loubnabnl's picture
loubnabnl HF staff
Model save
71f2d39 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9990828492815653,
"eval_steps": 500,
"global_step": 817,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0012228676245796392,
"grad_norm": 1.5651791434848155,
"learning_rate": 1.2195121951219513e-05,
"loss": 1.3765,
"step": 1
},
{
"epoch": 0.006114338122898196,
"grad_norm": 1.4895397594466544,
"learning_rate": 6.097560975609756e-05,
"loss": 1.3626,
"step": 5
},
{
"epoch": 0.012228676245796393,
"grad_norm": 1.5249099144693075,
"learning_rate": 0.00012195121951219512,
"loss": 1.3248,
"step": 10
},
{
"epoch": 0.01834301436869459,
"grad_norm": 0.6182572105126181,
"learning_rate": 0.00018292682926829268,
"loss": 1.2243,
"step": 15
},
{
"epoch": 0.024457352491592785,
"grad_norm": 0.41445396549550984,
"learning_rate": 0.00024390243902439024,
"loss": 1.1402,
"step": 20
},
{
"epoch": 0.03057169061449098,
"grad_norm": 0.3150276194376965,
"learning_rate": 0.0003048780487804878,
"loss": 1.1038,
"step": 25
},
{
"epoch": 0.03668602873738918,
"grad_norm": 0.14810738565646345,
"learning_rate": 0.00036585365853658537,
"loss": 1.0666,
"step": 30
},
{
"epoch": 0.042800366860287375,
"grad_norm": 0.1469799790499961,
"learning_rate": 0.0004268292682926829,
"loss": 1.0788,
"step": 35
},
{
"epoch": 0.04891470498318557,
"grad_norm": 0.11813746835657694,
"learning_rate": 0.0004878048780487805,
"loss": 1.0383,
"step": 40
},
{
"epoch": 0.055029043106083766,
"grad_norm": 0.11458144940287407,
"learning_rate": 0.0005487804878048781,
"loss": 1.0344,
"step": 45
},
{
"epoch": 0.06114338122898196,
"grad_norm": 0.12431506889021993,
"learning_rate": 0.0006097560975609756,
"loss": 1.0212,
"step": 50
},
{
"epoch": 0.06725771935188016,
"grad_norm": 0.1442069213894891,
"learning_rate": 0.0006707317073170732,
"loss": 1.0225,
"step": 55
},
{
"epoch": 0.07337205747477836,
"grad_norm": 0.10867878877350798,
"learning_rate": 0.0007317073170731707,
"loss": 1.0146,
"step": 60
},
{
"epoch": 0.07948639559767655,
"grad_norm": 0.11956283604570934,
"learning_rate": 0.0007926829268292683,
"loss": 1.01,
"step": 65
},
{
"epoch": 0.08560073372057475,
"grad_norm": 0.12502860090742626,
"learning_rate": 0.0008536585365853659,
"loss": 1.0053,
"step": 70
},
{
"epoch": 0.09171507184347294,
"grad_norm": 0.12326167917218363,
"learning_rate": 0.0009146341463414635,
"loss": 1.0029,
"step": 75
},
{
"epoch": 0.09782940996637114,
"grad_norm": 0.12744417766871155,
"learning_rate": 0.000975609756097561,
"loss": 0.9936,
"step": 80
},
{
"epoch": 0.10394374808926933,
"grad_norm": 0.2031560386367655,
"learning_rate": 0.0009999588943391596,
"loss": 0.9976,
"step": 85
},
{
"epoch": 0.11005808621216753,
"grad_norm": 0.17021719270809427,
"learning_rate": 0.0009997077175540067,
"loss": 0.9974,
"step": 90
},
{
"epoch": 0.11617242433506574,
"grad_norm": 0.16256998958046662,
"learning_rate": 0.0009992283150399447,
