llama10pGrad_2 / trainer_state.json
terry69's picture
Model save
3e5c819 verified
raw
history blame
29.6 kB
{
"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": 0.2949771583080292,
"learning_rate": 2.4390243902439027e-06,
"loss": 0.9838,
"step": 1
},
{
"epoch": 0.006157635467980296,
"grad_norm": 0.3101727366447449,
"learning_rate": 1.2195121951219513e-05,
"loss": 0.9644,
"step": 5
},
{
"epoch": 0.012315270935960592,
"grad_norm": 0.3715027868747711,
"learning_rate": 2.4390243902439026e-05,
"loss": 0.9825,
"step": 10
},
{
"epoch": 0.01847290640394089,
"grad_norm": 0.11249574273824692,
"learning_rate": 3.6585365853658535e-05,
"loss": 0.9393,
"step": 15
},
{
"epoch": 0.024630541871921183,
"grad_norm": 0.08815101534128189,
"learning_rate": 4.878048780487805e-05,
"loss": 0.9236,
"step": 20
},
{
"epoch": 0.03078817733990148,
"grad_norm": 0.10426054894924164,
"learning_rate": 6.097560975609756e-05,
"loss": 0.9237,
"step": 25
},
{
"epoch": 0.03694581280788178,
"grad_norm": 0.1105574294924736,
"learning_rate": 7.317073170731707e-05,
"loss": 0.9153,
"step": 30
},
{
"epoch": 0.04310344827586207,
"grad_norm": 0.09308202564716339,
"learning_rate": 8.53658536585366e-05,
"loss": 0.9281,
"step": 35
},
{
"epoch": 0.04926108374384237,
"grad_norm": 0.09463588148355484,
"learning_rate": 9.75609756097561e-05,
"loss": 0.9157,
"step": 40
},
{
"epoch": 0.05541871921182266,
"grad_norm": 0.11583919823169708,
"learning_rate": 0.00010975609756097563,
"loss": 0.8853,
"step": 45
},
{
"epoch": 0.06157635467980296,
"grad_norm": 0.09693233668804169,
"learning_rate": 0.00012195121951219512,
"loss": 0.8707,
"step": 50
},
{
"epoch": 0.06773399014778325,
"grad_norm": 0.0934528186917305,
"learning_rate": 0.00013414634146341464,
"loss": 0.8749,
"step": 55
},
{
"epoch": 0.07389162561576355,
"grad_norm": 0.10069940984249115,
"learning_rate": 0.00014634146341463414,
"loss": 0.8685,
"step": 60
},
{
"epoch": 0.08004926108374384,
"grad_norm": 0.09800374507904053,
"learning_rate": 0.00015853658536585366,
"loss": 0.8713,
"step": 65
},
{
"epoch": 0.08620689655172414,
"grad_norm": 0.12216204404830933,
"learning_rate": 0.0001707317073170732,
"loss": 0.8685,
"step": 70
},
{
"epoch": 0.09236453201970443,
"grad_norm": 0.09282781183719635,
"learning_rate": 0.0001829268292682927,
"loss": 0.8689,
"step": 75
},
{
"epoch": 0.09852216748768473,
"grad_norm": 0.09639699012041092,
"learning_rate": 0.0001951219512195122,
"loss": 0.8815,
"step": 80
},
{
"epoch": 0.10467980295566502,
"grad_norm": 0.0974295362830162,
"learning_rate": 0.0001999916658654738,
"loss": 0.8761,
"step": 85
},
{
"epoch": 0.11083743842364532,
"grad_norm": 0.08732698857784271,
"learning_rate": 0.0001999407400739705,
"loss": 0.8938,
"step": 90
},
{
"epoch": 0.11699507389162561,
"grad_norm": 0.09193898737430573,
"learning_rate": 0.00019984354211555644,
"loss": 0.851,
"step": 95
},
{
