qwen25_1p5mimo_r32 / checkpoint-2600 /trainer_state.json
moyixiao's picture
Training in progress, step 2600, checkpoint
5d3cc23 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.055229142185664,
"eval_steps": 500,
"global_step": 2600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.011747430249632892,
"grad_norm": 1.5699902772903442,
"learning_rate": 0.00027,
"loss": 3.0983,
"step": 10
},
{
"epoch": 0.023494860499265784,
"grad_norm": 1.6029695272445679,
"learning_rate": 0.00029991523567092526,
"loss": 2.062,
"step": 20
},
{
"epoch": 0.03524229074889868,
"grad_norm": 1.593436360359192,
"learning_rate": 0.00029962234616583063,
"loss": 1.2074,
"step": 30
},
{
"epoch": 0.04698972099853157,
"grad_norm": 0.5851414799690247,
"learning_rate": 0.00029912069357315393,
"loss": 0.888,
"step": 40
},
{
"epoch": 0.05873715124816446,
"grad_norm": 0.25992292165756226,
"learning_rate": 0.0002984109778320875,
"loss": 0.7685,
"step": 50
},
{
"epoch": 0.07048458149779736,
"grad_norm": 0.21082307398319244,
"learning_rate": 0.00029749418918542057,
"loss": 0.7096,
"step": 60
},
{
"epoch": 0.08223201174743025,
"grad_norm": 0.16843102872371674,
"learning_rate": 0.0002963716067978866,
"loss": 0.6901,
"step": 70
},
{
"epoch": 0.09397944199706314,
"grad_norm": 0.12076722830533981,
"learning_rate": 0.000295044796971387,
"loss": 0.6702,
"step": 80
},
{
"epoch": 0.10572687224669604,
"grad_norm": 0.21371866762638092,
"learning_rate": 0.000293515610959582,
"loss": 0.6353,
"step": 90
},
{
"epoch": 0.11747430249632893,
"grad_norm": 0.13458965718746185,
"learning_rate": 0.0002917861823848985,
"loss": 0.6479,
"step": 100
},
{
"epoch": 0.12922173274596183,
"grad_norm": 0.265765517950058,
"learning_rate": 0.0002898589242615568,
"loss": 0.6244,
"step": 110
},
{
"epoch": 0.14096916299559473,
"grad_norm": 0.1473032385110855,
"learning_rate": 0.0002877365256287728,
"loss": 0.6217,
"step": 120
},
{
"epoch": 0.1527165932452276,
"grad_norm": 0.1591167151927948,
"learning_rate": 0.00028542194779883047,
"loss": 0.6022,
"step": 130
},
{
"epoch": 0.1644640234948605,
"grad_norm": 0.13270772993564606,
"learning_rate": 0.00028291842022526133,
"loss": 0.6098,
"step": 140
},
{
"epoch": 0.1762114537444934,
"grad_norm": 0.1444919854402542,
"learning_rate": 0.0002802294359968954,
"loss": 0.5971,
"step": 150
},
{
"epoch": 0.18795888399412627,
"grad_norm": 0.1571902334690094,
"learning_rate": 0.0002773587469640702,
"loss": 0.5937,
"step": 160
},
{
"epoch": 0.19970631424375918,
"grad_norm": 0.11585285514593124,
"learning_rate": 0.0002743103585037989,
"loss": 0.6054,
"step": 170
},
{
"epoch": 0.21145374449339208,
"grad_norm": 0.10303252190351486,
"learning_rate": 0.0002710885239312008,
"loss": 0.5708,
"step": 180
},
{
"epoch": 0.22320117474302498,
"grad_norm": 0.09355439245700836,
"learning_rate": 0.00026769773856499167,
"loss": 0.5806,
"step": 190
},
{
"epoch": 0.23494860499265785,
"grad_norm": 0.09288550913333893,
"learning_rate": 0.0002641427334553158,
"loss": 0.5747,
"step": 200
},
{
"epoch": 0.24669603524229075,
"grad_norm": 0.10875760763883591,
"learning_rate": 0.00026042846878266795,
"loss": 0.5879,
"step": 210
},
{
"epoch": 0.25844346549192365,
"grad_norm": 0.09756477177143097,
"learning_rate": 0.0002565601269371192,
"loss": 0.5852,
"step": 220
},
{
"epoch": 0.2701908957415565,
"grad_norm": 0.10926368832588196,
"learning_rate": 0.0002525431052874997,
"loss": 0.5605,
"step": 230
},
{
"epoch": 0.28193832599118945,
"grad_norm": 0.09802033007144928,
"learning_rate": 0.00024838300865062966,
"loss": 0.5738,
"step": 240
},
{
"epoch": 0.2936857562408223,
"grad_norm": 0.10284294933080673,
"learning_rate": 0.00024408564147110443,
"loss": 0.5847,
"step": 250
},
{
"epoch": 0.3054331864904552,
"grad_norm": 0.09890703111886978,
"learning_rate": 0.00023965699972254602,
"loss": 0.5736,
"step": 260
},
{
"epoch": 0.31718061674008813,
"grad_norm": 0.09091509878635406,
"learning_rate": 0.00023510326254162027,
"loss": 0.5577,
"step": 270
},
{
"epoch": 0.328928046989721,
"grad_norm": 0.0930003970861435,
"learning_rate": 0.00023043078360649285,
"loss": 0.5651,
"step": 280
},
{
"epoch": 0.3406754772393539,
"grad_norm": 0.0988878533244133,
"learning_rate": 0.00022564608227175316,
"loss": 0.548,
"step": 290
},
{
"epoch": 0.3524229074889868,
"grad_norm": 0.11749754101037979,
"learning_rate": 0.0002207558344721757,
"loss": 0.5587,
"step": 300
},
{
"epoch": 0.3641703377386197,
"grad_norm": 0.10936658829450607,
