llama5pGrad_2 / trainer_state.json
terry69's picture
Model save
6aaf098 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": 0.23959890007972717,
"learning_rate": 2.4390243902439027e-06,
"loss": 0.8682,
"step": 1
},
{
"epoch": 0.006157635467980296,
"grad_norm": 0.2623080015182495,
"learning_rate": 1.2195121951219513e-05,
"loss": 0.9479,
"step": 5
},
{
"epoch": 0.012315270935960592,
"grad_norm": 0.35404738783836365,
"learning_rate": 2.4390243902439026e-05,
"loss": 0.9736,
"step": 10
},
{
"epoch": 0.01847290640394089,
"grad_norm": 0.08481761813163757,
"learning_rate": 3.6585365853658535e-05,
"loss": 0.9256,
"step": 15
},
{
"epoch": 0.024630541871921183,
"grad_norm": 0.0834408849477768,
"learning_rate": 4.878048780487805e-05,
"loss": 0.9218,
"step": 20
},
{
"epoch": 0.03078817733990148,
"grad_norm": 0.08868379145860672,
"learning_rate": 6.097560975609756e-05,
"loss": 0.9058,
"step": 25
},
{
"epoch": 0.03694581280788178,
"grad_norm": 0.09458460658788681,
"learning_rate": 7.317073170731707e-05,
"loss": 0.9297,
"step": 30
},
{
"epoch": 0.04310344827586207,
"grad_norm": 0.09731251746416092,
"learning_rate": 8.53658536585366e-05,
"loss": 0.9118,
"step": 35
},
{
"epoch": 0.04926108374384237,
"grad_norm": 0.09796521812677383,
"learning_rate": 9.75609756097561e-05,
"loss": 0.9063,
"step": 40
},
{
"epoch": 0.05541871921182266,
"grad_norm": 0.10772078484296799,
"learning_rate": 0.00010975609756097563,
"loss": 0.8765,
"step": 45
},
{
"epoch": 0.06157635467980296,
"grad_norm": 0.09252353757619858,
"learning_rate": 0.00012195121951219512,
"loss": 0.8856,
"step": 50
},
{
"epoch": 0.06773399014778325,
"grad_norm": 0.09331782162189484,
"learning_rate": 0.00013414634146341464,
"loss": 0.8474,
"step": 55
},
{
"epoch": 0.07389162561576355,
"grad_norm": 0.0972302258014679,
"learning_rate": 0.00014634146341463414,
"loss": 0.9011,
"step": 60
},
{
"epoch": 0.08004926108374384,
"grad_norm": 0.10011622309684753,
"learning_rate": 0.00015853658536585366,
"loss": 0.8622,
"step": 65
},
{
"epoch": 0.08620689655172414,
"grad_norm": 0.09244757890701294,
"learning_rate": 0.0001707317073170732,
"loss": 0.8681,
"step": 70
},
{
"epoch": 0.09236453201970443,
"grad_norm": 0.08707920461893082,
"learning_rate": 0.0001829268292682927,
"loss": 0.8781,
"step": 75
},
{
"epoch": 0.09852216748768473,
"grad_norm": 0.09925995022058487,
"learning_rate": 0.0001951219512195122,
"loss": 0.8579,
"step": 80
},
{
"epoch": 0.10467980295566502,
"grad_norm": 0.10458535701036453,
"learning_rate": 0.0001999916658654738,
"loss": 0.8557,
"step": 85
},
{
"epoch": 0.11083743842364532,
"grad_norm": 0.09851501137018204,
"learning_rate": 0.0001999407400739705,
"loss": 0.8547,
"step": 90
},
{
"epoch": 0.11699507389162561,
"grad_norm": 0.10369230061769485,
"learning_rate": 0.00019984354211555644,
"loss": 0.8874,
"step": 95
},
{
"epoch": 0.12315270935960591,
