Manirathinam21's picture
Intial commit
85dc566
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9545454545454546,
"global_step": 6500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.0000000000000003e-06,
"loss": 3.1215,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.000000000000001e-06,
"loss": 3.0579,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 6e-06,
"loss": 3.1027,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 8.000000000000001e-06,
"loss": 3.0934,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 3.0273,
"step": 50
},
{
"epoch": 0.03,
"learning_rate": 1.2e-05,
"loss": 2.9829,
"step": 60
},
{
"epoch": 0.03,
"learning_rate": 1.4e-05,
"loss": 2.8801,
"step": 70
},
{
"epoch": 0.04,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.7154,
"step": 80
},
{
"epoch": 0.04,
"learning_rate": 1.8e-05,
"loss": 2.5808,
"step": 90
},
{
"epoch": 0.05,
"learning_rate": 2e-05,
"loss": 2.2878,
"step": 100
},
{
"epoch": 0.05,
"learning_rate": 1.9969230769230773e-05,
"loss": 1.8999,
"step": 110
},
{
"epoch": 0.05,
"learning_rate": 1.993846153846154e-05,
"loss": 1.5681,
"step": 120
},
{
"epoch": 0.06,
"learning_rate": 1.990769230769231e-05,
"loss": 1.2633,
"step": 130
},
{
"epoch": 0.06,
"learning_rate": 1.987692307692308e-05,
"loss": 1.0283,
"step": 140
},
{
"epoch": 0.07,
"learning_rate": 1.9846153846153847e-05,
"loss": 0.9242,
"step": 150
},
{
"epoch": 0.07,
"learning_rate": 1.9815384615384618e-05,
"loss": 0.6346,
"step": 160
},
{
"epoch": 0.08,
"learning_rate": 1.9784615384615386e-05,
"loss": 0.6004,
"step": 170
},
{
"epoch": 0.08,
"learning_rate": 1.9753846153846153e-05,
"loss": 0.5833,
"step": 180
},
{
"epoch": 0.09,
"learning_rate": 1.9723076923076924e-05,
"loss": 0.3977,
"step": 190
},
{
"epoch": 0.09,
"learning_rate": 1.9692307692307696e-05,
"loss": 0.3478,
"step": 200
},
{
"epoch": 0.1,
"learning_rate": 1.9661538461538463e-05,
"loss": 0.3881,
"step": 210
},
{
"epoch": 0.1,
"learning_rate": 1.9630769230769234e-05,
"loss": 0.2242,
"step": 220
},
{
"epoch": 0.1,
"learning_rate": 1.9600000000000002e-05,
"loss": 0.3317,
"step": 230
},
{
"epoch": 0.11,
"learning_rate": 1.9569230769230773e-05,
"loss": 0.1648,
"step": 240
},
{
"epoch": 0.11,
"learning_rate": 1.953846153846154e-05,
"loss": 0.1313,
"step": 250
},
{
"epoch": 0.12,
"learning_rate": 1.950769230769231e-05,
"loss": 0.238,
"step": 260
},
{
"epoch": 0.12,
"learning_rate": 1.9476923076923076e-05,
"loss": 0.1908,
"step": 270
},
{
"epoch": 0.13,
"learning_rate": 1.9446153846153847e-05,
"loss": 0.085,
"step": 280
},
{
"epoch": 0.13,
"learning_rate": 1.9415384615384615e-05,
"loss": 0.1933,
"step": 290
},
{
"epoch": 0.14,
"learning_rate": 1.9384615384615386e-05,
"loss": 0.304,
"step": 300
},
{
"epoch": 0.14,
"learning_rate": 1.9353846153846157e-05,
"loss": 0.0776,
"step": 310
},
{
"epoch": 0.15,
"learning_rate": 1.9323076923076925e-05,
"loss": 0.2,
"step": 320
},
{
"epoch": 0.15,
"learning_rate": 1.9292307692307696e-05,
"loss": 0.1345,
"step": 330
},
{
"epoch": 0.15,
"learning_rate": 1.9261538461538464e-05,
"loss": 0.1144,
"step": 340
},
{
"epoch": 0.16,
"learning_rate": 1.923076923076923e-05,
"loss": 0.1022,
"step": 350
},
{
"epoch": 0.16,
"learning_rate": 1.9200000000000003e-05,
"loss": 0.0807,
"step": 360
},
{
"epoch": 0.17,
"learning_rate": 1.916923076923077e-05,
"loss": 0.0418,
"step": 370
},
{
"epoch": 0.17,
"learning_rate": 1.9138461538461538e-05,
"loss": 0.1183,
"step": 380
},
{
"epoch": 0.18,
"learning_rate": 1.910769230769231e-05,
"loss": 0.095,
"step": 390
},
{
"epoch": 0.18,
"learning_rate": 1.907692307692308e-05,
"loss": 0.0858,
"step": 400
},
{
"epoch": 0.19,
"learning_rate": 1.9046153846153848e-05,
"loss": 0.1787,
"step": 410
},
{
"epoch": 0.19,
"learning_rate": 1.901538461538462e-05,
"loss": 0.118,
"step": 420
},
{
"epoch": 0.2,
"learning_rate": 1.8984615384615387e-05,
"loss": 0.212,
"step": 430
},
{
"epoch": 0.2,
"learning_rate": 1.8953846153846158e-05,
"loss": 0.0655,
"step": 440
},
{
"epoch": 0.2,
"learning_rate": 1.8923076923076925e-05,
"loss": 0.1352,
"step": 450
},
{
"epoch": 0.21,
"learning_rate": 1.8892307692307693e-05,
"loss": 0.1011,
"step": 460
},
{
"epoch": 0.21,
"learning_rate": 1.886153846153846e-05,
"loss": 0.0258,
"step": 470
},
{
"epoch": 0.22,
"learning_rate": 1.8830769230769232e-05,
"loss": 0.1673,
"step": 480
},
{
"epoch": 0.22,
"learning_rate": 1.88e-05,
"loss": 0.0257,
"step": 490
},
{
"epoch": 0.23,
"learning_rate": 1.876923076923077e-05,
"loss": 0.0242,
"step": 500
},
{
"epoch": 0.23,
"learning_rate": 1.8738461538461542e-05,
"loss": 0.0987,
"step": 510
},
{
"epoch": 0.24,
"learning_rate": 1.870769230769231e-05,
"loss": 0.1029,
"step": 520
},
{
"epoch": 0.24,
"learning_rate": 1.867692307692308e-05,
"loss": 0.0693,
"step": 530
},
{
"epoch": 0.25,
"learning_rate": 1.8646153846153848e-05,
"loss": 0.0703,
"step": 540
},
{
"epoch": 0.25,
"learning_rate": 1.8615384615384616e-05,
"loss": 0.1149,
"step": 550
},
{
"epoch": 0.25,
"learning_rate": 1.8584615384615387e-05,
"loss": 0.0203,
"step": 560
},
{
"epoch": 0.26,
"learning_rate": 1.8553846153846155e-05,
"loss": 0.1444,
"step": 570
},
{
"epoch": 0.26,
"learning_rate": 1.8523076923076922e-05,
"loss": 0.0241,
"step": 580
},
{
"epoch": 0.27,
"learning_rate": 1.8492307692307694e-05,
"loss": 0.0439,
"step": 590
},
{
"epoch": 0.27,
"learning_rate": 1.8461538461538465e-05,
"loss": 0.1108,
"step": 600
},
{
"epoch": 0.28,
"learning_rate": 1.8430769230769232e-05,
"loss": 0.124,
"step": 610
},
{
"epoch": 0.28,
"learning_rate": 1.8400000000000003e-05,
"loss": 0.2086,
"step": 620
},
{
"epoch": 0.29,
"learning_rate": 1.836923076923077e-05,
"loss": 0.0169,
"step": 630
},
{
"epoch": 0.29,
"learning_rate": 1.8338461538461542e-05,
"loss": 0.0163,
"step": 640
},
{
"epoch": 0.3,
"learning_rate": 1.830769230769231e-05,
"loss": 0.0602,
"step": 650
},
{
"epoch": 0.3,
"learning_rate": 1.8276923076923078e-05,
"loss": 0.0148,
"step": 660
},
{
"epoch": 0.3,
"learning_rate": 1.8246153846153845e-05,
"loss": 0.0145,
"step": 670
},
{
"epoch": 0.31,
"learning_rate": 1.8215384615384616e-05,
"loss": 0.0137,
"step": 680
},
{
"epoch": 0.31,
"learning_rate": 1.8184615384615384e-05,
"loss": 0.1912,
"step": 690
},
{
"epoch": 0.32,
"learning_rate": 1.8153846153846155e-05,
"loss": 0.088,
"step": 700
},
{
"epoch": 0.32,
"learning_rate": 1.8123076923076926e-05,
"loss": 0.1182,
"step": 710
},
{
"epoch": 0.33,
"learning_rate": 1.8092307692307694e-05,
"loss": 0.1519,
"step": 720
},
{
"epoch": 0.33,
"learning_rate": 1.8061538461538465e-05,
"loss": 0.0122,
"step": 730
},
{
"epoch": 0.34,
"learning_rate": 1.8030769230769233e-05,
"loss": 0.0829,
"step": 740
},
{
"epoch": 0.34,
"learning_rate": 1.8e-05,
"loss": 0.0192,
"step": 750
},
{
"epoch": 0.35,
"learning_rate": 1.796923076923077e-05,
"loss": 0.0399,
"step": 760
},
{
"epoch": 0.35,
"learning_rate": 1.793846153846154e-05,
"loss": 0.1442,
"step": 770
},
{
"epoch": 0.35,
"learning_rate": 1.7907692307692307e-05,
"loss": 0.2089,
"step": 780
},
{
"epoch": 0.36,
"learning_rate": 1.7876923076923078e-05,
"loss": 0.141,
"step": 790
},
{
"epoch": 0.36,
"learning_rate": 1.784615384615385e-05,
"loss": 0.0447,
"step": 800
},
{
"epoch": 0.37,
"learning_rate": 1.7815384615384617e-05,
"loss": 0.0111,
"step": 810
},
{
"epoch": 0.37,
"learning_rate": 1.7784615384615388e-05,
"loss": 0.262,
"step": 820
},
{
