{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03830398467840613,
  "eval_steps": 500,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004255998297600681,
      "grad_norm": 5634.16845703125,
      "learning_rate": 2.4e-07,
      "loss": 14.1264,
      "step": 10
    },
    {
      "epoch": 0.0008511996595201362,
      "grad_norm": 2312.5771484375,
      "learning_rate": 1.04e-06,
      "loss": 13.2905,
      "step": 20
    },
    {
      "epoch": 0.0012767994892802044,
      "grad_norm": 2110.1591796875,
      "learning_rate": 1.84e-06,
      "loss": 12.6236,
      "step": 30
    },
    {
      "epoch": 0.0017023993190402723,
      "grad_norm": 1493.8431396484375,
      "learning_rate": 2.64e-06,
      "loss": 12.3954,
      "step": 40
    },
    {
      "epoch": 0.0021279991488003403,
      "grad_norm": 1430.7598876953125,
      "learning_rate": 3.44e-06,
      "loss": 12.265,
      "step": 50
    },
    {
      "epoch": 0.0025535989785604087,
      "grad_norm": 2192.621826171875,
      "learning_rate": 4.24e-06,
      "loss": 12.018,
      "step": 60
    },
    {
      "epoch": 0.0029791988083204767,
      "grad_norm": 1678.5159912109375,
      "learning_rate": 5.04e-06,
      "loss": 11.8932,
      "step": 70
    },
    {
      "epoch": 0.0034047986380805447,
      "grad_norm": 1261.883056640625,
      "learning_rate": 5.84e-06,
      "loss": 11.8077,
      "step": 80
    },
    {
      "epoch": 0.0038303984678406127,
      "grad_norm": 1710.3070068359375,
      "learning_rate": 6.640000000000001e-06,
      "loss": 11.6841,
      "step": 90
    },
    {
      "epoch": 0.004255998297600681,
      "grad_norm": 2306.063232421875,
      "learning_rate": 7.44e-06,
      "loss": 11.5426,
      "step": 100
    },
    {
      "epoch": 0.004681598127360749,
      "grad_norm": 2158.360107421875,
      "learning_rate": 8.24e-06,
      "loss": 11.4863,
      "step": 110
    },
    {
      "epoch": 0.0051071979571208174,
      "grad_norm": 2058.938232421875,
      "learning_rate": 9.04e-06,
      "loss": 11.5044,
      "step": 120
    },
    {
      "epoch": 0.005532797786880885,
      "grad_norm": 2320.1376953125,
      "learning_rate": 9.84e-06,
      "loss": 11.4696,
      "step": 130
    },
    {
      "epoch": 0.005958397616640953,
      "grad_norm": 3147.455078125,
      "learning_rate": 1.064e-05,
      "loss": 11.2994,
      "step": 140
    },
    {
      "epoch": 0.006383997446401022,
      "grad_norm": 1930.887451171875,
      "learning_rate": 1.144e-05,
      "loss": 11.2686,
      "step": 150
    },
    {
      "epoch": 0.006809597276161089,
      "grad_norm": 3005.495361328125,
      "learning_rate": 1.224e-05,
      "loss": 11.2556,
      "step": 160
    },
    {
      "epoch": 0.007235197105921158,
      "grad_norm": 1587.324462890625,
      "learning_rate": 1.3039999999999999e-05,
      "loss": 11.1593,
      "step": 170
    },
    {
      "epoch": 0.007660796935681225,
      "grad_norm": 1496.0810546875,
      "learning_rate": 1.384e-05,
      "loss": 11.0329,
      "step": 180
    },
    {
      "epoch": 0.008086396765441295,
      "grad_norm": 2397.255615234375,
      "learning_rate": 1.4560000000000001e-05,
      "loss": 11.0514,
      "step": 190
    },
    {
      "epoch": 0.008511996595201361,
      "grad_norm": 3627.1494140625,
      "learning_rate": 1.536e-05,
      "loss": 10.9684,
      "step": 200
    },
    {
      "epoch": 0.00893759642496143,
      "grad_norm": 1078.9390869140625,
      "learning_rate": 1.616e-05,
      "loss": 11.0077,
      "step": 210
    },
    {
      "epoch": 0.009363196254721498,
      "grad_norm": 1400.2003173828125,
      "learning_rate": 1.696e-05,
      "loss": 10.7138,
      "step": 220
    },
    {
      "epoch": 0.009788796084481566,
      "grad_norm": 880.6416015625,
