{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11988217967599411,
  "eval_steps": 500,
  "global_step": 2035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000589101620029455,
      "grad_norm": 1.1187952756881714,
      "learning_rate": 2.910112359550562e-06,
      "loss": 0.7831,
      "step": 10
    },
    {
      "epoch": 0.00117820324005891,
      "grad_norm": 1.0689250230789185,
      "learning_rate": 3.921348314606742e-06,
      "loss": 0.8085,
      "step": 20
    },
    {
      "epoch": 0.0017673048600883653,
      "grad_norm": 0.741685688495636,
      "learning_rate": 4.932584269662922e-06,
      "loss": 0.7525,
      "step": 30
    },
    {
      "epoch": 0.00235640648011782,
      "grad_norm": 0.8915156722068787,
      "learning_rate": 5.943820224719102e-06,
      "loss": 0.7265,
      "step": 40
    },
    {
      "epoch": 0.0029455081001472753,
      "grad_norm": 0.6924229264259338,
      "learning_rate": 6.955056179775282e-06,
      "loss": 0.7388,
      "step": 50
    },
    {
      "epoch": 0.0035346097201767305,
      "grad_norm": 0.7231901288032532,
      "learning_rate": 7.966292134831462e-06,
      "loss": 0.7317,
      "step": 60
    },
    {
      "epoch": 0.004123711340206186,
      "grad_norm": 0.7959139943122864,
      "learning_rate": 8.977528089887641e-06,
      "loss": 0.7457,
      "step": 70
    },
    {
      "epoch": 0.00471281296023564,
      "grad_norm": 0.8100572824478149,
      "learning_rate": 9.988764044943822e-06,
      "loss": 0.7577,
      "step": 80
    },
    {
      "epoch": 0.005301914580265096,
      "grad_norm": 0.7159477472305298,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.7537,
      "step": 90
    },
    {
      "epoch": 0.005891016200294551,
      "grad_norm": 0.8149115443229675,
      "learning_rate": 1.2011235955056182e-05,
      "loss": 0.7762,
      "step": 100
    },
    {
      "epoch": 0.006480117820324006,
      "grad_norm": 0.8290235996246338,
      "learning_rate": 1.3022471910112362e-05,
      "loss": 0.7777,
      "step": 110
    },
    {
      "epoch": 0.007069219440353461,
      "grad_norm": 0.7166168093681335,
      "learning_rate": 1.403370786516854e-05,
      "loss": 0.7597,
      "step": 120
    },
    {
      "epoch": 0.007658321060382916,
      "grad_norm": 0.8164111375808716,
      "learning_rate": 1.504494382022472e-05,
      "loss": 0.7249,
      "step": 130
    },
    {
      "epoch": 0.008247422680412371,
      "grad_norm": 0.7679075598716736,
      "learning_rate": 1.60561797752809e-05,
      "loss": 0.7427,
      "step": 140
    },
    {
      "epoch": 0.008836524300441826,
      "grad_norm": 0.7330767512321472,
      "learning_rate": 1.706741573033708e-05,
      "loss": 0.7465,
      "step": 150
    },
    {
      "epoch": 0.00942562592047128,
      "grad_norm": 0.6833717823028564,
      "learning_rate": 1.8078651685393256e-05,
      "loss": 0.7656,
      "step": 160
    },
    {
      "epoch": 0.010014727540500737,
      "grad_norm": 0.7289340496063232,
      "learning_rate": 1.908988764044944e-05,
      "loss": 0.7791,
      "step": 170
    },
    {
      "epoch": 0.010603829160530192,
      "grad_norm": 0.6722760200500488,
      "learning_rate": 2e-05,
      "loss": 0.7861,
      "step": 180
    },
    {
      "epoch": 0.011192930780559647,
      "grad_norm": 0.6587191820144653,
      "learning_rate": 2e-05,
      "loss": 0.7593,
      "step": 190
    },
    {
      "epoch": 0.011782032400589101,
      "grad_norm": 1.342365026473999,
      "learning_rate": 2e-05,
      "loss": 0.7532,
      "step": 200
    },
    {
      "epoch": 0.012371134020618556,
      "grad_norm": 0.7734410166740417,
      "learning_rate": 2e-05,
      "loss": 0.7475,
      "step": 210
    },
    {
      "epoch": 0.012960235640648013,
      "grad_norm": 0.6449353098869324,
      "learning_rate": 2e-05,
      "loss": 0.7669,
      "step": 220
    },
    {
      "epoch": 0.013549337260677467,
      "grad_norm": 0.6131564378738403,
      "learning_rate": 2e-05,
      "loss": 0.7472,
      "step": 230
    },
    {
      "epoch": 0.014138438880706922,
