deberta-v3-base-company-names / trainer_state.json
nbroad's picture
nbroad HF staff
End of training
ac86cb6 verified
raw history blame
No virus
78.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 6378,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 8.77742946708464e-07,
"loss": 1.1515,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 2.1316614420062697e-06,
"loss": 1.0942,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 3.3855799373040753e-06,
"loss": 0.825,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 4.639498432601881e-06,
"loss": 0.5304,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 5.8934169278996865e-06,
"loss": 0.3473,
"step": 50
},
{
"epoch": 0.03,
"learning_rate": 7.147335423197492e-06,
"loss": 0.2823,
"step": 60
},
{
"epoch": 0.03,
"learning_rate": 8.4012539184953e-06,
"loss": 0.2224,
"step": 70
},
{
"epoch": 0.04,
"learning_rate": 9.655172413793105e-06,
"loss": 0.1987,
"step": 80
},
{
"epoch": 0.04,
"learning_rate": 1.0909090909090909e-05,
"loss": 0.1516,
"step": 90
},
{
"epoch": 0.05,
"learning_rate": 1.2163009404388715e-05,
"loss": 0.1241,
"step": 100
},
{
"epoch": 0.05,
"learning_rate": 1.341692789968652e-05,
"loss": 0.1199,
"step": 110
},
{
"epoch": 0.06,
"learning_rate": 1.4670846394984329e-05,
"loss": 0.1113,
"step": 120
},
{
"epoch": 0.06,
"learning_rate": 1.5924764890282133e-05,
"loss": 0.105,
"step": 130
},
{
"epoch": 0.07,
"learning_rate": 1.717868338557994e-05,
"loss": 0.0879,
"step": 140
},
{
"epoch": 0.07,
"learning_rate": 1.8432601880877744e-05,
"loss": 0.105,
"step": 150
},
{
"epoch": 0.08,
"learning_rate": 1.968652037617555e-05,
"loss": 0.1043,
"step": 160
},
{
"epoch": 0.08,
"learning_rate": 2.0940438871473355e-05,
"loss": 0.1107,
"step": 170
},
{
"epoch": 0.08,
"learning_rate": 2.2194357366771163e-05,
"loss": 0.1098,
"step": 180
},
{
"epoch": 0.09,
"learning_rate": 2.3448275862068967e-05,
"loss": 0.0981,
"step": 190
},
{
"epoch": 0.09,
"learning_rate": 2.4702194357366774e-05,
"loss": 0.0919,
"step": 200
},
{
"epoch": 0.1,
"learning_rate": 2.595611285266458e-05,
"loss": 0.0782,
"step": 210
},
{
"epoch": 0.1,
"learning_rate": 2.7210031347962385e-05,
"loss": 0.0843,
"step": 220
},
{
"epoch": 0.11,
"learning_rate": 2.8463949843260192e-05,
"loss": 0.1103,
"step": 230
},
{
"epoch": 0.11,
"learning_rate": 2.9717868338557996e-05,
"loss": 0.0937,
"step": 240
},
{
"epoch": 0.12,
"learning_rate": 3.097178683385581e-05,
"loss": 0.092,
"step": 250
},
{
"epoch": 0.12,
"learning_rate": 3.222570532915361e-05,
"loss": 0.0871,
"step": 260
},
{
"epoch": 0.13,
"learning_rate": 3.3479623824451415e-05,
"loss": 0.0908,
"step": 270
},
{
"epoch": 0.13,
"learning_rate": 3.4733542319749215e-05,
"loss": 0.0849,
"step": 280
},
{
"epoch": 0.14,
"learning_rate": 3.598746081504703e-05,
"loss": 0.0972,
"step": 290
},
{
"epoch": 0.14,
"learning_rate": 3.724137931034483e-05,
"loss": 0.0819,
"step": 300
},
{
"epoch": 0.15,
"learning_rate": 3.849529780564264e-05,
"loss": 0.085,
"step": 310
},
{
"epoch": 0.15,
"learning_rate": 3.974921630094044e-05,
"loss": 0.0736,
"step": 320
},
{
"epoch": 0.16,
"learning_rate": 4.1003134796238245e-05,
"loss": 0.0918,
"step": 330
},
{
"epoch": 0.16,
"learning_rate": 4.225705329153606e-05,
"loss": 0.087,
"step": 340
},
{
"epoch": 0.16,
"learning_rate": 4.351097178683386e-05,
"loss": 0.0958,
"step": 350
},
{
"epoch": 0.17,
"learning_rate": 4.476489028213166e-05,
"loss": 0.1006,
"step": 360
},
{
"epoch": 0.17,
"learning_rate": 4.601880877742947e-05,
"loss": 0.0849,
"step": 370
},
{
"epoch": 0.18,
"learning_rate": 4.727272727272728e-05,
"loss": 0.0772,
"step": 380
},
{
"epoch": 0.18,
"learning_rate": 4.852664576802508e-05,
"loss": 0.0852,
"step": 390
},
{
"epoch": 0.19,
"learning_rate": 4.978056426332288e-05,
"loss": 0.0865,
"step": 400
},
{
"epoch": 0.19,
"learning_rate": 5.10344827586207e-05,
"loss": 0.0936,
"step": 410
},
{
"epoch": 0.2,
"learning_rate": 5.2288401253918504e-05,
"loss": 0.1028,
"step": 420
},
{
"epoch": 0.2,
"learning_rate": 5.3542319749216304e-05,
"loss": 0.0849,
"step": 430
},
{
"epoch": 0.21,
"learning_rate": 5.4796238244514105e-05,
"loss": 0.0935,
"step": 440
},
{
"epoch": 0.21,
"learning_rate": 5.605015673981192e-05,
"loss": 0.0838,
"step": 450
},
{
"epoch": 0.22,
"learning_rate": 5.7304075235109726e-05,
"loss": 0.0851,
"step": 460
},
{
"epoch": 0.22,
"learning_rate": 5.855799373040753e-05,
"loss": 0.0916,
"step": 470
},
{
"epoch": 0.23,
"learning_rate": 5.9811912225705334e-05,
"loss": 0.0926,
"step": 480
},
{
"epoch": 0.23,
"learning_rate": 6.106583072100315e-05,
"loss": 0.0742,
"step": 490
},
{
"epoch": 0.24,
"learning_rate": 6.231974921630095e-05,
"loss": 0.0882,
"step": 500
},
{
"epoch": 0.24,
"learning_rate": 6.357366771159875e-05,
"loss": 0.0789,
"step": 510
},
{
"epoch": 0.24,
"learning_rate": 6.482758620689655e-05,
"loss": 0.0847,
"step": 520
},
{
"epoch": 0.25,
"learning_rate": 6.608150470219436e-05,
"loss": 0.0764,
"step": 530
},
{
"epoch": 0.25,
"learning_rate": 6.733542319749216e-05,
"loss": 0.0963,
"step": 540
},
{
"epoch": 0.26,
"learning_rate": 6.858934169278998e-05,
"loss": 0.0695,
"step": 550
},
{
"epoch": 0.26,
"learning_rate": 6.984326018808778e-05,
"loss": 0.0693,
"step": 560
},
{
"epoch": 0.27,
"learning_rate": 7.109717868338559e-05,
"loss": 0.0908,
"step": 570
},
{
"epoch": 0.27,
"learning_rate": 7.23510971786834e-05,
"loss": 0.0779,
"step": 580
},
{
"epoch": 0.28,
"learning_rate": 7.36050156739812e-05,
"loss": 0.0825,
"step": 590
},
{
"epoch": 0.28,
"learning_rate": 7.485893416927901e-05,
"loss": 0.0813,
"step": 600
},
{
"epoch": 0.29,
"learning_rate": 7.611285266457681e-05,
"loss": 0.072,
"step": 610
},
{
"epoch": 0.29,
"learning_rate": 7.736677115987461e-05,
"loss": 0.0813,
"step": 620
},
{
"epoch": 0.3,
"learning_rate": 7.862068965517242e-05,
"loss": 0.0906,
"step": 630
},
{
"epoch": 0.3,
"learning_rate": 7.987460815047022e-05,
"loss": 0.0868,
"step": 640
},
{
"epoch": 0.31,
"learning_rate": 7.987456445993032e-05,
"loss": 0.0675,
"step": 650
},
{
"epoch": 0.31,
"learning_rate": 7.973519163763066e-05,
"loss": 0.0942,
"step": 660
},
{
"epoch": 0.32,
"learning_rate": 7.959581881533101e-05,
"loss": 0.0671,
"step": 670
},
{
"epoch": 0.32,
"learning_rate": 7.945644599303136e-05,
"loss": 0.0841,
"step": 680
},
{
"epoch": 0.32,
"learning_rate": 7.931707317073171e-05,
"loss": 0.0778,
"step": 690
},
{
"epoch": 0.33,
"learning_rate": 7.917770034843206e-05,
"loss": 0.0899,
"step": 700
},
{
"epoch": 0.33,
"learning_rate": 7.90383275261324e-05,
"loss": 0.0925,
"step": 710
},
{
"epoch": 0.34,
"learning_rate": 7.889895470383276e-05,
"loss": 0.0822,
"step": 720
},
{
"epoch": 0.34,
"learning_rate": 7.87595818815331e-05,
"loss": 0.0837,
"step": 730
},
{
"epoch": 0.35,
"learning_rate": 7.862020905923346e-05,
"loss": 0.077,
"step": 740
},
{
"epoch": 0.35,
"learning_rate": 7.84808362369338e-05,
"loss": 0.0705,
"step": 750
},
{
"epoch": 0.36,
"learning_rate": 7.834146341463415e-05,
"loss": 0.0849,
"step": 760
},
{
"epoch": 0.36,
"learning_rate": 7.82020905923345e-05,
"loss": 0.0792,
"step": 770
},
{
"epoch": 0.37,
"learning_rate": 7.806271777003485e-05,
"loss": 0.0786,
"step": 780
},
{
"epoch": 0.37,
"learning_rate": 7.79233449477352e-05,
"loss": 0.0862,
"step": 790
},
{
"epoch": 0.38,
"learning_rate": 7.778397212543555e-05,
"loss": 0.0828,