"epoch": 0.38,
"learning_rate": 1.7753846153846156e-05,
"loss": 0.2721,
"step": 830
},
{
"epoch": 0.38,
"learning_rate": 1.7723076923076927e-05,
"loss": 0.0332,
"step": 840
},
{
"epoch": 0.39,
"learning_rate": 1.7692307692307694e-05,
"loss": 0.0683,
"step": 850
},
{
"epoch": 0.39,
"learning_rate": 1.7661538461538462e-05,
"loss": 0.0987,
"step": 860
},
{
"epoch": 0.4,
"learning_rate": 1.763076923076923e-05,
"loss": 0.1833,
"step": 870
},
{
"epoch": 0.4,
"learning_rate": 1.76e-05,
"loss": 0.0347,
"step": 880
},
{
"epoch": 0.4,
"learning_rate": 1.7569230769230772e-05,
"loss": 0.0425,
"step": 890
},
{
"epoch": 0.41,
"learning_rate": 1.753846153846154e-05,
"loss": 0.0615,
"step": 900
},
{
"epoch": 0.41,
"learning_rate": 1.750769230769231e-05,
"loss": 0.1378,
"step": 910
},
{
"epoch": 0.42,
"learning_rate": 1.747692307692308e-05,
"loss": 0.1481,
"step": 920
},
{
"epoch": 0.42,
"learning_rate": 1.744615384615385e-05,
"loss": 0.0604,
"step": 930
},
{
"epoch": 0.43,
"learning_rate": 1.7415384615384617e-05,
"loss": 0.0099,
"step": 940
},
{
"epoch": 0.43,
"learning_rate": 1.7384615384615385e-05,
"loss": 0.0448,
"step": 950
},
{
"epoch": 0.44,
"learning_rate": 1.7353846153846156e-05,
"loss": 0.0093,
"step": 960
},
{
"epoch": 0.44,
"learning_rate": 1.7323076923076924e-05,
"loss": 0.0078,
"step": 970
},
{
"epoch": 0.45,
"learning_rate": 1.729230769230769e-05,
"loss": 0.0731,
"step": 980
},
{
"epoch": 0.45,
"learning_rate": 1.7261538461538463e-05,
"loss": 0.1749,
"step": 990
},
{
"epoch": 0.45,
"learning_rate": 1.7230769230769234e-05,
"loss": 0.0954,
"step": 1000
},
{
"epoch": 0.46,
"learning_rate": 1.72e-05,
"loss": 0.009,
"step": 1010
},
{
"epoch": 0.46,
"learning_rate": 1.7169230769230772e-05,
"loss": 0.0986,
"step": 1020
},
{
"epoch": 0.47,
"learning_rate": 1.713846153846154e-05,
"loss": 0.1027,
"step": 1030
},
{
"epoch": 0.47,
"learning_rate": 1.710769230769231e-05,
"loss": 0.008,
"step": 1040
},
{
"epoch": 0.48,
"learning_rate": 1.707692307692308e-05,
"loss": 0.009,
"step": 1050
},
{
"epoch": 0.48,
"learning_rate": 1.7046153846153847e-05,
"loss": 0.0071,
"step": 1060
},
{
"epoch": 0.49,
"learning_rate": 1.7015384615384614e-05,
"loss": 0.1062,
"step": 1070
},
{
"epoch": 0.49,
"learning_rate": 1.6984615384615385e-05,
"loss": 0.0069,
"step": 1080
},
{
"epoch": 0.5,
"learning_rate": 1.6953846153846156e-05,
"loss": 0.0069,
"step": 1090
},
{
"epoch": 0.5,
"learning_rate": 1.6923076923076924e-05,
"loss": 0.1227,
"step": 1100
},
{
"epoch": 0.5,
"learning_rate": 1.6892307692307695e-05,
"loss": 0.0422,
"step": 1110
},
{
"epoch": 0.51,
"learning_rate": 1.6861538461538463e-05,
"loss": 0.1685,
"step": 1120
},
{
"epoch": 0.51,
"learning_rate": 1.6830769230769234e-05,
"loss": 0.0902,
"step": 1130
},
{
"epoch": 0.52,
"learning_rate": 1.6800000000000002e-05,
"loss": 0.1685,
"step": 1140
},
{
"epoch": 0.52,
"learning_rate": 1.676923076923077e-05,
"loss": 0.0065,
"step": 1150
},
{
"epoch": 0.53,
"learning_rate": 1.673846153846154e-05,
"loss": 0.0173,
"step": 1160
},
{
"epoch": 0.53,
"learning_rate": 1.6707692307692308e-05,
"loss": 0.157,
"step": 1170
},
{
"epoch": 0.54,
"learning_rate": 1.6676923076923076e-05,
"loss": 0.0081,
"step": 1180
},
{
"epoch": 0.54,
"learning_rate": 1.6646153846153847e-05,
"loss": 0.1193,
"step": 1190
},
{
"epoch": 0.55,
"learning_rate": 1.6615384615384618e-05,
"loss": 0.0083,
"step": 1200
},
{
"epoch": 0.55,
"learning_rate": 1.6584615384615386e-05,
"loss": 0.0076,
"step": 1210
},
{
"epoch": 0.55,
"learning_rate": 1.6553846153846157e-05,
"loss": 0.007,
"step": 1220
},
{
"epoch": 0.56,
"learning_rate": 1.6523076923076925e-05,
"loss": 0.0059,
"step": 1230
},
{
"epoch": 0.56,
"learning_rate": 1.6492307692307696e-05,
"loss": 0.0802,
"step": 1240
},
{
"epoch": 0.57,
"learning_rate": 1.6461538461538463e-05,
"loss": 0.1481,
"step": 1250
},
{
"epoch": 0.57,
"learning_rate": 1.643076923076923e-05,
"loss": 0.0699,
"step": 1260
},
{
"epoch": 0.58,
"learning_rate": 1.64e-05,
"loss": 0.007,
"step": 1270
},
{
"epoch": 0.58,
"learning_rate": 1.636923076923077e-05,
"loss": 0.008,
"step": 1280
},
{
"epoch": 0.59,
"learning_rate": 1.633846153846154e-05,
"loss": 0.0059,
"step": 1290
},
{
"epoch": 0.59,
"learning_rate": 1.630769230769231e-05,
"loss": 0.0725,
"step": 1300
},
{
"epoch": 0.6,
"learning_rate": 1.627692307692308e-05,
"loss": 0.2037,
"step": 1310
},
{
"epoch": 0.6,
"learning_rate": 1.6246153846153848e-05,
"loss": 0.1485,
"step": 1320
},
{
"epoch": 0.6,
"learning_rate": 1.621538461538462e-05,
"loss": 0.0085,
"step": 1330
},
{
"epoch": 0.61,
"learning_rate": 1.6184615384615386e-05,
"loss": 0.0591,
"step": 1340
},
{
"epoch": 0.61,
"learning_rate": 1.6153846153846154e-05,
"loss": 0.0824,
"step": 1350
},
{
"epoch": 0.62,
"learning_rate": 1.6123076923076925e-05,
"loss": 0.0402,
"step": 1360
},
{
"epoch": 0.62,
"learning_rate": 1.6092307692307693e-05,
"loss": 0.005,
"step": 1370
},
{
"epoch": 0.63,
"learning_rate": 1.606153846153846e-05,
"loss": 0.0052,
"step": 1380
},
{
"epoch": 0.63,
"learning_rate": 1.603076923076923e-05,
"loss": 0.005,
"step": 1390
},
{
"epoch": 0.64,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0838,
"step": 1400
},
{
"epoch": 0.64,
"learning_rate": 1.596923076923077e-05,
"loss": 0.0052,
"step": 1410
},
{
"epoch": 0.65,
"learning_rate": 1.593846153846154e-05,
"loss": 0.0244,
"step": 1420
},
{
"epoch": 0.65,
"learning_rate": 1.590769230769231e-05,
"loss": 0.1059,
"step": 1430
},
{
"epoch": 0.65,
"learning_rate": 1.587692307692308e-05,
"loss": 0.1774,
"step": 1440
},
{
"epoch": 0.66,
"learning_rate": 1.5846153846153848e-05,
"loss": 0.1231,
"step": 1450
},
{
"epoch": 0.66,
"learning_rate": 1.5815384615384616e-05,
"loss": 0.0072,
"step": 1460
},
{
"epoch": 0.67,
"learning_rate": 1.5784615384615383e-05,
"loss": 0.0059,
"step": 1470
},
{
"epoch": 0.67,
"learning_rate": 1.5753846153846154e-05,
"loss": 0.0609,
"step": 1480
},
{
"epoch": 0.68,
"learning_rate": 1.5723076923076926e-05,
"loss": 0.2579,
"step": 1490
},
{
"epoch": 0.68,
"learning_rate": 1.5692307692307693e-05,
"loss": 0.0719,
"step": 1500
},
{
"epoch": 0.69,
"learning_rate": 1.5661538461538464e-05,
"loss": 0.0698,
"step": 1510
},
{
"epoch": 0.69,
"learning_rate": 1.5630769230769232e-05,
"loss": 0.0048,
"step": 1520
},
{
"epoch": 0.7,
"learning_rate": 1.5600000000000003e-05,
"loss": 0.0463,
"step": 1530
},
{
"epoch": 0.7,
"learning_rate": 1.556923076923077e-05,
"loss": 0.0206,
"step": 1540
},
{
"epoch": 0.7,
"learning_rate": 1.553846153846154e-05,
"loss": 0.0049,
"step": 1550
},
{
"epoch": 0.71,
"learning_rate": 1.550769230769231e-05,
"loss": 0.0749,
"step": 1560
},
{
"epoch": 0.71,
"learning_rate": 1.5476923076923077e-05,
"loss": 0.0638,
"step": 1570
},
{
"epoch": 0.72,
"learning_rate": 1.544615384615385e-05,
"loss": 0.0781,
"step": 1580
},
{
"epoch": 0.72,
"learning_rate": 1.5415384615384616e-05,
"loss": 0.0125,
"step": 1590
},
{
"epoch": 0.73,
"learning_rate": 1.5384615384615387e-05,
"loss": 0.0055,
"step": 1600
},
{
"epoch": 0.73,
"learning_rate": 1.5353846153846155e-05,
"loss": 0.0053,
"step": 1610
},
{
"epoch": 0.74,
"learning_rate": 1.5323076923076926e-05,
"loss": 0.2656,
"step": 1620
},
{
"epoch": 0.74,
"learning_rate": 1.5292307692307694e-05,
"loss": 0.0034,
"step": 1630
},
{
"epoch": 0.75,
"learning_rate": 1.5261538461538465e-05,
"loss": 0.1076,
"step": 1640
},
{
"epoch": 0.75,