"learning_rate": 0.00021576686340800985,
"loss": 0.5694,
"step": 310
},
{
"epoch": 0.37591776798825255,
"grad_norm": 0.15082670748233795,
"learning_rate": 0.00021068613002479553,
"loss": 0.5688,
"step": 320
},
{
"epoch": 0.3876651982378855,
"grad_norm": 0.10255635529756546,
"learning_rate": 0.00020552072330098716,
"loss": 0.56,
"step": 330
},
{
"epoch": 0.39941262848751835,
"grad_norm": 0.10504507273435593,
"learning_rate": 0.0002002778503569374,
"loss": 0.557,
"step": 340
},
{
"epoch": 0.4111600587371512,
"grad_norm": 0.1146383211016655,
"learning_rate": 0.00019496482639904194,
"loss": 0.5497,
"step": 350
},
{
"epoch": 0.42290748898678415,
"grad_norm": 0.09596443176269531,
"learning_rate": 0.00018958906451307489,
"loss": 0.556,
"step": 360
},
{
"epoch": 0.434654919236417,
"grad_norm": 0.10395421087741852,
"learning_rate": 0.0001841580653209565,
"loss": 0.5634,
"step": 370
},
{
"epoch": 0.44640234948604995,
"grad_norm": 0.08797866106033325,
"learning_rate": 0.00017867940651538483,
"loss": 0.5544,
"step": 380
},
{
"epoch": 0.4581497797356828,
"grad_norm": 0.1006847620010376,
"learning_rate": 0.0001731607322869329,
"loss": 0.5562,
"step": 390
},
{
"epoch": 0.4698972099853157,
"grad_norm": 0.09849337488412857,
"learning_rate": 0.00016760974265836331,
"loss": 0.5477,
"step": 400
},
{
"epoch": 0.48164464023494863,
"grad_norm": 0.0988384336233139,
"learning_rate": 0.00016203418274104278,
"loss": 0.5459,
"step": 410
},
{
"epoch": 0.4933920704845815,
"grad_norm": 0.09625212848186493,
"learning_rate": 0.0001564418319284454,
"loss": 0.5516,
"step": 420
},
{
"epoch": 0.5051395007342144,
"grad_norm": 0.09705183655023575,
"learning_rate": 0.00015084049304182347,
"loss": 0.5375,
"step": 430
},
{
"epoch": 0.5168869309838473,
"grad_norm": 0.17180472612380981,
"learning_rate": 0.00014523798144319027,
"loss": 0.539,
"step": 440
},
{
"epoch": 0.5286343612334802,
"grad_norm": 0.09553302824497223,
"learning_rate": 0.00013964211413080522,
"loss": 0.5418,
"step": 450
},
{
"epoch": 0.540381791483113,
"grad_norm": 0.10648112744092941,
"learning_rate": 0.0001340606988323758,
"loss": 0.5414,
"step": 460
},
{
"epoch": 0.5521292217327459,
"grad_norm": 0.09907692670822144,
"learning_rate": 0.00012850152311119498,
"loss": 0.5353,
"step": 470
},
{
"epoch": 0.5638766519823789,
"grad_norm": 0.11162377148866653,
"learning_rate": 0.00012297234350041228,
"loss": 0.528,
"step": 480
},
{
"epoch": 0.5756240822320118,
"grad_norm": 0.10550152510404587,
"learning_rate": 0.00011748087468060128,
"loss": 0.533,
"step": 490
},
{
"epoch": 0.5873715124816447,
"grad_norm": 0.09718377143144608,
"learning_rate": 0.0001120347787157222,
"loss": 0.5409,
"step": 500
},
{
"epoch": 0.5991189427312775,
"grad_norm": 0.09185861796140671,
"learning_rate": 0.0001066416543624984,
"loss": 0.5354,
"step": 510
},
{
"epoch": 0.6108663729809104,
"grad_norm": 0.0927920788526535,
"learning_rate": 0.00010130902646812369,
"loss": 0.5454,
"step": 520
},
{
"epoch": 0.6226138032305433,
"grad_norm": 0.087093785405159,
"learning_rate": 9.604433547109344e-05,
"loss": 0.5295,
"step": 530
},
{
"epoch": 0.6343612334801763,
"grad_norm": 0.09994326531887054,
"learning_rate": 9.085492701980751e-05,
"loss": 0.5322,
"step": 540
},
{
"epoch": 0.6461086637298091,
"grad_norm": 0.09507084637880325,
"learning_rate": 8.574804172343134e-05,
"loss": 0.5224,
"step": 550
},
{
"epoch": 0.657856093979442,
"grad_norm": 0.08571015298366547,
"learning_rate": 8.07308050493148e-05,
"loss": 0.5378,
"step": 560
},
{
"epoch": 0.6696035242290749,
"grad_norm": 0.08876761794090271,
"learning_rate": 7.581021738106408e-05,
"loss": 0.5265,
"step": 570
},
{
"epoch": 0.6813509544787077,
"grad_norm": 0.09467241168022156,
"learning_rate": 7.099314425113907e-05,
"loss": 0.5392,
"step": 580
},
{
"epoch": 0.6930983847283406,
"grad_norm": 0.08804601430892944,
"learning_rate": 6.628630676160445e-05,
"loss": 0.5365,
"step": 590
},
{
"epoch": 0.7048458149779736,
"grad_norm": 0.08877623081207275,
"learning_rate": 6.169627220639871e-05,
"loss": 0.5354,
"step": 600
},
{
"epoch": 0.7165932452276065,
"grad_norm": 0.09122662246227264,
"learning_rate": 5.722944490820774e-05,
"loss": 0.5356,
"step": 610
},
{
"epoch": 0.7283406754772394,
"grad_norm": 0.08744510263204575,
"learning_rate": 5.289205728272586e-05,
"loss": 0.5424,
"step": 620
},
{
"epoch": 0.7400881057268722,
"grad_norm": 0.08927814662456512,
"learning_rate": 4.869016114277345e-05,
"loss": 0.5268,
