{
  "best_global_step": 2500,
  "best_metric": 0.8020345252909776,
  "best_model_checkpoint": "voice_emotion_classification/checkpoint-2500",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008,
      "grad_norm": 1.4005043506622314,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.0903,
      "step": 1
    },
    {
      "epoch": 0.008,
      "grad_norm": 1.3180536031723022,
      "learning_rate": 6e-06,
      "loss": 2.0826,
      "step": 10
    },
    {
      "epoch": 0.016,
      "grad_norm": 1.0437175035476685,
      "learning_rate": 1.2e-05,
      "loss": 2.0693,
      "step": 20
    },
    {
      "epoch": 0.024,
      "grad_norm": 1.371071457862854,
      "learning_rate": 1.8e-05,
      "loss": 2.0463,
      "step": 30
    },
    {
      "epoch": 0.032,
      "grad_norm": 1.51685631275177,
      "learning_rate": 2.4e-05,
      "loss": 2.0423,
      "step": 40
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.4282890558242798,
      "learning_rate": 3e-05,
      "loss": 1.996,
      "step": 50
    },
    {
      "epoch": 0.048,
      "grad_norm": 1.860026478767395,
      "learning_rate": 2.991891891891892e-05,
      "loss": 1.9639,
      "step": 60
    },
    {
      "epoch": 0.056,
      "grad_norm": 2.121481418609619,
      "learning_rate": 2.983783783783784e-05,
      "loss": 1.9517,
      "step": 70
    },
    {
      "epoch": 0.064,
      "grad_norm": 2.056445837020874,
      "learning_rate": 2.9756756756756758e-05,
      "loss": 1.8765,
      "step": 80
    },
    {
      "epoch": 0.072,
      "grad_norm": 2.3928184509277344,
      "learning_rate": 2.9675675675675678e-05,
      "loss": 1.8703,
      "step": 90
    },
    {
      "epoch": 0.08,
      "grad_norm": 3.0733420848846436,
      "learning_rate": 2.9594594594594598e-05,
      "loss": 1.853,
      "step": 100
    },
    {
      "epoch": 0.088,
      "grad_norm": 2.88864803314209,
      "learning_rate": 2.9513513513513514e-05,
      "loss": 1.7652,
      "step": 110
    },
    {
      "epoch": 0.096,
      "grad_norm": 2.9048268795013428,
      "learning_rate": 2.943243243243243e-05,
      "loss": 1.7984,
      "step": 120
    },
    {
      "epoch": 0.104,
      "grad_norm": 2.6991426944732666,
      "learning_rate": 2.935135135135135e-05,
      "loss": 1.6869,
      "step": 130
    },
    {
      "epoch": 0.112,
      "grad_norm": 2.4570231437683105,
      "learning_rate": 2.927027027027027e-05,
      "loss": 1.7812,
      "step": 140
    },
    {
      "epoch": 0.12,
      "grad_norm": 4.502678871154785,
      "learning_rate": 2.918918918918919e-05,
      "loss": 1.8444,
      "step": 150
    },
    {
      "epoch": 0.128,
      "grad_norm": 3.117838144302368,
      "learning_rate": 2.9108108108108108e-05,
      "loss": 1.7544,
      "step": 160
    },
    {
      "epoch": 0.136,
      "grad_norm": 2.812086343765259,
      "learning_rate": 2.9027027027027028e-05,
      "loss": 1.638,
      "step": 170
    },
    {
      "epoch": 0.144,
      "grad_norm": 3.23271107673645,
      "learning_rate": 2.8954054054054057e-05,
      "loss": 1.7026,
      "step": 180
    },
    {
      "epoch": 0.152,
      "grad_norm": 3.975172996520996,
      "learning_rate": 2.8872972972972977e-05,
      "loss": 1.6715,
      "step": 190
    },
    {
      "epoch": 0.16,
      "grad_norm": 3.8965938091278076,
      "learning_rate": 2.879189189189189e-05,
      "loss": 1.6804,
      "step": 200
    },
    {
      "epoch": 0.168,
      "grad_norm": 4.267274856567383,
      "learning_rate": 2.871081081081081e-05,
      "loss": 1.6587,
      "step": 210
    },
    {
      "epoch": 0.176,
      "grad_norm": 3.524360179901123,
      "learning_rate": 2.862972972972973e-05,
      "loss": 1.4811,
      "step": 220
    },
    {
      "epoch": 0.184,
      "grad_norm": 3.266697883605957,
      "learning_rate": 2.854864864864865e-05,
      "loss": 1.672,
      "step": 230
    },
    {
      "epoch": 0.192,
      "grad_norm": 5.3684186935424805,
      "learning_rate": 2.8467567567567567e-05,
      "loss": 1.5284,
      "step": 240
    },
    {
      "epoch": 0.2,
      "grad_norm": 3.898176431655884,
      "learning_rate": 2.8386486486486487e-05,
      "loss": 1.5774,
      "step": 250
    },
    {
      "epoch": 0.208,
      "grad_norm": 3.189732074737549,
      "learning_rate": 2.8305405405405407e-05,
      "loss": 1.4874,
      "step": 260
    },
    {
      "epoch": 0.216,
      "grad_norm": 3.274244785308838,
      "learning_rate": 2.8224324324324327e-05,
      "loss": 1.5098,
      "step": 270
    },
    {
      "epoch": 0.224,
      "grad_norm": 5.691224098205566,
      "learning_rate": 2.8143243243243244e-05,
      "loss": 1.509,
      "step": 280
    },
    {
      "epoch": 0.232,
      "grad_norm": 6.856773376464844,
      "learning_rate": 2.8062162162162164e-05,
      "loss": 1.4558,
      "step": 290
    },
    {
      "epoch": 0.24,
      "grad_norm": 7.078716278076172,
      "learning_rate": 2.7981081081081084e-05,
      "loss": 1.5298,
      "step": 300
    },
    {
      "epoch": 0.248,
      "grad_norm": 4.4305100440979,
      "learning_rate": 2.79e-05,
      "loss": 1.3387,
      "step": 310
