 1.238797664642334,
      "learning_rate": 0.00020858285714285714,
      "loss": 0.2904,
      "step": 8000
    },
    {
      "epoch": 9.257142857142856,
      "grad_norm": 1.502020239830017,
      "learning_rate": 0.00020743999999999998,
      "loss": 0.2967,
      "step": 8100
    },
    {
      "epoch": 9.371428571428572,
      "grad_norm": 1.6706186532974243,
      "learning_rate": 0.00020629714285714284,
      "loss": 0.2889,
      "step": 8200
    },
    {
      "epoch": 9.485714285714286,
      "grad_norm": 1.4780162572860718,
      "learning_rate": 0.00020515428571428568,
      "loss": 0.3039,
      "step": 8300
    },
    {
      "epoch": 9.6,
      "grad_norm": 1.3221495151519775,
      "learning_rate": 0.00020401142857142854,
      "loss": 0.3087,
      "step": 8400
    },
    {
      "epoch": 9.714285714285714,
      "grad_norm": 1.9556879997253418,
      "learning_rate": 0.0002028685714285714,
      "loss": 0.3006,
      "step": 8500
    },
    {
      "epoch": 9.82857142857143,
      "grad_norm": 2.5484800338745117,
      "learning_rate": 0.00020172571428571425,
      "loss": 0.2918,
      "step": 8600
    },
    {
      "epoch": 9.942857142857143,
      "grad_norm": 1.202545166015625,
      "learning_rate": 0.0002005828571428571,
      "loss": 0.2955,
      "step": 8700
    },
    {
      "epoch": 10.057142857142857,
      "grad_norm": 1.2312058210372925,
      "learning_rate": 0.00019943999999999997,
      "loss": 0.2711,
      "step": 8800
    },
    {
      "epoch": 10.17142857142857,
      "grad_norm": 0.9658439755439758,
      "learning_rate": 0.00019829714285714287,
      "loss": 0.2536,
      "step": 8900
    },
    {
      "epoch": 10.285714285714286,
      "grad_norm": 1.4016692638397217,
      "learning_rate": 0.0001971542857142857,
      "loss": 0.2712,
      "step": 9000
    },
    {
      "epoch": 10.4,
      "grad_norm": 1.0595059394836426,
      "learning_rate": 0.00019601142857142857,
      "loss": 0.2631,
      "step": 9100
    },
    {
      "epoch": 10.514285714285714,
      "grad_norm": 1.6047881841659546,
      "learning_rate": 0.00019486857142857143,
      "loss": 0.2755,
      "step": 9200
    },
    {
      "epoch": 10.628571428571428,
      "grad_norm": 1.8473031520843506,
      "learning_rate": 0.00019372571428571427,
      "loss": 0.2783,
      "step": 9300
    },
    {
      "epoch": 10.742857142857144,
      "grad_norm": 1.9216639995574951,
      "learning_rate": 0.00019258285714285713,
      "loss": 0.2734,
      "step": 9400
    },
    {
      "epoch": 10.857142857142858,
      "grad_norm": 1.0926100015640259,
      "learning_rate": 0.00019143999999999997,
      "loss": 0.2778,
      "step": 9500
    },
    {
      "epoch": 10.971428571428572,
      "grad_norm": 1.4277852773666382,
      "learning_rate": 0.00019029714285714283,
      "loss": 0.2678,
      "step": 9600
    },
    {
      "epoch": 11.085714285714285,
      "grad_norm": 1.273311734199524,
      "learning_rate": 0.0001891542857142857,
      "loss": 0.2468,
      "step": 9700
    },
    {
      "epoch": 11.2,
      "grad_norm": 1.50382399559021,
      "learning_rate": 0.00018801142857142854,
      "loss": 0.2328,
      "step": 9800
    },
    {
      "epoch": 11.314285714285715,
      "grad_norm": 2.2691490650177,
      "learning_rate": 0.0001868685714285714,
      "loss": 0.246,
      "step": 9900
    },
    {
      "epoch": 11.428571428571429,
      "grad_norm": 1.2265568971633911,
      "learning_rate": 0.00018572571428571426,
      "loss": 0.2492,
      "step": 10000
    },
    {
      "epoch": 11.542857142857143,
      "grad_norm": 1.1587599515914917,
      "learning_rate": 0.0001845828571428571,
      "loss": 0.2453,
      "step": 10100
    },
    {
      "epoch": 11.657142857142857,
      "grad_norm": 1.1462079286575317,
      "learning_rate": 0.00018344,
      "loss": 0.253,
      "step": 10200
    },
    {
      "epoch": 11.771428571428572,
      "grad_norm": 1.9905078411102295,