      "grad_norm": 0.7450922131538391,
      "learning_rate": 2e-05,
      "loss": 0.7685,
      "step": 240
    },
    {
      "epoch": 0.014727540500736377,
      "grad_norm": 0.5752319693565369,
      "learning_rate": 2e-05,
      "loss": 0.7504,
      "step": 250
    },
    {
      "epoch": 0.015316642120765831,
      "grad_norm": 0.5238183736801147,
      "learning_rate": 2e-05,
      "loss": 0.7503,
      "step": 260
    },
    {
      "epoch": 0.015905743740795286,
      "grad_norm": 0.6273600459098816,
      "learning_rate": 2e-05,
      "loss": 0.7511,
      "step": 270
    },
    {
      "epoch": 0.016494845360824743,
      "grad_norm": 0.4939355254173279,
      "learning_rate": 2e-05,
      "loss": 0.7819,
      "step": 280
    },
    {
      "epoch": 0.017083946980854196,
      "grad_norm": 0.7005998492240906,
      "learning_rate": 2e-05,
      "loss": 0.7411,
      "step": 290
    },
    {
      "epoch": 0.017673048600883652,
      "grad_norm": 0.5144055485725403,
      "learning_rate": 2e-05,
      "loss": 0.7529,
      "step": 300
    },
    {
      "epoch": 0.01826215022091311,
      "grad_norm": 0.4719701111316681,
      "learning_rate": 2e-05,
      "loss": 0.755,
      "step": 310
    },
    {
      "epoch": 0.01885125184094256,
      "grad_norm": 0.5226520299911499,
      "learning_rate": 2e-05,
      "loss": 0.7586,
      "step": 320
    },
    {
      "epoch": 0.019440353460972018,
      "grad_norm": 0.5080249309539795,
      "learning_rate": 2e-05,
      "loss": 0.753,
      "step": 330
    },
    {
      "epoch": 0.020029455081001474,
      "grad_norm": 0.46481338143348694,
      "learning_rate": 2e-05,
      "loss": 0.7675,
      "step": 340
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 0.46027958393096924,
      "learning_rate": 2e-05,
      "loss": 0.7389,
      "step": 350
    },
    {
      "epoch": 0.021207658321060384,
      "grad_norm": 0.49125781655311584,
      "learning_rate": 2e-05,
      "loss": 0.758,
      "step": 360
    },
    {
      "epoch": 0.021796759941089837,
      "grad_norm": 0.4505169987678528,
      "learning_rate": 2e-05,
      "loss": 0.7586,
      "step": 370
    },
    {
      "epoch": 0.022385861561119293,
      "grad_norm": 0.5151411890983582,
      "learning_rate": 2e-05,
      "loss": 0.7431,
      "step": 380
    },
    {
      "epoch": 0.02297496318114875,
      "grad_norm": 0.4783925712108612,
      "learning_rate": 2e-05,
      "loss": 0.7412,
      "step": 390
    },
    {
      "epoch": 0.023564064801178203,
      "grad_norm": 0.4741362929344177,
      "learning_rate": 2e-05,
      "loss": 0.7413,
      "step": 400
    },
    {
      "epoch": 0.02415316642120766,
      "grad_norm": 0.46201640367507935,
      "learning_rate": 2e-05,
      "loss": 0.7445,
      "step": 410
    },
    {
      "epoch": 0.024742268041237112,
      "grad_norm": 0.4987025558948517,
      "learning_rate": 2e-05,
      "loss": 0.7517,
      "step": 420
    },
    {
      "epoch": 0.02533136966126657,
      "grad_norm": 0.4851631820201874,
      "learning_rate": 2e-05,
      "loss": 0.7594,
      "step": 430
    },
    {
      "epoch": 0.025920471281296025,
      "grad_norm": 0.47743213176727295,
      "learning_rate": 2e-05,
      "loss": 0.7565,
      "step": 440
    },
    {
      "epoch": 0.026509572901325478,
      "grad_norm": 0.5171688199043274,
      "learning_rate": 2e-05,
      "loss": 0.7569,
      "step": 450
    },
    {
      "epoch": 0.027098674521354935,
      "grad_norm": 0.5514922142028809,
      "learning_rate": 2e-05,
      "loss": 0.7244,
      "step": 460
    },
    {
      "epoch": 0.027687776141384388,
      "grad_norm": 0.4684111177921295,
      "learning_rate": 2e-05,
      "loss": 0.7346,
      "step": 470
    },
    {
      "epoch": 0.028276877761413844,
      "grad_norm": 0.49709105491638184,
      "learning_rate": 2e-05,
      "loss": 0.7644,
      "step": 480
    },
    {
      "epoch": 0.0288659793814433,
      "grad_norm": 0.4689137935638428,
      "learning_rate": 2e-05,
      "loss": 0.7314,
      "step": 490
    },
    {