"step": 800
},
{
"epoch": 0.38,
"learning_rate": 7.76445993031359e-05,
"loss": 0.0918,
"step": 810
},
{
"epoch": 0.39,
"learning_rate": 7.750522648083624e-05,
"loss": 0.0749,
"step": 820
},
{
"epoch": 0.39,
"learning_rate": 7.736585365853659e-05,
"loss": 0.083,
"step": 830
},
{
"epoch": 0.4,
"learning_rate": 7.722648083623694e-05,
"loss": 0.0666,
"step": 840
},
{
"epoch": 0.4,
"learning_rate": 7.708710801393729e-05,
"loss": 0.0811,
"step": 850
},
{
"epoch": 0.4,
"learning_rate": 7.694773519163764e-05,
"loss": 0.0877,
"step": 860
},
{
"epoch": 0.41,
"learning_rate": 7.680836236933799e-05,
"loss": 0.0825,
"step": 870
},
{
"epoch": 0.41,
"learning_rate": 7.666898954703834e-05,
"loss": 0.0759,
"step": 880
},
{
"epoch": 0.42,
"learning_rate": 7.652961672473867e-05,
"loss": 0.0723,
"step": 890
},
{
"epoch": 0.42,
"learning_rate": 7.639024390243902e-05,
"loss": 0.0763,
"step": 900
},
{
"epoch": 0.43,
"learning_rate": 7.625087108013937e-05,
"loss": 0.0716,
"step": 910
},
{
"epoch": 0.43,
"learning_rate": 7.611149825783972e-05,
"loss": 0.0698,
"step": 920
},
{
"epoch": 0.44,
"learning_rate": 7.597212543554007e-05,
"loss": 0.0873,
"step": 930
},
{
"epoch": 0.44,
"learning_rate": 7.583275261324042e-05,
"loss": 0.0701,
"step": 940
},
{
"epoch": 0.45,
"learning_rate": 7.569337979094077e-05,
"loss": 0.0775,
"step": 950
},
{
"epoch": 0.45,
"learning_rate": 7.555400696864112e-05,
"loss": 0.0705,
"step": 960
},
{
"epoch": 0.46,
"learning_rate": 7.541463414634147e-05,
"loss": 0.0792,
"step": 970
},
{
"epoch": 0.46,
"learning_rate": 7.527526132404182e-05,
"loss": 0.0695,
"step": 980
},
{
"epoch": 0.47,
"learning_rate": 7.513588850174217e-05,
"loss": 0.0934,
"step": 990
},
{
"epoch": 0.47,
"learning_rate": 7.499651567944252e-05,
"loss": 0.0903,
"step": 1000
},
{
"epoch": 0.48,
"learning_rate": 7.485714285714287e-05,
"loss": 0.0863,
"step": 1010
},
{
"epoch": 0.48,
"learning_rate": 7.471777003484322e-05,
"loss": 0.0801,
"step": 1020
},
{
"epoch": 0.48,
"learning_rate": 7.457839721254357e-05,
"loss": 0.0744,
"step": 1030
},
{
"epoch": 0.49,
"learning_rate": 7.443902439024392e-05,
"loss": 0.075,
"step": 1040
},
{
"epoch": 0.49,
"learning_rate": 7.429965156794425e-05,
"loss": 0.0711,
"step": 1050
},
{
"epoch": 0.5,
"learning_rate": 7.41602787456446e-05,
"loss": 0.0904,
"step": 1060
},
{
"epoch": 0.5,
"learning_rate": 7.402090592334495e-05,
"loss": 0.0771,
"step": 1070
},
{
"epoch": 0.51,
"learning_rate": 7.38815331010453e-05,
"loss": 0.0707,
"step": 1080
},
{
"epoch": 0.51,
"learning_rate": 7.374216027874565e-05,
"loss": 0.0655,
"step": 1090
},
{
"epoch": 0.52,
"learning_rate": 7.3602787456446e-05,
"loss": 0.077,
"step": 1100
},
{
"epoch": 0.52,
"learning_rate": 7.346341463414635e-05,
"loss": 0.0775,
"step": 1110
},
{
"epoch": 0.53,
"learning_rate": 7.33240418118467e-05,
"loss": 0.0825,
"step": 1120
},
{
"epoch": 0.53,
"learning_rate": 7.318466898954704e-05,
"loss": 0.0704,
"step": 1130
},
{
"epoch": 0.54,
"learning_rate": 7.304529616724739e-05,
"loss": 0.0614,
"step": 1140
},
{
"epoch": 0.54,
"learning_rate": 7.290592334494774e-05,
"loss": 0.0685,
"step": 1150
},
{
"epoch": 0.55,
"learning_rate": 7.276655052264809e-05,
"loss": 0.0766,
"step": 1160
},
{
"epoch": 0.55,
"learning_rate": 7.262717770034844e-05,
"loss": 0.0746,
"step": 1170
},
{
"epoch": 0.56,
"learning_rate": 7.248780487804878e-05,
"loss": 0.0723,
"step": 1180
},
{
"epoch": 0.56,
"learning_rate": 7.234843205574913e-05,
"loss": 0.0824,
"step": 1190
},
{
"epoch": 0.56,
"learning_rate": 7.220905923344948e-05,
"loss": 0.0708,
"step": 1200
},
{
"epoch": 0.57,
"learning_rate": 7.206968641114983e-05,
"loss": 0.0745,
"step": 1210
},
{
"epoch": 0.57,
"learning_rate": 7.193031358885018e-05,
"loss": 0.0743,
"step": 1220
},
{
"epoch": 0.58,
"learning_rate": 7.179094076655053e-05,
"loss": 0.0792,
"step": 1230
},
{
"epoch": 0.58,
"learning_rate": 7.165156794425088e-05,
"loss": 0.0729,
"step": 1240
},
{
"epoch": 0.59,
"learning_rate": 7.151219512195123e-05,
"loss": 0.0822,
"step": 1250
},
{
"epoch": 0.59,
"learning_rate": 7.137282229965158e-05,
"loss": 0.0766,
"step": 1260
},
{
"epoch": 0.6,
"learning_rate": 7.123344947735193e-05,
"loss": 0.07,
"step": 1270
},
{
"epoch": 0.6,
"learning_rate": 7.109407665505227e-05,
"loss": 0.0818,
"step": 1280
},
{
"epoch": 0.61,
"learning_rate": 7.095470383275262e-05,
"loss": 0.0748,
"step": 1290
},
{
"epoch": 0.61,
"learning_rate": 7.081533101045297e-05,
"loss": 0.0727,
"step": 1300
},
{
"epoch": 0.62,
"learning_rate": 7.067595818815332e-05,
"loss": 0.0798,
"step": 1310
},
{
"epoch": 0.62,
"learning_rate": 7.053658536585367e-05,
"loss": 0.0736,
"step": 1320
},
{
"epoch": 0.63,
"learning_rate": 7.039721254355402e-05,
"loss": 0.065,
"step": 1330
},
{
"epoch": 0.63,
"learning_rate": 7.025783972125437e-05,
"loss": 0.0699,
"step": 1340
},
{
"epoch": 0.63,
"learning_rate": 7.011846689895471e-05,
"loss": 0.066,
"step": 1350
},
{
"epoch": 0.64,
"learning_rate": 6.997909407665505e-05,
"loss": 0.0703,
"step": 1360
},
{
"epoch": 0.64,
"learning_rate": 6.98397212543554e-05,
"loss": 0.0801,
"step": 1370
},
{
"epoch": 0.65,
"learning_rate": 6.970034843205575e-05,
"loss": 0.0749,
"step": 1380
},
{
"epoch": 0.65,
"learning_rate": 6.95609756097561e-05,
"loss": 0.0658,
"step": 1390
},
{
"epoch": 0.66,
"learning_rate": 6.942160278745645e-05,
"loss": 0.0607,
"step": 1400
},
{
"epoch": 0.66,
"learning_rate": 6.92822299651568e-05,
"loss": 0.07,
"step": 1410
},
{
"epoch": 0.67,
"learning_rate": 6.914285714285715e-05,
"loss": 0.0747,
"step": 1420
},
{
"epoch": 0.67,
"learning_rate": 6.90034843205575e-05,
"loss": 0.0731,
"step": 1430
},
{
"epoch": 0.68,
"learning_rate": 6.886411149825785e-05,
"loss": 0.0703,
"step": 1440
},
{
"epoch": 0.68,
"learning_rate": 6.87247386759582e-05,
"loss": 0.0634,
"step": 1450
},
{
"epoch": 0.69,
"learning_rate": 6.858536585365855e-05,
"loss": 0.0748,
"step": 1460
},
{
"epoch": 0.69,
"learning_rate": 6.84459930313589e-05,
"loss": 0.0797,
"step": 1470
},
{
"epoch": 0.7,
"learning_rate": 6.830662020905925e-05,
"loss": 0.0899,
"step": 1480
},
{
"epoch": 0.7,
"learning_rate": 6.81672473867596e-05,
"loss": 0.0904,
"step": 1490
},
{
"epoch": 0.71,
"learning_rate": 6.802787456445995e-05,
"loss": 0.0723,
"step": 1500
},
{
"epoch": 0.71,
"learning_rate": 6.788850174216028e-05,
"loss": 0.0623,
"step": 1510
},
{
"epoch": 0.71,
"learning_rate": 6.774912891986063e-05,
"loss": 0.0698,
"step": 1520
},
{
"epoch": 0.72,
"learning_rate": 6.760975609756098e-05,
"loss": 0.0739,
"step": 1530
},
{
"epoch": 0.72,
"learning_rate": 6.747038327526133e-05,
"loss": 0.0655,
"step": 1540
},
{
"epoch": 0.73,
"learning_rate": 6.733101045296168e-05,
"loss": 0.0869,
"step": 1550
},
{
"epoch": 0.73,
"learning_rate": 6.719163763066203e-05,
"loss": 0.0708,
"step": 1560
},
{
"epoch": 0.74,
"learning_rate": 6.705226480836238e-05,
"loss": 0.0661,
"step": 1570
},
{
"epoch": 0.74,
"learning_rate": 6.691289198606273e-05,
"loss": 0.0795,
"step": 1580
},
{
"epoch": 0.75,
"learning_rate": 6.677351916376307e-05,
"loss": 0.0694,
"step": 1590
},
{
"epoch": 0.75,
"learning_rate": 6.663414634146341e-05,
"loss": 0.0923,
"step": 1600
},
{
"epoch": 0.76,
"learning_rate": 6.649477351916376e-05,
"loss": 0.0765,
"step": 1610
},
{
"epoch": 0.76,
"learning_rate": 6.635540069686411e-05,
"loss": 0.0703,
"step": 1620
},
{