"step": 630
},
{
"epoch": 0.7518355359765051,
"grad_norm": 0.09256933629512787,
"learning_rate": 4.462961925440341e-05,
"loss": 0.5414,
"step": 640
},
{
"epoch": 0.7635829662261381,
"grad_norm": 0.08703339844942093,
"learning_rate": 4.071609715677899e-05,
"loss": 0.5376,
"step": 650
},
{
"epoch": 0.775330396475771,
"grad_norm": 0.08876251429319382,
"learning_rate": 3.695505525723465e-05,
"loss": 0.5307,
"step": 660
},
{
"epoch": 0.7870778267254038,
"grad_norm": 0.08702490478754044,
"learning_rate": 3.3351741212551595e-05,
"loss": 0.5307,
"step": 670
},
{
"epoch": 0.7988252569750367,
"grad_norm": 0.08601511269807816,
"learning_rate": 2.9911182607076516e-05,
"loss": 0.5372,
"step": 680
},
{
"epoch": 0.8105726872246696,
"grad_norm": 0.0857272818684578,
"learning_rate": 2.663817993790021e-05,
"loss": 0.528,
"step": 690
},
{
"epoch": 0.8223201174743024,
"grad_norm": 0.08725214004516602,
"learning_rate": 2.3537299916883512e-05,
"loss": 0.5378,
"step": 700
},
{
"epoch": 0.8340675477239354,
"grad_norm": 0.0845843032002449,
"learning_rate": 2.0612869098875988e-05,
"loss": 0.5389,
"step": 710
},
{
"epoch": 0.8458149779735683,
"grad_norm": 0.08480172604322433,
"learning_rate": 1.786896784501778e-05,
"loss": 0.5244,
"step": 720
},
{
"epoch": 0.8575624082232012,
"grad_norm": 0.09265288710594177,
"learning_rate": 1.5309424629547164e-05,
"loss": 0.5403,
"step": 730
},
{
"epoch": 0.869309838472834,
"grad_norm": 0.08523637801408768,
"learning_rate": 1.2937810698057921e-05,
"loss": 0.5332,
"step": 740
},
{
"epoch": 0.8810572687224669,
"grad_norm": 0.08431612700223923,
"learning_rate": 1.0757435084658694e-05,
"loss": 0.5198,
"step": 750
},
{
"epoch": 0.8928046989720999,
"grad_norm": 0.08998807519674301,
"learning_rate": 8.771339994987953e-06,
"loss": 0.5251,
"step": 760
},
{
"epoch": 0.9045521292217328,
"grad_norm": 0.08884080499410629,
"learning_rate": 6.98229656152543e-06,
"loss": 0.5449,
"step": 770
},
{
"epoch": 0.9162995594713657,
"grad_norm": 0.08583056926727295,
"learning_rate": 5.392800977123047e-06,
"loss": 0.5264,
"step": 780
},
{
"epoch": 0.9280469897209985,
"grad_norm": 0.08824951946735382,
"learning_rate": 4.005071012149952e-06,
"loss": 0.5306,
"step": 790
},
{
"epoch": 0.9397944199706314,
"grad_norm": 0.08726619184017181,
"learning_rate": 2.821042920111427e-06,
"loss": 0.5205,
"step": 800
},
{
"epoch": 0.9515418502202643,
"grad_norm": 0.08729498088359833,
"learning_rate": 1.8423687360584137e-06,
"loss": 0.5217,
"step": 810
},
{
"epoch": 0.9632892804698973,
"grad_norm": 0.08497074991464615,
"learning_rate": 1.070413971558115e-06,
"loss": 0.534,
"step": 820
},
{
"epoch": 0.9750367107195301,
"grad_norm": 0.08497001975774765,
"learning_rate": 5.062557094410058e-07,
"loss": 0.5241,
"step": 830
},
{
"epoch": 0.986784140969163,
"grad_norm": 0.08295251429080963,
"learning_rate": 1.5068110098296338e-07,
"loss": 0.5337,
"step": 840
},
{
"epoch": 0.9985315712187959,
"grad_norm": 0.10860061645507812,
"learning_rate": 0.00022638651575377874,
"loss": 0.5227,
"step": 850
},
{
"epoch": 1.0105726872246696,
"grad_norm": 0.11796294897794724,
"learning_rate": 0.00022478592280680777,
"loss": 0.588,
"step": 860
},
{
"epoch": 1.0223201174743024,
"grad_norm": 0.1594405323266983,
"learning_rate": 0.0002231739162937319,
"loss": 0.5307,
"step": 870
},
{
"epoch": 1.0340675477239354,
"grad_norm": 0.10787333548069,
"learning_rate": 0.0002215507422333499,
"loss": 0.5359,
"step": 880
},
{
"epoch": 1.0458149779735684,
"grad_norm": 0.10763130336999893,
"learning_rate": 0.0002199166483488127,
"loss": 0.5407,
"step": 890
},
{
"epoch": 1.0575624082232011,
"grad_norm": 0.13658902049064636,
"learning_rate": 0.00021827188402981652,
"loss": 0.5255,
"step": 900
},
{
"epoch": 1.0693098384728341,
"grad_norm": 0.10522827506065369,
"learning_rate": 0.00021661670029454207,
"loss": 0.5276,
"step": 910
},
{
"epoch": 1.0810572687224669,
"grad_norm": 0.1422538459300995,
"learning_rate": 0.0002149513497513448,
"loss": 0.5245,
"step": 920
},
{
"epoch": 1.0928046989720999,
"grad_norm": 0.10326780378818512,
"learning_rate": 0.00021327608656020305,
"loss": 0.5294,
"step": 930
},
{
"epoch": 1.1045521292217328,
"grad_norm": 0.11100132018327713,
"learning_rate": 0.00021159116639392868,
"loss": 0.52,
"step": 940
},
{
"epoch": 1.1162995594713656,
"grad_norm": 0.09583411365747452,
"learning_rate": 0.00020989684639914738,
"loss": 0.5247,
"step": 950
},
{
"epoch": 1.1280469897209986,
"grad_norm": 0.10812857002019882,