      "learning_rate": 1.7760000000000003e-05,
      "loss": 10.4564,
      "step": 230
    },
    {
      "epoch": 0.010214395914241635,
      "grad_norm": 888.9507446289062,
      "learning_rate": 1.856e-05,
      "loss": 10.4699,
      "step": 240
    },
    {
      "epoch": 0.010639995744001702,
      "grad_norm": 604.7562255859375,
      "learning_rate": 1.936e-05,
      "loss": 10.5335,
      "step": 250
    },
    {
      "epoch": 0.01106559557376177,
      "grad_norm": 885.2161865234375,
      "learning_rate": 2.016e-05,
      "loss": 10.3258,
      "step": 260
    },
    {
      "epoch": 0.011491195403521838,
      "grad_norm": 689.9547729492188,
      "learning_rate": 2.0960000000000003e-05,
      "loss": 10.3034,
      "step": 270
    },
    {
      "epoch": 0.011916795233281907,
      "grad_norm": 1086.3548583984375,
      "learning_rate": 2.176e-05,
      "loss": 10.121,
      "step": 280
    },
    {
      "epoch": 0.012342395063041975,
      "grad_norm": 728.9247436523438,
      "learning_rate": 2.256e-05,
      "loss": 9.9983,
      "step": 290
    },
    {
      "epoch": 0.012767994892802044,
      "grad_norm": 931.4705200195312,
      "learning_rate": 2.336e-05,
      "loss": 10.1502,
      "step": 300
    },
    {
      "epoch": 0.01319359472256211,
      "grad_norm": 836.438720703125,
      "learning_rate": 2.4160000000000002e-05,
      "loss": 10.0117,
      "step": 310
    },
    {
      "epoch": 0.013619194552322179,
      "grad_norm": 481.8641662597656,
      "learning_rate": 2.496e-05,
      "loss": 10.0033,
      "step": 320
    },
    {
      "epoch": 0.014044794382082247,
      "grad_norm": 368.5486755371094,
      "learning_rate": 2.576e-05,
      "loss": 9.7842,
      "step": 330
    },
    {
      "epoch": 0.014470394211842316,
      "grad_norm": 408.945068359375,
      "learning_rate": 2.6560000000000003e-05,
      "loss": 10.0045,
      "step": 340
    },
    {
      "epoch": 0.014895994041602384,
      "grad_norm": 882.4168701171875,
      "learning_rate": 2.7360000000000002e-05,
      "loss": 9.8133,
      "step": 350
    },
    {
      "epoch": 0.01532159387136245,
      "grad_norm": 688.0091552734375,
      "learning_rate": 2.816e-05,
      "loss": 9.74,
      "step": 360
    },
    {
      "epoch": 0.01574719370112252,
      "grad_norm": 480.2123107910156,
      "learning_rate": 2.8960000000000004e-05,
      "loss": 9.7187,
      "step": 370
    },
    {
      "epoch": 0.01617279353088259,
      "grad_norm": 266.4781799316406,
      "learning_rate": 2.976e-05,
      "loss": 9.4574,
      "step": 380
    },
    {
      "epoch": 0.016598393360642654,
      "grad_norm": 426.8431091308594,
      "learning_rate": 3.056e-05,
      "loss": 9.4476,
      "step": 390
    },
    {
      "epoch": 0.017023993190402723,
      "grad_norm": 507.83984375,
      "learning_rate": 3.136e-05,
      "loss": 9.6252,
      "step": 400
    },
    {
      "epoch": 0.01744959302016279,
      "grad_norm": 345.3815612792969,
      "learning_rate": 3.2160000000000004e-05,
      "loss": 9.4701,
      "step": 410
    },
    {
      "epoch": 0.01787519284992286,
      "grad_norm": 661.6119384765625,
      "learning_rate": 3.296e-05,
      "loss": 9.2308,
      "step": 420
    },
    {
      "epoch": 0.018300792679682928,
      "grad_norm": 249.719970703125,
      "learning_rate": 3.376e-05,
      "loss": 9.2749,
      "step": 430
    },
    {
      "epoch": 0.018726392509442996,
      "grad_norm": 396.6395263671875,
      "learning_rate": 3.456e-05,
      "loss": 9.3583,
      "step": 440
    },
    {
      "epoch": 0.019151992339203065,
      "grad_norm": 317.9398193359375,
      "learning_rate": 3.536000000000001e-05,
      "loss": 9.2281,
      "step": 450
    },
    {
      "epoch": 0.019577592168963133,
      "grad_norm": 237.1824493408203,
