{
  "best_metric": 1.4095008373260498,
  "best_model_checkpoint": "./results/checkpoint-2000",
  "epoch": 1.9038553069966682,
  "eval_steps": 100,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00951927653498334,
      "grad_norm": 0.19429340958595276,
      "learning_rate": 5e-06,
      "loss": 1.9923,
      "step": 10
    },
    {
      "epoch": 0.01903855306996668,
      "grad_norm": 0.22915661334991455,
      "learning_rate": 1e-05,
      "loss": 2.0345,
      "step": 20
    },
    {
      "epoch": 0.028557829604950024,
      "grad_norm": 0.24586208164691925,
      "learning_rate": 1.5e-05,
      "loss": 1.9754,
      "step": 30
    },
    {
      "epoch": 0.03807710613993336,
      "grad_norm": 0.2809593677520752,
      "learning_rate": 2e-05,
      "loss": 1.9887,
      "step": 40
    },
    {
      "epoch": 0.047596382674916705,
      "grad_norm": 0.3456374406814575,
      "learning_rate": 2.5e-05,
      "loss": 1.9913,
      "step": 50
    },
    {
      "epoch": 0.05711565920990005,
      "grad_norm": 0.43767085671424866,
      "learning_rate": 3e-05,
      "loss": 1.9953,
      "step": 60
    },
    {
      "epoch": 0.06663493574488338,
      "grad_norm": 0.5941727757453918,
      "learning_rate": 3.5e-05,
      "loss": 1.9795,
      "step": 70
    },
    {
      "epoch": 0.07615421227986673,
      "grad_norm": 0.6205775141716003,
      "learning_rate": 4e-05,
      "loss": 1.9804,
      "step": 80
    },
    {
      "epoch": 0.08567348881485007,
      "grad_norm": 0.7349818348884583,
      "learning_rate": 4.5e-05,
      "loss": 1.9511,
      "step": 90
    },
    {
      "epoch": 0.09519276534983341,
      "grad_norm": 0.7896203398704529,
      "learning_rate": 5e-05,
      "loss": 1.9337,
      "step": 100
    },
    {
      "epoch": 0.09519276534983341,
      "eval_loss": 1.9389821290969849,
      "eval_runtime": 39.6995,
      "eval_samples_per_second": 2.519,
      "eval_steps_per_second": 0.63,
      "step": 100
    },
    {
      "epoch": 0.10471204188481675,
      "grad_norm": 0.8368595242500305,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.9052,
      "step": 110
    },
    {
      "epoch": 0.1142313184198001,
      "grad_norm": 0.9555522799491882,
      "learning_rate": 6e-05,
      "loss": 1.8766,
      "step": 120
    },
    {
      "epoch": 0.12375059495478344,
      "grad_norm": 0.9343065023422241,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.8416,
      "step": 130
    },
    {
      "epoch": 0.13326987148976677,
      "grad_norm": 0.82816481590271,
      "learning_rate": 7e-05,
      "loss": 1.8246,
      "step": 140
    },
    {
      "epoch": 0.14278914802475012,
      "grad_norm": 0.7882226705551147,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.7909,
      "step": 150
    },
    {
      "epoch": 0.15230842455973345,
      "grad_norm": 0.6617611646652222,
      "learning_rate": 8e-05,
      "loss": 1.7938,
      "step": 160
    },
    {
      "epoch": 0.1618277010947168,
      "grad_norm": 0.598513126373291,
      "learning_rate": 8.5e-05,
      "loss": 1.759,
      "step": 170
    },
    {
      "epoch": 0.17134697762970014,
      "grad_norm": 0.45931604504585266,
      "learning_rate": 9e-05,
      "loss": 1.7542,
      "step": 180
    },
    {
      "epoch": 0.1808662541646835,
      "grad_norm": 0.38422173261642456,
      "learning_rate": 9.5e-05,
      "loss": 1.7525,
      "step": 190
    },
    {
      "epoch": 0.19038553069966682,
      "grad_norm": 0.31998202204704285,
      "learning_rate": 0.0001,
      "loss": 1.732,
      "step": 200
    },
    {
      "epoch": 0.19038553069966682,
      "eval_loss": 1.7440533638000488,
      "eval_runtime": 39.6462,
      "eval_samples_per_second": 2.522,
      "eval_steps_per_second": 0.631,
      "step": 200
    },
    {
      "epoch": 0.19990480723465018,
      "grad_norm": 0.3325157165527344,
      "learning_rate": 0.000105,
      "loss": 1.7215,
      "step": 210
    },
    {
      "epoch": 0.2094240837696335,
      "grad_norm": 0.31313714385032654,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.7033,
      "step": 220
    },
    {
      "epoch": 0.21894336030461684,
      "grad_norm": 0.3179369270801544,
      "learning_rate": 0.00011499999999999999,
      "loss": 1.7025,
      "step": 230
    },
    {
      "epoch": 0.2284626368396002,
      "grad_norm": 0.3547224700450897,
      "learning_rate": 0.00012,
      "loss": 1.6833,
      "step": 240
    },
    {
      "epoch": 0.23798191337458352,
      "grad_norm": 0.3367106020450592,
      "learning_rate": 0.000125,
      "loss": 1.6524,
      "step": 250
    },
    {
      "epoch": 0.24750118990956688,
      "grad_norm": 0.38071829080581665,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.6425,
      "step": 260
    },
    {
      "epoch": 0.25702046644455023,
      "grad_norm": 0.34949544072151184,