"learning_rate": 0.00020819338515705378,
"loss": 0.5236,
"step": 960
},
{
"epoch": 1.1397944199706314,
"grad_norm": 0.12208293378353119,
"learning_rate": 0.00020648104264394784,
"loss": 0.5217,
"step": 970
},
{
"epoch": 1.1515418502202643,
"grad_norm": 0.11540035158395767,
"learning_rate": 0.00020476008019155794,
"loss": 0.5387,
"step": 980
},
{
"epoch": 1.1632892804698973,
"grad_norm": 0.10755149275064468,
"learning_rate": 0.00020303076044715738,
"loss": 0.5057,
"step": 990
},
{
"epoch": 1.17503671071953,
"grad_norm": 0.10145018994808197,
"learning_rate": 0.0002012933473334804,
"loss": 0.5202,
"step": 1000
},
{
"epoch": 1.186784140969163,
"grad_norm": 0.11095395684242249,
"learning_rate": 0.00019954810600844277,
"loss": 0.5314,
"step": 1010
},
{
"epoch": 1.1985315712187958,
"grad_norm": 0.097834512591362,
"learning_rate": 0.00019779530282467456,
"loss": 0.5178,
"step": 1020
},
{
"epoch": 1.2102790014684288,
"grad_norm": 0.09915532171726227,
"learning_rate": 0.00019603520528887027,
"loss": 0.5205,
"step": 1030
},
{
"epoch": 1.2220264317180616,
"grad_norm": 0.1107698306441307,
"learning_rate": 0.00019426808202096298,
"loss": 0.5268,
"step": 1040
},
{
"epoch": 1.2337738619676946,
"grad_norm": 0.11669424921274185,
"learning_rate": 0.0001924942027131284,
"loss": 0.53,
"step": 1050
},
{
"epoch": 1.2455212922173275,
"grad_norm": 0.11590099334716797,
"learning_rate": 0.00019071383808862534,
"loss": 0.5085,
"step": 1060
},
{
"epoch": 1.2572687224669603,
"grad_norm": 0.1027660220861435,
"learning_rate": 0.00018892725986047917,
"loss": 0.5193,
"step": 1070
},
{
"epoch": 1.2690161527165933,
"grad_norm": 0.09436651319265366,
"learning_rate": 0.00018713474069001354,
"loss": 0.5002,
"step": 1080
},
{
"epoch": 1.280763582966226,
"grad_norm": 0.11379121989011765,
"learning_rate": 0.00018533655414523808,
"loss": 0.5212,
"step": 1090
},
{
"epoch": 1.292511013215859,
"grad_norm": 0.09809733927249908,
"learning_rate": 0.00018353297465909717,
"loss": 0.5124,
"step": 1100
},
{
"epoch": 1.3042584434654918,
"grad_norm": 0.1027405858039856,
"learning_rate": 0.00018172427748758713,
"loss": 0.5177,
"step": 1110
},
{
"epoch": 1.3160058737151248,
"grad_norm": 0.10089763253927231,
"learning_rate": 0.0001799107386677475,
"loss": 0.4969,
"step": 1120
},
{
"epoch": 1.3277533039647578,
"grad_norm": 0.09994267672300339,
"learning_rate": 0.0001780926349755332,
"loss": 0.516,
"step": 1130
},
{
"epoch": 1.3395007342143905,
"grad_norm": 0.10974204540252686,
"learning_rate": 0.00017627024388357416,
"loss": 0.5035,
"step": 1140
},
{
"epoch": 1.3512481644640235,
"grad_norm": 0.09834876656532288,
"learning_rate": 0.00017444384351882817,
"loss": 0.5121,
"step": 1150
},
{
"epoch": 1.3629955947136563,
"grad_norm": 0.09756341576576233,
"learning_rate": 0.0001726137126201342,
"loss": 0.5289,
"step": 1160
},
{
"epoch": 1.3747430249632893,
"grad_norm": 0.09796813875436783,
"learning_rate": 0.0001707801304956723,
"loss": 0.5054,
"step": 1170
},
{
"epoch": 1.3864904552129222,
"grad_norm": 0.09447074681520462,
"learning_rate": 0.00016894337698033663,
"loss": 0.5067,
"step": 1180
},
{
"epoch": 1.398237885462555,
"grad_norm": 0.10086411237716675,
"learning_rate": 0.00016710373239302772,
"loss": 0.5191,
"step": 1190
},
{
"epoch": 1.409985315712188,
"grad_norm": 0.10048293322324753,
"learning_rate": 0.00016526147749387155,
"loss": 0.5073,
"step": 1200
},
{
"epoch": 1.4217327459618208,
"grad_norm": 0.09760654717683792,
"learning_rate": 0.00016341689344137088,
"loss": 0.5254,
"step": 1210
},
{
"epoch": 1.4334801762114537,
"grad_norm": 0.09539603441953659,
"learning_rate": 0.00016157026174949538,
"loss": 0.5116,
"step": 1220
},
{
"epoch": 1.4452276064610867,
"grad_norm": 0.09473835676908493,
"learning_rate": 0.00015972186424471855,
"loss": 0.5011,
"step": 1230
},
{
"epoch": 1.4569750367107195,
"grad_norm": 0.10754521191120148,
"learning_rate": 0.0001578719830230061,
"loss": 0.5116,
"step": 1240
},
{
"epoch": 1.4687224669603525,
"grad_norm": 0.09202101826667786,
"learning_rate": 0.00015602090040676324,
"loss": 0.4964,
"step": 1250
},
{
"epoch": 1.4804698972099852,
"grad_norm": 0.1060076653957367,
"learning_rate": 0.00015416889890174792,
"loss": 0.505,
"step": 1260
},
{
"epoch": 1.4922173274596182,
"grad_norm": 0.10437231510877609,
"learning_rate": 0.0001523162611539557,
"loss": 0.5065,
"step": 1270
},
{
"epoch": 1.5039647577092512,
"grad_norm": 0.14216673374176025,