"epoch": 0.12315270935960591,
"grad_norm": 0.09586363285779953,
"learning_rate": 0.00019970011699250152,
"loss": 0.9015,
"step": 100
},
{
"epoch": 0.12931034482758622,
"grad_norm": 0.10461977124214172,
"learning_rate": 0.00019951053111006976,
"loss": 0.8593,
"step": 105
},
{
"epoch": 0.1354679802955665,
"grad_norm": 0.10003778338432312,
"learning_rate": 0.00019927487224577402,
"loss": 0.8596,
"step": 110
},
{
"epoch": 0.1416256157635468,
"grad_norm": 0.08891289681196213,
"learning_rate": 0.0001989932495087353,
"loss": 0.8813,
"step": 115
},
{
"epoch": 0.1477832512315271,
"grad_norm": 0.09503619372844696,
"learning_rate": 0.0001986657932891657,
"loss": 0.8774,
"step": 120
},
{
"epoch": 0.1539408866995074,
"grad_norm": 0.08597695827484131,
"learning_rate": 0.0001982926551979982,
"loss": 0.85,
"step": 125
},
{
"epoch": 0.16009852216748768,
"grad_norm": 0.0924694836139679,
"learning_rate": 0.00019787400799669154,
"loss": 0.8549,
"step": 130
},
{
"epoch": 0.16625615763546797,
"grad_norm": 0.10183464735746384,
"learning_rate": 0.00019741004551724207,
"loss": 0.8501,
"step": 135
},
{
"epoch": 0.1724137931034483,
"grad_norm": 0.11476742476224899,
"learning_rate": 0.00019690098257244064,
"loss": 0.8757,
"step": 140
},
{
"epoch": 0.17857142857142858,
"grad_norm": 0.10026735812425613,
"learning_rate": 0.00019634705485641488,
"loss": 0.8547,
"step": 145
},
{
"epoch": 0.18472906403940886,
"grad_norm": 0.0951361283659935,
"learning_rate": 0.00019574851883550395,
"loss": 0.859,
"step": 150
},
{
"epoch": 0.19088669950738915,
"grad_norm": 0.09267546981573105,
"learning_rate": 0.00019510565162951537,
"loss": 0.8635,
"step": 155
},
{
"epoch": 0.19704433497536947,
"grad_norm": 0.10676441341638565,
"learning_rate": 0.00019441875088341997,
"loss": 0.8707,
"step": 160
},
{
"epoch": 0.20320197044334976,
"grad_norm": 0.08962992578744888,
"learning_rate": 0.00019368813462954316,
"loss": 0.8341,
"step": 165
},
{
"epoch": 0.20935960591133004,
"grad_norm": 0.10068422555923462,
"learning_rate": 0.00019291414114031743,
"loss": 0.8063,
"step": 170
},
{
"epoch": 0.21551724137931033,
"grad_norm": 0.09436162561178207,
"learning_rate": 0.00019209712877166349,
"loss": 0.8477,
"step": 175
},
{
"epoch": 0.22167487684729065,
"grad_norm": 0.0981898158788681,
"learning_rate": 0.00019123747579707275,
"loss": 0.8634,
"step": 180
},
{
"epoch": 0.22783251231527094,
"grad_norm": 0.09050612151622772,
"learning_rate": 0.00019033558023246844,
"loss": 0.8693,
"step": 185
},
{
"epoch": 0.23399014778325122,
"grad_norm": 0.09567181766033173,
"learning_rate": 0.0001893918596519257,
"loss": 0.8721,
"step": 190
},
{
"epoch": 0.24014778325123154,
"grad_norm": 0.09379356354475021,
"learning_rate": 0.00018840675099433636,
"loss": 0.8572,
"step": 195
},
{
"epoch": 0.24630541871921183,
"grad_norm": 0.09768428653478622,
"learning_rate": 0.00018738071036110808,
"loss": 0.8675,
