llama20pGrad_2 / trainer_state.json
terry69's picture
Model save
cda8996 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 812,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0012315270935960591,
"grad_norm": 0.3202645778656006,
"learning_rate": 2.4390243902439027e-06,
"loss": 1.0034,
"step": 1
},
{
"epoch": 0.006157635467980296,
"grad_norm": 0.34312453866004944,
"learning_rate": 1.2195121951219513e-05,
"loss": 0.978,
"step": 5
},
{
"epoch": 0.012315270935960592,
"grad_norm": 0.3679831922054291,
"learning_rate": 2.4390243902439026e-05,
"loss": 0.9639,
"step": 10
},
{
"epoch": 0.01847290640394089,
"grad_norm": 0.12030908465385437,
"learning_rate": 3.6585365853658535e-05,
"loss": 0.979,
"step": 15
},
{
"epoch": 0.024630541871921183,
"grad_norm": 0.1297861486673355,
"learning_rate": 4.878048780487805e-05,
"loss": 0.978,
"step": 20
},
{
"epoch": 0.03078817733990148,
"grad_norm": 0.10942083597183228,
"learning_rate": 6.097560975609756e-05,
"loss": 0.9532,
"step": 25
},
{
"epoch": 0.03694581280788178,
"grad_norm": 0.11847982555627823,
"learning_rate": 7.317073170731707e-05,
"loss": 0.8874,
"step": 30
},
{
"epoch": 0.04310344827586207,
"grad_norm": 0.10410485416650772,
"learning_rate": 8.53658536585366e-05,
"loss": 0.9053,
"step": 35
},
{
"epoch": 0.04926108374384237,
"grad_norm": 0.11295271664857864,
"learning_rate": 9.75609756097561e-05,
"loss": 0.9043,
"step": 40
},
{
"epoch": 0.05541871921182266,
"grad_norm": 0.09398676455020905,
"learning_rate": 0.00010975609756097563,
"loss": 0.8799,
"step": 45
},
{
"epoch": 0.06157635467980296,
"grad_norm": 0.10218280553817749,
"learning_rate": 0.00012195121951219512,
"loss": 0.8744,
"step": 50
},
{
"epoch": 0.06773399014778325,
"grad_norm": 0.10606866329908371,
"learning_rate": 0.00013414634146341464,
"loss": 0.8531,
"step": 55
},
{
"epoch": 0.07389162561576355,
"grad_norm": 0.09138131886720657,
"learning_rate": 0.00014634146341463414,
"loss": 0.8552,
"step": 60
},
{
"epoch": 0.08004926108374384,
"grad_norm": 0.10347121208906174,
"learning_rate": 0.00015853658536585366,
"loss": 0.8607,
"step": 65
},
{
"epoch": 0.08620689655172414,
"grad_norm": 0.09866124391555786,
"learning_rate": 0.0001707317073170732,
"loss": 0.8585,
"step": 70
},
{
"epoch": 0.09236453201970443,
"grad_norm": 0.10218536853790283,
"learning_rate": 0.0001829268292682927,
"loss": 0.8677,
"step": 75
},
{
"epoch": 0.09852216748768473,
"grad_norm": 0.10015806555747986,
"learning_rate": 0.0001951219512195122,
"loss": 0.861,
"step": 80
},
{
"epoch": 0.10467980295566502,
"grad_norm": 0.09940984100103378,
"learning_rate": 0.0001999916658654738,
"loss": 0.865,
"step": 85
},
{
"epoch": 0.11083743842364532,
"grad_norm": 0.09865906834602356,
"learning_rate": 0.0001999407400739705,
"loss": 0.8697,
"step": 90
},
{
"epoch": 0.11699507389162561,
"grad_norm": 0.10052310675382614,
"learning_rate": 0.00019984354211555644,