      "learning_rate": 0.00018229714285714286,
      "loss": 0.2556,
      "step": 10300
    },
    {
      "epoch": 11.885714285714286,
      "grad_norm": 1.667157769203186,
      "learning_rate": 0.00018115428571428572,
      "loss": 0.249,
      "step": 10400
    },
    {
      "epoch": 12.0,
      "grad_norm": 1.08194899559021,
      "learning_rate": 0.00018001142857142856,
      "loss": 0.2404,
      "step": 10500
    },
    {
      "epoch": 12.114285714285714,
      "grad_norm": 1.2508606910705566,
      "learning_rate": 0.00017886857142857142,
      "loss": 0.2171,
      "step": 10600
    },
    {
      "epoch": 12.228571428571428,
      "grad_norm": 1.10196053981781,
      "learning_rate": 0.00017772571428571426,
      "loss": 0.2162,
      "step": 10700
    },
    {
      "epoch": 12.342857142857143,
      "grad_norm": 1.325040340423584,
      "learning_rate": 0.00017658285714285712,
      "loss": 0.2165,
      "step": 10800
    },
    {
      "epoch": 12.457142857142857,
      "grad_norm": 1.4882842302322388,
      "learning_rate": 0.00017544,
      "loss": 0.2207,
      "step": 10900
    },
    {
      "epoch": 12.571428571428571,
      "grad_norm": 1.2574632167816162,
      "learning_rate": 0.00017429714285714282,
      "loss": 0.2292,
      "step": 11000
    },
    {
      "epoch": 12.685714285714285,
      "grad_norm": 1.5161538124084473,
      "learning_rate": 0.0001731542857142857,
      "loss": 0.2216,
      "step": 11100
    },
    {
      "epoch": 12.8,
      "grad_norm": 1.5018984079360962,
      "learning_rate": 0.00017201142857142855,
      "loss": 0.2273,
      "step": 11200
    },
    {
      "epoch": 12.914285714285715,
      "grad_norm": 1.2884104251861572,
      "learning_rate": 0.0001708685714285714,
      "loss": 0.2243,
      "step": 11300
    },
    {
      "epoch": 13.028571428571428,
      "grad_norm": 1.378460168838501,
      "learning_rate": 0.00016972571428571428,
      "loss": 0.225,
      "step": 11400
    },
    {
      "epoch": 13.142857142857142,
      "grad_norm": 1.5688245296478271,
      "learning_rate": 0.00016858285714285715,
      "loss": 0.1992,
      "step": 11500
    },
    {
      "epoch": 13.257142857142856,
      "grad_norm": 1.3006786108016968,
      "learning_rate": 0.00016744,
      "loss": 0.2068,
      "step": 11600
    },
    {
      "epoch": 13.371428571428572,
      "grad_norm": 1.047890543937683,
      "learning_rate": 0.00016629714285714285,
      "loss": 0.1957,
      "step": 11700
    },
    {
      "epoch": 13.485714285714286,
      "grad_norm": 0.9967881441116333,
      "learning_rate": 0.0001651542857142857,
      "loss": 0.2058,
      "step": 11800
    },
    {
      "epoch": 13.6,
      "grad_norm": 1.4264742136001587,
      "learning_rate": 0.00016401142857142855,
      "loss": 0.2063,
      "step": 11900
    },
    {
      "epoch": 13.714285714285714,
      "grad_norm": 1.3013545274734497,
      "learning_rate": 0.0001628685714285714,
      "loss": 0.2032,
      "step": 12000
    },
    {
      "epoch": 13.82857142857143,
      "grad_norm": 1.3055994510650635,
      "learning_rate": 0.00016172571428571428,
      "loss": 0.2162,
      "step": 12100
    },
    {
      "epoch": 13.942857142857143,
      "grad_norm": 1.4893743991851807,
      "learning_rate": 0.00016058285714285711,
      "loss": 0.2081,
      "step": 12200
    },
    {
      "epoch": 14.057142857142857,
      "grad_norm": 1.4137383699417114,
      "learning_rate": 0.00015943999999999998,
      "loss": 0.1841,
      "step": 12300
    },
    {
      "epoch": 14.17142857142857,
      "grad_norm": 1.8859280347824097,
      "learning_rate": 0.00015829714285714284,
      "loss": 0.1857,
      "step": 12400
    },
    {
      "epoch": 14.285714285714286,
      "grad_norm": 1.5282500982284546,
      "learning_rate": 0.00015715428571428568,
      "loss": 0.1904,
      "step": 12500
    },
    {
      "epoch": 14.4,
      "grad_norm": 0.9001047015190125,