"loss": 0.9981,
"step": 95
},
{
"epoch": 0.12228676245796392,
"grad_norm": 0.16488934277544587,
"learning_rate": 0.000998520905748941,
"loss": 0.994,
"step": 100
},
{
"epoch": 0.12840110058086213,
"grad_norm": 0.12662055003888464,
"learning_rate": 0.0009975858127678633,
"loss": 0.985,
"step": 105
},
{
"epoch": 0.13451543870376031,
"grad_norm": 0.12183795639733393,
"learning_rate": 0.0009964234631709187,
"loss": 0.982,
"step": 110
},
{
"epoch": 0.1406297768266585,
"grad_norm": 0.14273430665729847,
"learning_rate": 0.0009950343878246009,
"loss": 0.9944,
"step": 115
},
{
"epoch": 0.14674411494955672,
"grad_norm": 0.13530053769850683,
"learning_rate": 0.0009934192211452344,
"loss": 0.9868,
"step": 120
},
{
"epoch": 0.1528584530724549,
"grad_norm": 0.16040856740605441,
"learning_rate": 0.0009915787008092246,
"loss": 0.9821,
"step": 125
},
{
"epoch": 0.1589727911953531,
"grad_norm": 0.14036184991824666,
"learning_rate": 0.0009895136674161465,
"loss": 0.9726,
"step": 130
},
{
"epoch": 0.16508712931825129,
"grad_norm": 0.16453999088527366,
"learning_rate": 0.0009872250641048289,
"loss": 0.9803,
"step": 135
},
{
"epoch": 0.1712014674411495,
"grad_norm": 0.12609483380818387,
"learning_rate": 0.0009847139361226047,
"loss": 0.9747,
"step": 140
},
{
"epoch": 0.1773158055640477,
"grad_norm": 0.11833511610560972,
"learning_rate": 0.0009819814303479266,
"loss": 0.9764,
"step": 145
},
{
"epoch": 0.18343014368694588,
"grad_norm": 0.13867903334188714,
"learning_rate": 0.0009790287947665682,
"loss": 0.9705,
"step": 150
},
{
"epoch": 0.1895444818098441,
"grad_norm": 0.16359704719067755,
"learning_rate": 0.0009758573779016438,
"loss": 0.973,
"step": 155
},
{
"epoch": 0.19565881993274228,
"grad_norm": 0.1521247586416416,
"learning_rate": 0.0009724686281977146,
"loss": 0.9572,
"step": 160
},
{
"epoch": 0.20177315805564047,
"grad_norm": 0.12042783871397957,
"learning_rate": 0.0009688640933592572,
"loss": 0.9567,
"step": 165
},
{
"epoch": 0.20788749617853866,
"grad_norm": 0.12309002079679088,
"learning_rate": 0.0009650454196437975,
"loss": 0.9563,
"step": 170
},
{
"epoch": 0.21400183430143688,
"grad_norm": 0.18172628896470117,
"learning_rate": 0.0009610143511100353,
"loss": 0.9552,
"step": 175
},
{
"epoch": 0.22011617242433507,
"grad_norm": 0.15193832095784507,
"learning_rate": 0.0009567727288213005,
"loss": 0.9554,
"step": 180
},
{
"epoch": 0.22623051054723325,
"grad_norm": 0.11071517374274199,
"learning_rate": 0.0009523224900047051,
"loss": 0.944,
"step": 185
},
{
"epoch": 0.23234484867013147,
"grad_norm": 0.16605306055042693,
"learning_rate": 0.0009476656671663766,
"loss": 0.9515,
"step": 190
},
{
"epoch": 0.23845918679302966,
"grad_norm": 0.14817549608028274,
"learning_rate": 0.0009428043871631739,
"loss": 0.9394,
"step": 195
},
{
"epoch": 0.24457352491592785,
"grad_norm": 0.1220114307763855,
"learning_rate": 0.0009377408702313137,
"loss": 0.95,
