sedrickkeh's picture
End of training
1bfce01 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9991537376586743,
"eval_steps": 500,
"global_step": 1329,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.022566995768688293,
"grad_norm": 2.863170566955824,
"learning_rate": 7.462686567164179e-07,
"loss": 0.8503,
"step": 10
},
{
"epoch": 0.045133991537376586,
"grad_norm": 1.0142792486813195,
"learning_rate": 1.4925373134328358e-06,
"loss": 0.7616,
"step": 20
},
{
"epoch": 0.06770098730606489,
"grad_norm": 0.8684906705560901,
"learning_rate": 2.238805970149254e-06,
"loss": 0.7089,
"step": 30
},
{
"epoch": 0.09026798307475317,
"grad_norm": 0.8738166161325526,
"learning_rate": 2.9850746268656716e-06,
"loss": 0.6699,
"step": 40
},
{
"epoch": 0.11283497884344147,
"grad_norm": 0.68350941569959,
"learning_rate": 3.73134328358209e-06,
"loss": 0.6543,
"step": 50
},
{
"epoch": 0.13540197461212977,
"grad_norm": 0.6782468417382832,
"learning_rate": 4.477611940298508e-06,
"loss": 0.6478,
"step": 60
},
{
"epoch": 0.15796897038081806,
"grad_norm": 1.2236340684944484,
"learning_rate": 4.98811410459588e-06,
"loss": 0.6409,
"step": 70
},
{
"epoch": 0.18053596614950634,
"grad_norm": 1.0167606873907598,
"learning_rate": 4.948494453248812e-06,
"loss": 0.6406,
"step": 80
},
{
"epoch": 0.20310296191819463,
"grad_norm": 0.9537894238044289,
"learning_rate": 4.908874801901744e-06,
"loss": 0.6363,
"step": 90
},
{
"epoch": 0.22566995768688294,
"grad_norm": 0.7877279594502249,
"learning_rate": 4.8692551505546756e-06,
"loss": 0.6342,
"step": 100
},
{
"epoch": 0.24823695345557123,
"grad_norm": 0.6144739658197168,
"learning_rate": 4.829635499207607e-06,
"loss": 0.6241,
"step": 110
},
{
"epoch": 0.27080394922425954,
"grad_norm": 0.5714964033743125,
"learning_rate": 4.790015847860539e-06,
"loss": 0.6228,
"step": 120
},
{
"epoch": 0.2933709449929478,
"grad_norm": 0.6554886570548089,
"learning_rate": 4.750396196513471e-06,
"loss": 0.6235,
"step": 130
},
{
"epoch": 0.3159379407616361,
"grad_norm": 0.7757691264505117,
"learning_rate": 4.710776545166403e-06,
"loss": 0.618,
"step": 140
},
{
"epoch": 0.3385049365303244,
"grad_norm": 0.6722094607751704,
"learning_rate": 4.671156893819335e-06,
"loss": 0.618,
"step": 150
},
{
"epoch": 0.3610719322990127,
"grad_norm": 0.6071748856670994,
"learning_rate": 4.6315372424722664e-06,
"loss": 0.6199,
"step": 160
},
{
"epoch": 0.383638928067701,
"grad_norm": 0.6782846350559801,
"learning_rate": 4.591917591125198e-06,
"loss": 0.6156,
"step": 170
},
{
"epoch": 0.40620592383638926,
"grad_norm": 0.6054491230325086,
"learning_rate": 4.55229793977813e-06,
"loss": 0.612,
"step": 180
},
{
"epoch": 0.4287729196050776,
"grad_norm": 0.5629664740904267,
"learning_rate": 4.512678288431062e-06,
"loss": 0.6062,
"step": 190
},
{
"epoch": 0.4513399153737659,
"grad_norm": 0.6088703924978586,
"learning_rate": 4.473058637083994e-06,
"loss": 0.6126,
"step": 200
},
{
"epoch": 0.47390691114245415,
"grad_norm": 0.5575536173462763,
"learning_rate": 4.4334389857369255e-06,
"loss": 0.6089,
"step": 210
},
{
"epoch": 0.49647390691114246,
"grad_norm": 0.6222877409919465,
"learning_rate": 4.393819334389858e-06,
"loss": 0.6005,