      "learning_rate": 0.00013500000000000003,
      "loss": 1.6218,
      "step": 270
    },
    {
      "epoch": 0.26653974297953353,
      "grad_norm": 0.32234707474708557,
      "learning_rate": 0.00014,
      "loss": 1.6284,
      "step": 280
    },
    {
      "epoch": 0.2760590195145169,
      "grad_norm": 0.3492746949195862,
      "learning_rate": 0.000145,
      "loss": 1.6053,
      "step": 290
    },
    {
      "epoch": 0.28557829604950025,
      "grad_norm": 0.3380492031574249,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.5728,
      "step": 300
    },
    {
      "epoch": 0.28557829604950025,
      "eval_loss": 1.5842629671096802,
      "eval_runtime": 39.8763,
      "eval_samples_per_second": 2.508,
      "eval_steps_per_second": 0.627,
      "step": 300
    },
    {
      "epoch": 0.2950975725844836,
      "grad_norm": 0.3693602383136749,
      "learning_rate": 0.000155,
      "loss": 1.5769,
      "step": 310
    },
    {
      "epoch": 0.3046168491194669,
      "grad_norm": 0.3339674174785614,
      "learning_rate": 0.00016,
      "loss": 1.5691,
      "step": 320
    },
    {
      "epoch": 0.31413612565445026,
      "grad_norm": 0.33094632625579834,
      "learning_rate": 0.000165,
      "loss": 1.5501,
      "step": 330
    },
    {
      "epoch": 0.3236554021894336,
      "grad_norm": 0.3607189953327179,
      "learning_rate": 0.00017,
      "loss": 1.5373,
      "step": 340
    },
    {
      "epoch": 0.3331746787244169,
      "grad_norm": 0.34884127974510193,
      "learning_rate": 0.000175,
      "loss": 1.5084,
      "step": 350
    },
    {
      "epoch": 0.3426939552594003,
      "grad_norm": 0.33757245540618896,
      "learning_rate": 0.00018,
      "loss": 1.5158,
      "step": 360
    },
    {
      "epoch": 0.35221323179438363,
      "grad_norm": 0.34877315163612366,
      "learning_rate": 0.00018500000000000002,
      "loss": 1.5002,
      "step": 370
    },
    {
      "epoch": 0.361732508329367,
      "grad_norm": 0.38293707370758057,
      "learning_rate": 0.00019,
      "loss": 1.4845,
      "step": 380
    },
    {
      "epoch": 0.3712517848643503,
      "grad_norm": 0.3441324830055237,
      "learning_rate": 0.000195,
      "loss": 1.4849,
      "step": 390
    },
    {
      "epoch": 0.38077106139933364,
      "grad_norm": 0.41154617071151733,
      "learning_rate": 0.0002,
      "loss": 1.4862,
      "step": 400
    },
    {
      "epoch": 0.38077106139933364,
      "eval_loss": 1.4930579662322998,
      "eval_runtime": 39.6754,
      "eval_samples_per_second": 2.52,
      "eval_steps_per_second": 0.63,
      "step": 400
    },
    {
      "epoch": 0.390290337934317,
      "grad_norm": 0.36156630516052246,
      "learning_rate": 0.0001995876288659794,
      "loss": 1.4872,
      "step": 410
    },
    {
      "epoch": 0.39980961446930036,
      "grad_norm": 0.32177475094795227,
      "learning_rate": 0.00019917525773195877,
      "loss": 1.457,
      "step": 420
    },
    {
      "epoch": 0.40932889100428366,
      "grad_norm": 0.41120991110801697,
      "learning_rate": 0.00019876288659793816,
      "loss": 1.4794,
      "step": 430
    },
    {
      "epoch": 0.418848167539267,
      "grad_norm": 0.3899654448032379,
      "learning_rate": 0.00019835051546391753,
      "loss": 1.4728,
      "step": 440
    },
    {
      "epoch": 0.42836744407425037,
      "grad_norm": 0.3392334580421448,
      "learning_rate": 0.00019793814432989693,
      "loss": 1.4837,
      "step": 450
    },
    {
      "epoch": 0.43788672060923367,
      "grad_norm": 0.35381370782852173,
      "learning_rate": 0.00019752577319587632,
      "loss": 1.4722,
      "step": 460
    },
    {
      "epoch": 0.447405997144217,
      "grad_norm": 0.3540886342525482,
      "learning_rate": 0.0001971134020618557,
      "loss": 1.4608,
      "step": 470
    },
    {
      "epoch": 0.4569252736792004,
      "grad_norm": 0.38124117255210876,
      "learning_rate": 0.00019670103092783505,
      "loss": 1.4648,
      "step": 480
    },
    {
      "epoch": 0.46644455021418374,
      "grad_norm": 0.34540703892707825,
      "learning_rate": 0.00019628865979381442,
      "loss": 1.4651,
      "step": 490
    },
    {
      "epoch": 0.47596382674916704,
      "grad_norm": 0.34259673953056335,
      "learning_rate": 0.00019587628865979381,
      "loss": 1.442,
      "step": 500
    },
    {
      "epoch": 0.47596382674916704,
      "eval_loss": 1.4635019302368164,
      "eval_runtime": 39.7119,
      "eval_samples_per_second": 2.518,
      "eval_steps_per_second": 0.63,
      "step": 500
    },
    {
      "epoch": 0.4854831032841504,
      "grad_norm": 0.39079272747039795,
      "learning_rate": 0.0001954639175257732,
      "loss": 1.4676,
      "step": 510
    },
    {
      "epoch": 0.49500237981913375,
      "grad_norm": 0.3873017132282257,
      "learning_rate": 0.00019505154639175258,
