{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009009009009009009,
      "grad_norm": 1.3664734363555908,
      "learning_rate": 9.00900900900901e-06,
      "loss": 3.0355,
      "step": 10
    },
    {
      "epoch": 0.018018018018018018,
      "grad_norm": 1.426148533821106,
      "learning_rate": 1.801801801801802e-05,
      "loss": 3.0333,
      "step": 20
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 1.4102978706359863,
      "learning_rate": 2.702702702702703e-05,
      "loss": 2.8445,
      "step": 30
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 1.448880910873413,
      "learning_rate": 3.603603603603604e-05,
      "loss": 2.5113,
      "step": 40
    },
    {
      "epoch": 0.04504504504504504,
      "grad_norm": 1.8392173051834106,
      "learning_rate": 4.5045045045045046e-05,
      "loss": 2.2516,
      "step": 50
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.6239687204360962,
      "learning_rate": 5.405405405405406e-05,
      "loss": 2.1521,
      "step": 60
    },
    {
      "epoch": 0.06306306306306306,
      "grad_norm": 1.783531904220581,
      "learning_rate": 6.306306306306306e-05,
      "loss": 2.0766,
      "step": 70
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 1.878064513206482,
      "learning_rate": 7.207207207207208e-05,
      "loss": 2.0584,
      "step": 80
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 1.793707013130188,
      "learning_rate": 8.108108108108109e-05,
      "loss": 2.0741,
      "step": 90
    },
    {
      "epoch": 0.09009009009009009,
      "grad_norm": 1.812543511390686,
      "learning_rate": 9.009009009009009e-05,
      "loss": 1.9833,
      "step": 100
    },
    {
      "epoch": 0.0990990990990991,
      "grad_norm": 2.002195119857788,
      "learning_rate": 9.90990990990991e-05,
      "loss": 1.9653,
      "step": 110
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 2.367985963821411,
      "learning_rate": 9.99799753559161e-05,
      "loss": 2.0073,
      "step": 120
    },
    {
      "epoch": 0.11711711711711711,
      "grad_norm": 1.732643485069275,
      "learning_rate": 9.991077495600804e-05,
      "loss": 1.9519,
      "step": 130
    },
    {
      "epoch": 0.12612612612612611,
      "grad_norm": 1.9506319761276245,
      "learning_rate": 9.979221999536699e-05,
      "loss": 1.9233,
      "step": 140
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 1.7935253381729126,
      "learning_rate": 9.962442770775675e-05,
      "loss": 1.9716,
      "step": 150
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 2.0075876712799072,
      "learning_rate": 9.940756401555898e-05,
      "loss": 1.8546,
      "step": 160
    },
    {
      "epoch": 0.15315315315315314,
      "grad_norm": 1.8393422365188599,
      "learning_rate": 9.914184336569974e-05,
      "loss": 1.9295,
      "step": 170
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 2.006378650665283,
      "learning_rate": 9.882752851759248e-05,
      "loss": 1.872,
      "step": 180
    },
    {
      "epoch": 0.17117117117117117,
      "grad_norm": 1.8561218976974487,
      "learning_rate": 9.846493028330678e-05,
      "loss": 1.8979,
      "step": 190
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 1.9337742328643799,
      "learning_rate": 9.805440722022014e-05,
      "loss": 1.8461,
      "step": 200
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 1.990472435951233,
      "learning_rate": 9.759636527645633e-05,
      "loss": 1.885,
      "step": 210
    },
    {
      "epoch": 0.1981981981981982,
      "grad_norm": 2.0939085483551025,
      "learning_rate": 9.709125738946125e-05,
      "loss": 1.8196,
      "step": 220
    },
    {
      "epoch": 0.2072072072072072,
      "grad_norm": 2.165142297744751,
      "learning_rate": 9.65395830381131e-05,
      "loss": 1.8212,
      "step": 230
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 1.9272476434707642,