"step": 220
},
{
"epoch": 0.5190409026798307,
"grad_norm": 0.6116552913748422,
"learning_rate": 4.35419968304279e-06,
"loss": 0.6092,
"step": 230
},
{
"epoch": 0.5416078984485191,
"grad_norm": 0.6223323168638546,
"learning_rate": 4.314580031695722e-06,
"loss": 0.6078,
"step": 240
},
{
"epoch": 0.5641748942172073,
"grad_norm": 0.6096698662971849,
"learning_rate": 4.274960380348654e-06,
"loss": 0.6019,
"step": 250
},
{
"epoch": 0.5867418899858956,
"grad_norm": 0.6285075076711258,
"learning_rate": 4.235340729001585e-06,
"loss": 0.6045,
"step": 260
},
{
"epoch": 0.609308885754584,
"grad_norm": 0.6627050692979386,
"learning_rate": 4.195721077654517e-06,
"loss": 0.5998,
"step": 270
},
{
"epoch": 0.6318758815232722,
"grad_norm": 0.555386708198133,
"learning_rate": 4.156101426307449e-06,
"loss": 0.6062,
"step": 280
},
{
"epoch": 0.6544428772919605,
"grad_norm": 0.580318377315189,
"learning_rate": 4.116481774960381e-06,
"loss": 0.5995,
"step": 290
},
{
"epoch": 0.6770098730606487,
"grad_norm": 0.6230855644802704,
"learning_rate": 4.076862123613313e-06,
"loss": 0.6056,
"step": 300
},
{
"epoch": 0.6995768688293371,
"grad_norm": 0.5651082946111645,
"learning_rate": 4.0372424722662445e-06,
"loss": 0.5987,
"step": 310
},
{
"epoch": 0.7221438645980254,
"grad_norm": 0.5226787552110314,
"learning_rate": 3.997622820919176e-06,
"loss": 0.6019,
"step": 320
},
{
"epoch": 0.7447108603667136,
"grad_norm": 0.5442970886927759,
"learning_rate": 3.958003169572108e-06,
"loss": 0.5973,
"step": 330
},
{
"epoch": 0.767277856135402,
"grad_norm": 0.5598487375551561,
"learning_rate": 3.91838351822504e-06,
"loss": 0.5967,
"step": 340
},
{
"epoch": 0.7898448519040903,
"grad_norm": 0.5733391522244953,
"learning_rate": 3.878763866877972e-06,
"loss": 0.598,
"step": 350
},
{
"epoch": 0.8124118476727785,
"grad_norm": 0.6773102617007167,
"learning_rate": 3.8391442155309035e-06,
"loss": 0.597,
"step": 360
},
{
"epoch": 0.8349788434414669,
"grad_norm": 0.5940797885379248,
"learning_rate": 3.7995245641838358e-06,
"loss": 0.604,
"step": 370
},
{
"epoch": 0.8575458392101551,
"grad_norm": 0.5786293369264021,
"learning_rate": 3.7599049128367676e-06,
"loss": 0.6005,
"step": 380
},
{
"epoch": 0.8801128349788434,
"grad_norm": 0.5801103398635734,
"learning_rate": 3.720285261489699e-06,
"loss": 0.5946,
"step": 390
},
{
"epoch": 0.9026798307475318,
"grad_norm": 0.5750375316989407,
"learning_rate": 3.6806656101426308e-06,
"loss": 0.5967,
"step": 400
},
{
"epoch": 0.92524682651622,
"grad_norm": 0.5775359048430772,
"learning_rate": 3.6410459587955626e-06,
"loss": 0.5946,
"step": 410
},
{
"epoch": 0.9478138222849083,
"grad_norm": 0.6077368982806889,
"learning_rate": 3.6014263074484944e-06,
"loss": 0.5951,
"step": 420
},
{
"epoch": 0.9703808180535967,
"grad_norm": 0.5688170834677694,
"learning_rate": 3.561806656101426e-06,
"loss": 0.5891,
"step": 430
},
{
"epoch": 0.9929478138222849,
"grad_norm": 0.602208853320174,
"learning_rate": 3.5221870047543584e-06,
"loss": 0.5938,
"step": 440
},
{
"epoch": 0.9997179125528914,
"eval_loss": 0.591905951499939,
"eval_runtime": 686.9043,
"eval_samples_per_second": 17.384,
"eval_steps_per_second": 0.544,
"step": 443
},
{