      "loss": 1.4491,
      "step": 520
    },
    {
      "epoch": 0.504521656354117,
      "grad_norm": 0.46681663393974304,
      "learning_rate": 0.00019463917525773197,
      "loss": 1.4483,
      "step": 530
    },
    {
      "epoch": 0.5140409328891005,
      "grad_norm": 0.3657790720462799,
      "learning_rate": 0.00019422680412371134,
      "loss": 1.4402,
      "step": 540
    },
    {
      "epoch": 0.5235602094240838,
      "grad_norm": 0.3777405321598053,
      "learning_rate": 0.00019381443298969073,
      "loss": 1.4295,
      "step": 550
    },
    {
      "epoch": 0.5330794859590671,
      "grad_norm": 0.3857463002204895,
      "learning_rate": 0.00019340206185567012,
      "loss": 1.4548,
      "step": 560
    },
    {
      "epoch": 0.5425987624940505,
      "grad_norm": 0.36316171288490295,
      "learning_rate": 0.0001929896907216495,
      "loss": 1.4567,
      "step": 570
    },
    {
      "epoch": 0.5521180390290338,
      "grad_norm": 0.37083303928375244,
      "learning_rate": 0.00019257731958762889,
      "loss": 1.4458,
      "step": 580
    },
    {
      "epoch": 0.5616373155640171,
      "grad_norm": 0.39506301283836365,
      "learning_rate": 0.00019216494845360825,
      "loss": 1.4364,
      "step": 590
    },
    {
      "epoch": 0.5711565920990005,
      "grad_norm": 0.3553004264831543,
      "learning_rate": 0.00019175257731958765,
      "loss": 1.4676,
      "step": 600
    },
    {
      "epoch": 0.5711565920990005,
      "eval_loss": 1.449947714805603,
      "eval_runtime": 39.6196,
      "eval_samples_per_second": 2.524,
      "eval_steps_per_second": 0.631,
      "step": 600
    },
    {
      "epoch": 0.5806758686339838,
      "grad_norm": 0.4231698513031006,
      "learning_rate": 0.00019134020618556704,
      "loss": 1.4348,
      "step": 610
    },
    {
      "epoch": 0.5901951451689672,
      "grad_norm": 0.4203357994556427,
      "learning_rate": 0.0001909278350515464,
      "loss": 1.4455,
      "step": 620
    },
    {
      "epoch": 0.5997144217039505,
      "grad_norm": 0.39158034324645996,
      "learning_rate": 0.00019051546391752577,
      "loss": 1.4594,
      "step": 630
    },
    {
      "epoch": 0.6092336982389338,
      "grad_norm": 0.39505264163017273,
      "learning_rate": 0.00019010309278350514,
      "loss": 1.4653,
      "step": 640
    },
    {
      "epoch": 0.6187529747739172,
      "grad_norm": 0.3803844153881073,
      "learning_rate": 0.00018969072164948454,
      "loss": 1.4335,
      "step": 650
    },
    {
      "epoch": 0.6282722513089005,
      "grad_norm": 0.3700083792209625,
      "learning_rate": 0.00018927835051546393,
      "loss": 1.4409,
      "step": 660
    },
    {
      "epoch": 0.6377915278438838,
      "grad_norm": 0.35323163866996765,
      "learning_rate": 0.0001888659793814433,
      "loss": 1.4456,
      "step": 670
    },
    {
      "epoch": 0.6473108043788672,
      "grad_norm": 0.34639179706573486,
      "learning_rate": 0.0001884536082474227,
      "loss": 1.441,
      "step": 680
    },
    {
      "epoch": 0.6568300809138505,
      "grad_norm": 0.39847052097320557,
      "learning_rate": 0.00018804123711340206,
      "loss": 1.4214,
      "step": 690
    },
    {
      "epoch": 0.6663493574488338,
      "grad_norm": 0.3468664884567261,
      "learning_rate": 0.00018762886597938145,
      "loss": 1.4398,
      "step": 700
    },
    {
      "epoch": 0.6663493574488338,
      "eval_loss": 1.4422180652618408,
      "eval_runtime": 39.7751,
      "eval_samples_per_second": 2.514,
      "eval_steps_per_second": 0.629,
      "step": 700
    },
    {
      "epoch": 0.6758686339838172,
      "grad_norm": 0.35168835520744324,
      "learning_rate": 0.00018721649484536085,
      "loss": 1.436,
      "step": 710
    },
    {
      "epoch": 0.6853879105188005,
      "grad_norm": 0.3769698143005371,
      "learning_rate": 0.0001868041237113402,
      "loss": 1.4424,
      "step": 720
    },
    {
      "epoch": 0.694907187053784,
      "grad_norm": 0.4488052725791931,
      "learning_rate": 0.0001863917525773196,
      "loss": 1.4509,
      "step": 730
    },
    {
      "epoch": 0.7044264635887673,
      "grad_norm": 0.34030118584632874,
      "learning_rate": 0.00018597938144329897,
      "loss": 1.4355,
      "step": 740
    },
    {
      "epoch": 0.7139457401237506,
      "grad_norm": 0.3737122714519501,
      "learning_rate": 0.00018556701030927837,
      "loss": 1.4336,
      "step": 750
    },
    {
      "epoch": 0.723465016658734,
      "grad_norm": 0.36228156089782715,
      "learning_rate": 0.00018515463917525776,
      "loss": 1.4371,
      "step": 760
    },
    {
      "epoch": 0.7329842931937173,
      "grad_norm": 0.37088775634765625,
      "learning_rate": 0.00018474226804123713,
      "loss": 1.4445,
      "step": 770
    },
    {
      "epoch": 0.7425035697287006,