"learning_rate": 0.0001504632699064833,
"loss": 0.5221,
"step": 1280
},
{
"epoch": 1.515712187958884,
"grad_norm": 0.10676784813404083,
"learning_rate": 0.00014861020795637716,
"loss": 0.5057,
"step": 1290
},
{
"epoch": 1.5274596182085167,
"grad_norm": 0.09706170856952667,
"learning_rate": 0.00014675735811147444,
"loss": 0.5054,
"step": 1300
},
{
"epoch": 1.5392070484581497,
"grad_norm": 0.09725037962198257,
"learning_rate": 0.00014490500314724117,
"loss": 0.5083,
"step": 1310
},
{
"epoch": 1.5509544787077827,
"grad_norm": 0.09938537329435349,
"learning_rate": 0.0001430534257636167,
"loss": 0.5157,
"step": 1320
},
{
"epoch": 1.5627019089574157,
"grad_norm": 0.10331527143716812,
"learning_rate": 0.00014120290854186863,
"loss": 0.5151,
"step": 1330
},
{
"epoch": 1.5744493392070484,
"grad_norm": 0.09629181027412415,
"learning_rate": 0.00013935373390146634,
"loss": 0.507,
"step": 1340
},
{
"epoch": 1.5861967694566812,
"grad_norm": 0.10021866858005524,
"learning_rate": 0.00013750618405697912,
"loss": 0.4973,
"step": 1350
},
{
"epoch": 1.5979441997063142,
"grad_norm": 0.10414128750562668,
"learning_rate": 0.0001356605409750058,
"loss": 0.5033,
"step": 1360
},
{
"epoch": 1.6096916299559472,
"grad_norm": 0.11649428308010101,
"learning_rate": 0.0001340013252947644,
"loss": 0.5259,
"step": 1370
},
{
"epoch": 1.6214390602055802,
"grad_norm": 0.09817013144493103,
"learning_rate": 0.00013216008080267535,
"loss": 0.5164,
"step": 1380
},
{
"epoch": 1.633186490455213,
"grad_norm": 0.10239794105291367,
"learning_rate": 0.0001303215589766901,
"loss": 0.5011,
"step": 1390
},
{
"epoch": 1.6449339207048457,
"grad_norm": 0.09663370996713638,
"learning_rate": 0.00012848604040558272,
"loss": 0.5096,
"step": 1400
},
{
"epoch": 1.6566813509544787,
"grad_norm": 0.10224564373493195,
"learning_rate": 0.0001266538052197809,
"loss": 0.5055,
"step": 1410
},
{
"epoch": 1.6684287812041116,
"grad_norm": 0.09594379365444183,
"learning_rate": 0.00012482513304861364,
"loss": 0.5051,
"step": 1420
},
{
"epoch": 1.6801762114537446,
"grad_norm": 0.10660111159086227,
"learning_rate": 0.00012300030297763518,
"loss": 0.5076,
"step": 1430
},
{
"epoch": 1.6919236417033774,
"grad_norm": 0.10405760258436203,
"learning_rate": 0.0001211795935060317,
"loss": 0.5089,
"step": 1440
},
{
"epoch": 1.7036710719530102,
"grad_norm": 0.10634606331586838,
"learning_rate": 0.00011936328250411801,
"loss": 0.504,
"step": 1450
},
{
"epoch": 1.7154185022026431,
"grad_norm": 0.1119045689702034,
"learning_rate": 0.00011755164717092988,
"loss": 0.5105,
"step": 1460
},
{
"epoch": 1.7271659324522761,
"grad_norm": 0.10727712512016296,
"learning_rate": 0.00011574496399191876,
"loss": 0.5185,
"step": 1470
},
{
"epoch": 1.738913362701909,
"grad_norm": 0.09993914514780045,
"learning_rate": 0.00011394350869675567,
"loss": 0.5004,
"step": 1480
},
{
"epoch": 1.7506607929515419,
"grad_norm": 0.10068885236978531,
"learning_rate": 0.00011214755621725042,
"loss": 0.5091,
"step": 1490
},
{
"epoch": 1.7624082232011746,
"grad_norm": 0.09819114953279495,
"learning_rate": 0.00011035738064539201,
"loss": 0.496,
"step": 1500
},
{
"epoch": 1.7741556534508076,
"grad_norm": 0.09929963946342468,
"learning_rate": 0.00010857325519151842,
"loss": 0.5033,
"step": 1510
},
{
"epoch": 1.7859030837004406,
"grad_norm": 0.09696891903877258,
"learning_rate": 0.00010679545214261935,
"loss": 0.5133,
"step": 1520
},
{
"epoch": 1.7976505139500736,
"grad_norm": 0.1030985563993454,
"learning_rate": 0.0001050242428207814,
"loss": 0.5142,
"step": 1530
},
{
"epoch": 1.8093979441997063,
"grad_norm": 0.10666483640670776,
"learning_rate": 0.0001032598975417796,
"loss": 0.5205,
"step": 1540
},
{
"epoch": 1.821145374449339,
"grad_norm": 0.1053660586476326,
"learning_rate": 0.00010150268557382262,
"loss": 0.498,
"step": 1550
},
{
"epoch": 1.832892804698972,
"grad_norm": 0.1028640866279602,
"learning_rate": 9.975287509645826e-05,
"loss": 0.5096,
"step": 1560
},
{
"epoch": 1.844640234948605,
"grad_norm": 0.10187330096960068,
"learning_rate": 9.801073315964465e-05,
"loss": 0.4961,
"step": 1570
},
{
"epoch": 1.8563876651982378,
"grad_norm": 0.0993318185210228,
"learning_rate": 9.627652564299405e-05,
"loss": 0.5028,
"step": 1580
},
{
"epoch": 1.8681350954478708,
"grad_norm": 0.11013616621494293,
"learning_rate": 9.455051721519528e-05,
"loss": 0.5011,
"step": 1590
},
{
"epoch": 1.8798825256975036,
"grad_norm": 0.10433095693588257,
"learning_rate": 9.283297129362094e-05,