"epoch": 1.0155148095909732,
"grad_norm": 0.6726743690859625,
"learning_rate": 3.4825673534072902e-06,
"loss": 0.6072,
"step": 450
},
{
"epoch": 1.0380818053596614,
"grad_norm": 0.5962043484661436,
"learning_rate": 3.442947702060222e-06,
"loss": 0.5365,
"step": 460
},
{
"epoch": 1.0606488011283497,
"grad_norm": 0.586875220271223,
"learning_rate": 3.403328050713154e-06,
"loss": 0.5512,
"step": 470
},
{
"epoch": 1.0832157968970382,
"grad_norm": 0.621068104302263,
"learning_rate": 3.3637083993660857e-06,
"loss": 0.5388,
"step": 480
},
{
"epoch": 1.1057827926657264,
"grad_norm": 0.6037913432633323,
"learning_rate": 3.3240887480190175e-06,
"loss": 0.5492,
"step": 490
},
{
"epoch": 1.1283497884344147,
"grad_norm": 0.5592011230421303,
"learning_rate": 3.2844690966719493e-06,
"loss": 0.5475,
"step": 500
},
{
"epoch": 1.150916784203103,
"grad_norm": 0.5685964914856751,
"learning_rate": 3.244849445324881e-06,
"loss": 0.5481,
"step": 510
},
{
"epoch": 1.1734837799717912,
"grad_norm": 0.5535668718773792,
"learning_rate": 3.2052297939778134e-06,
"loss": 0.5405,
"step": 520
},
{
"epoch": 1.1960507757404795,
"grad_norm": 0.5636565369750155,
"learning_rate": 3.165610142630745e-06,
"loss": 0.546,
"step": 530
},
{
"epoch": 1.2186177715091677,
"grad_norm": 0.6049380586496252,
"learning_rate": 3.125990491283677e-06,
"loss": 0.5435,
"step": 540
},
{
"epoch": 1.2411847672778562,
"grad_norm": 0.6016747310367478,
"learning_rate": 3.086370839936609e-06,
"loss": 0.5483,
"step": 550
},
{
"epoch": 1.2637517630465445,
"grad_norm": 0.6176382234535089,
"learning_rate": 3.0467511885895406e-06,
"loss": 0.5497,
"step": 560
},
{
"epoch": 1.2863187588152327,
"grad_norm": 0.5774937087084417,
"learning_rate": 3.0071315372424724e-06,
"loss": 0.5467,
"step": 570
},
{
"epoch": 1.308885754583921,
"grad_norm": 0.5984064393180869,
"learning_rate": 2.9675118858954042e-06,
"loss": 0.5467,
"step": 580
},
{
"epoch": 1.3314527503526092,
"grad_norm": 0.5636068266127684,
"learning_rate": 2.9278922345483365e-06,
"loss": 0.5464,
"step": 590
},
{
"epoch": 1.3540197461212977,
"grad_norm": 0.5797861372555536,
"learning_rate": 2.8882725832012683e-06,
"loss": 0.5518,
"step": 600
},
{
"epoch": 1.376586741889986,
"grad_norm": 0.5699674712165612,
"learning_rate": 2.8486529318542e-06,
"loss": 0.5439,
"step": 610
},
{
"epoch": 1.3991537376586742,
"grad_norm": 0.5738925929277279,
"learning_rate": 2.809033280507132e-06,
"loss": 0.5482,
"step": 620
},
{
"epoch": 1.4217207334273625,
"grad_norm": 0.5558394841428566,
"learning_rate": 2.7694136291600637e-06,
"loss": 0.5459,
"step": 630
},
{
"epoch": 1.4442877291960508,
"grad_norm": 0.5593578549382234,
"learning_rate": 2.7297939778129955e-06,
"loss": 0.5454,
"step": 640
},
{
"epoch": 1.466854724964739,
"grad_norm": 0.6008446398868655,
"learning_rate": 2.6901743264659273e-06,
"loss": 0.5462,
"step": 650
},
{
"epoch": 1.4894217207334273,
"grad_norm": 0.6469908856500797,
"learning_rate": 2.650554675118859e-06,
"loss": 0.5496,
"step": 660
},
{
"epoch": 1.5119887165021155,
"grad_norm": 0.5884734659854615,
"learning_rate": 2.6109350237717914e-06,
"loss": 0.5446,
"step": 670
},
{
"epoch": 1.5345557122708038,
"grad_norm": 0.5672090998680375,
