{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6811989100817438,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006811989100817439,
      "grad_norm": 0.7318916320800781,
      "learning_rate": 1.8e-05,
      "loss": 0.8676,
      "step": 10
    },
    {
      "epoch": 0.013623978201634877,
      "grad_norm": 0.9373026490211487,
      "learning_rate": 3.8e-05,
      "loss": 0.8509,
      "step": 20
    },
    {
      "epoch": 0.020435967302452316,
      "grad_norm": 0.8689849972724915,
      "learning_rate": 5.8e-05,
      "loss": 0.7223,
      "step": 30
    },
    {
      "epoch": 0.027247956403269755,
      "grad_norm": 0.4938766062259674,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.5077,
      "step": 40
    },
    {
      "epoch": 0.0340599455040872,
      "grad_norm": 0.3275890052318573,
      "learning_rate": 9.8e-05,
      "loss": 0.3697,
      "step": 50
    },
    {
      "epoch": 0.04087193460490463,
      "grad_norm": 0.38690876960754395,
      "learning_rate": 9.997785653888835e-05,
      "loss": 0.3255,
      "step": 60
    },
    {
      "epoch": 0.047683923705722074,
      "grad_norm": 0.41433843970298767,
      "learning_rate": 9.990133642141359e-05,
      "loss": 0.3026,
      "step": 70
    },
    {
      "epoch": 0.05449591280653951,
      "grad_norm": 0.2683587074279785,
      "learning_rate": 9.977024992520602e-05,
      "loss": 0.2798,
      "step": 80
    },
    {
      "epoch": 0.06130790190735695,
      "grad_norm": 0.2740797996520996,
      "learning_rate": 9.95847403914247e-05,
      "loss": 0.2553,
      "step": 90
    },
    {
      "epoch": 0.0681198910081744,
      "grad_norm": 0.2203698456287384,
      "learning_rate": 9.934501067202117e-05,
      "loss": 0.2386,
      "step": 100
    },
    {
      "epoch": 0.07493188010899182,
      "grad_norm": 0.2193981111049652,
      "learning_rate": 9.905132290792394e-05,
      "loss": 0.229,
      "step": 110
    },
    {
      "epoch": 0.08174386920980926,
      "grad_norm": 0.42132753133773804,
      "learning_rate": 9.870399824239117e-05,
      "loss": 0.2323,
      "step": 120
    },
    {
      "epoch": 0.0885558583106267,
      "grad_norm": 0.5328313708305359,
      "learning_rate": 9.830341646984521e-05,
      "loss": 0.2085,
      "step": 130
    },
    {
      "epoch": 0.09536784741144415,
      "grad_norm": 0.27494603395462036,
      "learning_rate": 9.785001562057309e-05,
      "loss": 0.2207,
      "step": 140
    },
    {
      "epoch": 0.10217983651226158,
      "grad_norm": 0.21599100530147552,
      "learning_rate": 9.734429148174675e-05,
      "loss": 0.2097,
      "step": 150
    },
    {
      "epoch": 0.10899182561307902,
      "grad_norm": 0.3312373161315918,
      "learning_rate": 9.6786797055287e-05,
      "loss": 0.1968,
      "step": 160
    },
    {
      "epoch": 0.11580381471389646,
      "grad_norm": 0.3358154892921448,
      "learning_rate": 9.617814195316411e-05,
      "loss": 0.1921,
      "step": 170
    },
    {
      "epoch": 0.1226158038147139,
      "grad_norm": 0.23734018206596375,
      "learning_rate": 9.551899173079607e-05,
      "loss": 0.1897,
      "step": 180
    },
    {
      "epoch": 0.12942779291553133,
      "grad_norm": 0.224577397108078,
      "learning_rate": 9.481006715927351e-05,
      "loss": 0.1815,
      "step": 190
    },
    {
      "epoch": 0.1362397820163488,
      "grad_norm": 0.34203988313674927,
      "learning_rate": 9.405214343720707e-05,
      "loss": 0.1733,
      "step": 200
    },
    {
      "epoch": 0.14305177111716622,