"step": 200
},
{
"epoch": 0.2524630541871921,
"grad_norm": 0.0965338945388794,
"learning_rate": 0.00018631421280499116,
"loss": 0.869,
"step": 205
},
{
"epoch": 0.25862068965517243,
"grad_norm": 0.08635499328374863,
"learning_rate": 0.00018520775211013093,
"loss": 0.842,
"step": 210
},
{
"epoch": 0.2647783251231527,
"grad_norm": 0.08754138648509979,
"learning_rate": 0.00018406184056344782,
"loss": 0.8305,
"step": 215
},
{
"epoch": 0.270935960591133,
"grad_norm": 0.09839050471782684,
"learning_rate": 0.00018287700871745036,
"loss": 0.835,
"step": 220
},
{
"epoch": 0.2770935960591133,
"grad_norm": 0.11136944591999054,
"learning_rate": 0.0001816538051445916,
"loss": 0.8588,
"step": 225
},
{
"epoch": 0.2832512315270936,
"grad_norm": 0.0912737250328064,
"learning_rate": 0.00018039279618328212,
"loss": 0.8624,
"step": 230
},
{
"epoch": 0.2894088669950739,
"grad_norm": 0.07793363183736801,
"learning_rate": 0.00017909456567567772,
"loss": 0.8345,
"step": 235
},
{
"epoch": 0.2955665024630542,
"grad_norm": 0.10047736018896103,
"learning_rate": 0.0001777597146973627,
"loss": 0.8585,
"step": 240
},
{
"epoch": 0.3017241379310345,
"grad_norm": 0.08737127482891083,
"learning_rate": 0.00017638886127905427,
"loss": 0.8397,
"step": 245
},
{
"epoch": 0.3078817733990148,
"grad_norm": 0.1030949130654335,
"learning_rate": 0.00017498264012045687,
"loss": 0.8794,
"step": 250
},
{
"epoch": 0.31403940886699505,
"grad_norm": 0.08828911185264587,
"learning_rate": 0.00017354170229639856,
"loss": 0.854,
"step": 255
},
{
"epoch": 0.32019704433497537,
"grad_norm": 0.0845285952091217,
"learning_rate": 0.00017206671495538612,
"loss": 0.8413,
"step": 260
},
{
"epoch": 0.3263546798029557,
"grad_norm": 0.09490133821964264,
"learning_rate": 0.0001705583610107178,
"loss": 0.8278,
"step": 265
},
{
"epoch": 0.33251231527093594,
"grad_norm": 0.0908144861459732,
"learning_rate": 0.0001690173388242972,
"loss": 0.8589,
"step": 270
},
{
"epoch": 0.33866995073891626,
"grad_norm": 0.09003310650587082,
"learning_rate": 0.00016744436188329456,
"loss": 0.8572,
"step": 275
},
{
"epoch": 0.3448275862068966,
"grad_norm": 0.09844415634870529,
"learning_rate": 0.0001658401584698049,
"loss": 0.8628,
"step": 280
},
{
"epoch": 0.35098522167487683,
"grad_norm": 0.09799636900424957,
"learning_rate": 0.00016420547132365635,
"loss": 0.86,
"step": 285
},
{
"epoch": 0.35714285714285715,
"grad_norm": 0.0892237052321434,
"learning_rate": 0.00016254105729852464,
"loss": 0.8818,
"step": 290
},
{
"epoch": 0.3633004926108374,
"grad_norm": 0.09125364571809769,
"learning_rate": 0.00016084768701151263,
"loss": 0.8788,
"step": 295
},
{
"epoch": 0.3694581280788177,
"grad_norm": 0.09678944945335388,
"learning_rate": 0.00015912614448635782,
"loss": 0.8846,
"step": 300
},
{
"epoch": 0.37561576354679804,
"grad_norm": 0.09397515654563904,
"learning_rate": 0.00015737722679043248,