"loss": 0.8674,
"step": 95
},
{
"epoch": 0.12315270935960591,
"grad_norm": 0.09879495203495026,
"learning_rate": 0.00019970011699250152,
"loss": 0.8218,
"step": 100
},
{
"epoch": 0.12931034482758622,
"grad_norm": 0.10285568237304688,
"learning_rate": 0.00019951053111006976,
"loss": 0.8663,
"step": 105
},
{
"epoch": 0.1354679802955665,
"grad_norm": 0.10076833516359329,
"learning_rate": 0.00019927487224577402,
"loss": 0.8656,
"step": 110
},
{
"epoch": 0.1416256157635468,
"grad_norm": 0.10918958485126495,
"learning_rate": 0.0001989932495087353,
"loss": 0.8466,
"step": 115
},
{
"epoch": 0.1477832512315271,
"grad_norm": 0.10598968714475632,
"learning_rate": 0.0001986657932891657,
"loss": 0.8359,
"step": 120
},
{
"epoch": 0.1539408866995074,
"grad_norm": 0.10305009037256241,
"learning_rate": 0.0001982926551979982,
"loss": 0.8633,
"step": 125
},
{
"epoch": 0.16009852216748768,
"grad_norm": 0.1001807376742363,
"learning_rate": 0.00019787400799669154,
"loss": 0.8669,
"step": 130
},
{
"epoch": 0.16625615763546797,
"grad_norm": 0.11495460569858551,
"learning_rate": 0.00019741004551724207,
"loss": 0.8379,
"step": 135
},
{
"epoch": 0.1724137931034483,
"grad_norm": 0.09955433756113052,
"learning_rate": 0.00019690098257244064,
"loss": 0.847,
"step": 140
},
{
"epoch": 0.17857142857142858,
"grad_norm": 0.09870877861976624,
"learning_rate": 0.00019634705485641488,
"loss": 0.8419,
"step": 145
},
{
"epoch": 0.18472906403940886,
"grad_norm": 0.09604347497224808,
"learning_rate": 0.00019574851883550395,
"loss": 0.8751,
"step": 150
},
{
"epoch": 0.19088669950738915,
"grad_norm": 0.09326177835464478,
"learning_rate": 0.00019510565162951537,
"loss": 0.8586,
"step": 155
},
{
"epoch": 0.19704433497536947,
"grad_norm": 0.09584691375494003,
"learning_rate": 0.00019441875088341997,
"loss": 0.8613,
"step": 160
},
{
"epoch": 0.20320197044334976,
"grad_norm": 0.08351971209049225,
"learning_rate": 0.00019368813462954316,
"loss": 0.8533,
"step": 165
},
{
"epoch": 0.20935960591133004,
"grad_norm": 0.09796614199876785,
"learning_rate": 0.00019291414114031743,
"loss": 0.8551,
"step": 170
},
{
"epoch": 0.21551724137931033,
"grad_norm": 0.09448806941509247,
"learning_rate": 0.00019209712877166349,
"loss": 0.8531,
"step": 175
},
{
"epoch": 0.22167487684729065,
"grad_norm": 0.09499138593673706,
"learning_rate": 0.00019123747579707275,
"loss": 0.8679,
"step": 180
},
{
"epoch": 0.22783251231527094,
"grad_norm": 0.11031397432088852,
"learning_rate": 0.00019033558023246844,
"loss": 0.8238,
"step": 185
},
{
"epoch": 0.23399014778325122,
"grad_norm": 0.09239893406629562,
"learning_rate": 0.0001893918596519257,
"loss": 0.8438,
"step": 190
},
{
"epoch": 0.24014778325123154,
"grad_norm": 0.09333900362253189,
"learning_rate": 0.00018840675099433636,
"loss": 0.8437,
"step": 195
},
{
"epoch": 0.24630541871921183,
"grad_norm": 0.10700402408838272,
"learning_rate": 0.00018738071036110808,
