KLGR123's picture
commit message
5f1c52b
raw
history blame contribute delete
No virus
41.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.27843859943039,
"eval_steps": 500,
"global_step": 3400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.99993842168232e-05,
"loss": 1.2211,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.9997536897627915e-05,
"loss": 1.0276,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.9994458133418e-05,
"loss": 0.8587,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 4.999014807586154e-05,
"loss": 0.7431,
"step": 40
},
{
"epoch": 0.03,
"learning_rate": 4.9984606937283405e-05,
"loss": 0.6841,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 4.9977834990654804e-05,
"loss": 0.6452,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 4.99698325695798e-05,
"loss": 0.6347,
"step": 70
},
{
"epoch": 0.05,
"learning_rate": 4.9960600068278876e-05,
"loss": 0.6109,
"step": 80
},
{
"epoch": 0.06,
"learning_rate": 4.995013794156957e-05,
"loss": 0.5911,
"step": 90
},
{
"epoch": 0.07,
"learning_rate": 4.993844670484401e-05,
"loss": 0.5803,
"step": 100
},
{
"epoch": 0.07,
"learning_rate": 4.992552693404354e-05,
"loss": 0.5902,
"step": 110
},
{
"epoch": 0.08,
"learning_rate": 4.991137926563036e-05,
"loss": 0.5745,
"step": 120
},
{
"epoch": 0.09,
"learning_rate": 4.9896004396556176e-05,
"loss": 0.5538,
"step": 130
},
{
"epoch": 0.09,
"learning_rate": 4.987940308422783e-05,
"loss": 0.5495,
"step": 140
},
{
"epoch": 0.1,
"learning_rate": 4.986157614647005e-05,
"loss": 0.5433,
"step": 150
},
{
"epoch": 0.11,
"learning_rate": 4.984252446148508e-05,
"loss": 0.548,
"step": 160
},
{
"epoch": 0.11,
"learning_rate": 4.98222489678095e-05,
"loss": 0.5361,
"step": 170
},
{
"epoch": 0.12,
"learning_rate": 4.980075066426796e-05,
"loss": 0.5331,
"step": 180
},
{
"epoch": 0.13,
"learning_rate": 4.977803060992393e-05,
"loss": 0.53,
"step": 190
},
{
"epoch": 0.13,
"learning_rate": 4.97540899240276e-05,
"loss": 0.5135,
"step": 200
},
{
"epoch": 0.14,
"learning_rate": 4.972892978596069e-05,
"loss": 0.5101,
"step": 210
},
{
"epoch": 0.15,
"learning_rate": 4.970255143517838e-05,
"loss": 0.5125,
"step": 220
},
{
"epoch": 0.15,
"learning_rate": 4.967495617114826e-05,
"loss": 0.4928,
"step": 230
},
{
"epoch": 0.16,
"learning_rate": 4.964614535328626e-05,
"loss": 0.4878,
"step": 240
},
{
"epoch": 0.17,
"learning_rate": 4.961612040088973e-05,
"loss": 0.5017,
"step": 250
},
{
"epoch": 0.17,
"learning_rate": 4.9584882793067534e-05,
"loss": 0.4863,
"step": 260
},
{
"epoch": 0.18,
"learning_rate": 4.955243406866713e-05,
"loss": 0.4847,
"step": 270
},
{
"epoch": 0.19,
"learning_rate": 4.951877582619881e-05,
"loss": 0.4868,
"step": 280
},
{
"epoch": 0.19,
"learning_rate": 4.948390972375694e-05,
"loss": 0.4748,
"step": 290
},
{
"epoch": 0.2,
"learning_rate": 4.944783747893825e-05,
"loss": 0.4764,
"step": 300
},
{
"epoch": 0.21,
"learning_rate": 4.941056086875727e-05,
"loss": 0.4712,
"step": 310
},
{
"epoch": 0.21,
"learning_rate": 4.937208172955876e-05,
"loss": 0.4642,
"step": 320
},
{
"epoch": 0.22,
"learning_rate": 4.9332401956927224e-05,
"loss": 0.4642,
"step": 330
},
{
"epoch": 0.23,
"learning_rate": 4.9291523505593604e-05,
"loss": 0.4709,
"step": 340
},
{
"epoch": 0.23,
"learning_rate": 4.9249448389338905e-05,
"loss": 0.461,
"step": 350
},
{
"epoch": 0.24,
"learning_rate": 4.920617868089501e-05,
"loss": 0.4677,
"step": 360
},
{
"epoch": 0.25,
"learning_rate": 4.9161716511842614e-05,
"loss": 0.4564,
"step": 370
},
{
"epoch": 0.25,
"learning_rate": 4.911606407250617e-05,
"loss": 0.4663,
"step": 380
},
{
"epoch": 0.26,
"learning_rate": 4.9069223611846014e-05,
"loss": 0.4682,
"step": 390
},
{
"epoch": 0.27,
"learning_rate": 4.9021197437347555e-05,
"loss": 0.4636,
"step": 400
},
{
"epoch": 0.27,
"learning_rate": 4.897198791490762e-05,
"loss": 0.4569,