      "epoch": 0.029455081001472753,
      "grad_norm": 0.48819467425346375,
      "learning_rate": 2e-05,
      "loss": 0.7665,
      "step": 500
    },
    {
      "epoch": 0.03004418262150221,
      "grad_norm": 0.46228793263435364,
      "learning_rate": 2e-05,
      "loss": 0.7693,
      "step": 510
    },
    {
      "epoch": 0.030633284241531663,
      "grad_norm": 0.4367271661758423,
      "learning_rate": 2e-05,
      "loss": 0.739,
      "step": 520
    },
    {
      "epoch": 0.03122238586156112,
      "grad_norm": 0.4632743000984192,
      "learning_rate": 2e-05,
      "loss": 0.7376,
      "step": 530
    },
    {
      "epoch": 0.03181148748159057,
      "grad_norm": 0.47965553402900696,
      "learning_rate": 2e-05,
      "loss": 0.7633,
      "step": 540
    },
    {
      "epoch": 0.03240058910162003,
      "grad_norm": 0.48231041431427,
      "learning_rate": 2e-05,
      "loss": 0.7412,
      "step": 550
    },
    {
      "epoch": 0.032989690721649485,
      "grad_norm": 0.48584654927253723,
      "learning_rate": 2e-05,
      "loss": 0.7347,
      "step": 560
    },
    {
      "epoch": 0.03357879234167894,
      "grad_norm": 0.45019200444221497,
      "learning_rate": 2e-05,
      "loss": 0.755,
      "step": 570
    },
    {
      "epoch": 0.03416789396170839,
      "grad_norm": 0.44921109080314636,
      "learning_rate": 2e-05,
      "loss": 0.7483,
      "step": 580
    },
    {
      "epoch": 0.03475699558173785,
      "grad_norm": 0.45112189650535583,
      "learning_rate": 2e-05,
      "loss": 0.7656,
      "step": 590
    },
    {
      "epoch": 0.035346097201767304,
      "grad_norm": 0.4544597268104553,
      "learning_rate": 2e-05,
      "loss": 0.7557,
      "step": 600
    },
    {
      "epoch": 0.03593519882179676,
      "grad_norm": 0.5381441712379456,
      "learning_rate": 2e-05,
      "loss": 0.7488,
      "step": 610
    },
    {
      "epoch": 0.03652430044182622,
      "grad_norm": 0.42246851325035095,
      "learning_rate": 2e-05,
      "loss": 0.7706,
      "step": 620
    },
    {
      "epoch": 0.03711340206185567,
      "grad_norm": 0.4562056362628937,
      "learning_rate": 2e-05,
      "loss": 0.7692,
      "step": 630
    },
    {
      "epoch": 0.03770250368188512,
      "grad_norm": 0.45282721519470215,
      "learning_rate": 2e-05,
      "loss": 0.7365,
      "step": 640
    },
    {
      "epoch": 0.03829160530191458,
      "grad_norm": 0.4427643120288849,
      "learning_rate": 2e-05,
      "loss": 0.7497,
      "step": 650
    },
    {
      "epoch": 0.038880706921944036,
      "grad_norm": 0.4979972839355469,
      "learning_rate": 2e-05,
      "loss": 0.7486,
      "step": 660
    },
    {
      "epoch": 0.03946980854197349,
      "grad_norm": 0.42347976565361023,
      "learning_rate": 2e-05,
      "loss": 0.7343,
      "step": 670
    },
    {
      "epoch": 0.04005891016200295,
      "grad_norm": 0.4554508924484253,
      "learning_rate": 2e-05,
      "loss": 0.7442,
      "step": 680
    },
    {
      "epoch": 0.0406480117820324,
      "grad_norm": 0.46228188276290894,
      "learning_rate": 2e-05,
      "loss": 0.7706,
      "step": 690
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 0.44366255402565,
      "learning_rate": 2e-05,
      "loss": 0.7382,
      "step": 700
    },
    {
      "epoch": 0.04182621502209131,
      "grad_norm": 0.418224573135376,
      "learning_rate": 2e-05,
      "loss": 0.7221,
      "step": 710
    },
    {
      "epoch": 0.04241531664212077,
      "grad_norm": 0.4644136428833008,
      "learning_rate": 2e-05,
      "loss": 0.7238,
      "step": 720
    },
    {
      "epoch": 0.04300441826215022,
      "grad_norm": 0.4094725251197815,
      "learning_rate": 2e-05,
      "loss": 0.7274,
      "step": 730
    },
    {
      "epoch": 0.043593519882179674,
      "grad_norm": 0.431404173374176,
      "learning_rate": 2e-05,
      "loss": 0.7346,
      "step": 740
    },
    {
      "epoch": 0.044182621502209134,
      "grad_norm": 0.45599696040153503,
      "learning_rate": 2e-05,
      "loss": 0.7257,
      "step": 750
    },
    {