    },
    {
      "epoch": 0.256,
      "grad_norm": 10.400449752807617,
      "learning_rate": 2.7818918918918917e-05,
      "loss": 1.4501,
      "step": 320
    },
    {
      "epoch": 0.264,
      "grad_norm": 5.316948890686035,
      "learning_rate": 2.7737837837837837e-05,
      "loss": 1.367,
      "step": 330
    },
    {
      "epoch": 0.272,
      "grad_norm": 9.753177642822266,
      "learning_rate": 2.7656756756756757e-05,
      "loss": 1.4684,
      "step": 340
    },
    {
      "epoch": 0.28,
      "grad_norm": 8.100529670715332,
      "learning_rate": 2.7575675675675677e-05,
      "loss": 1.4175,
      "step": 350
    },
    {
      "epoch": 0.288,
      "grad_norm": 9.878854751586914,
      "learning_rate": 2.7494594594594594e-05,
      "loss": 1.308,
      "step": 360
    },
    {
      "epoch": 0.296,
      "grad_norm": 5.865877151489258,
      "learning_rate": 2.7413513513513514e-05,
      "loss": 1.3035,
      "step": 370
    },
    {
      "epoch": 0.304,
      "grad_norm": 7.870754241943359,
      "learning_rate": 2.7332432432432434e-05,
      "loss": 1.2915,
      "step": 380
    },
    {
      "epoch": 0.312,
      "grad_norm": 8.517908096313477,
      "learning_rate": 2.7251351351351354e-05,
      "loss": 1.4318,
      "step": 390
    },
    {
      "epoch": 0.32,
      "grad_norm": 4.7960309982299805,
      "learning_rate": 2.717027027027027e-05,
      "loss": 1.3154,
      "step": 400
    },
    {
      "epoch": 0.328,
      "grad_norm": 5.629390716552734,
      "learning_rate": 2.708918918918919e-05,
      "loss": 1.3433,
      "step": 410
    },
    {
      "epoch": 0.336,
      "grad_norm": 8.473249435424805,
      "learning_rate": 2.700810810810811e-05,
      "loss": 1.1474,
      "step": 420
    },
    {
      "epoch": 0.344,
      "grad_norm": 3.652617931365967,
      "learning_rate": 2.6927027027027028e-05,
      "loss": 1.3247,
      "step": 430
    },
    {
      "epoch": 0.352,
      "grad_norm": 4.9890055656433105,
      "learning_rate": 2.6845945945945944e-05,
      "loss": 1.3347,
      "step": 440
    },
    {
      "epoch": 0.36,
      "grad_norm": 5.2355055809021,
      "learning_rate": 2.6764864864864864e-05,
      "loss": 1.0932,
      "step": 450
    },
    {
      "epoch": 0.368,
      "grad_norm": 6.325026512145996,
      "learning_rate": 2.6683783783783785e-05,
      "loss": 1.4873,
      "step": 460
    },
    {
      "epoch": 0.376,
      "grad_norm": 6.78115701675415,
      "learning_rate": 2.6602702702702705e-05,
      "loss": 1.2311,
      "step": 470
    },
    {
      "epoch": 0.384,
      "grad_norm": 4.194353103637695,
      "learning_rate": 2.652162162162162e-05,
      "loss": 1.2493,
      "step": 480
    },
    {
      "epoch": 0.392,
      "grad_norm": 3.8817057609558105,
      "learning_rate": 2.644054054054054e-05,
      "loss": 1.1237,
      "step": 490
    },
    {
      "epoch": 0.4,
      "grad_norm": 6.7539520263671875,
      "learning_rate": 2.635945945945946e-05,
      "loss": 1.1135,
      "step": 500
    },
    {
      "epoch": 0.408,
      "grad_norm": 9.044737815856934,
      "learning_rate": 2.627837837837838e-05,
      "loss": 1.2459,
      "step": 510
    },
    {
      "epoch": 0.416,
      "grad_norm": 15.829017639160156,
      "learning_rate": 2.6197297297297298e-05,
      "loss": 1.2803,
      "step": 520
    },
    {
      "epoch": 0.424,
      "grad_norm": 10.789520263671875,
      "learning_rate": 2.6116216216216218e-05,
      "loss": 1.1912,
      "step": 530
    },
    {
      "epoch": 0.432,
      "grad_norm": 5.011368274688721,
      "learning_rate": 2.6035135135135135e-05,
      "loss": 1.0143,
      "step": 540
    },
    {
      "epoch": 0.44,
      "grad_norm": 8.985868453979492,
      "learning_rate": 2.5954054054054055e-05,
      "loss": 1.118,
      "step": 550
    },
    {
      "epoch": 0.448,
      "grad_norm": 6.862995147705078,
      "learning_rate": 2.587297297297297e-05,
      "loss": 1.1269,
      "step": 560
    },
    {
      "epoch": 0.456,
      "grad_norm": 10.972336769104004,
      "learning_rate": 2.579189189189189e-05,
      "loss": 1.1591,
      "step": 570
    },
    {
      "epoch": 0.464,
      "grad_norm": 8.179327011108398,
      "learning_rate": 2.5710810810810812e-05,
      "loss": 1.154,
      "step": 580
    },
    {
      "epoch": 0.472,
      "grad_norm": 11.713990211486816,
      "learning_rate": 2.5629729729729732e-05,
      "loss": 1.0995,
      "step": 590
    },
    {
      "epoch": 0.48,
      "grad_norm": 10.86710262298584,
      "learning_rate": 2.554864864864865e-05,
      "loss": 1.1544,
      "step": 600
    },
    {
      "epoch": 0.488,
      "grad_norm": 6.228063106536865,
      "learning_rate": 2.546756756756757e-05,
      "loss": 1.2395,
      "step": 610
    },
    {
      "epoch": 0.496,
      "grad_norm": 12.631518363952637,
      "learning_rate": 2.538648648648649e-05,
      "loss": 1.0992,
      "step": 620
    },
    {
      "epoch": 0.504,
      "grad_norm": 7.058006763458252,
      "learning_rate": 2.530540540540541e-05,
      "loss": 1.194,
      "step": 630
    },
    {
      "epoch": 0.512,