"loss": 0.4977,
"step": 1600
},
{
"epoch": 1.8916299559471366,
"grad_norm": 0.10458213835954666,
"learning_rate": 9.112415000412531e-05,
"loss": 0.5107,
"step": 1610
},
{
"epoch": 1.9033773861967695,
"grad_norm": 0.10259649157524109,
"learning_rate": 8.942431414104001e-05,
"loss": 0.4994,
"step": 1620
},
{
"epoch": 1.9151248164464023,
"grad_norm": 0.09932565689086914,
"learning_rate": 8.773372312737238e-05,
"loss": 0.499,
"step": 1630
},
{
"epoch": 1.9268722466960353,
"grad_norm": 0.10920233279466629,
"learning_rate": 8.605263497521283e-05,
"loss": 0.5061,
"step": 1640
},
{
"epoch": 1.938619676945668,
"grad_norm": 0.0942125990986824,
"learning_rate": 8.438130624635852e-05,
"loss": 0.4941,
"step": 1650
},
{
"epoch": 1.950367107195301,
"grad_norm": 0.12091836333274841,
"learning_rate": 8.271999201315755e-05,
"loss": 0.499,
"step": 1660
},
{
"epoch": 1.962114537444934,
"grad_norm": 0.10680700093507767,
"learning_rate": 8.106894581958054e-05,
"loss": 0.4949,
"step": 1670
},
{
"epoch": 1.9738619676945668,
"grad_norm": 0.10140874981880188,
"learning_rate": 7.942841964252586e-05,
"loss": 0.5032,
"step": 1680
},
{
"epoch": 1.9856093979441996,
"grad_norm": 0.10470426827669144,
"learning_rate": 7.779866385336391e-05,
"loss": 0.5072,
"step": 1690
},
{
"epoch": 1.9973568281938325,
"grad_norm": 0.10490316152572632,
"learning_rate": 7.617992717972585e-05,
"loss": 0.5024,
"step": 1700
},
{
"epoch": 2.0093979441997063,
"grad_norm": 0.10185109823942184,
"learning_rate": 7.457245666754417e-05,
"loss": 0.541,
"step": 1710
},
{
"epoch": 2.0211453744493393,
"grad_norm": 0.10151582956314087,
"learning_rate": 7.297649764334912e-05,
"loss": 0.4831,
"step": 1720
},
{
"epoch": 2.0328928046989723,
"grad_norm": 0.10989069938659668,
"learning_rate": 7.139229367682778e-05,
"loss": 0.486,
"step": 1730
},
{
"epoch": 2.044640234948605,
"grad_norm": 0.11440616101026535,
"learning_rate": 6.982008654365156e-05,
"loss": 0.4842,
"step": 1740
},
{
"epoch": 2.056387665198238,
"grad_norm": 0.1018548235297203,
"learning_rate": 6.82601161885771e-05,
"loss": 0.4911,
"step": 1750
},
{
"epoch": 2.0681350954478708,
"grad_norm": 0.1053592786192894,
"learning_rate": 6.671262068882665e-05,
"loss": 0.4924,
"step": 1760
},
{
"epoch": 2.0798825256975038,
"grad_norm": 0.10619944334030151,
"learning_rate": 6.517783621775382e-05,
"loss": 0.4736,
"step": 1770
},
{
"epoch": 2.0916299559471367,
"grad_norm": 0.11708024144172668,
"learning_rate": 6.36559970087992e-05,
"loss": 0.4824,
"step": 1780
},
{
"epoch": 2.1033773861967693,
"grad_norm": 0.12601934373378754,
"learning_rate": 6.214733531974292e-05,
"loss": 0.4834,
"step": 1790
},
{
"epoch": 2.1151248164464023,
"grad_norm": 0.10728344321250916,
"learning_rate": 6.065208139725811e-05,
"loss": 0.4889,
"step": 1800
},
{
"epoch": 2.1268722466960353,
"grad_norm": 0.10394187271595001,
"learning_rate": 5.917046344177123e-05,
"loss": 0.4893,
"step": 1810
},
{
"epoch": 2.1386196769456682,
"grad_norm": 0.11126961559057236,
"learning_rate": 5.770270757263536e-05,
"loss": 0.4876,
"step": 1820
},
{
"epoch": 2.150367107195301,
"grad_norm": 0.10413071513175964,
"learning_rate": 5.624903779362031e-05,
"loss": 0.4764,
"step": 1830
},
{
"epoch": 2.1621145374449338,
"grad_norm": 0.10565336793661118,
"learning_rate": 5.480967595872602e-05,
"loss": 0.4781,
"step": 1840
},
{
"epoch": 2.1738619676945667,
"grad_norm": 0.10836539417505264,
"learning_rate": 5.338484173832413e-05,
"loss": 0.4854,
"step": 1850
},
{
"epoch": 2.1856093979441997,
"grad_norm": 0.11080804467201233,
"learning_rate": 5.197475258563249e-05,
"loss": 0.4815,
"step": 1860
},
{
"epoch": 2.1973568281938327,
"grad_norm": 0.11599951237440109,
"learning_rate": 5.057962370352815e-05,
"loss": 0.4878,
"step": 1870
},
{
"epoch": 2.2091042584434657,
"grad_norm": 0.10745177417993546,
"learning_rate": 4.91996680117041e-05,
"loss": 0.4737,
"step": 1880
},
{
"epoch": 2.2208516886930982,
"grad_norm": 0.10236770659685135,
"learning_rate": 4.783509611417409e-05,
"loss": 0.4759,
"step": 1890
},
{
"epoch": 2.232599118942731,
"grad_norm": 0.11330056935548782,
"learning_rate": 4.648611626713082e-05,
"loss": 0.4725,
"step": 1900
},
{
"epoch": 2.244346549192364,
"grad_norm": 0.10368051379919052,
"learning_rate": 4.515293434716279e-05,
"loss": 0.4872,
"step": 1910
},
{
"epoch": 2.256093979441997,
"grad_norm": 0.10511163622140884,
"learning_rate": 4.38357538198343e-05,
"loss": 0.4839,
"step": 1920
},
{
"epoch": 2.2678414096916297,