      "epoch": 0.04477172312223859,
      "grad_norm": 0.4296494424343109,
      "learning_rate": 2e-05,
      "loss": 0.7408,
      "step": 760
    },
    {
      "epoch": 0.04536082474226804,
      "grad_norm": 0.44864070415496826,
      "learning_rate": 2e-05,
      "loss": 0.7327,
      "step": 770
    },
    {
      "epoch": 0.0459499263622975,
      "grad_norm": 0.4230384826660156,
      "learning_rate": 2e-05,
      "loss": 0.7599,
      "step": 780
    },
    {
      "epoch": 0.04653902798232695,
      "grad_norm": 0.4637373685836792,
      "learning_rate": 2e-05,
      "loss": 0.7239,
      "step": 790
    },
    {
      "epoch": 0.047128129602356406,
      "grad_norm": 0.5369905233383179,
      "learning_rate": 2e-05,
      "loss": 0.7488,
      "step": 800
    },
    {
      "epoch": 0.04771723122238586,
      "grad_norm": 0.492144912481308,
      "learning_rate": 2e-05,
      "loss": 0.752,
      "step": 810
    },
    {
      "epoch": 0.04830633284241532,
      "grad_norm": 0.4071194529533386,
      "learning_rate": 2e-05,
      "loss": 0.7192,
      "step": 820
    },
    {
      "epoch": 0.04889543446244477,
      "grad_norm": 0.44176292419433594,
      "learning_rate": 2e-05,
      "loss": 0.7558,
      "step": 830
    },
    {
      "epoch": 0.049484536082474224,
      "grad_norm": 0.4265081286430359,
      "learning_rate": 2e-05,
      "loss": 0.7669,
      "step": 840
    },
    {
      "epoch": 0.050073637702503684,
      "grad_norm": 0.4696004092693329,
      "learning_rate": 2e-05,
      "loss": 0.7304,
      "step": 850
    },
    {
      "epoch": 0.05066273932253314,
      "grad_norm": 0.5208477973937988,
      "learning_rate": 2e-05,
      "loss": 0.7265,
      "step": 860
    },
    {
      "epoch": 0.05125184094256259,
      "grad_norm": 0.5095232725143433,
      "learning_rate": 2e-05,
      "loss": 0.7576,
      "step": 870
    },
    {
      "epoch": 0.05184094256259205,
      "grad_norm": 0.4431394934654236,
      "learning_rate": 2e-05,
      "loss": 0.7343,
      "step": 880
    },
    {
      "epoch": 0.0524300441826215,
      "grad_norm": 0.4195699989795685,
      "learning_rate": 2e-05,
      "loss": 0.738,
      "step": 890
    },
    {
      "epoch": 0.053019145802650956,
      "grad_norm": 0.4056459069252014,
      "learning_rate": 2e-05,
      "loss": 0.7368,
      "step": 900
    },
    {
      "epoch": 0.05360824742268041,
      "grad_norm": 0.4221668243408203,
      "learning_rate": 2e-05,
      "loss": 0.762,
      "step": 910
    },
    {
      "epoch": 0.05419734904270987,
      "grad_norm": 0.4228168725967407,
      "learning_rate": 2e-05,
      "loss": 0.7391,
      "step": 920
    },
    {
      "epoch": 0.05478645066273932,
      "grad_norm": 0.4960448741912842,
      "learning_rate": 2e-05,
      "loss": 0.7296,
      "step": 930
    },
    {
      "epoch": 0.055375552282768775,
      "grad_norm": 0.4253543019294739,
      "learning_rate": 2e-05,
      "loss": 0.727,
      "step": 940
    },
    {
      "epoch": 0.055964653902798235,
      "grad_norm": 0.46824753284454346,
      "learning_rate": 2e-05,
      "loss": 0.7394,
      "step": 950
    },
    {
      "epoch": 0.05655375552282769,
      "grad_norm": 0.5169887542724609,
      "learning_rate": 2e-05,
      "loss": 0.7303,
      "step": 960
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 0.43343982100486755,
      "learning_rate": 2e-05,
      "loss": 0.735,
      "step": 970
    },
    {
      "epoch": 0.0577319587628866,
      "grad_norm": 1.695380687713623,
      "learning_rate": 2e-05,
      "loss": 0.7665,
      "step": 980
    },
    {
      "epoch": 0.058321060382916054,
      "grad_norm": 0.41318148374557495,
      "learning_rate": 2e-05,
      "loss": 0.7429,
      "step": 990
    },
    {
      "epoch": 0.05891016200294551,
      "grad_norm": 0.47614580392837524,
      "learning_rate": 2e-05,
      "loss": 0.7343,
      "step": 1000
    },
    {
      "epoch": 0.05949926362297496,
      "grad_norm": 0.4229415953159332,
      "learning_rate": 2e-05,
      "loss": 0.7456,
      "step": 1010
    },
    {