"epoch": 0.77,
"learning_rate": 6.621602787456446e-05,
"loss": 0.0757,
"step": 1630
},
{
"epoch": 0.77,
"learning_rate": 6.607665505226481e-05,
"loss": 0.0761,
"step": 1640
},
{
"epoch": 0.78,
"learning_rate": 6.593728222996516e-05,
"loss": 0.0721,
"step": 1650
},
{
"epoch": 0.78,
"learning_rate": 6.579790940766551e-05,
"loss": 0.077,
"step": 1660
},
{
"epoch": 0.79,
"learning_rate": 6.565853658536585e-05,
"loss": 0.0598,
"step": 1670
},
{
"epoch": 0.79,
"learning_rate": 6.55191637630662e-05,
"loss": 0.0727,
"step": 1680
},
{
"epoch": 0.79,
"learning_rate": 6.537979094076655e-05,
"loss": 0.0827,
"step": 1690
},
{
"epoch": 0.8,
"learning_rate": 6.52404181184669e-05,
"loss": 0.0725,
"step": 1700
},
{
"epoch": 0.8,
"learning_rate": 6.510104529616725e-05,
"loss": 0.0749,
"step": 1710
},
{
"epoch": 0.81,
"learning_rate": 6.49616724738676e-05,
"loss": 0.0773,
"step": 1720
},
{
"epoch": 0.81,
"learning_rate": 6.482229965156795e-05,
"loss": 0.081,
"step": 1730
},
{
"epoch": 0.82,
"learning_rate": 6.46829268292683e-05,
"loss": 0.0824,
"step": 1740
},
{
"epoch": 0.82,
"learning_rate": 6.454355400696865e-05,
"loss": 0.0662,
"step": 1750
},
{
"epoch": 0.83,
"learning_rate": 6.4404181184669e-05,
"loss": 0.0548,
"step": 1760
},
{
"epoch": 0.83,
"learning_rate": 6.426480836236935e-05,
"loss": 0.0847,
"step": 1770
},
{
"epoch": 0.84,
"learning_rate": 6.41254355400697e-05,
"loss": 0.0758,
"step": 1780
},
{
"epoch": 0.84,
"learning_rate": 6.398606271777004e-05,
"loss": 0.0636,
"step": 1790
},
{
"epoch": 0.85,
"learning_rate": 6.38466898954704e-05,
"loss": 0.0615,
"step": 1800
},
{
"epoch": 0.85,
"learning_rate": 6.370731707317074e-05,
"loss": 0.0672,
"step": 1810
},
{
"epoch": 0.86,
"learning_rate": 6.356794425087109e-05,
"loss": 0.0858,
"step": 1820
},
{
"epoch": 0.86,
"learning_rate": 6.342857142857143e-05,
"loss": 0.0699,
"step": 1830
},
{
"epoch": 0.87,
"learning_rate": 6.328919860627178e-05,
"loss": 0.0608,
"step": 1840
},
{
"epoch": 0.87,
"learning_rate": 6.314982578397213e-05,
"loss": 0.0749,
"step": 1850
},
{
"epoch": 0.87,
"learning_rate": 6.301045296167248e-05,
"loss": 0.083,
"step": 1860
},
{
"epoch": 0.88,
"learning_rate": 6.287108013937283e-05,
"loss": 0.0763,
"step": 1870
},
{
"epoch": 0.88,
"learning_rate": 6.273170731707318e-05,
"loss": 0.0634,
"step": 1880
},
{
"epoch": 0.89,
"learning_rate": 6.259233449477353e-05,
"loss": 0.0595,
"step": 1890
},
{
"epoch": 0.89,
"learning_rate": 6.245296167247386e-05,
"loss": 0.0555,
"step": 1900
},
{
"epoch": 0.9,
"learning_rate": 6.231358885017421e-05,
"loss": 0.0607,
"step": 1910
},
{
"epoch": 0.9,
"learning_rate": 6.217421602787456e-05,
"loss": 0.078,
"step": 1920
},
{
"epoch": 0.91,
"learning_rate": 6.203484320557491e-05,
"loss": 0.0894,
"step": 1930
},
{
"epoch": 0.91,
"learning_rate": 6.189547038327526e-05,
"loss": 0.0672,
"step": 1940
},
{
"epoch": 0.92,
"learning_rate": 6.175609756097561e-05,
"loss": 0.067,
"step": 1950
},
{
"epoch": 0.92,
"learning_rate": 6.161672473867596e-05,
"loss": 0.0733,
"step": 1960
},
{
"epoch": 0.93,
"learning_rate": 6.147735191637631e-05,
"loss": 0.0634,
"step": 1970
},
{
"epoch": 0.93,
"learning_rate": 6.133797909407666e-05,
"loss": 0.0795,
"step": 1980
},
{
"epoch": 0.94,
"learning_rate": 6.119860627177701e-05,
"loss": 0.0757,
"step": 1990
},
{
"epoch": 0.94,
"learning_rate": 6.105923344947736e-05,
"loss": 0.0769,
"step": 2000
},
{
"epoch": 0.95,
"learning_rate": 6.09198606271777e-05,
"loss": 0.0834,
"step": 2010
},
{
"epoch": 0.95,
"learning_rate": 6.078048780487805e-05,
"loss": 0.0655,
"step": 2020
},
{
"epoch": 0.95,
"learning_rate": 6.06411149825784e-05,
"loss": 0.0669,
"step": 2030
},
{
"epoch": 0.96,
"learning_rate": 6.050174216027875e-05,
"loss": 0.0723,
"step": 2040
},
{
"epoch": 0.96,
"learning_rate": 6.03623693379791e-05,
"loss": 0.0748,
"step": 2050
},
{
"epoch": 0.97,
"learning_rate": 6.0222996515679443e-05,
"loss": 0.077,
"step": 2060
},
{
"epoch": 0.97,
"learning_rate": 6.008362369337979e-05,
"loss": 0.0669,
"step": 2070
},
{
"epoch": 0.98,
"learning_rate": 5.994425087108014e-05,
"loss": 0.0818,
"step": 2080
},
{
"epoch": 0.98,
"learning_rate": 5.980487804878049e-05,
"loss": 0.0667,
"step": 2090
},
{
"epoch": 0.99,
"learning_rate": 5.966550522648084e-05,
"loss": 0.0674,
"step": 2100
},
{
"epoch": 0.99,
"learning_rate": 5.952613240418119e-05,
"loss": 0.0902,
"step": 2110
},
{
"epoch": 1.0,
"learning_rate": 5.938675958188154e-05,
"loss": 0.0752,
"step": 2120
},
{
"epoch": 1.0,
"eval_accuracy": 0.975717042417269,
"eval_f1": 0.7687279607809409,
"eval_loss": 0.0664275586605072,
"eval_precision": 0.7416196481911715,
"eval_recall": 0.7978932333511873,
"eval_runtime": 16.3951,
"eval_samples_per_second": 863.673,
"eval_steps_per_second": 107.959,
"step": 2126
},
{
"epoch": 1.0,
"learning_rate": 5.924738675958189e-05,
"loss": 0.0914,
"step": 2130
},
{
"epoch": 1.01,
"learning_rate": 5.9108013937282234e-05,
"loss": 0.0682,
"step": 2140
},
{
"epoch": 1.01,
"learning_rate": 5.896864111498258e-05,
"loss": 0.0591,
"step": 2150
},
{
"epoch": 1.02,
"learning_rate": 5.882926829268293e-05,
"loss": 0.0622,
"step": 2160
},
{
"epoch": 1.02,
"learning_rate": 5.868989547038328e-05,
"loss": 0.0692,
"step": 2170
},
{
"epoch": 1.03,
"learning_rate": 5.855052264808363e-05,
"loss": 0.054,
"step": 2180
},
{
"epoch": 1.03,
"learning_rate": 5.841114982578398e-05,
"loss": 0.0494,
"step": 2190
},
{
"epoch": 1.03,
"learning_rate": 5.827177700348433e-05,
"loss": 0.0648,
"step": 2200
},
{
"epoch": 1.04,
"learning_rate": 5.813240418118467e-05,
"loss": 0.0639,
"step": 2210
},
{
"epoch": 1.04,
"learning_rate": 5.799303135888502e-05,
"loss": 0.0595,
"step": 2220
},
{
"epoch": 1.05,
"learning_rate": 5.785365853658537e-05,
"loss": 0.0548,
"step": 2230
},
{
"epoch": 1.05,
"learning_rate": 5.7714285714285716e-05,
"loss": 0.0542,
"step": 2240
},
{
"epoch": 1.06,
"learning_rate": 5.7574912891986066e-05,
"loss": 0.0527,
"step": 2250
},
{
"epoch": 1.06,
"learning_rate": 5.7435540069686416e-05,
"loss": 0.0477,
"step": 2260
},
{
"epoch": 1.07,
"learning_rate": 5.7296167247386765e-05,
"loss": 0.0699,
"step": 2270
},
{
"epoch": 1.07,
"learning_rate": 5.7156794425087115e-05,
"loss": 0.0546,
"step": 2280
},
{
"epoch": 1.08,
"learning_rate": 5.701742160278746e-05,
"loss": 0.0543,
"step": 2290
},
{
"epoch": 1.08,
"learning_rate": 5.687804878048781e-05,
"loss": 0.052,
"step": 2300
},
{
"epoch": 1.09,
"learning_rate": 5.673867595818816e-05,
"loss": 0.0614,
"step": 2310
},
{
"epoch": 1.09,
"learning_rate": 5.659930313588851e-05,
"loss": 0.0692,
"step": 2320
},
{
"epoch": 1.1,
"learning_rate": 5.6459930313588856e-05,
"loss": 0.058,
"step": 2330
},
{
"epoch": 1.1,
"learning_rate": 5.6320557491289206e-05,
"loss": 0.064,
"step": 2340
},
{
"epoch": 1.11,
"learning_rate": 5.6181184668989555e-05,
"loss": 0.062,
"step": 2350
},
{
"epoch": 1.11,
"learning_rate": 5.6041811846689905e-05,
"loss": 0.0627,
"step": 2360
},
{
"epoch": 1.11,
"learning_rate": 5.590243902439025e-05,
"loss": 0.0613,
"step": 2370
},
{
"epoch": 1.12,
"learning_rate": 5.57630662020906e-05,
"loss": 0.0653,
"step": 2380
},
{
"epoch": 1.12,
"learning_rate": 5.562369337979095e-05,
"loss": 0.0592,
"step": 2390
},
{
"epoch": 1.13,
"learning_rate": 5.54843205574913e-05,
"loss": 0.0563,
"step": 2400
},
{
"epoch": 1.13,
"learning_rate": 5.5344947735191646e-05,