"loss": 0.8108,
"step": 200
},
{
"epoch": 0.2524630541871921,
"grad_norm": 0.09482070803642273,
"learning_rate": 0.00018631421280499116,
"loss": 0.8326,
"step": 205
},
{
"epoch": 0.25862068965517243,
"grad_norm": 0.0902240052819252,
"learning_rate": 0.00018520775211013093,
"loss": 0.8637,
"step": 210
},
{
"epoch": 0.2647783251231527,
"grad_norm": 0.0930478647351265,
"learning_rate": 0.00018406184056344782,
"loss": 0.8424,
"step": 215
},
{
"epoch": 0.270935960591133,
"grad_norm": 0.09855949133634567,
"learning_rate": 0.00018287700871745036,
"loss": 0.839,
"step": 220
},
{
"epoch": 0.2770935960591133,
"grad_norm": 0.10178953409194946,
"learning_rate": 0.0001816538051445916,
"loss": 0.8726,
"step": 225
},
{
"epoch": 0.2832512315270936,
"grad_norm": 0.09509410709142685,
"learning_rate": 0.00018039279618328212,
"loss": 0.8709,
"step": 230
},
{
"epoch": 0.2894088669950739,
"grad_norm": 0.09647022932767868,
"learning_rate": 0.00017909456567567772,
"loss": 0.8695,
"step": 235
},
{
"epoch": 0.2955665024630542,
"grad_norm": 0.0976739376783371,
"learning_rate": 0.0001777597146973627,
"loss": 0.8577,
"step": 240
},
{
"epoch": 0.3017241379310345,
"grad_norm": 0.09781508892774582,
"learning_rate": 0.00017638886127905427,
"loss": 0.8495,
"step": 245
},
{
"epoch": 0.3078817733990148,
"grad_norm": 0.09447339177131653,
"learning_rate": 0.00017498264012045687,
"loss": 0.8569,
"step": 250
},
{
"epoch": 0.31403940886699505,
"grad_norm": 0.09428857266902924,
"learning_rate": 0.00017354170229639856,
"loss": 0.8309,
"step": 255
},
{
"epoch": 0.32019704433497537,
"grad_norm": 0.09784238040447235,
"learning_rate": 0.00017206671495538612,
"loss": 0.88,
"step": 260
},
{
"epoch": 0.3263546798029557,
"grad_norm": 0.10478725284337997,
"learning_rate": 0.0001705583610107178,
"loss": 0.8466,
"step": 265
},
{
"epoch": 0.33251231527093594,
"grad_norm": 0.10171061754226685,
"learning_rate": 0.0001690173388242972,
"loss": 0.8407,
"step": 270
},
{
"epoch": 0.33866995073891626,
"grad_norm": 0.09914927929639816,
"learning_rate": 0.00016744436188329456,
"loss": 0.8362,
"step": 275
},
{
"epoch": 0.3448275862068966,
"grad_norm": 0.10386697202920914,
"learning_rate": 0.0001658401584698049,
"loss": 0.842,
"step": 280
},
{
"epoch": 0.35098522167487683,
"grad_norm": 0.09510869532823563,
"learning_rate": 0.00016420547132365635,
"loss": 0.8615,
"step": 285
},
{
"epoch": 0.35714285714285715,
"grad_norm": 0.10018317401409149,
"learning_rate": 0.00016254105729852464,
"loss": 0.88,
"step": 290
},
{
"epoch": 0.3633004926108374,
"grad_norm": 0.0965588241815567,
"learning_rate": 0.00016084768701151263,
"loss": 0.8345,
"step": 295
},
{
"epoch": 0.3694581280788177,
"grad_norm": 0.09997261315584183,
"learning_rate": 0.00015912614448635782,
"loss": 0.8474,
"step": 300
},
{
"epoch": 0.37561576354679804,
"grad_norm": 0.1020544171333313,