      "epoch": 0.06008836524300442,
      "grad_norm": 0.47622278332710266,
      "learning_rate": 2e-05,
      "loss": 0.7293,
      "step": 1020
    },
    {
      "epoch": 0.06067746686303387,
      "grad_norm": 0.4421570897102356,
      "learning_rate": 2e-05,
      "loss": 0.7518,
      "step": 1030
    },
    {
      "epoch": 0.061266568483063326,
      "grad_norm": 0.4493580162525177,
      "learning_rate": 2e-05,
      "loss": 0.7131,
      "step": 1040
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 0.42369574308395386,
      "learning_rate": 2e-05,
      "loss": 0.7445,
      "step": 1050
    },
    {
      "epoch": 0.06244477172312224,
      "grad_norm": 0.5011873841285706,
      "learning_rate": 2e-05,
      "loss": 0.7186,
      "step": 1060
    },
    {
      "epoch": 0.06303387334315169,
      "grad_norm": 0.4701177477836609,
      "learning_rate": 2e-05,
      "loss": 0.7367,
      "step": 1070
    },
    {
      "epoch": 0.06362297496318114,
      "grad_norm": 0.5048543214797974,
      "learning_rate": 2e-05,
      "loss": 0.7686,
      "step": 1080
    },
    {
      "epoch": 0.0642120765832106,
      "grad_norm": 0.43808069825172424,
      "learning_rate": 2e-05,
      "loss": 0.7496,
      "step": 1090
    },
    {
      "epoch": 0.06480117820324006,
      "grad_norm": 0.4087897539138794,
      "learning_rate": 2e-05,
      "loss": 0.7428,
      "step": 1100
    },
    {
      "epoch": 0.06539027982326952,
      "grad_norm": 0.94446861743927,
      "learning_rate": 2e-05,
      "loss": 0.7528,
      "step": 1110
    },
    {
      "epoch": 0.06597938144329897,
      "grad_norm": 0.5377583503723145,
      "learning_rate": 2e-05,
      "loss": 0.7481,
      "step": 1120
    },
    {
      "epoch": 0.06656848306332842,
      "grad_norm": 0.48349031805992126,
      "learning_rate": 2e-05,
      "loss": 0.7193,
      "step": 1130
    },
    {
      "epoch": 0.06715758468335788,
      "grad_norm": 0.42557501792907715,
      "learning_rate": 2e-05,
      "loss": 0.7669,
      "step": 1140
    },
    {
      "epoch": 0.06774668630338733,
      "grad_norm": 0.5073610544204712,
      "learning_rate": 2e-05,
      "loss": 0.7277,
      "step": 1150
    },
    {
      "epoch": 0.06833578792341678,
      "grad_norm": 0.41803184151649475,
      "learning_rate": 2e-05,
      "loss": 0.7231,
      "step": 1160
    },
    {
      "epoch": 0.06892488954344625,
      "grad_norm": 0.4486277401447296,
      "learning_rate": 2e-05,
      "loss": 0.7348,
      "step": 1170
    },
    {
      "epoch": 0.0695139911634757,
      "grad_norm": 0.415258526802063,
      "learning_rate": 2e-05,
      "loss": 0.7541,
      "step": 1180
    },
    {
      "epoch": 0.07010309278350516,
      "grad_norm": 0.4587970972061157,
      "learning_rate": 2e-05,
      "loss": 0.7237,
      "step": 1190
    },
    {
      "epoch": 0.07069219440353461,
      "grad_norm": 0.5214656591415405,
      "learning_rate": 2e-05,
      "loss": 0.734,
      "step": 1200
    },
    {
      "epoch": 0.07128129602356406,
      "grad_norm": 0.4164435863494873,
      "learning_rate": 2e-05,
      "loss": 0.7187,
      "step": 1210
    },
    {
      "epoch": 0.07187039764359351,
      "grad_norm": 0.4546908140182495,
      "learning_rate": 2e-05,
      "loss": 0.7283,
      "step": 1220
    },
    {
      "epoch": 0.07245949926362298,
      "grad_norm": 0.4424133896827698,
      "learning_rate": 2e-05,
      "loss": 0.752,
      "step": 1230
    },
    {
      "epoch": 0.07304860088365243,
      "grad_norm": 0.443491667509079,
      "learning_rate": 2e-05,
      "loss": 0.7748,
      "step": 1240
    },
    {
      "epoch": 0.07363770250368189,
      "grad_norm": 0.44335657358169556,
      "learning_rate": 2e-05,
      "loss": 0.7453,
      "step": 1250
    },
    {
      "epoch": 0.07422680412371134,
      "grad_norm": 1.5585325956344604,
      "learning_rate": 2e-05,
      "loss": 0.7408,
      "step": 1260
    },
    {
      "epoch": 0.0748159057437408,
      "grad_norm": 0.41405925154685974,
      "learning_rate": 2e-05,
      "loss": 0.7703,