"step": 410
},
{
"epoch": 0.28,
"learning_rate": 4.8921597468717887e-05,
"loss": 0.462,
"step": 420
},
{
"epoch": 0.29,
"learning_rate": 4.887002858114548e-05,
"loss": 0.4563,
"step": 430
},
{
"epoch": 0.29,
"learning_rate": 4.881728379261068e-05,
"loss": 0.4563,
"step": 440
},
{
"epoch": 0.3,
"learning_rate": 4.876336570146175e-05,
"loss": 0.4468,
"step": 450
},
{
"epoch": 0.31,
"learning_rate": 4.870827696384698e-05,
"loss": 0.4508,
"step": 460
},
{
"epoch": 0.31,
"learning_rate": 4.865202029358379e-05,
"loss": 0.4507,
"step": 470
},
{
"epoch": 0.32,
"learning_rate": 4.859459846202507e-05,
"loss": 0.4486,
"step": 480
},
{
"epoch": 0.33,
"learning_rate": 4.853601429792265e-05,
"loss": 0.4423,
"step": 490
},
{
"epoch": 0.34,
"learning_rate": 4.847627068728795e-05,
"loss": 0.4369,
"step": 500
},
{
"epoch": 0.34,
"learning_rate": 4.841537057324979e-05,
"loss": 0.4429,
"step": 510
},
{
"epoch": 0.35,
"learning_rate": 4.835331695590943e-05,
"loss": 0.4389,
"step": 520
},
{
"epoch": 0.36,
"learning_rate": 4.829011289219276e-05,
"loss": 0.44,
"step": 530
},
{
"epoch": 0.36,
"learning_rate": 4.82257614956997e-05,
"loss": 0.4476,
"step": 540
},
{
"epoch": 0.37,
"learning_rate": 4.816026593655085e-05,
"loss": 0.4367,
"step": 550
},
{
"epoch": 0.38,
"learning_rate": 4.809362944123129e-05,
"loss": 0.4357,
"step": 560
},
{
"epoch": 0.38,
"learning_rate": 4.802585529243164e-05,
"loss": 0.4492,
"step": 570
},
{
"epoch": 0.39,
"learning_rate": 4.795694682888635e-05,
"loss": 0.4403,
"step": 580
},
{
"epoch": 0.4,
"learning_rate": 4.7886907445209234e-05,
"loss": 0.4406,
"step": 590
},
{
"epoch": 0.4,
"learning_rate": 4.781574059172621e-05,
"loss": 0.4317,
"step": 600
},
{
"epoch": 0.41,
"learning_rate": 4.7743449774305386e-05,
"loss": 0.4379,
"step": 610
},
{
"epoch": 0.42,
"learning_rate": 4.7670038554184296e-05,
"loss": 0.4324,
"step": 620
},
{
"epoch": 0.42,
"learning_rate": 4.7595510547794465e-05,
"loss": 0.4329,
"step": 630
},
{
"epoch": 0.43,
"learning_rate": 4.751986942658332e-05,
"loss": 0.4259,
"step": 640
},
{
"epoch": 0.44,
"learning_rate": 4.744311891683325e-05,
"loss": 0.4256,
"step": 650
},
{
"epoch": 0.44,
"learning_rate": 4.736526279947807e-05,
"loss": 0.4289,
"step": 660
},
{
"epoch": 0.45,
"learning_rate": 4.728630490991676e-05,
"loss": 0.4353,
"step": 670
},
{
"epoch": 0.46,
"learning_rate": 4.7206249137824535e-05,
"loss": 0.4413,
"step": 680
},
{
"epoch": 0.46,
"learning_rate": 4.7125099426961185e-05,
"loss": 0.4302,
"step": 690
},
{
"epoch": 0.47,
"learning_rate": 4.704285977497687e-05,
"loss": 0.4365,
"step": 700
},
{
"epoch": 0.48,
"learning_rate": 4.6959534233215116e-05,
"loss": 0.4238,
"step": 710
},
{
"epoch": 0.48,
"learning_rate": 4.687512690651328e-05,
"loss": 0.4284,
"step": 720
},
{
"epoch": 0.49,
"learning_rate": 4.678964195300028e-05,
"loss": 0.4193,
"step": 730
},
{
"epoch": 0.5,
"learning_rate": 4.670308358389184e-05,
"loss": 0.4256,
"step": 740
},
{
"epoch": 0.5,
"learning_rate": 4.6615456063282944e-05,
"loss": 0.4288,
"step": 750
},
{
"epoch": 0.51,
"learning_rate": 4.652676370793784e-05,
"loss": 0.4335,
"step": 760
},
{
"epoch": 0.52,
"learning_rate": 4.643701088707736e-05,
"loss": 0.4271,
"step": 770
},
{
"epoch": 0.52,
"learning_rate": 4.634620202216366e-05,
"loss": 0.4304,
"step": 780
},
{
"epoch": 0.53,
"learning_rate": 4.625434158668246e-05,
"loss": 0.4249,
"step": 790
},
{
"epoch": 0.54,
"learning_rate": 4.6161434105922616e-05,
"loss": 0.4322,
"step": 800
},
{
"epoch": 0.54,
"learning_rate": 4.6067484156753234e-05,
"loss": 0.4229,
"step": 810
},
{
"epoch": 0.55,
"learning_rate": 4.597249636739815e-05,
"loss": 0.4252,
"step": 820
},
{
"epoch": 0.56,
"learning_rate": 4.5876475417207974e-05,
"loss": 0.413,
"step": 830
},
{
"epoch": 0.56,
"learning_rate": 4.577942603642959e-05,
"loss": 0.4186,
"step": 840
},
{
"epoch": 0.57,