"learning_rate": 1.523076923076923e-05,
"loss": 0.0046,
"step": 1650
},
{
"epoch": 0.75,
"learning_rate": 1.5200000000000002e-05,
"loss": 0.3507,
"step": 1660
},
{
"epoch": 0.76,
"learning_rate": 1.516923076923077e-05,
"loss": 0.0046,
"step": 1670
},
{
"epoch": 0.76,
"learning_rate": 1.5138461538461539e-05,
"loss": 0.0044,
"step": 1680
},
{
"epoch": 0.77,
"learning_rate": 1.510769230769231e-05,
"loss": 0.0059,
"step": 1690
},
{
"epoch": 0.77,
"learning_rate": 1.5076923076923078e-05,
"loss": 0.0424,
"step": 1700
},
{
"epoch": 0.78,
"learning_rate": 1.5046153846153849e-05,
"loss": 0.0035,
"step": 1710
},
{
"epoch": 0.78,
"learning_rate": 1.5015384615384617e-05,
"loss": 0.1403,
"step": 1720
},
{
"epoch": 0.79,
"learning_rate": 1.4984615384615386e-05,
"loss": 0.1405,
"step": 1730
},
{
"epoch": 0.79,
"learning_rate": 1.4953846153846154e-05,
"loss": 0.0236,
"step": 1740
},
{
"epoch": 0.8,
"learning_rate": 1.4923076923076925e-05,
"loss": 0.1671,
"step": 1750
},
{
"epoch": 0.8,
"learning_rate": 1.4892307692307692e-05,
"loss": 0.0038,
"step": 1760
},
{
"epoch": 0.8,
"learning_rate": 1.4861538461538464e-05,
"loss": 0.0037,
"step": 1770
},
{
"epoch": 0.81,
"learning_rate": 1.4830769230769233e-05,
"loss": 0.0388,
"step": 1780
},
{
"epoch": 0.81,
"learning_rate": 1.48e-05,
"loss": 0.1272,
"step": 1790
},
{
"epoch": 0.82,
"learning_rate": 1.4769230769230772e-05,
"loss": 0.0034,
"step": 1800
},
{
"epoch": 0.82,
"learning_rate": 1.473846153846154e-05,
"loss": 0.045,
"step": 1810
},
{
"epoch": 0.83,
"learning_rate": 1.4707692307692309e-05,
"loss": 0.1702,
"step": 1820
},
{
"epoch": 0.83,
"learning_rate": 1.4676923076923078e-05,
"loss": 0.1103,
"step": 1830
},
{
"epoch": 0.84,
"learning_rate": 1.4646153846153848e-05,
"loss": 0.0579,
"step": 1840
},
{
"epoch": 0.84,
"learning_rate": 1.4615384615384615e-05,
"loss": 0.0034,
"step": 1850
},
{
"epoch": 0.85,
"learning_rate": 1.4584615384615386e-05,
"loss": 0.1787,
"step": 1860
},
{
"epoch": 0.85,
"learning_rate": 1.4553846153846154e-05,
"loss": 0.0039,
"step": 1870
},
{
"epoch": 0.85,
"learning_rate": 1.4523076923076923e-05,
"loss": 0.0044,
"step": 1880
},
{
"epoch": 0.86,
"learning_rate": 1.4492307692307695e-05,
"loss": 0.172,
"step": 1890
},
{
"epoch": 0.86,
"learning_rate": 1.4461538461538462e-05,
"loss": 0.0036,
"step": 1900
},
{
"epoch": 0.87,
"learning_rate": 1.4430769230769233e-05,
"loss": 0.1737,
"step": 1910
},
{
"epoch": 0.87,
"learning_rate": 1.4400000000000001e-05,
"loss": 0.0028,
"step": 1920
},
{
"epoch": 0.88,
"learning_rate": 1.436923076923077e-05,
"loss": 0.2204,
"step": 1930
},
{
"epoch": 0.88,
"learning_rate": 1.4338461538461538e-05,
"loss": 0.0989,
"step": 1940
},
{
"epoch": 0.89,
"learning_rate": 1.430769230769231e-05,
"loss": 0.0718,
"step": 1950
},
{
"epoch": 0.89,
"learning_rate": 1.4276923076923077e-05,
"loss": 0.0097,
"step": 1960
},
{
"epoch": 0.9,
"learning_rate": 1.4246153846153848e-05,
"loss": 0.0874,
"step": 1970
},
{
"epoch": 0.9,
"learning_rate": 1.4215384615384617e-05,
"loss": 0.0045,
"step": 1980
},
{
"epoch": 0.9,
"learning_rate": 1.4184615384615385e-05,
"loss": 0.0039,
"step": 1990
},
{
"epoch": 0.91,
"learning_rate": 1.4153846153846156e-05,
"loss": 0.0046,
"step": 2000
},
{
"epoch": 0.91,
"learning_rate": 1.4123076923076924e-05,
"loss": 0.1695,
"step": 2010
},
{
"epoch": 0.92,
"learning_rate": 1.4092307692307693e-05,
"loss": 0.0039,
"step": 2020
},
{
"epoch": 0.92,
"learning_rate": 1.4061538461538463e-05,
"loss": 0.004,
"step": 2030
},
{
"epoch": 0.93,
"learning_rate": 1.4030769230769232e-05,
"loss": 0.1985,
"step": 2040
},
{
"epoch": 0.93,
"learning_rate": 1.4e-05,
"loss": 0.146,
"step": 2050
},
{
"epoch": 0.94,
"learning_rate": 1.3969230769230771e-05,
"loss": 0.0027,
"step": 2060
},
{
"epoch": 0.94,
"learning_rate": 1.393846153846154e-05,
"loss": 0.1138,
"step": 2070
},
{
"epoch": 0.95,
"learning_rate": 1.3907692307692308e-05,
"loss": 0.0072,
"step": 2080
},
{
"epoch": 0.95,
"learning_rate": 1.3876923076923079e-05,
"loss": 0.0027,
"step": 2090
},
{
"epoch": 0.95,
"learning_rate": 1.3846153846153847e-05,
"loss": 0.003,
"step": 2100
},
{
"epoch": 0.96,
"learning_rate": 1.3815384615384618e-05,
"loss": 0.1025,
"step": 2110
},
{
"epoch": 0.96,
"learning_rate": 1.3784615384615386e-05,
"loss": 0.029,
"step": 2120
},
{
"epoch": 0.97,
"learning_rate": 1.3753846153846155e-05,
"loss": 0.0877,
"step": 2130
},
{
"epoch": 0.97,
"learning_rate": 1.3723076923076923e-05,
"loss": 0.0486,
"step": 2140
},
{
"epoch": 0.98,
"learning_rate": 1.3692307692307694e-05,
"loss": 0.0355,
"step": 2150
},
{
"epoch": 0.98,
"learning_rate": 1.3661538461538461e-05,
"loss": 0.2253,
"step": 2160
},
{
"epoch": 0.99,
"learning_rate": 1.3630769230769233e-05,
"loss": 0.1129,
"step": 2170
},
{
"epoch": 0.99,
"learning_rate": 1.3600000000000002e-05,
"loss": 0.0035,
"step": 2180
},
{
"epoch": 1.0,
"learning_rate": 1.356923076923077e-05,
"loss": 0.0881,
"step": 2190
},
{
"epoch": 1.0,
"learning_rate": 1.353846153846154e-05,
"loss": 0.0028,
"step": 2200
},
{
"epoch": 1.0,
"eval_Accuracy": 0.9888636363636364,
"eval_F1": 0.9890284902407037,
"eval_loss": 0.08128699660301208,
"eval_runtime": 150.6254,
"eval_samples_per_second": 29.212,
"eval_steps_per_second": 1.826,
"step": 2200
},
{
"epoch": 1.0,
"learning_rate": 1.3507692307692308e-05,
"loss": 0.0792,
"step": 2210
},
{
"epoch": 1.01,
"learning_rate": 1.3476923076923078e-05,
"loss": 0.1501,
"step": 2220
},
{
"epoch": 1.01,
"learning_rate": 1.3446153846153847e-05,
"loss": 0.1827,
"step": 2230
},
{
"epoch": 1.02,
"learning_rate": 1.3415384615384617e-05,
"loss": 0.0505,
"step": 2240
},
{
"epoch": 1.02,
"learning_rate": 1.3384615384615384e-05,
"loss": 0.0044,
"step": 2250
},
{
"epoch": 1.03,
"learning_rate": 1.3353846153846155e-05,
"loss": 0.113,
"step": 2260
},
{
"epoch": 1.03,
"learning_rate": 1.3323076923076925e-05,
"loss": 0.0928,
"step": 2270
},
{
"epoch": 1.04,
"learning_rate": 1.3292307692307692e-05,
"loss": 0.0496,
"step": 2280
},
{
"epoch": 1.04,
"learning_rate": 1.3261538461538464e-05,
"loss": 0.0048,
"step": 2290
},
{
"epoch": 1.05,
"learning_rate": 1.3230769230769231e-05,
"loss": 0.0026,
"step": 2300
},
{
"epoch": 1.05,
"learning_rate": 1.3200000000000002e-05,
"loss": 0.114,
"step": 2310
},
{
"epoch": 1.05,
"learning_rate": 1.316923076923077e-05,
"loss": 0.0367,
"step": 2320
},
{
"epoch": 1.06,
"learning_rate": 1.313846153846154e-05,
"loss": 0.0756,
"step": 2330
},
{
"epoch": 1.06,
"learning_rate": 1.3107692307692307e-05,
"loss": 0.0752,
"step": 2340
},
{
"epoch": 1.07,
"learning_rate": 1.3076923076923078e-05,
"loss": 0.149,
"step": 2350
},
{
"epoch": 1.07,
"learning_rate": 1.3046153846153846e-05,
"loss": 0.0047,
"step": 2360
},
{
"epoch": 1.08,
"learning_rate": 1.3015384615384617e-05,
"loss": 0.0041,
"step": 2370
},
{
"epoch": 1.08,
"learning_rate": 1.2984615384615386e-05,
"loss": 0.0028,
"step": 2380
},
{
"epoch": 1.09,
"learning_rate": 1.2953846153846154e-05,
"loss": 0.0023,
"step": 2390
},
{
"epoch": 1.09,
"learning_rate": 1.2923076923076925e-05,
"loss": 0.0027,
"step": 2400
},
{
"epoch": 1.1,
"learning_rate": 1.2892307692307693e-05,
"loss": 0.0023,
"step": 2410
},
{
"epoch": 1.1,
"learning_rate": 1.2861538461538462e-05,
"loss": 0.0555,
"step": 2420
},
{
"epoch": 1.1,
"learning_rate": 1.2830769230769232e-05,
"loss": 0.002,
"step": 2430
},
{
"epoch": 1.11,
"learning_rate": 1.2800000000000001e-05,