"learning_rate": 0.00015737722679043248,
"loss": 0.8398,
"step": 305
},
{
"epoch": 0.3817733990147783,
"grad_norm": 0.09508492052555084,
"learning_rate": 0.00015560174366570446,
"loss": 0.8346,
"step": 310
},
{
"epoch": 0.3879310344827586,
"grad_norm": 0.09102219343185425,
"learning_rate": 0.00015380051715382996,
"loss": 0.8834,
"step": 315
},
{
"epoch": 0.39408866995073893,
"grad_norm": 0.09441574662923813,
"learning_rate": 0.0001519743812155516,
"loss": 0.8431,
"step": 320
},
{
"epoch": 0.4002463054187192,
"grad_norm": 0.10017410665750504,
"learning_rate": 0.00015012418134457755,
"loss": 0.868,
"step": 325
},
{
"epoch": 0.4064039408866995,
"grad_norm": 0.09937512874603271,
"learning_rate": 0.00014825077417612186,
"loss": 0.8404,
"step": 330
},
{
"epoch": 0.4125615763546798,
"grad_norm": 0.1004796102643013,
"learning_rate": 0.0001463550270902851,
"loss": 0.8417,
"step": 335
},
{
"epoch": 0.4187192118226601,
"grad_norm": 0.09814818203449249,
"learning_rate": 0.00014443781781046136,
"loss": 0.8592,
"step": 340
},
{
"epoch": 0.4248768472906404,
"grad_norm": 0.09534980356693268,
"learning_rate": 0.0001425000339969554,
"loss": 0.8637,
"step": 345
},
{
"epoch": 0.43103448275862066,
"grad_norm": 0.09524567425251007,
"learning_rate": 0.00014054257283599973,
"loss": 0.8278,
"step": 350
},
{
"epoch": 0.437192118226601,
"grad_norm": 0.09492156654596329,
"learning_rate": 0.0001385663406243607,
"loss": 0.8371,
"step": 355
},
{
"epoch": 0.4433497536945813,
"grad_norm": 0.10173512995243073,
"learning_rate": 0.00013657225234972695,
"loss": 0.8592,
"step": 360
},
{
"epoch": 0.44950738916256155,
"grad_norm": 0.11124896258115768,
"learning_rate": 0.00013456123126707334,
"loss": 0.8543,
"step": 365
},
{
"epoch": 0.45566502463054187,
"grad_norm": 0.09352728724479675,
"learning_rate": 0.00013253420847119803,
"loss": 0.8592,
"step": 370
},
{
"epoch": 0.4618226600985222,
"grad_norm": 0.11169470101594925,
"learning_rate": 0.0001304921224656289,
"loss": 0.8233,
"step": 375
},
{
"epoch": 0.46798029556650245,
"grad_norm": 0.09410259872674942,
"learning_rate": 0.0001284359187281004,
"loss": 0.8702,
"step": 380
},
{
"epoch": 0.47413793103448276,
"grad_norm": 0.09482759982347488,
"learning_rate": 0.00012636654927280073,
"loss": 0.818,
"step": 385
},
{
"epoch": 0.4802955665024631,
"grad_norm": 0.11693406850099564,
"learning_rate": 0.0001242849722095936,
"loss": 0.8476,
"step": 390
},
{
"epoch": 0.48645320197044334,
"grad_norm": 0.09488484263420105,
"learning_rate": 0.00012219215130041656,
"loss": 0.7966,
"step": 395
},
{
"epoch": 0.49261083743842365,
"grad_norm": 0.09644895046949387,
"learning_rate": 0.00012008905551306356,
"loss": 0.8411,
"step": 400
},
{
"epoch": 0.4987684729064039,
"grad_norm": 0.09742914140224457,
"learning_rate": 0.00011797665857255621,
"loss": 0.8306,
"step": 405
},
{
"epoch": 0.5049261083743842,
"grad_norm": 0.11031042784452438,
