{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008,
      "grad_norm": 166.17074584960938,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 11.9701,
      "step": 20
    },
    {
      "epoch": 0.016,
      "grad_norm": 79.01113891601562,
      "learning_rate": 5.333333333333333e-05,
      "loss": 9.669,
      "step": 40
    },
    {
      "epoch": 0.024,
      "grad_norm": 85.70152282714844,
      "learning_rate": 8e-05,
      "loss": 6.905,
      "step": 60
    },
    {
      "epoch": 0.032,
      "grad_norm": 106.15095520019531,
      "learning_rate": 9.999895105006994e-05,
      "loss": 3.7532,
      "step": 80
    },
    {
      "epoch": 0.04,
      "grad_norm": 138.3174285888672,
      "learning_rate": 9.997377845227576e-05,
      "loss": 4.0354,
      "step": 100
    },
    {
      "epoch": 0.048,
      "grad_norm": 57.63945770263672,
      "learning_rate": 9.991505881949837e-05,
      "loss": 3.5036,
      "step": 120
    },
    {
      "epoch": 0.056,
      "grad_norm": 163.03395080566406,
      "learning_rate": 9.982283156980132e-05,
      "loss": 2.5848,
      "step": 140
    },
    {
      "epoch": 0.064,
      "grad_norm": 63.67021942138672,
      "learning_rate": 9.96971586146684e-05,
      "loss": 1.9652,
      "step": 160
    },
    {
      "epoch": 0.072,
      "grad_norm": 79.90151977539062,
      "learning_rate": 9.953812431744276e-05,
      "loss": 1.6136,
      "step": 180
    },
    {
      "epoch": 0.08,
      "grad_norm": 69.72734069824219,
      "learning_rate": 9.934583543669453e-05,
      "loss": 1.4255,
      "step": 200
    },
    {
      "epoch": 0.088,
      "grad_norm": 114.95301055908203,
      "learning_rate": 9.912042105455463e-05,
      "loss": 1.1624,
      "step": 220
    },
    {
      "epoch": 0.096,
      "grad_norm": 136.07012939453125,
      "learning_rate": 9.886203249006265e-05,
      "loss": 1.7055,
      "step": 240
    },
    {
      "epoch": 0.104,
      "grad_norm": 68.01107025146484,
      "learning_rate": 9.857084319758772e-05,
      "loss": 1.9069,
      "step": 260
    },
    {
      "epoch": 0.112,
      "grad_norm": 55.16877746582031,
      "learning_rate": 9.824704865038968e-05,
      "loss": 1.6613,
      "step": 280
    },
    {
      "epoch": 0.12,
      "grad_norm": 148.36671447753906,
      "learning_rate": 9.789086620939936e-05,
      "loss": 1.0507,
      "step": 300
    },
    {
      "epoch": 0.128,
      "grad_norm": 45.765541076660156,
      "learning_rate": 9.75025349773058e-05,
      "loss": 1.076,
      "step": 320
    },
    {
      "epoch": 0.136,
      "grad_norm": 29.589893341064453,
      "learning_rate": 9.708231563804828e-05,
      "loss": 1.1486,
      "step": 340
    },
    {
      "epoch": 0.144,
      "grad_norm": 101.57962799072266,
      "learning_rate": 9.663049028182111e-05,
      "loss": 0.9937,
      "step": 360
    },
    {
      "epoch": 0.152,
      "grad_norm": 67.2091293334961,
      "learning_rate": 9.61473622157086e-05,
      "loss": 0.7819,
      "step": 380
    },
    {
      "epoch": 0.16,
      "grad_norm": 142.623291015625,
      "learning_rate": 9.563325576007701e-05,
      "loss": 1.1036,
      "step": 400
    },
    {
      "epoch": 0.168,
      "grad_norm": 99.56015014648438,
      "learning_rate": 9.508851603086093e-05,
      "loss": 0.9757,
      "step": 420
    },
    {
      "epoch": 0.176,
      "grad_norm": 76.89378356933594,
      "learning_rate": 9.45135087078892e-05,
      "loss": 0.8925,
      "step": 440
    },
    {
      "epoch": 0.184,
      "grad_norm": 61.822608947753906,
      "learning_rate": 9.390861978940686e-05,
      "loss": 0.9001,
      "step": 460
    },
    {
      "epoch": 0.192,
      "grad_norm": 97.94097900390625,
      "learning_rate": 9.327425533295724e-05,
      "loss": 0.9383,
      "step": 480
    },
    {
      "epoch": 0.2,
      "grad_norm": 94.21862030029297,
      "learning_rate": 9.261084118279847e-05,
      "loss": 1.1101,
      "step": 500
    },
    {
      "epoch": 0.208,
      "grad_norm": 99.49618530273438,