"loss": 0.0516,
"step": 2410
},
{
"epoch": 1.14,
"learning_rate": 5.520557491289199e-05,
"loss": 0.0619,
"step": 2420
},
{
"epoch": 1.14,
"learning_rate": 5.506620209059234e-05,
"loss": 0.0698,
"step": 2430
},
{
"epoch": 1.15,
"learning_rate": 5.492682926829269e-05,
"loss": 0.0541,
"step": 2440
},
{
"epoch": 1.15,
"learning_rate": 5.478745644599303e-05,
"loss": 0.0459,
"step": 2450
},
{
"epoch": 1.16,
"learning_rate": 5.464808362369338e-05,
"loss": 0.0544,
"step": 2460
},
{
"epoch": 1.16,
"learning_rate": 5.450871080139373e-05,
"loss": 0.0533,
"step": 2470
},
{
"epoch": 1.17,
"learning_rate": 5.436933797909408e-05,
"loss": 0.0597,
"step": 2480
},
{
"epoch": 1.17,
"learning_rate": 5.422996515679443e-05,
"loss": 0.0553,
"step": 2490
},
{
"epoch": 1.18,
"learning_rate": 5.409059233449478e-05,
"loss": 0.0583,
"step": 2500
},
{
"epoch": 1.18,
"learning_rate": 5.395121951219513e-05,
"loss": 0.0552,
"step": 2510
},
{
"epoch": 1.19,
"learning_rate": 5.381184668989547e-05,
"loss": 0.0582,
"step": 2520
},
{
"epoch": 1.19,
"learning_rate": 5.367247386759582e-05,
"loss": 0.059,
"step": 2530
},
{
"epoch": 1.19,
"learning_rate": 5.353310104529617e-05,
"loss": 0.0657,
"step": 2540
},
{
"epoch": 1.2,
"learning_rate": 5.339372822299652e-05,
"loss": 0.0563,
"step": 2550
},
{
"epoch": 1.2,
"learning_rate": 5.325435540069687e-05,
"loss": 0.0568,
"step": 2560
},
{
"epoch": 1.21,
"learning_rate": 5.311498257839722e-05,
"loss": 0.067,
"step": 2570
},
{
"epoch": 1.21,
"learning_rate": 5.297560975609757e-05,
"loss": 0.064,
"step": 2580
},
{
"epoch": 1.22,
"learning_rate": 5.283623693379792e-05,
"loss": 0.0546,
"step": 2590
},
{
"epoch": 1.22,
"learning_rate": 5.2696864111498255e-05,
"loss": 0.0575,
"step": 2600
},
{
"epoch": 1.23,
"learning_rate": 5.2557491289198605e-05,
"loss": 0.0497,
"step": 2610
},
{
"epoch": 1.23,
"learning_rate": 5.2418118466898955e-05,
"loss": 0.0616,
"step": 2620
},
{
"epoch": 1.24,
"learning_rate": 5.2278745644599304e-05,
"loss": 0.0498,
"step": 2630
},
{
"epoch": 1.24,
"learning_rate": 5.2139372822299654e-05,
"loss": 0.0622,
"step": 2640
},
{
"epoch": 1.25,
"learning_rate": 5.2000000000000004e-05,
"loss": 0.0542,
"step": 2650
},
{
"epoch": 1.25,
"learning_rate": 5.186062717770035e-05,
"loss": 0.0625,
"step": 2660
},
{
"epoch": 1.26,
"learning_rate": 5.17212543554007e-05,
"loss": 0.0494,
"step": 2670
},
{
"epoch": 1.26,
"learning_rate": 5.1581881533101046e-05,
"loss": 0.0511,
"step": 2680
},
{
"epoch": 1.27,
"learning_rate": 5.1442508710801395e-05,
"loss": 0.0562,
"step": 2690
},
{
"epoch": 1.27,
"learning_rate": 5.1303135888501745e-05,
"loss": 0.067,
"step": 2700
},
{
"epoch": 1.27,
"learning_rate": 5.1163763066202095e-05,
"loss": 0.0528,
"step": 2710
},
{
"epoch": 1.28,
"learning_rate": 5.1024390243902444e-05,
"loss": 0.0677,
"step": 2720
},
{
"epoch": 1.28,
"learning_rate": 5.0885017421602794e-05,
"loss": 0.0668,
"step": 2730
},
{
"epoch": 1.29,
"learning_rate": 5.0745644599303143e-05,
"loss": 0.0677,
"step": 2740
},
{
"epoch": 1.29,
"learning_rate": 5.060627177700349e-05,
"loss": 0.0446,
"step": 2750
},
{
"epoch": 1.3,
"learning_rate": 5.0466898954703836e-05,
"loss": 0.0474,
"step": 2760
},
{
"epoch": 1.3,
"learning_rate": 5.0327526132404186e-05,
"loss": 0.0634,
"step": 2770
},
{
"epoch": 1.31,
"learning_rate": 5.0188153310104535e-05,
"loss": 0.0588,
"step": 2780
},
{
"epoch": 1.31,
"learning_rate": 5.0048780487804885e-05,
"loss": 0.0587,
"step": 2790
},
{
"epoch": 1.32,
"learning_rate": 4.9909407665505234e-05,
"loss": 0.0653,
"step": 2800
},
{
"epoch": 1.32,
"learning_rate": 4.9770034843205584e-05,
"loss": 0.057,
"step": 2810
},
{
"epoch": 1.33,
"learning_rate": 4.9630662020905934e-05,
"loss": 0.0584,
"step": 2820
},
{
"epoch": 1.33,
"learning_rate": 4.949128919860627e-05,
"loss": 0.0485,
"step": 2830
},
{
"epoch": 1.34,
"learning_rate": 4.935191637630662e-05,
"loss": 0.0595,
"step": 2840
},
{
"epoch": 1.34,
"learning_rate": 4.921254355400697e-05,
"loss": 0.0595,
"step": 2850
},
{
"epoch": 1.35,
"learning_rate": 4.907317073170732e-05,
"loss": 0.0536,
"step": 2860
},
{
"epoch": 1.35,
"learning_rate": 4.893379790940767e-05,
"loss": 0.0674,
"step": 2870
},
{
"epoch": 1.35,
"learning_rate": 4.879442508710802e-05,
"loss": 0.061,
"step": 2880
},
{
"epoch": 1.36,
"learning_rate": 4.865505226480837e-05,
"loss": 0.0528,
"step": 2890
},
{
"epoch": 1.36,
"learning_rate": 4.851567944250872e-05,
"loss": 0.0531,
"step": 2900
},
{
"epoch": 1.37,
"learning_rate": 4.837630662020906e-05,
"loss": 0.0558,
"step": 2910
},
{
"epoch": 1.37,
"learning_rate": 4.823693379790941e-05,
"loss": 0.0708,
"step": 2920
},
{
"epoch": 1.38,
"learning_rate": 4.809756097560976e-05,
"loss": 0.0595,
"step": 2930
},
{
"epoch": 1.38,
"learning_rate": 4.795818815331011e-05,
"loss": 0.0486,
"step": 2940
},
{
"epoch": 1.39,
"learning_rate": 4.781881533101046e-05,
"loss": 0.0644,
"step": 2950
},
{
"epoch": 1.39,
"learning_rate": 4.767944250871081e-05,
"loss": 0.0525,
"step": 2960
},
{
"epoch": 1.4,
"learning_rate": 4.754006968641116e-05,
"loss": 0.0704,
"step": 2970
},
{
"epoch": 1.4,
"learning_rate": 4.740069686411151e-05,
"loss": 0.0612,
"step": 2980
},
{
"epoch": 1.41,
"learning_rate": 4.726132404181185e-05,
"loss": 0.061,
"step": 2990
},
{
"epoch": 1.41,
"learning_rate": 4.71219512195122e-05,
"loss": 0.0616,
"step": 3000
},
{
"epoch": 1.42,
"learning_rate": 4.698257839721254e-05,
"loss": 0.0682,
"step": 3010
},
{
"epoch": 1.42,
"learning_rate": 4.684320557491289e-05,
"loss": 0.0509,
"step": 3020
},
{
"epoch": 1.43,
"learning_rate": 4.670383275261324e-05,
"loss": 0.0587,
"step": 3030
},
{
"epoch": 1.43,
"learning_rate": 4.656445993031359e-05,
"loss": 0.0562,
"step": 3040
},
{
"epoch": 1.43,
"learning_rate": 4.642508710801394e-05,
"loss": 0.0606,
"step": 3050
},
{
"epoch": 1.44,
"learning_rate": 4.628571428571429e-05,
"loss": 0.0576,
"step": 3060
},
{
"epoch": 1.44,
"learning_rate": 4.6146341463414634e-05,
"loss": 0.0461,
"step": 3070
},
{
"epoch": 1.45,
"learning_rate": 4.600696864111498e-05,
"loss": 0.0582,
"step": 3080
},
{
"epoch": 1.45,
"learning_rate": 4.586759581881533e-05,
"loss": 0.0583,
"step": 3090
},
{
"epoch": 1.46,
"learning_rate": 4.572822299651568e-05,
"loss": 0.054,
"step": 3100
},
{
"epoch": 1.46,
"learning_rate": 4.558885017421603e-05,
"loss": 0.0495,
"step": 3110
},
{
"epoch": 1.47,
"learning_rate": 4.544947735191638e-05,
"loss": 0.0565,
"step": 3120
},
{
"epoch": 1.47,
"learning_rate": 4.531010452961673e-05,
"loss": 0.0439,
"step": 3130
},
{
"epoch": 1.48,
"learning_rate": 4.5170731707317074e-05,
"loss": 0.055,
"step": 3140
},
{
"epoch": 1.48,
"learning_rate": 4.5031358885017424e-05,
"loss": 0.0626,
"step": 3150
},
{
"epoch": 1.49,
"learning_rate": 4.4891986062717773e-05,
"loss": 0.0628,
"step": 3160
},
{
"epoch": 1.49,
"learning_rate": 4.475261324041812e-05,
"loss": 0.0627,
"step": 3170
},
{
"epoch": 1.5,
"learning_rate": 4.461324041811847e-05,
"loss": 0.0544,
"step": 3180
},
{
"epoch": 1.5,
"learning_rate": 4.447386759581882e-05,
"loss": 0.0464,
"step": 3190
},
{
"epoch": 1.51,
"learning_rate": 4.433449477351917e-05,
"loss": 0.0494,
"step": 3200
},
{
"epoch": 1.51,
"learning_rate": 4.419512195121952e-05,
"loss": 0.052,
"step": 3210
},
{
"epoch": 1.51,
"learning_rate": 4.405574912891986e-05,
"loss": 0.0553,
"step": 3220
},
{