      "learning_rate": 0.00015601142857142854,
      "loss": 0.1853,
      "step": 12600
    },
    {
      "epoch": 14.514285714285714,
      "grad_norm": 1.1927658319473267,
      "learning_rate": 0.00015486857142857143,
      "loss": 0.1874,
      "step": 12700
    },
    {
      "epoch": 14.628571428571428,
      "grad_norm": 1.1758664846420288,
      "learning_rate": 0.0001537257142857143,
      "loss": 0.1754,
      "step": 12800
    },
    {
      "epoch": 14.742857142857144,
      "grad_norm": 1.1734734773635864,
      "learning_rate": 0.00015258285714285714,
      "loss": 0.1868,
      "step": 12900
    },
    {
      "epoch": 14.857142857142858,
      "grad_norm": 0.8678969740867615,
      "learning_rate": 0.00015144,
      "loss": 0.1795,
      "step": 13000
    },
    {
      "epoch": 14.971428571428572,
      "grad_norm": 2.2901735305786133,
      "learning_rate": 0.00015029714285714284,
      "loss": 0.1965,
      "step": 13100
    },
    {
      "epoch": 15.085714285714285,
      "grad_norm": 1.0252338647842407,
      "learning_rate": 0.0001491542857142857,
      "loss": 0.1649,
      "step": 13200
    },
    {
      "epoch": 15.2,
      "grad_norm": 1.1025043725967407,
      "learning_rate": 0.00014801142857142857,
      "loss": 0.1722,
      "step": 13300
    },
    {
      "epoch": 15.314285714285715,
      "grad_norm": 1.2872519493103027,
      "learning_rate": 0.0001468685714285714,
      "loss": 0.1694,
      "step": 13400
    },
    {
      "epoch": 15.428571428571429,
      "grad_norm": 2.815004348754883,
      "learning_rate": 0.00014572571428571427,
      "loss": 0.1758,
      "step": 13500
    },
    {
      "epoch": 15.542857142857143,
      "grad_norm": 1.7336875200271606,
      "learning_rate": 0.00014458285714285713,
      "loss": 0.1698,
      "step": 13600
    },
    {
      "epoch": 15.657142857142857,
      "grad_norm": 1.5906660556793213,
      "learning_rate": 0.00014344,
      "loss": 0.1554,
      "step": 13700
    },
    {
      "epoch": 15.771428571428572,
      "grad_norm": 1.0536751747131348,
      "learning_rate": 0.00014229714285714286,
      "loss": 0.1667,
      "step": 13800
    },
    {
      "epoch": 15.885714285714286,
      "grad_norm": 2.1150689125061035,
      "learning_rate": 0.0001411542857142857,
      "loss": 0.1725,
      "step": 13900
    },
    {
      "epoch": 16.0,
      "grad_norm": 2.3918333053588867,
      "learning_rate": 0.00014001142857142856,
      "loss": 0.1855,
      "step": 14000
    },
    {
      "epoch": 16.114285714285714,
      "grad_norm": 1.5179935693740845,
      "learning_rate": 0.00013886857142857143,
      "loss": 0.1509,
      "step": 14100
    },
    {
      "epoch": 16.228571428571428,
      "grad_norm": 1.0404243469238281,
      "learning_rate": 0.00013772571428571426,
      "loss": 0.1545,
      "step": 14200
    },
    {
      "epoch": 16.34285714285714,
      "grad_norm": 1.7319324016571045,
      "learning_rate": 0.00013658285714285713,
      "loss": 0.1553,
      "step": 14300
    },
    {
      "epoch": 16.457142857142856,
      "grad_norm": 1.694320797920227,
      "learning_rate": 0.00013544,
      "loss": 0.1543,
      "step": 14400
    },
    {
      "epoch": 16.571428571428573,
      "grad_norm": 1.1056307554244995,
      "learning_rate": 0.00013429714285714285,
      "loss": 0.1639,
      "step": 14500
    },
    {
      "epoch": 16.685714285714287,
      "grad_norm": 1.5444873571395874,
      "learning_rate": 0.0001331542857142857,
      "loss": 0.1575,
      "step": 14600
    },
    {
      "epoch": 16.8,
      "grad_norm": 1.3893969058990479,
      "learning_rate": 0.00013201142857142856,
      "loss": 0.163,
      "step": 14700
    },
    {
      "epoch": 16.914285714285715,
      "grad_norm": 1.6132880449295044,
      "learning_rate": 0.00013086857142857142,
      "loss": 0.1537,
      "step": 14800
    },
    {
      "epoch": 17.02857142857143,