"grad_norm": 0.1089601218700409,
"learning_rate": 0.00019970011699250152,
"loss": 0.8667,
"step": 100
},
{
"epoch": 0.12931034482758622,
"grad_norm": 0.11249925941228867,
"learning_rate": 0.00019951053111006976,
"loss": 0.8727,
"step": 105
},
{
"epoch": 0.1354679802955665,
"grad_norm": 0.10554239898920059,
"learning_rate": 0.00019927487224577402,
"loss": 0.8552,
"step": 110
},
{
"epoch": 0.1416256157635468,
"grad_norm": 0.10719837248325348,
"learning_rate": 0.0001989932495087353,
"loss": 0.8611,
"step": 115
},
{
"epoch": 0.1477832512315271,
"grad_norm": 0.11034558713436127,
"learning_rate": 0.0001986657932891657,
"loss": 0.859,
"step": 120
},
{
"epoch": 0.1539408866995074,
"grad_norm": 0.11908762902021408,
"learning_rate": 0.0001982926551979982,
"loss": 0.8769,
"step": 125
},
{
"epoch": 0.16009852216748768,
"grad_norm": 0.10843163728713989,
"learning_rate": 0.00019787400799669154,
"loss": 0.8572,
"step": 130
},
{
"epoch": 0.16625615763546797,
"grad_norm": 0.09607932716608047,
"learning_rate": 0.00019741004551724207,
"loss": 0.8544,
"step": 135
},
{
"epoch": 0.1724137931034483,
"grad_norm": 0.09270977973937988,
"learning_rate": 0.00019690098257244064,
"loss": 0.8713,
"step": 140
},
{
"epoch": 0.17857142857142858,
"grad_norm": 0.09110839664936066,
"learning_rate": 0.00019634705485641488,
"loss": 0.8562,
"step": 145
},
{
"epoch": 0.18472906403940886,
"grad_norm": 0.10726200044155121,
"learning_rate": 0.00019574851883550395,
"loss": 0.8793,
"step": 150
},
{
"epoch": 0.19088669950738915,
"grad_norm": 0.09080515801906586,
"learning_rate": 0.00019510565162951537,
"loss": 0.8593,
"step": 155
},
{
"epoch": 0.19704433497536947,
"grad_norm": 0.08680335432291031,
"learning_rate": 0.00019441875088341997,
"loss": 0.8495,
"step": 160
},
{
"epoch": 0.20320197044334976,
"grad_norm": 0.09110551327466965,
"learning_rate": 0.00019368813462954316,
"loss": 0.8555,
"step": 165
},
{
"epoch": 0.20935960591133004,
"grad_norm": 0.09650521725416183,
"learning_rate": 0.00019291414114031743,
"loss": 0.8319,
"step": 170
},
{
"epoch": 0.21551724137931033,
"grad_norm": 0.09564988315105438,
"learning_rate": 0.00019209712877166349,
"loss": 0.8827,
"step": 175
},
{
"epoch": 0.22167487684729065,
"grad_norm": 0.09996647387742996,
"learning_rate": 0.00019123747579707275,
"loss": 0.8575,
"step": 180
},
{
"epoch": 0.22783251231527094,
"grad_norm": 0.08969279378652573,
"learning_rate": 0.00019033558023246844,
"loss": 0.8581,
"step": 185
},
{
"epoch": 0.23399014778325122,
"grad_norm": 0.09902820736169815,
"learning_rate": 0.0001893918596519257,
"loss": 0.8952,
"step": 190
},
{
"epoch": 0.24014778325123154,
"grad_norm": 0.0955020859837532,
"learning_rate": 0.00018840675099433636,
"loss": 0.8442,
"step": 195
},
{
"epoch": 0.24630541871921183,
"grad_norm": 0.10569384694099426,
"learning_rate": 0.00018738071036110808,
"loss": 0.88,
"step": 200