      "grad_norm": 5.026750087738037,
      "learning_rate": 2.5224324324324325e-05,
      "loss": 1.103,
      "step": 640
    },
    {
      "epoch": 0.52,
      "grad_norm": 7.1134843826293945,
      "learning_rate": 2.5143243243243242e-05,
      "loss": 0.9427,
      "step": 650
    },
    {
      "epoch": 0.528,
      "grad_norm": 7.147433280944824,
      "learning_rate": 2.5062162162162162e-05,
      "loss": 0.9881,
      "step": 660
    },
    {
      "epoch": 0.536,
      "grad_norm": 6.535639762878418,
      "learning_rate": 2.4981081081081082e-05,
      "loss": 1.1143,
      "step": 670
    },
    {
      "epoch": 0.544,
      "grad_norm": 10.878937721252441,
      "learning_rate": 2.49e-05,
      "loss": 0.8909,
      "step": 680
    },
    {
      "epoch": 0.552,
      "grad_norm": 5.79094934463501,
      "learning_rate": 2.481891891891892e-05,
      "loss": 0.9728,
      "step": 690
    },
    {
      "epoch": 0.56,
      "grad_norm": 6.935592174530029,
      "learning_rate": 2.473783783783784e-05,
      "loss": 1.0735,
      "step": 700
    },
    {
      "epoch": 0.568,
      "grad_norm": 5.661824703216553,
      "learning_rate": 2.465675675675676e-05,
      "loss": 1.0012,
      "step": 710
    },
    {
      "epoch": 0.576,
      "grad_norm": 13.233421325683594,
      "learning_rate": 2.4575675675675676e-05,
      "loss": 1.0315,
      "step": 720
    },
    {
      "epoch": 0.584,
      "grad_norm": 9.292459487915039,
      "learning_rate": 2.4494594594594596e-05,
      "loss": 0.9547,
      "step": 730
    },
    {
      "epoch": 0.592,
      "grad_norm": 13.138367652893066,
      "learning_rate": 2.442162162162162e-05,
      "loss": 0.9379,
      "step": 740
    },
    {
      "epoch": 0.6,
      "grad_norm": 13.352531433105469,
      "learning_rate": 2.434054054054054e-05,
      "loss": 0.9484,
      "step": 750
    },
    {
      "epoch": 0.608,
      "grad_norm": 11.993139266967773,
      "learning_rate": 2.4259459459459458e-05,
      "loss": 1.1064,
      "step": 760
    },
    {
      "epoch": 0.616,
      "grad_norm": 12.132452011108398,
      "learning_rate": 2.4178378378378378e-05,
      "loss": 1.1363,
      "step": 770
    },
    {
      "epoch": 0.624,
      "grad_norm": 13.944737434387207,
      "learning_rate": 2.4097297297297298e-05,
      "loss": 0.9835,
      "step": 780
    },
    {
      "epoch": 0.632,
      "grad_norm": 6.077609062194824,
      "learning_rate": 2.4016216216216218e-05,
      "loss": 0.8391,
      "step": 790
    },
    {
      "epoch": 0.64,
      "grad_norm": 7.873855113983154,
      "learning_rate": 2.3935135135135135e-05,
      "loss": 0.7772,
      "step": 800
    },
    {
      "epoch": 0.648,
      "grad_norm": 13.312115669250488,
      "learning_rate": 2.3854054054054055e-05,
      "loss": 1.0117,
      "step": 810
    },
    {
      "epoch": 0.656,
      "grad_norm": 9.016510963439941,
      "learning_rate": 2.3772972972972975e-05,
      "loss": 0.9353,
      "step": 820
    },
    {
      "epoch": 0.664,
      "grad_norm": 8.618375778198242,
      "learning_rate": 2.3691891891891895e-05,
      "loss": 0.9598,
      "step": 830
    },
    {
      "epoch": 0.672,
      "grad_norm": 10.867205619812012,
      "learning_rate": 2.361081081081081e-05,
      "loss": 0.8726,
      "step": 840
    },
    {
      "epoch": 0.68,
      "grad_norm": 13.182415962219238,
      "learning_rate": 2.3529729729729728e-05,
      "loss": 0.9202,
      "step": 850
    },
    {
      "epoch": 0.688,
      "grad_norm": 12.405129432678223,
      "learning_rate": 2.3448648648648648e-05,
      "loss": 0.8795,
      "step": 860
    },
    {
      "epoch": 0.696,
      "grad_norm": 8.207524299621582,
      "learning_rate": 2.3367567567567568e-05,
      "loss": 0.8015,
      "step": 870
    },
    {
      "epoch": 0.704,
      "grad_norm": 15.442817687988281,
      "learning_rate": 2.3286486486486485e-05,
      "loss": 0.9932,
      "step": 880
    },
    {
      "epoch": 0.712,
      "grad_norm": 13.388226509094238,
      "learning_rate": 2.3205405405405405e-05,
      "loss": 0.87,
      "step": 890
    },
    {
      "epoch": 0.72,
      "grad_norm": 8.635920524597168,
      "learning_rate": 2.3124324324324325e-05,
      "loss": 0.7842,
      "step": 900
    },
    {
      "epoch": 0.728,
      "grad_norm": 11.66073989868164,
      "learning_rate": 2.3043243243243245e-05,
      "loss": 0.9023,
      "step": 910
    },
    {
      "epoch": 0.736,
      "grad_norm": 12.954612731933594,
      "learning_rate": 2.2962162162162162e-05,
      "loss": 1.0076,
      "step": 920
    },
    {
      "epoch": 0.744,
      "grad_norm": 11.18680191040039,
      "learning_rate": 2.2881081081081082e-05,
      "loss": 1.1349,
      "step": 930
    },
    {
      "epoch": 0.752,
      "grad_norm": 8.514711380004883,
      "learning_rate": 2.2800000000000002e-05,
      "loss": 0.9604,
      "step": 940
    },
    {
      "epoch": 0.76,
      "grad_norm": 4.436418056488037,
      "learning_rate": 2.2718918918918922e-05,
      "loss": 0.9632,
      "step": 950
    },
    {
      "epoch": 0.768,
      "grad_norm": 10.213781356811523,