      "learning_rate": 3.616e-05,
      "loss": 9.0913,
      "step": 460
    },
    {
      "epoch": 0.0200031919987232,
      "grad_norm": 427.8457336425781,
      "learning_rate": 3.696e-05,
      "loss": 9.0147,
      "step": 470
    },
    {
      "epoch": 0.02042879182848327,
      "grad_norm": 380.43719482421875,
      "learning_rate": 3.776e-05,
      "loss": 8.9519,
      "step": 480
    },
    {
      "epoch": 0.020854391658243338,
      "grad_norm": 222.20193481445312,
      "learning_rate": 3.8560000000000004e-05,
      "loss": 9.0848,
      "step": 490
    },
    {
      "epoch": 0.021279991488003403,
      "grad_norm": 343.4478454589844,
      "learning_rate": 3.936e-05,
      "loss": 8.8757,
      "step": 500
    },
    {
      "epoch": 0.02170559131776347,
      "grad_norm": 261.2217712402344,
      "learning_rate": 4.016e-05,
      "loss": 8.9742,
      "step": 510
    },
    {
      "epoch": 0.02213119114752354,
      "grad_norm": 263.2187805175781,
      "learning_rate": 4.096e-05,
      "loss": 8.6574,
      "step": 520
    },
    {
      "epoch": 0.02255679097728361,
      "grad_norm": 323.5589904785156,
      "learning_rate": 4.176000000000001e-05,
      "loss": 8.8006,
      "step": 530
    },
    {
      "epoch": 0.022982390807043677,
      "grad_norm": 275.9966735839844,
      "learning_rate": 4.256e-05,
      "loss": 8.3938,
      "step": 540
    },
    {
      "epoch": 0.023407990636803745,
      "grad_norm": 217.8997344970703,
      "learning_rate": 4.336e-05,
      "loss": 8.7494,
      "step": 550
    },
    {
      "epoch": 0.023833590466563814,
      "grad_norm": 238.54171752929688,
      "learning_rate": 4.4160000000000004e-05,
      "loss": 8.4978,
      "step": 560
    },
    {
      "epoch": 0.024259190296323882,
      "grad_norm": 248.50515747070312,
      "learning_rate": 4.496e-05,
      "loss": 8.4339,
      "step": 570
    },
    {
      "epoch": 0.02468479012608395,
      "grad_norm": 300.531982421875,
      "learning_rate": 4.576e-05,
      "loss": 8.5025,
      "step": 580
    },
    {
      "epoch": 0.02511038995584402,
      "grad_norm": 262.1846923828125,
      "learning_rate": 4.656e-05,
      "loss": 8.3452,
      "step": 590
    },
    {
      "epoch": 0.025535989785604087,
      "grad_norm": 236.63243103027344,
      "learning_rate": 4.736000000000001e-05,
      "loss": 8.2499,
      "step": 600
    },
    {
      "epoch": 0.025961589615364152,
      "grad_norm": 312.71343994140625,
      "learning_rate": 4.816e-05,
      "loss": 8.2303,
      "step": 610
    },
    {
      "epoch": 0.02638718944512422,
      "grad_norm": 247.94815063476562,
      "learning_rate": 4.8880000000000006e-05,
      "loss": 8.1981,
      "step": 620
    },
    {
      "epoch": 0.02681278927488429,
      "grad_norm": 230.76556396484375,
      "learning_rate": 4.9680000000000005e-05,
      "loss": 8.1115,
      "step": 630
    },
    {
      "epoch": 0.027238389104644357,
      "grad_norm": 185.8600616455078,
      "learning_rate": 5.0480000000000005e-05,
      "loss": 8.1543,
      "step": 640
    },
    {
      "epoch": 0.027663988934404426,
      "grad_norm": 210.5782470703125,
      "learning_rate": 5.1280000000000004e-05,
      "loss": 8.0605,
      "step": 650
    },
    {
      "epoch": 0.028089588764164494,
      "grad_norm": 244.0819549560547,
      "learning_rate": 5.208000000000001e-05,
      "loss": 7.9563,
      "step": 660
    },
    {
      "epoch": 0.028515188593924563,
      "grad_norm": 226.42645263671875,
      "learning_rate": 5.288000000000001e-05,
      "loss": 7.946,
      "step": 670
    },
    {
      "epoch": 0.02894078842368463,
      "grad_norm": 297.0813903808594,
      "learning_rate": 5.368000000000001e-05,
      "loss": 7.8138,
      "step": 680
    },
    {