"learning_rate": 4.568135300597306e-05,
"loss": 0.4233,
"step": 850
},
{
"epoch": 0.58,
"learning_rate": 4.5582261157176164e-05,
"loss": 0.4177,
"step": 860
},
{
"epoch": 0.58,
"learning_rate": 4.5482155371566384e-05,
"loss": 0.4236,
"step": 870
},
{
"epoch": 0.59,
"learning_rate": 4.538104058062042e-05,
"loss": 0.4228,
"step": 880
},
{
"epoch": 0.6,
"learning_rate": 4.5278921765521234e-05,
"loss": 0.4181,
"step": 890
},
{
"epoch": 0.6,
"learning_rate": 4.51758039569127e-05,
"loss": 0.4261,
"step": 900
},
{
"epoch": 0.61,
"learning_rate": 4.5071692234651764e-05,
"loss": 0.4217,
"step": 910
},
{
"epoch": 0.62,
"learning_rate": 4.4966591727558184e-05,
"loss": 0.4191,
"step": 920
},
{
"epoch": 0.62,
"learning_rate": 4.48605076131619e-05,
"loss": 0.4247,
"step": 930
},
{
"epoch": 0.63,
"learning_rate": 4.475344511744794e-05,
"loss": 0.4236,
"step": 940
},
{
"epoch": 0.64,
"learning_rate": 4.464540951459902e-05,
"loss": 0.4172,
"step": 950
},
{
"epoch": 0.64,
"learning_rate": 4.4536406126735664e-05,
"loss": 0.4209,
"step": 960
},
{
"epoch": 0.65,
"learning_rate": 4.442644032365407e-05,
"loss": 0.4179,
"step": 970
},
{
"epoch": 0.66,
"learning_rate": 4.431551752256155e-05,
"loss": 0.4166,
"step": 980
},
{
"epoch": 0.66,
"learning_rate": 4.420364318780973e-05,
"loss": 0.4173,
"step": 990
},
{
"epoch": 0.67,
"learning_rate": 4.4090822830625236e-05,
"loss": 0.4166,
"step": 1000
},
{
"epoch": 0.68,
"learning_rate": 4.3977062008838307e-05,
"loss": 0.4173,
"step": 1010
},
{
"epoch": 0.68,
"learning_rate": 4.3862366326608975e-05,
"loss": 0.4049,
"step": 1020
},
{
"epoch": 0.69,
"learning_rate": 4.374674143415096e-05,
"loss": 0.4143,
"step": 1030
},
{
"epoch": 0.7,
"learning_rate": 4.363019302745334e-05,
"loss": 0.4219,
"step": 1040
},
{
"epoch": 0.7,
"learning_rate": 4.3512726847999987e-05,
"loss": 0.4152,
"step": 1050
},
{
"epoch": 0.71,
"learning_rate": 4.339434868248665e-05,
"loss": 0.4153,
"step": 1060
},
{
"epoch": 0.72,
"learning_rate": 4.3275064362535966e-05,
"loss": 0.4148,
"step": 1070
},
{
"epoch": 0.72,
"learning_rate": 4.315487976441014e-05,
"loss": 0.4147,
"step": 1080
},
{
"epoch": 0.73,
"learning_rate": 4.303380080872145e-05,
"loss": 0.41,
"step": 1090
},
{
"epoch": 0.74,
"learning_rate": 4.291183346014063e-05,
"loss": 0.4119,
"step": 1100
},
{
"epoch": 0.74,
"learning_rate": 4.278898372710296e-05,
"loss": 0.4173,
"step": 1110
},
{
"epoch": 0.75,
"learning_rate": 4.266525766151238e-05,
"loss": 0.4119,
"step": 1120
},
{
"epoch": 0.76,
"learning_rate": 4.254066135844326e-05,
"loss": 0.4163,
"step": 1130
},
{
"epoch": 0.76,
"learning_rate": 4.2415200955840184e-05,
"loss": 0.4104,
"step": 1140
},
{
"epoch": 0.77,
"learning_rate": 4.228888263421557e-05,
"loss": 0.4045,
"step": 1150
},
{
"epoch": 0.78,
"learning_rate": 4.216171261634521e-05,
"loss": 0.413,
"step": 1160
},
{
"epoch": 0.78,
"learning_rate": 4.2033697166961716e-05,
"loss": 0.4112,
"step": 1170
},
{
"epoch": 0.79,
"learning_rate": 4.1904842592445906e-05,
"loss": 0.4018,
"step": 1180
},
{
"epoch": 0.8,
"learning_rate": 4.177515524051609e-05,
"loss": 0.4068,
"step": 1190
},
{
"epoch": 0.8,
"learning_rate": 4.1644641499915454e-05,
"loss": 0.4029,
"step": 1200
},
{
"epoch": 0.81,
"learning_rate": 4.151330780009726e-05,
"loss": 0.4009,
"step": 1210
},
{
"epoch": 0.82,
"learning_rate": 4.1381160610908134e-05,
"loss": 0.4073,
"step": 1220
},
{
"epoch": 0.82,
"learning_rate": 4.124820644226936e-05,
"loss": 0.4138,
"step": 1230
},
{
"epoch": 0.83,
"learning_rate": 4.111445184385616e-05,
"loss": 0.4139,
"step": 1240
},
{
"epoch": 0.84,
"learning_rate": 4.097990340477507e-05,
"loss": 0.4062,
"step": 1250
},
{
"epoch": 0.84,
"learning_rate": 4.0844567753239276e-05,
"loss": 0.4044,
"step": 1260
},
{
"epoch": 0.85,
"learning_rate": 4.070845155624221e-05,
"loss": 0.3978,
"step": 1270
},
{
"epoch": 0.86,
"learning_rate": 4.0571561519228984e-05,