"step": 200
},
{
"epoch": 0.25068786303882606,
"grad_norm": 0.11567261614693129,
"learning_rate": 0.0009324774289723468,
"loss": 0.9492,
"step": 205
},
{
"epoch": 0.25680220116172425,
"grad_norm": 0.15943169108613203,
"learning_rate": 0.0009270164672969508,
"loss": 0.9466,
"step": 210
},
{
"epoch": 0.26291653928462244,
"grad_norm": 0.10563236585959133,
"learning_rate": 0.0009213604793270196,
"loss": 0.9437,
"step": 215
},
{
"epoch": 0.26903087740752063,
"grad_norm": 0.12137894462956439,
"learning_rate": 0.000915512048256552,
"loss": 0.946,
"step": 220
},
{
"epoch": 0.2751452155304188,
"grad_norm": 0.1254514821868344,
"learning_rate": 0.0009094738451718594,
"loss": 0.9448,
"step": 225
},
{
"epoch": 0.281259553653317,
"grad_norm": 0.12275607048530816,
"learning_rate": 0.0009032486278316315,
"loss": 0.9486,
"step": 230
},
{
"epoch": 0.28737389177621525,
"grad_norm": 0.11222179304998407,
"learning_rate": 0.0008968392394074163,
"loss": 0.944,
"step": 235
},
{
"epoch": 0.29348822989911344,
"grad_norm": 0.13700620863862228,
"learning_rate": 0.0008902486071850926,
"loss": 0.9413,
"step": 240
},
{
"epoch": 0.29960256802201163,
"grad_norm": 0.12147382100215783,
"learning_rate": 0.0008834797412279236,
"loss": 0.9314,
"step": 245
},
{
"epoch": 0.3057169061449098,
"grad_norm": 0.10835379277656058,
"learning_rate": 0.0008765357330018055,
"loss": 0.9272,
"step": 250
},
{
"epoch": 0.311831244267808,
"grad_norm": 0.11862083478281513,
"learning_rate": 0.0008694197539633384,
"loss": 0.9404,
"step": 255
},
{
"epoch": 0.3179455823907062,
"grad_norm": 0.10703516760798883,
"learning_rate": 0.0008621350541113637,
"loss": 0.9327,
"step": 260
},
{
"epoch": 0.3240599205136044,
"grad_norm": 0.14408727173165917,
"learning_rate": 0.0008546849605026289,
"loss": 0.93,
"step": 265
},
{
"epoch": 0.33017425863650257,
"grad_norm": 0.1352262854726781,
"learning_rate": 0.0008470728757322603,
"loss": 0.927,
"step": 270
},
{
"epoch": 0.3362885967594008,
"grad_norm": 0.17065892900202725,
"learning_rate": 0.0008393022763797346,
"loss": 0.9361,
"step": 275
},
{
"epoch": 0.342402934882299,
"grad_norm": 0.15109584505284554,
"learning_rate": 0.0008313767114210615,
"loss": 0.9357,
"step": 280
},
{
"epoch": 0.3485172730051972,
"grad_norm": 0.10720327809906864,
"learning_rate": 0.0008232998006078997,
"loss": 0.928,
"step": 285
},
{
"epoch": 0.3546316111280954,
"grad_norm": 0.12388797358800836,
"learning_rate": 0.0008150752328143514,
"loss": 0.9254,
"step": 290
},
{
"epoch": 0.36074594925099357,
"grad_norm": 0.12765973869133845,
"learning_rate": 0.0008067067643521834,
"loss": 0.903,
"step": 295
},
{
"epoch": 0.36686028737389176,
"grad_norm": 0.22025311153904717,
"learning_rate": 0.0007981982172552517,
"loss": 0.9312,
"step": 300
},
{
"epoch": 0.37297462549678995,
"grad_norm": 0.11123495383204336,
"learning_rate": 0.0007895534775339084,
"loss": 0.9157,
"step": 305
},
{