      "grad_norm": 0.39574727416038513,
      "learning_rate": 0.0001843298969072165,
      "loss": 1.4252,
      "step": 780
    },
    {
      "epoch": 0.752022846263684,
      "grad_norm": 0.41419413685798645,
      "learning_rate": 0.00018391752577319586,
      "loss": 1.4173,
      "step": 790
    },
    {
      "epoch": 0.7615421227986673,
      "grad_norm": 0.3290116786956787,
      "learning_rate": 0.00018350515463917526,
      "loss": 1.4544,
      "step": 800
    },
    {
      "epoch": 0.7615421227986673,
      "eval_loss": 1.436285138130188,
      "eval_runtime": 39.7262,
      "eval_samples_per_second": 2.517,
      "eval_steps_per_second": 0.629,
      "step": 800
    },
    {
      "epoch": 0.7710613993336506,
      "grad_norm": 0.38003116846084595,
      "learning_rate": 0.00018309278350515465,
      "loss": 1.425,
      "step": 810
    },
    {
      "epoch": 0.780580675868634,
      "grad_norm": 0.3706168532371521,
      "learning_rate": 0.00018268041237113402,
      "loss": 1.4537,
      "step": 820
    },
    {
      "epoch": 0.7900999524036173,
      "grad_norm": 0.36038973927497864,
      "learning_rate": 0.0001822680412371134,
      "loss": 1.4188,
      "step": 830
    },
    {
      "epoch": 0.7996192289386007,
      "grad_norm": 0.36866557598114014,
      "learning_rate": 0.00018185567010309278,
      "loss": 1.4246,
      "step": 840
    },
    {
      "epoch": 0.809138505473584,
      "grad_norm": 0.37158384919166565,
      "learning_rate": 0.00018144329896907217,
      "loss": 1.4323,
      "step": 850
    },
    {
      "epoch": 0.8186577820085673,
      "grad_norm": 0.3713236153125763,
      "learning_rate": 0.00018103092783505157,
      "loss": 1.4407,
      "step": 860
    },
    {
      "epoch": 0.8281770585435507,
      "grad_norm": 0.3830552101135254,
      "learning_rate": 0.00018061855670103093,
      "loss": 1.4427,
      "step": 870
    },
    {
      "epoch": 0.837696335078534,
      "grad_norm": 0.3613452613353729,
      "learning_rate": 0.00018020618556701033,
      "loss": 1.445,
      "step": 880
    },
    {
      "epoch": 0.8472156116135173,
      "grad_norm": 0.3281649351119995,
      "learning_rate": 0.0001797938144329897,
      "loss": 1.4311,
      "step": 890
    },
    {
      "epoch": 0.8567348881485007,
      "grad_norm": 0.3342822194099426,
      "learning_rate": 0.0001793814432989691,
      "loss": 1.4455,
      "step": 900
    },
    {
      "epoch": 0.8567348881485007,
      "eval_loss": 1.4309983253479004,
      "eval_runtime": 39.6671,
      "eval_samples_per_second": 2.521,
      "eval_steps_per_second": 0.63,
      "step": 900
    },
    {
      "epoch": 0.866254164683484,
      "grad_norm": 0.3413979411125183,
      "learning_rate": 0.00017896907216494848,
      "loss": 1.4416,
      "step": 910
    },
    {
      "epoch": 0.8757734412184673,
      "grad_norm": 0.36158689856529236,
      "learning_rate": 0.00017855670103092785,
      "loss": 1.4328,
      "step": 920
    },
    {
      "epoch": 0.8852927177534508,
      "grad_norm": 0.3876676857471466,
      "learning_rate": 0.00017814432989690724,
      "loss": 1.4321,
      "step": 930
    },
    {
      "epoch": 0.894811994288434,
      "grad_norm": 0.35580044984817505,
      "learning_rate": 0.00017773195876288658,
      "loss": 1.4377,
      "step": 940
    },
    {
      "epoch": 0.9043312708234175,
      "grad_norm": 0.3638615906238556,
      "learning_rate": 0.00017731958762886598,
      "loss": 1.4222,
      "step": 950
    },
    {
      "epoch": 0.9138505473584008,
      "grad_norm": 0.32744646072387695,
      "learning_rate": 0.00017690721649484537,
      "loss": 1.4235,
      "step": 960
    },
    {
      "epoch": 0.9233698238933841,
      "grad_norm": 0.3513677716255188,
      "learning_rate": 0.00017649484536082474,
      "loss": 1.4511,
      "step": 970
    },
    {
      "epoch": 0.9328891004283675,
      "grad_norm": 0.35235506296157837,
      "learning_rate": 0.00017608247422680413,
      "loss": 1.4274,
      "step": 980
    },
    {
      "epoch": 0.9424083769633508,
      "grad_norm": 0.343514621257782,
      "learning_rate": 0.0001756701030927835,
      "loss": 1.417,
      "step": 990
    },
    {
      "epoch": 0.9519276534983341,
      "grad_norm": 0.38501816987991333,
      "learning_rate": 0.0001752577319587629,
      "loss": 1.4422,
      "step": 1000
    },
    {
      "epoch": 0.9519276534983341,
      "eval_loss": 1.4280465841293335,
      "eval_runtime": 39.8059,
      "eval_samples_per_second": 2.512,
      "eval_steps_per_second": 0.628,
      "step": 1000
    },
    {
      "epoch": 0.9614469300333175,
      "grad_norm": 0.3453533351421356,
      "learning_rate": 0.0001748453608247423,
      "loss": 1.4134,
      "step": 1010
    },
    {
      "epoch": 0.9709662065683008,
      "grad_norm": 0.3687838017940521,
