{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.232177894048398,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.052321778940483975,
      "grad_norm": 73.5,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.4785,
      "step": 10
    },
    {
      "epoch": 0.10464355788096795,
      "grad_norm": 280.0,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.4749,
      "step": 20
    },
    {
      "epoch": 0.15696533682145192,
      "grad_norm": 664.0,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.5162,
      "step": 30
    },
    {
      "epoch": 0.2092871157619359,
      "grad_norm": 684.0,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.7172,
      "step": 40
    },
    {
      "epoch": 0.2616088947024199,
      "grad_norm": 209.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.8219,
      "step": 50
    },
    {
      "epoch": 0.31393067364290383,
      "grad_norm": 122.0,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.1019,
      "step": 60
    },
    {
      "epoch": 0.36625245258338784,
      "grad_norm": 149.0,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.145,
      "step": 70
    },
    {
      "epoch": 0.4185742315238718,
      "grad_norm": 123.5,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.1876,
      "step": 80
    },
    {
      "epoch": 0.4708960104643558,
      "grad_norm": 89.0,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 1.207,
      "step": 90
    },
    {
      "epoch": 0.5232177894048398,
      "grad_norm": 372.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.0986,
      "step": 100
    },
    {
      "epoch": 0.5755395683453237,
      "grad_norm": 69.0,
      "learning_rate": 8.8e-06,
      "loss": 0.8367,
      "step": 110
    },
    {
      "epoch": 0.6278613472858077,
      "grad_norm": 60.25,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.8822,
      "step": 120
    },
    {
      "epoch": 0.6801831262262917,
      "grad_norm": 44.75,
      "learning_rate": 1.04e-05,
      "loss": 1.2104,
      "step": 130
    },
    {
      "epoch": 0.7325049051667757,
      "grad_norm": 49.0,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.8587,
      "step": 140
    },
    {
      "epoch": 0.7848266841072596,
      "grad_norm": 42.5,
      "learning_rate": 1.2e-05,
      "loss": 0.761,
      "step": 150
    },
    {
      "epoch": 0.8371484630477436,
      "grad_norm": 42.5,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 0.7207,
      "step": 160
    },
    {
      "epoch": 0.8894702419882276,
      "grad_norm": 28.25,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 0.7541,
      "step": 170
    },
    {
      "epoch": 0.9417920209287116,
      "grad_norm": 40.75,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 0.7367,
      "step": 180
    },
    {
      "epoch": 0.9941137998691956,
      "grad_norm": 231.0,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 0.8107,
      "step": 190
    },
    {
      "epoch": 1.0464355788096795,
      "grad_norm": 70.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.7498,
      "step": 200
    },
    {
      "epoch": 1.0987573577501635,
      "grad_norm": 33.5,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 0.7138,
      "step": 210
    },
    {
      "epoch": 1.1510791366906474,
      "grad_norm": 34.75,
      "learning_rate": 1.76e-05,
      "loss": 0.6399,
      "step": 220
    },
    {
      "epoch": 1.2034009156311314,
      "grad_norm": 20.125,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 0.5844,
      "step": 230
    },
    {
      "epoch": 1.2557226945716153,
      "grad_norm": 34.25,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.6765,
      "step": 240
    },
    {
      "epoch": 1.3080444735120995,
      "grad_norm": 37.0,
      "learning_rate": 2e-05,
      "loss": 3.7542,
      "step": 250
    },
    {
      "epoch": 1.3603662524525835,
      "grad_norm": 27.25,
      "learning_rate": 1.9999025240093045e-05,
      "loss": 0.7183,
      "step": 260