      "step": 1270
    },
    {
      "epoch": 0.07540500736377025,
      "grad_norm": 0.42153358459472656,
      "learning_rate": 2e-05,
      "loss": 0.724,
      "step": 1280
    },
    {
      "epoch": 0.0759941089837997,
      "grad_norm": 0.4355378746986389,
      "learning_rate": 2e-05,
      "loss": 0.7554,
      "step": 1290
    },
    {
      "epoch": 0.07658321060382917,
      "grad_norm": 0.41889065504074097,
      "learning_rate": 2e-05,
      "loss": 0.7185,
      "step": 1300
    },
    {
      "epoch": 0.07717231222385862,
      "grad_norm": 0.508222222328186,
      "learning_rate": 2e-05,
      "loss": 0.7345,
      "step": 1310
    },
    {
      "epoch": 0.07776141384388807,
      "grad_norm": 0.46808117628097534,
      "learning_rate": 2e-05,
      "loss": 0.7343,
      "step": 1320
    },
    {
      "epoch": 0.07835051546391752,
      "grad_norm": 0.4918811321258545,
      "learning_rate": 2e-05,
      "loss": 0.7327,
      "step": 1330
    },
    {
      "epoch": 0.07893961708394698,
      "grad_norm": 0.4409327208995819,
      "learning_rate": 2e-05,
      "loss": 0.7378,
      "step": 1340
    },
    {
      "epoch": 0.07952871870397643,
      "grad_norm": 0.4449012875556946,
      "learning_rate": 2e-05,
      "loss": 0.7319,
      "step": 1350
    },
    {
      "epoch": 0.0801178203240059,
      "grad_norm": 0.46577584743499756,
      "learning_rate": 2e-05,
      "loss": 0.7294,
      "step": 1360
    },
    {
      "epoch": 0.08070692194403535,
      "grad_norm": 0.6492505073547363,
      "learning_rate": 2e-05,
      "loss": 0.7226,
      "step": 1370
    },
    {
      "epoch": 0.0812960235640648,
      "grad_norm": 0.42449140548706055,
      "learning_rate": 2e-05,
      "loss": 0.7532,
      "step": 1380
    },
    {
      "epoch": 0.08188512518409426,
      "grad_norm": 0.4328237771987915,
      "learning_rate": 2e-05,
      "loss": 0.7396,
      "step": 1390
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.4322971701622009,
      "learning_rate": 2e-05,
      "loss": 0.7283,
      "step": 1400
    },
    {
      "epoch": 0.08306332842415316,
      "grad_norm": 0.4679484963417053,
      "learning_rate": 2e-05,
      "loss": 0.7279,
      "step": 1410
    },
    {
      "epoch": 0.08365243004418262,
      "grad_norm": 0.42679035663604736,
      "learning_rate": 2e-05,
      "loss": 0.7292,
      "step": 1420
    },
    {
      "epoch": 0.08424153166421208,
      "grad_norm": 0.41338619589805603,
      "learning_rate": 2e-05,
      "loss": 0.7474,
      "step": 1430
    },
    {
      "epoch": 0.08483063328424154,
      "grad_norm": 0.46909600496292114,
      "learning_rate": 2e-05,
      "loss": 0.7116,
      "step": 1440
    },
    {
      "epoch": 0.08541973490427099,
      "grad_norm": 0.7349217534065247,
      "learning_rate": 2e-05,
      "loss": 0.7249,
      "step": 1450
    },
    {
      "epoch": 0.08600883652430044,
      "grad_norm": 0.4277472198009491,
      "learning_rate": 2e-05,
      "loss": 0.7343,
      "step": 1460
    },
    {
      "epoch": 0.0865979381443299,
      "grad_norm": 0.5415593981742859,
      "learning_rate": 2e-05,
      "loss": 0.7304,
      "step": 1470
    },
    {
      "epoch": 0.08718703976435935,
      "grad_norm": 0.417657732963562,
      "learning_rate": 2e-05,
      "loss": 0.7356,
      "step": 1480
    },
    {
      "epoch": 0.0877761413843888,
      "grad_norm": 0.4391482174396515,
      "learning_rate": 2e-05,
      "loss": 0.7235,
      "step": 1490
    },
    {
      "epoch": 0.08836524300441827,
      "grad_norm": 0.46071121096611023,
      "learning_rate": 2e-05,
      "loss": 0.7277,
      "step": 1500
    },
    {
      "epoch": 0.08895434462444772,
      "grad_norm": 0.521892786026001,
      "learning_rate": 2e-05,
      "loss": 0.7776,
      "step": 1510
    },
    {
      "epoch": 0.08954344624447717,
      "grad_norm": 0.43941742181777954,
      "learning_rate": 2e-05,
      "loss": 0.7179,
      "step": 1520
    },
    {
      "epoch": 0.09013254786450663,
      "grad_norm": 0.4313391149044037,
      "learning_rate": 2e-05,