"loss": 0.0021,
"step": 2440
},
{
"epoch": 1.11,
"learning_rate": 1.2769230769230769e-05,
"loss": 0.0511,
"step": 2450
},
{
"epoch": 1.12,
"learning_rate": 1.273846153846154e-05,
"loss": 0.0022,
"step": 2460
},
{
"epoch": 1.12,
"learning_rate": 1.270769230769231e-05,
"loss": 0.0026,
"step": 2470
},
{
"epoch": 1.13,
"learning_rate": 1.2676923076923077e-05,
"loss": 0.0976,
"step": 2480
},
{
"epoch": 1.13,
"learning_rate": 1.2646153846153848e-05,
"loss": 0.23,
"step": 2490
},
{
"epoch": 1.14,
"learning_rate": 1.2615384615384616e-05,
"loss": 0.1016,
"step": 2500
},
{
"epoch": 1.14,
"learning_rate": 1.2584615384615387e-05,
"loss": 0.2139,
"step": 2510
},
{
"epoch": 1.15,
"learning_rate": 1.2553846153846155e-05,
"loss": 0.2166,
"step": 2520
},
{
"epoch": 1.15,
"learning_rate": 1.2523076923076924e-05,
"loss": 0.0542,
"step": 2530
},
{
"epoch": 1.15,
"learning_rate": 1.2492307692307692e-05,
"loss": 0.0533,
"step": 2540
},
{
"epoch": 1.16,
"learning_rate": 1.2461538461538463e-05,
"loss": 0.057,
"step": 2550
},
{
"epoch": 1.16,
"learning_rate": 1.243076923076923e-05,
"loss": 0.0036,
"step": 2560
},
{
"epoch": 1.17,
"learning_rate": 1.2400000000000002e-05,
"loss": 0.0039,
"step": 2570
},
{
"epoch": 1.17,
"learning_rate": 1.2369230769230771e-05,
"loss": 0.003,
"step": 2580
},
{
"epoch": 1.18,
"learning_rate": 1.2338461538461539e-05,
"loss": 0.0024,
"step": 2590
},
{
"epoch": 1.18,
"learning_rate": 1.230769230769231e-05,
"loss": 0.0022,
"step": 2600
},
{
"epoch": 1.19,
"learning_rate": 1.2276923076923077e-05,
"loss": 0.0967,
"step": 2610
},
{
"epoch": 1.19,
"learning_rate": 1.2246153846153847e-05,
"loss": 0.0695,
"step": 2620
},
{
"epoch": 1.2,
"learning_rate": 1.2215384615384616e-05,
"loss": 0.0028,
"step": 2630
},
{
"epoch": 1.2,
"learning_rate": 1.2184615384615386e-05,
"loss": 0.0233,
"step": 2640
},
{
"epoch": 1.2,
"learning_rate": 1.2153846153846153e-05,
"loss": 0.0908,
"step": 2650
},
{
"epoch": 1.21,
"learning_rate": 1.2123076923076924e-05,
"loss": 0.0058,
"step": 2660
},
{
"epoch": 1.21,
"learning_rate": 1.2092307692307694e-05,
"loss": 0.0031,
"step": 2670
},
{
"epoch": 1.22,
"learning_rate": 1.2061538461538462e-05,
"loss": 0.1291,
"step": 2680
},
{
"epoch": 1.22,
"learning_rate": 1.2030769230769233e-05,
"loss": 0.1178,
"step": 2690
},
{
"epoch": 1.23,
"learning_rate": 1.2e-05,
"loss": 0.0052,
"step": 2700
},
{
"epoch": 1.23,
"learning_rate": 1.1969230769230771e-05,
"loss": 0.0385,
"step": 2710
},
{
"epoch": 1.24,
"learning_rate": 1.1938461538461539e-05,
"loss": 0.1806,
"step": 2720
},
{
"epoch": 1.24,
"learning_rate": 1.1907692307692308e-05,
"loss": 0.0217,
"step": 2730
},
{
"epoch": 1.25,
"learning_rate": 1.1876923076923076e-05,
"loss": 0.0024,
"step": 2740
},
{
"epoch": 1.25,
"learning_rate": 1.1846153846153847e-05,
"loss": 0.0022,
"step": 2750
},
{
"epoch": 1.25,
"learning_rate": 1.1815384615384617e-05,
"loss": 0.0029,
"step": 2760
},
{
"epoch": 1.26,
"learning_rate": 1.1784615384615386e-05,
"loss": 0.1312,
"step": 2770
},
{
"epoch": 1.26,
"learning_rate": 1.1753846153846155e-05,
"loss": 0.0022,
"step": 2780
},
{
"epoch": 1.27,
"learning_rate": 1.1723076923076923e-05,
"loss": 0.0019,
"step": 2790
},
{
"epoch": 1.27,
"learning_rate": 1.1692307692307694e-05,
"loss": 0.197,
"step": 2800
},
{
"epoch": 1.28,
"learning_rate": 1.1661538461538462e-05,
"loss": 0.003,
"step": 2810
},
{
"epoch": 1.28,
"learning_rate": 1.1630769230769231e-05,
"loss": 0.0028,
"step": 2820
},
{
"epoch": 1.29,
"learning_rate": 1.16e-05,
"loss": 0.0024,
"step": 2830
},
{
"epoch": 1.29,
"learning_rate": 1.156923076923077e-05,
"loss": 0.002,
"step": 2840
},
{
"epoch": 1.3,
"learning_rate": 1.1538461538461538e-05,
"loss": 0.0021,
"step": 2850
},
{
"epoch": 1.3,
"learning_rate": 1.1507692307692309e-05,
"loss": 0.0564,
"step": 2860
},
{
"epoch": 1.3,
"learning_rate": 1.1476923076923078e-05,
"loss": 0.002,
"step": 2870
},
{
"epoch": 1.31,
"learning_rate": 1.1446153846153846e-05,
"loss": 0.0243,
"step": 2880
},
{
"epoch": 1.31,
"learning_rate": 1.1415384615384617e-05,
"loss": 0.0363,
"step": 2890
},
{
"epoch": 1.32,
"learning_rate": 1.1384615384615385e-05,
"loss": 0.1064,
"step": 2900
},
{
"epoch": 1.32,
"learning_rate": 1.1353846153846156e-05,
"loss": 0.0019,
"step": 2910
},
{
"epoch": 1.33,
"learning_rate": 1.1323076923076924e-05,
"loss": 0.0049,
"step": 2920
},
{
"epoch": 1.33,
"learning_rate": 1.1292307692307693e-05,
"loss": 0.0814,
"step": 2930
},
{
"epoch": 1.34,
"learning_rate": 1.126153846153846e-05,
"loss": 0.0839,
"step": 2940
},
{
"epoch": 1.34,
"learning_rate": 1.1230769230769232e-05,
"loss": 0.0028,
"step": 2950
},
{
"epoch": 1.35,
"learning_rate": 1.1200000000000001e-05,
"loss": 0.2127,
"step": 2960
},
{
"epoch": 1.35,
"learning_rate": 1.116923076923077e-05,
"loss": 0.0026,
"step": 2970
},
{
"epoch": 1.35,
"learning_rate": 1.113846153846154e-05,
"loss": 0.0368,
"step": 2980
},
{
"epoch": 1.36,
"learning_rate": 1.1107692307692308e-05,
"loss": 0.0468,
"step": 2990
},
{
"epoch": 1.36,
"learning_rate": 1.1076923076923079e-05,
"loss": 0.0019,
"step": 3000
},
{
"epoch": 1.37,
"learning_rate": 1.1046153846153846e-05,
"loss": 0.0017,
"step": 3010
},
{
"epoch": 1.37,
"learning_rate": 1.1015384615384616e-05,
"loss": 0.1788,
"step": 3020
},
{
"epoch": 1.38,
"learning_rate": 1.0984615384615385e-05,
"loss": 0.0705,
"step": 3030
},
{
"epoch": 1.38,
"learning_rate": 1.0953846153846155e-05,
"loss": 0.0524,
"step": 3040
},
{
"epoch": 1.39,
"learning_rate": 1.0923076923076922e-05,
"loss": 0.0035,
"step": 3050
},
{
"epoch": 1.39,
"learning_rate": 1.0892307692307693e-05,
"loss": 0.002,
"step": 3060
},
{
"epoch": 1.4,
"learning_rate": 1.0861538461538463e-05,
"loss": 0.0015,
"step": 3070
},
{
"epoch": 1.4,
"learning_rate": 1.083076923076923e-05,
"loss": 0.0017,
"step": 3080
},
{
"epoch": 1.4,
"learning_rate": 1.0800000000000002e-05,
"loss": 0.0015,
"step": 3090
},
{
"epoch": 1.41,
"learning_rate": 1.076923076923077e-05,
"loss": 0.0017,
"step": 3100
},
{
"epoch": 1.41,
"learning_rate": 1.073846153846154e-05,
"loss": 0.1966,
"step": 3110
},
{
"epoch": 1.42,
"learning_rate": 1.0707692307692308e-05,
"loss": 0.0829,
"step": 3120
},
{
"epoch": 1.42,
"learning_rate": 1.0676923076923078e-05,
"loss": 0.0827,
"step": 3130
},
{
"epoch": 1.43,
"learning_rate": 1.0646153846153845e-05,
"loss": 0.0049,
"step": 3140
},
{
"epoch": 1.43,
"learning_rate": 1.0615384615384616e-05,
"loss": 0.0194,
"step": 3150
},
{
"epoch": 1.44,
"learning_rate": 1.0584615384615386e-05,
"loss": 0.0026,
"step": 3160
},
{
"epoch": 1.44,
"learning_rate": 1.0553846153846155e-05,
"loss": 0.0679,
"step": 3170
},
{
"epoch": 1.45,
"learning_rate": 1.0523076923076924e-05,
"loss": 0.115,
"step": 3180
},
{
"epoch": 1.45,
"learning_rate": 1.0492307692307692e-05,
"loss": 0.0629,
"step": 3190
},
{
"epoch": 1.45,
"learning_rate": 1.0461538461538463e-05,
"loss": 0.0267,
"step": 3200
},
{
"epoch": 1.46,
"learning_rate": 1.0430769230769231e-05,
"loss": 0.1529,
"step": 3210
},
{
"epoch": 1.46,
"learning_rate": 1.04e-05,
"loss": 0.002,
"step": 3220
},
{
"epoch": 1.47,
"learning_rate": 1.036923076923077e-05,
"loss": 0.0018,
"step": 3230
},
{
"epoch": 1.47,
"learning_rate": 1.033846153846154e-05,
"loss": 0.002,
"step": 3240
},
{
"epoch": 1.48,
"learning_rate": 1.0307692307692307e-05,
"loss": 0.0348,
"step": 3250
},
{
"epoch": 1.48,