"epoch": 1.52,
"learning_rate": 4.391637630662021e-05,
"loss": 0.0565,
"step": 3230
},
{
"epoch": 1.52,
"learning_rate": 4.377700348432056e-05,
"loss": 0.0576,
"step": 3240
},
{
"epoch": 1.53,
"learning_rate": 4.3637630662020907e-05,
"loss": 0.0613,
"step": 3250
},
{
"epoch": 1.53,
"learning_rate": 4.3498257839721256e-05,
"loss": 0.0601,
"step": 3260
},
{
"epoch": 1.54,
"learning_rate": 4.3358885017421606e-05,
"loss": 0.0566,
"step": 3270
},
{
"epoch": 1.54,
"learning_rate": 4.3219512195121955e-05,
"loss": 0.0551,
"step": 3280
},
{
"epoch": 1.55,
"learning_rate": 4.3080139372822305e-05,
"loss": 0.0478,
"step": 3290
},
{
"epoch": 1.55,
"learning_rate": 4.294076655052265e-05,
"loss": 0.0561,
"step": 3300
},
{
"epoch": 1.56,
"learning_rate": 4.2801393728223e-05,
"loss": 0.0577,
"step": 3310
},
{
"epoch": 1.56,
"learning_rate": 4.266202090592335e-05,
"loss": 0.0533,
"step": 3320
},
{
"epoch": 1.57,
"learning_rate": 4.25226480836237e-05,
"loss": 0.0603,
"step": 3330
},
{
"epoch": 1.57,
"learning_rate": 4.2383275261324046e-05,
"loss": 0.0533,
"step": 3340
},
{
"epoch": 1.58,
"learning_rate": 4.2243902439024396e-05,
"loss": 0.0718,
"step": 3350
},
{
"epoch": 1.58,
"learning_rate": 4.2104529616724746e-05,
"loss": 0.0557,
"step": 3360
},
{
"epoch": 1.59,
"learning_rate": 4.1965156794425095e-05,
"loss": 0.0656,
"step": 3370
},
{
"epoch": 1.59,
"learning_rate": 4.182578397212544e-05,
"loss": 0.0608,
"step": 3380
},
{
"epoch": 1.59,
"learning_rate": 4.168641114982579e-05,
"loss": 0.0588,
"step": 3390
},
{
"epoch": 1.6,
"learning_rate": 4.154703832752614e-05,
"loss": 0.0556,
"step": 3400
},
{
"epoch": 1.6,
"learning_rate": 4.140766550522649e-05,
"loss": 0.0615,
"step": 3410
},
{
"epoch": 1.61,
"learning_rate": 4.1268292682926837e-05,
"loss": 0.0524,
"step": 3420
},
{
"epoch": 1.61,
"learning_rate": 4.1128919860627186e-05,
"loss": 0.0688,
"step": 3430
},
{
"epoch": 1.62,
"learning_rate": 4.0989547038327536e-05,
"loss": 0.053,
"step": 3440
},
{
"epoch": 1.62,
"learning_rate": 4.085017421602787e-05,
"loss": 0.0657,
"step": 3450
},
{
"epoch": 1.63,
"learning_rate": 4.071080139372822e-05,
"loss": 0.0641,
"step": 3460
},
{
"epoch": 1.63,
"learning_rate": 4.057142857142857e-05,
"loss": 0.0628,
"step": 3470
},
{
"epoch": 1.64,
"learning_rate": 4.043205574912892e-05,
"loss": 0.0599,
"step": 3480
},
{
"epoch": 1.64,
"learning_rate": 4.029268292682927e-05,
"loss": 0.0512,
"step": 3490
},
{
"epoch": 1.65,
"learning_rate": 4.015331010452962e-05,
"loss": 0.0552,
"step": 3500
},
{
"epoch": 1.65,
"learning_rate": 4.001393728222997e-05,
"loss": 0.0572,
"step": 3510
},
{
"epoch": 1.66,
"learning_rate": 3.987456445993032e-05,
"loss": 0.063,
"step": 3520
},
{
"epoch": 1.66,
"learning_rate": 3.973519163763067e-05,
"loss": 0.0634,
"step": 3530
},
{
"epoch": 1.67,
"learning_rate": 3.959581881533102e-05,
"loss": 0.061,
"step": 3540
},
{
"epoch": 1.67,
"learning_rate": 3.945644599303136e-05,
"loss": 0.0543,
"step": 3550
},
{
"epoch": 1.67,
"learning_rate": 3.931707317073171e-05,
"loss": 0.0698,
"step": 3560
},
{
"epoch": 1.68,
"learning_rate": 3.917770034843206e-05,
"loss": 0.0638,
"step": 3570
},
{
"epoch": 1.68,
"learning_rate": 3.903832752613241e-05,
"loss": 0.0584,
"step": 3580
},
{
"epoch": 1.69,
"learning_rate": 3.889895470383275e-05,
"loss": 0.0532,
"step": 3590
},
{
"epoch": 1.69,
"learning_rate": 3.87595818815331e-05,
"loss": 0.0547,
"step": 3600
},
{
"epoch": 1.7,
"learning_rate": 3.862020905923345e-05,
"loss": 0.0624,
"step": 3610
},
{
"epoch": 1.7,
"learning_rate": 3.84808362369338e-05,
"loss": 0.0597,
"step": 3620
},
{
"epoch": 1.71,
"learning_rate": 3.8341463414634145e-05,
"loss": 0.0636,
"step": 3630
},
{
"epoch": 1.71,
"learning_rate": 3.8202090592334494e-05,
"loss": 0.0603,
"step": 3640
},
{
"epoch": 1.72,
"learning_rate": 3.8062717770034844e-05,
"loss": 0.0618,
"step": 3650
},
{
"epoch": 1.72,
"learning_rate": 3.7923344947735194e-05,
"loss": 0.059,
"step": 3660
},
{
"epoch": 1.73,
"learning_rate": 3.778397212543554e-05,
"loss": 0.0674,
"step": 3670
},
{
"epoch": 1.73,
"learning_rate": 3.764459930313589e-05,
"loss": 0.0628,
"step": 3680
},
{
"epoch": 1.74,
"learning_rate": 3.750522648083624e-05,
"loss": 0.0623,
"step": 3690
},
{
"epoch": 1.74,
"learning_rate": 3.736585365853659e-05,
"loss": 0.0545,
"step": 3700
},
{
"epoch": 1.75,
"learning_rate": 3.7226480836236935e-05,
"loss": 0.0559,
"step": 3710
},
{
"epoch": 1.75,
"learning_rate": 3.7087108013937285e-05,
"loss": 0.0563,
"step": 3720
},
{
"epoch": 1.75,
"learning_rate": 3.6947735191637634e-05,
"loss": 0.0634,
"step": 3730
},
{
"epoch": 1.76,
"learning_rate": 3.680836236933798e-05,
"loss": 0.0624,
"step": 3740
},
{
"epoch": 1.76,
"learning_rate": 3.666898954703833e-05,
"loss": 0.0485,
"step": 3750
},
{
"epoch": 1.77,
"learning_rate": 3.6529616724738676e-05,
"loss": 0.0564,
"step": 3760
},
{
"epoch": 1.77,
"learning_rate": 3.6390243902439026e-05,
"loss": 0.0605,
"step": 3770
},
{
"epoch": 1.78,
"learning_rate": 3.6250871080139376e-05,
"loss": 0.0603,
"step": 3780
},
{
"epoch": 1.78,
"learning_rate": 3.6111498257839725e-05,
"loss": 0.0635,
"step": 3790
},
{
"epoch": 1.79,
"learning_rate": 3.5972125435540075e-05,
"loss": 0.056,
"step": 3800
},
{
"epoch": 1.79,
"learning_rate": 3.5832752613240425e-05,
"loss": 0.0578,
"step": 3810
},
{
"epoch": 1.8,
"learning_rate": 3.569337979094077e-05,
"loss": 0.0574,
"step": 3820
},
{
"epoch": 1.8,
"learning_rate": 3.555400696864112e-05,
"loss": 0.0649,
"step": 3830
},
{
"epoch": 1.81,
"learning_rate": 3.541463414634147e-05,
"loss": 0.0566,
"step": 3840
},
{
"epoch": 1.81,
"learning_rate": 3.5275261324041816e-05,
"loss": 0.0562,
"step": 3850
},
{
"epoch": 1.82,
"learning_rate": 3.513588850174216e-05,
"loss": 0.0475,
"step": 3860
},
{
"epoch": 1.82,
"learning_rate": 3.499651567944251e-05,
"loss": 0.0559,
"step": 3870
},
{
"epoch": 1.83,
"learning_rate": 3.485714285714286e-05,
"loss": 0.0487,
"step": 3880
},
{
"epoch": 1.83,
"learning_rate": 3.471777003484321e-05,
"loss": 0.065,
"step": 3890
},
{
"epoch": 1.83,
"learning_rate": 3.457839721254356e-05,
"loss": 0.0655,
"step": 3900
},
{
"epoch": 1.84,
"learning_rate": 3.443902439024391e-05,
"loss": 0.056,
"step": 3910
},
{
"epoch": 1.84,
"learning_rate": 3.429965156794426e-05,
"loss": 0.0547,
"step": 3920
},
{
"epoch": 1.85,
"learning_rate": 3.4160278745644606e-05,
"loss": 0.0573,
"step": 3930
},
{
"epoch": 1.85,
"learning_rate": 3.402090592334495e-05,
"loss": 0.0618,
"step": 3940
},
{
"epoch": 1.86,
"learning_rate": 3.38815331010453e-05,
"loss": 0.0564,
"step": 3950
},
{
"epoch": 1.86,
"learning_rate": 3.374216027874565e-05,
"loss": 0.0547,
"step": 3960
},
{
"epoch": 1.87,
"learning_rate": 3.3602787456446e-05,
"loss": 0.0644,
"step": 3970
},
{
"epoch": 1.87,
"learning_rate": 3.346341463414634e-05,
"loss": 0.0564,
"step": 3980
},
{
"epoch": 1.88,
"learning_rate": 3.332404181184669e-05,
"loss": 0.0633,
"step": 3990
},
{
"epoch": 1.88,
"learning_rate": 3.318466898954704e-05,
"loss": 0.0574,
"step": 4000
},
{
"epoch": 1.89,
"learning_rate": 3.304529616724739e-05,
"loss": 0.0547,
"step": 4010
},
{
"epoch": 1.89,
"learning_rate": 3.290592334494774e-05,
"loss": 0.0665,
"step": 4020
},
{
"epoch": 1.9,
"learning_rate": 3.276655052264809e-05,
"loss": 0.0545,
"step": 4030
},
{
"epoch": 1.9,
"learning_rate": 3.262717770034844e-05,
