{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.436442989634479,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00436442989634479,
      "grad_norm": 74.5,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.044,
      "step": 10
    },
    {
      "epoch": 0.00872885979268958,
      "grad_norm": 166.0,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.0152,
      "step": 20
    },
    {
      "epoch": 0.01309328968903437,
      "grad_norm": 249.0,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.0905,
      "step": 30
    },
    {
      "epoch": 0.01745771958537916,
      "grad_norm": 210.0,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 1.1291,
      "step": 40
    },
    {
      "epoch": 0.02182214948172395,
      "grad_norm": 151.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.384,
      "step": 50
    },
    {
      "epoch": 0.02618657937806874,
      "grad_norm": 516.0,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.5235,
      "step": 60
    },
    {
      "epoch": 0.03055100927441353,
      "grad_norm": 684.0,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.888,
      "step": 70
    },
    {
      "epoch": 0.03491543917075832,
      "grad_norm": 504.0,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.9856,
      "step": 80
    },
    {
      "epoch": 0.03927986906710311,
      "grad_norm": 175.0,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 1.628,
      "step": 90
    },
    {
      "epoch": 0.0436442989634479,
      "grad_norm": 964.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.8794,
      "step": 100
    },
    {
      "epoch": 0.04800872885979269,
      "grad_norm": 151.0,
      "learning_rate": 8.8e-06,
      "loss": 1.4958,
      "step": 110
    },
    {
      "epoch": 0.05237315875613748,
      "grad_norm": 45.25,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.741,
      "step": 120
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 50.5,
      "learning_rate": 1.04e-05,
      "loss": 1.5346,
      "step": 130
    },
    {
      "epoch": 0.06110201854882706,
      "grad_norm": 116.5,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 1.498,
      "step": 140
    },
    {
      "epoch": 0.06546644844517185,
      "grad_norm": 35.0,
      "learning_rate": 1.2e-05,
      "loss": 1.3559,
      "step": 150
    },
    {
      "epoch": 0.06983087834151663,
      "grad_norm": 57.5,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 1.3762,
      "step": 160
    },
    {
      "epoch": 0.07419530823786143,
      "grad_norm": 40.25,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 1.5166,
      "step": 170
    },
    {
      "epoch": 0.07855973813420622,
      "grad_norm": 22.5,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 1.3441,
      "step": 180
    },
    {
      "epoch": 0.08292416803055101,
      "grad_norm": 14.875,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 1.6288,
      "step": 190
    },
    {
      "epoch": 0.0872885979268958,
      "grad_norm": 203.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.1069,
      "step": 200
    },
    {
      "epoch": 0.09165302782324058,
      "grad_norm": 57.5,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 1.5319,
      "step": 210
    },
    {
      "epoch": 0.09601745771958538,
      "grad_norm": 26.0,
      "learning_rate": 1.76e-05,
      "loss": 1.5801,
      "step": 220
    },
    {
      "epoch": 0.10038188761593017,
      "grad_norm": 24.125,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 1.3185,
      "step": 230
    },
    {
      "epoch": 0.10474631751227496,
      "grad_norm": 29.875,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 1.3118,
      "step": 240
    },
    {
      "epoch": 0.10911074740861974,
      "grad_norm": 18.625,
      "learning_rate": 2e-05,
      "loss": 1.1643,
      "step": 250
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 25.5,
      "learning_rate": 1.9999025240093045e-05,
      "loss": 1.3403,