      "grad_norm": 0.2753185033798218,
      "learning_rate": 9.32460493430591e-05,
      "loss": 0.1869,
      "step": 210
    },
    {
      "epoch": 0.14986376021798364,
      "grad_norm": 0.22734495997428894,
      "learning_rate": 9.239266632888659e-05,
      "loss": 0.1625,
      "step": 220
    },
    {
      "epoch": 0.1566757493188011,
      "grad_norm": 0.2831128239631653,
      "learning_rate": 9.14929275564863e-05,
      "loss": 0.1716,
      "step": 230
    },
    {
      "epoch": 0.16348773841961853,
      "grad_norm": 0.32288429141044617,
      "learning_rate": 9.0547816876996e-05,
      "loss": 0.1631,
      "step": 240
    },
    {
      "epoch": 0.17029972752043596,
      "grad_norm": 0.3539080023765564,
      "learning_rate": 8.955836775506776e-05,
      "loss": 0.1631,
      "step": 250
    },
    {
      "epoch": 0.1771117166212534,
      "grad_norm": 0.4158879220485687,
      "learning_rate": 8.852566213878947e-05,
      "loss": 0.1564,
      "step": 260
    },
    {
      "epoch": 0.18392370572207084,
      "grad_norm": 0.27678024768829346,
      "learning_rate": 8.745082927659047e-05,
      "loss": 0.1602,
      "step": 270
    },
    {
      "epoch": 0.1907356948228883,
      "grad_norm": 0.49956148862838745,
      "learning_rate": 8.633504448242505e-05,
      "loss": 0.1563,
      "step": 280
    },
    {
      "epoch": 0.19754768392370572,
      "grad_norm": 0.41748130321502686,
      "learning_rate": 8.517952785058385e-05,
      "loss": 0.1571,
      "step": 290
    },
    {
      "epoch": 0.20435967302452315,
      "grad_norm": 0.43028420209884644,
      "learning_rate": 8.398554292153866e-05,
      "loss": 0.1565,
      "step": 300
    },
    {
      "epoch": 0.2111716621253406,
      "grad_norm": 0.4846581220626831,
      "learning_rate": 8.275439530027948e-05,
      "loss": 0.1496,
      "step": 310
    },
    {
      "epoch": 0.21798365122615804,
      "grad_norm": 0.24525447189807892,
      "learning_rate": 8.148743122865463e-05,
      "loss": 0.1454,
      "step": 320
    },
    {
      "epoch": 0.22479564032697547,
      "grad_norm": 0.3764805793762207,
      "learning_rate": 8.018603611327504e-05,
      "loss": 0.1427,
      "step": 330
    },
    {
      "epoch": 0.23160762942779292,
      "grad_norm": 0.3890218138694763,
      "learning_rate": 7.88516330105925e-05,
      "loss": 0.1364,
      "step": 340
    },
    {
      "epoch": 0.23841961852861035,
      "grad_norm": 0.39584898948669434,
      "learning_rate": 7.748568107080832e-05,
      "loss": 0.138,
      "step": 350
    },
    {
      "epoch": 0.2452316076294278,
      "grad_norm": 0.3259540796279907,
      "learning_rate": 7.608967394231387e-05,
      "loss": 0.1381,
      "step": 360
    },
    {
      "epoch": 0.25204359673024523,
      "grad_norm": 0.6704043745994568,
      "learning_rate": 7.466513813840825e-05,
      "loss": 0.1363,
      "step": 370
    },
    {
      "epoch": 0.25885558583106266,
      "grad_norm": 0.3741641342639923,
      "learning_rate": 7.32136313680782e-05,
      "loss": 0.131,
      "step": 380
    },
    {
      "epoch": 0.2656675749318801,
      "grad_norm": 0.3064197599887848,
      "learning_rate": 7.173674083266624e-05,
      "loss": 0.1339,
      "step": 390
    },
    {
      "epoch": 0.2724795640326976,
      "grad_norm": 0.4971103072166443,
      "learning_rate": 7.023608149028937e-05,
      "loss": 0.128,
      "step": 400
    },
    {
      "epoch": 0.279291553133515,
      "grad_norm": 0.38094639778137207,