"loss": 0.0692,
"step": 4040
},
{
"epoch": 1.9,
"learning_rate": 3.248780487804879e-05,
"loss": 0.0648,
"step": 4050
},
{
"epoch": 1.91,
"learning_rate": 3.234843205574913e-05,
"loss": 0.0542,
"step": 4060
},
{
"epoch": 1.91,
"learning_rate": 3.220905923344948e-05,
"loss": 0.0562,
"step": 4070
},
{
"epoch": 1.92,
"learning_rate": 3.206968641114983e-05,
"loss": 0.0531,
"step": 4080
},
{
"epoch": 1.92,
"learning_rate": 3.193031358885017e-05,
"loss": 0.0615,
"step": 4090
},
{
"epoch": 1.93,
"learning_rate": 3.179094076655052e-05,
"loss": 0.0484,
"step": 4100
},
{
"epoch": 1.93,
"learning_rate": 3.165156794425087e-05,
"loss": 0.0492,
"step": 4110
},
{
"epoch": 1.94,
"learning_rate": 3.151219512195122e-05,
"loss": 0.0594,
"step": 4120
},
{
"epoch": 1.94,
"learning_rate": 3.137282229965157e-05,
"loss": 0.0489,
"step": 4130
},
{
"epoch": 1.95,
"learning_rate": 3.123344947735192e-05,
"loss": 0.0619,
"step": 4140
},
{
"epoch": 1.95,
"learning_rate": 3.1094076655052264e-05,
"loss": 0.0491,
"step": 4150
},
{
"epoch": 1.96,
"learning_rate": 3.0954703832752614e-05,
"loss": 0.0627,
"step": 4160
},
{
"epoch": 1.96,
"learning_rate": 3.0815331010452964e-05,
"loss": 0.0503,
"step": 4170
},
{
"epoch": 1.97,
"learning_rate": 3.067595818815331e-05,
"loss": 0.0495,
"step": 4180
},
{
"epoch": 1.97,
"learning_rate": 3.053658536585366e-05,
"loss": 0.064,
"step": 4190
},
{
"epoch": 1.98,
"learning_rate": 3.0397212543554012e-05,
"loss": 0.0634,
"step": 4200
},
{
"epoch": 1.98,
"learning_rate": 3.0257839721254355e-05,
"loss": 0.0582,
"step": 4210
},
{
"epoch": 1.98,
"learning_rate": 3.0118466898954705e-05,
"loss": 0.0654,
"step": 4220
},
{
"epoch": 1.99,
"learning_rate": 2.9979094076655055e-05,
"loss": 0.0524,
"step": 4230
},
{
"epoch": 1.99,
"learning_rate": 2.9839721254355404e-05,
"loss": 0.0613,
"step": 4240
},
{
"epoch": 2.0,
"learning_rate": 2.970034843205575e-05,
"loss": 0.0484,
"step": 4250
},
{
"epoch": 2.0,
"eval_accuracy": 0.9767567988685532,
"eval_f1": 0.7813079163357163,
"eval_loss": 0.06523581594228745,
"eval_precision": 0.7725130890052356,
"eval_recall": 0.7903053026245314,
"eval_runtime": 16.6261,
"eval_samples_per_second": 851.671,
"eval_steps_per_second": 106.459,
"step": 4252
},
{
"epoch": 2.0,
"learning_rate": 2.95609756097561e-05,
"loss": 0.0381,
"step": 4260
},
{
"epoch": 2.01,
"learning_rate": 2.942160278745645e-05,
"loss": 0.0487,
"step": 4270
},
{
"epoch": 2.01,
"learning_rate": 2.92822299651568e-05,
"loss": 0.046,
"step": 4280
},
{
"epoch": 2.02,
"learning_rate": 2.9142857142857146e-05,
"loss": 0.0403,
"step": 4290
},
{
"epoch": 2.02,
"learning_rate": 2.9003484320557492e-05,
"loss": 0.0403,
"step": 4300
},
{
"epoch": 2.03,
"learning_rate": 2.886411149825784e-05,
"loss": 0.04,
"step": 4310
},
{
"epoch": 2.03,
"learning_rate": 2.872473867595819e-05,
"loss": 0.0481,
"step": 4320
},
{
"epoch": 2.04,
"learning_rate": 2.8585365853658537e-05,
"loss": 0.0436,
"step": 4330
},
{
"epoch": 2.04,
"learning_rate": 2.8445993031358887e-05,
"loss": 0.0363,
"step": 4340
},
{
"epoch": 2.05,
"learning_rate": 2.8306620209059237e-05,
"loss": 0.0476,
"step": 4350
},
{
"epoch": 2.05,
"learning_rate": 2.8167247386759586e-05,
"loss": 0.0398,
"step": 4360
},
{
"epoch": 2.06,
"learning_rate": 2.8027874564459932e-05,
"loss": 0.0443,
"step": 4370
},
{
"epoch": 2.06,
"learning_rate": 2.7888501742160282e-05,
"loss": 0.0451,
"step": 4380
},
{
"epoch": 2.06,
"learning_rate": 2.774912891986063e-05,
"loss": 0.0411,
"step": 4390
},
{
"epoch": 2.07,
"learning_rate": 2.7609756097560974e-05,
"loss": 0.0524,
"step": 4400
},
{
"epoch": 2.07,
"learning_rate": 2.7470383275261324e-05,
"loss": 0.0449,
"step": 4410
},
{
"epoch": 2.08,
"learning_rate": 2.7331010452961674e-05,
"loss": 0.0405,
"step": 4420
},
{
"epoch": 2.08,
"learning_rate": 2.7191637630662023e-05,
"loss": 0.0502,
"step": 4430
},
{
"epoch": 2.09,
"learning_rate": 2.705226480836237e-05,
"loss": 0.0444,
"step": 4440
},
{
"epoch": 2.09,
"learning_rate": 2.691289198606272e-05,
"loss": 0.0371,
"step": 4450
},
{
"epoch": 2.1,
"learning_rate": 2.677351916376307e-05,
"loss": 0.0485,
"step": 4460
},
{
"epoch": 2.1,
"learning_rate": 2.663414634146342e-05,
"loss": 0.0444,
"step": 4470
},
{
"epoch": 2.11,
"learning_rate": 2.6494773519163765e-05,
"loss": 0.0392,
"step": 4480
},
{
"epoch": 2.11,
"learning_rate": 2.6355400696864114e-05,
"loss": 0.0461,
"step": 4490
},
{
"epoch": 2.12,
"learning_rate": 2.6216027874564464e-05,
"loss": 0.0459,
"step": 4500
},
{
"epoch": 2.12,
"learning_rate": 2.6076655052264814e-05,
"loss": 0.0537,
"step": 4510
},
{
"epoch": 2.13,
"learning_rate": 2.5937282229965156e-05,
"loss": 0.0409,
"step": 4520
},
{
"epoch": 2.13,
"learning_rate": 2.5797909407665506e-05,
"loss": 0.0446,
"step": 4530
},
{
"epoch": 2.14,
"learning_rate": 2.5658536585365856e-05,
"loss": 0.0512,
"step": 4540
},
{
"epoch": 2.14,
"learning_rate": 2.5519163763066205e-05,
"loss": 0.0475,
"step": 4550
},
{
"epoch": 2.14,
"learning_rate": 2.537979094076655e-05,
"loss": 0.045,
"step": 4560
},
{
"epoch": 2.15,
"learning_rate": 2.52404181184669e-05,
"loss": 0.0443,
"step": 4570
},
{
"epoch": 2.15,
"learning_rate": 2.510104529616725e-05,
"loss": 0.0409,
"step": 4580
},
{
"epoch": 2.16,
"learning_rate": 2.49616724738676e-05,
"loss": 0.0511,
"step": 4590
},
{
"epoch": 2.16,
"learning_rate": 2.4822299651567943e-05,
"loss": 0.0429,
"step": 4600
},
{
"epoch": 2.17,
"learning_rate": 2.4682926829268293e-05,
"loss": 0.0407,
"step": 4610
},
{
"epoch": 2.17,
"learning_rate": 2.4543554006968642e-05,
"loss": 0.0422,
"step": 4620
},
{
"epoch": 2.18,
"learning_rate": 2.4404181184668992e-05,
"loss": 0.0381,
"step": 4630
},
{
"epoch": 2.18,
"learning_rate": 2.426480836236934e-05,
"loss": 0.0382,
"step": 4640
},
{
"epoch": 2.19,
"learning_rate": 2.4125435540069688e-05,
"loss": 0.044,
"step": 4650
},
{
"epoch": 2.19,
"learning_rate": 2.3986062717770038e-05,
"loss": 0.0462,
"step": 4660
},
{
"epoch": 2.2,
"learning_rate": 2.3846689895470387e-05,
"loss": 0.0453,
"step": 4670
},
{
"epoch": 2.2,
"learning_rate": 2.3707317073170733e-05,
"loss": 0.0449,
"step": 4680
},
{
"epoch": 2.21,
"learning_rate": 2.3567944250871083e-05,
"loss": 0.0404,
"step": 4690
},
{
"epoch": 2.21,
"learning_rate": 2.3428571428571433e-05,
"loss": 0.0375,
"step": 4700
},
{
"epoch": 2.22,
"learning_rate": 2.3289198606271776e-05,
"loss": 0.0422,
"step": 4710
},
{
"epoch": 2.22,
"learning_rate": 2.3149825783972125e-05,
"loss": 0.0448,
"step": 4720
},
{
"epoch": 2.22,
"learning_rate": 2.3010452961672475e-05,
"loss": 0.0368,
"step": 4730
},
{
"epoch": 2.23,
"learning_rate": 2.2871080139372824e-05,
"loss": 0.0477,
"step": 4740
},
{
"epoch": 2.23,
"learning_rate": 2.273170731707317e-05,
"loss": 0.0418,
"step": 4750
},
{
"epoch": 2.24,
"learning_rate": 2.259233449477352e-05,
"loss": 0.0372,
"step": 4760
},
{
"epoch": 2.24,
"learning_rate": 2.245296167247387e-05,
"loss": 0.0428,
"step": 4770
},
{
"epoch": 2.25,
"learning_rate": 2.231358885017422e-05,
"loss": 0.0353,
"step": 4780
},
{
"epoch": 2.25,
"learning_rate": 2.2174216027874566e-05,
"loss": 0.046,
"step": 4790
},
{
"epoch": 2.26,
"learning_rate": 2.2034843205574915e-05,
"loss": 0.042,
"step": 4800
},
{
"epoch": 2.26,
"learning_rate": 2.1895470383275265e-05,
"loss": 0.0436,
"step": 4810
},
{
"epoch": 2.27,
"learning_rate": 2.1756097560975615e-05,