      "grad_norm": 1.5396114587783813,
      "learning_rate": 0.00012972571428571426,
      "loss": 0.1548,
      "step": 14900
    },
    {
      "epoch": 17.142857142857142,
      "grad_norm": 1.0118181705474854,
      "learning_rate": 0.00012858285714285715,
      "loss": 0.1417,
      "step": 15000
    },
    {
      "epoch": 17.257142857142856,
      "grad_norm": 1.0827256441116333,
      "learning_rate": 0.00012743999999999999,
      "loss": 0.1418,
      "step": 15100
    },
    {
      "epoch": 17.37142857142857,
      "grad_norm": 1.5309821367263794,
      "learning_rate": 0.00012629714285714285,
      "loss": 0.1375,
      "step": 15200
    },
    {
      "epoch": 17.485714285714284,
      "grad_norm": 1.1401481628417969,
      "learning_rate": 0.00012515428571428571,
      "loss": 0.1465,
      "step": 15300
    },
    {
      "epoch": 17.6,
      "grad_norm": 1.150075912475586,
      "learning_rate": 0.00012401142857142855,
      "loss": 0.1421,
      "step": 15400
    },
    {
      "epoch": 17.714285714285715,
      "grad_norm": 1.1666033267974854,
      "learning_rate": 0.00012286857142857142,
      "loss": 0.1527,
      "step": 15500
    },
    {
      "epoch": 17.82857142857143,
      "grad_norm": 0.8309689164161682,
      "learning_rate": 0.00012172571428571428,
      "loss": 0.1505,
      "step": 15600
    },
    {
      "epoch": 17.942857142857143,
      "grad_norm": 1.5989408493041992,
      "learning_rate": 0.00012058285714285713,
      "loss": 0.1436,
      "step": 15700
    },
    {
      "epoch": 18.057142857142857,
      "grad_norm": 0.6489440202713013,
      "learning_rate": 0.00011944,
      "loss": 0.1375,
      "step": 15800
    },
    {
      "epoch": 18.17142857142857,
      "grad_norm": 1.6196086406707764,
      "learning_rate": 0.00011829714285714285,
      "loss": 0.1352,
      "step": 15900
    },
    {
      "epoch": 18.285714285714285,
      "grad_norm": 1.2241395711898804,
      "learning_rate": 0.0001171542857142857,
      "loss": 0.1313,
      "step": 16000
    },
    {
      "epoch": 18.4,
      "grad_norm": 0.9825499653816223,
      "learning_rate": 0.00011601142857142856,
      "loss": 0.1346,
      "step": 16100
    },
    {
      "epoch": 18.514285714285712,
      "grad_norm": 1.8467905521392822,
      "learning_rate": 0.00011486857142857142,
      "loss": 0.1334,
      "step": 16200
    },
    {
      "epoch": 18.62857142857143,
      "grad_norm": 1.0591373443603516,
      "learning_rate": 0.00011372571428571428,
      "loss": 0.1392,
      "step": 16300
    },
    {
      "epoch": 18.742857142857144,
      "grad_norm": 2.0883259773254395,
      "learning_rate": 0.00011258285714285714,
      "loss": 0.134,
      "step": 16400
    },
    {
      "epoch": 18.857142857142858,
      "grad_norm": 1.0738496780395508,
      "learning_rate": 0.00011143999999999999,
      "loss": 0.1338,
      "step": 16500
    },
    {
      "epoch": 18.97142857142857,
      "grad_norm": 1.3434749841690063,
      "learning_rate": 0.00011029714285714284,
      "loss": 0.1296,
      "step": 16600
    },
    {
      "epoch": 19.085714285714285,
      "grad_norm": 0.6826351284980774,
      "learning_rate": 0.0001091542857142857,
      "loss": 0.1221,
      "step": 16700
    },
    {
      "epoch": 19.2,
      "grad_norm": 1.7247623205184937,
      "learning_rate": 0.00010801142857142856,
      "loss": 0.1212,
      "step": 16800
    },
    {
      "epoch": 19.314285714285713,
      "grad_norm": 1.4077801704406738,
      "learning_rate": 0.00010686857142857142,
      "loss": 0.1204,
      "step": 16900
    },
    {
      "epoch": 19.428571428571427,
      "grad_norm": 0.789215624332428,
      "learning_rate": 0.00010572571428571428,
      "loss": 0.1184,
      "step": 17000
    },
    {
      "epoch": 19.542857142857144,
      "grad_norm": 2.175265073776245,
      "learning_rate": 0.00010458285714285713,
      "loss": 0.1231,
      "step": 17100
    },
    {