"loss": 0.4102,
"step": 1280
},
{
"epoch": 0.86,
"learning_rate": 4.043390438576616e-05,
"loss": 0.4052,
"step": 1290
},
{
"epoch": 0.87,
"learning_rate": 4.029548693720949e-05,
"loss": 0.4048,
"step": 1300
},
{
"epoch": 0.88,
"learning_rate": 4.0156315992369864e-05,
"loss": 0.4008,
"step": 1310
},
{
"epoch": 0.88,
"learning_rate": 4.001639840717741e-05,
"loss": 0.4038,
"step": 1320
},
{
"epoch": 0.89,
"learning_rate": 3.9875741074343744e-05,
"loss": 0.408,
"step": 1330
},
{
"epoch": 0.9,
"learning_rate": 3.973435092302239e-05,
"loss": 0.406,
"step": 1340
},
{
"epoch": 0.9,
"learning_rate": 3.959223491846749e-05,
"loss": 0.3991,
"step": 1350
},
{
"epoch": 0.91,
"learning_rate": 3.94494000616906e-05,
"loss": 0.4091,
"step": 1360
},
{
"epoch": 0.92,
"learning_rate": 3.93058533891159e-05,
"loss": 0.4,
"step": 1370
},
{
"epoch": 0.92,
"learning_rate": 3.916160197223344e-05,
"loss": 0.4112,
"step": 1380
},
{
"epoch": 0.93,
"learning_rate": 3.901665291725091e-05,
"loss": 0.4024,
"step": 1390
},
{
"epoch": 0.94,
"learning_rate": 3.887101336474346e-05,
"loss": 0.4048,
"step": 1400
},
{
"epoch": 0.94,
"learning_rate": 3.8724690489302004e-05,
"loss": 0.4112,
"step": 1410
},
{
"epoch": 0.95,
"learning_rate": 3.857769149917973e-05,
"loss": 0.3947,
"step": 1420
},
{
"epoch": 0.96,
"learning_rate": 3.843002363593707e-05,
"loss": 0.4005,
"step": 1430
},
{
"epoch": 0.96,
"learning_rate": 3.828169417408488e-05,
"loss": 0.3976,
"step": 1440
},
{
"epoch": 0.97,
"learning_rate": 3.8132710420726146e-05,
"loss": 0.4006,
"step": 1450
},
{
"epoch": 0.98,
"learning_rate": 3.7983079715195984e-05,
"loss": 0.398,
"step": 1460
},
{
"epoch": 0.99,
"learning_rate": 3.78328094287001e-05,
"loss": 0.3987,
"step": 1470
},
{
"epoch": 0.99,
"learning_rate": 3.768190696395162e-05,
"loss": 0.4013,
"step": 1480
},
{
"epoch": 1.0,
"learning_rate": 3.7530379754806494e-05,
"loss": 0.4028,
"step": 1490
},
{
"epoch": 1.01,
"learning_rate": 3.737823526589722e-05,
"loss": 0.4036,
"step": 1500
},
{
"epoch": 1.01,
"learning_rate": 3.7225480992265125e-05,
"loss": 0.3937,
"step": 1510
},
{
"epoch": 1.02,
"learning_rate": 3.707212445899116e-05,
"loss": 0.4007,
"step": 1520
},
{
"epoch": 1.03,
"learning_rate": 3.6918173220825204e-05,
"loss": 0.4004,
"step": 1530
},
{
"epoch": 1.03,
"learning_rate": 3.6763634861813836e-05,
"loss": 0.4004,
"step": 1540
},
{
"epoch": 1.04,
"learning_rate": 3.660851699492679e-05,
"loss": 0.3991,
"step": 1550
},
{
"epoch": 1.05,
"learning_rate": 3.645282726168191e-05,
"loss": 0.4042,
"step": 1560
},
{
"epoch": 1.05,
"learning_rate": 3.6296573331768664e-05,
"loss": 0.4043,
"step": 1570
},
{
"epoch": 1.06,
"learning_rate": 3.613976290267036e-05,
"loss": 0.3948,
"step": 1580
},
{
"epoch": 1.07,
"learning_rate": 3.598240369928494e-05,
"loss": 0.3952,
"step": 1590
},
{
"epoch": 1.07,
"learning_rate": 3.5824503473544405e-05,
"loss": 0.4002,
"step": 1600
},
{
"epoch": 1.08,
"learning_rate": 3.566607000403298e-05,
"loss": 0.4079,
"step": 1610
},
{
"epoch": 1.09,
"learning_rate": 3.5523030408223166e-05,
"loss": 0.3942,
"step": 1620
},
{
"epoch": 1.09,
"learning_rate": 3.5363605299319165e-05,
"loss": 0.3935,
"step": 1630
},
{
"epoch": 1.1,
"learning_rate": 3.520366965171161e-05,
"loss": 0.3898,
"step": 1640
},
{
"epoch": 1.11,
"learning_rate": 3.504323134425501e-05,
"loss": 0.4006,
"step": 1650
},
{
"epoch": 1.11,
"learning_rate": 3.48822982805662e-05,
"loss": 0.4089,
"step": 1660
},
{
"epoch": 1.12,
"learning_rate": 3.472087838863505e-05,
"loss": 0.3982,
"step": 1670
},
{
"epoch": 1.13,
"learning_rate": 3.455897962043387e-05,
"loss": 0.399,
"step": 1680
},
{
"epoch": 1.13,
"learning_rate": 3.4396609951525676e-05,
"loss": 0.3964,
"step": 1690
},
{
"epoch": 1.14,
"learning_rate": 3.423377738067132e-05,
"loss": 0.3909,
"step": 1700
},
{
"epoch": 1.15,
"learning_rate": 3.407048992943541e-05,