"learning_rate": 0.00011585593851031347,
"loss": 0.8356,
"step": 410
},
{
"epoch": 0.5110837438423645,
"grad_norm": 0.11047101765871048,
"learning_rate": 0.00011372787721132648,
"loss": 0.8616,
"step": 415
},
{
"epoch": 0.5172413793103449,
"grad_norm": 0.11460606008768082,
"learning_rate": 0.00011159345995955006,
"loss": 0.8332,
"step": 420
},
{
"epoch": 0.5233990147783252,
"grad_norm": 0.09033536165952682,
"learning_rate": 0.00010945367498171993,
"loss": 0.8455,
"step": 425
},
{
"epoch": 0.5295566502463054,
"grad_norm": 0.09113427996635437,
"learning_rate": 0.00010730951298980776,
"loss": 0.871,
"step": 430
},
{
"epoch": 0.5357142857142857,
"grad_norm": 0.09332713484764099,
"learning_rate": 0.00010516196672232539,
"loss": 0.8643,
"step": 435
},
{
"epoch": 0.541871921182266,
"grad_norm": 0.09998837858438492,
"learning_rate": 0.00010301203048469083,
"loss": 0.838,
"step": 440
},
{
"epoch": 0.5480295566502463,
"grad_norm": 0.09564919024705887,
"learning_rate": 0.00010086069968886885,
"loss": 0.8245,
"step": 445
},
{
"epoch": 0.5541871921182266,
"grad_norm": 0.10122521966695786,
"learning_rate": 9.870897039249911e-05,
"loss": 0.8496,
"step": 450
},
{
"epoch": 0.5603448275862069,
"grad_norm": 0.09907156229019165,
"learning_rate": 9.655783883772545e-05,
"loss": 0.8678,
"step": 455
},
{
"epoch": 0.5665024630541872,
"grad_norm": 0.10225577652454376,
"learning_rate": 9.440830098993969e-05,
"loss": 0.8295,
"step": 460
},
{
"epoch": 0.5726600985221675,
"grad_norm": 0.09626160562038422,
"learning_rate": 9.22613520766537e-05,
"loss": 0.8396,
"step": 465
},
{
"epoch": 0.5788177339901478,
"grad_norm": 0.10784432291984558,
"learning_rate": 9.011798612671286e-05,
"loss": 0.8471,
"step": 470
},
{
"epoch": 0.5849753694581281,
"grad_norm": 0.10687639564275742,
"learning_rate": 8.797919551006475e-05,
"loss": 0.8497,
"step": 475
},
{
"epoch": 0.5911330049261084,
"grad_norm": 0.09171903878450394,
"learning_rate": 8.58459704782957e-05,
"loss": 0.8569,
"step": 480
},
{
"epoch": 0.5972906403940886,
"grad_norm": 0.09949865937232971,
"learning_rate": 8.371929870614833e-05,
"loss": 0.8751,
"step": 485
},
{
"epoch": 0.603448275862069,
"grad_norm": 0.10091466456651688,
"learning_rate": 8.160016483423199e-05,
"loss": 0.827,
"step": 490
},
{
"epoch": 0.6096059113300493,
"grad_norm": 0.09927868098020554,
"learning_rate": 7.948955001313811e-05,
"loss": 0.837,
"step": 495
},
{
"epoch": 0.6157635467980296,
"grad_norm": 0.09563671797513962,
"learning_rate": 7.738843144917119e-05,
"loss": 0.846,
"step": 500
},
{
"epoch": 0.6219211822660099,
"grad_norm": 0.09975801408290863,
"learning_rate": 7.529778195190645e-05,
"loss": 0.8362,
"step": 505
},
{
"epoch": 0.6280788177339901,
"grad_norm": 0.10187681764364243,
"learning_rate": 7.321856948378259e-05,
"loss": 0.8295,
"step": 510
},
{
"epoch": 0.6342364532019704,
"grad_norm": 0.10099563747644424,