      "learning_rate": 2.263783783783784e-05,
      "loss": 0.8139,
      "step": 960
    },
    {
      "epoch": 0.776,
      "grad_norm": 9.987252235412598,
      "learning_rate": 2.2556756756756755e-05,
      "loss": 0.8276,
      "step": 970
    },
    {
      "epoch": 0.784,
      "grad_norm": 12.511467933654785,
      "learning_rate": 2.2475675675675675e-05,
      "loss": 0.8709,
      "step": 980
    },
    {
      "epoch": 0.792,
      "grad_norm": 8.908098220825195,
      "learning_rate": 2.2394594594594595e-05,
      "loss": 0.8812,
      "step": 990
    },
    {
      "epoch": 0.8,
      "grad_norm": 10.62246322631836,
      "learning_rate": 2.2313513513513512e-05,
      "loss": 0.9733,
      "step": 1000
    },
    {
      "epoch": 0.808,
      "grad_norm": 14.651544570922852,
      "learning_rate": 2.2232432432432432e-05,
      "loss": 1.0309,
      "step": 1010
    },
    {
      "epoch": 0.816,
      "grad_norm": 19.1525936126709,
      "learning_rate": 2.2151351351351352e-05,
      "loss": 0.8808,
      "step": 1020
    },
    {
      "epoch": 0.824,
      "grad_norm": 7.289106369018555,
      "learning_rate": 2.2070270270270272e-05,
      "loss": 0.9126,
      "step": 1030
    },
    {
      "epoch": 0.832,
      "grad_norm": 5.375001907348633,
      "learning_rate": 2.198918918918919e-05,
      "loss": 0.847,
      "step": 1040
    },
    {
      "epoch": 0.84,
      "grad_norm": 8.623431205749512,
      "learning_rate": 2.190810810810811e-05,
      "loss": 0.9139,
      "step": 1050
    },
    {
      "epoch": 0.848,
      "grad_norm": 6.639071941375732,
      "learning_rate": 2.182702702702703e-05,
      "loss": 0.9345,
      "step": 1060
    },
    {
      "epoch": 0.856,
      "grad_norm": 7.635943412780762,
      "learning_rate": 2.174594594594595e-05,
      "loss": 0.8134,
      "step": 1070
    },
    {
      "epoch": 0.864,
      "grad_norm": 12.048315048217773,
      "learning_rate": 2.1664864864864862e-05,
      "loss": 0.6728,
      "step": 1080
    },
    {
      "epoch": 0.872,
      "grad_norm": 13.869949340820312,
      "learning_rate": 2.1583783783783783e-05,
      "loss": 0.8256,
      "step": 1090
    },
    {
      "epoch": 0.88,
      "grad_norm": 26.233325958251953,
      "learning_rate": 2.1502702702702703e-05,
      "loss": 0.7044,
      "step": 1100
    },
    {
      "epoch": 0.888,
      "grad_norm": 7.98716926574707,
      "learning_rate": 2.1421621621621623e-05,
      "loss": 0.7398,
      "step": 1110
    },
    {
      "epoch": 0.896,
      "grad_norm": 13.682205200195312,
      "learning_rate": 2.134054054054054e-05,
      "loss": 0.7522,
      "step": 1120
    },
    {
      "epoch": 0.904,
      "grad_norm": 9.086796760559082,
      "learning_rate": 2.125945945945946e-05,
      "loss": 0.8574,
      "step": 1130
    },
    {
      "epoch": 0.912,
      "grad_norm": 10.3043851852417,
      "learning_rate": 2.117837837837838e-05,
      "loss": 0.8005,
      "step": 1140
    },
    {
      "epoch": 0.92,
      "grad_norm": 12.477950096130371,
      "learning_rate": 2.10972972972973e-05,
      "loss": 0.8436,
      "step": 1150
    },
    {
      "epoch": 0.928,
      "grad_norm": 16.634178161621094,
      "learning_rate": 2.1016216216216216e-05,
      "loss": 0.6515,
      "step": 1160
    },
    {
      "epoch": 0.936,
      "grad_norm": 11.066425323486328,
      "learning_rate": 2.0935135135135136e-05,
      "loss": 0.8689,
      "step": 1170
    },
    {
      "epoch": 0.944,
      "grad_norm": 19.47179412841797,
      "learning_rate": 2.0854054054054056e-05,
      "loss": 0.6605,
      "step": 1180
    },
    {
      "epoch": 0.952,
      "grad_norm": 3.917236804962158,
      "learning_rate": 2.0772972972972973e-05,
      "loss": 0.6826,
      "step": 1190
    },
    {
      "epoch": 0.96,
      "grad_norm": 16.43979263305664,
      "learning_rate": 2.069189189189189e-05,
      "loss": 0.7731,
      "step": 1200
    },
    {
      "epoch": 0.968,
      "grad_norm": 6.7848711013793945,
      "learning_rate": 2.061081081081081e-05,
      "loss": 0.705,
      "step": 1210
    },
    {
      "epoch": 0.976,
      "grad_norm": 7.472936153411865,
      "learning_rate": 2.052972972972973e-05,
      "loss": 0.7663,
      "step": 1220
    },
    {
      "epoch": 0.984,
      "grad_norm": 5.729743957519531,
      "learning_rate": 2.044864864864865e-05,
      "loss": 0.9337,
      "step": 1230
    },
    {
      "epoch": 0.992,
      "grad_norm": 6.306894302368164,
      "learning_rate": 2.0367567567567567e-05,
      "loss": 0.7655,
      "step": 1240
    },
    {
      "epoch": 1.0,
      "grad_norm": 17.98261260986328,
      "learning_rate": 2.0286486486486487e-05,
      "loss": 0.8202,
      "step": 1250
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7668834417208604,
      "eval_f1": 0.7589222033223469,
      "eval_loss": 0.7338727712631226,
      "eval_model_preparation_time": 0.0029,
      "eval_runtime": 59.9403,
      "eval_samples_per_second": 33.35,
      "eval_steps_per_second": 4.171,
      "step": 1250
    },
    {
      "epoch": 1.008,
      "grad_norm": 3.764857292175293,
      "learning_rate": 2.0205405405405407e-05,