"loss": 0.4015,
"step": 1710
},
{
"epoch": 1.15,
"learning_rate": 3.39067556417912e-05,
"loss": 0.3915,
"step": 1720
},
{
"epoch": 1.16,
"learning_rate": 3.374258258372426e-05,
"loss": 0.3845,
"step": 1730
},
{
"epoch": 1.17,
"learning_rate": 3.357797884283517e-05,
"loss": 0.4018,
"step": 1740
},
{
"epoch": 1.17,
"learning_rate": 3.3412952527941096e-05,
"loss": 0.3914,
"step": 1750
},
{
"epoch": 1.18,
"learning_rate": 3.32475117686763e-05,
"loss": 0.3909,
"step": 1760
},
{
"epoch": 1.19,
"learning_rate": 3.308166471509171e-05,
"loss": 0.3993,
"step": 1770
},
{
"epoch": 1.19,
"learning_rate": 3.2915419537253346e-05,
"loss": 0.3906,
"step": 1780
},
{
"epoch": 1.2,
"learning_rate": 3.274878442483991e-05,
"loss": 0.3897,
"step": 1790
},
{
"epoch": 1.21,
"learning_rate": 3.258176758673932e-05,
"loss": 0.3954,
"step": 1800
},
{
"epoch": 1.21,
"learning_rate": 3.241437725064431e-05,
"loss": 0.3835,
"step": 1810
},
{
"epoch": 1.22,
"learning_rate": 3.224662166264711e-05,
"loss": 0.3854,
"step": 1820
},
{
"epoch": 1.23,
"learning_rate": 3.207850908683322e-05,
"loss": 0.3924,
"step": 1830
},
{
"epoch": 1.23,
"learning_rate": 3.191004780487434e-05,
"loss": 0.3888,
"step": 1840
},
{
"epoch": 1.24,
"learning_rate": 3.1741246115620336e-05,
"loss": 0.3914,
"step": 1850
},
{
"epoch": 1.25,
"learning_rate": 3.157211233469042e-05,
"loss": 0.391,
"step": 1860
},
{
"epoch": 1.25,
"learning_rate": 3.140265479406358e-05,
"loss": 0.3916,
"step": 1870
},
{
"epoch": 1.26,
"learning_rate": 3.1232881841668015e-05,
"loss": 0.4012,
"step": 1880
},
{
"epoch": 1.27,
"learning_rate": 3.106280184096996e-05,
"loss": 0.3934,
"step": 1890
},
{
"epoch": 1.27,
"learning_rate": 3.089242317056168e-05,
"loss": 0.3908,
"step": 1900
},
{
"epoch": 1.28,
"learning_rate": 3.072175422374867e-05,
"loss": 0.3972,
"step": 1910
},
{
"epoch": 1.29,
"learning_rate": 3.055080340813623e-05,
"loss": 0.3963,
"step": 1920
},
{
"epoch": 1.29,
"learning_rate": 3.0379579145215287e-05,
"loss": 0.3941,
"step": 1930
},
{
"epoch": 1.3,
"learning_rate": 3.0208089869947475e-05,
"loss": 0.3887,
"step": 1940
},
{
"epoch": 1.31,
"learning_rate": 3.0036344030349644e-05,
"loss": 0.3879,
"step": 1950
},
{
"epoch": 1.31,
"learning_rate": 2.9864350087077702e-05,
"loss": 0.3945,
"step": 1960
},
{
"epoch": 1.32,
"learning_rate": 2.969211651300978e-05,
"loss": 0.3909,
"step": 1970
},
{
"epoch": 1.33,
"learning_rate": 2.9519651792828877e-05,
"loss": 0.3871,
"step": 1980
},
{
"epoch": 1.33,
"learning_rate": 2.9346964422604846e-05,
"loss": 0.3803,
"step": 1990
},
{
"epoch": 1.34,
"learning_rate": 2.9174062909375892e-05,
"loss": 0.3868,
"step": 2000
},
{
"epoch": 1.35,
"learning_rate": 2.9000955770729464e-05,
"loss": 0.385,
"step": 2010
},
{
"epoch": 1.35,
"learning_rate": 2.8827651534382655e-05,
"loss": 0.3871,
"step": 2020
},
{
"epoch": 1.36,
"learning_rate": 2.8654158737762122e-05,
"loss": 0.3956,
"step": 2030
},
{
"epoch": 1.37,
"learning_rate": 2.8480485927583506e-05,
"loss": 0.3884,
"step": 2040
},
{
"epoch": 1.37,
"learning_rate": 2.8306641659430382e-05,
"loss": 0.3829,
"step": 2050
},
{
"epoch": 1.38,
"learning_rate": 2.8132634497332815e-05,
"loss": 0.3916,
"step": 2060
},
{
"epoch": 1.39,
"learning_rate": 2.7958473013345447e-05,
"loss": 0.3924,
"step": 2070
},
{
"epoch": 1.39,
"learning_rate": 2.7784165787125226e-05,
"loss": 0.3906,
"step": 2080
},
{
"epoch": 1.4,
"learning_rate": 2.7609721405508758e-05,
"loss": 0.383,
"step": 2090
},
{
"epoch": 1.41,
"learning_rate": 2.7435148462089282e-05,
"loss": 0.3892,
"step": 2100
},
{
"epoch": 1.41,
"learning_rate": 2.7260455556793325e-05,
"loss": 0.3866,
"step": 2110
},
{
"epoch": 1.42,
"learning_rate": 2.708565129545706e-05,
"loss": 0.382,
"step": 2120
},
{
"epoch": 1.43,
"learning_rate": 2.691074428940237e-05,
"loss": 0.3825,
"step": 2130
},
{
"epoch": 1.43,