      "learning_rate": 9.594188774880982e-05,
      "loss": 1.7787,
      "step": 240
    },
    {
      "epoch": 0.22522522522522523,
      "grad_norm": 1.9800828695297241,
      "learning_rate": 9.5298762556022e-05,
      "loss": 1.8144,
      "step": 250
    },
    {
      "epoch": 0.23423423423423423,
      "grad_norm": 2.138906240463257,
      "learning_rate": 9.46108434178452e-05,
      "loss": 1.8595,
      "step": 260
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 2.0844318866729736,
      "learning_rate": 9.387881058712888e-05,
      "loss": 1.8435,
      "step": 270
    },
    {
      "epoch": 0.25225225225225223,
      "grad_norm": 2.002121925354004,
      "learning_rate": 9.310338793880458e-05,
      "loss": 1.7743,
      "step": 280
    },
    {
      "epoch": 0.26126126126126126,
      "grad_norm": 2.004910469055176,
      "learning_rate": 9.228534225407781e-05,
      "loss": 1.7949,
      "step": 290
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 2.2141101360321045,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.7682,
      "step": 300
    },
    {
      "epoch": 0.27927927927927926,
      "grad_norm": 2.036374807357788,
      "learning_rate": 9.05246588405146e-05,
      "loss": 1.761,
      "step": 310
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 2.0280163288116455,
      "learning_rate": 8.958376217373428e-05,
      "loss": 1.8201,
      "step": 320
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 2.244485378265381,
      "learning_rate": 8.860372287300431e-05,
      "loss": 1.762,
      "step": 330
    },
    {
      "epoch": 0.3063063063063063,
      "grad_norm": 2.02524471282959,
      "learning_rate": 8.758551005589967e-05,
      "loss": 1.7456,
      "step": 340
    },
    {
      "epoch": 0.3153153153153153,
      "grad_norm": 2.269183397293091,
      "learning_rate": 8.653013058809944e-05,
      "loss": 1.7447,
      "step": 350
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 2.273630142211914,
      "learning_rate": 8.543862808774192e-05,
      "loss": 1.7693,
      "step": 360
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.9659849405288696,
      "learning_rate": 8.43120818934367e-05,
      "loss": 1.7175,
      "step": 370
    },
    {
      "epoch": 0.34234234234234234,
      "grad_norm": 2.624666690826416,
      "learning_rate": 8.315160599695434e-05,
      "loss": 1.7573,
      "step": 380
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 2.3735556602478027,
      "learning_rate": 8.195834794164925e-05,
      "loss": 1.7034,
      "step": 390
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 2.209813117980957,
      "learning_rate": 8.073348768770462e-05,
      "loss": 1.7617,
      "step": 400
    },
    {
      "epoch": 0.36936936936936937,
      "grad_norm": 2.607027530670166,
      "learning_rate": 7.947823644532198e-05,
      "loss": 1.7826,
      "step": 410
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 2.2740437984466553,
      "learning_rate": 7.81938354770089e-05,
      "loss": 1.7294,
      "step": 420
    },
    {
      "epoch": 0.38738738738738737,
      "grad_norm": 2.4003989696502686,
      "learning_rate": 7.688155487014936e-05,
      "loss": 1.7352,
      "step": 430
    },
    {
      "epoch": 0.3963963963963964,
      "grad_norm": 2.295224905014038,
      "learning_rate": 7.554269228107044e-05,
      "loss": 1.7472,
      "step": 440
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 2.1371731758117676,
      "learning_rate": 7.417857165184723e-05,
      "loss": 1.66,
      "step": 450
    },
    {
      "epoch": 0.4144144144144144,
      "grad_norm": 2.535508155822754,
      "learning_rate": 7.279054190111506e-05,
      "loss": 1.6889,
      "step": 460
    },
    {
      "epoch": 0.42342342342342343,
      "grad_norm": 2.1276588439941406,
      "learning_rate": 7.137997559018346e-05,