      "epoch": 19.65714285714286,
      "grad_norm": 1.1125848293304443,
      "learning_rate": 0.00010343999999999999,
      "loss": 0.1227,
      "step": 17200
    },
    {
      "epoch": 19.771428571428572,
      "grad_norm": 1.0844342708587646,
      "learning_rate": 0.00010229714285714285,
      "loss": 0.1255,
      "step": 17300
    },
    {
      "epoch": 19.885714285714286,
      "grad_norm": 0.6973736882209778,
      "learning_rate": 0.0001011542857142857,
      "loss": 0.1277,
      "step": 17400
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.9680613279342651,
      "learning_rate": 0.00010001142857142856,
      "loss": 0.1254,
      "step": 17500
    },
    {
      "epoch": 20.114285714285714,
      "grad_norm": 1.4217584133148193,
      "learning_rate": 9.886857142857143e-05,
      "loss": 0.1108,
      "step": 17600
    },
    {
      "epoch": 20.228571428571428,
      "grad_norm": 1.2597243785858154,
      "learning_rate": 9.772571428571428e-05,
      "loss": 0.1209,
      "step": 17700
    },
    {
      "epoch": 20.34285714285714,
      "grad_norm": 1.3436779975891113,
      "learning_rate": 9.658285714285713e-05,
      "loss": 0.1206,
      "step": 17800
    },
    {
      "epoch": 20.457142857142856,
      "grad_norm": 1.175439715385437,
      "learning_rate": 9.544e-05,
      "loss": 0.1164,
      "step": 17900
    },
    {
      "epoch": 20.571428571428573,
      "grad_norm": 1.3990012407302856,
      "learning_rate": 9.429714285714284e-05,
      "loss": 0.1144,
      "step": 18000
    },
    {
      "epoch": 20.685714285714287,
      "grad_norm": 1.0105007886886597,
      "learning_rate": 9.31542857142857e-05,
      "loss": 0.1135,
      "step": 18100
    },
    {
      "epoch": 20.8,
      "grad_norm": 1.1308010816574097,
      "learning_rate": 9.201142857142857e-05,
      "loss": 0.1141,
      "step": 18200
    },
    {
      "epoch": 20.914285714285715,
      "grad_norm": 0.7414535284042358,
      "learning_rate": 9.086857142857142e-05,
      "loss": 0.1208,
      "step": 18300
    },
    {
      "epoch": 21.02857142857143,
      "grad_norm": 0.8291124701499939,
      "learning_rate": 8.972571428571427e-05,
      "loss": 0.1049,
      "step": 18400
    },
    {
      "epoch": 21.142857142857142,
      "grad_norm": 0.7733851671218872,
      "learning_rate": 8.858285714285714e-05,
      "loss": 0.1071,
      "step": 18500
    },
    {
      "epoch": 21.257142857142856,
      "grad_norm": 2.2193784713745117,
      "learning_rate": 8.743999999999999e-05,
      "loss": 0.102,
      "step": 18600
    },
    {
      "epoch": 21.37142857142857,
      "grad_norm": 1.0695987939834595,
      "learning_rate": 8.629714285714284e-05,
      "loss": 0.106,
      "step": 18700
    },
    {
      "epoch": 21.485714285714284,
      "grad_norm": 1.0461671352386475,
      "learning_rate": 8.515428571428572e-05,
      "loss": 0.107,
      "step": 18800
    },
    {
      "epoch": 21.6,
      "grad_norm": 1.5757765769958496,
      "learning_rate": 8.401142857142857e-05,
      "loss": 0.106,
      "step": 18900
    },
    {
      "epoch": 21.714285714285715,
      "grad_norm": 1.9472708702087402,
      "learning_rate": 8.286857142857142e-05,
      "loss": 0.108,
      "step": 19000
    },
    {
      "epoch": 21.82857142857143,
      "grad_norm": 0.9918070435523987,
      "learning_rate": 8.172571428571428e-05,
      "loss": 0.1152,
      "step": 19100
    },
    {
      "epoch": 21.942857142857143,
      "grad_norm": 1.0311241149902344,
      "learning_rate": 8.058285714285713e-05,
      "loss": 0.1047,
      "step": 19200
    },
    {
      "epoch": 22.057142857142857,
      "grad_norm": 1.0554375648498535,
      "learning_rate": 7.943999999999998e-05,
      "loss": 0.1076,
      "step": 19300
    },
    {
      "epoch": 22.17142857142857,
      "grad_norm": 0.7874680757522583,
      "learning_rate": 7.829714285714286e-05,
      "loss": 0.0997,
      "step": 19400
    },
    {
