{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.003338898163606,
  "eval_steps": 50,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022259321090706732,
      "grad_norm": 0.4673316478729248,
      "learning_rate": 7.3529411764705884e-06,
      "loss": 1.2911,
      "step": 5
    },
    {
      "epoch": 0.044518642181413465,
      "grad_norm": 0.5188754200935364,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.3411,
      "step": 10
    },
    {
      "epoch": 0.0667779632721202,
      "grad_norm": 0.584618866443634,
      "learning_rate": 2.2058823529411766e-05,
      "loss": 1.2434,
      "step": 15
    },
    {
      "epoch": 0.08903728436282693,
      "grad_norm": 0.40156278014183044,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.2591,
      "step": 20
    },
    {
      "epoch": 0.11129660545353366,
      "grad_norm": 0.2917367219924927,
      "learning_rate": 3.6764705882352945e-05,
      "loss": 1.2279,
      "step": 25
    },
    {
      "epoch": 0.1335559265442404,
      "grad_norm": 0.2543434500694275,
      "learning_rate": 4.411764705882353e-05,
      "loss": 1.226,
      "step": 30
    },
    {
      "epoch": 0.15581524763494714,
      "grad_norm": 0.28222939372062683,
      "learning_rate": 5.147058823529411e-05,
      "loss": 1.1873,
      "step": 35
    },
    {
      "epoch": 0.17807456872565386,
      "grad_norm": 0.25760558247566223,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.1476,
      "step": 40
    },
    {
      "epoch": 0.2003338898163606,
      "grad_norm": 0.3042117953300476,
      "learning_rate": 6.61764705882353e-05,
      "loss": 1.1758,
      "step": 45
    },
    {
      "epoch": 0.22259321090706732,
      "grad_norm": 0.31747791171073914,
      "learning_rate": 7.352941176470589e-05,
      "loss": 1.1373,
      "step": 50
    },
    {
      "epoch": 0.22259321090706732,
      "eval_loss": 1.1148781776428223,
      "eval_runtime": 52.0257,
      "eval_samples_per_second": 15.358,
      "eval_steps_per_second": 1.922,
      "step": 50
    },
    {
      "epoch": 0.24485253199777407,
      "grad_norm": 0.2843828797340393,
      "learning_rate": 8.088235294117648e-05,
      "loss": 1.0659,
      "step": 55
    },
    {
      "epoch": 0.2671118530884808,
      "grad_norm": 0.30523741245269775,
      "learning_rate": 8.823529411764706e-05,
      "loss": 1.0535,
      "step": 60
    },
    {
      "epoch": 0.28937117417918756,
      "grad_norm": 0.3263162076473236,
      "learning_rate": 9.558823529411765e-05,
      "loss": 1.0327,
      "step": 65
    },
    {
      "epoch": 0.3116304952698943,
      "grad_norm": 0.34655460715293884,
      "learning_rate": 9.999729465939036e-05,
      "loss": 1.1408,
      "step": 70
    },
    {
      "epoch": 0.333889816360601,
      "grad_norm": 0.32706472277641296,
      "learning_rate": 9.996686293953675e-05,
      "loss": 1.0506,
      "step": 75
    },
    {
      "epoch": 0.3561491374513077,
      "grad_norm": 0.37062904238700867,
      "learning_rate": 9.990263847374976e-05,
      "loss": 1.0611,
      "step": 80
    },
    {
      "epoch": 0.3784084585420145,
      "grad_norm": 0.38553890585899353,
      "learning_rate": 9.98046646972368e-05,
      "loss": 1.0951,
      "step": 85
    },
    {
      "epoch": 0.4006677796327212,
      "grad_norm": 0.31734517216682434,
      "learning_rate": 9.96730078699698e-05,
      "loss": 1.0661,
      "step": 90
    },
    {
      "epoch": 0.42292710072342793,
      "grad_norm": 0.3253045380115509,
      "learning_rate": 9.950775703187354e-05,
