{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 454,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022026431718061676,
      "grad_norm": 1.0935207970465015,
      "learning_rate": 4.347826086956522e-06,
      "loss": 1.3623,
      "step": 1
    },
    {
      "epoch": 0.011013215859030838,
      "grad_norm": 1.0619934894299083,
      "learning_rate": 2.173913043478261e-05,
      "loss": 1.3747,
      "step": 5
    },
    {
      "epoch": 0.022026431718061675,
      "grad_norm": 0.25351576673529874,
      "learning_rate": 4.347826086956522e-05,
      "loss": 1.3541,
      "step": 10
    },
    {
      "epoch": 0.03303964757709251,
      "grad_norm": 0.2278849128178173,
      "learning_rate": 6.521739130434783e-05,
      "loss": 1.3162,
      "step": 15
    },
    {
      "epoch": 0.04405286343612335,
      "grad_norm": 0.1855238377034502,
      "learning_rate": 8.695652173913044e-05,
      "loss": 1.259,
      "step": 20
    },
    {
      "epoch": 0.05506607929515418,
      "grad_norm": 0.1452973877554258,
      "learning_rate": 0.00010869565217391305,
      "loss": 1.2263,
      "step": 25
    },
    {
      "epoch": 0.06607929515418502,
      "grad_norm": 0.10223461213864794,
      "learning_rate": 0.00013043478260869567,
      "loss": 1.2169,
      "step": 30
    },
    {
      "epoch": 0.07709251101321586,
      "grad_norm": 0.09738462561658244,
      "learning_rate": 0.00015217391304347827,
      "loss": 1.2041,
      "step": 35
    },
    {
      "epoch": 0.0881057268722467,
      "grad_norm": 0.09054576261597842,
      "learning_rate": 0.00017391304347826088,
      "loss": 1.1826,
      "step": 40
    },
    {
      "epoch": 0.09911894273127753,
      "grad_norm": 0.08674850660946061,
      "learning_rate": 0.0001956521739130435,
      "loss": 1.1734,
      "step": 45
    },
    {
      "epoch": 0.11013215859030837,
      "grad_norm": 0.09808296793590265,
      "learning_rate": 0.0001999525719713366,
      "loss": 1.1869,
      "step": 50
    },
    {
      "epoch": 0.1211453744493392,
      "grad_norm": 0.10256381268719783,
      "learning_rate": 0.0001997599727063717,
      "loss": 1.137,
      "step": 55
    },
    {
      "epoch": 0.13215859030837004,
      "grad_norm": 0.09401999180532912,
      "learning_rate": 0.00019941952317728147,
      "loss": 1.1505,
      "step": 60
    },
    {
      "epoch": 0.14317180616740088,
      "grad_norm": 0.07941243235115872,
      "learning_rate": 0.00019893172795069144,
      "loss": 1.1563,
      "step": 65
    },
    {
      "epoch": 0.15418502202643172,
      "grad_norm": 0.09518349218263038,
      "learning_rate": 0.0001982973099683902,
      "loss": 1.1397,
      "step": 70
    },
    {
      "epoch": 0.16519823788546256,
      "grad_norm": 0.07317938488194159,
      "learning_rate": 0.00019751720947588602,
      "loss": 1.1214,
      "step": 75
    },
    {
      "epoch": 0.1762114537444934,
      "grad_norm": 0.07067546841879777,
      "learning_rate": 0.00019659258262890683,
      "loss": 1.1514,
      "step": 80
    },
    {
      "epoch": 0.18722466960352424,
      "grad_norm": 0.08477547989478108,
      "learning_rate": 0.000195524799779908,
      "loss": 1.1413,
      "step": 85
    },
    {
      "epoch": 0.19823788546255505,
      "grad_norm": 0.08043454343502093,
      "learning_rate": 0.00019431544344712776,
      "loss": 1.1204,
      "step": 90
    },
    {
      "epoch": 0.2092511013215859,
      "grad_norm": 0.07585966181487593,
      "learning_rate": 0.00019296630596920023,
      "loss": 1.1363,
      "step": 95
    },
    {
      "epoch": 0.22026431718061673,
      "grad_norm": 0.06977946901923308,
      "learning_rate": 0.0001914793868488021,
      "loss": 1.1388,
      "step": 100
    },
    {
      "epoch": 0.23127753303964757,
      "grad_norm": 0.09828209309581792,
      "learning_rate": 0.0001898568897892697,
      "loss": 1.1323,
      "step": 105
    },
    {
      "epoch": 0.2422907488986784,
      "grad_norm": 0.08128484219994006,
      "learning_rate": 0.00018810121942857845,
      "loss": 1.1282,
      "step": 110
    },
    {
      "epoch": 0.2533039647577093,