"learning_rate": 2.673574315501259e-05,
"loss": 0.3828,
"step": 2140
},
{
"epoch": 1.44,
"learning_rate": 2.656065651330808e-05,
"loss": 0.3845,
"step": 2150
},
{
"epoch": 1.45,
"learning_rate": 2.6385492989521522e-05,
"loss": 0.3904,
"step": 2160
},
{
"epoch": 1.45,
"learning_rate": 2.6210261212673004e-05,
"loss": 0.3934,
"step": 2170
},
{
"epoch": 1.46,
"learning_rate": 2.6034969815144938e-05,
"loss": 0.3893,
"step": 2180
},
{
"epoch": 1.47,
"learning_rate": 2.5859627432256816e-05,
"loss": 0.3965,
"step": 2190
},
{
"epoch": 1.47,
"learning_rate": 2.568424270183981e-05,
"loss": 0.3833,
"step": 2200
},
{
"epoch": 1.48,
"learning_rate": 2.550882426381123e-05,
"loss": 0.3822,
"step": 2210
},
{
"epoch": 1.49,
"learning_rate": 2.5333380759748925e-05,
"loss": 0.3823,
"step": 2220
},
{
"epoch": 1.49,
"learning_rate": 2.515792083246556e-05,
"loss": 0.3861,
"step": 2230
},
{
"epoch": 1.5,
"learning_rate": 2.4982453125582834e-05,
"loss": 0.3861,
"step": 2240
},
{
"epoch": 1.51,
"learning_rate": 2.4806986283105712e-05,
"loss": 0.3909,
"step": 2250
},
{
"epoch": 1.51,
"learning_rate": 2.463152894899658e-05,
"loss": 0.3854,
"step": 2260
},
{
"epoch": 1.52,
"learning_rate": 2.445608976674939e-05,
"loss": 0.394,
"step": 2270
},
{
"epoch": 1.53,
"learning_rate": 2.4280677378963906e-05,
"loss": 0.3866,
"step": 2280
},
{
"epoch": 1.53,
"learning_rate": 2.410530042691992e-05,
"loss": 0.3879,
"step": 2290
},
{
"epoch": 1.54,
"learning_rate": 2.3929967550151568e-05,
"loss": 0.388,
"step": 2300
},
{
"epoch": 1.55,
"learning_rate": 2.375468738602171e-05,
"loss": 0.3868,
"step": 2310
},
{
"epoch": 1.55,
"learning_rate": 2.3579468569296464e-05,
"loss": 0.3769,
"step": 2320
},
{
"epoch": 1.56,
"learning_rate": 2.340431973171978e-05,
"loss": 0.3811,
"step": 2330
},
{
"epoch": 1.57,
"learning_rate": 2.3229249501588278e-05,
"loss": 0.3805,
"step": 2340
},
{
"epoch": 1.57,
"learning_rate": 2.3054266503326165e-05,
"loss": 0.3822,
"step": 2350
},
{
"epoch": 1.58,
"learning_rate": 2.2879379357060345e-05,
"loss": 0.3875,
"step": 2360
},
{
"epoch": 1.59,
"learning_rate": 2.2704596678195827e-05,
"loss": 0.3884,
"step": 2370
},
{
"epoch": 1.59,
"learning_rate": 2.2529927076991283e-05,
"loss": 0.381,
"step": 2380
},
{
"epoch": 1.6,
"learning_rate": 2.2355379158134843e-05,
"loss": 0.3933,
"step": 2390
},
{
"epoch": 1.61,
"learning_rate": 2.2180961520320278e-05,
"loss": 0.3853,
"step": 2400
},
{
"epoch": 1.62,
"learning_rate": 2.2006682755823367e-05,
"loss": 0.3871,
"step": 2410
},
{
"epoch": 1.62,
"learning_rate": 2.1832551450078594e-05,
"loss": 0.3867,
"step": 2420
},
{
"epoch": 1.63,
"learning_rate": 2.165857618125625e-05,
"loss": 0.3878,
"step": 2430
},
{
"epoch": 1.64,
"learning_rate": 2.1484765519839843e-05,
"loss": 0.386,
"step": 2440
},
{
"epoch": 1.64,
"learning_rate": 2.1311128028203863e-05,
"loss": 0.3836,
"step": 2450
},
{
"epoch": 1.65,
"learning_rate": 2.1137672260192004e-05,
"loss": 0.3849,
"step": 2460
},
{
"epoch": 1.66,
"learning_rate": 2.09644067606958e-05,
"loss": 0.3841,
"step": 2470
},
{
"epoch": 1.66,
"learning_rate": 2.079134006523359e-05,
"loss": 0.3848,
"step": 2480
},
{
"epoch": 1.67,
"learning_rate": 2.061848069953017e-05,
"loss": 0.3817,
"step": 2490
},
{
"epoch": 1.68,
"learning_rate": 2.044583717909667e-05,
"loss": 0.3839,
"step": 2500
},
{
"epoch": 1.68,
"learning_rate": 2.0273418008811125e-05,
"loss": 0.3749,
"step": 2510
},
{
"epoch": 1.69,
"learning_rate": 2.0101231682499506e-05,
"loss": 0.3824,
"step": 2520
},
{
"epoch": 1.7,
"learning_rate": 1.9929286682517235e-05,
"loss": 0.3854,
"step": 2530
},
{
"epoch": 1.7,
"learning_rate": 1.9757591479331382e-05,
"loss": 0.3894,
"step": 2540
},
{
"epoch": 1.71,
"learning_rate": 1.9586154531103373e-05,
"loss": 0.3871,
"step": 2550
},
{
"epoch": 1.72,
"learning_rate": 1.9414984283272286e-05,
"loss": 0.382,
"step": 2560
},
{