      "loss": 1.0389,
      "step": 95
    },
    {
      "epoch": 0.44518642181413465,
      "grad_norm": 0.3521738648414612,
      "learning_rate": 9.930902394260747e-05,
      "loss": 1.1163,
      "step": 100
    },
    {
      "epoch": 0.44518642181413465,
      "eval_loss": 1.0541198253631592,
      "eval_runtime": 50.9676,
      "eval_samples_per_second": 15.677,
      "eval_steps_per_second": 1.962,
      "step": 100
    },
    {
      "epoch": 0.4674457429048414,
      "grad_norm": 0.3556961119174957,
      "learning_rate": 9.907694300598237e-05,
      "loss": 1.0173,
      "step": 105
    },
    {
      "epoch": 0.48970506399554814,
      "grad_norm": 0.355704665184021,
      "learning_rate": 9.881167117906275e-05,
      "loss": 1.0947,
      "step": 110
    },
    {
      "epoch": 0.5119643850862549,
      "grad_norm": 0.389106810092926,
      "learning_rate": 9.851338786601614e-05,
      "loss": 1.018,
      "step": 115
    },
    {
      "epoch": 0.5342237061769616,
      "grad_norm": 0.3406746983528137,
      "learning_rate": 9.818229479678158e-05,
      "loss": 1.0,
      "step": 120
    },
    {
      "epoch": 0.5564830272676683,
      "grad_norm": 0.38247111439704895,
      "learning_rate": 9.781861589063895e-05,
      "loss": 1.0442,
      "step": 125
    },
    {
      "epoch": 0.5787423483583751,
      "grad_norm": 0.3582042157649994,
      "learning_rate": 9.742259710477177e-05,
      "loss": 1.0627,
      "step": 130
    },
    {
      "epoch": 0.6010016694490818,
      "grad_norm": 0.3528626263141632,
      "learning_rate": 9.699450626792548e-05,
      "loss": 1.1155,
      "step": 135
    },
    {
      "epoch": 0.6232609905397886,
      "grad_norm": 0.33342617750167847,
      "learning_rate": 9.653463289927411e-05,
      "loss": 1.0184,
      "step": 140
    },
    {
      "epoch": 0.6455203116304953,
      "grad_norm": 0.32322484254837036,
      "learning_rate": 9.604328801261746e-05,
      "loss": 1.0169,
      "step": 145
    },
    {
      "epoch": 0.667779632721202,
      "grad_norm": 0.33450886607170105,
      "learning_rate": 9.55208039060416e-05,
      "loss": 1.0256,
      "step": 150
    },
    {
      "epoch": 0.667779632721202,
      "eval_loss": 1.0322891473770142,
      "eval_runtime": 50.8847,
      "eval_samples_per_second": 15.702,
      "eval_steps_per_second": 1.965,
      "step": 150
    },
    {
      "epoch": 0.6900389538119087,
      "grad_norm": 0.352691650390625,
      "learning_rate": 9.496753393718453e-05,
      "loss": 1.0888,
      "step": 155
    },
    {
      "epoch": 0.7122982749026154,
      "grad_norm": 0.39313045144081116,
      "learning_rate": 9.438385228425938e-05,
      "loss": 1.0477,
      "step": 160
    },
    {
      "epoch": 0.7345575959933222,
      "grad_norm": 0.3759097158908844,
      "learning_rate": 9.377015369299651e-05,
      "loss": 1.0776,
      "step": 165
    },
    {
      "epoch": 0.756816917084029,
      "grad_norm": 0.3853538930416107,
      "learning_rate": 9.312685320967564e-05,
      "loss": 1.0664,
      "step": 170
    },
    {
      "epoch": 0.7790762381747357,
      "grad_norm": 0.38343074917793274,
      "learning_rate": 9.245438590042887e-05,
      "loss": 1.0407,
      "step": 175
    },
    {
      "epoch": 0.8013355592654424,
      "grad_norm": 0.3434021770954132,
      "learning_rate": 9.175320655700406e-05,
      "loss": 1.0624,
      "step": 180
    },
    {
      "epoch": 0.8235948803561491,
      "grad_norm": 0.3616039752960205,
      "learning_rate": 9.102378938918764e-05,