      "learning_rate": 9.191882268403743e-05,
      "loss": 0.8639,
      "step": 520
    },
    {
      "epoch": 0.216,
      "grad_norm": 91.68159484863281,
      "learning_rate": 9.119866438367263e-05,
      "loss": 1.1308,
      "step": 540
    },
    {
      "epoch": 0.224,
      "grad_norm": 88.58736419677734,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0318,
      "step": 560
    },
    {
      "epoch": 0.232,
      "grad_norm": 74.4514389038086,
      "learning_rate": 8.967588069182185e-05,
      "loss": 0.7682,
      "step": 580
    },
    {
      "epoch": 0.24,
      "grad_norm": 132.3037872314453,
      "learning_rate": 8.887427753398248e-05,
      "loss": 1.0116,
      "step": 600
    },
    {
      "epoch": 0.248,
      "grad_norm": 93.67770385742188,
      "learning_rate": 8.804657835561456e-05,
      "loss": 0.8581,
      "step": 620
    },
    {
      "epoch": 0.256,
      "grad_norm": 167.17413330078125,
      "learning_rate": 8.719333878517273e-05,
      "loss": 0.8944,
      "step": 640
    },
    {
      "epoch": 0.264,
      "grad_norm": 80.31649017333984,
      "learning_rate": 8.631513159619151e-05,
      "loss": 1.1003,
      "step": 660
    },
    {
      "epoch": 0.272,
      "grad_norm": 91.23484802246094,
      "learning_rate": 8.541254632278665e-05,
      "loss": 0.5505,
      "step": 680
    },
    {
      "epoch": 0.28,
      "grad_norm": 111.9620361328125,
      "learning_rate": 8.448618886390522e-05,
      "loss": 0.7148,
      "step": 700
    },
    {
      "epoch": 0.288,
      "grad_norm": 64.58492279052734,
      "learning_rate": 8.353668107658984e-05,
      "loss": 0.5565,
      "step": 720
    },
    {
      "epoch": 0.296,
      "grad_norm": 161.78875732421875,
      "learning_rate": 8.256466035853076e-05,
      "loss": 0.8629,
      "step": 740
    },
    {
      "epoch": 0.304,
      "grad_norm": 61.221771240234375,
      "learning_rate": 8.157077922018537e-05,
      "loss": 0.7266,
      "step": 760
    },
    {
      "epoch": 0.312,
      "grad_norm": 153.8072052001953,
      "learning_rate": 8.055570484675251e-05,
      "loss": 0.8071,
      "step": 780
    },
    {
      "epoch": 0.32,
      "grad_norm": 159.62533569335938,
      "learning_rate": 7.952011865029614e-05,
      "loss": 0.6098,
      "step": 800
    },
    {
      "epoch": 0.328,
      "grad_norm": 174.14382934570312,
      "learning_rate": 7.846471581231814e-05,
      "loss": 0.8592,
      "step": 820
    },
    {
      "epoch": 0.336,
      "grad_norm": 42.97473907470703,
      "learning_rate": 7.739020481708815e-05,
      "loss": 0.6594,
      "step": 840
    },
    {
      "epoch": 0.344,
      "grad_norm": 62.19815444946289,
      "learning_rate": 7.629730697604314e-05,
      "loss": 0.5692,
      "step": 860
    },
    {
      "epoch": 0.352,
      "grad_norm": 112.52002716064453,
      "learning_rate": 7.518675594357633e-05,
      "loss": 0.6515,
      "step": 880
    },
    {
      "epoch": 0.36,
      "grad_norm": 71.151611328125,
      "learning_rate": 7.405929722454026e-05,
      "loss": 0.6949,
      "step": 900
    },
    {
      "epoch": 0.368,
      "grad_norm": 82.4411392211914,
      "learning_rate": 7.291568767379484e-05,
      "loss": 0.688,
      "step": 920
    },
    {
      "epoch": 0.376,
      "grad_norm": 53.197975158691406,
      "learning_rate": 7.175669498813617e-05,
      "loss": 0.5941,
      "step": 940
    },
    {
      "epoch": 0.384,
      "grad_norm": 96.15673828125,
      "learning_rate": 7.05830971909472e-05,
      "loss": 0.7445,
      "step": 960
    },
    {
      "epoch": 0.392,
      "grad_norm": 71.28498077392578,
      "learning_rate": 6.939568210991633e-05,
      "loss": 0.7837,
      "step": 980
    },
    {
      "epoch": 0.4,
      "grad_norm": 98.7578353881836,
      "learning_rate": 6.819524684817438e-05,
      "loss": 0.867,
      "step": 1000
    },
    {
      "epoch": 0.408,
      "grad_norm": 34.90584945678711,
      "learning_rate": 6.698259724920502e-05,