},
{
"epoch": 0.2524630541871921,
"grad_norm": 0.09179041534662247,
"learning_rate": 0.00018631421280499116,
"loss": 0.851,
"step": 205
},
{
"epoch": 0.25862068965517243,
"grad_norm": 0.09090536832809448,
"learning_rate": 0.00018520775211013093,
"loss": 0.8773,
"step": 210
},
{
"epoch": 0.2647783251231527,
"grad_norm": 0.08043532073497772,
"learning_rate": 0.00018406184056344782,
"loss": 0.8889,
"step": 215
},
{
"epoch": 0.270935960591133,
"grad_norm": 0.09549892693758011,
"learning_rate": 0.00018287700871745036,
"loss": 0.8857,
"step": 220
},
{
"epoch": 0.2770935960591133,
"grad_norm": 0.0889943391084671,
"learning_rate": 0.0001816538051445916,
"loss": 0.8594,
"step": 225
},
{
"epoch": 0.2832512315270936,
"grad_norm": 0.08636672794818878,
"learning_rate": 0.00018039279618328212,
"loss": 0.895,
"step": 230
},
{
"epoch": 0.2894088669950739,
"grad_norm": 0.09121069312095642,
"learning_rate": 0.00017909456567567772,
"loss": 0.8516,
"step": 235
},
{
"epoch": 0.2955665024630542,
"grad_norm": 0.0952455922961235,
"learning_rate": 0.0001777597146973627,
"loss": 0.8445,
"step": 240
},
{
"epoch": 0.3017241379310345,
"grad_norm": 0.09121528267860413,
"learning_rate": 0.00017638886127905427,
"loss": 0.8505,
"step": 245
},
{
"epoch": 0.3078817733990148,
"grad_norm": 0.09336868673563004,
"learning_rate": 0.00017498264012045687,
"loss": 0.8569,
"step": 250
},
{
"epoch": 0.31403940886699505,
"grad_norm": 0.09783859550952911,
"learning_rate": 0.00017354170229639856,
"loss": 0.8445,
"step": 255
},
{
"epoch": 0.32019704433497537,
"grad_norm": 0.09338293969631195,
"learning_rate": 0.00017206671495538612,
"loss": 0.863,
"step": 260
},
{
"epoch": 0.3263546798029557,
"grad_norm": 0.09042429178953171,
"learning_rate": 0.0001705583610107178,
"loss": 0.8527,
"step": 265
},
{
"epoch": 0.33251231527093594,
"grad_norm": 0.09664267301559448,
"learning_rate": 0.0001690173388242972,
"loss": 0.8578,
"step": 270
},
{
"epoch": 0.33866995073891626,
"grad_norm": 0.08856074512004852,
"learning_rate": 0.00016744436188329456,
"loss": 0.8505,
"step": 275
},
{
"epoch": 0.3448275862068966,
"grad_norm": 0.10030202567577362,
"learning_rate": 0.0001658401584698049,
"loss": 0.8566,
"step": 280
},
{
"epoch": 0.35098522167487683,
"grad_norm": 0.08838096261024475,
"learning_rate": 0.00016420547132365635,
"loss": 0.8406,
"step": 285
},
{
"epoch": 0.35714285714285715,
"grad_norm": 0.09203306585550308,
"learning_rate": 0.00016254105729852464,
"loss": 0.8661,
"step": 290
},
{
"epoch": 0.3633004926108374,
"grad_norm": 0.09134566783905029,
"learning_rate": 0.00016084768701151263,
"loss": 0.8572,
"step": 295
},
{
"epoch": 0.3694581280788177,
"grad_norm": 0.08635319769382477,
"learning_rate": 0.00015912614448635782,
"loss": 0.8662,
"step": 300
},
{
"epoch": 0.37561576354679804,
"grad_norm": 0.09094405174255371,
"learning_rate": 0.00015737722679043248,