      "loss": 0.9745,
      "step": 185
    },
    {
      "epoch": 0.8458542014468559,
      "grad_norm": 0.4113802909851074,
      "learning_rate": 9.026662770409522e-05,
      "loss": 1.0284,
      "step": 190
    },
    {
      "epoch": 0.8681135225375626,
      "grad_norm": 0.371598482131958,
      "learning_rate": 8.948223357254636e-05,
      "loss": 1.0205,
      "step": 195
    },
    {
      "epoch": 0.8903728436282693,
      "grad_norm": 0.3975715637207031,
      "learning_rate": 8.86711374827494e-05,
      "loss": 1.057,
      "step": 200
    },
    {
      "epoch": 0.8903728436282693,
      "eval_loss": 1.0230859518051147,
      "eval_runtime": 50.8798,
      "eval_samples_per_second": 15.704,
      "eval_steps_per_second": 1.965,
      "step": 200
    },
    {
      "epoch": 0.9126321647189761,
      "grad_norm": 0.49988657236099243,
      "learning_rate": 8.783388798153074e-05,
      "loss": 1.1316,
      "step": 205
    },
    {
      "epoch": 0.9348914858096828,
      "grad_norm": 0.3169264495372772,
      "learning_rate": 8.697105130335085e-05,
      "loss": 1.0057,
      "step": 210
    },
    {
      "epoch": 0.9571508069003896,
      "grad_norm": 0.3785440921783447,
      "learning_rate": 8.608321098735811e-05,
      "loss": 1.1214,
      "step": 215
    },
    {
      "epoch": 0.9794101279910963,
      "grad_norm": 0.35510075092315674,
      "learning_rate": 8.517096748273951e-05,
      "loss": 0.9736,
      "step": 220
    },
    {
      "epoch": 1.001669449081803,
      "grad_norm": 0.3593966066837311,
      "learning_rate": 8.423493774263493e-05,
      "loss": 1.0571,
      "step": 225
    },
    {
      "epoch": 1.0239287701725097,
      "grad_norm": 0.3669678270816803,
      "learning_rate": 8.327575480688985e-05,
      "loss": 1.0336,
      "step": 230
    },
    {
      "epoch": 1.0461880912632164,
      "grad_norm": 0.3945116400718689,
      "learning_rate": 8.229406737392843e-05,
      "loss": 1.0242,
      "step": 235
    },
    {
      "epoch": 1.0684474123539232,
      "grad_norm": 0.4227205514907837,
      "learning_rate": 8.129053936203687e-05,
      "loss": 0.9969,
      "step": 240
    },
    {
      "epoch": 1.0907067334446299,
      "grad_norm": 0.39083144068717957,
      "learning_rate": 8.026584946035331e-05,
      "loss": 0.9173,
      "step": 245
    },
    {
      "epoch": 1.1129660545353366,
      "grad_norm": 0.41568800806999207,
      "learning_rate": 7.92206906698682e-05,
      "loss": 0.9623,
      "step": 250
    },
    {
      "epoch": 1.1129660545353366,
      "eval_loss": 1.0195302963256836,
      "eval_runtime": 50.891,
      "eval_samples_per_second": 15.7,
      "eval_steps_per_second": 1.965,
      "step": 250
    },
    {
      "epoch": 1.1352253756260433,
      "grad_norm": 0.449934720993042,
      "learning_rate": 7.815576983474562e-05,
      "loss": 1.0695,
      "step": 255
    },
    {
      "epoch": 1.1574846967167502,
      "grad_norm": 0.44527217745780945,
      "learning_rate": 7.707180716428237e-05,
      "loss": 1.0041,
      "step": 260
    },
    {
      "epoch": 1.179744017807457,
      "grad_norm": 0.42600926756858826,
      "learning_rate": 7.596953574582814e-05,
      "loss": 0.9999,
      "step": 265
    },
    {
      "epoch": 1.2020033388981637,
      "grad_norm": 0.49353349208831787,
      "learning_rate": 7.484970104899624e-05,
      "loss": 0.9788,
      "step": 270
    },
    {
      "epoch": 1.2242626599888704,
      "grad_norm": 0.5350990295410156,
      "learning_rate": 7.371306042150012e-05,