      "loss": 1.7011,
      "step": 470
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 2.2915713787078857,
      "learning_rate": 6.994826756577082e-05,
      "loss": 1.6353,
      "step": 480
    },
    {
      "epoch": 0.44144144144144143,
      "grad_norm": 2.1963353157043457,
      "learning_rate": 6.849683358070217e-05,
      "loss": 1.6553,
      "step": 490
    },
    {
      "epoch": 0.45045045045045046,
      "grad_norm": 2.3190746307373047,
      "learning_rate": 6.702710889393369e-05,
      "loss": 1.6471,
      "step": 500
    },
    {
      "epoch": 0.45045045045045046,
      "eval_loss": 1.7359974384307861,
      "eval_runtime": 51.5503,
      "eval_samples_per_second": 76.527,
      "eval_steps_per_second": 19.146,
      "step": 500
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 2.2826740741729736,
      "learning_rate": 6.554054685128856e-05,
      "loss": 1.7566,
      "step": 510
    },
    {
      "epoch": 0.46846846846846846,
      "grad_norm": 2.4409995079040527,
      "learning_rate": 6.403861744830747e-05,
      "loss": 1.7117,
      "step": 520
    },
    {
      "epoch": 0.4774774774774775,
      "grad_norm": 2.375598907470703,
      "learning_rate": 6.252280587663492e-05,
      "loss": 1.6775,
      "step": 530
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 2.470062255859375,
      "learning_rate": 6.099461105537889e-05,
      "loss": 1.6699,
      "step": 540
    },
    {
      "epoch": 0.4954954954954955,
      "grad_norm": 2.439343214035034,
      "learning_rate": 5.945554414889582e-05,
      "loss": 1.6072,
      "step": 550
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 2.3654677867889404,
      "learning_rate": 5.790712707246705e-05,
      "loss": 1.6006,
      "step": 560
    },
    {
      "epoch": 0.5135135135135135,
      "grad_norm": 2.3721349239349365,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 1.6737,
      "step": 570
    },
    {
      "epoch": 0.5225225225225225,
      "grad_norm": 2.794997453689575,
      "learning_rate": 5.478837478665021e-05,
      "loss": 1.695,
      "step": 580
    },
    {
      "epoch": 0.5315315315315315,
      "grad_norm": 2.6293647289276123,
      "learning_rate": 5.322112357363841e-05,
      "loss": 1.6577,
      "step": 590
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 2.333765745162964,
      "learning_rate": 5.1650687133805674e-05,
      "loss": 1.6792,
      "step": 600
    },
    {
      "epoch": 0.5495495495495496,
      "grad_norm": 2.4596219062805176,
      "learning_rate": 5.007861840237923e-05,
      "loss": 1.6937,
      "step": 610
    },
    {
      "epoch": 0.5585585585585585,
      "grad_norm": 2.6094493865966797,
      "learning_rate": 4.850647192868735e-05,
      "loss": 1.6714,
      "step": 620
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 2.353469133377075,
      "learning_rate": 4.69358023389342e-05,
      "loss": 1.6349,
      "step": 630
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 2.481355667114258,
      "learning_rate": 4.536816279889865e-05,
      "loss": 1.5774,
      "step": 640
    },
    {
      "epoch": 0.5855855855855856,
      "grad_norm": 2.60036563873291,
      "learning_rate": 4.380510347807725e-05,
      "loss": 1.6312,
      "step": 650
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 2.5595216751098633,
      "learning_rate": 4.224817001679011e-05,
      "loss": 1.6359,
      "step": 660
    },
    {
      "epoch": 0.6036036036036037,
      "grad_norm": 2.7325408458709717,
      "learning_rate": 4.06989019977654e-05,
      "loss": 1.7161,
      "step": 670
    },
    {
      "epoch": 0.6126126126126126,
      "grad_norm": 2.384521007537842,
      "learning_rate": 3.9158831423714036e-05,
      "loss": 1.6495,
      "step": 680
    },
    {
      "epoch": 0.6216216216216216,
      "grad_norm": 2.7080259323120117,
      "learning_rate": 3.762948120239988e-05,