      "learning_rate": 6.871329428990602e-05,
      "loss": 0.1329,
      "step": 410
    },
    {
      "epoch": 0.28610354223433243,
      "grad_norm": 0.3880401849746704,
      "learning_rate": 6.71700443769625e-05,
      "loss": 0.1326,
      "step": 420
    },
    {
      "epoch": 0.29291553133514986,
      "grad_norm": 0.4513886272907257,
      "learning_rate": 6.56080192725808e-05,
      "loss": 0.133,
      "step": 430
    },
    {
      "epoch": 0.2997275204359673,
      "grad_norm": 0.331877738237381,
      "learning_rate": 6.402892702827916e-05,
      "loss": 0.1213,
      "step": 440
    },
    {
      "epoch": 0.3065395095367847,
      "grad_norm": 0.43866991996765137,
      "learning_rate": 6.243449435824276e-05,
      "loss": 0.129,
      "step": 450
    },
    {
      "epoch": 0.3133514986376022,
      "grad_norm": 0.5115529894828796,
      "learning_rate": 6.0826464751186994e-05,
      "loss": 0.1323,
      "step": 460
    },
    {
      "epoch": 0.3201634877384196,
      "grad_norm": 0.42644116282463074,
      "learning_rate": 5.9206596563878357e-05,
      "loss": 0.1259,
      "step": 470
    },
    {
      "epoch": 0.32697547683923706,
      "grad_norm": 0.35875576734542847,
      "learning_rate": 5.757666109839702e-05,
      "loss": 0.1273,
      "step": 480
    },
    {
      "epoch": 0.3337874659400545,
      "grad_norm": 0.3547762930393219,
      "learning_rate": 5.5938440665244006e-05,
      "loss": 0.1255,
      "step": 490
    },
    {
      "epoch": 0.3405994550408719,
      "grad_norm": 0.7186785936355591,
      "learning_rate": 5.4293726634410855e-05,
      "loss": 0.1236,
      "step": 500
    },
    {
      "epoch": 0.3474114441416894,
      "grad_norm": 0.3978801965713501,
      "learning_rate": 5.264431747654284e-05,
      "loss": 0.1252,
      "step": 510
    },
    {
      "epoch": 0.3542234332425068,
      "grad_norm": 0.4443363845348358,
      "learning_rate": 5.0992016796337686e-05,
      "loss": 0.1224,
      "step": 520
    },
    {
      "epoch": 0.36103542234332425,
      "grad_norm": 0.4192752242088318,
      "learning_rate": 4.93386313603304e-05,
      "loss": 0.1185,
      "step": 530
    },
    {
      "epoch": 0.3678474114441417,
      "grad_norm": 0.41421979665756226,
      "learning_rate": 4.7685969121220456e-05,
      "loss": 0.1234,
      "step": 540
    },
    {
      "epoch": 0.3746594005449591,
      "grad_norm": 0.6001840829849243,
      "learning_rate": 4.60358372409022e-05,
      "loss": 0.1125,
      "step": 550
    },
    {
      "epoch": 0.3814713896457766,
      "grad_norm": 0.47750324010849,
      "learning_rate": 4.439004011435979e-05,
      "loss": 0.1216,
      "step": 560
    },
    {
      "epoch": 0.388283378746594,
      "grad_norm": 0.39754268527030945,
      "learning_rate": 4.275037739658771e-05,
      "loss": 0.1162,
      "step": 570
    },
    {
      "epoch": 0.39509536784741145,
      "grad_norm": 0.3878563344478607,
      "learning_rate": 4.111864203469457e-05,
      "loss": 0.1189,
      "step": 580
    },
    {
      "epoch": 0.4019073569482289,
      "grad_norm": 0.4804205894470215,
      "learning_rate": 3.949661830734172e-05,
      "loss": 0.119,
      "step": 590
    },
    {
      "epoch": 0.4087193460490463,
      "grad_norm": 0.34473225474357605,
      "learning_rate": 3.788607987366069e-05,
      "loss": 0.1176,
      "step": 600
    },
    {
      "epoch": 0.41553133514986373,
      "grad_norm": 0.3620869219303131,
      "learning_rate": 3.628878783378302e-05,
      "loss": 0.1201,
      "step": 610