      "loss": 0.6991,
      "step": 1260
    },
    {
      "epoch": 1.016,
      "grad_norm": 12.638517379760742,
      "learning_rate": 2.0124324324324327e-05,
      "loss": 0.7653,
      "step": 1270
    },
    {
      "epoch": 1.024,
      "grad_norm": 17.76312255859375,
      "learning_rate": 2.0043243243243243e-05,
      "loss": 0.8033,
      "step": 1280
    },
    {
      "epoch": 1.032,
      "grad_norm": 11.941933631896973,
      "learning_rate": 1.9962162162162163e-05,
      "loss": 0.699,
      "step": 1290
    },
    {
      "epoch": 1.04,
      "grad_norm": 17.107053756713867,
      "learning_rate": 1.988108108108108e-05,
      "loss": 0.706,
      "step": 1300
    },
    {
      "epoch": 1.048,
      "grad_norm": 6.369427680969238,
      "learning_rate": 1.98e-05,
      "loss": 0.6494,
      "step": 1310
    },
    {
      "epoch": 1.056,
      "grad_norm": 7.1872477531433105,
      "learning_rate": 1.9718918918918917e-05,
      "loss": 0.5989,
      "step": 1320
    },
    {
      "epoch": 1.064,
      "grad_norm": 3.7603728771209717,
      "learning_rate": 1.9637837837837837e-05,
      "loss": 0.7582,
      "step": 1330
    },
    {
      "epoch": 1.072,
      "grad_norm": 10.045304298400879,
      "learning_rate": 1.9556756756756757e-05,
      "loss": 0.7192,
      "step": 1340
    },
    {
      "epoch": 1.08,
      "grad_norm": 14.639888763427734,
      "learning_rate": 1.9475675675675677e-05,
      "loss": 0.7959,
      "step": 1350
    },
    {
      "epoch": 1.088,
      "grad_norm": 8.216081619262695,
      "learning_rate": 1.9394594594594594e-05,
      "loss": 0.6062,
      "step": 1360
    },
    {
      "epoch": 1.096,
      "grad_norm": 5.784476280212402,
      "learning_rate": 1.9313513513513514e-05,
      "loss": 0.541,
      "step": 1370
    },
    {
      "epoch": 1.104,
      "grad_norm": 5.356358051300049,
      "learning_rate": 1.9232432432432434e-05,
      "loss": 0.6993,
      "step": 1380
    },
    {
      "epoch": 1.112,
      "grad_norm": 17.11981773376465,
      "learning_rate": 1.9151351351351354e-05,
      "loss": 0.7217,
      "step": 1390
    },
    {
      "epoch": 1.12,
      "grad_norm": 15.52505111694336,
      "learning_rate": 1.907027027027027e-05,
      "loss": 0.548,
      "step": 1400
    },
    {
      "epoch": 1.1280000000000001,
      "grad_norm": 12.326894760131836,
      "learning_rate": 1.8989189189189187e-05,
      "loss": 0.7058,
      "step": 1410
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 12.889031410217285,
      "learning_rate": 1.8908108108108107e-05,
      "loss": 0.7748,
      "step": 1420
    },
    {
      "epoch": 1.144,
      "grad_norm": 12.953654289245605,
      "learning_rate": 1.8827027027027027e-05,
      "loss": 0.7251,
      "step": 1430
    },
    {
      "epoch": 1.152,
      "grad_norm": 2.564222812652588,
      "learning_rate": 1.8745945945945944e-05,
      "loss": 0.551,
      "step": 1440
    },
    {
      "epoch": 1.16,
      "grad_norm": 9.111184120178223,
      "learning_rate": 1.8664864864864864e-05,
      "loss": 0.5548,
      "step": 1450
    },
    {
      "epoch": 1.168,
      "grad_norm": 7.713393211364746,
      "learning_rate": 1.8583783783783784e-05,
      "loss": 0.564,
      "step": 1460
    },
    {
      "epoch": 1.176,
      "grad_norm": 8.282889366149902,
      "learning_rate": 1.8502702702702704e-05,
      "loss": 0.7312,
      "step": 1470
    },
    {
      "epoch": 1.184,
      "grad_norm": 15.445865631103516,
      "learning_rate": 1.842162162162162e-05,
      "loss": 0.6974,
      "step": 1480
    },
    {
      "epoch": 1.192,
      "grad_norm": 6.040890693664551,
      "learning_rate": 1.834054054054054e-05,
      "loss": 0.6808,
      "step": 1490
    },
    {
      "epoch": 1.2,
      "grad_norm": 17.368532180786133,
      "learning_rate": 1.825945945945946e-05,
      "loss": 0.5695,
      "step": 1500
    },
    {
      "epoch": 1.208,
      "grad_norm": 11.174856185913086,
      "learning_rate": 1.817837837837838e-05,
      "loss": 0.8114,
      "step": 1510
    },
    {
      "epoch": 1.216,
      "grad_norm": 18.861087799072266,
      "learning_rate": 1.8097297297297298e-05,
      "loss": 0.601,
      "step": 1520
    },
    {
      "epoch": 1.224,
      "grad_norm": 4.157520771026611,
      "learning_rate": 1.8016216216216214e-05,
      "loss": 0.6195,
      "step": 1530
    },
    {
      "epoch": 1.232,
      "grad_norm": 40.063621520996094,
      "learning_rate": 1.7935135135135134e-05,
      "loss": 0.6502,
      "step": 1540
    },
    {
      "epoch": 1.24,
      "grad_norm": 12.99301528930664,
      "learning_rate": 1.7854054054054055e-05,
      "loss": 0.5463,
      "step": 1550
    },
    {
      "epoch": 1.248,
      "grad_norm": 3.057586908340454,
      "learning_rate": 1.7772972972972975e-05,
      "loss": 0.5025,
      "step": 1560
    },
    {
      "epoch": 1.256,
      "grad_norm": 7.806783199310303,
      "learning_rate": 1.769189189189189e-05,
      "loss": 0.5544,
      "step": 1570
    },
    {
      "epoch": 1.264,
      "grad_norm": 6.477509498596191,
      "learning_rate": 1.761081081081081e-05,