      "step": 260
    },
    {
      "epoch": 0.11783960720130933,
      "grad_norm": 20.75,
      "learning_rate": 1.9996101150403543e-05,
      "loss": 1.2914,
      "step": 270
    },
    {
      "epoch": 0.12220403709765412,
      "grad_norm": 17.625,
      "learning_rate": 1.9991228300988586e-05,
      "loss": 1.2328,
      "step": 280
    },
    {
      "epoch": 0.1265684669939989,
      "grad_norm": 37.25,
      "learning_rate": 1.9984407641819812e-05,
      "loss": 1.2335,
      "step": 290
    },
    {
      "epoch": 0.1309328968903437,
      "grad_norm": 18.75,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 1.1872,
      "step": 300
    },
    {
      "epoch": 0.1352973267866885,
      "grad_norm": 22.625,
      "learning_rate": 1.9964928592495046e-05,
      "loss": 1.1274,
      "step": 310
    },
    {
      "epoch": 0.13966175668303327,
      "grad_norm": 15.8125,
      "learning_rate": 1.9952273999818312e-05,
      "loss": 1.235,
      "step": 320
    },
    {
      "epoch": 0.14402618657937807,
      "grad_norm": 16.5,
      "learning_rate": 1.9937679191605964e-05,
      "loss": 1.1159,
      "step": 330
    },
    {
      "epoch": 0.14839061647572285,
      "grad_norm": 17.5,
      "learning_rate": 1.9921147013144782e-05,
      "loss": 1.0252,
      "step": 340
    },
    {
      "epoch": 0.15275504637206766,
      "grad_norm": 6.78125,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 1.0231,
      "step": 350
    },
    {
      "epoch": 0.15711947626841244,
      "grad_norm": 20.375,
      "learning_rate": 1.988228381446553e-05,
      "loss": 1.086,
      "step": 360
    },
    {
      "epoch": 0.16148390616475722,
      "grad_norm": 29.375,
      "learning_rate": 1.985996037070505e-05,
      "loss": 1.0803,
      "step": 370
    },
    {
      "epoch": 0.16584833606110203,
      "grad_norm": 10.9375,
      "learning_rate": 1.983571470813386e-05,
      "loss": 0.987,
      "step": 380
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 12.625,
      "learning_rate": 1.9809551553491918e-05,
      "loss": 1.2151,
      "step": 390
    },
    {
      "epoch": 0.1745771958537916,
      "grad_norm": 14.125,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 0.9436,
      "step": 400
    },
    {
      "epoch": 0.1789416257501364,
      "grad_norm": 56.0,
      "learning_rate": 1.9751493543055634e-05,
      "loss": 1.0427,
      "step": 410
    },
    {
      "epoch": 0.18330605564648117,
      "grad_norm": 17.5,
      "learning_rate": 1.9719610005785466e-05,
      "loss": 1.0463,
      "step": 420
    },
    {
      "epoch": 0.18767048554282598,
      "grad_norm": 14.4375,
      "learning_rate": 1.9685831611286312e-05,
      "loss": 1.0375,
      "step": 430
    },
    {
      "epoch": 0.19203491543917076,
      "grad_norm": 14.3125,
      "learning_rate": 1.9650164944723116e-05,
      "loss": 1.0024,
      "step": 440
    },
    {
      "epoch": 0.19639934533551553,
      "grad_norm": 10.75,
      "learning_rate": 1.961261695938319e-05,
      "loss": 1.0858,
      "step": 450
    },
    {
      "epoch": 0.20076377523186034,
      "grad_norm": 8.1875,
      "learning_rate": 1.9573194975320672e-05,
      "loss": 0.9583,
      "step": 460
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 16.75,
      "learning_rate": 1.9531906677929472e-05,
      "loss": 1.048,
      "step": 470
    },
    {
      "epoch": 0.20949263502454993,
      "grad_norm": 24.25,
      "learning_rate": 1.9488760116444966e-05,
      "loss": 0.9226,
      "step": 480
    },
    {
      "epoch": 0.2138570649208947,
      "grad_norm": 12.125,
      "learning_rate": 1.944376370237481e-05,
      "loss": 1.0239,
      "step": 490
    },
    {
      "epoch": 0.2182214948172395,
      "grad_norm": 15.9375,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.9481,
      "step": 500
    },
    {
      "epoch": 0.2225859247135843,
      "grad_norm": 8.0,
      "learning_rate": 1.9348256763960146e-05,