    },
    {
      "epoch": 0.4223433242506812,
      "grad_norm": 0.35693806409835815,
      "learning_rate": 3.470648880310313e-05,
      "loss": 0.1123,
      "step": 620
    },
    {
      "epoch": 0.42915531335149865,
      "grad_norm": 0.31234225630760193,
      "learning_rate": 3.3140913002379995e-05,
      "loss": 0.1121,
      "step": 630
    },
    {
      "epoch": 0.4359673024523161,
      "grad_norm": 0.46420344710350037,
      "learning_rate": 3.1593772365766105e-05,
      "loss": 0.1143,
      "step": 640
    },
    {
      "epoch": 0.4427792915531335,
      "grad_norm": 0.3229459226131439,
      "learning_rate": 3.006675866883275e-05,
      "loss": 0.1194,
      "step": 650
    },
    {
      "epoch": 0.44959128065395093,
      "grad_norm": 0.42538201808929443,
      "learning_rate": 2.8561541678638142e-05,
      "loss": 0.1243,
      "step": 660
    },
    {
      "epoch": 0.4564032697547684,
      "grad_norm": 0.43292859196662903,
      "learning_rate": 2.707976732786166e-05,
      "loss": 0.1232,
      "step": 670
    },
    {
      "epoch": 0.46321525885558584,
      "grad_norm": 0.28717246651649475,
      "learning_rate": 2.562305591500069e-05,
      "loss": 0.1207,
      "step": 680
    },
    {
      "epoch": 0.47002724795640327,
      "grad_norm": 0.4433380365371704,
      "learning_rate": 2.419300033259798e-05,
      "loss": 0.1169,
      "step": 690
    },
    {
      "epoch": 0.4768392370572207,
      "grad_norm": 0.39058682322502136,
      "learning_rate": 2.279116432543705e-05,
      "loss": 0.116,
      "step": 700
    },
    {
      "epoch": 0.48365122615803813,
      "grad_norm": 0.4982820749282837,
      "learning_rate": 2.1419080780610123e-05,
      "loss": 0.1248,
      "step": 710
    },
    {
      "epoch": 0.4904632152588556,
      "grad_norm": 0.3196106553077698,
      "learning_rate": 2.0078250051328784e-05,
      "loss": 0.118,
      "step": 720
    },
    {
      "epoch": 0.49727520435967304,
      "grad_norm": 0.349829763174057,
      "learning_rate": 1.877013831630961e-05,
      "loss": 0.1135,
      "step": 730
    },
    {
      "epoch": 0.5040871934604905,
      "grad_norm": 0.3523980975151062,
      "learning_rate": 1.749617597652934e-05,
      "loss": 0.104,
      "step": 740
    },
    {
      "epoch": 0.510899182561308,
      "grad_norm": 0.3857523202896118,
      "learning_rate": 1.62577560911024e-05,
      "loss": 0.1238,
      "step": 750
    },
    {
      "epoch": 0.5177111716621253,
      "grad_norm": 0.38921502232551575,
      "learning_rate": 1.5056232853991209e-05,
      "loss": 0.1058,
      "step": 760
    },
    {
      "epoch": 0.5245231607629428,
      "grad_norm": 0.39803993701934814,
      "learning_rate": 1.389292011321498e-05,
      "loss": 0.1199,
      "step": 770
    },
    {
      "epoch": 0.5313351498637602,
      "grad_norm": 0.4115196764469147,
      "learning_rate": 1.2769089934176126e-05,
      "loss": 0.1143,
      "step": 780
    },
    {
      "epoch": 0.5381471389645777,
      "grad_norm": 0.4663422703742981,
      "learning_rate": 1.1685971208675539e-05,
      "loss": 0.1125,
      "step": 790
    },
    {
      "epoch": 0.5449591280653951,
      "grad_norm": 0.401262104511261,
      "learning_rate": 1.0644748311137376e-05,
      "loss": 0.1063,
      "step": 800
    },
    {
      "epoch": 0.5517711171662125,
      "grad_norm": 0.3948645293712616,
      "learning_rate": 9.646559803512994e-06,
      "loss": 0.1218,
      "step": 810
    },
    {
      "epoch": 0.55858310626703,