      "loss": 1.6727,
      "step": 690
    },
    {
      "epoch": 0.6306306306306306,
      "grad_norm": 2.678630828857422,
      "learning_rate": 3.6112363640703476e-05,
      "loss": 1.6925,
      "step": 700
    },
    {
      "epoch": 0.6396396396396397,
      "grad_norm": 2.457289457321167,
      "learning_rate": 3.4608978949168614e-05,
      "loss": 1.6202,
      "step": 710
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 2.3443291187286377,
      "learning_rate": 3.312081375851038e-05,
      "loss": 1.5941,
      "step": 720
    },
    {
      "epoch": 0.6576576576576577,
      "grad_norm": 2.434515953063965,
      "learning_rate": 3.164933964955174e-05,
      "loss": 1.622,
      "step": 730
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.5307750701904297,
      "learning_rate": 3.019601169804216e-05,
      "loss": 1.6565,
      "step": 740
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 2.6859347820281982,
      "learning_rate": 2.876226703579761e-05,
      "loss": 1.6155,
      "step": 750
    },
    {
      "epoch": 0.6846846846846847,
      "grad_norm": 2.6468803882598877,
      "learning_rate": 2.7349523429584305e-05,
      "loss": 1.6692,
      "step": 760
    },
    {
      "epoch": 0.6936936936936937,
      "grad_norm": 2.4167847633361816,
      "learning_rate": 2.595917787915176e-05,
      "loss": 1.5915,
      "step": 770
    },
    {
      "epoch": 0.7027027027027027,
      "grad_norm": 2.6717164516448975,
      "learning_rate": 2.459260523580154e-05,
      "loss": 1.6659,
      "step": 780
    },
    {
      "epoch": 0.7117117117117117,
      "grad_norm": 2.5674118995666504,
      "learning_rate": 2.325115684285743e-05,
      "loss": 1.5425,
      "step": 790
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 2.6461567878723145,
      "learning_rate": 2.1936159199381743e-05,
      "loss": 1.6597,
      "step": 800
    },
    {
      "epoch": 0.7297297297297297,
      "grad_norm": 2.5922305583953857,
      "learning_rate": 2.0648912648459074e-05,
      "loss": 1.6627,
      "step": 810
    },
    {
      "epoch": 0.7387387387387387,
      "grad_norm": 2.553170680999756,
      "learning_rate": 1.939069009134433e-05,
      "loss": 1.5385,
      "step": 820
    },
    {
      "epoch": 0.7477477477477478,
      "grad_norm": 2.7178986072540283,
      "learning_rate": 1.8162735728746975e-05,
      "loss": 1.5861,
      "step": 830
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 2.497939348220825,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 1.694,
      "step": 840
    },
    {
      "epoch": 0.7657657657657657,
      "grad_norm": 2.7136847972869873,
      "learning_rate": 1.5802457534801718e-05,
      "loss": 1.6814,
      "step": 850
    },
    {
      "epoch": 0.7747747747747747,
      "grad_norm": 2.701145887374878,
      "learning_rate": 1.4672467678303386e-05,
      "loss": 1.5897,
      "step": 860
    },
    {
      "epoch": 0.7837837837837838,
      "grad_norm": 2.8379249572753906,
      "learning_rate": 1.3577411658056966e-05,
      "loss": 1.6266,
      "step": 870
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 2.6730990409851074,
      "learning_rate": 1.2518372326590877e-05,
      "loss": 1.5935,
      "step": 880
    },
    {
      "epoch": 0.8018018018018018,
      "grad_norm": 2.6736879348754883,
      "learning_rate": 1.149639692112095e-05,
      "loss": 1.5966,
      "step": 890
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 2.9796481132507324,
      "learning_rate": 1.0512496027983714e-05,
      "loss": 1.6568,
      "step": 900
    },
    {
      "epoch": 0.8198198198198198,
      "grad_norm": 2.821319103240967,
      "learning_rate": 9.56764258331226e-06,
      "loss": 1.6065,
      "step": 910
    },
    {
      "epoch": 0.8288288288288288,
      "grad_norm": 2.5861129760742188,
      "learning_rate": 8.662770910942692e-06,