      "loss": 0.9285,
      "step": 510
    },
    {
      "epoch": 0.22695035460992907,
      "grad_norm": 16.625,
      "learning_rate": 1.9297764858882516e-05,
      "loss": 0.9811,
      "step": 520
    },
    {
      "epoch": 0.23131478450627388,
      "grad_norm": 7.34375,
      "learning_rate": 1.9245460336123136e-05,
      "loss": 0.8843,
      "step": 530
    },
    {
      "epoch": 0.23567921440261866,
      "grad_norm": 12.5,
      "learning_rate": 1.9191353392552346e-05,
      "loss": 0.869,
      "step": 540
    },
    {
      "epoch": 0.24004364429896344,
      "grad_norm": 10.25,
      "learning_rate": 1.913545457642601e-05,
      "loss": 0.9146,
      "step": 550
    },
    {
      "epoch": 0.24440807419530824,
      "grad_norm": 20.75,
      "learning_rate": 1.907777478532909e-05,
      "loss": 0.904,
      "step": 560
    },
    {
      "epoch": 0.24877250409165302,
      "grad_norm": 13.9375,
      "learning_rate": 1.901832526405114e-05,
      "loss": 0.8561,
      "step": 570
    },
    {
      "epoch": 0.2531369339879978,
      "grad_norm": 9.25,
      "learning_rate": 1.895711760239413e-05,
      "loss": 0.9274,
      "step": 580
    },
    {
      "epoch": 0.2575013638843426,
      "grad_norm": 9.5625,
      "learning_rate": 1.889416373291298e-05,
      "loss": 0.9191,
      "step": 590
    },
    {
      "epoch": 0.2618657937806874,
      "grad_norm": 6.75,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 0.9027,
      "step": 600
    },
    {
      "epoch": 0.2662302236770322,
      "grad_norm": 9.5,
      "learning_rate": 1.8763066800438638e-05,
      "loss": 0.9427,
      "step": 610
    },
    {
      "epoch": 0.270594653573377,
      "grad_norm": 13.125,
      "learning_rate": 1.869494929505219e-05,
      "loss": 0.8664,
      "step": 620
    },
    {
      "epoch": 0.27495908346972175,
      "grad_norm": 19.375,
      "learning_rate": 1.8625136692072577e-05,
      "loss": 0.9021,
      "step": 630
    },
    {
      "epoch": 0.27932351336606653,
      "grad_norm": 14.5,
      "learning_rate": 1.855364260160507e-05,
      "loss": 0.9041,
      "step": 640
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 8.75,
      "learning_rate": 1.848048096156426e-05,
      "loss": 0.8482,
      "step": 650
    },
    {
      "epoch": 0.28805237315875615,
      "grad_norm": 18.5,
      "learning_rate": 1.8405666034956842e-05,
      "loss": 0.9267,
      "step": 660
    },
    {
      "epoch": 0.2924168030551009,
      "grad_norm": 5.875,
      "learning_rate": 1.8329212407100996e-05,
      "loss": 0.8678,
      "step": 670
    },
    {
      "epoch": 0.2967812329514457,
      "grad_norm": 12.625,
      "learning_rate": 1.8251134982782952e-05,
      "loss": 0.8268,
      "step": 680
    },
    {
      "epoch": 0.3011456628477905,
      "grad_norm": 12.875,
      "learning_rate": 1.8171448983351284e-05,
      "loss": 0.8265,
      "step": 690
    },
    {
      "epoch": 0.3055100927441353,
      "grad_norm": 8.6875,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.8773,
      "step": 700
    },
    {
      "epoch": 0.3098745226404801,
      "grad_norm": 16.75,
      "learning_rate": 1.8007313709487334e-05,
      "loss": 0.8472,
      "step": 710
    },
    {
      "epoch": 0.3142389525368249,
      "grad_norm": 7.53125,
      "learning_rate": 1.792289643355191e-05,
      "loss": 0.8534,
      "step": 720
    },
    {
      "epoch": 0.31860338243316966,
      "grad_norm": 15.125,
      "learning_rate": 1.78369345732584e-05,
      "loss": 0.8069,
      "step": 730
    },
    {
      "epoch": 0.32296781232951444,
      "grad_norm": 11.5,
      "learning_rate": 1.7749444887041797e-05,
      "loss": 0.8533,
      "step": 740
    },
    {
      "epoch": 0.32733224222585927,
      "grad_norm": 14.75,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.8662,
      "step": 750
    },
    {
      "epoch": 0.33169667212220405,
      "grad_norm": 15.75,
      "learning_rate": 1.7569950556517566e-05,