      "epoch": 0.0293663882534447,
      "grad_norm": 250.51219177246094,
      "learning_rate": 5.448e-05,
      "loss": 7.9005,
      "step": 690
    },
    {
      "epoch": 0.029791988083204768,
      "grad_norm": 215.31597900390625,
      "learning_rate": 5.528e-05,
      "loss": 7.8383,
      "step": 700
    },
    {
      "epoch": 0.030217587912964836,
      "grad_norm": 190.99282836914062,
      "learning_rate": 5.608e-05,
      "loss": 7.8832,
      "step": 710
    },
    {
      "epoch": 0.0306431877427249,
      "grad_norm": 220.77931213378906,
      "learning_rate": 5.688e-05,
      "loss": 7.6152,
      "step": 720
    },
    {
      "epoch": 0.03106878757248497,
      "grad_norm": 239.42454528808594,
      "learning_rate": 5.7680000000000003e-05,
      "loss": 7.8036,
      "step": 730
    },
    {
      "epoch": 0.03149438740224504,
      "grad_norm": 184.58163452148438,
      "learning_rate": 5.848e-05,
      "loss": 7.8012,
      "step": 740
    },
    {
      "epoch": 0.031919987232005106,
      "grad_norm": 201.47549438476562,
      "learning_rate": 5.928e-05,
      "loss": 7.6639,
      "step": 750
    },
    {
      "epoch": 0.03234558706176518,
      "grad_norm": 157.16506958007812,
      "learning_rate": 6.008e-05,
      "loss": 7.8203,
      "step": 760
    },
    {
      "epoch": 0.03277118689152524,
      "grad_norm": 236.1090545654297,
      "learning_rate": 6.088000000000001e-05,
      "loss": 7.6494,
      "step": 770
    },
    {
      "epoch": 0.03319678672128531,
      "grad_norm": 196.18592834472656,
      "learning_rate": 6.168e-05,
      "loss": 7.7588,
      "step": 780
    },
    {
      "epoch": 0.03362238655104538,
      "grad_norm": 172.52780151367188,
      "learning_rate": 6.248000000000001e-05,
      "loss": 7.65,
      "step": 790
    },
    {
      "epoch": 0.034047986380805445,
      "grad_norm": 167.19175720214844,
      "learning_rate": 6.328e-05,
      "loss": 7.5127,
      "step": 800
    },
    {
      "epoch": 0.03447358621056552,
      "grad_norm": 156.87774658203125,
      "learning_rate": 6.408000000000001e-05,
      "loss": 7.4108,
      "step": 810
    },
    {
      "epoch": 0.03489918604032558,
      "grad_norm": 159.38601684570312,
      "learning_rate": 6.488e-05,
      "loss": 7.437,
      "step": 820
    },
    {
      "epoch": 0.035324785870085654,
      "grad_norm": 153.8631134033203,
      "learning_rate": 6.568000000000001e-05,
      "loss": 7.6065,
      "step": 830
    },
    {
      "epoch": 0.03575038569984572,
      "grad_norm": 190.62391662597656,
      "learning_rate": 6.648e-05,
      "loss": 7.5105,
      "step": 840
    },
    {
      "epoch": 0.03617598552960579,
      "grad_norm": 185.58334350585938,
      "learning_rate": 6.727999999999999e-05,
      "loss": 7.3454,
      "step": 850
    },
    {
      "epoch": 0.036601585359365855,
      "grad_norm": 250.2914581298828,
      "learning_rate": 6.808e-05,
      "loss": 7.3132,
      "step": 860
    },
    {
      "epoch": 0.03702718518912593,
      "grad_norm": 146.8917999267578,
      "learning_rate": 6.888e-05,
      "loss": 7.2683,
      "step": 870
    },
    {
      "epoch": 0.03745278501888599,
      "grad_norm": 132.48252868652344,
      "learning_rate": 6.968e-05,
      "loss": 7.2115,
      "step": 880
    },
    {
      "epoch": 0.03787838484864606,
      "grad_norm": 124.25926208496094,
      "learning_rate": 7.048e-05,
      "loss": 7.2205,
      "step": 890
    },
    {
      "epoch": 0.03830398467840613,
      "grad_norm": 134.99722290039062,
      "learning_rate": 7.128000000000001e-05,
      "loss": 7.2713,
      "step": 900
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 426,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3172736067584e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}