"epoch": 0.3790889636196882,
"grad_norm": 0.12003692642329743,
"learning_rate": 0.0007807764934001874,
"loss": 0.9033,
"step": 310
},
{
"epoch": 0.3852033017425864,
"grad_norm": 0.15092887769329769,
"learning_rate": 0.000771871273464585,
"loss": 0.92,
"step": 315
},
{
"epoch": 0.39131763986548457,
"grad_norm": 0.1053602258718211,
"learning_rate": 0.0007628418849052523,
"loss": 0.9129,
"step": 320
},
{
"epoch": 0.39743197798838276,
"grad_norm": 0.12125259732003754,
"learning_rate": 0.0007536924516104411,
"loss": 0.913,
"step": 325
},
{
"epoch": 0.40354631611128094,
"grad_norm": 0.13999049875939493,
"learning_rate": 0.0007444271522950469,
"loss": 0.9008,
"step": 330
},
{
"epoch": 0.40966065423417913,
"grad_norm": 0.11628169728091785,
"learning_rate": 0.0007350502185921132,
"loss": 0.9095,
"step": 335
},
{
"epoch": 0.4157749923570773,
"grad_norm": 0.12414661387014203,
"learning_rate": 0.0007255659331201672,
"loss": 0.9173,
"step": 340
},
{
"epoch": 0.42188933047997557,
"grad_norm": 0.12133875571492429,
"learning_rate": 0.0007159786275272686,
"loss": 0.9052,
"step": 345
},
{
"epoch": 0.42800366860287375,
"grad_norm": 0.10406959912373474,
"learning_rate": 0.0007062926805126653,
"loss": 0.9131,
"step": 350
},
{
"epoch": 0.43411800672577194,
"grad_norm": 0.12728690442797477,
"learning_rate": 0.0006965125158269618,
"loss": 0.9072,
"step": 355
},
{
"epoch": 0.44023234484867013,
"grad_norm": 0.1170318049898702,
"learning_rate": 0.0006866426002517105,
"loss": 0.9059,
"step": 360
},
{
"epoch": 0.4463466829715683,
"grad_norm": 0.10171836143290221,
"learning_rate": 0.0006766874415593496,
"loss": 0.9101,
"step": 365
},
{
"epoch": 0.4524610210944665,
"grad_norm": 0.09660525775453423,
"learning_rate": 0.0006666515864544209,
"loss": 0.9065,
"step": 370
},
{
"epoch": 0.4585753592173647,
"grad_norm": 0.12897677659098664,
"learning_rate": 0.0006565396184970059,
"loss": 0.9158,
"step": 375
},
{
"epoch": 0.46468969734026294,
"grad_norm": 0.12229565064806812,
"learning_rate": 0.0006463561560093292,
"loss": 0.9028,
"step": 380
},
{
"epoch": 0.47080403546316113,
"grad_norm": 0.11734011152355654,
"learning_rate": 0.0006361058499664855,
"loss": 0.8985,
"step": 385
},
{
"epoch": 0.4769183735860593,
"grad_norm": 0.10225820834821302,
"learning_rate": 0.0006257933818722543,
"loss": 0.8992,
"step": 390
},
{
"epoch": 0.4830327117089575,
"grad_norm": 0.1210863256030476,
"learning_rate": 0.0006154234616209693,
"loss": 0.9004,
"step": 395
},
{
"epoch": 0.4891470498318557,
"grad_norm": 0.14049274054700558,
"learning_rate": 0.0006050008253464246,
"loss": 0.894,
"step": 400
},
{
"epoch": 0.4952613879547539,
"grad_norm": 0.11520417692209506,
"learning_rate": 0.0005945302332587938,
"loss": 0.8941,
"step": 405
},
{
"epoch": 0.5013757260776521,
"grad_norm": 0.11679009305377734,
"learning_rate": 0.0005840164674705543,
"loss": 0.8875,
"step": 410
},
{
"epoch": 0.5074900642005503,