      "loss": 0.5447,
      "step": 1580
    },
    {
      "epoch": 1.272,
      "grad_norm": 28.918643951416016,
      "learning_rate": 1.752972972972973e-05,
      "loss": 0.7803,
      "step": 1590
    },
    {
      "epoch": 1.28,
      "grad_norm": 23.26552391052246,
      "learning_rate": 1.744864864864865e-05,
      "loss": 0.7442,
      "step": 1600
    },
    {
      "epoch": 1.288,
      "grad_norm": 24.359582901000977,
      "learning_rate": 1.7367567567567568e-05,
      "loss": 0.705,
      "step": 1610
    },
    {
      "epoch": 1.296,
      "grad_norm": 20.904409408569336,
      "learning_rate": 1.7286486486486488e-05,
      "loss": 0.7149,
      "step": 1620
    },
    {
      "epoch": 1.304,
      "grad_norm": 11.675884246826172,
      "learning_rate": 1.7205405405405408e-05,
      "loss": 0.5916,
      "step": 1630
    },
    {
      "epoch": 1.312,
      "grad_norm": 19.712337493896484,
      "learning_rate": 1.7124324324324325e-05,
      "loss": 0.59,
      "step": 1640
    },
    {
      "epoch": 1.32,
      "grad_norm": 1.4685373306274414,
      "learning_rate": 1.704324324324324e-05,
      "loss": 0.6127,
      "step": 1650
    },
    {
      "epoch": 1.328,
      "grad_norm": 13.145341873168945,
      "learning_rate": 1.696216216216216e-05,
      "loss": 0.5311,
      "step": 1660
    },
    {
      "epoch": 1.336,
      "grad_norm": 33.24889373779297,
      "learning_rate": 1.6881081081081082e-05,
      "loss": 0.539,
      "step": 1670
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 2.730905771255493,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 0.6207,
      "step": 1680
    },
    {
      "epoch": 1.3519999999999999,
      "grad_norm": 18.928560256958008,
      "learning_rate": 1.671891891891892e-05,
      "loss": 0.5226,
      "step": 1690
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 6.420986175537109,
      "learning_rate": 1.663783783783784e-05,
      "loss": 0.5054,
      "step": 1700
    },
    {
      "epoch": 1.3679999999999999,
      "grad_norm": 10.68362045288086,
      "learning_rate": 1.655675675675676e-05,
      "loss": 0.553,
      "step": 1710
    },
    {
      "epoch": 1.376,
      "grad_norm": 23.89041519165039,
      "learning_rate": 1.647567567567568e-05,
      "loss": 0.585,
      "step": 1720
    },
    {
      "epoch": 1.384,
      "grad_norm": 0.6503021717071533,
      "learning_rate": 1.6394594594594595e-05,
      "loss": 0.5443,
      "step": 1730
    },
    {
      "epoch": 1.392,
      "grad_norm": 16.69384002685547,
      "learning_rate": 1.6313513513513515e-05,
      "loss": 0.777,
      "step": 1740
    },
    {
      "epoch": 1.4,
      "grad_norm": 11.571426391601562,
      "learning_rate": 1.6232432432432432e-05,
      "loss": 0.7578,
      "step": 1750
    },
    {
      "epoch": 1.408,
      "grad_norm": 19.505590438842773,
      "learning_rate": 1.6151351351351352e-05,
      "loss": 0.755,
      "step": 1760
    },
    {
      "epoch": 1.416,
      "grad_norm": 12.909994125366211,
      "learning_rate": 1.607027027027027e-05,
      "loss": 0.5617,
      "step": 1770
    },
    {
      "epoch": 1.424,
      "grad_norm": 10.301375389099121,
      "learning_rate": 1.598918918918919e-05,
      "loss": 0.7985,
      "step": 1780
    },
    {
      "epoch": 1.432,
      "grad_norm": 20.1243839263916,
      "learning_rate": 1.590810810810811e-05,
      "loss": 0.6966,
      "step": 1790
    },
    {
      "epoch": 1.44,
      "grad_norm": 5.007569789886475,
      "learning_rate": 1.582702702702703e-05,
      "loss": 0.5544,
      "step": 1800
    },
    {
      "epoch": 1.448,
      "grad_norm": 2.8352081775665283,
      "learning_rate": 1.5745945945945946e-05,
      "loss": 0.8716,
      "step": 1810
    },
    {
      "epoch": 1.456,
      "grad_norm": 8.246051788330078,
      "learning_rate": 1.5664864864864866e-05,
      "loss": 0.449,
      "step": 1820
    },
    {
      "epoch": 1.464,
      "grad_norm": 7.072529315948486,
      "learning_rate": 1.5583783783783786e-05,
      "loss": 0.6345,
      "step": 1830
    },
    {
      "epoch": 1.472,
      "grad_norm": 11.075968742370605,
      "learning_rate": 1.5502702702702706e-05,
      "loss": 0.5029,
      "step": 1840
    },
    {
      "epoch": 1.48,
      "grad_norm": 10.411526679992676,
      "learning_rate": 1.5421621621621622e-05,
      "loss": 0.4708,
      "step": 1850
    },
    {
      "epoch": 1.488,
      "grad_norm": 13.274471282958984,
      "learning_rate": 1.534054054054054e-05,
      "loss": 0.4823,
      "step": 1860
    },
    {
      "epoch": 1.496,
      "grad_norm": 8.039985656738281,
      "learning_rate": 1.525945945945946e-05,
      "loss": 0.5719,
      "step": 1870
    },
    {
      "epoch": 1.504,
      "grad_norm": 19.872621536254883,
      "learning_rate": 1.5178378378378381e-05,
      "loss": 0.7933,
      "step": 1880
    },
    {
      "epoch": 1.512,
      "grad_norm": 12.538918495178223,
      "learning_rate": 1.5097297297297296e-05,
      "loss": 0.4885,
      "step": 1890
    },
    {
      "epoch": 1.52,
      "grad_norm": 26.685623168945312,
      "learning_rate": 1.5016216216216216e-05,