"learning_rate": 1.0276923076923078e-05,
"loss": 0.0019,
"step": 3260
},
{
"epoch": 1.49,
"learning_rate": 1.0246153846153847e-05,
"loss": 0.0017,
"step": 3270
},
{
"epoch": 1.49,
"learning_rate": 1.0215384615384615e-05,
"loss": 0.0688,
"step": 3280
},
{
"epoch": 1.5,
"learning_rate": 1.0184615384615386e-05,
"loss": 0.2175,
"step": 3290
},
{
"epoch": 1.5,
"learning_rate": 1.0153846153846154e-05,
"loss": 0.0031,
"step": 3300
},
{
"epoch": 1.5,
"learning_rate": 1.0123076923076925e-05,
"loss": 0.0017,
"step": 3310
},
{
"epoch": 1.51,
"learning_rate": 1.0092307692307693e-05,
"loss": 0.0024,
"step": 3320
},
{
"epoch": 1.51,
"learning_rate": 1.0061538461538462e-05,
"loss": 0.065,
"step": 3330
},
{
"epoch": 1.52,
"learning_rate": 1.0030769230769231e-05,
"loss": 0.0027,
"step": 3340
},
{
"epoch": 1.52,
"learning_rate": 1e-05,
"loss": 0.0389,
"step": 3350
},
{
"epoch": 1.53,
"learning_rate": 9.96923076923077e-06,
"loss": 0.1488,
"step": 3360
},
{
"epoch": 1.53,
"learning_rate": 9.93846153846154e-06,
"loss": 0.1107,
"step": 3370
},
{
"epoch": 1.54,
"learning_rate": 9.907692307692309e-06,
"loss": 0.2026,
"step": 3380
},
{
"epoch": 1.54,
"learning_rate": 9.876923076923077e-06,
"loss": 0.0154,
"step": 3390
},
{
"epoch": 1.55,
"learning_rate": 9.846153846153848e-06,
"loss": 0.0568,
"step": 3400
},
{
"epoch": 1.55,
"learning_rate": 9.815384615384617e-06,
"loss": 0.0015,
"step": 3410
},
{
"epoch": 1.55,
"learning_rate": 9.784615384615387e-06,
"loss": 0.1328,
"step": 3420
},
{
"epoch": 1.56,
"learning_rate": 9.753846153846154e-06,
"loss": 0.073,
"step": 3430
},
{
"epoch": 1.56,
"learning_rate": 9.723076923076924e-06,
"loss": 0.0713,
"step": 3440
},
{
"epoch": 1.57,
"learning_rate": 9.692307692307693e-06,
"loss": 0.0484,
"step": 3450
},
{
"epoch": 1.57,
"learning_rate": 9.661538461538462e-06,
"loss": 0.0703,
"step": 3460
},
{
"epoch": 1.58,
"learning_rate": 9.630769230769232e-06,
"loss": 0.1891,
"step": 3470
},
{
"epoch": 1.58,
"learning_rate": 9.600000000000001e-06,
"loss": 0.1082,
"step": 3480
},
{
"epoch": 1.59,
"learning_rate": 9.569230769230769e-06,
"loss": 0.0017,
"step": 3490
},
{
"epoch": 1.59,
"learning_rate": 9.53846153846154e-06,
"loss": 0.0096,
"step": 3500
},
{
"epoch": 1.6,
"learning_rate": 9.50769230769231e-06,
"loss": 0.022,
"step": 3510
},
{
"epoch": 1.6,
"learning_rate": 9.476923076923079e-06,
"loss": 0.0016,
"step": 3520
},
{
"epoch": 1.6,
"learning_rate": 9.446153846153847e-06,
"loss": 0.0013,
"step": 3530
},
{
"epoch": 1.61,
"learning_rate": 9.415384615384616e-06,
"loss": 0.0017,
"step": 3540
},
{
"epoch": 1.61,
"learning_rate": 9.384615384615385e-06,
"loss": 0.0016,
"step": 3550
},
{
"epoch": 1.62,
"learning_rate": 9.353846153846155e-06,
"loss": 0.0012,
"step": 3560
},
{
"epoch": 1.62,
"learning_rate": 9.323076923076924e-06,
"loss": 0.1051,
"step": 3570
},
{
"epoch": 1.63,
"learning_rate": 9.292307692307694e-06,
"loss": 0.0012,
"step": 3580
},
{
"epoch": 1.63,
"learning_rate": 9.261538461538461e-06,
"loss": 0.0013,
"step": 3590
},
{
"epoch": 1.64,
"learning_rate": 9.230769230769232e-06,
"loss": 0.0446,
"step": 3600
},
{
"epoch": 1.64,
"learning_rate": 9.200000000000002e-06,
"loss": 0.0728,
"step": 3610
},
{
"epoch": 1.65,
"learning_rate": 9.169230769230771e-06,
"loss": 0.0021,
"step": 3620
},
{
"epoch": 1.65,
"learning_rate": 9.138461538461539e-06,
"loss": 0.002,
"step": 3630
},
{
"epoch": 1.65,
"learning_rate": 9.107692307692308e-06,
"loss": 0.0564,
"step": 3640
},
{
"epoch": 1.66,
"learning_rate": 9.076923076923078e-06,
"loss": 0.0688,
"step": 3650
},
{
"epoch": 1.66,
"learning_rate": 9.046153846153847e-06,
"loss": 0.1502,
"step": 3660
},
{
"epoch": 1.67,
"learning_rate": 9.015384615384616e-06,
"loss": 0.0015,
"step": 3670
},
{
"epoch": 1.67,
"learning_rate": 8.984615384615386e-06,
"loss": 0.0627,
"step": 3680
},
{
"epoch": 1.68,
"learning_rate": 8.953846153846153e-06,
"loss": 0.002,
"step": 3690
},
{
"epoch": 1.68,
"learning_rate": 8.923076923076925e-06,
"loss": 0.0399,
"step": 3700
},
{
"epoch": 1.69,
"learning_rate": 8.892307692307694e-06,
"loss": 0.0023,
"step": 3710
},
{
"epoch": 1.69,
"learning_rate": 8.861538461538463e-06,
"loss": 0.0719,
"step": 3720
},
{
"epoch": 1.7,
"learning_rate": 8.830769230769231e-06,
"loss": 0.0019,
"step": 3730
},
{
"epoch": 1.7,
"learning_rate": 8.8e-06,
"loss": 0.0579,
"step": 3740
},
{
"epoch": 1.7,
"learning_rate": 8.76923076923077e-06,
"loss": 0.0016,
"step": 3750
},
{
"epoch": 1.71,
"learning_rate": 8.73846153846154e-06,
"loss": 0.0521,
"step": 3760
},
{
"epoch": 1.71,
"learning_rate": 8.707692307692309e-06,
"loss": 0.1428,
"step": 3770
},
{
"epoch": 1.72,
"learning_rate": 8.676923076923078e-06,
"loss": 0.0464,
"step": 3780
},
{
"epoch": 1.72,
"learning_rate": 8.646153846153846e-06,
"loss": 0.0394,
"step": 3790
},
{
"epoch": 1.73,
"learning_rate": 8.615384615384617e-06,
"loss": 0.0908,
"step": 3800
},
{
"epoch": 1.73,
"learning_rate": 8.584615384615386e-06,
"loss": 0.0027,
"step": 3810
},
{
"epoch": 1.74,
"learning_rate": 8.553846153846156e-06,
"loss": 0.0717,
"step": 3820
},
{
"epoch": 1.74,
"learning_rate": 8.523076923076923e-06,
"loss": 0.178,
"step": 3830
},
{
"epoch": 1.75,
"learning_rate": 8.492307692307693e-06,
"loss": 0.1158,
"step": 3840
},
{
"epoch": 1.75,
"learning_rate": 8.461538461538462e-06,
"loss": 0.0016,
"step": 3850
},
{
"epoch": 1.75,
"learning_rate": 8.430769230769231e-06,
"loss": 0.0504,
"step": 3860
},
{
"epoch": 1.76,
"learning_rate": 8.400000000000001e-06,
"loss": 0.1092,
"step": 3870
},
{
"epoch": 1.76,
"learning_rate": 8.36923076923077e-06,
"loss": 0.114,
"step": 3880
},
{
"epoch": 1.77,
"learning_rate": 8.338461538461538e-06,
"loss": 0.002,
"step": 3890
},
{
"epoch": 1.77,
"learning_rate": 8.307692307692309e-06,
"loss": 0.0029,
"step": 3900
},
{
"epoch": 1.78,
"learning_rate": 8.276923076923078e-06,
"loss": 0.002,
"step": 3910
},
{
"epoch": 1.78,
"learning_rate": 8.246153846153848e-06,
"loss": 0.1239,
"step": 3920
},
{
"epoch": 1.79,
"learning_rate": 8.215384615384616e-06,
"loss": 0.0016,
"step": 3930
},
{
"epoch": 1.79,
"learning_rate": 8.184615384615385e-06,
"loss": 0.0265,
"step": 3940
},
{
"epoch": 1.8,
"learning_rate": 8.153846153846154e-06,
"loss": 0.0836,
"step": 3950
},
{
"epoch": 1.8,
"learning_rate": 8.123076923076924e-06,
"loss": 0.0017,
"step": 3960
},
{
"epoch": 1.8,
"learning_rate": 8.092307692307693e-06,
"loss": 0.0014,
"step": 3970
},
{
"epoch": 1.81,
"learning_rate": 8.061538461538463e-06,
"loss": 0.1186,
"step": 3980
},
{
"epoch": 1.81,
"learning_rate": 8.03076923076923e-06,
"loss": 0.0791,
"step": 3990
},
{
"epoch": 1.82,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0021,
"step": 4000
},
{
"epoch": 1.82,
"learning_rate": 7.96923076923077e-06,
"loss": 0.2008,
"step": 4010
},
{
"epoch": 1.83,
"learning_rate": 7.93846153846154e-06,
"loss": 0.1339,
"step": 4020
},
{
"epoch": 1.83,
"learning_rate": 7.907692307692308e-06,
"loss": 0.0873,
"step": 4030
},
{
"epoch": 1.84,
"learning_rate": 7.876923076923077e-06,
"loss": 0.0076,
"step": 4040
},
{
"epoch": 1.84,
"learning_rate": 7.846153846153847e-06,
"loss": 0.0695,
"step": 4050
},
{
"epoch": 1.85,
"learning_rate": 7.815384615384616e-06,
"loss": 0.0023,
"step": 4060
},
{
"epoch": 1.85,
"learning_rate": 7.784615384615385e-06,
"loss": 0.1105,
"step": 4070
},
{
"epoch": 1.85,
"learning_rate": 7.753846153846155e-06,
"loss": 0.0645,