"learning_rate": 2.571315372424723e-06,
"loss": 0.5385,
"step": 680
},
{
"epoch": 1.5571227080394923,
"grad_norm": 0.5974082469537848,
"learning_rate": 2.531695721077655e-06,
"loss": 0.5403,
"step": 690
},
{
"epoch": 1.5796897038081805,
"grad_norm": 0.5739321175372246,
"learning_rate": 2.4920760697305864e-06,
"loss": 0.5444,
"step": 700
},
{
"epoch": 1.6022566995768688,
"grad_norm": 0.8132053089517468,
"learning_rate": 2.452456418383518e-06,
"loss": 0.547,
"step": 710
},
{
"epoch": 1.6248236953455573,
"grad_norm": 0.5611312889106296,
"learning_rate": 2.4128367670364504e-06,
"loss": 0.5549,
"step": 720
},
{
"epoch": 1.6473906911142455,
"grad_norm": 0.5791359972267569,
"learning_rate": 2.3732171156893823e-06,
"loss": 0.538,
"step": 730
},
{
"epoch": 1.6699576868829338,
"grad_norm": 0.5814345186044484,
"learning_rate": 2.333597464342314e-06,
"loss": 0.5536,
"step": 740
},
{
"epoch": 1.692524682651622,
"grad_norm": 0.5624703263810815,
"learning_rate": 2.293977812995246e-06,
"loss": 0.5448,
"step": 750
},
{
"epoch": 1.7150916784203103,
"grad_norm": 1.867941174224022,
"learning_rate": 2.2543581616481777e-06,
"loss": 0.5436,
"step": 760
},
{
"epoch": 1.7376586741889986,
"grad_norm": 0.5358650029316937,
"learning_rate": 2.2147385103011095e-06,
"loss": 0.5442,
"step": 770
},
{
"epoch": 1.7602256699576868,
"grad_norm": 0.5719206405479228,
"learning_rate": 2.1751188589540413e-06,
"loss": 0.5401,
"step": 780
},
{
"epoch": 1.782792665726375,
"grad_norm": 0.5453893729749778,
"learning_rate": 2.135499207606973e-06,
"loss": 0.5433,
"step": 790
},
{
"epoch": 1.8053596614950633,
"grad_norm": 0.5632958967357027,
"learning_rate": 2.0958795562599054e-06,
"loss": 0.5382,
"step": 800
},
{
"epoch": 1.8279266572637518,
"grad_norm": 0.5314143844009186,
"learning_rate": 2.056259904912837e-06,
"loss": 0.5488,
"step": 810
},
{
"epoch": 1.85049365303244,
"grad_norm": 0.5357056509168667,
"learning_rate": 2.016640253565769e-06,
"loss": 0.5359,
"step": 820
},
{
"epoch": 1.8730606488011283,
"grad_norm": 0.5376264698310887,
"learning_rate": 1.9770206022187004e-06,
"loss": 0.5479,
"step": 830
},
{
"epoch": 1.8956276445698168,
"grad_norm": 0.547941092343902,
"learning_rate": 1.937400950871632e-06,
"loss": 0.548,
"step": 840
},
{
"epoch": 1.918194640338505,
"grad_norm": 0.5657397015384529,
"learning_rate": 1.8977812995245642e-06,
"loss": 0.5353,
"step": 850
},
{
"epoch": 1.9407616361071933,
"grad_norm": 0.5386418315790085,
"learning_rate": 1.858161648177496e-06,
"loss": 0.5404,
"step": 860
},
{
"epoch": 1.9633286318758816,
"grad_norm": 0.5476830108115235,
"learning_rate": 1.818541996830428e-06,
"loss": 0.5469,
"step": 870
},
{
"epoch": 1.9858956276445698,
"grad_norm": 0.5490628587056525,
"learning_rate": 1.7789223454833599e-06,
"loss": 0.5447,
"step": 880
},
{
"epoch": 1.9994358251057829,
"eval_loss": 0.5841004252433777,
"eval_runtime": 686.5509,
"eval_samples_per_second": 17.393,
"eval_steps_per_second": 0.545,
"step": 886
},
{
"epoch": 2.008462623413258,
"grad_norm": 0.8053636155718226,
"learning_rate": 1.7393026941362917e-06,
"loss": 0.5767,
"step": 890
},
{
"epoch": 2.0310296191819464,
"grad_norm": 0.5735363517466061,