"epoch": 1.72,
"learning_rate": 1.9244089168138836e-05,
"loss": 0.3858,
"step": 2570
},
{
"epoch": 1.73,
"learning_rate": 1.9073477604449985e-05,
"loss": 0.3819,
"step": 2580
},
{
"epoch": 1.74,
"learning_rate": 1.8903157996984174e-05,
"loss": 0.3795,
"step": 2590
},
{
"epoch": 1.74,
"learning_rate": 1.873313873613733e-05,
"loss": 0.3827,
"step": 2600
},
{
"epoch": 1.75,
"learning_rate": 1.8563428197509502e-05,
"loss": 0.385,
"step": 2610
},
{
"epoch": 1.76,
"learning_rate": 1.839403474149225e-05,
"loss": 0.3846,
"step": 2620
},
{
"epoch": 1.76,
"learning_rate": 1.8224966712856806e-05,
"loss": 0.3828,
"step": 2630
},
{
"epoch": 1.77,
"learning_rate": 1.8056232440343013e-05,
"loss": 0.3792,
"step": 2640
},
{
"epoch": 1.78,
"learning_rate": 1.788784023624896e-05,
"loss": 0.3814,
"step": 2650
},
{
"epoch": 1.78,
"learning_rate": 1.7719798396021558e-05,
"loss": 0.3819,
"step": 2660
},
{
"epoch": 1.79,
"learning_rate": 1.7552115197847884e-05,
"loss": 0.3798,
"step": 2670
},
{
"epoch": 1.8,
"learning_rate": 1.7384798902247316e-05,
"loss": 0.3772,
"step": 2680
},
{
"epoch": 1.8,
"learning_rate": 1.7217857751664663e-05,
"loss": 0.3758,
"step": 2690
},
{
"epoch": 1.81,
"learning_rate": 1.7051299970064098e-05,
"loss": 0.3706,
"step": 2700
},
{
"epoch": 1.82,
"learning_rate": 1.6885133762523985e-05,
"loss": 0.3805,
"step": 2710
},
{
"epoch": 1.82,
"learning_rate": 1.6719367314832756e-05,
"loss": 0.3892,
"step": 2720
},
{
"epoch": 1.83,
"learning_rate": 1.65540087930856e-05,
"loss": 0.387,
"step": 2730
},
{
"epoch": 1.84,
"learning_rate": 1.6389066343282168e-05,
"loss": 0.3773,
"step": 2740
},
{
"epoch": 1.84,
"learning_rate": 1.6224548090925323e-05,
"loss": 0.3829,
"step": 2750
},
{
"epoch": 1.85,
"learning_rate": 1.6060462140620835e-05,
"loss": 0.3697,
"step": 2760
},
{
"epoch": 1.86,
"learning_rate": 1.589681657567811e-05,
"loss": 0.3817,
"step": 2770
},
{
"epoch": 1.86,
"learning_rate": 1.5733619457712037e-05,
"loss": 0.3819,
"step": 2780
},
{
"epoch": 1.87,
"learning_rate": 1.5570878826245773e-05,
"loss": 0.3756,
"step": 2790
},
{
"epoch": 1.88,
"learning_rate": 1.5408602698314777e-05,
"loss": 0.3791,
"step": 2800
},
{
"epoch": 1.88,
"learning_rate": 1.5246799068071818e-05,
"loss": 0.3765,
"step": 2810
},
{
"epoch": 1.89,
"learning_rate": 1.5085475906393153e-05,
"loss": 0.3834,
"step": 2820
},
{
"epoch": 1.9,
"learning_rate": 1.4924641160485923e-05,
"loss": 0.381,
"step": 2830
},
{
"epoch": 1.9,
"learning_rate": 1.4764302753496584e-05,
"loss": 0.3766,
"step": 2840
},
{
"epoch": 1.91,
"learning_rate": 1.4604468584120607e-05,
"loss": 0.3815,
"step": 2850
},
{
"epoch": 1.92,
"learning_rate": 1.4445146526213415e-05,
"loss": 0.3774,
"step": 2860
},
{
"epoch": 1.92,
"learning_rate": 1.4286344428402454e-05,
"loss": 0.3879,
"step": 2870
},
{
"epoch": 1.93,
"learning_rate": 1.412807011370052e-05,
"loss": 0.3777,
"step": 2880
},
{
"epoch": 1.94,
"learning_rate": 1.3970331379120455e-05,
"loss": 0.3806,
"step": 2890
},
{
"epoch": 1.94,
"learning_rate": 1.3813135995290988e-05,
"loss": 0.3848,
"step": 2900
},
{
"epoch": 1.95,
"learning_rate": 1.3656491706073935e-05,
"loss": 0.3745,
"step": 2910
},
{
"epoch": 1.96,
"learning_rate": 1.350040622818275e-05,
"loss": 0.377,
"step": 2920
},
{
"epoch": 1.96,
"learning_rate": 1.3344887250802345e-05,
"loss": 0.3783,
"step": 2930
},
{
"epoch": 1.97,
"learning_rate": 1.3189942435210301e-05,
"loss": 0.3768,
"step": 2940
},
{
"epoch": 1.98,
"learning_rate": 1.303557941439949e-05,
"loss": 0.3744,
"step": 2950
},
{
"epoch": 1.98,
"learning_rate": 1.2881805792702031e-05,
"loss": 0.3788,
"step": 2960
},
{
"epoch": 1.99,
"learning_rate": 1.2728629145414645e-05,
"loss": 0.3735,
"step": 2970
},
{
"epoch": 2.0,
"learning_rate": 1.257605701842554e-05,
"loss": 0.3819,
"step": 2980
},
{
"epoch": 2.0,
"learning_rate": 1.242409692784265e-05,
"loss": 0.3812,