"step": 4080
},
{
"epoch": 1.86,
"learning_rate": 7.723076923076924e-06,
"loss": 0.0019,
"step": 4090
},
{
"epoch": 1.86,
"learning_rate": 7.692307692307694e-06,
"loss": 0.0652,
"step": 4100
},
{
"epoch": 1.87,
"learning_rate": 7.661538461538463e-06,
"loss": 0.1311,
"step": 4110
},
{
"epoch": 1.87,
"learning_rate": 7.630769230769232e-06,
"loss": 0.0037,
"step": 4120
},
{
"epoch": 1.88,
"learning_rate": 7.600000000000001e-06,
"loss": 0.0161,
"step": 4130
},
{
"epoch": 1.88,
"learning_rate": 7.5692307692307695e-06,
"loss": 0.0014,
"step": 4140
},
{
"epoch": 1.89,
"learning_rate": 7.538461538461539e-06,
"loss": 0.0014,
"step": 4150
},
{
"epoch": 1.89,
"learning_rate": 7.507692307692308e-06,
"loss": 0.1131,
"step": 4160
},
{
"epoch": 1.9,
"learning_rate": 7.476923076923077e-06,
"loss": 0.0515,
"step": 4170
},
{
"epoch": 1.9,
"learning_rate": 7.446153846153846e-06,
"loss": 0.0013,
"step": 4180
},
{
"epoch": 1.9,
"learning_rate": 7.4153846153846164e-06,
"loss": 0.01,
"step": 4190
},
{
"epoch": 1.91,
"learning_rate": 7.384615384615386e-06,
"loss": 0.0011,
"step": 4200
},
{
"epoch": 1.91,
"learning_rate": 7.353846153846154e-06,
"loss": 0.001,
"step": 4210
},
{
"epoch": 1.92,
"learning_rate": 7.323076923076924e-06,
"loss": 0.1202,
"step": 4220
},
{
"epoch": 1.92,
"learning_rate": 7.292307692307693e-06,
"loss": 0.001,
"step": 4230
},
{
"epoch": 1.93,
"learning_rate": 7.261538461538462e-06,
"loss": 0.0686,
"step": 4240
},
{
"epoch": 1.93,
"learning_rate": 7.230769230769231e-06,
"loss": 0.0012,
"step": 4250
},
{
"epoch": 1.94,
"learning_rate": 7.2000000000000005e-06,
"loss": 0.0012,
"step": 4260
},
{
"epoch": 1.94,
"learning_rate": 7.169230769230769e-06,
"loss": 0.0012,
"step": 4270
},
{
"epoch": 1.95,
"learning_rate": 7.1384615384615385e-06,
"loss": 0.1015,
"step": 4280
},
{
"epoch": 1.95,
"learning_rate": 7.107692307692309e-06,
"loss": 0.1873,
"step": 4290
},
{
"epoch": 1.95,
"learning_rate": 7.076923076923078e-06,
"loss": 0.0013,
"step": 4300
},
{
"epoch": 1.96,
"learning_rate": 7.046153846153847e-06,
"loss": 0.0024,
"step": 4310
},
{
"epoch": 1.96,
"learning_rate": 7.015384615384616e-06,
"loss": 0.0013,
"step": 4320
},
{
"epoch": 1.97,
"learning_rate": 6.9846153846153854e-06,
"loss": 0.0289,
"step": 4330
},
{
"epoch": 1.97,
"learning_rate": 6.953846153846154e-06,
"loss": 0.0013,
"step": 4340
},
{
"epoch": 1.98,
"learning_rate": 6.923076923076923e-06,
"loss": 0.0804,
"step": 4350
},
{
"epoch": 1.98,
"learning_rate": 6.892307692307693e-06,
"loss": 0.0897,
"step": 4360
},
{
"epoch": 1.99,
"learning_rate": 6.861538461538461e-06,
"loss": 0.0316,
"step": 4370
},
{
"epoch": 1.99,
"learning_rate": 6.830769230769231e-06,
"loss": 0.0015,
"step": 4380
},
{
"epoch": 2.0,
"learning_rate": 6.800000000000001e-06,
"loss": 0.0921,
"step": 4390
},
{
"epoch": 2.0,
"learning_rate": 6.76923076923077e-06,
"loss": 0.0011,
"step": 4400
},
{
"epoch": 2.0,
"eval_Accuracy": 0.9897727272727272,
"eval_F1": 0.9898706979395142,
"eval_loss": 0.06447935849428177,
"eval_runtime": 150.7492,
"eval_samples_per_second": 29.188,
"eval_steps_per_second": 1.824,
"step": 4400
},
{
"epoch": 2.0,
"learning_rate": 6.738461538461539e-06,
"loss": 0.001,
"step": 4410
},
{
"epoch": 2.01,
"learning_rate": 6.707692307692308e-06,
"loss": 0.0389,
"step": 4420
},
{
"epoch": 2.01,
"learning_rate": 6.676923076923078e-06,
"loss": 0.1424,
"step": 4430
},
{
"epoch": 2.02,
"learning_rate": 6.646153846153846e-06,
"loss": 0.0012,
"step": 4440
},
{
"epoch": 2.02,
"learning_rate": 6.615384615384616e-06,
"loss": 0.0662,
"step": 4450
},
{
"epoch": 2.03,
"learning_rate": 6.584615384615385e-06,
"loss": 0.0536,
"step": 4460
},
{
"epoch": 2.03,
"learning_rate": 6.553846153846154e-06,
"loss": 0.0683,
"step": 4470
},
{
"epoch": 2.04,
"learning_rate": 6.523076923076923e-06,
"loss": 0.0012,
"step": 4480
},
{
"epoch": 2.04,
"learning_rate": 6.492307692307693e-06,
"loss": 0.0011,
"step": 4490
},
{
"epoch": 2.05,
"learning_rate": 6.461538461538463e-06,
"loss": 0.0014,
"step": 4500
},
{
"epoch": 2.05,
"learning_rate": 6.430769230769231e-06,
"loss": 0.0317,
"step": 4510
},
{
"epoch": 2.05,
"learning_rate": 6.4000000000000006e-06,
"loss": 0.0974,
"step": 4520
},
{
"epoch": 2.06,
"learning_rate": 6.36923076923077e-06,
"loss": 0.0994,
"step": 4530
},
{
"epoch": 2.06,
"learning_rate": 6.3384615384615385e-06,
"loss": 0.0027,
"step": 4540
},
{
"epoch": 2.07,
"learning_rate": 6.307692307692308e-06,
"loss": 0.0508,
"step": 4550
},
{
"epoch": 2.07,
"learning_rate": 6.276923076923077e-06,
"loss": 0.0017,
"step": 4560
},
{
"epoch": 2.08,
"learning_rate": 6.246153846153846e-06,
"loss": 0.0453,
"step": 4570
},
{
"epoch": 2.08,
"learning_rate": 6.215384615384615e-06,
"loss": 0.0022,
"step": 4580
},
{
"epoch": 2.09,
"learning_rate": 6.1846153846153855e-06,
"loss": 0.0014,
"step": 4590
},
{
"epoch": 2.09,
"learning_rate": 6.153846153846155e-06,
"loss": 0.0015,
"step": 4600
},
{
"epoch": 2.1,
"learning_rate": 6.123076923076923e-06,
"loss": 0.0015,
"step": 4610
},
{
"epoch": 2.1,
"learning_rate": 6.092307692307693e-06,
"loss": 0.0015,
"step": 4620
},
{
"epoch": 2.1,
"learning_rate": 6.061538461538462e-06,
"loss": 0.065,
"step": 4630
},
{
"epoch": 2.11,
"learning_rate": 6.030769230769231e-06,
"loss": 0.0013,
"step": 4640
},
{
"epoch": 2.11,
"learning_rate": 6e-06,
"loss": 0.0018,
"step": 4650
},
{
"epoch": 2.12,
"learning_rate": 5.9692307692307695e-06,
"loss": 0.0021,
"step": 4660
},
{
"epoch": 2.12,
"learning_rate": 5.938461538461538e-06,
"loss": 0.0708,
"step": 4670
},
{
"epoch": 2.13,
"learning_rate": 5.907692307692308e-06,
"loss": 0.0318,
"step": 4680
},
{
"epoch": 2.13,
"learning_rate": 5.876923076923078e-06,
"loss": 0.0107,
"step": 4690
},
{
"epoch": 2.14,
"learning_rate": 5.846153846153847e-06,
"loss": 0.0012,
"step": 4700
},
{
"epoch": 2.14,
"learning_rate": 5.815384615384616e-06,
"loss": 0.0635,
"step": 4710
},
{
"epoch": 2.15,
"learning_rate": 5.784615384615385e-06,
"loss": 0.0056,
"step": 4720
},
{
"epoch": 2.15,
"learning_rate": 5.7538461538461545e-06,
"loss": 0.0009,
"step": 4730
},
{
"epoch": 2.15,
"learning_rate": 5.723076923076923e-06,
"loss": 0.0404,
"step": 4740
},
{
"epoch": 2.16,
"learning_rate": 5.692307692307692e-06,
"loss": 0.0012,
"step": 4750
},
{
"epoch": 2.16,
"learning_rate": 5.661538461538462e-06,
"loss": 0.1147,
"step": 4760
},
{
"epoch": 2.17,
"learning_rate": 5.63076923076923e-06,
"loss": 0.0591,
"step": 4770
},
{
"epoch": 2.17,
"learning_rate": 5.600000000000001e-06,
"loss": 0.0515,
"step": 4780
},
{
"epoch": 2.18,
"learning_rate": 5.56923076923077e-06,
"loss": 0.0009,
"step": 4790
},
{
"epoch": 2.18,
"learning_rate": 5.538461538461539e-06,
"loss": 0.001,
"step": 4800
},
{
"epoch": 2.19,
"learning_rate": 5.507692307692308e-06,
"loss": 0.0009,
"step": 4810
},
{
"epoch": 2.19,
"learning_rate": 5.476923076923077e-06,
"loss": 0.0013,
"step": 4820
},
{
"epoch": 2.2,
"learning_rate": 5.446153846153847e-06,
"loss": 0.0009,
"step": 4830
},
{
"epoch": 2.2,
"learning_rate": 5.415384615384615e-06,
"loss": 0.0332,
"step": 4840
},
{
"epoch": 2.2,
"learning_rate": 5.384615384615385e-06,
"loss": 0.0977,
"step": 4850
},
{
"epoch": 2.21,
"learning_rate": 5.353846153846154e-06,
"loss": 0.0376,
"step": 4860
},
{
"epoch": 2.21,
"learning_rate": 5.323076923076923e-06,
"loss": 0.0396,
"step": 4870
},
{
"epoch": 2.22,
"learning_rate": 5.292307692307693e-06,