"learning_rate": 1.6996830427892235e-06,
"loss": 0.5017,
"step": 900
},
{
"epoch": 2.0535966149506346,
"grad_norm": 0.5772677785164054,
"learning_rate": 1.6600633914421555e-06,
"loss": 0.5043,
"step": 910
},
{
"epoch": 2.076163610719323,
"grad_norm": 0.549936789056863,
"learning_rate": 1.6204437400950873e-06,
"loss": 0.4963,
"step": 920
},
{
"epoch": 2.098730606488011,
"grad_norm": 0.5634393121057476,
"learning_rate": 1.5808240887480191e-06,
"loss": 0.5033,
"step": 930
},
{
"epoch": 2.1212976022566994,
"grad_norm": 0.5731016432065377,
"learning_rate": 1.541204437400951e-06,
"loss": 0.507,
"step": 940
},
{
"epoch": 2.143864598025388,
"grad_norm": 0.5789375591878266,
"learning_rate": 1.501584786053883e-06,
"loss": 0.5081,
"step": 950
},
{
"epoch": 2.1664315937940763,
"grad_norm": 0.5694386854589488,
"learning_rate": 1.4619651347068148e-06,
"loss": 0.5042,
"step": 960
},
{
"epoch": 2.1889985895627646,
"grad_norm": 0.5481525726151266,
"learning_rate": 1.4223454833597466e-06,
"loss": 0.5009,
"step": 970
},
{
"epoch": 2.211565585331453,
"grad_norm": 0.5695713582701112,
"learning_rate": 1.3827258320126786e-06,
"loss": 0.4953,
"step": 980
},
{
"epoch": 2.234132581100141,
"grad_norm": 0.552689038377049,
"learning_rate": 1.3431061806656104e-06,
"loss": 0.4948,
"step": 990
},
{
"epoch": 2.2566995768688294,
"grad_norm": 0.5719371883341671,
"learning_rate": 1.303486529318542e-06,
"loss": 0.5043,
"step": 1000
},
{
"epoch": 2.2792665726375176,
"grad_norm": 0.5655546811881795,
"learning_rate": 1.2638668779714738e-06,
"loss": 0.51,
"step": 1010
},
{
"epoch": 2.301833568406206,
"grad_norm": 0.5754609713473701,
"learning_rate": 1.2242472266244059e-06,
"loss": 0.5038,
"step": 1020
},
{
"epoch": 2.324400564174894,
"grad_norm": 0.5844870653050052,
"learning_rate": 1.1846275752773377e-06,
"loss": 0.5079,
"step": 1030
},
{
"epoch": 2.3469675599435824,
"grad_norm": 0.5438906909333213,
"learning_rate": 1.1450079239302695e-06,
"loss": 0.505,
"step": 1040
},
{
"epoch": 2.3695345557122707,
"grad_norm": 0.5491770359380203,
"learning_rate": 1.1053882725832013e-06,
"loss": 0.5022,
"step": 1050
},
{
"epoch": 2.392101551480959,
"grad_norm": 0.5250630294662261,
"learning_rate": 1.0657686212361331e-06,
"loss": 0.5014,
"step": 1060
},
{
"epoch": 2.414668547249647,
"grad_norm": 0.5504767727997151,
"learning_rate": 1.0261489698890651e-06,
"loss": 0.5016,
"step": 1070
},
{
"epoch": 2.4372355430183354,
"grad_norm": 0.5687924913757153,
"learning_rate": 9.86529318541997e-07,
"loss": 0.5053,
"step": 1080
},
{
"epoch": 2.459802538787024,
"grad_norm": 0.5279683089182464,
"learning_rate": 9.469096671949288e-07,
"loss": 0.5032,
"step": 1090
},
{
"epoch": 2.4823695345557124,
"grad_norm": 0.556251527422648,
"learning_rate": 9.072900158478607e-07,
"loss": 0.5058,
"step": 1100
},
{
"epoch": 2.5049365303244007,
"grad_norm": 0.5422440346045919,
"learning_rate": 8.676703645007925e-07,
"loss": 0.5088,
"step": 1110
},
{
"epoch": 2.527503526093089,
"grad_norm": 0.5309924695301984,
"learning_rate": 8.280507131537244e-07,
"loss": 0.4985,
"step": 1120
},
{
"epoch": 2.550070521861777,
"grad_norm": 0.5390842566603322,
"learning_rate": 7.884310618066561e-07,