"learning_rate": 7.115175671193913e-05,
"loss": 0.8567,
"step": 515
},
{
"epoch": 0.6403940886699507,
"grad_norm": 0.0974687784910202,
"learning_rate": 6.909830056250527e-05,
"loss": 0.8356,
"step": 520
},
{
"epoch": 0.646551724137931,
"grad_norm": 0.11131696403026581,
"learning_rate": 6.7059151777547e-05,
"loss": 0.8212,
"step": 525
},
{
"epoch": 0.6527093596059114,
"grad_norm": 0.09260319918394089,
"learning_rate": 6.503525447487715e-05,
"loss": 0.8279,
"step": 530
},
{
"epoch": 0.6588669950738916,
"grad_norm": 0.09697587788105011,
"learning_rate": 6.30275457109327e-05,
"loss": 0.8031,
"step": 535
},
{
"epoch": 0.6650246305418719,
"grad_norm": 0.11103641986846924,
"learning_rate": 6.103695504692122e-05,
"loss": 0.8436,
"step": 540
},
{
"epoch": 0.6711822660098522,
"grad_norm": 0.1072748601436615,
"learning_rate": 5.906440411843787e-05,
"loss": 0.8248,
"step": 545
},
{
"epoch": 0.6773399014778325,
"grad_norm": 0.1020703986287117,
"learning_rate": 5.7110806208751655e-05,
"loss": 0.8498,
"step": 550
},
{
"epoch": 0.6834975369458128,
"grad_norm": 0.10344262421131134,
"learning_rate": 5.5177065825958966e-05,
"loss": 0.8355,
"step": 555
},
{
"epoch": 0.6896551724137931,
"grad_norm": 0.10204443335533142,
"learning_rate": 5.326407828419979e-05,
"loss": 0.8224,
"step": 560
},
{
"epoch": 0.6958128078817734,
"grad_norm": 0.10229265689849854,
"learning_rate": 5.137272928913097e-05,
"loss": 0.8366,
"step": 565
},
{
"epoch": 0.7019704433497537,
"grad_norm": 0.10783268511295319,
"learning_rate": 4.9503894527847964e-05,
"loss": 0.8345,
"step": 570
},
{
"epoch": 0.708128078817734,
"grad_norm": 0.09613071382045746,
"learning_rate": 4.7658439263445e-05,
"loss": 0.8786,
"step": 575
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.09664251655340195,
"learning_rate": 4.583721793440188e-05,
"loss": 0.8881,
"step": 580
},
{
"epoch": 0.7204433497536946,
"grad_norm": 0.09146658331155777,
"learning_rate": 4.4041073758982335e-05,
"loss": 0.8425,
"step": 585
},
{
"epoch": 0.7266009852216748,
"grad_norm": 0.10532376915216446,
"learning_rate": 4.227083834482728e-05,
"loss": 0.8319,
"step": 590
},
{
"epoch": 0.7327586206896551,
"grad_norm": 0.09909343719482422,
"learning_rate": 4.052733130392367e-05,
"loss": 0.8396,
"step": 595
},
{
"epoch": 0.7389162561576355,
"grad_norm": 0.10966886579990387,
"learning_rate": 3.881135987312757e-05,
"loss": 0.8404,
"step": 600
},
{
"epoch": 0.7450738916256158,
"grad_norm": 0.10393289476633072,
"learning_rate": 3.712371854041654e-05,
"loss": 0.8524,
"step": 605
},
{
"epoch": 0.7512315270935961,
"grad_norm": 0.09633342921733856,
"learning_rate": 3.546518867704499e-05,
"loss": 0.8542,
"step": 610
},
{
"epoch": 0.7573891625615764,
"grad_norm": 0.10098910331726074,
"learning_rate": 3.383653817577216e-05,
"loss": 0.8552,
"step": 615
},
{
"epoch": 0.7635467980295566,
"grad_norm": 0.10073598474264145,
"learning_rate": 3.223852109533112e-05,