"loss": 0.8566,
"step": 305
},
{
"epoch": 0.3817733990147783,
"grad_norm": 0.08986654132604599,
"learning_rate": 0.00015560174366570446,
"loss": 0.8321,
"step": 310
},
{
"epoch": 0.3879310344827586,
"grad_norm": 0.09454771876335144,
"learning_rate": 0.00015380051715382996,
"loss": 0.8826,
"step": 315
},
{
"epoch": 0.39408866995073893,
"grad_norm": 0.092396080493927,
"learning_rate": 0.0001519743812155516,
"loss": 0.8526,
"step": 320
},
{
"epoch": 0.4002463054187192,
"grad_norm": 0.10106166452169418,
"learning_rate": 0.00015012418134457755,
"loss": 0.847,
"step": 325
},
{
"epoch": 0.4064039408866995,
"grad_norm": 0.091457299888134,
"learning_rate": 0.00014825077417612186,
"loss": 0.8469,
"step": 330
},
{
"epoch": 0.4125615763546798,
"grad_norm": 0.09755238145589828,
"learning_rate": 0.0001463550270902851,
"loss": 0.8296,
"step": 335
},
{
"epoch": 0.4187192118226601,
"grad_norm": 0.09282223135232925,
"learning_rate": 0.00014443781781046136,
"loss": 0.8452,
"step": 340
},
{
"epoch": 0.4248768472906404,
"grad_norm": 0.09217504411935806,
"learning_rate": 0.0001425000339969554,
"loss": 0.8357,
"step": 345
},
{
"epoch": 0.43103448275862066,
"grad_norm": 0.0990719348192215,
"learning_rate": 0.00014054257283599973,
"loss": 0.8402,
"step": 350
},
{
"epoch": 0.437192118226601,
"grad_norm": 0.09021298587322235,
"learning_rate": 0.0001385663406243607,
"loss": 0.8454,
"step": 355
},
{
"epoch": 0.4433497536945813,
"grad_norm": 0.09311360120773315,
"learning_rate": 0.00013657225234972695,
"loss": 0.8449,
"step": 360
},
{
"epoch": 0.44950738916256155,
"grad_norm": 0.09712479263544083,
"learning_rate": 0.00013456123126707334,
"loss": 0.8718,
"step": 365
},
{
"epoch": 0.45566502463054187,
"grad_norm": 0.098002128303051,
"learning_rate": 0.00013253420847119803,
"loss": 0.8467,
"step": 370
},
{
"epoch": 0.4618226600985222,
"grad_norm": 0.08402260392904282,
"learning_rate": 0.0001304921224656289,
"loss": 0.8279,
"step": 375
},
{
"epoch": 0.46798029556650245,
"grad_norm": 0.09465406835079193,
"learning_rate": 0.0001284359187281004,
"loss": 0.8749,
"step": 380
},
{
"epoch": 0.47413793103448276,
"grad_norm": 0.08619461953639984,
"learning_rate": 0.00012636654927280073,
"loss": 0.8495,
"step": 385
},
{
"epoch": 0.4802955665024631,
"grad_norm": 0.09889654070138931,
"learning_rate": 0.0001242849722095936,
"loss": 0.8447,
"step": 390
},
{
"epoch": 0.48645320197044334,
"grad_norm": 0.0903097614645958,
"learning_rate": 0.00012219215130041656,
"loss": 0.8186,
"step": 395
},
{
"epoch": 0.49261083743842365,
"grad_norm": 0.09543944150209427,
"learning_rate": 0.00012008905551306356,
"loss": 0.8497,
"step": 400
},
{
"epoch": 0.4987684729064039,
"grad_norm": 0.09465156495571136,
"learning_rate": 0.00011797665857255621,
"loss": 0.8496,
"step": 405
},
{
"epoch": 0.5049261083743842,
"grad_norm": 0.09152977913618088,
"learning_rate": 0.00011585593851031347,