      "epoch": 22.285714285714285,
      "grad_norm": 1.1105536222457886,
      "learning_rate": 7.715428571428571e-05,
      "loss": 0.1,
      "step": 19500
    },
    {
      "epoch": 22.4,
      "grad_norm": 1.0579336881637573,
      "learning_rate": 7.601142857142856e-05,
      "loss": 0.0963,
      "step": 19600
    },
    {
      "epoch": 22.514285714285712,
      "grad_norm": 1.0726921558380127,
      "learning_rate": 7.486857142857143e-05,
      "loss": 0.1005,
      "step": 19700
    },
    {
      "epoch": 22.62857142857143,
      "grad_norm": 1.0421086549758911,
      "learning_rate": 7.372571428571428e-05,
      "loss": 0.0976,
      "step": 19800
    },
    {
      "epoch": 22.742857142857144,
      "grad_norm": 1.198748230934143,
      "learning_rate": 7.258285714285714e-05,
      "loss": 0.1059,
      "step": 19900
    },
    {
      "epoch": 22.857142857142858,
      "grad_norm": 1.479467749595642,
      "learning_rate": 7.144e-05,
      "loss": 0.0993,
      "step": 20000
    },
    {
      "epoch": 22.97142857142857,
      "grad_norm": 1.1370179653167725,
      "learning_rate": 7.029714285714284e-05,
      "loss": 0.1021,
      "step": 20100
    },
    {
      "epoch": 23.085714285714285,
      "grad_norm": 0.9663624167442322,
      "learning_rate": 6.915428571428571e-05,
      "loss": 0.0956,
      "step": 20200
    },
    {
      "epoch": 23.2,
      "grad_norm": 0.6943888664245605,
      "learning_rate": 6.801142857142857e-05,
      "loss": 0.0994,
      "step": 20300
    },
    {
      "epoch": 23.314285714285713,
      "grad_norm": 1.3604183197021484,
      "learning_rate": 6.686857142857142e-05,
      "loss": 0.0963,
      "step": 20400
    },
    {
      "epoch": 23.428571428571427,
      "grad_norm": 1.3610256910324097,
      "learning_rate": 6.572571428571427e-05,
      "loss": 0.0956,
      "step": 20500
    },
    {
      "epoch": 23.542857142857144,
      "grad_norm": 1.2277686595916748,
      "learning_rate": 6.458285714285714e-05,
      "loss": 0.0953,
      "step": 20600
    },
    {
      "epoch": 23.65714285714286,
      "grad_norm": 1.1448625326156616,
      "learning_rate": 6.343999999999999e-05,
      "loss": 0.0954,
      "step": 20700
    },
    {
      "epoch": 23.771428571428572,
      "grad_norm": 0.8833436369895935,
      "learning_rate": 6.229714285714285e-05,
      "loss": 0.0968,
      "step": 20800
    },
    {
      "epoch": 23.885714285714286,
      "grad_norm": 1.0425817966461182,
      "learning_rate": 6.115428571428572e-05,
      "loss": 0.094,
      "step": 20900
    },
    {
      "epoch": 24.0,
      "grad_norm": 1.7617619037628174,
      "learning_rate": 6.001142857142857e-05,
      "loss": 0.098,
      "step": 21000
    },
    {
      "epoch": 24.114285714285714,
      "grad_norm": 0.7041512131690979,
      "learning_rate": 5.886857142857142e-05,
      "loss": 0.0891,
      "step": 21100
    },
    {
      "epoch": 24.228571428571428,
      "grad_norm": 1.3548294305801392,
      "learning_rate": 5.772571428571428e-05,
      "loss": 0.0937,
      "step": 21200
    },
    {
      "epoch": 24.34285714285714,
      "grad_norm": 1.0486685037612915,
      "learning_rate": 5.658285714285714e-05,
      "loss": 0.0947,
      "step": 21300
    },
    {
      "epoch": 24.457142857142856,
      "grad_norm": 1.6215624809265137,
      "learning_rate": 5.543999999999999e-05,
      "loss": 0.0934,
      "step": 21400
    },
    {
      "epoch": 24.571428571428573,
      "grad_norm": 1.0335862636566162,
      "learning_rate": 5.4297142857142855e-05,
      "loss": 0.088,
      "step": 21500
    },
    {
      "epoch": 24.685714285714287,
      "grad_norm": 1.3150044679641724,
      "learning_rate": 5.315428571428571e-05,
      "loss": 0.0957,
      "step": 21600
    },
    {
      "epoch": 24.8,
      "grad_norm": 1.3469773530960083,
      "learning_rate": 5.201142857142856e-05,
      "loss": 0.0893,
      "step": 21700
    },
    {