      "loss": 0.9951,
      "step": 275
    },
    {
      "epoch": 1.2465219810795771,
      "grad_norm": 0.49454548954963684,
      "learning_rate": 7.256038257695687e-05,
      "loss": 0.9426,
      "step": 280
    },
    {
      "epoch": 1.2687813021702838,
      "grad_norm": 0.49435731768608093,
      "learning_rate": 7.139244707500363e-05,
      "loss": 0.98,
      "step": 285
    },
    {
      "epoch": 1.2910406232609906,
      "grad_norm": 0.4851316809654236,
      "learning_rate": 7.021004379407909e-05,
      "loss": 0.9591,
      "step": 290
    },
    {
      "epoch": 1.3132999443516973,
      "grad_norm": 0.5039463639259338,
      "learning_rate": 6.901397239722616e-05,
      "loss": 0.9815,
      "step": 295
    },
    {
      "epoch": 1.335559265442404,
      "grad_norm": 0.5476050972938538,
      "learning_rate": 6.780504179127734e-05,
      "loss": 0.9334,
      "step": 300
    },
    {
      "epoch": 1.335559265442404,
      "eval_loss": 1.0174856185913086,
      "eval_runtime": 50.9073,
      "eval_samples_per_second": 15.695,
      "eval_steps_per_second": 1.964,
      "step": 300
    },
    {
      "epoch": 1.3578185865331107,
      "grad_norm": 0.5071010589599609,
      "learning_rate": 6.658406957978862e-05,
      "loss": 0.9943,
      "step": 305
    },
    {
      "epoch": 1.3800779076238174,
      "grad_norm": 0.5222419500350952,
      "learning_rate": 6.535188151009143e-05,
      "loss": 0.9503,
      "step": 310
    },
    {
      "epoch": 1.4023372287145242,
      "grad_norm": 0.5639395713806152,
      "learning_rate": 6.41093109148373e-05,
      "loss": 1.019,
      "step": 315
    },
    {
      "epoch": 1.4245965498052309,
      "grad_norm": 0.5787636637687683,
      "learning_rate": 6.28571981484123e-05,
      "loss": 0.8958,
      "step": 320
    },
    {
      "epoch": 1.4468558708959378,
      "grad_norm": 0.5925642848014832,
      "learning_rate": 6.159639001860277e-05,
      "loss": 0.9914,
      "step": 325
    },
    {
      "epoch": 1.4691151919866443,
      "grad_norm": 0.57623690366745,
      "learning_rate": 6.032773921389655e-05,
      "loss": 0.9708,
      "step": 330
    },
    {
      "epoch": 1.4913745130773512,
      "grad_norm": 0.5331757664680481,
      "learning_rate": 5.905210372680704e-05,
      "loss": 1.0122,
      "step": 335
    },
    {
      "epoch": 1.5136338341680577,
      "grad_norm": 0.5566096901893616,
      "learning_rate": 5.7770346273610254e-05,
      "loss": 1.012,
      "step": 340
    },
    {
      "epoch": 1.5358931552587647,
      "grad_norm": 0.5592398047447205,
      "learning_rate": 5.648333371088706e-05,
      "loss": 1.0056,
      "step": 345
    },
    {
      "epoch": 1.5581524763494712,
      "grad_norm": 0.5523474812507629,
      "learning_rate": 5.519193644926535e-05,
      "loss": 1.0113,
      "step": 350
    },
    {
      "epoch": 1.5581524763494712,
      "eval_loss": 1.0144401788711548,
      "eval_runtime": 50.9085,
      "eval_samples_per_second": 15.695,
      "eval_steps_per_second": 1.964,
      "step": 350
    },
    {
      "epoch": 1.5804117974401781,
      "grad_norm": 0.5672771334648132,
      "learning_rate": 5.389702786475862e-05,
      "loss": 1.0022,
      "step": 355
    },
    {
      "epoch": 1.6026711185308848,
      "grad_norm": 0.5656226873397827,
      "learning_rate": 5.2599483708099016e-05,
      "loss": 0.9705,
      "step": 360
    },
    {
      "epoch": 1.6249304396215916,
      "grad_norm": 0.575705349445343,
      "learning_rate": 5.130018151246445e-05,
      "loss": 0.9638,