      "grad_norm": 0.0705528387018198,
      "learning_rate": 0.00018621497777552507,
      "loss": 1.1478,
      "step": 115
    },
    {
      "epoch": 0.2643171806167401,
      "grad_norm": 0.07222951437049585,
      "learning_rate": 0.00018420096035339452,
      "loss": 1.1281,
      "step": 120
    },
    {
      "epoch": 0.2753303964757709,
      "grad_norm": 0.07745334706329449,
      "learning_rate": 0.00018206215205682683,
      "loss": 1.1305,
      "step": 125
    },
    {
      "epoch": 0.28634361233480177,
      "grad_norm": 0.07138923529008301,
      "learning_rate": 0.000179801722728024,
      "loss": 1.1248,
      "step": 130
    },
    {
      "epoch": 0.2973568281938326,
      "grad_norm": 0.07479603203788834,
      "learning_rate": 0.00017742302245885383,
      "loss": 1.1273,
      "step": 135
    },
    {
      "epoch": 0.30837004405286345,
      "grad_norm": 0.07733525226694472,
      "learning_rate": 0.00017492957662581295,
      "loss": 1.1109,
      "step": 140
    },
    {
      "epoch": 0.31938325991189426,
      "grad_norm": 0.07371826786635874,
      "learning_rate": 0.00017232508066520702,
      "loss": 1.1358,
      "step": 145
    },
    {
      "epoch": 0.3303964757709251,
      "grad_norm": 0.07313288578427013,
      "learning_rate": 0.0001696133945962927,
      "loss": 1.1366,
      "step": 150
    },
    {
      "epoch": 0.34140969162995594,
      "grad_norm": 0.07112918824502681,
      "learning_rate": 0.00016679853730049743,
      "loss": 1.1278,
      "step": 155
    },
    {
      "epoch": 0.3524229074889868,
      "grad_norm": 0.07765780862323055,
      "learning_rate": 0.00016388468056519612,
      "loss": 1.114,
      "step": 160
    },
    {
      "epoch": 0.3634361233480176,
      "grad_norm": 0.08642134716689472,
      "learning_rate": 0.00016087614290087208,
      "loss": 1.1254,
      "step": 165
    },
    {
      "epoch": 0.3744493392070485,
      "grad_norm": 0.08329985092613008,
      "learning_rate": 0.00015777738314082514,
      "loss": 1.1424,
      "step": 170
    },
    {
      "epoch": 0.3854625550660793,
      "grad_norm": 0.08324403766808654,
      "learning_rate": 0.00015459299383291345,
      "loss": 1.126,
      "step": 175
    },
    {
      "epoch": 0.3964757709251101,
      "grad_norm": 0.0824304632426703,
      "learning_rate": 0.00015132769443312207,
      "loss": 1.109,
      "step": 180
    },
    {
      "epoch": 0.40748898678414097,
      "grad_norm": 0.07117156561482839,
      "learning_rate": 0.00014798632431104592,
      "loss": 1.1036,
      "step": 185
    },
    {
      "epoch": 0.4185022026431718,
      "grad_norm": 0.07457290539374888,
      "learning_rate": 0.00014457383557765386,
      "loss": 1.1315,
      "step": 190
    },
    {
      "epoch": 0.42951541850220265,
      "grad_norm": 0.07127883301068033,
      "learning_rate": 0.00014109528574596301,
      "loss": 1.115,
      "step": 195
    },
    {
      "epoch": 0.44052863436123346,
      "grad_norm": 0.07115222351808868,
      "learning_rate": 0.00013755583023550126,
      "loss": 1.1125,
      "step": 200
    },
    {
      "epoch": 0.45154185022026433,
      "grad_norm": 0.07230426175014865,
      "learning_rate": 0.00013396071473166613,
      "loss": 1.1264,
      "step": 205
    },
    {
      "epoch": 0.46255506607929514,
      "grad_norm": 0.07086336369316362,
      "learning_rate": 0.00013031526741130435,
      "loss": 1.1395,
      "step": 210
    },
    {
      "epoch": 0.473568281938326,
      "grad_norm": 0.07876282139247363,
      "learning_rate": 0.0001266248910460341,
      "loss": 1.1198,
      "step": 215
    },
    {
      "epoch": 0.4845814977973568,
      "grad_norm": 0.07398923802908818,
      "learning_rate": 0.0001228950549950134,
      "loss": 1.1191,
      "step": 220
    },
    {
      "epoch": 0.4955947136563877,
      "grad_norm": 0.07631700509520113,
      "learning_rate": 0.00011913128709902181,
      "loss": 1.1015,
      "step": 225
    },
    {
      "epoch": 0.5066079295154186,
      "grad_norm": 0.07776652535484273,
      "learning_rate": 0.00011533916548786857,
      "loss": 1.0927,