"loss": 0.8653,
"step": 305
},
{
"epoch": 0.3817733990147783,
"grad_norm": 0.09235331416130066,
"learning_rate": 0.00015560174366570446,
"loss": 0.8572,
"step": 310
},
{
"epoch": 0.3879310344827586,
"grad_norm": 0.09784611314535141,
"learning_rate": 0.00015380051715382996,
"loss": 0.8631,
"step": 315
},
{
"epoch": 0.39408866995073893,
"grad_norm": 0.09743879735469818,
"learning_rate": 0.0001519743812155516,
"loss": 0.8726,
"step": 320
},
{
"epoch": 0.4002463054187192,
"grad_norm": 0.09685247391462326,
"learning_rate": 0.00015012418134457755,
"loss": 0.861,
"step": 325
},
{
"epoch": 0.4064039408866995,
"grad_norm": 0.09240145981311798,
"learning_rate": 0.00014825077417612186,
"loss": 0.8762,
"step": 330
},
{
"epoch": 0.4125615763546798,
"grad_norm": 0.09885115176439285,
"learning_rate": 0.0001463550270902851,
"loss": 0.8497,
"step": 335
},
{
"epoch": 0.4187192118226601,
"grad_norm": 0.0954485759139061,
"learning_rate": 0.00014443781781046136,
"loss": 0.8951,
"step": 340
},
{
"epoch": 0.4248768472906404,
"grad_norm": 0.09606096148490906,
"learning_rate": 0.0001425000339969554,
"loss": 0.8083,
"step": 345
},
{
"epoch": 0.43103448275862066,
"grad_norm": 0.09620077162981033,
"learning_rate": 0.00014054257283599973,
"loss": 0.845,
"step": 350
},
{
"epoch": 0.437192118226601,
"grad_norm": 0.08843566477298737,
"learning_rate": 0.0001385663406243607,
"loss": 0.8403,
"step": 355
},
{
"epoch": 0.4433497536945813,
"grad_norm": 0.099284827709198,
"learning_rate": 0.00013657225234972695,
"loss": 0.8653,
"step": 360
},
{
"epoch": 0.44950738916256155,
"grad_norm": 0.09899378567934036,
"learning_rate": 0.00013456123126707334,
"loss": 0.8588,
"step": 365
},
{
"epoch": 0.45566502463054187,
"grad_norm": 0.09079897403717041,
"learning_rate": 0.00013253420847119803,
"loss": 0.8437,
"step": 370
},
{
"epoch": 0.4618226600985222,
"grad_norm": 0.09493466466665268,
"learning_rate": 0.0001304921224656289,
"loss": 0.8333,
"step": 375
},
{
"epoch": 0.46798029556650245,
"grad_norm": 0.10698249191045761,
"learning_rate": 0.0001284359187281004,
"loss": 0.8608,
"step": 380
},
{
"epoch": 0.47413793103448276,
"grad_norm": 0.0892605111002922,
"learning_rate": 0.00012636654927280073,
"loss": 0.8564,
"step": 385
},
{
"epoch": 0.4802955665024631,
"grad_norm": 0.10004895180463791,
"learning_rate": 0.0001242849722095936,
"loss": 0.8315,
"step": 390
},
{
"epoch": 0.48645320197044334,
"grad_norm": 0.09279712289571762,
"learning_rate": 0.00012219215130041656,
"loss": 0.8536,
"step": 395
},
{
"epoch": 0.49261083743842365,
"grad_norm": 0.10286492109298706,
"learning_rate": 0.00012008905551306356,
"loss": 0.8752,
"step": 400
},
{
"epoch": 0.4987684729064039,
"grad_norm": 0.0989002138376236,
"learning_rate": 0.00011797665857255621,
"loss": 0.8681,
"step": 405
},
{
"epoch": 0.5049261083743842,
"grad_norm": 0.0905391201376915,