      "step": 365
    },
    {
      "epoch": 1.6471897607122983,
      "grad_norm": 0.5695839524269104,
      "learning_rate": 5e-05,
      "loss": 0.9957,
      "step": 370
    },
    {
      "epoch": 1.669449081803005,
      "grad_norm": 0.6090526580810547,
      "learning_rate": 4.869981848753556e-05,
      "loss": 0.9637,
      "step": 375
    },
    {
      "epoch": 1.6917084028937117,
      "grad_norm": 0.5683362483978271,
      "learning_rate": 4.740051629190099e-05,
      "loss": 0.9425,
      "step": 380
    },
    {
      "epoch": 1.7139677239844184,
      "grad_norm": 0.48340535163879395,
      "learning_rate": 4.61029721352414e-05,
      "loss": 0.9211,
      "step": 385
    },
    {
      "epoch": 1.7362270450751254,
      "grad_norm": 0.6130196452140808,
      "learning_rate": 4.480806355073467e-05,
      "loss": 0.9821,
      "step": 390
    },
    {
      "epoch": 1.7584863661658319,
      "grad_norm": 0.5705894231796265,
      "learning_rate": 4.351666628911295e-05,
      "loss": 0.8659,
      "step": 395
    },
    {
      "epoch": 1.7807456872565388,
      "grad_norm": 0.5951923131942749,
      "learning_rate": 4.2229653726389765e-05,
      "loss": 0.9537,
      "step": 400
    },
    {
      "epoch": 1.7807456872565388,
      "eval_loss": 1.010872483253479,
      "eval_runtime": 50.8897,
      "eval_samples_per_second": 15.701,
      "eval_steps_per_second": 1.965,
      "step": 400
    },
    {
      "epoch": 1.8030050083472453,
      "grad_norm": 0.535017728805542,
      "learning_rate": 4.094789627319298e-05,
      "loss": 1.009,
      "step": 405
    },
    {
      "epoch": 1.8252643294379522,
      "grad_norm": 0.5428237915039062,
      "learning_rate": 3.967226078610347e-05,
      "loss": 0.9533,
      "step": 410
    },
    {
      "epoch": 1.8475236505286587,
      "grad_norm": 0.5607818961143494,
      "learning_rate": 3.840360998139724e-05,
      "loss": 0.9488,
      "step": 415
    },
    {
      "epoch": 1.8697829716193657,
      "grad_norm": 0.5991472005844116,
      "learning_rate": 3.714280185158771e-05,
      "loss": 1.0467,
      "step": 420
    },
    {
      "epoch": 1.8920422927100722,
      "grad_norm": 0.6074681282043457,
      "learning_rate": 3.589068908516271e-05,
      "loss": 0.9183,
      "step": 425
    },
    {
      "epoch": 1.9143016138007791,
      "grad_norm": 0.5638883113861084,
      "learning_rate": 3.464811848990859e-05,
      "loss": 0.9581,
      "step": 430
    },
    {
      "epoch": 1.9365609348914858,
      "grad_norm": 0.5864625573158264,
      "learning_rate": 3.341593042021138e-05,
      "loss": 0.9824,
      "step": 435
    },
    {
      "epoch": 1.9588202559821926,
      "grad_norm": 0.5764511227607727,
      "learning_rate": 3.219495820872265e-05,
      "loss": 0.9699,
      "step": 440
    },
    {
      "epoch": 1.9810795770728993,
      "grad_norm": 0.5945712327957153,
      "learning_rate": 3.098602760277385e-05,
      "loss": 0.9828,
      "step": 445
    },
    {
      "epoch": 2.003338898163606,
      "grad_norm": 0.5488788485527039,
      "learning_rate": 2.978995620592092e-05,
      "loss": 0.9356,
      "step": 450
    },
    {
      "epoch": 2.003338898163606,
      "eval_loss": 1.0078463554382324,
      "eval_runtime": 50.8879,
      "eval_samples_per_second": 15.701,
      "eval_steps_per_second": 1.965,
      "step": 450
    }
  ],
  "logging_steps": 5,
  "max_steps": 672,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.99240623805694e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}