"loss": 0.8406,
"step": 410
},
{
"epoch": 0.5110837438423645,
"grad_norm": 0.09556221961975098,
"learning_rate": 0.00011372787721132648,
"loss": 0.851,
"step": 415
},
{
"epoch": 0.5172413793103449,
"grad_norm": 0.09278736263513565,
"learning_rate": 0.00011159345995955006,
"loss": 0.8636,
"step": 420
},
{
"epoch": 0.5233990147783252,
"grad_norm": 0.09471924602985382,
"learning_rate": 0.00010945367498171993,
"loss": 0.8628,
"step": 425
},
{
"epoch": 0.5295566502463054,
"grad_norm": 0.09358783066272736,
"learning_rate": 0.00010730951298980776,
"loss": 0.864,
"step": 430
},
{
"epoch": 0.5357142857142857,
"grad_norm": 0.10094843059778214,
"learning_rate": 0.00010516196672232539,
"loss": 0.8698,
"step": 435
},
{
"epoch": 0.541871921182266,
"grad_norm": 0.09740354865789413,
"learning_rate": 0.00010301203048469083,
"loss": 0.8419,
"step": 440
},
{
"epoch": 0.5480295566502463,
"grad_norm": 0.09911592304706573,
"learning_rate": 0.00010086069968886885,
"loss": 0.8524,
"step": 445
},
{
"epoch": 0.5541871921182266,
"grad_norm": 0.09378519654273987,
"learning_rate": 9.870897039249911e-05,
"loss": 0.8673,
"step": 450
},
{
"epoch": 0.5603448275862069,
"grad_norm": 0.0991242304444313,
"learning_rate": 9.655783883772545e-05,
"loss": 0.8624,
"step": 455
},
{
"epoch": 0.5665024630541872,
"grad_norm": 0.09386149048805237,
"learning_rate": 9.440830098993969e-05,
"loss": 0.8161,
"step": 460
},
{
"epoch": 0.5726600985221675,
"grad_norm": 0.09219907224178314,
"learning_rate": 9.22613520766537e-05,
"loss": 0.8519,
"step": 465
},
{
"epoch": 0.5788177339901478,
"grad_norm": 0.09010721743106842,
"learning_rate": 9.011798612671286e-05,
"loss": 0.8489,
"step": 470
},
{
"epoch": 0.5849753694581281,
"grad_norm": 0.10001237690448761,
"learning_rate": 8.797919551006475e-05,
"loss": 0.8526,
"step": 475
},
{
"epoch": 0.5911330049261084,
"grad_norm": 0.09620565176010132,
"learning_rate": 8.58459704782957e-05,
"loss": 0.85,
"step": 480
},
{
"epoch": 0.5972906403940886,
"grad_norm": 0.0897950753569603,
"learning_rate": 8.371929870614833e-05,
"loss": 0.8458,
"step": 485
},
{
"epoch": 0.603448275862069,
"grad_norm": 0.08846917748451233,
"learning_rate": 8.160016483423199e-05,
"loss": 0.8512,
"step": 490
},
{
"epoch": 0.6096059113300493,
"grad_norm": 0.09186448156833649,
"learning_rate": 7.948955001313811e-05,
"loss": 0.8699,
"step": 495
},
{
"epoch": 0.6157635467980296,
"grad_norm": 0.10069604963064194,
"learning_rate": 7.738843144917119e-05,
"loss": 0.8398,
"step": 500
},
{
"epoch": 0.6219211822660099,
"grad_norm": 0.09906591475009918,
"learning_rate": 7.529778195190645e-05,
"loss": 0.8378,
"step": 505
},
{
"epoch": 0.6280788177339901,
"grad_norm": 0.09918715059757233,
"learning_rate": 7.321856948378259e-05,
"loss": 0.8584,
"step": 510
},
{
"epoch": 0.6342364532019704,
"grad_norm": 0.09439591318368912,
"learning_rate": 7.115175671193913e-05,