"learning_rate": 0.00011585593851031347,
"loss": 0.8259,
"step": 410
},
{
"epoch": 0.5110837438423645,
"grad_norm": 0.09226394444704056,
"learning_rate": 0.00011372787721132648,
"loss": 0.8508,
"step": 415
},
{
"epoch": 0.5172413793103449,
"grad_norm": 0.08922280371189117,
"learning_rate": 0.00011159345995955006,
"loss": 0.8461,
"step": 420
},
{
"epoch": 0.5233990147783252,
"grad_norm": 0.10110611468553543,
"learning_rate": 0.00010945367498171993,
"loss": 0.8539,
"step": 425
},
{
"epoch": 0.5295566502463054,
"grad_norm": 0.09112325310707092,
"learning_rate": 0.00010730951298980776,
"loss": 0.8349,
"step": 430
},
{
"epoch": 0.5357142857142857,
"grad_norm": 0.08943382650613785,
"learning_rate": 0.00010516196672232539,
"loss": 0.8615,
"step": 435
},
{
"epoch": 0.541871921182266,
"grad_norm": 0.09342249482870102,
"learning_rate": 0.00010301203048469083,
"loss": 0.8884,
"step": 440
},
{
"epoch": 0.5480295566502463,
"grad_norm": 0.10344105213880539,
"learning_rate": 0.00010086069968886885,
"loss": 0.8484,
"step": 445
},
{
"epoch": 0.5541871921182266,
"grad_norm": 0.09956018626689911,
"learning_rate": 9.870897039249911e-05,
"loss": 0.8512,
"step": 450
},
{
"epoch": 0.5603448275862069,
"grad_norm": 0.0998009741306305,
"learning_rate": 9.655783883772545e-05,
"loss": 0.8494,
"step": 455
},
{
"epoch": 0.5665024630541872,
"grad_norm": 0.09044328331947327,
"learning_rate": 9.440830098993969e-05,
"loss": 0.8421,
"step": 460
},
{
"epoch": 0.5726600985221675,
"grad_norm": 0.09510013461112976,
"learning_rate": 9.22613520766537e-05,
"loss": 0.8363,
"step": 465
},
{
"epoch": 0.5788177339901478,
"grad_norm": 0.09868821501731873,
"learning_rate": 9.011798612671286e-05,
"loss": 0.8268,
"step": 470
},
{
"epoch": 0.5849753694581281,
"grad_norm": 0.10146130621433258,
"learning_rate": 8.797919551006475e-05,
"loss": 0.8301,
"step": 475
},
{
"epoch": 0.5911330049261084,
"grad_norm": 0.09029935300350189,
"learning_rate": 8.58459704782957e-05,
"loss": 0.8431,
"step": 480
},
{
"epoch": 0.5972906403940886,
"grad_norm": 0.087819404900074,
"learning_rate": 8.371929870614833e-05,
"loss": 0.8725,
"step": 485
},
{
"epoch": 0.603448275862069,
"grad_norm": 0.08721251785755157,
"learning_rate": 8.160016483423199e-05,
"loss": 0.8225,
"step": 490
},
{
"epoch": 0.6096059113300493,
"grad_norm": 0.09416023641824722,
"learning_rate": 7.948955001313811e-05,
"loss": 0.8354,
"step": 495
},
{
"epoch": 0.6157635467980296,
"grad_norm": 0.09370820969343185,
"learning_rate": 7.738843144917119e-05,
"loss": 0.8494,
"step": 500
},
{
"epoch": 0.6219211822660099,
"grad_norm": 0.09217171370983124,
"learning_rate": 7.529778195190645e-05,
"loss": 0.8747,
"step": 505
},
{
"epoch": 0.6280788177339901,
"grad_norm": 0.10151168704032898,
"learning_rate": 7.321856948378259e-05,
"loss": 0.8403,
"step": 510
},
{
"epoch": 0.6342364532019704,
"grad_norm": 0.0952015370130539,