      "learning_rate": 0.00017443298969072165,
      "loss": 1.4357,
      "step": 1020
    },
    {
      "epoch": 0.9804854831032842,
      "grad_norm": 0.3397800624370575,
      "learning_rate": 0.00017402061855670105,
      "loss": 1.4221,
      "step": 1030
    },
    {
      "epoch": 0.9900047596382675,
      "grad_norm": 0.3534553647041321,
      "learning_rate": 0.00017360824742268042,
      "loss": 1.4232,
      "step": 1040
    },
    {
      "epoch": 0.9995240361732508,
      "grad_norm": 0.31195327639579773,
      "learning_rate": 0.0001731958762886598,
      "loss": 1.4316,
      "step": 1050
    },
    {
      "epoch": 1.009043312708234,
      "grad_norm": 0.3326282799243927,
      "learning_rate": 0.0001727835051546392,
      "loss": 1.4361,
      "step": 1060
    },
    {
      "epoch": 1.0185625892432175,
      "grad_norm": 0.38880521059036255,
      "learning_rate": 0.00017237113402061857,
      "loss": 1.4282,
      "step": 1070
    },
    {
      "epoch": 1.028081865778201,
      "grad_norm": 0.3405047357082367,
      "learning_rate": 0.00017195876288659796,
      "loss": 1.4295,
      "step": 1080
    },
    {
      "epoch": 1.0376011423131841,
      "grad_norm": 0.3320964574813843,
      "learning_rate": 0.0001715463917525773,
      "loss": 1.426,
      "step": 1090
    },
    {
      "epoch": 1.0471204188481675,
      "grad_norm": 0.3246203660964966,
      "learning_rate": 0.0001711340206185567,
      "loss": 1.4115,
      "step": 1100
    },
    {
      "epoch": 1.0471204188481675,
      "eval_loss": 1.4249218702316284,
      "eval_runtime": 39.6935,
      "eval_samples_per_second": 2.519,
      "eval_steps_per_second": 0.63,
      "step": 1100
    },
    {
      "epoch": 1.056639695383151,
      "grad_norm": 0.33676016330718994,
      "learning_rate": 0.0001707216494845361,
      "loss": 1.4429,
      "step": 1110
    },
    {
      "epoch": 1.0661589719181341,
      "grad_norm": 0.304193913936615,
      "learning_rate": 0.00017030927835051546,
      "loss": 1.4145,
      "step": 1120
    },
    {
      "epoch": 1.0756782484531175,
      "grad_norm": 0.3132353723049164,
      "learning_rate": 0.00016989690721649485,
      "loss": 1.3993,
      "step": 1130
    },
    {
      "epoch": 1.085197524988101,
      "grad_norm": 0.3249862492084503,
      "learning_rate": 0.00016948453608247422,
      "loss": 1.4079,
      "step": 1140
    },
    {
      "epoch": 1.0947168015230841,
      "grad_norm": 0.31127285957336426,
      "learning_rate": 0.00016907216494845361,
      "loss": 1.4189,
      "step": 1150
    },
    {
      "epoch": 1.1042360780580676,
      "grad_norm": 0.3150855302810669,
      "learning_rate": 0.000168659793814433,
      "loss": 1.4211,
      "step": 1160
    },
    {
      "epoch": 1.113755354593051,
      "grad_norm": 0.3354848325252533,
      "learning_rate": 0.00016824742268041238,
      "loss": 1.4146,
      "step": 1170
    },
    {
      "epoch": 1.1232746311280342,
      "grad_norm": 0.36233270168304443,
      "learning_rate": 0.00016783505154639177,
      "loss": 1.4289,
      "step": 1180
    },
    {
      "epoch": 1.1327939076630176,
      "grad_norm": 0.3264828622341156,
      "learning_rate": 0.00016742268041237114,
      "loss": 1.4021,
      "step": 1190
    },
    {
      "epoch": 1.142313184198001,
      "grad_norm": 0.3206409215927124,
      "learning_rate": 0.00016701030927835053,
      "loss": 1.4014,
      "step": 1200
    },
    {
      "epoch": 1.142313184198001,
      "eval_loss": 1.4221289157867432,
      "eval_runtime": 39.6868,
      "eval_samples_per_second": 2.52,
      "eval_steps_per_second": 0.63,
      "step": 1200
    },
    {
      "epoch": 1.1518324607329844,
      "grad_norm": 0.31770697236061096,
      "learning_rate": 0.00016659793814432993,
      "loss": 1.424,
      "step": 1210
    },
    {
      "epoch": 1.1613517372679676,
      "grad_norm": 0.313504695892334,
      "learning_rate": 0.0001661855670103093,
      "loss": 1.4229,
      "step": 1220
    },
    {
      "epoch": 1.170871013802951,
      "grad_norm": 0.35023483633995056,
      "learning_rate": 0.00016577319587628869,
      "loss": 1.4059,
      "step": 1230
    },
    {
      "epoch": 1.1803902903379344,
      "grad_norm": 0.3138754963874817,
      "learning_rate": 0.00016536082474226803,
      "loss": 1.4185,
      "step": 1240
    },
    {
      "epoch": 1.1899095668729176,
      "grad_norm": 0.31875547766685486,
      "learning_rate": 0.00016494845360824742,
      "loss": 1.4115,
      "step": 1250
    },
    {
      "epoch": 1.199428843407901,
      "grad_norm": 0.3276744484901428,
      "learning_rate": 0.00016453608247422681,
      "loss": 1.405,
      "step": 1260
    },
    {
      "epoch": 1.2089481199428844,
      "grad_norm": 0.3124449849128723,
      "learning_rate": 0.00016412371134020618,
      "loss": 1.4164,
      "step": 1270