"loss": 0.8423,
"step": 620
},
{
"epoch": 0.7697044334975369,
"grad_norm": 0.10078535974025726,
"learning_rate": 3.0671877311302244e-05,
"loss": 0.8402,
"step": 625
},
{
"epoch": 0.7758620689655172,
"grad_norm": 0.10436087101697922,
"learning_rate": 2.9137332173554043e-05,
"loss": 0.8111,
"step": 630
},
{
"epoch": 0.7820197044334976,
"grad_norm": 0.09869997948408127,
"learning_rate": 2.763559617040876e-05,
"loss": 0.8407,
"step": 635
},
{
"epoch": 0.7881773399014779,
"grad_norm": 0.10569991171360016,
"learning_rate": 2.616736459968936e-05,
"loss": 0.8173,
"step": 640
},
{
"epoch": 0.7943349753694581,
"grad_norm": 0.09898445755243301,
"learning_rate": 2.473331724679917e-05,
"loss": 0.8236,
"step": 645
},
{
"epoch": 0.8004926108374384,
"grad_norm": 0.10241784900426865,
"learning_rate": 2.33341180699841e-05,
"loss": 0.8373,
"step": 650
},
{
"epoch": 0.8066502463054187,
"grad_norm": 0.10218991339206696,
"learning_rate": 2.1970414892922442e-05,
"loss": 0.8255,
"step": 655
},
{
"epoch": 0.812807881773399,
"grad_norm": 0.09686244279146194,
"learning_rate": 2.0642839104785272e-05,
"loss": 0.837,
"step": 660
},
{
"epoch": 0.8189655172413793,
"grad_norm": 0.09895747154951096,
"learning_rate": 1.9352005367905536e-05,
"loss": 0.8532,
"step": 665
},
{
"epoch": 0.8251231527093597,
"grad_norm": 0.10845907032489777,
"learning_rate": 1.8098511333192024e-05,
"loss": 0.8555,
"step": 670
},
{
"epoch": 0.8312807881773399,
"grad_norm": 0.10947497189044952,
"learning_rate": 1.6882937363419203e-05,
"loss": 0.8312,
"step": 675
},
{
"epoch": 0.8374384236453202,
"grad_norm": 0.10034690797328949,
"learning_rate": 1.570584626452173e-05,
"loss": 0.8377,
"step": 680
},
{
"epoch": 0.8435960591133005,
"grad_norm": 0.0978924036026001,
"learning_rate": 1.4567783025017301e-05,
"loss": 0.8337,
"step": 685
},
{
"epoch": 0.8497536945812808,
"grad_norm": 0.09215282648801804,
"learning_rate": 1.3469274563679402e-05,
"loss": 0.8057,
"step": 690
},
{
"epoch": 0.8559113300492611,
"grad_norm": 0.09425260126590729,
"learning_rate": 1.2410829485575704e-05,
"loss": 0.83,
"step": 695
},
{
"epoch": 0.8620689655172413,
"grad_norm": 0.09816047549247742,
"learning_rate": 1.1392937846586215e-05,
"loss": 0.8389,
"step": 700
},
{
"epoch": 0.8682266009852216,
"grad_norm": 0.09517823904752731,
"learning_rate": 1.0416070926509113e-05,
"loss": 0.8154,
"step": 705
},
{
"epoch": 0.874384236453202,
"grad_norm": 0.097825787961483,
"learning_rate": 9.48068101086026e-06,
"loss": 0.8492,
"step": 710
},
{
"epoch": 0.8805418719211823,
"grad_norm": 0.10528585314750671,
"learning_rate": 8.58720118146662e-06,
"loss": 0.8618,
"step": 715
},
{
"epoch": 0.8866995073891626,
"grad_norm": 0.09678342193365097,
"learning_rate": 7.736045115951251e-06,
"loss": 0.8349,
"step": 720
},
{
"epoch": 0.8928571428571429,
"grad_norm": 0.10073202848434448,
"learning_rate": 6.927606896202066e-06,