"grad_norm": 0.10841284729961655,
"learning_rate": 0.000573464329812409,
"loss": 0.8896,
"step": 415
},
{
"epoch": 0.5136044023234485,
"grad_norm": 0.08635350201084568,
"learning_rate": 0.0005628786396402013,
"loss": 0.8905,
"step": 420
},
{
"epoch": 0.5197187404463467,
"grad_norm": 0.09367583733135104,
"learning_rate": 0.0005522642316338268,
"loss": 0.8961,
"step": 425
},
{
"epoch": 0.5258330785692449,
"grad_norm": 0.11185275146645236,
"learning_rate": 0.0005416259535891447,
"loss": 0.8923,
"step": 430
},
{
"epoch": 0.5319474166921431,
"grad_norm": 0.09083283056030737,
"learning_rate": 0.0005309686642039016,
"loss": 0.8803,
"step": 435
},
{
"epoch": 0.5380617548150413,
"grad_norm": 0.10225155676046674,
"learning_rate": 0.0005202972308586735,
"loss": 0.898,
"step": 440
},
{
"epoch": 0.5441760929379394,
"grad_norm": 0.09491178641730136,
"learning_rate": 0.0005096165273938436,
"loss": 0.8941,
"step": 445
},
{
"epoch": 0.5502904310608376,
"grad_norm": 0.10185484555043305,
"learning_rate": 0.0004989314318836302,
"loss": 0.8872,
"step": 450
},
{
"epoch": 0.5564047691837358,
"grad_norm": 0.09988997099687283,
"learning_rate": 0.00048824682440817927,
"loss": 0.8886,
"step": 455
},
{
"epoch": 0.562519107306634,
"grad_norm": 0.10706473271135161,
"learning_rate": 0.0004775675848247427,
"loss": 0.8921,
"step": 460
},
{
"epoch": 0.5686334454295322,
"grad_norm": 0.11773894458274514,
"learning_rate": 0.0004668985905389563,
"loss": 0.881,
"step": 465
},
{
"epoch": 0.5747477835524305,
"grad_norm": 0.09095900658172308,
"learning_rate": 0.0004562447142772404,
"loss": 0.8833,
"step": 470
},
{
"epoch": 0.5808621216753287,
"grad_norm": 0.09485196310765555,
"learning_rate": 0.0004456108218613346,
"loss": 0.8738,
"step": 475
},
{
"epoch": 0.5869764597982269,
"grad_norm": 0.09527296343968149,
"learning_rate": 0.00043500176998598775,
"loss": 0.8716,
"step": 480
},
{
"epoch": 0.5930907979211251,
"grad_norm": 0.09706717496523788,
"learning_rate": 0.0004244224040008156,
"loss": 0.8683,
"step": 485
},
{
"epoch": 0.5992051360440233,
"grad_norm": 0.0924175028621673,
"learning_rate": 0.00041387755569734057,
"loss": 0.8804,
"step": 490
},
{
"epoch": 0.6053194741669214,
"grad_norm": 0.09217501490527663,
"learning_rate": 0.0004033720411022235,
"loss": 0.8725,
"step": 495
},
{
"epoch": 0.6114338122898196,
"grad_norm": 0.08372781939532938,
"learning_rate": 0.00039291065827769484,
"loss": 0.8702,
"step": 500
},
{
"epoch": 0.6175481504127178,
"grad_norm": 0.09199560200708774,
"learning_rate": 0.0003824981851301924,
"loss": 0.8659,
"step": 505
},
{
"epoch": 0.623662488535616,
"grad_norm": 0.09842312407252246,
"learning_rate": 0.0003721393772282022,
"loss": 0.8697,
"step": 510
},
{
"epoch": 0.6297768266585142,
"grad_norm": 0.10750466193891031,
"learning_rate": 0.00036183896563030295,
"loss": 0.881,
"step": 515
},
{
"epoch": 0.6358911647814124,
"grad_norm": 0.11299900150340132,