      "step": 230
    },
    {
      "epoch": 0.5176211453744494,
      "grad_norm": 0.0779293920050639,
      "learning_rate": 0.00011152431031326978,
      "loss": 1.1106,
      "step": 235
    },
    {
      "epoch": 0.5286343612334802,
      "grad_norm": 0.07173097000465865,
      "learning_rate": 0.0001076923754194464,
      "loss": 1.1192,
      "step": 240
    },
    {
      "epoch": 0.539647577092511,
      "grad_norm": 0.06808021677810269,
      "learning_rate": 0.00010384903996378783,
      "loss": 1.1141,
      "step": 245
    },
    {
      "epoch": 0.5506607929515418,
      "grad_norm": 0.07092915110115385,
      "learning_rate": 0.0001,
      "loss": 1.1005,
      "step": 250
    },
    {
      "epoch": 0.5616740088105727,
      "grad_norm": 0.07272607907211924,
      "learning_rate": 9.615096003621221e-05,
      "loss": 1.1199,
      "step": 255
    },
    {
      "epoch": 0.5726872246696035,
      "grad_norm": 0.07107512047821021,
      "learning_rate": 9.230762458055363e-05,
      "loss": 1.1026,
      "step": 260
    },
    {
      "epoch": 0.5837004405286343,
      "grad_norm": 0.07442425494453343,
      "learning_rate": 8.847568968673026e-05,
      "loss": 1.1419,
      "step": 265
    },
    {
      "epoch": 0.5947136563876652,
      "grad_norm": 0.07080798721909222,
      "learning_rate": 8.466083451213144e-05,
      "loss": 1.0954,
      "step": 270
    },
    {
      "epoch": 0.6057268722466961,
      "grad_norm": 0.07188012114083321,
      "learning_rate": 8.086871290097821e-05,
      "loss": 1.1214,
      "step": 275
    },
    {
      "epoch": 0.6167400881057269,
      "grad_norm": 0.07245225851302386,
      "learning_rate": 7.710494500498662e-05,
      "loss": 1.095,
      "step": 280
    },
    {
      "epoch": 0.6277533039647577,
      "grad_norm": 0.07006313027766538,
      "learning_rate": 7.337510895396591e-05,
      "loss": 1.0988,
      "step": 285
    },
    {
      "epoch": 0.6387665198237885,
      "grad_norm": 0.07232286737424776,
      "learning_rate": 6.968473258869566e-05,
      "loss": 1.118,
      "step": 290
    },
    {
      "epoch": 0.6497797356828194,
      "grad_norm": 0.07049128615067844,
      "learning_rate": 6.603928526833387e-05,
      "loss": 1.1004,
      "step": 295
    },
    {
      "epoch": 0.6607929515418502,
      "grad_norm": 0.0746599685264263,
      "learning_rate": 6.244416976449875e-05,
      "loss": 1.1059,
      "step": 300
    },
    {
      "epoch": 0.6718061674008811,
      "grad_norm": 0.07192896430027275,
      "learning_rate": 5.890471425403703e-05,
      "loss": 1.1028,
      "step": 305
    },
    {
      "epoch": 0.6828193832599119,
      "grad_norm": 0.06921226870329861,
      "learning_rate": 5.542616442234618e-05,
      "loss": 1.1112,
      "step": 310
    },
    {
      "epoch": 0.6938325991189427,
      "grad_norm": 0.07384850031320968,
      "learning_rate": 5.201367568895408e-05,
      "loss": 1.1116,
      "step": 315
    },
    {
      "epoch": 0.7048458149779736,
      "grad_norm": 0.07138390105976088,
      "learning_rate": 4.8672305566877964e-05,
      "loss": 1.1309,
      "step": 320
    },
    {
      "epoch": 0.7158590308370044,
      "grad_norm": 0.06880496070020393,
      "learning_rate": 4.540700616708658e-05,
      "loss": 1.1076,
      "step": 325
    },
    {
      "epoch": 0.7268722466960352,
      "grad_norm": 0.06923475218927538,
      "learning_rate": 4.222261685917489e-05,
      "loss": 1.108,
      "step": 330
    },
    {
      "epoch": 0.737885462555066,
      "grad_norm": 0.07248582746669294,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 1.1317,
      "step": 335
    },
    {
      "epoch": 0.748898678414097,
      "grad_norm": 0.07283051607038368,
      "learning_rate": 3.6115319434803894e-05,
      "loss": 1.1133,
      "step": 340
    },
    {
      "epoch": 0.7599118942731278,
      "grad_norm": 0.06818813267960931,
      "learning_rate": 3.32014626995026e-05,
      "loss": 1.112,
      "step": 345
    },
    {
      "epoch": 0.7709251101321586,
      "grad_norm": 0.08412840165527498,
      "learning_rate": 3.0386605403707346e-05,