      "loss": 0.74,
      "step": 1530
    },
    {
      "epoch": 0.09072164948453608,
      "grad_norm": 0.560111403465271,
      "learning_rate": 2e-05,
      "loss": 0.7364,
      "step": 1540
    },
    {
      "epoch": 0.09131075110456553,
      "grad_norm": 0.4297552704811096,
      "learning_rate": 2e-05,
      "loss": 0.7237,
      "step": 1550
    },
    {
      "epoch": 0.091899852724595,
      "grad_norm": 0.4254915416240692,
      "learning_rate": 2e-05,
      "loss": 0.7141,
      "step": 1560
    },
    {
      "epoch": 0.09248895434462445,
      "grad_norm": 0.5323898196220398,
      "learning_rate": 2e-05,
      "loss": 0.7166,
      "step": 1570
    },
    {
      "epoch": 0.0930780559646539,
      "grad_norm": 0.4295822083950043,
      "learning_rate": 2e-05,
      "loss": 0.7103,
      "step": 1580
    },
    {
      "epoch": 0.09366715758468336,
      "grad_norm": 0.45835748314857483,
      "learning_rate": 2e-05,
      "loss": 0.722,
      "step": 1590
    },
    {
      "epoch": 0.09425625920471281,
      "grad_norm": 0.4352903664112091,
      "learning_rate": 2e-05,
      "loss": 0.7396,
      "step": 1600
    },
    {
      "epoch": 0.09484536082474226,
      "grad_norm": 0.42194947600364685,
      "learning_rate": 2e-05,
      "loss": 0.7174,
      "step": 1610
    },
    {
      "epoch": 0.09543446244477172,
      "grad_norm": 0.41238200664520264,
      "learning_rate": 2e-05,
      "loss": 0.7161,
      "step": 1620
    },
    {
      "epoch": 0.09602356406480118,
      "grad_norm": 0.5528646111488342,
      "learning_rate": 2e-05,
      "loss": 0.7377,
      "step": 1630
    },
    {
      "epoch": 0.09661266568483064,
      "grad_norm": 0.4552900195121765,
      "learning_rate": 2e-05,
      "loss": 0.7126,
      "step": 1640
    },
    {
      "epoch": 0.09720176730486009,
      "grad_norm": 0.5200653672218323,
      "learning_rate": 2e-05,
      "loss": 0.7421,
      "step": 1650
    },
    {
      "epoch": 0.09779086892488954,
      "grad_norm": 0.4877001643180847,
      "learning_rate": 2e-05,
      "loss": 0.7637,
      "step": 1660
    },
    {
      "epoch": 0.098379970544919,
      "grad_norm": 0.4906533658504486,
      "learning_rate": 2e-05,
      "loss": 0.7365,
      "step": 1670
    },
    {
      "epoch": 0.09896907216494845,
      "grad_norm": 0.47109371423721313,
      "learning_rate": 2e-05,
      "loss": 0.7152,
      "step": 1680
    },
    {
      "epoch": 0.0995581737849779,
      "grad_norm": 0.4154045283794403,
      "learning_rate": 2e-05,
      "loss": 0.7114,
      "step": 1690
    },
    {
      "epoch": 0.10014727540500737,
      "grad_norm": 0.4646206498146057,
      "learning_rate": 2e-05,
      "loss": 0.7276,
      "step": 1700
    },
    {
      "epoch": 0.10073637702503682,
      "grad_norm": 0.46414250135421753,
      "learning_rate": 2e-05,
      "loss": 0.7419,
      "step": 1710
    },
    {
      "epoch": 0.10132547864506627,
      "grad_norm": 0.5728378295898438,
      "learning_rate": 2e-05,
      "loss": 0.7351,
      "step": 1720
    },
    {
      "epoch": 0.10191458026509573,
      "grad_norm": 0.49045124650001526,
      "learning_rate": 2e-05,
      "loss": 0.7357,
      "step": 1730
    },
    {
      "epoch": 0.10250368188512518,
      "grad_norm": 0.40880975127220154,
      "learning_rate": 2e-05,
      "loss": 0.7404,
      "step": 1740
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 0.41513314843177795,
      "learning_rate": 2e-05,
      "loss": 0.7142,
      "step": 1750
    },
    {
      "epoch": 0.1036818851251841,
      "grad_norm": 0.4373551607131958,
      "learning_rate": 2e-05,
      "loss": 0.733,
      "step": 1760
    },
    {
      "epoch": 0.10427098674521355,
      "grad_norm": 0.4935678541660309,
      "learning_rate": 2e-05,
      "loss": 0.723,
      "step": 1770
    },
    {
      "epoch": 0.104860088365243,
      "grad_norm": 0.5708635449409485,
      "learning_rate": 2e-05,
      "loss": 0.7434,
      "step": 1780
    },
    {
      "epoch": 0.10544918998527246,
      "grad_norm": 0.44515126943588257,