      "loss": 0.6399,
      "step": 1900
    },
    {
      "epoch": 1.528,
      "grad_norm": 10.571418762207031,
      "learning_rate": 1.4935135135135136e-05,
      "loss": 0.6462,
      "step": 1910
    },
    {
      "epoch": 1.536,
      "grad_norm": 3.1144027709960938,
      "learning_rate": 1.4854054054054054e-05,
      "loss": 0.6041,
      "step": 1920
    },
    {
      "epoch": 1.544,
      "grad_norm": 5.647855758666992,
      "learning_rate": 1.4772972972972975e-05,
      "loss": 0.584,
      "step": 1930
    },
    {
      "epoch": 1.552,
      "grad_norm": 9.756006240844727,
      "learning_rate": 1.4691891891891893e-05,
      "loss": 0.3929,
      "step": 1940
    },
    {
      "epoch": 1.56,
      "grad_norm": 7.031187534332275,
      "learning_rate": 1.4610810810810811e-05,
      "loss": 0.5963,
      "step": 1950
    },
    {
      "epoch": 1.568,
      "grad_norm": 19.187641143798828,
      "learning_rate": 1.452972972972973e-05,
      "loss": 0.4967,
      "step": 1960
    },
    {
      "epoch": 1.576,
      "grad_norm": 16.660043716430664,
      "learning_rate": 1.444864864864865e-05,
      "loss": 0.632,
      "step": 1970
    },
    {
      "epoch": 1.584,
      "grad_norm": 15.292383193969727,
      "learning_rate": 1.4367567567567568e-05,
      "loss": 0.6671,
      "step": 1980
    },
    {
      "epoch": 1.592,
      "grad_norm": 15.64156436920166,
      "learning_rate": 1.4286486486486488e-05,
      "loss": 0.5182,
      "step": 1990
    },
    {
      "epoch": 1.6,
      "grad_norm": 12.81575870513916,
      "learning_rate": 1.4205405405405405e-05,
      "loss": 0.7377,
      "step": 2000
    },
    {
      "epoch": 1.608,
      "grad_norm": 28.722570419311523,
      "learning_rate": 1.4124324324324325e-05,
      "loss": 0.6432,
      "step": 2010
    },
    {
      "epoch": 1.616,
      "grad_norm": 9.101573944091797,
      "learning_rate": 1.4043243243243243e-05,
      "loss": 0.7597,
      "step": 2020
    },
    {
      "epoch": 1.624,
      "grad_norm": 18.51584815979004,
      "learning_rate": 1.3962162162162163e-05,
      "loss": 0.5169,
      "step": 2030
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 19.951353073120117,
      "learning_rate": 1.3881081081081082e-05,
      "loss": 0.6938,
      "step": 2040
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.7395208477973938,
      "learning_rate": 1.3800000000000002e-05,
      "loss": 0.5438,
      "step": 2050
    },
    {
      "epoch": 1.6480000000000001,
      "grad_norm": 23.373943328857422,
      "learning_rate": 1.3718918918918918e-05,
      "loss": 0.543,
      "step": 2060
    },
    {
      "epoch": 1.6560000000000001,
      "grad_norm": 13.313843727111816,
      "learning_rate": 1.3637837837837838e-05,
      "loss": 0.752,
      "step": 2070
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 19.967775344848633,
      "learning_rate": 1.3556756756756757e-05,
      "loss": 0.5858,
      "step": 2080
    },
    {
      "epoch": 1.6720000000000002,
      "grad_norm": 6.15806770324707,
      "learning_rate": 1.3475675675675677e-05,
      "loss": 0.6735,
      "step": 2090
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 20.810691833496094,
      "learning_rate": 1.3394594594594595e-05,
      "loss": 0.7207,
      "step": 2100
    },
    {
      "epoch": 1.688,
      "grad_norm": 21.559804916381836,
      "learning_rate": 1.3313513513513514e-05,
      "loss": 0.6681,
      "step": 2110
    },
    {
      "epoch": 1.696,
      "grad_norm": 5.827245235443115,
      "learning_rate": 1.3232432432432432e-05,
      "loss": 0.5774,
      "step": 2120
    },
    {
      "epoch": 1.704,
      "grad_norm": 4.7927069664001465,
      "learning_rate": 1.3151351351351352e-05,
      "loss": 0.6439,
      "step": 2130
    },
    {
      "epoch": 1.712,
      "grad_norm": 14.177338600158691,
      "learning_rate": 1.307027027027027e-05,
      "loss": 0.7137,
      "step": 2140
    },
    {
      "epoch": 1.72,
      "grad_norm": 14.718915939331055,
      "learning_rate": 1.298918918918919e-05,
      "loss": 0.5463,
      "step": 2150
    },
    {
      "epoch": 1.728,
      "grad_norm": 18.23885726928711,
      "learning_rate": 1.2908108108108109e-05,
      "loss": 0.6557,
      "step": 2160
    },
    {
      "epoch": 1.736,
      "grad_norm": 9.514300346374512,
      "learning_rate": 1.2827027027027027e-05,
      "loss": 0.5304,
      "step": 2170
    },
    {
      "epoch": 1.744,
      "grad_norm": 15.950238227844238,
      "learning_rate": 1.2745945945945946e-05,
      "loss": 0.721,
      "step": 2180
    },
    {
      "epoch": 1.752,
      "grad_norm": 5.722634315490723,
      "learning_rate": 1.2664864864864866e-05,
      "loss": 0.3436,
      "step": 2190
    },
    {
      "epoch": 1.76,
      "grad_norm": 11.308035850524902,
      "learning_rate": 1.2583783783783784e-05,
      "loss": 0.5269,
      "step": 2200
    },
    {
      "epoch": 1.768,
      "grad_norm": 5.413994789123535,
      "learning_rate": 1.2502702702702704e-05,
      "loss": 0.4461,
      "step": 2210
    },
    {
      "epoch": 1.776,
      "grad_norm": 29.982696533203125,