"learning_rate": 0.0003516016547244047,
"loss": 0.8737,
"step": 520
},
{
"epoch": 0.6420055029043106,
"grad_norm": 0.4042681858963164,
"learning_rate": 0.00034143212007916793,
"loss": 0.876,
"step": 525
},
{
"epoch": 0.6481198410272088,
"grad_norm": 0.0999580549896975,
"learning_rate": 0.00033133500630858504,
"loss": 0.863,
"step": 530
},
{
"epoch": 0.654234179150107,
"grad_norm": 0.09704623218277748,
"learning_rate": 0.0003213149249506997,
"loss": 0.8726,
"step": 535
},
{
"epoch": 0.6603485172730051,
"grad_norm": 0.10372675529566282,
"learning_rate": 0.00031137645236143204,
"loss": 0.8616,
"step": 540
},
{
"epoch": 0.6664628553959034,
"grad_norm": 0.09213896359947416,
"learning_rate": 0.0003015241276244729,
"loss": 0.8706,
"step": 545
},
{
"epoch": 0.6725771935188016,
"grad_norm": 0.10042976905418785,
"learning_rate": 0.00029176245047820063,
"loss": 0.8491,
"step": 550
},
{
"epoch": 0.6786915316416998,
"grad_norm": 0.10028696192833891,
"learning_rate": 0.0002820958792605669,
"loss": 0.8574,
"step": 555
},
{
"epoch": 0.684805869764598,
"grad_norm": 0.09020811948567081,
"learning_rate": 0.00027252882887289287,
"loss": 0.8588,
"step": 560
},
{
"epoch": 0.6909202078874962,
"grad_norm": 0.10345140225018136,
"learning_rate": 0.0002630656687635007,
"loss": 0.8696,
"step": 565
},
{
"epoch": 0.6970345460103944,
"grad_norm": 0.10749740190617728,
"learning_rate": 0.0002537107209321074,
"loss": 0.8654,
"step": 570
},
{
"epoch": 0.7031488841332926,
"grad_norm": 0.08655101600658618,
"learning_rate": 0.0002444682579558872,
"loss": 0.8634,
"step": 575
},
{
"epoch": 0.7092632222561908,
"grad_norm": 0.11313373365287832,
"learning_rate": 0.00023534250103810628,
"loss": 0.8545,
"step": 580
},
{
"epoch": 0.715377560379089,
"grad_norm": 0.10389782206053953,
"learning_rate": 0.00022633761808022273,
"loss": 0.8563,
"step": 585
},
{
"epoch": 0.7214918985019871,
"grad_norm": 0.09141224639004816,
"learning_rate": 0.00021745772177832756,
"loss": 0.8678,
"step": 590
},
{
"epoch": 0.7276062366248853,
"grad_norm": 0.08733638591751752,
"learning_rate": 0.00020870686774480197,
"loss": 0.8587,
"step": 595
},
{
"epoch": 0.7337205747477835,
"grad_norm": 0.08848072887713172,
"learning_rate": 0.00020008905265604316,
"loss": 0.8514,
"step": 600
},
{
"epoch": 0.7398349128706817,
"grad_norm": 0.09707736850029325,
"learning_rate": 0.00019160821242710958,
"loss": 0.8633,
"step": 605
},
{
"epoch": 0.7459492509935799,
"grad_norm": 0.08787799540475368,
"learning_rate": 0.00018326822041411523,
"loss": 0.8576,
"step": 610
},
{
"epoch": 0.7520635891164782,
"grad_norm": 0.15694998805819793,
"learning_rate": 0.00017507288564519647,
"loss": 0.8526,
"step": 615
},
{
"epoch": 0.7581779272393764,
"grad_norm": 0.08920551112607182,
"learning_rate": 0.00016702595108085945,
"loss": 0.8684,
"step": 620
},
{
"epoch": 0.7642922653622746,
"grad_norm": 0.08761186010488109,