      "loss": 0.5197,
      "step": 1020
    },
    {
      "epoch": 0.416,
      "grad_norm": 106.12273406982422,
      "learning_rate": 6.575854735588794e-05,
      "loss": 0.6065,
      "step": 1040
    },
    {
      "epoch": 0.424,
      "grad_norm": 74.21955871582031,
      "learning_rate": 6.452391886403767e-05,
      "loss": 0.5775,
      "step": 1060
    },
    {
      "epoch": 0.432,
      "grad_norm": 56.11361312866211,
      "learning_rate": 6.327954057080526e-05,
      "loss": 0.4924,
      "step": 1080
    },
    {
      "epoch": 0.44,
      "grad_norm": 51.63819122314453,
      "learning_rate": 6.202624781831268e-05,
      "loss": 0.6356,
      "step": 1100
    },
    {
      "epoch": 0.448,
      "grad_norm": 51.09682083129883,
      "learning_rate": 6.076488193289375e-05,
      "loss": 0.4962,
      "step": 1120
    },
    {
      "epoch": 0.456,
      "grad_norm": 48.28594970703125,
      "learning_rate": 5.949628966031785e-05,
      "loss": 0.4634,
      "step": 1140
    },
    {
      "epoch": 0.464,
      "grad_norm": 50.485267639160156,
      "learning_rate": 5.822132259737565e-05,
      "loss": 0.4791,
      "step": 1160
    },
    {
      "epoch": 0.472,
      "grad_norm": 158.87379455566406,
      "learning_rate": 5.6940836620208346e-05,
      "loss": 0.5748,
      "step": 1180
    },
    {
      "epoch": 0.48,
      "grad_norm": 75.37374877929688,
      "learning_rate": 5.565569130976422e-05,
      "loss": 0.5684,
      "step": 1200
    },
    {
      "epoch": 0.488,
      "grad_norm": 118.30435180664062,
      "learning_rate": 5.43667493747682e-05,
      "loss": 0.6176,
      "step": 1220
    },
    {
      "epoch": 0.496,
      "grad_norm": 86.57565307617188,
      "learning_rate": 5.307487607259175e-05,
      "loss": 0.6251,
      "step": 1240
    },
    {
      "epoch": 0.504,
      "grad_norm": 98.3755874633789,
      "learning_rate": 5.1780938628411794e-05,
      "loss": 0.5336,
      "step": 1260
    },
    {
      "epoch": 0.512,
      "grad_norm": 116.37334442138672,
      "learning_rate": 5.048580565304887e-05,
      "loss": 0.6277,
      "step": 1280
    },
    {
      "epoch": 0.52,
      "grad_norm": 66.12716674804688,
      "learning_rate": 4.919034655987493e-05,
      "loss": 0.4566,
      "step": 1300
    },
    {
      "epoch": 0.528,
      "grad_norm": 114.47698211669922,
      "learning_rate": 4.789543098118241e-05,
      "loss": 0.4926,
      "step": 1320
    },
    {
      "epoch": 0.536,
      "grad_norm": 32.51777648925781,
      "learning_rate": 4.660192818440641e-05,
      "loss": 0.5048,
      "step": 1340
    },
    {
      "epoch": 0.544,
      "grad_norm": 59.64183807373047,
      "learning_rate": 4.5310706488591856e-05,
      "loss": 0.4574,
      "step": 1360
    },
    {
      "epoch": 0.552,
      "grad_norm": 113.23239135742188,
      "learning_rate": 4.402263268149706e-05,
      "loss": 0.5314,
      "step": 1380
    },
    {
      "epoch": 0.56,
      "grad_norm": 51.29038619995117,
      "learning_rate": 4.27385714377255e-05,
      "loss": 0.4766,
      "step": 1400
    },
    {
      "epoch": 0.568,
      "grad_norm": 54.05197525024414,
      "learning_rate": 4.145938473827598e-05,
      "loss": 0.5337,
      "step": 1420
    },
    {
      "epoch": 0.576,
      "grad_norm": 105.83946990966797,
      "learning_rate": 4.018593129190113e-05,
      "loss": 0.4519,
      "step": 1440
    },
    {
      "epoch": 0.584,
      "grad_norm": 36.12518310546875,
      "learning_rate": 3.89190659586623e-05,
      "loss": 0.3604,
      "step": 1460
    },
    {
      "epoch": 0.592,
      "grad_norm": 46.54783248901367,
      "learning_rate": 3.765963917606828e-05,
      "loss": 0.381,
      "step": 1480
    },
    {
      "epoch": 0.6,
      "grad_norm": 68.79725646972656,
      "learning_rate": 3.640849638818286e-05,
      "loss": 0.4085,
      "step": 1500
    },
    {
      "epoch": 0.608,
      "grad_norm": 44.10316848754883,
      "learning_rate": 3.516647747808417e-05,
      "loss": 0.3213,