"grad_norm": 0.09937173873186111,
"learning_rate": 4.253477570863275e-05,
"loss": 0.4768,
"step": 1930
},
{
"epoch": 2.2795888399412627,
"grad_norm": 0.1072772666811943,
"learning_rate": 4.1250198564289644e-05,
"loss": 0.4915,
"step": 1940
},
{
"epoch": 2.2913362701908957,
"grad_norm": 0.11077064275741577,
"learning_rate": 3.998221843447808e-05,
"loss": 0.4773,
"step": 1950
},
{
"epoch": 2.3030837004405287,
"grad_norm": 0.10051790624856949,
"learning_rate": 3.8731028833892955e-05,
"loss": 0.4728,
"step": 1960
},
{
"epoch": 2.3148311306901617,
"grad_norm": 0.11899662017822266,
"learning_rate": 3.749682071471727e-05,
"loss": 0.4978,
"step": 1970
},
{
"epoch": 2.3265785609397946,
"grad_norm": 0.1075495257973671,
"learning_rate": 3.627978243747965e-05,
"loss": 0.491,
"step": 1980
},
{
"epoch": 2.338325991189427,
"grad_norm": 0.10509738326072693,
"learning_rate": 3.5080099742307495e-05,
"loss": 0.4672,
"step": 1990
},
{
"epoch": 2.35007342143906,
"grad_norm": 0.10816201567649841,
"learning_rate": 3.3897955720579985e-05,
"loss": 0.4856,
"step": 2000
},
{
"epoch": 2.361820851688693,
"grad_norm": 0.11207477003335953,
"learning_rate": 3.2733530786985124e-05,
"loss": 0.4893,
"step": 2010
},
{
"epoch": 2.373568281938326,
"grad_norm": 0.10209004580974579,
"learning_rate": 3.1587002651985776e-05,
"loss": 0.4737,
"step": 2020
},
{
"epoch": 2.3853157121879587,
"grad_norm": 0.11698783189058304,
"learning_rate": 3.0458546294697954e-05,
"loss": 0.4883,
"step": 2030
},
{
"epoch": 2.3970631424375917,
"grad_norm": 0.09947340935468674,
"learning_rate": 2.9348333936186003e-05,
"loss": 0.4761,
"step": 2040
},
{
"epoch": 2.4088105726872246,
"grad_norm": 0.1026497632265091,
"learning_rate": 2.82565350131791e-05,
"loss": 0.4867,
"step": 2050
},
{
"epoch": 2.4205580029368576,
"grad_norm": 0.10487735271453857,
"learning_rate": 2.718331615221218e-05,
"loss": 0.4759,
"step": 2060
},
{
"epoch": 2.4323054331864906,
"grad_norm": 0.10684232413768768,
"learning_rate": 2.61288411441961e-05,
"loss": 0.4881,
"step": 2070
},
{
"epoch": 2.444052863436123,
"grad_norm": 0.104823999106884,
"learning_rate": 2.5093270919420383e-05,
"loss": 0.4973,
"step": 2080
},
{
"epoch": 2.455800293685756,
"grad_norm": 0.10103822499513626,
"learning_rate": 2.4076763522992665e-05,
"loss": 0.4887,
"step": 2090
},
{
"epoch": 2.467547723935389,
"grad_norm": 0.10180474817752838,
"learning_rate": 2.307947409071825e-05,
"loss": 0.4791,
"step": 2100
},
{
"epoch": 2.479295154185022,
"grad_norm": 0.10081729292869568,
"learning_rate": 2.210155482542402e-05,
"loss": 0.4822,
"step": 2110
},
{
"epoch": 2.491042584434655,
"grad_norm": 0.10296090692281723,
"learning_rate": 2.1143154973729735e-05,
"loss": 0.4776,
"step": 2120
},
{
"epoch": 2.5027900146842876,
"grad_norm": 0.10592051595449448,
"learning_rate": 2.0204420803270327e-05,
"loss": 0.484,
"step": 2130
},
{
"epoch": 2.5145374449339206,
"grad_norm": 0.10436718910932541,
"learning_rate": 1.9285495580373362e-05,
"loss": 0.4741,
"step": 2140
},
{
"epoch": 2.5262848751835536,
"grad_norm": 0.10932262241840363,
"learning_rate": 1.8386519548193994e-05,
"loss": 0.4846,
"step": 2150
},
{
"epoch": 2.5380323054331866,
"grad_norm": 0.10435889661312103,
"learning_rate": 1.7507629905311644e-05,
"loss": 0.4984,
"step": 2160
},
{
"epoch": 2.5497797356828196,
"grad_norm": 0.11018865555524826,
"learning_rate": 1.664896078479126e-05,
"loss": 0.4728,
"step": 2170
},
{
"epoch": 2.561527165932452,
"grad_norm": 0.10020755231380463,
"learning_rate": 1.581064323371225e-05,
"loss": 0.4808,
"step": 2180
},
{
"epoch": 2.573274596182085,
"grad_norm": 0.10242980718612671,
"learning_rate": 1.4992805193168717e-05,
"loss": 0.483,
"step": 2190
},
{
"epoch": 2.585022026431718,
"grad_norm": 0.10522596538066864,
"learning_rate": 1.4195571478743495e-05,
"loss": 0.4798,
"step": 2200
},
{
"epoch": 2.596769456681351,
"grad_norm": 0.10111811757087708,
"learning_rate": 1.3419063761459025e-05,
"loss": 0.4758,
"step": 2210
},
{
"epoch": 2.6085168869309836,
"grad_norm": 0.10785708576440811,
"learning_rate": 1.2663400549208741e-05,
"loss": 0.4785,
"step": 2220
},
{
"epoch": 2.6202643171806166,
"grad_norm": 0.10563918203115463,
"learning_rate": 1.1928697168670465e-05,
"loss": 0.4838,
"step": 2230
},
{
"epoch": 2.6320117474302496,
"grad_norm": 0.10474205017089844,
"learning_rate": 1.1215065747705742e-05,
"loss": 0.4752,
"step": 2240
},
{
"epoch": 2.6437591776798826,
"grad_norm": 0.1004628837108612,