"loss": 0.0398,
"step": 4820
},
{
"epoch": 2.27,
"learning_rate": 2.1616724738675958e-05,
"loss": 0.0396,
"step": 4830
},
{
"epoch": 2.28,
"learning_rate": 2.1477351916376307e-05,
"loss": 0.0474,
"step": 4840
},
{
"epoch": 2.28,
"learning_rate": 2.1337979094076657e-05,
"loss": 0.0405,
"step": 4850
},
{
"epoch": 2.29,
"learning_rate": 2.1198606271777006e-05,
"loss": 0.0473,
"step": 4860
},
{
"epoch": 2.29,
"learning_rate": 2.1059233449477353e-05,
"loss": 0.044,
"step": 4870
},
{
"epoch": 2.3,
"learning_rate": 2.0919860627177702e-05,
"loss": 0.0388,
"step": 4880
},
{
"epoch": 2.3,
"learning_rate": 2.0780487804878052e-05,
"loss": 0.0403,
"step": 4890
},
{
"epoch": 2.3,
"learning_rate": 2.06411149825784e-05,
"loss": 0.041,
"step": 4900
},
{
"epoch": 2.31,
"learning_rate": 2.0501742160278744e-05,
"loss": 0.0429,
"step": 4910
},
{
"epoch": 2.31,
"learning_rate": 2.0362369337979094e-05,
"loss": 0.0363,
"step": 4920
},
{
"epoch": 2.32,
"learning_rate": 2.0222996515679444e-05,
"loss": 0.0414,
"step": 4930
},
{
"epoch": 2.32,
"learning_rate": 2.0083623693379793e-05,
"loss": 0.0515,
"step": 4940
},
{
"epoch": 2.33,
"learning_rate": 1.9944250871080143e-05,
"loss": 0.0447,
"step": 4950
},
{
"epoch": 2.33,
"learning_rate": 1.980487804878049e-05,
"loss": 0.0545,
"step": 4960
},
{
"epoch": 2.34,
"learning_rate": 1.966550522648084e-05,
"loss": 0.0416,
"step": 4970
},
{
"epoch": 2.34,
"learning_rate": 1.9526132404181185e-05,
"loss": 0.0387,
"step": 4980
},
{
"epoch": 2.35,
"learning_rate": 1.9386759581881535e-05,
"loss": 0.0332,
"step": 4990
},
{
"epoch": 2.35,
"learning_rate": 1.9247386759581884e-05,
"loss": 0.0409,
"step": 5000
},
{
"epoch": 2.36,
"learning_rate": 1.910801393728223e-05,
"loss": 0.0371,
"step": 5010
},
{
"epoch": 2.36,
"learning_rate": 1.896864111498258e-05,
"loss": 0.0448,
"step": 5020
},
{
"epoch": 2.37,
"learning_rate": 1.8829268292682926e-05,
"loss": 0.0517,
"step": 5030
},
{
"epoch": 2.37,
"learning_rate": 1.8689895470383276e-05,
"loss": 0.0436,
"step": 5040
},
{
"epoch": 2.38,
"learning_rate": 1.8550522648083626e-05,
"loss": 0.0394,
"step": 5050
},
{
"epoch": 2.38,
"learning_rate": 1.8411149825783975e-05,
"loss": 0.046,
"step": 5060
},
{
"epoch": 2.38,
"learning_rate": 1.827177700348432e-05,
"loss": 0.0414,
"step": 5070
},
{
"epoch": 2.39,
"learning_rate": 1.813240418118467e-05,
"loss": 0.0338,
"step": 5080
},
{
"epoch": 2.39,
"learning_rate": 1.7993031358885017e-05,
"loss": 0.046,
"step": 5090
},
{
"epoch": 2.4,
"learning_rate": 1.7853658536585367e-05,
"loss": 0.0481,
"step": 5100
},
{
"epoch": 2.4,
"learning_rate": 1.7714285714285717e-05,
"loss": 0.0428,
"step": 5110
},
{
"epoch": 2.41,
"learning_rate": 1.7574912891986066e-05,
"loss": 0.0365,
"step": 5120
},
{
"epoch": 2.41,
"learning_rate": 1.7435540069686412e-05,
"loss": 0.046,
"step": 5130
},
{
"epoch": 2.42,
"learning_rate": 1.7296167247386762e-05,
"loss": 0.0357,
"step": 5140
},
{
"epoch": 2.42,
"learning_rate": 1.7156794425087108e-05,
"loss": 0.0387,
"step": 5150
},
{
"epoch": 2.43,
"learning_rate": 1.7017421602787458e-05,
"loss": 0.0364,
"step": 5160
},
{
"epoch": 2.43,
"learning_rate": 1.6878048780487804e-05,
"loss": 0.041,
"step": 5170
},
{
"epoch": 2.44,
"learning_rate": 1.6738675958188154e-05,
"loss": 0.0431,
"step": 5180
},
{
"epoch": 2.44,
"learning_rate": 1.6599303135888503e-05,
"loss": 0.0456,
"step": 5190
},
{
"epoch": 2.45,
"learning_rate": 1.6459930313588853e-05,
"loss": 0.0446,
"step": 5200
},
{
"epoch": 2.45,
"learning_rate": 1.63205574912892e-05,
"loss": 0.0349,
"step": 5210
},
{
"epoch": 2.46,
"learning_rate": 1.618118466898955e-05,
"loss": 0.0405,
"step": 5220
},
{
"epoch": 2.46,
"learning_rate": 1.6041811846689895e-05,
"loss": 0.0447,
"step": 5230
},
{
"epoch": 2.46,
"learning_rate": 1.5902439024390245e-05,
"loss": 0.0359,
"step": 5240
},
{
"epoch": 2.47,
"learning_rate": 1.5763066202090594e-05,
"loss": 0.0391,
"step": 5250
},
{
"epoch": 2.47,
"learning_rate": 1.5623693379790944e-05,
"loss": 0.0412,
"step": 5260
},
{
"epoch": 2.48,
"learning_rate": 1.548432055749129e-05,
"loss": 0.0384,
"step": 5270
},
{
"epoch": 2.48,
"learning_rate": 1.534494773519164e-05,
"loss": 0.0417,
"step": 5280
},
{
"epoch": 2.49,
"learning_rate": 1.5205574912891988e-05,
"loss": 0.0442,
"step": 5290
},
{
"epoch": 2.49,
"learning_rate": 1.5066202090592337e-05,
"loss": 0.0462,
"step": 5300
},
{
"epoch": 2.5,
"learning_rate": 1.4926829268292684e-05,
"loss": 0.0357,
"step": 5310
},
{
"epoch": 2.5,
"learning_rate": 1.4787456445993033e-05,
"loss": 0.0431,
"step": 5320
},
{
"epoch": 2.51,
"learning_rate": 1.4648083623693381e-05,
"loss": 0.0464,
"step": 5330
},
{
"epoch": 2.51,
"learning_rate": 1.4508710801393729e-05,
"loss": 0.0324,
"step": 5340
},
{
"epoch": 2.52,
"learning_rate": 1.4369337979094079e-05,
"loss": 0.046,
"step": 5350
},
{
"epoch": 2.52,
"learning_rate": 1.4229965156794425e-05,
"loss": 0.0494,
"step": 5360
},
{
"epoch": 2.53,
"learning_rate": 1.4090592334494775e-05,
"loss": 0.0406,
"step": 5370
},
{
"epoch": 2.53,
"learning_rate": 1.3951219512195122e-05,
"loss": 0.0474,
"step": 5380
},
{
"epoch": 2.54,
"learning_rate": 1.3811846689895472e-05,
"loss": 0.0434,
"step": 5390
},
{
"epoch": 2.54,
"learning_rate": 1.3672473867595818e-05,
"loss": 0.0502,
"step": 5400
},
{
"epoch": 2.54,
"learning_rate": 1.3533101045296168e-05,
"loss": 0.0461,
"step": 5410
},
{
"epoch": 2.55,
"learning_rate": 1.3393728222996516e-05,
"loss": 0.0414,
"step": 5420
},
{
"epoch": 2.55,
"learning_rate": 1.3254355400696866e-05,
"loss": 0.0386,
"step": 5430
},
{
"epoch": 2.56,
"learning_rate": 1.3114982578397213e-05,
"loss": 0.0377,
"step": 5440
},
{
"epoch": 2.56,
"learning_rate": 1.2975609756097563e-05,
"loss": 0.0501,
"step": 5450
},
{
"epoch": 2.57,
"learning_rate": 1.283623693379791e-05,
"loss": 0.0433,
"step": 5460
},
{
"epoch": 2.57,
"learning_rate": 1.2696864111498259e-05,
"loss": 0.0405,
"step": 5470
},
{
"epoch": 2.58,
"learning_rate": 1.2557491289198607e-05,
"loss": 0.044,
"step": 5480
},
{
"epoch": 2.58,
"learning_rate": 1.2418118466898957e-05,
"loss": 0.0463,
"step": 5490
},
{
"epoch": 2.59,
"learning_rate": 1.2278745644599304e-05,
"loss": 0.0442,
"step": 5500
},
{
"epoch": 2.59,
"learning_rate": 1.2139372822299652e-05,
"loss": 0.0422,
"step": 5510
},
{
"epoch": 2.6,
"learning_rate": 1.2e-05,
"loss": 0.0366,
"step": 5520
},
{
"epoch": 2.6,
"learning_rate": 1.186062717770035e-05,
"loss": 0.0283,
"step": 5530
},
{
"epoch": 2.61,
"learning_rate": 1.1721254355400698e-05,
"loss": 0.034,
"step": 5540
},
{
"epoch": 2.61,
"learning_rate": 1.1581881533101047e-05,
"loss": 0.0441,
"step": 5550
},
{
"epoch": 2.62,
"learning_rate": 1.1442508710801394e-05,
"loss": 0.0364,
"step": 5560
},
{
"epoch": 2.62,
"learning_rate": 1.1303135888501743e-05,
"loss": 0.0535,
"step": 5570
},
{
"epoch": 2.62,
"learning_rate": 1.1163763066202091e-05,
"loss": 0.0502,
"step": 5580
},
{
"epoch": 2.63,
"learning_rate": 1.1024390243902441e-05,
"loss": 0.0441,
"step": 5590
},
{
"epoch": 2.63,
"learning_rate": 1.0885017421602789e-05,
"loss": 0.0359,
"step": 5600
},
{
"epoch": 2.64,
"learning_rate": 1.0745644599303138e-05,
"loss": 0.0343,
"step": 5610
},
{
"epoch": 2.64,
"learning_rate": 1.0606271777003485e-05,
"loss": 0.0461,
"step": 5620
},
{
"epoch": 2.65,
"learning_rate": 1.0466898954703834e-05,
"loss": 0.0396,