"learning_rate": 0.0001591310919045003,
"loss": 0.8665,
"step": 625
},
{
"epoch": 0.7704066034851728,
"grad_norm": 0.09195087795786469,
"learning_rate": 0.00015139191384388095,
"loss": 0.8454,
"step": 630
},
{
"epoch": 0.776520941608071,
"grad_norm": 0.10138883693988116,
"learning_rate": 0.00014381195152432768,
"loss": 0.8561,
"step": 635
},
{
"epoch": 0.7826352797309691,
"grad_norm": 0.08632117453676007,
"learning_rate": 0.00013639466685440134,
"loss": 0.8527,
"step": 640
},
{
"epoch": 0.7887496178538673,
"grad_norm": 0.09976824535412168,
"learning_rate": 0.00012914344744478112,
"loss": 0.8614,
"step": 645
},
{
"epoch": 0.7948639559767655,
"grad_norm": 0.0905710833584601,
"learning_rate": 0.0001220616050610791,
"loss": 0.8492,
"step": 650
},
{
"epoch": 0.8009782940996637,
"grad_norm": 0.1010968459506448,
"learning_rate": 0.00011515237411129698,
"loss": 0.8562,
"step": 655
},
{
"epoch": 0.8070926322225619,
"grad_norm": 0.08701870226697464,
"learning_rate": 0.00010841891016861154,
"loss": 0.8451,
"step": 660
},
{
"epoch": 0.8132069703454601,
"grad_norm": 0.0905216571291058,
"learning_rate": 0.00010186428853016605,
"loss": 0.8505,
"step": 665
},
{
"epoch": 0.8193213084683583,
"grad_norm": 0.08450629810354952,
"learning_rate": 9.549150281252633e-05,
"loss": 0.8548,
"step": 670
},
{
"epoch": 0.8254356465912565,
"grad_norm": 0.07782082601508845,
"learning_rate": 8.930346358443952e-05,
"loss": 0.8537,
"step": 675
},
{
"epoch": 0.8315499847141546,
"grad_norm": 0.07932529243696208,
"learning_rate": 8.330299703752498e-05,
"loss": 0.8516,
"step": 680
},
{
"epoch": 0.8376643228370529,
"grad_norm": 0.08755277608836383,
"learning_rate": 7.749284369549953e-05,
"loss": 0.8492,
"step": 685
},
{
"epoch": 0.8437786609599511,
"grad_norm": 0.08663207768299419,
"learning_rate": 7.187565716252992e-05,
"loss": 0.8571,
"step": 690
},
{
"epoch": 0.8498929990828493,
"grad_norm": 0.09041918396193563,
"learning_rate": 6.645400291128356e-05,
"loss": 0.8522,
"step": 695
},
{
"epoch": 0.8560073372057475,
"grad_norm": 0.08393639987821447,
"learning_rate": 6.123035711122859e-05,
"loss": 0.8462,
"step": 700
},
{
"epoch": 0.8621216753286457,
"grad_norm": 0.13260901574408163,
"learning_rate": 5.6207105497722956e-05,
"loss": 0.8454,
"step": 705
},
{
"epoch": 0.8682360134515439,
"grad_norm": 0.0901850885792999,
"learning_rate": 5.138654228240425e-05,
"loss": 0.8474,
"step": 710
},
{
"epoch": 0.8743503515744421,
"grad_norm": 0.07895758711701614,
"learning_rate": 4.677086910538092e-05,
"loss": 0.845,
"step": 715
},
{
"epoch": 0.8804646896973403,
"grad_norm": 0.07735814272716246,
"learning_rate": 4.236219402970326e-05,
"loss": 0.8582,
"step": 720
},
{
"epoch": 0.8865790278202385,
"grad_norm": 0.08201034719715149,
"learning_rate": 3.816253057857144e-05,
"loss": 0.8429,
"step": 725
},
{
"epoch": 0.8926933659431366,
"grad_norm": 0.9278041030137772,
"learning_rate": 3.417379681572297e-05,
