{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.914529914529915,
  "eval_steps": 500,
  "global_step": 870,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.158817857503891,
      "learning_rate": 0.0001999348095389677,
      "loss": 0.9924,
      "step": 10
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.21280939877033234,
      "learning_rate": 0.000199739323151795,
      "loss": 0.819,
      "step": 20
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.22974510490894318,
      "learning_rate": 0.00019941379571543596,
      "loss": 0.767,
      "step": 30
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.20720455050468445,
      "learning_rate": 0.00019895865165556377,
      "loss": 0.6948,
      "step": 40
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.1902514398097992,
      "learning_rate": 0.00019837448439320027,
      "loss": 0.6509,
      "step": 50
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.18335820734500885,
      "learning_rate": 0.00019766205557100868,
      "loss": 0.6344,
      "step": 60
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.17900069057941437,
      "learning_rate": 0.00019682229406025635,
      "loss": 0.6447,
      "step": 70
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.16915330290794373,
      "learning_rate": 0.00019585629474974415,
      "loss": 0.6335,
      "step": 80
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.16036000847816467,
      "learning_rate": 0.00019476531711828027,
      "loss": 0.634,
      "step": 90
    },
    {
      "epoch": 1.1396011396011396,
      "grad_norm": 0.16852639615535736,
      "learning_rate": 0.0001935507835925601,
      "loss": 0.6058,
      "step": 100
    },
    {
      "epoch": 1.2535612535612537,
      "grad_norm": 0.15856905281543732,
      "learning_rate": 0.00019221427769259333,
      "loss": 0.5902,
      "step": 110
    },
    {
      "epoch": 1.3675213675213675,
      "grad_norm": 0.16909192502498627,
      "learning_rate": 0.00019075754196709572,
      "loss": 0.6051,
      "step": 120
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.1899166703224182,
      "learning_rate": 0.00018918247572153823,
      "loss": 0.6098,
      "step": 130
    },
    {
      "epoch": 1.5954415954415955,
      "grad_norm": 0.17596793174743652,
      "learning_rate": 0.00018749113254181498,
      "loss": 0.597,
      "step": 140
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 0.16560517251491547,
      "learning_rate": 0.00018568571761675893,
      "loss": 0.5899,
      "step": 150
    },
    {
      "epoch": 1.8233618233618234,
      "grad_norm": 0.16513986885547638,
      "learning_rate": 0.00018376858486299647,
      "loss": 0.5989,
      "step": 160
    },
    {
      "epoch": 1.9373219373219372,
      "grad_norm": 0.20360782742500305,
      "learning_rate": 0.00018174223385588917,
      "loss": 0.5982,
      "step": 170
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 0.16155321896076202,
      "learning_rate": 0.00017960930657056438,
      "loss": 0.593,
      "step": 180
    },
    {
      "epoch": 2.1652421652421654,
      "grad_norm": 0.1811763048171997,
      "learning_rate": 0.00017737258393728364,
      "loss": 0.6077,
      "step": 190
    },
    {
      "epoch": 2.2792022792022792,
      "grad_norm": 0.16952063143253326,
      "learning_rate": 0.00017503498221564025,
      "loss": 0.5749,
      "step": 200
    },
    {
      "epoch": 2.393162393162393,
      "grad_norm": 0.17240603268146515,
      "learning_rate": 0.0001725995491923131,
      "loss": 0.5592,
      "step": 210
    },
    {
      "epoch": 2.5071225071225074,
      "grad_norm": 0.1657334417104721,
      "learning_rate": 0.00017006946020733425,
      "loss": 0.5779,
      "step": 220
    },
    {
      "epoch": 2.6210826210826212,
      "grad_norm": 0.16417497396469116,