"step": 2990
},
{
"epoch": 2.01,
"learning_rate": 1.2272756359623342e-05,
"loss": 0.3769,
"step": 3000
},
{
"epoch": 2.02,
"learning_rate": 1.2122042769205702e-05,
"loss": 0.3779,
"step": 3010
},
{
"epoch": 2.02,
"learning_rate": 1.1971963581141196e-05,
"loss": 0.3817,
"step": 3020
},
{
"epoch": 2.03,
"learning_rate": 1.1822526188728966e-05,
"loss": 0.3788,
"step": 3030
},
{
"epoch": 2.04,
"learning_rate": 1.1673737953651601e-05,
"loss": 0.3776,
"step": 3040
},
{
"epoch": 2.04,
"learning_rate": 1.1525606205612447e-05,
"loss": 0.3785,
"step": 3050
},
{
"epoch": 2.05,
"learning_rate": 1.1378138241974595e-05,
"loss": 0.3858,
"step": 3060
},
{
"epoch": 2.06,
"learning_rate": 1.1231341327401323e-05,
"loss": 0.3766,
"step": 3070
},
{
"epoch": 2.06,
"learning_rate": 1.1085222693498256e-05,
"loss": 0.3766,
"step": 3080
},
{
"epoch": 2.07,
"learning_rate": 1.093978953845713e-05,
"loss": 0.3795,
"step": 3090
},
{
"epoch": 2.08,
"learning_rate": 1.079504902670117e-05,
"loss": 0.3837,
"step": 3100
},
{
"epoch": 2.08,
"learning_rate": 1.065100828853213e-05,
"loss": 0.377,
"step": 3110
},
{
"epoch": 2.09,
"learning_rate": 1.0507674419779085e-05,
"loss": 0.3759,
"step": 3120
},
{
"epoch": 2.1,
"learning_rate": 1.0365054481448849e-05,
"loss": 0.3704,
"step": 3130
},
{
"epoch": 2.1,
"learning_rate": 1.02231554993781e-05,
"loss": 0.3751,
"step": 3140
},
{
"epoch": 2.11,
"learning_rate": 1.0081984463887325e-05,
"loss": 0.396,
"step": 3150
},
{
"epoch": 2.12,
"learning_rate": 9.941548329436425e-06,
"loss": 0.3788,
"step": 3160
},
{
"epoch": 2.12,
"learning_rate": 9.801854014282108e-06,
"loss": 0.3767,
"step": 3170
},
{
"epoch": 2.13,
"learning_rate": 9.662908400137125e-06,
"loss": 0.3783,
"step": 3180
},
{
"epoch": 2.14,
"learning_rate": 9.524718331831186e-06,
"loss": 0.3775,
"step": 3190
},
{
"epoch": 2.14,
"learning_rate": 9.387290616973859e-06,
"loss": 0.3789,
"step": 3200
},
{
"epoch": 2.15,
"learning_rate": 9.250632025619104e-06,
"loss": 0.3776,
"step": 3210
},
{
"epoch": 2.16,
"learning_rate": 9.11474928993187e-06,
"loss": 0.368,
"step": 3220
},
{
"epoch": 2.16,
"learning_rate": 8.979649103856345e-06,
"loss": 0.378,
"step": 3230
},
{
"epoch": 2.17,
"learning_rate": 8.84533812278629e-06,
"loss": 0.3776,
"step": 3240
},
{
"epoch": 2.18,
"learning_rate": 8.711822963237093e-06,
"loss": 0.3731,
"step": 3250
},
{
"epoch": 2.18,
"learning_rate": 8.579110202519894e-06,
"loss": 0.3827,
"step": 3260
},
{
"epoch": 2.19,
"learning_rate": 8.447206378417533e-06,
"loss": 0.3725,
"step": 3270
},
{
"epoch": 2.2,
"learning_rate": 8.31611798886246e-06,
"loss": 0.372,
"step": 3280
},
{
"epoch": 2.2,
"learning_rate": 8.185851491616677e-06,
"loss": 0.3753,
"step": 3290
},
{
"epoch": 2.21,
"learning_rate": 8.0564133039536e-06,
"loss": 0.3732,
"step": 3300
},
{
"epoch": 2.22,
"learning_rate": 7.927809802341876e-06,
"loss": 0.37,
"step": 3310
},
{
"epoch": 2.22,
"learning_rate": 7.800047322131346e-06,
"loss": 0.372,
"step": 3320
},
{
"epoch": 2.23,
"learning_rate": 7.673132157240877e-06,
"loss": 0.3734,
"step": 3330
},
{
"epoch": 2.24,
"learning_rate": 7.5470705598483405e-06,
"loss": 0.3734,
"step": 3340
},
{
"epoch": 2.24,
"learning_rate": 7.4218687400826075e-06,
"loss": 0.3784,
"step": 3350
},
{
"epoch": 2.25,
"learning_rate": 7.297532865717638e-06,
"loss": 0.3715,
"step": 3360
},
{
"epoch": 2.26,
"learning_rate": 7.174069061868591e-06,
"loss": 0.3836,
"step": 3370
},
{
"epoch": 2.27,
"learning_rate": 7.05148341069014e-06,
"loss": 0.3784,
"step": 3380
},
{
"epoch": 2.27,
"learning_rate": 6.929781951076836e-06,
"loss": 0.3737,
"step": 3390
},
{
"epoch": 2.28,
"learning_rate": 6.80897067836557e-06,
"loss": 0.3827,
"step": 3400
}
],
"logging_steps": 10,
"max_steps": 4476,
"num_train_epochs": 3,
"save_steps": 200,
"total_flos": 3.0930648367343075e+19,
"trial_name": null,
"trial_params": null
}