      "loss": 0.8397,
      "step": 760
    },
    {
      "epoch": 0.33606110201854883,
      "grad_norm": 19.875,
      "learning_rate": 1.747798090498532e-05,
      "loss": 0.7535,
      "step": 770
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 11.75,
      "learning_rate": 1.7384553406258842e-05,
      "loss": 0.8573,
      "step": 780
    },
    {
      "epoch": 0.3447899618112384,
      "grad_norm": 6.9375,
      "learning_rate": 1.7289686274214116e-05,
      "loss": 0.8559,
      "step": 790
    },
    {
      "epoch": 0.3491543917075832,
      "grad_norm": 10.9375,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 0.8459,
      "step": 800
    },
    {
      "epoch": 0.353518821603928,
      "grad_norm": 12.0625,
      "learning_rate": 1.709570736536521e-05,
      "loss": 0.8352,
      "step": 810
    },
    {
      "epoch": 0.3578832515002728,
      "grad_norm": 4.59375,
      "learning_rate": 1.6996633405133656e-05,
      "loss": 0.8146,
      "step": 820
    },
    {
      "epoch": 0.36224768139661756,
      "grad_norm": 15.0,
      "learning_rate": 1.68961954373567e-05,
      "loss": 0.78,
      "step": 830
    },
    {
      "epoch": 0.36661211129296234,
      "grad_norm": 5.6875,
      "learning_rate": 1.6794413042615168e-05,
      "loss": 0.8002,
      "step": 840
    },
    {
      "epoch": 0.3709765411893072,
      "grad_norm": 18.5,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 0.8296,
      "step": 850
    },
    {
      "epoch": 0.37534097108565195,
      "grad_norm": 42.0,
      "learning_rate": 1.6586894601186804e-05,
      "loss": 0.8742,
      "step": 860
    },
    {
      "epoch": 0.37970540098199673,
      "grad_norm": 9.5,
      "learning_rate": 1.6481199010631312e-05,
      "loss": 0.779,
      "step": 870
    },
    {
      "epoch": 0.3840698308783415,
      "grad_norm": 6.0625,
      "learning_rate": 1.63742398974869e-05,
      "loss": 0.747,
      "step": 880
    },
    {
      "epoch": 0.3884342607746863,
      "grad_norm": 9.375,
      "learning_rate": 1.6266038113644605e-05,
      "loss": 0.8371,
      "step": 890
    },
    {
      "epoch": 0.39279869067103107,
      "grad_norm": 7.9375,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 0.7598,
      "step": 900
    },
    {
      "epoch": 0.3971631205673759,
      "grad_norm": 14.75,
      "learning_rate": 1.6045991148623752e-05,
      "loss": 0.7371,
      "step": 910
    },
    {
      "epoch": 0.4015275504637207,
      "grad_norm": 5.09375,
      "learning_rate": 1.5934188866037017e-05,
      "loss": 0.7388,
      "step": 920
    },
    {
      "epoch": 0.40589198036006546,
      "grad_norm": 7.96875,
      "learning_rate": 1.5821229701572897e-05,
      "loss": 0.7652,
      "step": 930
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 12.3125,
      "learning_rate": 1.570713567684432e-05,
      "loss": 0.82,
      "step": 940
    },
    {
      "epoch": 0.414620840152755,
      "grad_norm": 9.5,
      "learning_rate": 1.5591929034707468e-05,
      "loss": 0.7934,
      "step": 950
    },
    {
      "epoch": 0.41898527004909986,
      "grad_norm": 8.5625,
      "learning_rate": 1.5475632234925505e-05,
      "loss": 0.7752,
      "step": 960
    },
    {
      "epoch": 0.42334969994544464,
      "grad_norm": 8.375,
      "learning_rate": 1.5358267949789968e-05,
      "loss": 0.7438,
      "step": 970
    },
    {
      "epoch": 0.4277141298417894,
      "grad_norm": 7.6875,
      "learning_rate": 1.5239859059700794e-05,
      "loss": 0.7512,
      "step": 980
    },
    {
      "epoch": 0.4320785597381342,
      "grad_norm": 9.1875,
      "learning_rate": 1.5120428648705716e-05,
      "loss": 0.6996,
      "step": 990
    },
    {
      "epoch": 0.436442989634479,
      "grad_norm": 6.0625,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.7038,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.82656621576192e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}