"loss": 0.0016,
"step": 4880
},
{
"epoch": 2.22,
"learning_rate": 5.261538461538462e-06,
"loss": 0.0212,
"step": 4890
},
{
"epoch": 2.23,
"learning_rate": 5.230769230769232e-06,
"loss": 0.0588,
"step": 4900
},
{
"epoch": 2.23,
"learning_rate": 5.2e-06,
"loss": 0.0011,
"step": 4910
},
{
"epoch": 2.24,
"learning_rate": 5.16923076923077e-06,
"loss": 0.0009,
"step": 4920
},
{
"epoch": 2.24,
"learning_rate": 5.138461538461539e-06,
"loss": 0.1418,
"step": 4930
},
{
"epoch": 2.25,
"learning_rate": 5.1076923076923075e-06,
"loss": 0.0538,
"step": 4940
},
{
"epoch": 2.25,
"learning_rate": 5.076923076923077e-06,
"loss": 0.0155,
"step": 4950
},
{
"epoch": 2.25,
"learning_rate": 5.046153846153846e-06,
"loss": 0.1014,
"step": 4960
},
{
"epoch": 2.26,
"learning_rate": 5.015384615384616e-06,
"loss": 0.0013,
"step": 4970
},
{
"epoch": 2.26,
"learning_rate": 4.984615384615385e-06,
"loss": 0.0126,
"step": 4980
},
{
"epoch": 2.27,
"learning_rate": 4.9538461538461545e-06,
"loss": 0.0569,
"step": 4990
},
{
"epoch": 2.27,
"learning_rate": 4.923076923076924e-06,
"loss": 0.0241,
"step": 5000
},
{
"epoch": 2.28,
"learning_rate": 4.892307692307693e-06,
"loss": 0.001,
"step": 5010
},
{
"epoch": 2.28,
"learning_rate": 4.861538461538462e-06,
"loss": 0.0029,
"step": 5020
},
{
"epoch": 2.29,
"learning_rate": 4.830769230769231e-06,
"loss": 0.0042,
"step": 5030
},
{
"epoch": 2.29,
"learning_rate": 4.800000000000001e-06,
"loss": 0.04,
"step": 5040
},
{
"epoch": 2.3,
"learning_rate": 4.76923076923077e-06,
"loss": 0.0008,
"step": 5050
},
{
"epoch": 2.3,
"learning_rate": 4.738461538461539e-06,
"loss": 0.0014,
"step": 5060
},
{
"epoch": 2.3,
"learning_rate": 4.707692307692308e-06,
"loss": 0.0959,
"step": 5070
},
{
"epoch": 2.31,
"learning_rate": 4.676923076923077e-06,
"loss": 0.0009,
"step": 5080
},
{
"epoch": 2.31,
"learning_rate": 4.646153846153847e-06,
"loss": 0.0137,
"step": 5090
},
{
"epoch": 2.32,
"learning_rate": 4.615384615384616e-06,
"loss": 0.1642,
"step": 5100
},
{
"epoch": 2.32,
"learning_rate": 4.5846153846153855e-06,
"loss": 0.0026,
"step": 5110
},
{
"epoch": 2.33,
"learning_rate": 4.553846153846154e-06,
"loss": 0.1011,
"step": 5120
},
{
"epoch": 2.33,
"learning_rate": 4.5230769230769235e-06,
"loss": 0.0456,
"step": 5130
},
{
"epoch": 2.34,
"learning_rate": 4.492307692307693e-06,
"loss": 0.0484,
"step": 5140
},
{
"epoch": 2.34,
"learning_rate": 4.461538461538462e-06,
"loss": 0.0272,
"step": 5150
},
{
"epoch": 2.35,
"learning_rate": 4.430769230769232e-06,
"loss": 0.0009,
"step": 5160
},
{
"epoch": 2.35,
"learning_rate": 4.4e-06,
"loss": 0.1856,
"step": 5170
},
{
"epoch": 2.35,
"learning_rate": 4.36923076923077e-06,
"loss": 0.0075,
"step": 5180
},
{
"epoch": 2.36,
"learning_rate": 4.338461538461539e-06,
"loss": 0.0019,
"step": 5190
},
{
"epoch": 2.36,
"learning_rate": 4.307692307692308e-06,
"loss": 0.0012,
"step": 5200
},
{
"epoch": 2.37,
"learning_rate": 4.276923076923078e-06,
"loss": 0.001,
"step": 5210
},
{
"epoch": 2.37,
"learning_rate": 4.246153846153846e-06,
"loss": 0.0975,
"step": 5220
},
{
"epoch": 2.38,
"learning_rate": 4.215384615384616e-06,
"loss": 0.0011,
"step": 5230
},
{
"epoch": 2.38,
"learning_rate": 4.184615384615385e-06,
"loss": 0.0011,
"step": 5240
},
{
"epoch": 2.39,
"learning_rate": 4.1538461538461545e-06,
"loss": 0.0012,
"step": 5250
},
{
"epoch": 2.39,
"learning_rate": 4.123076923076924e-06,
"loss": 0.1065,
"step": 5260
},
{
"epoch": 2.4,
"learning_rate": 4.0923076923076925e-06,
"loss": 0.0019,
"step": 5270
},
{
"epoch": 2.4,
"learning_rate": 4.061538461538462e-06,
"loss": 0.0016,
"step": 5280
},
{
"epoch": 2.4,
"learning_rate": 4.030769230769231e-06,
"loss": 0.0017,
"step": 5290
},
{
"epoch": 2.41,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0372,
"step": 5300
},
{
"epoch": 2.41,
"learning_rate": 3.96923076923077e-06,
"loss": 0.088,
"step": 5310
},
{
"epoch": 2.42,
"learning_rate": 3.938461538461539e-06,
"loss": 0.1187,
"step": 5320
},
{
"epoch": 2.42,
"learning_rate": 3.907692307692308e-06,
"loss": 0.001,
"step": 5330
},
{
"epoch": 2.43,
"learning_rate": 3.876923076923077e-06,
"loss": 0.0011,
"step": 5340
},
{
"epoch": 2.43,
"learning_rate": 3.846153846153847e-06,
"loss": 0.0494,
"step": 5350
},
{
"epoch": 2.44,
"learning_rate": 3.815384615384616e-06,
"loss": 0.001,
"step": 5360
},
{
"epoch": 2.44,
"learning_rate": 3.7846153846153847e-06,
"loss": 0.0008,
"step": 5370
},
{
"epoch": 2.45,
"learning_rate": 3.753846153846154e-06,
"loss": 0.085,
"step": 5380
},
{
"epoch": 2.45,
"learning_rate": 3.723076923076923e-06,
"loss": 0.001,
"step": 5390
},
{
"epoch": 2.45,
"learning_rate": 3.692307692307693e-06,
"loss": 0.1068,
"step": 5400
},
{
"epoch": 2.46,
"learning_rate": 3.661538461538462e-06,
"loss": 0.086,
"step": 5410
},
{
"epoch": 2.46,
"learning_rate": 3.630769230769231e-06,
"loss": 0.0531,
"step": 5420
},
{
"epoch": 2.47,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.051,
"step": 5430
},
{
"epoch": 2.47,
"learning_rate": 3.5692307692307692e-06,
"loss": 0.0009,
"step": 5440
},
{
"epoch": 2.48,
"learning_rate": 3.538461538461539e-06,
"loss": 0.001,
"step": 5450
},
{
"epoch": 2.48,
"learning_rate": 3.507692307692308e-06,
"loss": 0.0015,
"step": 5460
},
{
"epoch": 2.49,
"learning_rate": 3.476923076923077e-06,
"loss": 0.0118,
"step": 5470
},
{
"epoch": 2.49,
"learning_rate": 3.4461538461538464e-06,
"loss": 0.0124,
"step": 5480
},
{
"epoch": 2.5,
"learning_rate": 3.4153846153846154e-06,
"loss": 0.0032,
"step": 5490
},
{
"epoch": 2.5,
"learning_rate": 3.384615384615385e-06,
"loss": 0.0013,
"step": 5500
},
{
"epoch": 2.5,
"learning_rate": 3.353846153846154e-06,
"loss": 0.1963,
"step": 5510
},
{
"epoch": 2.51,
"learning_rate": 3.323076923076923e-06,
"loss": 0.053,
"step": 5520
},
{
"epoch": 2.51,
"learning_rate": 3.2923076923076925e-06,
"loss": 0.001,
"step": 5530
},
{
"epoch": 2.52,
"learning_rate": 3.2615384615384615e-06,
"loss": 0.0281,
"step": 5540
},
{
"epoch": 2.52,
"learning_rate": 3.2307692307692313e-06,
"loss": 0.0941,
"step": 5550
},
{
"epoch": 2.53,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.001,
"step": 5560
},
{
"epoch": 2.53,
"learning_rate": 3.1692307692307693e-06,
"loss": 0.001,
"step": 5570
},
{
"epoch": 2.54,
"learning_rate": 3.1384615384615386e-06,
"loss": 0.001,
"step": 5580
},
{
"epoch": 2.54,
"learning_rate": 3.1076923076923076e-06,
"loss": 0.0008,
"step": 5590
},
{
"epoch": 2.55,
"learning_rate": 3.0769230769230774e-06,
"loss": 0.0318,
"step": 5600
},
{
"epoch": 2.55,
"learning_rate": 3.0461538461538464e-06,
"loss": 0.0009,
"step": 5610
},
{
"epoch": 2.55,
"learning_rate": 3.0153846153846154e-06,
"loss": 0.0156,
"step": 5620
},
{
"epoch": 2.56,
"learning_rate": 2.9846153846153848e-06,
"loss": 0.1011,
"step": 5630
},
{
"epoch": 2.56,
"learning_rate": 2.953846153846154e-06,
"loss": 0.0008,
"step": 5640
},
{
"epoch": 2.57,
"learning_rate": 2.9230769230769236e-06,
"loss": 0.0009,
"step": 5650
},
{
"epoch": 2.57,
"learning_rate": 2.8923076923076925e-06,
"loss": 0.0008,
"step": 5660
},
{
"epoch": 2.58,
"learning_rate": 2.8615384615384615e-06,
"loss": 0.0008,
"step": 5670
},
{
"epoch": 2.58,
"learning_rate": 2.830769230769231e-06,
"loss": 0.0266,
"step": 5680
},
{
"epoch": 2.59,
"learning_rate": 2.8000000000000003e-06,
"loss": 0.0008,
"step": 5690
},
{
"epoch": 2.59,
"learning_rate": 2.7692307692307697e-06,