    },
    {
      "epoch": 1.2184673964778676,
      "grad_norm": 0.31706124544143677,
      "learning_rate": 0.00016371134020618558,
      "loss": 1.413,
      "step": 1280
    },
    {
      "epoch": 1.227986673012851,
      "grad_norm": 0.3277345895767212,
      "learning_rate": 0.00016329896907216494,
      "loss": 1.4339,
      "step": 1290
    },
    {
      "epoch": 1.2375059495478344,
      "grad_norm": 0.3391578793525696,
      "learning_rate": 0.00016288659793814434,
      "loss": 1.414,
      "step": 1300
    },
    {
      "epoch": 1.2375059495478344,
      "eval_loss": 1.4196603298187256,
      "eval_runtime": 39.6612,
      "eval_samples_per_second": 2.521,
      "eval_steps_per_second": 0.63,
      "step": 1300
    },
    {
      "epoch": 1.2470252260828176,
      "grad_norm": 0.3561215400695801,
      "learning_rate": 0.00016247422680412373,
      "loss": 1.431,
      "step": 1310
    },
    {
      "epoch": 1.256544502617801,
      "grad_norm": 0.3222928047180176,
      "learning_rate": 0.0001620618556701031,
      "loss": 1.4207,
      "step": 1320
    },
    {
      "epoch": 1.2660637791527845,
      "grad_norm": 0.29916074872016907,
      "learning_rate": 0.0001616494845360825,
      "loss": 1.413,
      "step": 1330
    },
    {
      "epoch": 1.2755830556877679,
      "grad_norm": 0.31502220034599304,
      "learning_rate": 0.00016123711340206186,
      "loss": 1.4041,
      "step": 1340
    },
    {
      "epoch": 1.285102332222751,
      "grad_norm": 0.30248329043388367,
      "learning_rate": 0.00016082474226804125,
      "loss": 1.4136,
      "step": 1350
    },
    {
      "epoch": 1.2946216087577345,
      "grad_norm": 0.29750174283981323,
      "learning_rate": 0.00016041237113402065,
      "loss": 1.4149,
      "step": 1360
    },
    {
      "epoch": 1.3041408852927177,
      "grad_norm": 0.35403352975845337,
      "learning_rate": 0.00016,
      "loss": 1.434,
      "step": 1370
    },
    {
      "epoch": 1.313660161827701,
      "grad_norm": 0.3174794614315033,
      "learning_rate": 0.0001595876288659794,
      "loss": 1.4129,
      "step": 1380
    },
    {
      "epoch": 1.3231794383626845,
      "grad_norm": 0.31973496079444885,
      "learning_rate": 0.00015917525773195875,
      "loss": 1.4312,
      "step": 1390
    },
    {
      "epoch": 1.332698714897668,
      "grad_norm": 0.29147669672966003,
      "learning_rate": 0.00015876288659793814,
      "loss": 1.4203,
      "step": 1400
    },
    {
      "epoch": 1.332698714897668,
      "eval_loss": 1.4181098937988281,
      "eval_runtime": 39.59,
      "eval_samples_per_second": 2.526,
      "eval_steps_per_second": 0.631,
      "step": 1400
    },
    {
      "epoch": 1.342217991432651,
      "grad_norm": 0.3290899097919464,
      "learning_rate": 0.00015835051546391754,
      "loss": 1.4159,
      "step": 1410
    },
    {
      "epoch": 1.3517372679676345,
      "grad_norm": 0.2933942377567291,
      "learning_rate": 0.0001579381443298969,
      "loss": 1.4399,
      "step": 1420
    },
    {
      "epoch": 1.3612565445026177,
      "grad_norm": 0.3046482801437378,
      "learning_rate": 0.0001575257731958763,
      "loss": 1.4004,
      "step": 1430
    },
    {
      "epoch": 1.370775821037601,
      "grad_norm": 0.29072305560112,
      "learning_rate": 0.00015711340206185566,
      "loss": 1.4026,
      "step": 1440
    },
    {
      "epoch": 1.3802950975725845,
      "grad_norm": 0.32136955857276917,
      "learning_rate": 0.00015670103092783506,
      "loss": 1.4189,
      "step": 1450
    },
    {
      "epoch": 1.389814374107568,
      "grad_norm": 0.3227519094944,
      "learning_rate": 0.00015628865979381445,
      "loss": 1.417,
      "step": 1460
    },
    {
      "epoch": 1.399333650642551,
      "grad_norm": 0.32664725184440613,
      "learning_rate": 0.00015587628865979382,
      "loss": 1.41,
      "step": 1470
    },
    {
      "epoch": 1.4088529271775345,
      "grad_norm": 0.3103736340999603,
      "learning_rate": 0.0001554639175257732,
      "loss": 1.4175,
      "step": 1480
    },
    {
      "epoch": 1.418372203712518,
      "grad_norm": 0.30146801471710205,
      "learning_rate": 0.00015505154639175258,
      "loss": 1.4281,
      "step": 1490
    },
    {
      "epoch": 1.4278914802475011,
      "grad_norm": 0.3465326726436615,
      "learning_rate": 0.00015463917525773197,
      "loss": 1.3968,
      "step": 1500
    },
    {
      "epoch": 1.4278914802475011,
      "eval_loss": 1.4155893325805664,
      "eval_runtime": 39.6723,
      "eval_samples_per_second": 2.521,
      "eval_steps_per_second": 0.63,
      "step": 1500
    },
    {
      "epoch": 1.4374107567824845,
      "grad_norm": 0.33584079146385193,
      "learning_rate": 0.00015422680412371137,
      "loss": 1.4215,
      "step": 1510
    },
    {
      "epoch": 1.446930033317468,