"learning_rate": 7.115175671193913e-05,
"loss": 0.8728,
"step": 515
},
{
"epoch": 0.6403940886699507,
"grad_norm": 0.09815708547830582,
"learning_rate": 6.909830056250527e-05,
"loss": 0.8394,
"step": 520
},
{
"epoch": 0.646551724137931,
"grad_norm": 0.0990515947341919,
"learning_rate": 6.7059151777547e-05,
"loss": 0.8653,
"step": 525
},
{
"epoch": 0.6527093596059114,
"grad_norm": 0.09415574371814728,
"learning_rate": 6.503525447487715e-05,
"loss": 0.8428,
"step": 530
},
{
"epoch": 0.6588669950738916,
"grad_norm": 0.09867296367883682,
"learning_rate": 6.30275457109327e-05,
"loss": 0.8642,
"step": 535
},
{
"epoch": 0.6650246305418719,
"grad_norm": 0.09695271402597427,
"learning_rate": 6.103695504692122e-05,
"loss": 0.8525,
"step": 540
},
{
"epoch": 0.6711822660098522,
"grad_norm": 0.09747792780399323,
"learning_rate": 5.906440411843787e-05,
"loss": 0.8353,
"step": 545
},
{
"epoch": 0.6773399014778325,
"grad_norm": 0.10167969763278961,
"learning_rate": 5.7110806208751655e-05,
"loss": 0.8598,
"step": 550
},
{
"epoch": 0.6834975369458128,
"grad_norm": 0.10404445976018906,
"learning_rate": 5.5177065825958966e-05,
"loss": 0.8508,
"step": 555
},
{
"epoch": 0.6896551724137931,
"grad_norm": 0.10252311080694199,
"learning_rate": 5.326407828419979e-05,
"loss": 0.8628,
"step": 560
},
{
"epoch": 0.6958128078817734,
"grad_norm": 0.0978783667087555,
"learning_rate": 5.137272928913097e-05,
"loss": 0.8444,
"step": 565
},
{
"epoch": 0.7019704433497537,
"grad_norm": 0.09531436115503311,
"learning_rate": 4.9503894527847964e-05,
"loss": 0.8516,
"step": 570
},
{
"epoch": 0.708128078817734,
"grad_norm": 0.09567014127969742,
"learning_rate": 4.7658439263445e-05,
"loss": 0.8498,
"step": 575
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.09696997702121735,
"learning_rate": 4.583721793440188e-05,
"loss": 0.8388,
"step": 580
},
{
"epoch": 0.7204433497536946,
"grad_norm": 0.09134112298488617,
"learning_rate": 4.4041073758982335e-05,
"loss": 0.8842,
"step": 585
},
{
"epoch": 0.7266009852216748,
"grad_norm": 0.0912870541214943,
"learning_rate": 4.227083834482728e-05,
"loss": 0.843,
"step": 590
},
{
"epoch": 0.7327586206896551,
"grad_norm": 0.10903932899236679,
"learning_rate": 4.052733130392367e-05,
"loss": 0.85,
"step": 595
},
{
"epoch": 0.7389162561576355,
"grad_norm": 0.09636314958333969,
"learning_rate": 3.881135987312757e-05,
"loss": 0.8293,
"step": 600
},
{
"epoch": 0.7450738916256158,
"grad_norm": 0.09389379620552063,
"learning_rate": 3.712371854041654e-05,
"loss": 0.8587,
"step": 605
},
{
"epoch": 0.7512315270935961,
"grad_norm": 0.08844725042581558,
"learning_rate": 3.546518867704499e-05,
"loss": 0.8531,
"step": 610
},
{
"epoch": 0.7573891625615764,
"grad_norm": 0.0951227992773056,
"learning_rate": 3.383653817577216e-05,
"loss": 0.8389,
"step": 615
},
{
"epoch": 0.7635467980295566,
"grad_norm": 0.09906347841024399,