      "learning_rate": 1.2421621621621622e-05,
      "loss": 0.5942,
      "step": 2220
    },
    {
      "epoch": 1.784,
      "grad_norm": 25.45384979248047,
      "learning_rate": 1.234054054054054e-05,
      "loss": 0.5469,
      "step": 2230
    },
    {
      "epoch": 1.792,
      "grad_norm": 10.957773208618164,
      "learning_rate": 1.225945945945946e-05,
      "loss": 0.4809,
      "step": 2240
    },
    {
      "epoch": 1.8,
      "grad_norm": 11.609101295471191,
      "learning_rate": 1.217837837837838e-05,
      "loss": 0.73,
      "step": 2250
    },
    {
      "epoch": 1.808,
      "grad_norm": 14.325447082519531,
      "learning_rate": 1.2097297297297298e-05,
      "loss": 0.3926,
      "step": 2260
    },
    {
      "epoch": 1.8159999999999998,
      "grad_norm": 4.8160719871521,
      "learning_rate": 1.2016216216216218e-05,
      "loss": 0.5617,
      "step": 2270
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 6.287977695465088,
      "learning_rate": 1.1935135135135134e-05,
      "loss": 0.3482,
      "step": 2280
    },
    {
      "epoch": 1.8319999999999999,
      "grad_norm": 9.819110870361328,
      "learning_rate": 1.1854054054054054e-05,
      "loss": 0.5353,
      "step": 2290
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 7.572418689727783,
      "learning_rate": 1.1772972972972973e-05,
      "loss": 0.7756,
      "step": 2300
    },
    {
      "epoch": 1.8479999999999999,
      "grad_norm": 16.719934463500977,
      "learning_rate": 1.1691891891891893e-05,
      "loss": 0.6298,
      "step": 2310
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 18.21957778930664,
      "learning_rate": 1.1610810810810811e-05,
      "loss": 0.4695,
      "step": 2320
    },
    {
      "epoch": 1.8639999999999999,
      "grad_norm": 5.47652530670166,
      "learning_rate": 1.1529729729729731e-05,
      "loss": 0.2983,
      "step": 2330
    },
    {
      "epoch": 1.8719999999999999,
      "grad_norm": 22.044818878173828,
      "learning_rate": 1.1448648648648648e-05,
      "loss": 0.5972,
      "step": 2340
    },
    {
      "epoch": 1.88,
      "grad_norm": 26.34394645690918,
      "learning_rate": 1.1367567567567568e-05,
      "loss": 0.4404,
      "step": 2350
    },
    {
      "epoch": 1.888,
      "grad_norm": 21.979583740234375,
      "learning_rate": 1.1286486486486486e-05,
      "loss": 0.6474,
      "step": 2360
    },
    {
      "epoch": 1.896,
      "grad_norm": 15.81022834777832,
      "learning_rate": 1.1205405405405406e-05,
      "loss": 0.552,
      "step": 2370
    },
    {
      "epoch": 1.904,
      "grad_norm": 13.853069305419922,
      "learning_rate": 1.1124324324324325e-05,
      "loss": 0.5908,
      "step": 2380
    },
    {
      "epoch": 1.912,
      "grad_norm": 4.924503326416016,
      "learning_rate": 1.1043243243243243e-05,
      "loss": 0.3883,
      "step": 2390
    },
    {
      "epoch": 1.92,
      "grad_norm": 15.801043510437012,
      "learning_rate": 1.0962162162162162e-05,
      "loss": 0.4635,
      "step": 2400
    },
    {
      "epoch": 1.928,
      "grad_norm": 17.398475646972656,
      "learning_rate": 1.0881081081081082e-05,
      "loss": 0.5509,
      "step": 2410
    },
    {
      "epoch": 1.936,
      "grad_norm": 12.026921272277832,
      "learning_rate": 1.08e-05,
      "loss": 0.533,
      "step": 2420
    },
    {
      "epoch": 1.944,
      "grad_norm": 23.21822738647461,
      "learning_rate": 1.071891891891892e-05,
      "loss": 0.5655,
      "step": 2430
    },
    {
      "epoch": 1.952,
      "grad_norm": 9.777156829833984,
      "learning_rate": 1.0637837837837838e-05,
      "loss": 0.7364,
      "step": 2440
    },
    {
      "epoch": 1.96,
      "grad_norm": 17.892311096191406,
      "learning_rate": 1.0556756756756757e-05,
      "loss": 0.5123,
      "step": 2450
    },
    {
      "epoch": 1.968,
      "grad_norm": 10.79381275177002,
      "learning_rate": 1.0475675675675675e-05,
      "loss": 0.5601,
      "step": 2460
    },
    {
      "epoch": 1.976,
      "grad_norm": 16.45550537109375,
      "learning_rate": 1.0394594594594595e-05,
      "loss": 0.3604,
      "step": 2470
    },
    {
      "epoch": 1.984,
      "grad_norm": 4.945703506469727,
      "learning_rate": 1.0313513513513514e-05,
      "loss": 0.5801,
      "step": 2480
    },
    {
      "epoch": 1.992,
      "grad_norm": 7.19441556930542,
      "learning_rate": 1.0232432432432434e-05,
      "loss": 0.5552,
      "step": 2490
    },
    {
      "epoch": 2.0,
      "grad_norm": 16.103708267211914,
      "learning_rate": 1.0151351351351352e-05,
      "loss": 0.5873,
      "step": 2500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7983991995997999,
      "eval_f1": 0.8020345252909776,
      "eval_loss": 0.6678956747055054,
      "eval_model_preparation_time": 0.0029,
      "eval_runtime": 59.5494,
      "eval_samples_per_second": 33.569,
      "eval_steps_per_second": 4.198,
      "step": 2500
    }
  ],
  "logging_steps": 10,
  "max_steps": 3750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 8.83389772226827e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}