      "grad_norm": 0.3028492331504822,
      "learning_rate": 0.00015381443298969073,
      "loss": 1.4143,
      "step": 1520
    },
    {
      "epoch": 1.4564493098524511,
      "grad_norm": 0.29686522483825684,
      "learning_rate": 0.00015340206185567013,
      "loss": 1.4249,
      "step": 1530
    },
    {
      "epoch": 1.4659685863874345,
      "grad_norm": 0.30677148699760437,
      "learning_rate": 0.00015298969072164947,
      "loss": 1.4225,
      "step": 1540
    },
    {
      "epoch": 1.475487862922418,
      "grad_norm": 0.3218235969543457,
      "learning_rate": 0.00015257731958762886,
      "loss": 1.3925,
      "step": 1550
    },
    {
      "epoch": 1.4850071394574011,
      "grad_norm": 0.29073500633239746,
      "learning_rate": 0.00015216494845360826,
      "loss": 1.4068,
      "step": 1560
    },
    {
      "epoch": 1.4945264159923846,
      "grad_norm": 0.3078315258026123,
      "learning_rate": 0.00015175257731958762,
      "loss": 1.404,
      "step": 1570
    },
    {
      "epoch": 1.504045692527368,
      "grad_norm": 0.30224424600601196,
      "learning_rate": 0.00015134020618556702,
      "loss": 1.4244,
      "step": 1580
    },
    {
      "epoch": 1.5135649690623514,
      "grad_norm": 0.3163105845451355,
      "learning_rate": 0.00015092783505154638,
      "loss": 1.4099,
      "step": 1590
    },
    {
      "epoch": 1.5230842455973346,
      "grad_norm": 0.289919376373291,
      "learning_rate": 0.00015051546391752578,
      "loss": 1.4235,
      "step": 1600
    },
    {
      "epoch": 1.5230842455973346,
      "eval_loss": 1.4139596223831177,
      "eval_runtime": 39.6382,
      "eval_samples_per_second": 2.523,
      "eval_steps_per_second": 0.631,
      "step": 1600
    },
    {
      "epoch": 1.532603522132318,
      "grad_norm": 0.2937719225883484,
      "learning_rate": 0.00015010309278350517,
      "loss": 1.4112,
      "step": 1610
    },
    {
      "epoch": 1.5421227986673012,
      "grad_norm": 0.30618056654930115,
      "learning_rate": 0.00014969072164948454,
      "loss": 1.41,
      "step": 1620
    },
    {
      "epoch": 1.5516420752022846,
      "grad_norm": 0.3118852972984314,
      "learning_rate": 0.00014927835051546393,
      "loss": 1.4234,
      "step": 1630
    },
    {
      "epoch": 1.561161351737268,
      "grad_norm": 0.30171871185302734,
      "learning_rate": 0.0001488659793814433,
      "loss": 1.4151,
      "step": 1640
    },
    {
      "epoch": 1.5706806282722514,
      "grad_norm": 0.3201466500759125,
      "learning_rate": 0.0001484536082474227,
      "loss": 1.4054,
      "step": 1650
    },
    {
      "epoch": 1.5801999048072346,
      "grad_norm": 0.3177640736103058,
      "learning_rate": 0.0001480412371134021,
      "loss": 1.4043,
      "step": 1660
    },
    {
      "epoch": 1.589719181342218,
      "grad_norm": 0.3199518918991089,
      "learning_rate": 0.00014762886597938146,
      "loss": 1.4049,
      "step": 1670
    },
    {
      "epoch": 1.5992384578772012,
      "grad_norm": 0.30514276027679443,
      "learning_rate": 0.00014721649484536085,
      "loss": 1.4103,
      "step": 1680
    },
    {
      "epoch": 1.6087577344121846,
      "grad_norm": 0.31192877888679504,
      "learning_rate": 0.0001468041237113402,
      "loss": 1.4173,
      "step": 1690
    },
    {
      "epoch": 1.618277010947168,
      "grad_norm": 0.2868764400482178,
      "learning_rate": 0.00014639175257731958,
      "loss": 1.4154,
      "step": 1700
    },
    {
      "epoch": 1.618277010947168,
      "eval_loss": 1.4129725694656372,
      "eval_runtime": 39.6482,
      "eval_samples_per_second": 2.522,
      "eval_steps_per_second": 0.631,
      "step": 1700
    },
    {
      "epoch": 1.6277962874821514,
      "grad_norm": 0.2957026958465576,
      "learning_rate": 0.00014597938144329898,
      "loss": 1.413,
      "step": 1710
    },
    {
      "epoch": 1.6373155640171349,
      "grad_norm": 0.2958736717700958,
      "learning_rate": 0.00014556701030927834,
      "loss": 1.4209,
      "step": 1720
    },
    {
      "epoch": 1.646834840552118,
      "grad_norm": 0.31275510787963867,
      "learning_rate": 0.00014515463917525774,
      "loss": 1.4022,
      "step": 1730
    },
    {
      "epoch": 1.6563541170871012,
      "grad_norm": 0.32319965958595276,
      "learning_rate": 0.0001447422680412371,
      "loss": 1.3997,
      "step": 1740
    },
    {
      "epoch": 1.6658733936220846,
      "grad_norm": 0.29642221331596375,
      "learning_rate": 0.0001443298969072165,
      "loss": 1.4032,
      "step": 1750
    },
    {
      "epoch": 1.675392670157068,
      "grad_norm": 0.32867589592933655,
      "learning_rate": 0.0001439175257731959,
      "loss": 1.4203,
      "step": 1760
    },
    {
      "epoch": 1.6849119466920515,
      "grad_norm": 0.31527167558670044,
      "learning_rate": 0.00014350515463917526,