      "loss": 1.1116,
      "step": 350
    },
    {
      "epoch": 0.7819383259911894,
      "grad_norm": 0.07095418638014062,
      "learning_rate": 2.7674919334793035e-05,
      "loss": 1.104,
      "step": 355
    },
    {
      "epoch": 0.7929515418502202,
      "grad_norm": 0.07547366887662493,
      "learning_rate": 2.507042337418707e-05,
      "loss": 1.0963,
      "step": 360
    },
    {
      "epoch": 0.8039647577092511,
      "grad_norm": 0.06961831699039754,
      "learning_rate": 2.2576977541146193e-05,
      "loss": 1.1181,
      "step": 365
    },
    {
      "epoch": 0.8149779735682819,
      "grad_norm": 0.06804271947624164,
      "learning_rate": 2.0198277271976052e-05,
      "loss": 1.0993,
      "step": 370
    },
    {
      "epoch": 0.8259911894273128,
      "grad_norm": 0.07293836582897208,
      "learning_rate": 1.793784794317319e-05,
      "loss": 1.1165,
      "step": 375
    },
    {
      "epoch": 0.8370044052863436,
      "grad_norm": 0.06982718554857356,
      "learning_rate": 1.5799039646605486e-05,
      "loss": 1.1063,
      "step": 380
    },
    {
      "epoch": 0.8480176211453745,
      "grad_norm": 0.06858309519021612,
      "learning_rate": 1.3785022224474942e-05,
      "loss": 1.0918,
      "step": 385
    },
    {
      "epoch": 0.8590308370044053,
      "grad_norm": 0.0682809739031729,
      "learning_rate": 1.1898780571421552e-05,
      "loss": 1.0911,
      "step": 390
    },
    {
      "epoch": 0.8700440528634361,
      "grad_norm": 0.07165844802397829,
      "learning_rate": 1.0143110210730312e-05,
      "loss": 1.1113,
      "step": 395
    },
    {
      "epoch": 0.8810572687224669,
      "grad_norm": 0.0692445707168849,
      "learning_rate": 8.520613151197898e-06,
      "loss": 1.1252,
      "step": 400
    },
    {
      "epoch": 0.8920704845814978,
      "grad_norm": 0.06866962638477613,
      "learning_rate": 7.033694030799787e-06,
      "loss": 1.0891,
      "step": 405
    },
    {
      "epoch": 0.9030837004405287,
      "grad_norm": 0.07273616328237217,
      "learning_rate": 5.684556552872256e-06,
      "loss": 1.116,
      "step": 410
    },
    {
      "epoch": 0.9140969162995595,
      "grad_norm": 0.06934023088458012,
      "learning_rate": 4.475200220092002e-06,
      "loss": 1.0892,
      "step": 415
    },
    {
      "epoch": 0.9251101321585903,
      "grad_norm": 0.0701825275643681,
      "learning_rate": 3.40741737109318e-06,
      "loss": 1.0988,
      "step": 420
    },
    {
      "epoch": 0.9361233480176211,
      "grad_norm": 0.06927772495486725,
      "learning_rate": 2.482790524113998e-06,
      "loss": 1.1088,
      "step": 425
    },
    {
      "epoch": 0.947136563876652,
      "grad_norm": 0.0685769456667081,
      "learning_rate": 1.7026900316098215e-06,
      "loss": 1.1237,
      "step": 430
    },
    {
      "epoch": 0.9581497797356828,
      "grad_norm": 0.06848296141460276,
      "learning_rate": 1.0682720493085607e-06,
      "loss": 1.0978,
      "step": 435
    },
    {
      "epoch": 0.9691629955947136,
      "grad_norm": 0.06944396554705634,
      "learning_rate": 5.804768227185565e-07,
      "loss": 1.1155,
      "step": 440
    },
    {
      "epoch": 0.9801762114537445,
      "grad_norm": 0.0711777792122946,
      "learning_rate": 2.400272936283088e-07,
      "loss": 1.1072,
      "step": 445
    },
    {
      "epoch": 0.9911894273127754,
      "grad_norm": 0.06801313867689823,
      "learning_rate": 4.74280286634099e-08,
      "loss": 1.0891,
      "step": 450
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.9785001873970032,
      "eval_runtime": 2.2823,
      "eval_samples_per_second": 3.067,
      "eval_steps_per_second": 0.876,
      "step": 454
    },
    {
      "epoch": 1.0,
      "step": 454,
      "total_flos": 1.4408836278386688e+16,
      "train_loss": 1.1317675271223295,
      "train_runtime": 17254.8753,
      "train_samples_per_second": 3.367,
      "train_steps_per_second": 0.026
    }
  ],
  "logging_steps": 5,
  "max_steps": 454,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4408836278386688e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}