    },
    {
      "epoch": 1.4126880313930674,
      "grad_norm": 20.25,
      "learning_rate": 1.9996101150403543e-05,
      "loss": 0.5714,
      "step": 270
    },
    {
      "epoch": 1.4650098103335514,
      "grad_norm": 21.125,
      "learning_rate": 1.9991228300988586e-05,
      "loss": 0.5506,
      "step": 280
    },
    {
      "epoch": 1.5173315892740353,
      "grad_norm": 23.625,
      "learning_rate": 1.9984407641819812e-05,
      "loss": 0.5253,
      "step": 290
    },
    {
      "epoch": 1.5696533682145193,
      "grad_norm": 20.75,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 0.5671,
      "step": 300
    },
    {
      "epoch": 1.6219751471550032,
      "grad_norm": 15.6875,
      "learning_rate": 1.9964928592495046e-05,
      "loss": 0.4991,
      "step": 310
    },
    {
      "epoch": 1.6742969260954872,
      "grad_norm": 18.125,
      "learning_rate": 1.9952273999818312e-05,
      "loss": 0.5376,
      "step": 320
    },
    {
      "epoch": 1.7266187050359711,
      "grad_norm": 18.125,
      "learning_rate": 1.9937679191605964e-05,
      "loss": 0.5307,
      "step": 330
    },
    {
      "epoch": 1.7789404839764553,
      "grad_norm": 17.125,
      "learning_rate": 1.9921147013144782e-05,
      "loss": 0.522,
      "step": 340
    },
    {
      "epoch": 1.831262262916939,
      "grad_norm": 11.375,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 0.4873,
      "step": 350
    },
    {
      "epoch": 1.8835840418574232,
      "grad_norm": 19.625,
      "learning_rate": 1.988228381446553e-05,
      "loss": 0.4609,
      "step": 360
    },
    {
      "epoch": 1.9359058207979072,
      "grad_norm": 15.0625,
      "learning_rate": 1.985996037070505e-05,
      "loss": 0.4225,
      "step": 370
    },
    {
      "epoch": 1.9882275997383911,
      "grad_norm": 19.0,
      "learning_rate": 1.983571470813386e-05,
      "loss": 0.4309,
      "step": 380
    },
    {
      "epoch": 2.040549378678875,
      "grad_norm": 18.5,
      "learning_rate": 1.9809551553491918e-05,
      "loss": 0.4062,
      "step": 390
    },
    {
      "epoch": 2.092871157619359,
      "grad_norm": 10.25,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 0.3827,
      "step": 400
    },
    {
      "epoch": 2.145192936559843,
      "grad_norm": 23.75,
      "learning_rate": 1.9751493543055634e-05,
      "loss": 0.3883,
      "step": 410
    },
    {
      "epoch": 2.197514715500327,
      "grad_norm": 14.8125,
      "learning_rate": 1.9719610005785466e-05,
      "loss": 0.4069,
      "step": 420
    },
    {
      "epoch": 2.249836494440811,
      "grad_norm": 23.125,
      "learning_rate": 1.9685831611286312e-05,
      "loss": 0.3815,
      "step": 430
    },
    {
      "epoch": 2.302158273381295,
      "grad_norm": 10.8125,
      "learning_rate": 1.9650164944723116e-05,
      "loss": 0.3719,
      "step": 440
    },
    {
      "epoch": 2.354480052321779,
      "grad_norm": 15.6875,
      "learning_rate": 1.961261695938319e-05,
      "loss": 0.4038,
      "step": 450
    },
    {
      "epoch": 2.4068018312622628,
      "grad_norm": 18.875,
      "learning_rate": 1.9573194975320672e-05,
      "loss": 0.3864,
      "step": 460
    },
    {
      "epoch": 2.459123610202747,
      "grad_norm": 21.375,
      "learning_rate": 1.9531906677929472e-05,
      "loss": 0.3941,
      "step": 470
    },
    {
      "epoch": 2.5114453891432307,
      "grad_norm": 24.75,
      "learning_rate": 1.9488760116444966e-05,
      "loss": 0.3661,
      "step": 480
    },
    {
      "epoch": 2.563767168083715,
      "grad_norm": 30.0,
      "learning_rate": 1.944376370237481e-05,
      "loss": 0.3604,
      "step": 490
    },
    {
      "epoch": 2.616088947024199,
      "grad_norm": 11.6875,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.3618,
      "step": 500
    },
    {
      "epoch": 2.6684107259646828,
      "grad_norm": 24.875,
      "learning_rate": 1.9348256763960146e-05,
      "loss": 0.3942,
      "step": 510