"loss": 0.5035,
"step": 1130
},
{
"epoch": 2.5726375176304654,
"grad_norm": 0.5440422875041593,
"learning_rate": 7.488114104595879e-07,
"loss": 0.5015,
"step": 1140
},
{
"epoch": 2.5952045133991537,
"grad_norm": 0.5420045233161901,
"learning_rate": 7.091917591125198e-07,
"loss": 0.5019,
"step": 1150
},
{
"epoch": 2.617771509167842,
"grad_norm": 0.5306061046553697,
"learning_rate": 6.695721077654517e-07,
"loss": 0.5054,
"step": 1160
},
{
"epoch": 2.64033850493653,
"grad_norm": 0.5264381405098679,
"learning_rate": 6.299524564183836e-07,
"loss": 0.4938,
"step": 1170
},
{
"epoch": 2.6629055007052185,
"grad_norm": 0.5384467501061415,
"learning_rate": 5.903328050713154e-07,
"loss": 0.5049,
"step": 1180
},
{
"epoch": 2.685472496473907,
"grad_norm": 0.5376062383214052,
"learning_rate": 5.507131537242473e-07,
"loss": 0.5054,
"step": 1190
},
{
"epoch": 2.7080394922425954,
"grad_norm": 0.5331042555195942,
"learning_rate": 5.110935023771791e-07,
"loss": 0.5036,
"step": 1200
},
{
"epoch": 2.7306064880112837,
"grad_norm": 0.543912548569607,
"learning_rate": 4.71473851030111e-07,
"loss": 0.5043,
"step": 1210
},
{
"epoch": 2.753173483779972,
"grad_norm": 0.5349643652738619,
"learning_rate": 4.3185419968304285e-07,
"loss": 0.5006,
"step": 1220
},
{
"epoch": 2.77574047954866,
"grad_norm": 0.5238224036950911,
"learning_rate": 3.922345483359747e-07,
"loss": 0.5075,
"step": 1230
},
{
"epoch": 2.7983074753173485,
"grad_norm": 0.5253657530587171,
"learning_rate": 3.5261489698890647e-07,
"loss": 0.5057,
"step": 1240
},
{
"epoch": 2.8208744710860367,
"grad_norm": 0.5258908564351523,
"learning_rate": 3.129952456418384e-07,
"loss": 0.5053,
"step": 1250
},
{
"epoch": 2.843441466854725,
"grad_norm": 0.5469617628875234,
"learning_rate": 2.7337559429477025e-07,
"loss": 0.5069,
"step": 1260
},
{
"epoch": 2.8660084626234132,
"grad_norm": 0.5159024487279192,
"learning_rate": 2.3375594294770207e-07,
"loss": 0.504,
"step": 1270
},
{
"epoch": 2.8885754583921015,
"grad_norm": 0.5160343456448424,
"learning_rate": 1.9413629160063393e-07,
"loss": 0.5014,
"step": 1280
},
{
"epoch": 2.9111424541607898,
"grad_norm": 0.5216209520835643,
"learning_rate": 1.5451664025356577e-07,
"loss": 0.5053,
"step": 1290
},
{
"epoch": 2.933709449929478,
"grad_norm": 0.5227114231383605,
"learning_rate": 1.1489698890649763e-07,
"loss": 0.5003,
"step": 1300
},
{
"epoch": 2.9562764456981663,
"grad_norm": 0.6046731154894333,
"learning_rate": 7.527733755942949e-08,
"loss": 0.5043,
"step": 1310
},
{
"epoch": 2.9788434414668545,
"grad_norm": 0.5222846946950428,
"learning_rate": 3.565768621236134e-08,
"loss": 0.4998,
"step": 1320
},
{
"epoch": 2.9991537376586743,
"eval_loss": 0.5896643400192261,
"eval_runtime": 687.6245,
"eval_samples_per_second": 17.366,
"eval_steps_per_second": 0.544,
"step": 1329
},
{
"epoch": 2.9991537376586743,
"step": 1329,
"total_flos": 5064195066298368.0,
"train_loss": 0.5577808463367149,
"train_runtime": 120872.8154,
"train_samples_per_second": 5.631,
"train_steps_per_second": 0.011
}
],
"logging_steps": 10,
"max_steps": 1329,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5064195066298368.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}