"loss": 0.1243,
"step": 5700
},
{
"epoch": 2.6,
"learning_rate": 2.7384615384615387e-06,
"loss": 0.0009,
"step": 5710
},
{
"epoch": 2.6,
"learning_rate": 2.7076923076923076e-06,
"loss": 0.1052,
"step": 5720
},
{
"epoch": 2.6,
"learning_rate": 2.676923076923077e-06,
"loss": 0.1307,
"step": 5730
},
{
"epoch": 2.61,
"learning_rate": 2.6461538461538464e-06,
"loss": 0.1628,
"step": 5740
},
{
"epoch": 2.61,
"learning_rate": 2.615384615384616e-06,
"loss": 0.0011,
"step": 5750
},
{
"epoch": 2.62,
"learning_rate": 2.584615384615385e-06,
"loss": 0.001,
"step": 5760
},
{
"epoch": 2.62,
"learning_rate": 2.5538461538461538e-06,
"loss": 0.013,
"step": 5770
},
{
"epoch": 2.63,
"learning_rate": 2.523076923076923e-06,
"loss": 0.1045,
"step": 5780
},
{
"epoch": 2.63,
"learning_rate": 2.4923076923076926e-06,
"loss": 0.003,
"step": 5790
},
{
"epoch": 2.64,
"learning_rate": 2.461538461538462e-06,
"loss": 0.0009,
"step": 5800
},
{
"epoch": 2.64,
"learning_rate": 2.430769230769231e-06,
"loss": 0.0008,
"step": 5810
},
{
"epoch": 2.65,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.0085,
"step": 5820
},
{
"epoch": 2.65,
"learning_rate": 2.3692307692307697e-06,
"loss": 0.0008,
"step": 5830
},
{
"epoch": 2.65,
"learning_rate": 2.3384615384615387e-06,
"loss": 0.0321,
"step": 5840
},
{
"epoch": 2.66,
"learning_rate": 2.307692307692308e-06,
"loss": 0.0397,
"step": 5850
},
{
"epoch": 2.66,
"learning_rate": 2.276923076923077e-06,
"loss": 0.002,
"step": 5860
},
{
"epoch": 2.67,
"learning_rate": 2.2461538461538464e-06,
"loss": 0.0009,
"step": 5870
},
{
"epoch": 2.67,
"learning_rate": 2.215384615384616e-06,
"loss": 0.0025,
"step": 5880
},
{
"epoch": 2.68,
"learning_rate": 2.184615384615385e-06,
"loss": 0.1094,
"step": 5890
},
{
"epoch": 2.68,
"learning_rate": 2.153846153846154e-06,
"loss": 0.0009,
"step": 5900
},
{
"epoch": 2.69,
"learning_rate": 2.123076923076923e-06,
"loss": 0.0009,
"step": 5910
},
{
"epoch": 2.69,
"learning_rate": 2.0923076923076926e-06,
"loss": 0.0699,
"step": 5920
},
{
"epoch": 2.7,
"learning_rate": 2.061538461538462e-06,
"loss": 0.0011,
"step": 5930
},
{
"epoch": 2.7,
"learning_rate": 2.030769230769231e-06,
"loss": 0.0288,
"step": 5940
},
{
"epoch": 2.7,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0018,
"step": 5950
},
{
"epoch": 2.71,
"learning_rate": 1.9692307692307693e-06,
"loss": 0.0479,
"step": 5960
},
{
"epoch": 2.71,
"learning_rate": 1.9384615384615387e-06,
"loss": 0.0015,
"step": 5970
},
{
"epoch": 2.72,
"learning_rate": 1.907692307692308e-06,
"loss": 0.0009,
"step": 5980
},
{
"epoch": 2.72,
"learning_rate": 1.876923076923077e-06,
"loss": 0.0009,
"step": 5990
},
{
"epoch": 2.73,
"learning_rate": 1.8461538461538465e-06,
"loss": 0.0009,
"step": 6000
},
{
"epoch": 2.73,
"learning_rate": 1.8153846153846154e-06,
"loss": 0.0603,
"step": 6010
},
{
"epoch": 2.74,
"learning_rate": 1.7846153846153846e-06,
"loss": 0.013,
"step": 6020
},
{
"epoch": 2.74,
"learning_rate": 1.753846153846154e-06,
"loss": 0.0023,
"step": 6030
},
{
"epoch": 2.75,
"learning_rate": 1.7230769230769232e-06,
"loss": 0.0009,
"step": 6040
},
{
"epoch": 2.75,
"learning_rate": 1.6923076923076926e-06,
"loss": 0.0007,
"step": 6050
},
{
"epoch": 2.75,
"learning_rate": 1.6615384615384616e-06,
"loss": 0.0305,
"step": 6060
},
{
"epoch": 2.76,
"learning_rate": 1.6307692307692307e-06,
"loss": 0.0008,
"step": 6070
},
{
"epoch": 2.76,
"learning_rate": 1.6000000000000001e-06,
"loss": 0.0544,
"step": 6080
},
{
"epoch": 2.77,
"learning_rate": 1.5692307692307693e-06,
"loss": 0.0691,
"step": 6090
},
{
"epoch": 2.77,
"learning_rate": 1.5384615384615387e-06,
"loss": 0.0217,
"step": 6100
},
{
"epoch": 2.78,
"learning_rate": 1.5076923076923077e-06,
"loss": 0.0579,
"step": 6110
},
{
"epoch": 2.78,
"learning_rate": 1.476923076923077e-06,
"loss": 0.0013,
"step": 6120
},
{
"epoch": 2.79,
"learning_rate": 1.4461538461538463e-06,
"loss": 0.0008,
"step": 6130
},
{
"epoch": 2.79,
"learning_rate": 1.4153846153846155e-06,
"loss": 0.0007,
"step": 6140
},
{
"epoch": 2.8,
"learning_rate": 1.3846153846153848e-06,
"loss": 0.0126,
"step": 6150
},
{
"epoch": 2.8,
"learning_rate": 1.3538461538461538e-06,
"loss": 0.0534,
"step": 6160
},
{
"epoch": 2.8,
"learning_rate": 1.3230769230769232e-06,
"loss": 0.1074,
"step": 6170
},
{
"epoch": 2.81,
"learning_rate": 1.2923076923076924e-06,
"loss": 0.001,
"step": 6180
},
{
"epoch": 2.81,
"learning_rate": 1.2615384615384616e-06,
"loss": 0.001,
"step": 6190
},
{
"epoch": 2.82,
"learning_rate": 1.230769230769231e-06,
"loss": 0.0106,
"step": 6200
},
{
"epoch": 2.82,
"learning_rate": 1.2000000000000002e-06,
"loss": 0.0008,
"step": 6210
},
{
"epoch": 2.83,
"learning_rate": 1.1692307692307693e-06,
"loss": 0.0681,
"step": 6220
},
{
"epoch": 2.83,
"learning_rate": 1.1384615384615385e-06,
"loss": 0.0008,
"step": 6230
},
{
"epoch": 2.84,
"learning_rate": 1.107692307692308e-06,
"loss": 0.0008,
"step": 6240
},
{
"epoch": 2.84,
"learning_rate": 1.076923076923077e-06,
"loss": 0.001,
"step": 6250
},
{
"epoch": 2.85,
"learning_rate": 1.0461538461538463e-06,
"loss": 0.0008,
"step": 6260
},
{
"epoch": 2.85,
"learning_rate": 1.0153846153846155e-06,
"loss": 0.0197,
"step": 6270
},
{
"epoch": 2.85,
"learning_rate": 9.846153846153847e-07,
"loss": 0.0016,
"step": 6280
},
{
"epoch": 2.86,
"learning_rate": 9.53846153846154e-07,
"loss": 0.0817,
"step": 6290
},
{
"epoch": 2.86,
"learning_rate": 9.230769230769232e-07,
"loss": 0.0281,
"step": 6300
},
{
"epoch": 2.87,
"learning_rate": 8.923076923076923e-07,
"loss": 0.0009,
"step": 6310
},
{
"epoch": 2.87,
"learning_rate": 8.615384615384616e-07,
"loss": 0.0158,
"step": 6320
},
{
"epoch": 2.88,
"learning_rate": 8.307692307692308e-07,
"loss": 0.0296,
"step": 6330
},
{
"epoch": 2.88,
"learning_rate": 8.000000000000001e-07,
"loss": 0.0334,
"step": 6340
},
{
"epoch": 2.89,
"learning_rate": 7.692307692307694e-07,
"loss": 0.0612,
"step": 6350
},
{
"epoch": 2.89,
"learning_rate": 7.384615384615385e-07,
"loss": 0.102,
"step": 6360
},
{
"epoch": 2.9,
"learning_rate": 7.076923076923077e-07,
"loss": 0.0007,
"step": 6370
},
{
"epoch": 2.9,
"learning_rate": 6.769230769230769e-07,
"loss": 0.097,
"step": 6380
},
{
"epoch": 2.9,
"learning_rate": 6.461538461538462e-07,
"loss": 0.1572,
"step": 6390
},
{
"epoch": 2.91,
"learning_rate": 6.153846153846155e-07,
"loss": 0.0007,
"step": 6400
},
{
"epoch": 2.91,
"learning_rate": 5.846153846153847e-07,
"loss": 0.0551,
"step": 6410
},
{
"epoch": 2.92,
"learning_rate": 5.53846153846154e-07,
"loss": 0.0014,
"step": 6420
},
{
"epoch": 2.92,
"learning_rate": 5.230769230769231e-07,
"loss": 0.001,
"step": 6430
},
{
"epoch": 2.93,
"learning_rate": 4.923076923076923e-07,
"loss": 0.0007,
"step": 6440
},
{
"epoch": 2.93,
"learning_rate": 4.615384615384616e-07,
"loss": 0.0009,
"step": 6450
},
{
"epoch": 2.94,
"learning_rate": 4.307692307692308e-07,
"loss": 0.0082,
"step": 6460
},
{
"epoch": 2.94,
"learning_rate": 4.0000000000000003e-07,
"loss": 0.0008,
"step": 6470
},
{
"epoch": 2.95,
"learning_rate": 3.6923076923076927e-07,
"loss": 0.0009,
"step": 6480
},
{
"epoch": 2.95,
"learning_rate": 3.3846153846153845e-07,
"loss": 0.0008,
"step": 6490
},
{
"epoch": 2.95,
"learning_rate": 3.0769230769230774e-07,
"loss": 0.0008,
"step": 6500
}
],
"max_steps": 6600,
"num_train_epochs": 3,
"total_flos": 1.368423174144e+16,
"trial_name": null,
"trial_params": null
}