    },
    {
      "epoch": 2.720732504905167,
      "grad_norm": 3.390625,
      "learning_rate": 1.9297764858882516e-05,
      "loss": 0.3458,
      "step": 520
    },
    {
      "epoch": 2.7730542838456507,
      "grad_norm": 10.3125,
      "learning_rate": 1.9245460336123136e-05,
      "loss": 0.3533,
      "step": 530
    },
    {
      "epoch": 2.825376062786135,
      "grad_norm": 20.875,
      "learning_rate": 1.9191353392552346e-05,
      "loss": 0.3546,
      "step": 540
    },
    {
      "epoch": 2.8776978417266186,
      "grad_norm": 14.3125,
      "learning_rate": 1.913545457642601e-05,
      "loss": 0.366,
      "step": 550
    },
    {
      "epoch": 2.9300196206671028,
      "grad_norm": 13.875,
      "learning_rate": 1.907777478532909e-05,
      "loss": 0.3353,
      "step": 560
    },
    {
      "epoch": 2.982341399607587,
      "grad_norm": 4.25,
      "learning_rate": 1.901832526405114e-05,
      "loss": 0.3564,
      "step": 570
    },
    {
      "epoch": 3.0346631785480707,
      "grad_norm": 10.3125,
      "learning_rate": 1.895711760239413e-05,
      "loss": 0.3324,
      "step": 580
    },
    {
      "epoch": 3.0869849574885544,
      "grad_norm": 6.15625,
      "learning_rate": 1.889416373291298e-05,
      "loss": 0.3254,
      "step": 590
    },
    {
      "epoch": 3.1393067364290386,
      "grad_norm": 9.6875,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 0.3278,
      "step": 600
    },
    {
      "epoch": 3.1916285153695227,
      "grad_norm": 10.4375,
      "learning_rate": 1.8763066800438638e-05,
      "loss": 0.2962,
      "step": 610
    },
    {
      "epoch": 3.2439502943100065,
      "grad_norm": 15.125,
      "learning_rate": 1.869494929505219e-05,
      "loss": 0.311,
      "step": 620
    },
    {
      "epoch": 3.2962720732504907,
      "grad_norm": 13.0625,
      "learning_rate": 1.8625136692072577e-05,
      "loss": 0.2956,
      "step": 630
    },
    {
      "epoch": 3.3485938521909744,
      "grad_norm": 12.875,
      "learning_rate": 1.855364260160507e-05,
      "loss": 0.3173,
      "step": 640
    },
    {
      "epoch": 3.4009156311314586,
      "grad_norm": 10.1875,
      "learning_rate": 1.848048096156426e-05,
      "loss": 0.298,
      "step": 650
    },
    {
      "epoch": 3.4532374100719423,
      "grad_norm": 6.375,
      "learning_rate": 1.8405666034956842e-05,
      "loss": 0.3216,
      "step": 660
    },
    {
      "epoch": 3.5055591890124265,
      "grad_norm": 23.25,
      "learning_rate": 1.8329212407100996e-05,
      "loss": 0.3417,
      "step": 670
    },
    {
      "epoch": 3.5578809679529106,
      "grad_norm": 11.25,
      "learning_rate": 1.8251134982782952e-05,
      "loss": 0.3169,
      "step": 680
    },
    {
      "epoch": 3.6102027468933944,
      "grad_norm": 14.9375,
      "learning_rate": 1.8171448983351284e-05,
      "loss": 0.3221,
      "step": 690
    },
    {
      "epoch": 3.662524525833878,
      "grad_norm": 9.375,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.2793,
      "step": 700
    },
    {
      "epoch": 3.7148463047743623,
      "grad_norm": 3.3125,
      "learning_rate": 1.8007313709487334e-05,
      "loss": 0.3063,
      "step": 710
    },
    {
      "epoch": 3.7671680837148465,
      "grad_norm": 13.0625,
      "learning_rate": 1.792289643355191e-05,
      "loss": 0.2723,
      "step": 720
    },
    {
      "epoch": 3.81948986265533,
      "grad_norm": 13.0,
      "learning_rate": 1.78369345732584e-05,
      "loss": 0.2924,
      "step": 730
    },
    {
      "epoch": 3.8718116415958144,
      "grad_norm": 20.25,
      "learning_rate": 1.7749444887041797e-05,
      "loss": 0.314,
      "step": 740
    },
    {
      "epoch": 3.924133420536298,
      "grad_norm": 7.0625,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.2965,
      "step": 750
    },
    {
      "epoch": 3.9764551994767823,
      "grad_norm": 12.25,
      "learning_rate": 1.7569950556517566e-05,
      "loss": 0.2784,