"learning_rate": 3.223852109533112e-05,
"loss": 0.8572,
"step": 620
},
{
"epoch": 0.7697044334975369,
"grad_norm": 0.10321184247732162,
"learning_rate": 3.0671877311302244e-05,
"loss": 0.8657,
"step": 625
},
{
"epoch": 0.7758620689655172,
"grad_norm": 0.094594806432724,
"learning_rate": 2.9137332173554043e-05,
"loss": 0.8217,
"step": 630
},
{
"epoch": 0.7820197044334976,
"grad_norm": 0.09115397185087204,
"learning_rate": 2.763559617040876e-05,
"loss": 0.8625,
"step": 635
},
{
"epoch": 0.7881773399014779,
"grad_norm": 0.09720595180988312,
"learning_rate": 2.616736459968936e-05,
"loss": 0.8399,
"step": 640
},
{
"epoch": 0.7943349753694581,
"grad_norm": 0.09503541141748428,
"learning_rate": 2.473331724679917e-05,
"loss": 0.8649,
"step": 645
},
{
"epoch": 0.8004926108374384,
"grad_norm": 0.09784215688705444,
"learning_rate": 2.33341180699841e-05,
"loss": 0.8547,
"step": 650
},
{
"epoch": 0.8066502463054187,
"grad_norm": 0.10509417206048965,
"learning_rate": 2.1970414892922442e-05,
"loss": 0.8536,
"step": 655
},
{
"epoch": 0.812807881773399,
"grad_norm": 0.09280036389827728,
"learning_rate": 2.0642839104785272e-05,
"loss": 0.8686,
"step": 660
},
{
"epoch": 0.8189655172413793,
"grad_norm": 0.09563688188791275,
"learning_rate": 1.9352005367905536e-05,
"loss": 0.834,
"step": 665
},
{
"epoch": 0.8251231527093597,
"grad_norm": 0.09236620366573334,
"learning_rate": 1.8098511333192024e-05,
"loss": 0.8427,
"step": 670
},
{
"epoch": 0.8312807881773399,
"grad_norm": 0.09800606966018677,
"learning_rate": 1.6882937363419203e-05,
"loss": 0.886,
"step": 675
},
{
"epoch": 0.8374384236453202,
"grad_norm": 0.10096932202577591,
"learning_rate": 1.570584626452173e-05,
"loss": 0.8588,
"step": 680
},
{
"epoch": 0.8435960591133005,
"grad_norm": 0.08817877620458603,
"learning_rate": 1.4567783025017301e-05,
"loss": 0.8696,
"step": 685
},
{
"epoch": 0.8497536945812808,
"grad_norm": 0.09163439273834229,
"learning_rate": 1.3469274563679402e-05,
"loss": 0.8385,
"step": 690
},
{
"epoch": 0.8559113300492611,
"grad_norm": 0.10107564181089401,
"learning_rate": 1.2410829485575704e-05,
"loss": 0.8644,
"step": 695
},
{
"epoch": 0.8620689655172413,
"grad_norm": 0.09278399497270584,
"learning_rate": 1.1392937846586215e-05,
"loss": 0.8424,
"step": 700
},
{
"epoch": 0.8682266009852216,
"grad_norm": 0.09335629642009735,
"learning_rate": 1.0416070926509113e-05,
"loss": 0.8341,
"step": 705
},
{
"epoch": 0.874384236453202,
"grad_norm": 0.09166532754898071,
"learning_rate": 9.48068101086026e-06,
"loss": 0.8183,
"step": 710
},
{
"epoch": 0.8805418719211823,
"grad_norm": 0.08948343247175217,
"learning_rate": 8.58720118146662e-06,
"loss": 0.8486,
"step": 715
},
{
"epoch": 0.8866995073891626,
"grad_norm": 0.08922126144170761,
"learning_rate": 7.736045115951251e-06,
"loss": 0.8228,
"step": 720
},
{
"epoch": 0.8928571428571429,
"grad_norm": 0.09619385004043579,