"step": 5630
},
{
"epoch": 2.65,
"learning_rate": 1.0327526132404182e-05,
"loss": 0.0348,
"step": 5640
},
{
"epoch": 2.66,
"learning_rate": 1.018815331010453e-05,
"loss": 0.0428,
"step": 5650
},
{
"epoch": 2.66,
"learning_rate": 1.0048780487804878e-05,
"loss": 0.0394,
"step": 5660
},
{
"epoch": 2.67,
"learning_rate": 9.909407665505228e-06,
"loss": 0.0348,
"step": 5670
},
{
"epoch": 2.67,
"learning_rate": 9.770034843205576e-06,
"loss": 0.0484,
"step": 5680
},
{
"epoch": 2.68,
"learning_rate": 9.630662020905924e-06,
"loss": 0.0452,
"step": 5690
},
{
"epoch": 2.68,
"learning_rate": 9.491289198606273e-06,
"loss": 0.0365,
"step": 5700
},
{
"epoch": 2.69,
"learning_rate": 9.351916376306621e-06,
"loss": 0.0365,
"step": 5710
},
{
"epoch": 2.69,
"learning_rate": 9.212543554006969e-06,
"loss": 0.0368,
"step": 5720
},
{
"epoch": 2.7,
"learning_rate": 9.073170731707319e-06,
"loss": 0.051,
"step": 5730
},
{
"epoch": 2.7,
"learning_rate": 8.933797909407667e-06,
"loss": 0.0454,
"step": 5740
},
{
"epoch": 2.7,
"learning_rate": 8.794425087108015e-06,
"loss": 0.0429,
"step": 5750
},
{
"epoch": 2.71,
"learning_rate": 8.655052264808364e-06,
"loss": 0.0384,
"step": 5760
},
{
"epoch": 2.71,
"learning_rate": 8.515679442508712e-06,
"loss": 0.0391,
"step": 5770
},
{
"epoch": 2.72,
"learning_rate": 8.37630662020906e-06,
"loss": 0.0351,
"step": 5780
},
{
"epoch": 2.72,
"learning_rate": 8.23693379790941e-06,
"loss": 0.05,
"step": 5790
},
{
"epoch": 2.73,
"learning_rate": 8.097560975609758e-06,
"loss": 0.0361,
"step": 5800
},
{
"epoch": 2.73,
"learning_rate": 7.958188153310104e-06,
"loss": 0.0365,
"step": 5810
},
{
"epoch": 2.74,
"learning_rate": 7.818815331010453e-06,
"loss": 0.0414,
"step": 5820
},
{
"epoch": 2.74,
"learning_rate": 7.679442508710801e-06,
"loss": 0.0513,
"step": 5830
},
{
"epoch": 2.75,
"learning_rate": 7.54006968641115e-06,
"loss": 0.0406,
"step": 5840
},
{
"epoch": 2.75,
"learning_rate": 7.400696864111498e-06,
"loss": 0.0449,
"step": 5850
},
{
"epoch": 2.76,
"learning_rate": 7.261324041811847e-06,
"loss": 0.0413,
"step": 5860
},
{
"epoch": 2.76,
"learning_rate": 7.121951219512196e-06,
"loss": 0.0389,
"step": 5870
},
{
"epoch": 2.77,
"learning_rate": 6.982578397212544e-06,
"loss": 0.0362,
"step": 5880
},
{
"epoch": 2.77,
"learning_rate": 6.843205574912892e-06,
"loss": 0.0418,
"step": 5890
},
{
"epoch": 2.78,
"learning_rate": 6.703832752613241e-06,
"loss": 0.0365,
"step": 5900
},
{
"epoch": 2.78,
"learning_rate": 6.564459930313589e-06,
"loss": 0.0377,
"step": 5910
},
{
"epoch": 2.78,
"learning_rate": 6.425087108013938e-06,
"loss": 0.0476,
"step": 5920
},
{
"epoch": 2.79,
"learning_rate": 6.285714285714286e-06,
"loss": 0.0453,
"step": 5930
},
{
"epoch": 2.79,
"learning_rate": 6.1463414634146346e-06,
"loss": 0.0412,
"step": 5940
},
{
"epoch": 2.8,
"learning_rate": 6.006968641114983e-06,
"loss": 0.0493,
"step": 5950
},
{
"epoch": 2.8,
"learning_rate": 5.867595818815331e-06,
"loss": 0.0429,
"step": 5960
},
{
"epoch": 2.81,
"learning_rate": 5.72822299651568e-06,
"loss": 0.0406,
"step": 5970
},
{
"epoch": 2.81,
"learning_rate": 5.588850174216028e-06,
"loss": 0.0423,
"step": 5980
},
{
"epoch": 2.82,
"learning_rate": 5.449477351916377e-06,
"loss": 0.0353,
"step": 5990
},
{
"epoch": 2.82,
"learning_rate": 5.3101045296167255e-06,
"loss": 0.0362,
"step": 6000
},
{
"epoch": 2.83,
"learning_rate": 5.1707317073170735e-06,
"loss": 0.0478,
"step": 6010
},
{
"epoch": 2.83,
"learning_rate": 5.031358885017422e-06,
"loss": 0.0431,
"step": 6020
},
{
"epoch": 2.84,
"learning_rate": 4.891986062717771e-06,
"loss": 0.0354,
"step": 6030
},
{
"epoch": 2.84,
"learning_rate": 4.752613240418119e-06,
"loss": 0.0414,
"step": 6040
},
{
"epoch": 2.85,
"learning_rate": 4.613240418118467e-06,
"loss": 0.0397,
"step": 6050
},
{
"epoch": 2.85,
"learning_rate": 4.473867595818816e-06,
"loss": 0.0351,
"step": 6060
},
{
"epoch": 2.86,
"learning_rate": 4.334494773519164e-06,
"loss": 0.0331,
"step": 6070
},
{
"epoch": 2.86,
"learning_rate": 4.195121951219512e-06,
"loss": 0.0423,
"step": 6080
},
{
"epoch": 2.86,
"learning_rate": 4.055749128919861e-06,
"loss": 0.042,
"step": 6090
},
{
"epoch": 2.87,
"learning_rate": 3.916376306620209e-06,
"loss": 0.0285,
"step": 6100
},
{
"epoch": 2.87,
"learning_rate": 3.777003484320558e-06,
"loss": 0.0447,
"step": 6110
},
{
"epoch": 2.88,
"learning_rate": 3.6376306620209062e-06,
"loss": 0.0389,
"step": 6120
},
{
"epoch": 2.88,
"learning_rate": 3.4982578397212546e-06,
"loss": 0.0395,
"step": 6130
},
{
"epoch": 2.89,
"learning_rate": 3.358885017421603e-06,
"loss": 0.0364,
"step": 6140
},
{
"epoch": 2.89,
"learning_rate": 3.2195121951219517e-06,
"loss": 0.054,
"step": 6150
},
{
"epoch": 2.9,
"learning_rate": 3.0801393728223e-06,
"loss": 0.0442,
"step": 6160
},
{
"epoch": 2.9,
"learning_rate": 2.9407665505226484e-06,
"loss": 0.0413,
"step": 6170
},
{
"epoch": 2.91,
"learning_rate": 2.8013937282229968e-06,
"loss": 0.0406,
"step": 6180
},
{
"epoch": 2.91,
"learning_rate": 2.6620209059233455e-06,
"loss": 0.047,
"step": 6190
},
{
"epoch": 2.92,
"learning_rate": 2.522648083623694e-06,
"loss": 0.0382,
"step": 6200
},
{
"epoch": 2.92,
"learning_rate": 2.383275261324042e-06,
"loss": 0.043,
"step": 6210
},
{
"epoch": 2.93,
"learning_rate": 2.2439024390243906e-06,
"loss": 0.0435,
"step": 6220
},
{
"epoch": 2.93,
"learning_rate": 2.104529616724739e-06,
"loss": 0.0436,
"step": 6230
},
{
"epoch": 2.94,
"learning_rate": 1.9651567944250873e-06,
"loss": 0.0472,
"step": 6240
},
{
"epoch": 2.94,
"learning_rate": 1.8257839721254357e-06,
"loss": 0.0368,
"step": 6250
},
{
"epoch": 2.94,
"learning_rate": 1.686411149825784e-06,
"loss": 0.038,
"step": 6260
},
{
"epoch": 2.95,
"learning_rate": 1.5470383275261324e-06,
"loss": 0.0437,
"step": 6270
},
{
"epoch": 2.95,
"learning_rate": 1.407665505226481e-06,
"loss": 0.0353,
"step": 6280
},
{
"epoch": 2.96,
"learning_rate": 1.2682926829268293e-06,
"loss": 0.044,
"step": 6290
},
{
"epoch": 2.96,
"learning_rate": 1.1289198606271779e-06,
"loss": 0.0358,
"step": 6300
},
{
"epoch": 2.97,
"learning_rate": 9.895470383275262e-07,
"loss": 0.0378,
"step": 6310
},
{
"epoch": 2.97,
"learning_rate": 8.501742160278746e-07,
"loss": 0.0346,
"step": 6320
},
{
"epoch": 2.98,
"learning_rate": 7.10801393728223e-07,
"loss": 0.0456,
"step": 6330
},
{
"epoch": 2.98,
"learning_rate": 5.714285714285715e-07,
"loss": 0.0494,
"step": 6340
},
{
"epoch": 2.99,
"learning_rate": 4.320557491289199e-07,
"loss": 0.0406,
"step": 6350
},
{
"epoch": 2.99,
"learning_rate": 2.926829268292683e-07,
"loss": 0.0386,
"step": 6360
},
{
"epoch": 3.0,
"learning_rate": 1.5331010452961674e-07,
"loss": 0.0415,
"step": 6370
},
{
"epoch": 3.0,
"eval_accuracy": 0.9769126125154315,
"eval_f1": 0.7849694196330357,
"eval_loss": 0.06933891773223877,
"eval_precision": 0.7739696312364425,
"eval_recall": 0.7962863774326013,
"eval_runtime": 16.4386,
"eval_samples_per_second": 861.385,
"eval_steps_per_second": 107.673,
"step": 6378
},
{
"epoch": 3.0,
"step": 6378,
"total_flos": 1.2518895383371872e+16,
"train_loss": 0.06623676680927928,
"train_runtime": 577.8703,
"train_samples_per_second": 529.624,
"train_steps_per_second": 11.037
}
],
"logging_steps": 10,
"max_steps": 6378,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 1.2518895383371872e+16,
"trial_name": null,
"trial_params": null
}