      "epoch": 24.914285714285715,
      "grad_norm": 0.7123535871505737,
      "learning_rate": 5.086857142857143e-05,
      "loss": 0.0833,
      "step": 21800
    },
    {
      "epoch": 25.02857142857143,
      "grad_norm": 0.9019558429718018,
      "learning_rate": 4.9725714285714285e-05,
      "loss": 0.084,
      "step": 21900
    },
    {
      "epoch": 25.142857142857142,
      "grad_norm": 1.2943990230560303,
      "learning_rate": 4.8582857142857136e-05,
      "loss": 0.0786,
      "step": 22000
    },
    {
      "epoch": 25.257142857142856,
      "grad_norm": 1.431429386138916,
      "learning_rate": 4.743999999999999e-05,
      "loss": 0.0882,
      "step": 22100
    },
    {
      "epoch": 25.37142857142857,
      "grad_norm": 0.8068431615829468,
      "learning_rate": 4.629714285714286e-05,
      "loss": 0.0846,
      "step": 22200
    },
    {
      "epoch": 25.485714285714284,
      "grad_norm": 1.0088834762573242,
      "learning_rate": 4.515428571428571e-05,
      "loss": 0.0832,
      "step": 22300
    },
    {
      "epoch": 25.6,
      "grad_norm": 1.1686701774597168,
      "learning_rate": 4.4011428571428565e-05,
      "loss": 0.0761,
      "step": 22400
    },
    {
      "epoch": 25.714285714285715,
      "grad_norm": 1.5640618801116943,
      "learning_rate": 4.286857142857143e-05,
      "loss": 0.0894,
      "step": 22500
    },
    {
      "epoch": 25.82857142857143,
      "grad_norm": 1.4497385025024414,
      "learning_rate": 4.172571428571428e-05,
      "loss": 0.0917,
      "step": 22600
    },
    {
      "epoch": 25.942857142857143,
      "grad_norm": 1.151632308959961,
      "learning_rate": 4.058285714285714e-05,
      "loss": 0.0826,
      "step": 22700
    },
    {
      "epoch": 26.057142857142857,
      "grad_norm": 1.5499285459518433,
      "learning_rate": 3.944e-05,
      "loss": 0.0826,
      "step": 22800
    },
    {
      "epoch": 26.17142857142857,
      "grad_norm": 1.4620537757873535,
      "learning_rate": 3.829714285714285e-05,
      "loss": 0.0843,
      "step": 22900
    },
    {
      "epoch": 26.285714285714285,
      "grad_norm": 0.7379088401794434,
      "learning_rate": 3.715428571428571e-05,
      "loss": 0.0748,
      "step": 23000
    },
    {
      "epoch": 26.4,
      "grad_norm": 0.5435966849327087,
      "learning_rate": 3.601142857142857e-05,
      "loss": 0.0758,
      "step": 23100
    },
    {
      "epoch": 26.514285714285712,
      "grad_norm": 0.7340735197067261,
      "learning_rate": 3.4868571428571425e-05,
      "loss": 0.0836,
      "step": 23200
    },
    {
      "epoch": 26.62857142857143,
      "grad_norm": 0.8306871056556702,
      "learning_rate": 3.372571428571428e-05,
      "loss": 0.0848,
      "step": 23300
    },
    {
      "epoch": 26.742857142857144,
      "grad_norm": 1.6395269632339478,
      "learning_rate": 3.258285714285714e-05,
      "loss": 0.0804,
      "step": 23400
    },
    {
      "epoch": 26.857142857142858,
      "grad_norm": 1.2032523155212402,
      "learning_rate": 3.144e-05,
      "loss": 0.0804,
      "step": 23500
    },
    {
      "epoch": 26.97142857142857,
      "grad_norm": 1.6825361251831055,
      "learning_rate": 3.0297142857142855e-05,
      "loss": 0.0827,
      "step": 23600
    },
    {
      "epoch": 27.085714285714285,
      "grad_norm": 1.4704478979110718,
      "learning_rate": 2.9154285714285712e-05,
      "loss": 0.0804,
      "step": 23700
    },
    {
      "epoch": 27.2,
      "grad_norm": 1.5141932964324951,
      "learning_rate": 2.801142857142857e-05,
      "loss": 0.0748,
      "step": 23800
    },
    {
      "epoch": 27.314285714285713,
      "grad_norm": 0.6547297835350037,
      "learning_rate": 2.6868571428571427e-05,
      "loss": 0.0791,
      "step": 23900
    },
    {
      "epoch": 27.428571428571427,
      "grad_norm": 1.112829327583313,
      "learning_rate": 2.5725714285714284e-05,
      "loss": 0.0781,
      "step": 24000
    },
    {