"loss": 0.8571,
"step": 730
},
{
"epoch": 0.8988077040660348,
"grad_norm": 0.07949661992375699,
"learning_rate": 3.0397814469416973e-05,
"loss": 0.8534,
"step": 735
},
{
"epoch": 0.904922042188933,
"grad_norm": 0.08460584169650966,
"learning_rate": 2.683630810041787e-05,
"loss": 0.8517,
"step": 740
},
{
"epoch": 0.9110363803118312,
"grad_norm": 0.07824416631858255,
"learning_rate": 2.349090431435641e-05,
"loss": 0.8422,
"step": 745
},
{
"epoch": 0.9171507184347294,
"grad_norm": 0.08718216227123719,
"learning_rate": 2.0363131018828753e-05,
"loss": 0.8475,
"step": 750
},
{
"epoch": 0.9232650565576276,
"grad_norm": 0.07763832558735692,
"learning_rate": 1.7454416725573353e-05,
"loss": 0.8383,
"step": 755
},
{
"epoch": 0.9293793946805259,
"grad_norm": 0.07705992848954801,
"learning_rate": 1.4766089898042678e-05,
"loss": 0.8518,
"step": 760
},
{
"epoch": 0.9354937328034241,
"grad_norm": 0.08210162590156625,
"learning_rate": 1.2299378344669988e-05,
"loss": 0.8462,
"step": 765
},
{
"epoch": 0.9416080709263223,
"grad_norm": 0.07772244992401371,
"learning_rate": 1.0055408658106447e-05,
"loss": 0.8479,
"step": 770
},
{
"epoch": 0.9477224090492204,
"grad_norm": 0.08562907738973832,
"learning_rate": 8.035205700685167e-06,
"loss": 0.8588,
"step": 775
},
{
"epoch": 0.9538367471721186,
"grad_norm": 0.08630642465450503,
"learning_rate": 6.239692136348285e-06,
"loss": 0.8528,
"step": 780
},
{
"epoch": 0.9599510852950168,
"grad_norm": 0.07836684511882595,
"learning_rate": 4.669688009248607e-06,
"loss": 0.8361,
"step": 785
},
{
"epoch": 0.966065423417915,
"grad_norm": 0.0787423003956017,
"learning_rate": 3.325910369220975e-06,
"loss": 0.8372,
"step": 790
},
{
"epoch": 0.9721797615408132,
"grad_norm": 0.07733940581906677,
"learning_rate": 2.20897294429212e-06,
"loss": 0.8405,
"step": 795
},
{
"epoch": 0.9782940996637114,
"grad_norm": 0.07748645453278243,
"learning_rate": 1.3193858603794961e-06,
"loss": 0.8582,
"step": 800
},
{
"epoch": 0.9844084377866096,
"grad_norm": 0.07696238659021956,
"learning_rate": 6.575554083078084e-07,
"loss": 0.8446,
"step": 805
},
{
"epoch": 0.9905227759095078,
"grad_norm": 0.08299813015507701,
"learning_rate": 2.2378385824833868e-07,
"loss": 0.8424,
"step": 810
},
{
"epoch": 0.996637114032406,
"grad_norm": 0.08001939447953087,
"learning_rate": 1.8269321666375404e-08,
"loss": 0.857,
"step": 815
},
{
"epoch": 0.9990828492815653,
"eval_loss": 1.2017358541488647,
"eval_runtime": 112.3291,
"eval_samples_per_second": 186.506,
"eval_steps_per_second": 5.831,
"step": 817
},
{
"epoch": 0.9990828492815653,
"step": 817,
"total_flos": 80161328332800.0,
"train_loss": 0.9151807048767258,
"train_runtime": 1859.3287,
"train_samples_per_second": 56.289,
"train_steps_per_second": 0.439
}
],
"logging_steps": 5,
"max_steps": 817,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 80161328332800.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}