{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 823,
  "global_step": 1646,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006075334143377885,
      "eval_loss": NaN,
      "eval_runtime": 210.1616,
      "eval_samples_per_second": 26.384,
      "eval_steps_per_second": 1.651,
      "step": 1
    },
    {
      "epoch": 0.006075334143377886,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.012150668286755772,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.018226002430133656,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.024301336573511544,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.030376670716889428,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.03645200486026731,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.0425273390036452,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.04860267314702309,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.054678007290400975,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.060753341433778855,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.06682867557715674,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.07290400972053462,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.07897934386391252,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.0850546780072904,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.0911300121506683,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.09720534629404617,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.10328068043742406,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.10935601458080195,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.11543134872417983,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.12150668286755771,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.1275820170109356,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 0.1336573511543135,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 220
    },
    {
      "epoch": 0.13973268529769137,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 230
    },
    {
      "epoch": 0.14580801944106925,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 240
    },
    {
      "epoch": 0.15188335358444716,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 0.15795868772782504,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 260
    },
    {
      "epoch": 0.16403402187120292,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 270
    },
    {
      "epoch": 0.1701093560145808,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 280
    },
    {
      "epoch": 0.17618469015795868,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 290
    },
    {
      "epoch": 0.1822600243013366,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 0.18833535844471447,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 310
    },
    {
      "epoch": 0.19441069258809235,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 320
    },
    {
      "epoch": 0.20048602673147023,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 330
    },
    {
      "epoch": 0.2065613608748481,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 340
    },
    {
      "epoch": 0.212636695018226,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 350
    },
    {
      "epoch": 0.2187120291616039,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 360
    },
    {
      "epoch": 0.22478736330498178,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 370
    },
    {
      "epoch": 0.23086269744835966,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 380
    },
    {
      "epoch": 0.23693803159173754,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 390
    },
    {
      "epoch": 0.24301336573511542,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 0.24908869987849333,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 410
    },
    {
      "epoch": 0.2551640340218712,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 420
    },
    {
      "epoch": 0.26123936816524906,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 430
    },
    {
      "epoch": 0.267314702308627,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 440
    },
    {
      "epoch": 0.2733900364520049,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 450
    },
    {
      "epoch": 0.27946537059538273,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 460
    },
    {
      "epoch": 0.28554070473876064,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 470
    },
    {
      "epoch": 0.2916160388821385,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 480
    },
    {
      "epoch": 0.2976913730255164,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 490
    },
    {
      "epoch": 0.3037667071688943,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 500
    },
    {
      "epoch": 0.30984204131227217,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 510
    },
    {
      "epoch": 0.3159173754556501,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 520
    },
    {
      "epoch": 0.3219927095990279,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 530
    },
    {
      "epoch": 0.32806804374240583,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 540
    },
    {
      "epoch": 0.33414337788578374,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 550
    },
    {
      "epoch": 0.3402187120291616,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 560
    },
    {
      "epoch": 0.3462940461725395,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 570
    },
    {
      "epoch": 0.35236938031591736,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 580
    },
    {
      "epoch": 0.35844471445929527,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 590
    },
    {
      "epoch": 0.3645200486026732,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 600
    },
    {
      "epoch": 0.370595382746051,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 610
    },
    {
      "epoch": 0.37667071688942894,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 620
    },
    {
      "epoch": 0.3827460510328068,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 630
    },
    {
      "epoch": 0.3888213851761847,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 640
    },
    {
      "epoch": 0.39489671931956255,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 650
    },
    {
      "epoch": 0.40097205346294046,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 660
    },
    {
      "epoch": 0.40704738760631837,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 670
    },
    {
      "epoch": 0.4131227217496962,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 680
    },
    {
      "epoch": 0.41919805589307413,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 690
    },
    {
      "epoch": 0.425273390036452,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 700
    },
    {
      "epoch": 0.4313487241798299,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 710
    },
    {
      "epoch": 0.4374240583232078,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 720
    },
    {
      "epoch": 0.44349939246658565,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 730
    },
    {
      "epoch": 0.44957472660996356,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 740
    },
    {
      "epoch": 0.4556500607533414,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 750
    },
    {
      "epoch": 0.4617253948967193,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 760
    },
    {
      "epoch": 0.46780072904009723,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 770
    },
    {
      "epoch": 0.4738760631834751,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 780
    },
    {
      "epoch": 0.479951397326853,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 790
    },
    {
      "epoch": 0.48602673147023084,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 800
    },
    {
      "epoch": 0.49210206561360875,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 810
    },
    {
      "epoch": 0.49817739975698666,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 820
    },
    {
      "epoch": 0.5,
      "eval_loss": NaN,
      "eval_runtime": 210.1069,
      "eval_samples_per_second": 26.391,
      "eval_steps_per_second": 1.652,
      "step": 823
    },
    {
      "epoch": 0.5042527339003645,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 830
    },
    {
      "epoch": 0.5103280680437424,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 840
    },
    {
      "epoch": 0.5164034021871203,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 850
    },
    {