      "grad_norm": 0.524081826210022,
      "learning_rate": 8.692497190280224e-06,
      "loss": 0.1053,
      "step": 820
    },
    {
      "epoch": 0.5653950953678474,
      "grad_norm": 0.3104141652584076,
      "learning_rate": 7.783603724899257e-06,
      "loss": 0.1051,
      "step": 830
    },
    {
      "epoch": 0.5722070844686649,
      "grad_norm": 0.6254291534423828,
      "learning_rate": 6.92087326903022e-06,
      "loss": 0.1054,
      "step": 840
    },
    {
      "epoch": 0.5790190735694822,
      "grad_norm": 0.33461639285087585,
      "learning_rate": 6.1052492057601275e-06,
      "loss": 0.1179,
      "step": 850
    },
    {
      "epoch": 0.5858310626702997,
      "grad_norm": 0.34688347578048706,
      "learning_rate": 5.337623408027293e-06,
      "loss": 0.1145,
      "step": 860
    },
    {
      "epoch": 0.5926430517711172,
      "grad_norm": 0.34610840678215027,
      "learning_rate": 4.618835263371396e-06,
      "loss": 0.109,
      "step": 870
    },
    {
      "epoch": 0.5994550408719346,
      "grad_norm": 0.4084641635417938,
      "learning_rate": 3.949670756075447e-06,
      "loss": 0.1015,
      "step": 880
    },
    {
      "epoch": 0.6062670299727521,
      "grad_norm": 0.47374227643013,
      "learning_rate": 3.3308616077036115e-06,
      "loss": 0.1095,
      "step": 890
    },
    {
      "epoch": 0.6130790190735694,
      "grad_norm": 0.3465811014175415,
      "learning_rate": 2.7630844769743757e-06,
      "loss": 0.1196,
      "step": 900
    },
    {
      "epoch": 0.6198910081743869,
      "grad_norm": 0.3198418617248535,
      "learning_rate": 2.2469602198441573e-06,
      "loss": 0.1079,
      "step": 910
    },
    {
      "epoch": 0.6267029972752044,
      "grad_norm": 0.6482970118522644,
      "learning_rate": 1.7830532106104747e-06,
      "loss": 0.1223,
      "step": 920
    },
    {
      "epoch": 0.6335149863760218,
      "grad_norm": 0.5484973192214966,
      "learning_rate": 1.3718707247769135e-06,
      "loss": 0.1169,
      "step": 930
    },
    {
      "epoch": 0.6403269754768393,
      "grad_norm": 0.3990526497364044,
      "learning_rate": 1.0138623843548078e-06,
      "loss": 0.1028,
      "step": 940
    },
    {
      "epoch": 0.6471389645776566,
      "grad_norm": 0.43871477246284485,
      "learning_rate": 7.094196662081831e-07,
      "loss": 0.1164,
      "step": 950
    },
    {
      "epoch": 0.6539509536784741,
      "grad_norm": 0.4919513761997223,
      "learning_rate": 4.5887547397955864e-07,
      "loss": 0.1082,
      "step": 960
    },
    {
      "epoch": 0.6607629427792916,
      "grad_norm": 0.43623319268226624,
      "learning_rate": 2.625037740646763e-07,
      "loss": 0.1085,
      "step": 970
    },
    {
      "epoch": 0.667574931880109,
      "grad_norm": 0.437269926071167,
      "learning_rate": 1.2051929603428825e-07,
      "loss": 0.113,
      "step": 980
    },
    {
      "epoch": 0.6743869209809265,
      "grad_norm": 0.4403259754180908,
      "learning_rate": 3.3077297830541584e-08,
      "loss": 0.1139,
      "step": 990
    },
    {
      "epoch": 0.6811989100817438,
      "grad_norm": 0.4222445785999298,
      "learning_rate": 2.7339599464326627e-10,
      "loss": 0.1078,
      "step": 1000
    },
    {
      "epoch": 0.6811989100817438,
      "step": 1000,
      "total_flos": 0.0,
      "train_loss": 0.16795521533489227,
      "train_runtime": 804.1147,
      "train_samples_per_second": 39.795,
      "train_steps_per_second": 1.244
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}