      "loss": 1.5545,
      "step": 920
    },
    {
      "epoch": 0.8378378378378378,
      "grad_norm": 2.6395463943481445,
      "learning_rate": 7.798775798502483e-06,
      "loss": 1.5567,
      "step": 930
    },
    {
      "epoch": 0.8468468468468469,
      "grad_norm": 2.8468408584594727,
      "learning_rate": 6.976511612594622e-06,
      "loss": 1.5972,
      "step": 940
    },
    {
      "epoch": 0.8558558558558559,
      "grad_norm": 3.0037944316864014,
      "learning_rate": 6.1967914539521e-06,
      "loss": 1.6084,
      "step": 950
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 2.7935662269592285,
      "learning_rate": 5.460386353398583e-06,
      "loss": 1.571,
      "step": 960
    },
    {
      "epoch": 0.8738738738738738,
      "grad_norm": 2.817194938659668,
      "learning_rate": 4.768024509410096e-06,
      "loss": 1.5944,
      "step": 970
    },
    {
      "epoch": 0.8828828828828829,
      "grad_norm": 2.5486297607421875,
      "learning_rate": 4.120390568031673e-06,
      "loss": 1.5694,
      "step": 980
    },
    {
      "epoch": 0.8918918918918919,
      "grad_norm": 2.557070255279541,
      "learning_rate": 3.51812494586114e-06,
      "loss": 1.6251,
      "step": 990
    },
    {
      "epoch": 0.9009009009009009,
      "grad_norm": 2.4766974449157715,
      "learning_rate": 2.9618231967694532e-06,
      "loss": 1.6062,
      "step": 1000
    },
    {
      "epoch": 0.9009009009009009,
      "eval_loss": 1.6383798122406006,
      "eval_runtime": 51.1987,
      "eval_samples_per_second": 77.053,
      "eval_steps_per_second": 19.278,
      "step": 1000
    },
    {
      "epoch": 0.9099099099099099,
      "grad_norm": 2.7714474201202393,
      "learning_rate": 2.452035422983734e-06,
      "loss": 1.5405,
      "step": 1010
    },
    {
      "epoch": 0.918918918918919,
      "grad_norm": 2.9670562744140625,
      "learning_rate": 1.9892657311155248e-06,
      "loss": 1.6195,
      "step": 1020
    },
    {
      "epoch": 0.9279279279279279,
      "grad_norm": 2.3906571865081787,
      "learning_rate": 1.5739717336720084e-06,
      "loss": 1.5761,
      "step": 1030
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 2.843130588531494,
      "learning_rate": 1.2065640965432001e-06,
      "loss": 1.5647,
      "step": 1040
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 2.8360941410064697,
      "learning_rate": 8.874061329125938e-07,
      "loss": 1.6573,
      "step": 1050
    },
    {
      "epoch": 0.954954954954955,
      "grad_norm": 2.885618209838867,
      "learning_rate": 6.168134439928364e-07,
      "loss": 1.5961,
      "step": 1060
    },
    {
      "epoch": 0.963963963963964,
      "grad_norm": 2.8238613605499268,
      "learning_rate": 3.950536069415756e-07,
      "loss": 1.6878,
      "step": 1070
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 2.663311719894409,
      "learning_rate": 2.223459102662695e-07,
      "loss": 1.6297,
      "step": 1080
    },
    {
      "epoch": 0.9819819819819819,
      "grad_norm": 2.4804253578186035,
      "learning_rate": 9.886113697944454e-08,
      "loss": 1.6147,
      "step": 1090
    },
    {
      "epoch": 0.990990990990991,
      "grad_norm": 2.756866216659546,
      "learning_rate": 2.4721395718924068e-08,
      "loss": 1.6267,
      "step": 1100
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.6657907962799072,
      "learning_rate": 0.0,
      "loss": 1.5991,
      "step": 1110
    },
    {
      "epoch": 1.0,
      "step": 1110,
      "total_flos": 2.3250303254423142e+17,
      "train_loss": 1.7593931747986389,
      "train_runtime": 934.3961,
      "train_samples_per_second": 37.998,
      "train_steps_per_second": 1.188
    }
  ],
  "logging_steps": 10,
  "max_steps": 1110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3250303254423142e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}