      "learning_rate": 0.0001674480140140514,
      "loss": 0.5675,
      "step": 230
    },
    {
      "epoch": 2.735042735042735,
      "grad_norm": 0.174308180809021,
      "learning_rate": 0.00016473862847818277,
      "loss": 0.5977,
      "step": 240
    },
    {
      "epoch": 2.849002849002849,
      "grad_norm": 0.17116901278495789,
      "learning_rate": 0.0001619448361215723,
      "loss": 0.5582,
      "step": 250
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.16816489398479462,
      "learning_rate": 0.0001590702795164551,
      "loss": 0.5813,
      "step": 260
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.17530137300491333,
      "learning_rate": 0.00015611870653623825,
      "loss": 0.559,
      "step": 270
    },
    {
      "epoch": 3.190883190883191,
      "grad_norm": 0.1744232326745987,
      "learning_rate": 0.0001530939654689887,
      "loss": 0.5668,
      "step": 280
    },
    {
      "epoch": 3.304843304843305,
      "grad_norm": 0.1809006929397583,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.5754,
      "step": 290
    },
    {
      "epoch": 3.4188034188034186,
      "grad_norm": 0.16484159231185913,
      "learning_rate": 0.00014684084406997903,
      "loss": 0.5731,
      "step": 300
    },
    {
      "epoch": 3.532763532763533,
      "grad_norm": 0.19075918197631836,
      "learning_rate": 0.00014362061661555675,
      "loss": 0.5496,
      "step": 310
    },
    {
      "epoch": 3.646723646723647,
      "grad_norm": 0.18451079726219177,
      "learning_rate": 0.00014034351619898088,
      "loss": 0.5463,
      "step": 320
    },
    {
      "epoch": 3.7606837606837606,
      "grad_norm": 0.18566997349262238,
      "learning_rate": 0.00013701381553399145,
      "loss": 0.5768,
      "step": 330
    },
    {
      "epoch": 3.8746438746438745,
      "grad_norm": 0.1669853925704956,
      "learning_rate": 0.0001336358559150175,
      "loss": 0.5606,
      "step": 340
    },
    {
      "epoch": 3.9886039886039883,
      "grad_norm": 0.17847082018852234,
      "learning_rate": 0.00013021404155695725,
      "loss": 0.5756,
      "step": 350
    },
    {
      "epoch": 4.102564102564102,
      "grad_norm": 0.16660483181476593,
      "learning_rate": 0.00012675283385292212,
      "loss": 0.5585,
      "step": 360
    },
    {
      "epoch": 4.216524216524217,
      "grad_norm": 0.17163340747356415,
      "learning_rate": 0.00012325674555743106,
      "loss": 0.5434,
      "step": 370
    },
    {
      "epoch": 4.330484330484331,
      "grad_norm": 0.16264410316944122,
      "learning_rate": 0.00011973033490264001,
      "loss": 0.5449,
      "step": 380
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.17614829540252686,
      "learning_rate": 0.0001161781996552765,
      "loss": 0.5574,
      "step": 390
    },
    {
      "epoch": 4.5584045584045585,
      "grad_norm": 0.19437584280967712,
      "learning_rate": 0.00011260497112202895,
      "loss": 0.5448,
      "step": 400
    },
    {
      "epoch": 4.672364672364672,
      "grad_norm": 0.19045701622962952,
      "learning_rate": 0.00010901530811120655,
      "loss": 0.5474,
      "step": 410
    },
    {
      "epoch": 4.786324786324786,
      "grad_norm": 0.21330882608890533,
      "learning_rate": 0.00010541389085854176,
      "loss": 0.5552,
      "step": 420
    },
    {
      "epoch": 4.9002849002849,
      "grad_norm": 0.17429402470588684,
      "learning_rate": 0.00010180541492505604,
      "loss": 0.5495,
      "step": 430
    },
    {
      "epoch": 5.014245014245014,
      "grad_norm": 0.17785826325416565,
      "learning_rate": 9.819458507494394e-05,
      "loss": 0.5583,
      "step": 440
    },
    {
      "epoch": 5.128205128205128,
      "grad_norm": 0.19076977670192719,
      "learning_rate": 9.458610914145826e-05,
      "loss": 0.5291,