"loss": 0.823,
"step": 725
},
{
"epoch": 0.8990147783251231,
"grad_norm": 0.10746844857931137,
"learning_rate": 6.16226082591359e-06,
"loss": 0.8406,
"step": 730
},
{
"epoch": 0.9051724137931034,
"grad_norm": 0.09784899652004242,
"learning_rate": 5.440361257285742e-06,
"loss": 0.8522,
"step": 735
},
{
"epoch": 0.9113300492610837,
"grad_norm": 0.0988786518573761,
"learning_rate": 4.762242426960262e-06,
"loss": 0.838,
"step": 740
},
{
"epoch": 0.9174876847290641,
"grad_norm": 0.11292924731969833,
"learning_rate": 4.128218301270359e-06,
"loss": 0.8077,
"step": 745
},
{
"epoch": 0.9236453201970444,
"grad_norm": 0.10150548070669174,
"learning_rate": 3.5385824308756587e-06,
"loss": 0.8248,
"step": 750
},
{
"epoch": 0.9298029556650246,
"grad_norm": 0.09723605215549469,
"learning_rate": 2.9936078148492973e-06,
"loss": 0.8465,
"step": 755
},
{
"epoch": 0.9359605911330049,
"grad_norm": 0.0988769456744194,
"learning_rate": 2.493546774280531e-06,
"loss": 0.8601,
"step": 760
},
{
"epoch": 0.9421182266009852,
"grad_norm": 0.10142029821872711,
"learning_rate": 2.0386308354509942e-06,
"loss": 0.8635,
"step": 765
},
{
"epoch": 0.9482758620689655,
"grad_norm": 0.10347957164049149,
"learning_rate": 1.6290706226390285e-06,
"loss": 0.8088,
"step": 770
},
{
"epoch": 0.9544334975369458,
"grad_norm": 0.0945996567606926,
"learning_rate": 1.2650557606013635e-06,
"loss": 0.8074,
"step": 775
},
{
"epoch": 0.9605911330049262,
"grad_norm": 0.09384027868509293,
"learning_rate": 9.46754786777726e-07,
"loss": 0.8235,
"step": 780
},
{
"epoch": 0.9667487684729064,
"grad_norm": 0.10256475955247879,
"learning_rate": 6.74315073258569e-07,
"loss": 0.8613,
"step": 785
},
{
"epoch": 0.9729064039408867,
"grad_norm": 0.09143529087305069,
"learning_rate": 4.4786275855247527e-07,
"loss": 0.8044,
"step": 790
},
{
"epoch": 0.979064039408867,
"grad_norm": 0.10207488387823105,
"learning_rate": 2.675026891844512e-07,
"loss": 0.8265,
"step": 795
},
{
"epoch": 0.9852216748768473,
"grad_norm": 0.100164495408535,
"learning_rate": 1.333183711524133e-07,
"loss": 0.8307,
"step": 800
},
{
"epoch": 0.9913793103448276,
"grad_norm": 0.10022486746311188,
"learning_rate": 4.5371931264270864e-08,
"loss": 0.8189,
"step": 805
},
{
"epoch": 0.9975369458128078,
"grad_norm": 0.10022631287574768,
"learning_rate": 3.7040883734462683e-09,
"loss": 0.8204,
"step": 810
},
{
"epoch": 1.0,
"eval_loss": 1.2506881952285767,
"eval_runtime": 107.8412,
"eval_samples_per_second": 10.71,
"eval_steps_per_second": 0.677,
"step": 812
},
{
"epoch": 1.0,
"step": 812,
"total_flos": 2.1301458550160097e+18,
"train_loss": 0.26981097944264343,
"train_runtime": 10382.4605,
"train_samples_per_second": 10.01,
"train_steps_per_second": 0.078
}
],
"logging_steps": 5,
"max_steps": 812,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.1301458550160097e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}