      "step": 1520
    },
    {
      "epoch": 0.616,
      "grad_norm": 75.88388061523438,
      "learning_rate": 3.3934416204057395e-05,
      "loss": 0.469,
      "step": 1540
    },
    {
      "epoch": 0.624,
      "grad_norm": 65.06538391113281,
      "learning_rate": 3.271313963989886e-05,
      "loss": 0.4438,
      "step": 1560
    },
    {
      "epoch": 0.632,
      "grad_norm": 62.845802307128906,
      "learning_rate": 3.150346761970741e-05,
      "loss": 0.4573,
      "step": 1580
    },
    {
      "epoch": 0.64,
      "grad_norm": 92.78313446044922,
      "learning_rate": 3.0306212187535653e-05,
      "loss": 0.4057,
      "step": 1600
    },
    {
      "epoch": 0.648,
      "grad_norm": 56.57185745239258,
      "learning_rate": 2.912217705227075e-05,
      "loss": 0.3921,
      "step": 1620
    },
    {
      "epoch": 0.656,
      "grad_norm": 37.49650192260742,
      "learning_rate": 2.7952157048110406e-05,
      "loss": 0.4174,
      "step": 1640
    },
    {
      "epoch": 0.664,
      "grad_norm": 41.775672912597656,
      "learning_rate": 2.6796937600996587e-05,
      "loss": 0.443,
      "step": 1660
    },
    {
      "epoch": 0.672,
      "grad_norm": 34.62808609008789,
      "learning_rate": 2.5657294201364522e-05,
      "loss": 0.4454,
      "step": 1680
    },
    {
      "epoch": 0.68,
      "grad_norm": 22.669153213500977,
      "learning_rate": 2.4533991883561868e-05,
      "loss": 0.384,
      "step": 1700
    },
    {
      "epoch": 0.688,
      "grad_norm": 73.54237365722656,
      "learning_rate": 2.3427784712286478e-05,
      "loss": 0.4722,
      "step": 1720
    },
    {
      "epoch": 0.696,
      "grad_norm": 91.86062622070312,
      "learning_rate": 2.2339415276388476e-05,
      "loss": 0.3731,
      "step": 1740
    },
    {
      "epoch": 0.704,
      "grad_norm": 70.42198181152344,
      "learning_rate": 2.1269614190375475e-05,
      "loss": 0.3745,
      "step": 1760
    },
    {
      "epoch": 0.712,
      "grad_norm": 66.34053039550781,
      "learning_rate": 2.021909960395661e-05,
      "loss": 0.3536,
      "step": 1780
    },
    {
      "epoch": 0.72,
      "grad_norm": 70.81706237792969,
      "learning_rate": 1.9188576719953633e-05,
      "loss": 0.3935,
      "step": 1800
    },
    {
      "epoch": 0.728,
      "grad_norm": 59.28203201293945,
      "learning_rate": 1.81787373209036e-05,
      "loss": 0.419,
      "step": 1820
    },
    {
      "epoch": 0.736,
      "grad_norm": 80.54914093017578,
      "learning_rate": 1.7190259304670038e-05,
      "loss": 0.3998,
      "step": 1840
    },
    {
      "epoch": 0.744,
      "grad_norm": 54.67918395996094,
      "learning_rate": 1.6223806229375182e-05,
      "loss": 0.3775,
      "step": 1860
    },
    {
      "epoch": 0.752,
      "grad_norm": 65.14604949951172,
      "learning_rate": 1.5280026867958185e-05,
      "loss": 0.3423,
      "step": 1880
    },
    {
      "epoch": 0.76,
      "grad_norm": 79.72464752197266,
      "learning_rate": 1.4359554772658552e-05,
      "loss": 0.4525,
      "step": 1900
    },
    {
      "epoch": 0.768,
      "grad_norm": 34.39617919921875,
      "learning_rate": 1.3463007849717036e-05,
      "loss": 0.2967,
      "step": 1920
    },
    {
      "epoch": 0.776,
      "grad_norm": 56.02670669555664,
      "learning_rate": 1.2590987944579807e-05,
      "loss": 0.362,
      "step": 1940
    },
    {
      "epoch": 0.784,
      "grad_norm": 77.49681091308594,
      "learning_rate": 1.1744080437883859e-05,
      "loss": 0.3531,
      "step": 1960
    },
    {
      "epoch": 0.792,
      "grad_norm": 61.57918930053711,
      "learning_rate": 1.092285385249528e-05,
      "loss": 0.3696,
      "step": 1980
    },
    {
      "epoch": 0.8,
      "grad_norm": 31.039453506469727,
      "learning_rate": 1.012785947186397e-05,
      "loss": 0.356,
      "step": 2000
    }
  ],
  "logging_steps": 20,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.2090517618564096e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}