      "step": 450
    },
    {
      "epoch": 5.2421652421652425,
      "grad_norm": 0.19988471269607544,
      "learning_rate": 9.098469188879349e-05,
      "loss": 0.5311,
      "step": 460
    },
    {
      "epoch": 5.356125356125356,
      "grad_norm": 0.19638335704803467,
      "learning_rate": 8.739502887797107e-05,
      "loss": 0.5684,
      "step": 470
    },
    {
      "epoch": 5.47008547008547,
      "grad_norm": 0.2043437659740448,
      "learning_rate": 8.382180034472353e-05,
      "loss": 0.5371,
      "step": 480
    },
    {
      "epoch": 5.584045584045584,
      "grad_norm": 0.2045976221561432,
      "learning_rate": 8.026966509736001e-05,
      "loss": 0.5307,
      "step": 490
    },
    {
      "epoch": 5.698005698005698,
      "grad_norm": 0.21237310767173767,
      "learning_rate": 7.674325444256899e-05,
      "loss": 0.5483,
      "step": 500
    },
    {
      "epoch": 5.811965811965812,
      "grad_norm": 0.22306476533412933,
      "learning_rate": 7.324716614707793e-05,
      "loss": 0.5572,
      "step": 510
    },
    {
      "epoch": 5.925925925925926,
      "grad_norm": 0.20065273344516754,
      "learning_rate": 6.978595844304271e-05,
      "loss": 0.5363,
      "step": 520
    },
    {
      "epoch": 6.0398860398860394,
      "grad_norm": 0.21213628351688385,
      "learning_rate": 6.636414408498249e-05,
      "loss": 0.521,
      "step": 530
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 0.1936779022216797,
      "learning_rate": 6.298618446600856e-05,
      "loss": 0.5283,
      "step": 540
    },
    {
      "epoch": 6.267806267806268,
      "grad_norm": 0.19564631581306458,
      "learning_rate": 5.965648380101916e-05,
      "loss": 0.5301,
      "step": 550
    },
    {
      "epoch": 6.381766381766382,
      "grad_norm": 0.20069913566112518,
      "learning_rate": 5.6379383384443255e-05,
      "loss": 0.5204,
      "step": 560
    },
    {
      "epoch": 6.495726495726496,
      "grad_norm": 0.21325626969337463,
      "learning_rate": 5.3159155930021e-05,
      "loss": 0.5419,
      "step": 570
    },
    {
      "epoch": 6.60968660968661,
      "grad_norm": 0.21303197741508484,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.543,
      "step": 580
    },
    {
      "epoch": 6.7236467236467234,
      "grad_norm": 0.21136346459388733,
      "learning_rate": 4.6906034531011346e-05,
      "loss": 0.5217,
      "step": 590
    },
    {
      "epoch": 6.837606837606837,
      "grad_norm": 0.21392931044101715,
      "learning_rate": 4.388129346376178e-05,
      "loss": 0.5288,
      "step": 600
    },
    {
      "epoch": 6.951566951566951,
      "grad_norm": 0.22880437970161438,
      "learning_rate": 4.092972048354491e-05,
      "loss": 0.5273,
      "step": 610
    },
    {
      "epoch": 7.065527065527066,
      "grad_norm": 0.21491903066635132,
      "learning_rate": 3.80551638784277e-05,
      "loss": 0.5332,
      "step": 620
    },
    {
      "epoch": 7.17948717948718,
      "grad_norm": 0.26633119583129883,
      "learning_rate": 3.5261371521817244e-05,
      "loss": 0.5239,
      "step": 630
    },
    {
      "epoch": 7.293447293447294,
      "grad_norm": 0.23685385286808014,
      "learning_rate": 3.2551985985948616e-05,
      "loss": 0.5309,
      "step": 640
    },
    {
      "epoch": 7.407407407407407,
      "grad_norm": 0.22292840480804443,
      "learning_rate": 2.993053979266577e-05,
      "loss": 0.5372,
      "step": 650
    },
    {
      "epoch": 7.521367521367521,
      "grad_norm": 0.2220107614994049,
      "learning_rate": 2.7400450807686938e-05,
      "loss": 0.5083,
      "step": 660
    },
    {
      "epoch": 7.635327635327635,
      "grad_norm": 0.2191537618637085,
      "learning_rate": 2.496501778435977e-05,
      "loss": 0.5164,
      "step": 670
    },
    {
      "epoch": 7.749287749287749,