      "epoch": 27.542857142857144,
      "grad_norm": 1.1256695985794067,
      "learning_rate": 2.458285714285714e-05,
      "loss": 0.0828,
      "step": 24100
    },
    {
      "epoch": 27.65714285714286,
      "grad_norm": 1.4872969388961792,
      "learning_rate": 2.344e-05,
      "loss": 0.0793,
      "step": 24200
    },
    {
      "epoch": 27.771428571428572,
      "grad_norm": 1.0138152837753296,
      "learning_rate": 2.2297142857142857e-05,
      "loss": 0.0794,
      "step": 24300
    },
    {
      "epoch": 27.885714285714286,
      "grad_norm": 1.5701348781585693,
      "learning_rate": 2.115428571428571e-05,
      "loss": 0.079,
      "step": 24400
    },
    {
      "epoch": 28.0,
      "grad_norm": 1.4342325925827026,
      "learning_rate": 2.001142857142857e-05,
      "loss": 0.0815,
      "step": 24500
    },
    {
      "epoch": 28.114285714285714,
      "grad_norm": 0.6444075107574463,
      "learning_rate": 1.886857142857143e-05,
      "loss": 0.082,
      "step": 24600
    },
    {
      "epoch": 28.228571428571428,
      "grad_norm": 1.483933448791504,
      "learning_rate": 1.7725714285714283e-05,
      "loss": 0.0743,
      "step": 24700
    },
    {
      "epoch": 28.34285714285714,
      "grad_norm": 0.6548141241073608,
      "learning_rate": 1.6582857142857144e-05,
      "loss": 0.0755,
      "step": 24800
    },
    {
      "epoch": 28.457142857142856,
      "grad_norm": 1.0112509727478027,
      "learning_rate": 1.5439999999999998e-05,
      "loss": 0.0752,
      "step": 24900
    },
    {
      "epoch": 28.571428571428573,
      "grad_norm": 0.8533725738525391,
      "learning_rate": 1.4297142857142855e-05,
      "loss": 0.0819,
      "step": 25000
    },
    {
      "epoch": 28.685714285714287,
      "grad_norm": 1.2526988983154297,
      "learning_rate": 1.3154285714285713e-05,
      "loss": 0.0725,
      "step": 25100
    },
    {
      "epoch": 28.8,
      "grad_norm": 0.8007093667984009,
      "learning_rate": 1.2011428571428572e-05,
      "loss": 0.0764,
      "step": 25200
    },
    {
      "epoch": 28.914285714285715,
      "grad_norm": 0.9422992467880249,
      "learning_rate": 1.0868571428571428e-05,
      "loss": 0.0743,
      "step": 25300
    },
    {
      "epoch": 29.02857142857143,
      "grad_norm": 0.9128634333610535,
      "learning_rate": 9.725714285714285e-06,
      "loss": 0.0754,
      "step": 25400
    },
    {
      "epoch": 29.142857142857142,
      "grad_norm": 1.241011619567871,
      "learning_rate": 8.582857142857142e-06,
      "loss": 0.077,
      "step": 25500
    },
    {
      "epoch": 29.257142857142856,
      "grad_norm": 1.006628394126892,
      "learning_rate": 7.439999999999999e-06,
      "loss": 0.0689,
      "step": 25600
    },
    {
      "epoch": 29.37142857142857,
      "grad_norm": 1.3787076473236084,
      "learning_rate": 6.2971428571428565e-06,
      "loss": 0.0789,
      "step": 25700
    },
    {
      "epoch": 29.485714285714284,
      "grad_norm": 1.1843293905258179,
      "learning_rate": 5.154285714285714e-06,
      "loss": 0.0746,
      "step": 25800
    },
    {
      "epoch": 29.6,
      "grad_norm": 0.8705450296401978,
      "learning_rate": 4.0114285714285705e-06,
      "loss": 0.0754,
      "step": 25900
    },
    {
      "epoch": 29.714285714285715,
      "grad_norm": 1.1954331398010254,
      "learning_rate": 2.868571428571428e-06,
      "loss": 0.0716,
      "step": 26000
    },
    {
      "epoch": 29.82857142857143,
      "grad_norm": 0.8840579986572266,
      "learning_rate": 1.7257142857142856e-06,
      "loss": 0.0802,
      "step": 26100
    },
    {
      "epoch": 29.942857142857143,
      "grad_norm": 0.8856578469276428,
      "learning_rate": 5.828571428571428e-07,
      "loss": 0.076,
      "step": 26200
    }
  ],
  "logging_steps": 100,
  "max_steps": 26250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7105444577280000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}