"loss": 0.8519,
"step": 515
},
{
"epoch": 0.6403940886699507,
"grad_norm": 0.0965607687830925,
"learning_rate": 6.909830056250527e-05,
"loss": 0.8607,
"step": 520
},
{
"epoch": 0.646551724137931,
"grad_norm": 0.09937562048435211,
"learning_rate": 6.7059151777547e-05,
"loss": 0.8547,
"step": 525
},
{
"epoch": 0.6527093596059114,
"grad_norm": 0.10041774064302444,
"learning_rate": 6.503525447487715e-05,
"loss": 0.8584,
"step": 530
},
{
"epoch": 0.6588669950738916,
"grad_norm": 0.09252887219190598,
"learning_rate": 6.30275457109327e-05,
"loss": 0.8824,
"step": 535
},
{
"epoch": 0.6650246305418719,
"grad_norm": 0.09451112896203995,
"learning_rate": 6.103695504692122e-05,
"loss": 0.8371,
"step": 540
},
{
"epoch": 0.6711822660098522,
"grad_norm": 0.10130809247493744,
"learning_rate": 5.906440411843787e-05,
"loss": 0.8807,
"step": 545
},
{
"epoch": 0.6773399014778325,
"grad_norm": 0.09514950215816498,
"learning_rate": 5.7110806208751655e-05,
"loss": 0.8571,
"step": 550
},
{
"epoch": 0.6834975369458128,
"grad_norm": 0.0906277671456337,
"learning_rate": 5.5177065825958966e-05,
"loss": 0.8376,
"step": 555
},
{
"epoch": 0.6896551724137931,
"grad_norm": 0.08796288818120956,
"learning_rate": 5.326407828419979e-05,
"loss": 0.8283,
"step": 560
},
{
"epoch": 0.6958128078817734,
"grad_norm": 0.09175130724906921,
"learning_rate": 5.137272928913097e-05,
"loss": 0.8502,
"step": 565
},
{
"epoch": 0.7019704433497537,
"grad_norm": 0.09584875404834747,
"learning_rate": 4.9503894527847964e-05,
"loss": 0.8398,
"step": 570
},
{
"epoch": 0.708128078817734,
"grad_norm": 0.09284964203834534,
"learning_rate": 4.7658439263445e-05,
"loss": 0.8328,
"step": 575
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.09421636164188385,
"learning_rate": 4.583721793440188e-05,
"loss": 0.8395,
"step": 580
},
{
"epoch": 0.7204433497536946,
"grad_norm": 0.1052021011710167,
"learning_rate": 4.4041073758982335e-05,
"loss": 0.8579,
"step": 585
},
{
"epoch": 0.7266009852216748,
"grad_norm": 0.09751743078231812,
"learning_rate": 4.227083834482728e-05,
"loss": 0.8348,
"step": 590
},
{
"epoch": 0.7327586206896551,
"grad_norm": 0.09555874764919281,
"learning_rate": 4.052733130392367e-05,
"loss": 0.8386,
"step": 595
},
{
"epoch": 0.7389162561576355,
"grad_norm": 0.09556646645069122,
"learning_rate": 3.881135987312757e-05,
"loss": 0.8858,
"step": 600
},
{
"epoch": 0.7450738916256158,
"grad_norm": 0.0967402383685112,
"learning_rate": 3.712371854041654e-05,
"loss": 0.8306,
"step": 605
},
{
"epoch": 0.7512315270935961,
"grad_norm": 0.1028241440653801,
"learning_rate": 3.546518867704499e-05,
"loss": 0.8657,
"step": 610
},
{
"epoch": 0.7573891625615764,
"grad_norm": 0.09105245769023895,
"learning_rate": 3.383653817577216e-05,
"loss": 0.8398,
"step": 615
},
{
"epoch": 0.7635467980295566,
"grad_norm": 0.09858682006597519,
"learning_rate": 3.223852109533112e-05,