      "epoch": 0.5224787363304981,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 860
    },
    {
      "epoch": 0.528554070473876,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 870
    },
    {
      "epoch": 0.534629404617254,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 880
    },
    {
      "epoch": 0.5407047387606319,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 890
    },
    {
      "epoch": 0.5467800729040098,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 900
    },
    {
      "epoch": 0.5528554070473876,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 910
    },
    {
      "epoch": 0.5589307411907655,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 920
    },
    {
      "epoch": 0.5650060753341434,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 930
    },
    {
      "epoch": 0.5710814094775213,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 940
    },
    {
      "epoch": 0.5771567436208992,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 950
    },
    {
      "epoch": 0.583232077764277,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 960
    },
    {
      "epoch": 0.5893074119076549,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 970
    },
    {
      "epoch": 0.5953827460510328,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 980
    },
    {
      "epoch": 0.6014580801944107,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 990
    },
    {
      "epoch": 0.6075334143377886,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1000
    },
    {
      "epoch": 0.6136087484811664,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1010
    },
    {
      "epoch": 0.6196840826245443,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1020
    },
    {
      "epoch": 0.6257594167679222,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1030
    },
    {
      "epoch": 0.6318347509113001,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1040
    },
    {
      "epoch": 0.637910085054678,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1050
    },
    {
      "epoch": 0.6439854191980559,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1060
    },
    {
      "epoch": 0.6500607533414338,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1070
    },
    {
      "epoch": 0.6561360874848117,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1080
    },
    {
      "epoch": 0.6622114216281896,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1090
    },
    {
      "epoch": 0.6682867557715675,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1100
    },
    {
      "epoch": 0.6743620899149453,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1110
    },
    {
      "epoch": 0.6804374240583232,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1120
    },
    {
      "epoch": 0.6865127582017011,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1130
    },
    {
      "epoch": 0.692588092345079,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1140
    },
    {
      "epoch": 0.6986634264884569,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1150
    },
    {
      "epoch": 0.7047387606318347,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1160
    },
    {
      "epoch": 0.7108140947752126,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1170
    },
    {
      "epoch": 0.7168894289185905,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1180
    },
    {
      "epoch": 0.7229647630619684,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1190
    },
    {
      "epoch": 0.7290400972053463,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1200
    },
    {
      "epoch": 0.7351154313487241,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1210
    },
    {
      "epoch": 0.741190765492102,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1220
    },
    {
      "epoch": 0.74726609963548,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1230
    },
    {
      "epoch": 0.7533414337788579,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1240
    },
    {
      "epoch": 0.7594167679222357,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1250
    },
    {
      "epoch": 0.7654921020656136,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1260
    },
    {
      "epoch": 0.7715674362089915,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1270
    },
    {
      "epoch": 0.7776427703523694,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1280
    },
    {
      "epoch": 0.7837181044957473,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1290
    },
    {
      "epoch": 0.7897934386391251,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1300
    },
    {
      "epoch": 0.795868772782503,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1310
    },
    {
      "epoch": 0.8019441069258809,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1320
    },
    {
      "epoch": 0.8080194410692588,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1330
    },
    {
      "epoch": 0.8140947752126367,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1340
    },
    {
      "epoch": 0.8201701093560145,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1350
    },
    {
      "epoch": 0.8262454434993924,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1360
    },
    {
      "epoch": 0.8323207776427703,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1370
    },
    {
      "epoch": 0.8383961117861483,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1380
    },
    {
      "epoch": 0.8444714459295262,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1390
    },
    {
      "epoch": 0.850546780072904,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1400
    },
    {
      "epoch": 0.8566221142162819,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1410
    },
    {
      "epoch": 0.8626974483596598,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1420
    },
    {
      "epoch": 0.8687727825030377,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1430
    },
    {
      "epoch": 0.8748481166464156,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1440
    },
    {
      "epoch": 0.8809234507897934,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1450
    },
    {
      "epoch": 0.8869987849331713,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1460
    },
    {
      "epoch": 0.8930741190765492,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1470
    },
    {
      "epoch": 0.8991494532199271,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1480
    },
    {
      "epoch": 0.905224787363305,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1490
    },
    {
      "epoch": 0.9113001215066828,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1500
    },
    {
      "epoch": 0.9173754556500607,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1510
    },
    {
      "epoch": 0.9234507897934386,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1520
    },
    {
      "epoch": 0.9295261239368166,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1530
    },
    {
      "epoch": 0.9356014580801945,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1540
    },
    {
      "epoch": 0.9416767922235723,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1550
    },
    {
      "epoch": 0.9477521263669502,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1560
    },
    {
      "epoch": 0.9538274605103281,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1570
    },
    {
      "epoch": 0.959902794653706,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1580
    },
    {
      "epoch": 0.9659781287970839,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1590
    },
    {
      "epoch": 0.9720534629404617,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1600
    },
    {
      "epoch": 0.9781287970838396,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1610
    },
    {
      "epoch": 0.9842041312272175,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1620
    },
    {
      "epoch": 0.9902794653705954,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1630
    },
    {
      "epoch": 0.9963547995139733,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1640
    },
    {
      "epoch": 1.0,
      "eval_loss": NaN,
      "eval_runtime": 210.0744,
      "eval_samples_per_second": 26.395,
      "eval_steps_per_second": 1.652,
      "step": 1646
    }
  ],
  "logging_steps": 10,
  "max_steps": 1646,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 823,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3906163426852864e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}