      "learning_rate": 2e-05,
      "loss": 0.7481,
      "step": 1790
    },
    {
      "epoch": 0.10603829160530191,
      "grad_norm": 0.44421878457069397,
      "learning_rate": 2e-05,
      "loss": 0.7142,
      "step": 1800
    },
    {
      "epoch": 0.10662739322533137,
      "grad_norm": 0.4646596610546112,
      "learning_rate": 2e-05,
      "loss": 0.7169,
      "step": 1810
    },
    {
      "epoch": 0.10721649484536082,
      "grad_norm": 0.4383988380432129,
      "learning_rate": 2e-05,
      "loss": 0.7304,
      "step": 1820
    },
    {
      "epoch": 0.10780559646539029,
      "grad_norm": 0.4752575755119324,
      "learning_rate": 2e-05,
      "loss": 0.729,
      "step": 1830
    },
    {
      "epoch": 0.10839469808541974,
      "grad_norm": 0.5204085111618042,
      "learning_rate": 2e-05,
      "loss": 0.7303,
      "step": 1840
    },
    {
      "epoch": 0.10898379970544919,
      "grad_norm": 0.40991365909576416,
      "learning_rate": 2e-05,
      "loss": 0.6899,
      "step": 1850
    },
    {
      "epoch": 0.10957290132547864,
      "grad_norm": 0.511846661567688,
      "learning_rate": 2e-05,
      "loss": 0.7096,
      "step": 1860
    },
    {
      "epoch": 0.1101620029455081,
      "grad_norm": 0.3975253701210022,
      "learning_rate": 2e-05,
      "loss": 0.7464,
      "step": 1870
    },
    {
      "epoch": 0.11075110456553755,
      "grad_norm": 0.4428749680519104,
      "learning_rate": 2e-05,
      "loss": 0.7214,
      "step": 1880
    },
    {
      "epoch": 0.11134020618556702,
      "grad_norm": 0.6127219796180725,
      "learning_rate": 2e-05,
      "loss": 0.7163,
      "step": 1890
    },
    {
      "epoch": 0.11192930780559647,
      "grad_norm": 0.7660998106002808,
      "learning_rate": 2e-05,
      "loss": 0.7328,
      "step": 1900
    },
    {
      "epoch": 0.11251840942562592,
      "grad_norm": 0.4295995235443115,
      "learning_rate": 2e-05,
      "loss": 0.7419,
      "step": 1910
    },
    {
      "epoch": 0.11310751104565538,
      "grad_norm": 0.5128087997436523,
      "learning_rate": 2e-05,
      "loss": 0.7466,
      "step": 1920
    },
    {
      "epoch": 0.11369661266568483,
      "grad_norm": 0.4301770329475403,
      "learning_rate": 2e-05,
      "loss": 0.7115,
      "step": 1930
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.5042638182640076,
      "learning_rate": 2e-05,
      "loss": 0.7535,
      "step": 1940
    },
    {
      "epoch": 0.11487481590574374,
      "grad_norm": 0.39604488015174866,
      "learning_rate": 2e-05,
      "loss": 0.7089,
      "step": 1950
    },
    {
      "epoch": 0.1154639175257732,
      "grad_norm": 0.4408802092075348,
      "learning_rate": 2e-05,
      "loss": 0.7264,
      "step": 1960
    },
    {
      "epoch": 0.11605301914580265,
      "grad_norm": 0.44488540291786194,
      "learning_rate": 2e-05,
      "loss": 0.7287,
      "step": 1970
    },
    {
      "epoch": 0.11664212076583211,
      "grad_norm": 0.4116921126842499,
      "learning_rate": 2e-05,
      "loss": 0.7409,
      "step": 1980
    },
    {
      "epoch": 0.11723122238586156,
      "grad_norm": 0.47106829285621643,
      "learning_rate": 2e-05,
      "loss": 0.7338,
      "step": 1990
    },
    {
      "epoch": 0.11782032400589101,
      "grad_norm": 0.41873085498809814,
      "learning_rate": 2e-05,
      "loss": 0.7142,
      "step": 2000
    },
    {
      "epoch": 0.11840942562592047,
      "grad_norm": 0.606903612613678,
      "learning_rate": 2e-05,
      "loss": 0.7108,
      "step": 2010
    },
    {
      "epoch": 0.11899852724594992,
      "grad_norm": 0.42234426736831665,
      "learning_rate": 2e-05,
      "loss": 0.7445,
      "step": 2020
    },
    {
      "epoch": 0.11958762886597939,
      "grad_norm": 0.5257266759872437,
      "learning_rate": 2e-05,
      "loss": 0.725,
      "step": 2030
    }
  ],
  "logging_steps": 10,
  "max_steps": 5935,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2035,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.084295122442519e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}