"loss": 0.8218,
"step": 620
},
{
"epoch": 0.7697044334975369,
"grad_norm": 0.09542707353830338,
"learning_rate": 3.0671877311302244e-05,
"loss": 0.8243,
"step": 625
},
{
"epoch": 0.7758620689655172,
"grad_norm": 0.09767568111419678,
"learning_rate": 2.9137332173554043e-05,
"loss": 0.8449,
"step": 630
},
{
"epoch": 0.7820197044334976,
"grad_norm": 0.10336579382419586,
"learning_rate": 2.763559617040876e-05,
"loss": 0.8441,
"step": 635
},
{
"epoch": 0.7881773399014779,
"grad_norm": 0.09993448853492737,
"learning_rate": 2.616736459968936e-05,
"loss": 0.8388,
"step": 640
},
{
"epoch": 0.7943349753694581,
"grad_norm": 0.09298530966043472,
"learning_rate": 2.473331724679917e-05,
"loss": 0.8385,
"step": 645
},
{
"epoch": 0.8004926108374384,
"grad_norm": 0.09422852843999863,
"learning_rate": 2.33341180699841e-05,
"loss": 0.8178,
"step": 650
},
{
"epoch": 0.8066502463054187,
"grad_norm": 0.09662608057260513,
"learning_rate": 2.1970414892922442e-05,
"loss": 0.8483,
"step": 655
},
{
"epoch": 0.812807881773399,
"grad_norm": 0.09834180027246475,
"learning_rate": 2.0642839104785272e-05,
"loss": 0.8452,
"step": 660
},
{
"epoch": 0.8189655172413793,
"grad_norm": 0.12449537217617035,
"learning_rate": 1.9352005367905536e-05,
"loss": 0.8379,
"step": 665
},
{
"epoch": 0.8251231527093597,
"grad_norm": 0.10711503773927689,
"learning_rate": 1.8098511333192024e-05,
"loss": 0.8604,
"step": 670
},
{
"epoch": 0.8312807881773399,
"grad_norm": 0.09627261012792587,
"learning_rate": 1.6882937363419203e-05,
"loss": 0.8234,
"step": 675
},
{
"epoch": 0.8374384236453202,
"grad_norm": 0.10317688435316086,
"learning_rate": 1.570584626452173e-05,
"loss": 0.8325,
"step": 680
},
{
"epoch": 0.8435960591133005,
"grad_norm": 0.10015459358692169,
"learning_rate": 1.4567783025017301e-05,
"loss": 0.8418,
"step": 685
},
{
"epoch": 0.8497536945812808,
"grad_norm": 0.09650367498397827,
"learning_rate": 1.3469274563679402e-05,
"loss": 0.8248,
"step": 690
},
{
"epoch": 0.8559113300492611,
"grad_norm": 0.10634295642375946,
"learning_rate": 1.2410829485575704e-05,
"loss": 0.8538,
"step": 695
},
{
"epoch": 0.8620689655172413,
"grad_norm": 0.09615869075059891,
"learning_rate": 1.1392937846586215e-05,
"loss": 0.8669,
"step": 700
},
{
"epoch": 0.8682266009852216,
"grad_norm": 0.09273919463157654,
"learning_rate": 1.0416070926509113e-05,
"loss": 0.8374,
"step": 705
},
{
"epoch": 0.874384236453202,
"grad_norm": 0.10093870013952255,
"learning_rate": 9.48068101086026e-06,
"loss": 0.8638,
"step": 710
},
{
"epoch": 0.8805418719211823,
"grad_norm": 0.09216069430112839,
"learning_rate": 8.58720118146662e-06,
"loss": 0.8302,
"step": 715
},
{
"epoch": 0.8866995073891626,
"grad_norm": 0.09972187131643295,
"learning_rate": 7.736045115951251e-06,
"loss": 0.8679,
"step": 720
},
{
"epoch": 0.8928571428571429,
"grad_norm": 0.09708079695701599,