"learning_rate": 6.927606896202066e-06,
"loss": 0.8306,
"step": 725
},
{
"epoch": 0.8990147783251231,
"grad_norm": 0.0950331911444664,
"learning_rate": 6.16226082591359e-06,
"loss": 0.8468,
"step": 730
},
{
"epoch": 0.9051724137931034,
"grad_norm": 0.09271179139614105,
"learning_rate": 5.440361257285742e-06,
"loss": 0.8281,
"step": 735
},
{
"epoch": 0.9113300492610837,
"grad_norm": 0.09265490621328354,
"learning_rate": 4.762242426960262e-06,
"loss": 0.8358,
"step": 740
},
{
"epoch": 0.9174876847290641,
"grad_norm": 0.09312190115451813,
"learning_rate": 4.128218301270359e-06,
"loss": 0.8572,
"step": 745
},
{
"epoch": 0.9236453201970444,
"grad_norm": 0.08909430354833603,
"learning_rate": 3.5385824308756587e-06,
"loss": 0.8504,
"step": 750
},
{
"epoch": 0.9298029556650246,
"grad_norm": 0.09229204058647156,
"learning_rate": 2.9936078148492973e-06,
"loss": 0.8476,
"step": 755
},
{
"epoch": 0.9359605911330049,
"grad_norm": 0.091829314827919,
"learning_rate": 2.493546774280531e-06,
"loss": 0.8428,
"step": 760
},
{
"epoch": 0.9421182266009852,
"grad_norm": 0.09492628276348114,
"learning_rate": 2.0386308354509942e-06,
"loss": 0.8425,
"step": 765
},
{
"epoch": 0.9482758620689655,
"grad_norm": 0.09082033485174179,
"learning_rate": 1.6290706226390285e-06,
"loss": 0.8508,
"step": 770
},
{
"epoch": 0.9544334975369458,
"grad_norm": 0.09625081717967987,
"learning_rate": 1.2650557606013635e-06,
"loss": 0.8274,
"step": 775
},
{
"epoch": 0.9605911330049262,
"grad_norm": 0.10376901179552078,
"learning_rate": 9.46754786777726e-07,
"loss": 0.8682,
"step": 780
},
{
"epoch": 0.9667487684729064,
"grad_norm": 0.09615808725357056,
"learning_rate": 6.74315073258569e-07,
"loss": 0.8665,
"step": 785
},
{
"epoch": 0.9729064039408867,
"grad_norm": 0.09874554723501205,
"learning_rate": 4.4786275855247527e-07,
"loss": 0.857,
"step": 790
},
{
"epoch": 0.979064039408867,
"grad_norm": 0.08657025545835495,
"learning_rate": 2.675026891844512e-07,
"loss": 0.8418,
"step": 795
},
{
"epoch": 0.9852216748768473,
"grad_norm": 0.09017368406057358,
"learning_rate": 1.333183711524133e-07,
"loss": 0.8469,
"step": 800
},
{
"epoch": 0.9913793103448276,
"grad_norm": 0.0891832485795021,
"learning_rate": 4.5371931264270864e-08,
"loss": 0.8224,
"step": 805
},
{
"epoch": 0.9975369458128078,
"grad_norm": 0.0949506014585495,
"learning_rate": 3.7040883734462683e-09,
"loss": 0.8656,
"step": 810
},
{
"epoch": 1.0,
"eval_loss": 1.2676365375518799,
"eval_runtime": 133.6838,
"eval_samples_per_second": 8.64,
"eval_steps_per_second": 0.546,
"step": 812
},
{
"epoch": 1.0,
"step": 812,
"total_flos": 2.031234394303234e+18,
"train_loss": 0.8583573980871679,
"train_runtime": 32078.1302,
"train_samples_per_second": 3.24,
"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": 2.031234394303234e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}