      "loss": 1.4157,
      "step": 1770
    },
    {
      "epoch": 1.6944312232270349,
      "grad_norm": 0.3072745203971863,
      "learning_rate": 0.00014309278350515465,
      "loss": 1.3823,
      "step": 1780
    },
    {
      "epoch": 1.703950499762018,
      "grad_norm": 0.28791388869285583,
      "learning_rate": 0.00014268041237113402,
      "loss": 1.4317,
      "step": 1790
    },
    {
      "epoch": 1.7134697762970015,
      "grad_norm": 0.28491660952568054,
      "learning_rate": 0.00014226804123711342,
      "loss": 1.4128,
      "step": 1800
    },
    {
      "epoch": 1.7134697762970015,
      "eval_loss": 1.4114233255386353,
      "eval_runtime": 39.5879,
      "eval_samples_per_second": 2.526,
      "eval_steps_per_second": 0.632,
      "step": 1800
    },
    {
      "epoch": 1.7229890528319847,
      "grad_norm": 0.2969178259372711,
      "learning_rate": 0.0001418556701030928,
      "loss": 1.4014,
      "step": 1810
    },
    {
      "epoch": 1.732508329366968,
      "grad_norm": 0.29975786805152893,
      "learning_rate": 0.00014144329896907218,
      "loss": 1.3926,
      "step": 1820
    },
    {
      "epoch": 1.7420276059019515,
      "grad_norm": 0.31133607029914856,
      "learning_rate": 0.00014103092783505157,
      "loss": 1.4063,
      "step": 1830
    },
    {
      "epoch": 1.751546882436935,
      "grad_norm": 0.29973700642585754,
      "learning_rate": 0.0001406185567010309,
      "loss": 1.4148,
      "step": 1840
    },
    {
      "epoch": 1.761066158971918,
      "grad_norm": 0.2864433228969574,
      "learning_rate": 0.0001402061855670103,
      "loss": 1.4032,
      "step": 1850
    },
    {
      "epoch": 1.7705854355069015,
      "grad_norm": 0.2933174669742584,
      "learning_rate": 0.0001397938144329897,
      "loss": 1.4284,
      "step": 1860
    },
    {
      "epoch": 1.7801047120418847,
      "grad_norm": 0.2991732060909271,
      "learning_rate": 0.00013938144329896907,
      "loss": 1.4039,
      "step": 1870
    },
    {
      "epoch": 1.789623988576868,
      "grad_norm": 0.2981884479522705,
      "learning_rate": 0.00013896907216494846,
      "loss": 1.3952,
      "step": 1880
    },
    {
      "epoch": 1.7991432651118515,
      "grad_norm": 0.29072457551956177,
      "learning_rate": 0.00013855670103092783,
      "loss": 1.4121,
      "step": 1890
    },
    {
      "epoch": 1.808662541646835,
      "grad_norm": 0.3064673840999603,
      "learning_rate": 0.00013814432989690722,
      "loss": 1.4029,
      "step": 1900
    },
    {
      "epoch": 1.808662541646835,
      "eval_loss": 1.4104112386703491,
      "eval_runtime": 39.5819,
      "eval_samples_per_second": 2.526,
      "eval_steps_per_second": 0.632,
      "step": 1900
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.28513726592063904,
      "learning_rate": 0.00013773195876288661,
      "loss": 1.4098,
      "step": 1910
    },
    {
      "epoch": 1.8277010947168015,
      "grad_norm": 0.3132310211658478,
      "learning_rate": 0.00013731958762886598,
      "loss": 1.4157,
      "step": 1920
    },
    {
      "epoch": 1.8372203712517847,
      "grad_norm": 0.2846241295337677,
      "learning_rate": 0.00013690721649484538,
      "loss": 1.4045,
      "step": 1930
    },
    {
      "epoch": 1.8467396477867681,
      "grad_norm": 0.2918606996536255,
      "learning_rate": 0.00013649484536082474,
      "loss": 1.4107,
      "step": 1940
    },
    {
      "epoch": 1.8562589243217515,
      "grad_norm": 0.28303080797195435,
      "learning_rate": 0.00013608247422680414,
      "loss": 1.4221,
      "step": 1950
    },
    {
      "epoch": 1.865778200856735,
      "grad_norm": 0.2898513674736023,
      "learning_rate": 0.00013567010309278353,
      "loss": 1.3937,
      "step": 1960
    },
    {
      "epoch": 1.8752974773917184,
      "grad_norm": 0.2937197685241699,
      "learning_rate": 0.0001352577319587629,
      "loss": 1.4134,
      "step": 1970
    },
    {
      "epoch": 1.8848167539267016,
      "grad_norm": 0.2756626605987549,
      "learning_rate": 0.0001348453608247423,
      "loss": 1.4085,
      "step": 1980
    },
    {
      "epoch": 1.8943360304616848,
      "grad_norm": 0.28634968400001526,
      "learning_rate": 0.00013443298969072166,
      "loss": 1.3999,
      "step": 1990
    },
    {
      "epoch": 1.9038553069966682,
      "grad_norm": 0.28319478034973145,
      "learning_rate": 0.00013402061855670103,
      "loss": 1.3935,
      "step": 2000
    },
    {
      "epoch": 1.9038553069966682,
      "eval_loss": 1.4095008373260498,
      "eval_runtime": 39.6055,
      "eval_samples_per_second": 2.525,
      "eval_steps_per_second": 0.631,
      "step": 2000
    }
  ],
  "logging_steps": 10,
  "max_steps": 5250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.296083329417216e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}