"learning_rate": 6.927606896202066e-06,
"loss": 0.8348,
"step": 725
},
{
"epoch": 0.8990147783251231,
"grad_norm": 0.09960056841373444,
"learning_rate": 6.16226082591359e-06,
"loss": 0.8403,
"step": 730
},
{
"epoch": 0.9051724137931034,
"grad_norm": 0.09734474867582321,
"learning_rate": 5.440361257285742e-06,
"loss": 0.8567,
"step": 735
},
{
"epoch": 0.9113300492610837,
"grad_norm": 0.0940781757235527,
"learning_rate": 4.762242426960262e-06,
"loss": 0.8456,
"step": 740
},
{
"epoch": 0.9174876847290641,
"grad_norm": 0.09184621274471283,
"learning_rate": 4.128218301270359e-06,
"loss": 0.8516,
"step": 745
},
{
"epoch": 0.9236453201970444,
"grad_norm": 0.095575712621212,
"learning_rate": 3.5385824308756587e-06,
"loss": 0.8433,
"step": 750
},
{
"epoch": 0.9298029556650246,
"grad_norm": 0.09812497347593307,
"learning_rate": 2.9936078148492973e-06,
"loss": 0.865,
"step": 755
},
{
"epoch": 0.9359605911330049,
"grad_norm": 0.09702542424201965,
"learning_rate": 2.493546774280531e-06,
"loss": 0.8249,
"step": 760
},
{
"epoch": 0.9421182266009852,
"grad_norm": 0.09994158893823624,
"learning_rate": 2.0386308354509942e-06,
"loss": 0.8355,
"step": 765
},
{
"epoch": 0.9482758620689655,
"grad_norm": 0.09425787627696991,
"learning_rate": 1.6290706226390285e-06,
"loss": 0.8094,
"step": 770
},
{
"epoch": 0.9544334975369458,
"grad_norm": 0.10560785979032516,
"learning_rate": 1.2650557606013635e-06,
"loss": 0.8512,
"step": 775
},
{
"epoch": 0.9605911330049262,
"grad_norm": 0.09790593385696411,
"learning_rate": 9.46754786777726e-07,
"loss": 0.8378,
"step": 780
},
{
"epoch": 0.9667487684729064,
"grad_norm": 0.09701854735612869,
"learning_rate": 6.74315073258569e-07,
"loss": 0.8201,
"step": 785
},
{
"epoch": 0.9729064039408867,
"grad_norm": 0.0912141278386116,
"learning_rate": 4.4786275855247527e-07,
"loss": 0.8304,
"step": 790
},
{
"epoch": 0.979064039408867,
"grad_norm": 0.10074811428785324,
"learning_rate": 2.675026891844512e-07,
"loss": 0.8649,
"step": 795
},
{
"epoch": 0.9852216748768473,
"grad_norm": 0.09760763496160507,
"learning_rate": 1.333183711524133e-07,
"loss": 0.8527,
"step": 800
},
{
"epoch": 0.9913793103448276,
"grad_norm": 0.10889925807714462,
"learning_rate": 4.5371931264270864e-08,
"loss": 0.8688,
"step": 805
},
{
"epoch": 0.9975369458128078,
"grad_norm": 0.0987965315580368,
"learning_rate": 3.7040883734462683e-09,
"loss": 0.842,
"step": 810
},
{
"epoch": 1.0,
"eval_loss": 1.241860270500183,
"eval_runtime": 133.9183,
"eval_samples_per_second": 8.625,
"eval_steps_per_second": 0.545,
"step": 812
},
{
"epoch": 1.0,
"step": 812,
"total_flos": 2.0167297520684237e+18,
"train_loss": 0.8562019185479639,
"train_runtime": 32009.8427,
"train_samples_per_second": 3.247,
"train_steps_per_second": 0.025
}
],
"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": 2.0167297520684237e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}