      "step": 760
    },
    {
      "epoch": 4.028776978417266,
      "grad_norm": 7.5,
      "learning_rate": 1.747798090498532e-05,
      "loss": 0.2626,
      "step": 770
    },
    {
      "epoch": 4.08109875735775,
      "grad_norm": 15.0625,
      "learning_rate": 1.7384553406258842e-05,
      "loss": 0.2629,
      "step": 780
    },
    {
      "epoch": 4.133420536298234,
      "grad_norm": 11.625,
      "learning_rate": 1.7289686274214116e-05,
      "loss": 0.252,
      "step": 790
    },
    {
      "epoch": 4.185742315238718,
      "grad_norm": 9.75,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 0.2466,
      "step": 800
    },
    {
      "epoch": 4.238064094179202,
      "grad_norm": 11.3125,
      "learning_rate": 1.709570736536521e-05,
      "loss": 0.2547,
      "step": 810
    },
    {
      "epoch": 4.290385873119686,
      "grad_norm": 7.15625,
      "learning_rate": 1.6996633405133656e-05,
      "loss": 0.272,
      "step": 820
    },
    {
      "epoch": 4.34270765206017,
      "grad_norm": 9.1875,
      "learning_rate": 1.68961954373567e-05,
      "loss": 0.2467,
      "step": 830
    },
    {
      "epoch": 4.395029431000654,
      "grad_norm": 8.125,
      "learning_rate": 1.6794413042615168e-05,
      "loss": 0.2421,
      "step": 840
    },
    {
      "epoch": 4.447351209941138,
      "grad_norm": 9.4375,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 0.2699,
      "step": 850
    },
    {
      "epoch": 4.499672988881622,
      "grad_norm": 4.96875,
      "learning_rate": 1.6586894601186804e-05,
      "loss": 0.2446,
      "step": 860
    },
    {
      "epoch": 4.551994767822106,
      "grad_norm": 7.46875,
      "learning_rate": 1.6481199010631312e-05,
      "loss": 0.2501,
      "step": 870
    },
    {
      "epoch": 4.60431654676259,
      "grad_norm": 12.875,
      "learning_rate": 1.63742398974869e-05,
      "loss": 0.2508,
      "step": 880
    },
    {
      "epoch": 4.656638325703074,
      "grad_norm": 10.4375,
      "learning_rate": 1.6266038113644605e-05,
      "loss": 0.2487,
      "step": 890
    },
    {
      "epoch": 4.708960104643558,
      "grad_norm": 3.046875,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 0.2384,
      "step": 900
    },
    {
      "epoch": 4.761281883584042,
      "grad_norm": 11.1875,
      "learning_rate": 1.6045991148623752e-05,
      "loss": 0.2552,
      "step": 910
    },
    {
      "epoch": 4.8136036625245255,
      "grad_norm": 10.6875,
      "learning_rate": 1.5934188866037017e-05,
      "loss": 0.2299,
      "step": 920
    },
    {
      "epoch": 4.86592544146501,
      "grad_norm": 10.375,
      "learning_rate": 1.5821229701572897e-05,
      "loss": 0.2443,
      "step": 930
    },
    {
      "epoch": 4.918247220405494,
      "grad_norm": 2.109375,
      "learning_rate": 1.570713567684432e-05,
      "loss": 0.2364,
      "step": 940
    },
    {
      "epoch": 4.970568999345978,
      "grad_norm": 3.828125,
      "learning_rate": 1.5591929034707468e-05,
      "loss": 0.252,
      "step": 950
    },
    {
      "epoch": 5.022890778286461,
      "grad_norm": 3.53125,
      "learning_rate": 1.5475632234925505e-05,
      "loss": 0.2499,
      "step": 960
    },
    {
      "epoch": 5.075212557226946,
      "grad_norm": 7.90625,
      "learning_rate": 1.5358267949789968e-05,
      "loss": 0.2217,
      "step": 970
    },
    {
      "epoch": 5.12753433616743,
      "grad_norm": 8.125,
      "learning_rate": 1.5239859059700794e-05,
      "loss": 0.2111,
      "step": 980
    },
    {
      "epoch": 5.179856115107913,
      "grad_norm": 8.75,
      "learning_rate": 1.5120428648705716e-05,
      "loss": 0.2166,
      "step": 990
    },
    {
      "epoch": 5.232177894048398,
      "grad_norm": 10.375,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.2056,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 14,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.8253704138194944e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}