      "grad_norm": 0.22593119740486145,
      "learning_rate": 2.2627416062716366e-05,
      "loss": 0.5152,
      "step": 680
    },
    {
      "epoch": 7.863247863247864,
      "grad_norm": 0.23532789945602417,
      "learning_rate": 2.0390693429435627e-05,
      "loss": 0.5269,
      "step": 690
    },
    {
      "epoch": 7.977207977207978,
      "grad_norm": 0.25111591815948486,
      "learning_rate": 1.825776614411082e-05,
      "loss": 0.5335,
      "step": 700
    },
    {
      "epoch": 8.091168091168091,
      "grad_norm": 0.21956747770309448,
      "learning_rate": 1.6231415137003537e-05,
      "loss": 0.5144,
      "step": 710
    },
    {
      "epoch": 8.205128205128204,
      "grad_norm": 0.23355403542518616,
      "learning_rate": 1.4314282383241096e-05,
      "loss": 0.5294,
      "step": 720
    },
    {
      "epoch": 8.31908831908832,
      "grad_norm": 0.23712006211280823,
      "learning_rate": 1.2508867458185037e-05,
      "loss": 0.5229,
      "step": 730
    },
    {
      "epoch": 8.433048433048434,
      "grad_norm": 0.22506175935268402,
      "learning_rate": 1.0817524278461776e-05,
      "loss": 0.5212,
      "step": 740
    },
    {
      "epoch": 8.547008547008547,
      "grad_norm": 0.21853385865688324,
      "learning_rate": 9.242458032904311e-06,
      "loss": 0.5193,
      "step": 750
    },
    {
      "epoch": 8.660968660968662,
      "grad_norm": 0.23257511854171753,
      "learning_rate": 7.785722307406684e-06,
      "loss": 0.5039,
      "step": 760
    },
    {
      "epoch": 8.774928774928775,
      "grad_norm": 0.21563945710659027,
      "learning_rate": 6.4492164074399065e-06,
      "loss": 0.5232,
      "step": 770
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 0.22108329832553864,
      "learning_rate": 5.2346828817197655e-06,
      "loss": 0.5309,
      "step": 780
    },
    {
      "epoch": 9.002849002849002,
      "grad_norm": 0.22330021858215332,
      "learning_rate": 4.143705250255869e-06,
      "loss": 0.5287,
      "step": 790
    },
    {
      "epoch": 9.116809116809117,
      "grad_norm": 0.22394247353076935,
      "learning_rate": 3.1777059397436692e-06,
      "loss": 0.5007,
      "step": 800
    },
    {
      "epoch": 9.23076923076923,
      "grad_norm": 0.2144930511713028,
      "learning_rate": 2.3379444289913342e-06,
      "loss": 0.5277,
      "step": 810
    },
    {
      "epoch": 9.344729344729345,
      "grad_norm": 0.2214236557483673,
      "learning_rate": 1.6255156067997323e-06,
      "loss": 0.5173,
      "step": 820
    },
    {
      "epoch": 9.45868945868946,
      "grad_norm": 0.2192196100950241,
      "learning_rate": 1.0413483444362771e-06,
      "loss": 0.5123,
      "step": 830
    },
    {
      "epoch": 9.572649572649572,
      "grad_norm": 0.22837017476558685,
      "learning_rate": 5.862042845640403e-07,
      "loss": 0.5279,
      "step": 840
    },
    {
      "epoch": 9.686609686609687,
      "grad_norm": 0.21172335743904114,
      "learning_rate": 2.606768482050215e-07,
      "loss": 0.5263,
      "step": 850
    },
    {
      "epoch": 9.8005698005698,
      "grad_norm": 0.23530949652194977,
      "learning_rate": 6.519046103230508e-08,
      "loss": 0.5202,
      "step": 860
    },
    {
      "epoch": 9.914529914529915,
      "grad_norm": 0.23058444261550903,
      "learning_rate": 0.0,
      "loss": 0.5243,
      "step": 870
    },
    {
      "epoch": 9.914529914529915,
      "step": 870,
      "total_flos": 5.67984355540992e+16,
      "train_loss": 0.5655439464525245,
      "train_runtime": 2716.1071,
      "train_samples_per_second": 1.292,
      "train_steps_per_second": 0.32
    }
  ],
  "logging_steps": 10,
  "max_steps": 870,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 5.67984355540992e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}