"learning_rate": 1.0522615198247364e-05,
"loss": 0.4812,
"step": 2250
},
{
"epoch": 2.6555066079295155,
"grad_norm": 0.10973802208900452,
"learning_rate": 9.851451199677573e-06,
"loss": 0.4984,
"step": 2260
},
{
"epoch": 2.6672540381791485,
"grad_norm": 0.0998314619064331,
"learning_rate": 9.201676182699558e-06,
"loss": 0.4908,
"step": 2270
},
{
"epoch": 2.679001468428781,
"grad_norm": 0.10704085975885391,
"learning_rate": 8.573389313704981e-06,
"loss": 0.4659,
"step": 2280
},
{
"epoch": 2.690748898678414,
"grad_norm": 0.1085141971707344,
"learning_rate": 7.966686479639428e-06,
"loss": 0.4846,
"step": 2290
},
{
"epoch": 2.702496328928047,
"grad_norm": 0.10413148999214172,
"learning_rate": 7.381660273368572e-06,
"loss": 0.4787,
"step": 2300
},
{
"epoch": 2.71424375917768,
"grad_norm": 0.10362162441015244,
"learning_rate": 6.818399979546885e-06,
"loss": 0.4793,
"step": 2310
},
{
"epoch": 2.7259911894273126,
"grad_norm": 0.11292777210474014,
"learning_rate": 6.276991560991395e-06,
"loss": 0.4861,
"step": 2320
},
{
"epoch": 2.7377386196769455,
"grad_norm": 0.10381820797920227,
"learning_rate": 5.7575176455622764e-06,
"loss": 0.4834,
"step": 2330
},
{
"epoch": 2.7494860499265785,
"grad_norm": 0.10142537951469421,
"learning_rate": 5.260057513552573e-06,
"loss": 0.4812,
"step": 2340
},
{
"epoch": 2.7612334801762115,
"grad_norm": 0.10647214204072952,
"learning_rate": 4.78468708558864e-06,
"loss": 0.4782,
"step": 2350
},
{
"epoch": 2.7729809104258445,
"grad_norm": 0.10398197919130325,
"learning_rate": 4.3314789110433675e-06,
"loss": 0.4849,
"step": 2360
},
{
"epoch": 2.7847283406754775,
"grad_norm": 0.10818745195865631,
"learning_rate": 3.90050215696408e-06,
"loss": 0.477,
"step": 2370
},
{
"epoch": 2.79647577092511,
"grad_norm": 0.10164166986942291,
"learning_rate": 3.491822597516375e-06,
"loss": 0.4788,
"step": 2380
},
{
"epoch": 2.808223201174743,
"grad_norm": 0.1044260635972023,
"learning_rate": 3.1055026039459863e-06,
"loss": 0.482,
"step": 2390
},
{
"epoch": 2.819970631424376,
"grad_norm": 0.09673094749450684,
"learning_rate": 2.741601135059851e-06,
"loss": 0.4799,
"step": 2400
},
{
"epoch": 2.831718061674009,
"grad_norm": 0.1022416204214096,
"learning_rate": 2.4001737282280055e-06,
"loss": 0.4966,
"step": 2410
},
{
"epoch": 2.8434654919236415,
"grad_norm": 0.10257957875728607,
"learning_rate": 2.081272490907765e-06,
"loss": 0.4785,
"step": 2420
},
{
"epoch": 2.8552129221732745,
"grad_norm": 0.10026570409536362,
"learning_rate": 1.784946092691153e-06,
"loss": 0.4849,
"step": 2430
},
{
"epoch": 2.8669603524229075,
"grad_norm": 0.10606394708156586,
"learning_rate": 1.5112397578771585e-06,
"loss": 0.4804,
"step": 2440
},
{
"epoch": 2.8787077826725405,
"grad_norm": 0.1049143448472023,
"learning_rate": 1.2601952585698405e-06,
"loss": 0.488,
"step": 2450
},
{
"epoch": 2.8904552129221734,
"grad_norm": 0.10490565001964569,
"learning_rate": 1.0318509083030447e-06,
"loss": 0.4713,
"step": 2460
},
{
"epoch": 2.9022026431718064,
"grad_norm": 0.10494933277368546,
"learning_rate": 8.2624155619328e-07,
"loss": 0.4845,
"step": 2470
},
{
"epoch": 2.913950073421439,
"grad_norm": 0.10932092368602753,
"learning_rate": 6.43398581621124e-07,
"loss": 0.4881,
"step": 2480
},
{
"epoch": 2.925697503671072,
"grad_norm": 0.10375595092773438,
"learning_rate": 4.833498894421528e-07,
"loss": 0.4851,
"step": 2490
},
{
"epoch": 2.937444933920705,
"grad_norm": 0.10374415665864944,
"learning_rate": 3.4611990572829815e-07,
"loss": 0.4789,
"step": 2500
},
{
"epoch": 2.9491923641703375,
"grad_norm": 0.10261189937591553,
"learning_rate": 2.317295740399294e-07,
"loss": 0.4806,
"step": 2510
},
{
"epoch": 2.9609397944199705,
"grad_norm": 0.10277044773101807,
"learning_rate": 1.4019635222961012e-07,
"loss": 0.4829,
"step": 2520
},
{
"epoch": 2.9726872246696034,
"grad_norm": 0.10454323142766953,
"learning_rate": 7.153420977766278e-08,
"loss": 0.4732,
"step": 2530
},
{
"epoch": 2.9844346549192364,
"grad_norm": 0.10006184130907059,
"learning_rate": 2.5753625660224208e-08,
"loss": 0.4826,
"step": 2540
},
{
"epoch": 2.9961820851688694,
"grad_norm": 0.10631806403398514,
"learning_rate": 2.8615867500414447e-09,
"loss": 0.4913,
"step": 2550
},
{
"epoch": 3.008225616921269,
"grad_norm": 0.11900587379932404,
"learning_rate": 0.00015,
"loss": 0.5113,
"step": 2560
},
{
"epoch": 3.0199764982373676,
"grad_norm": 0.13684682548046112,
"learning_rate": 0.00014907528274502106,
"loss": 0.5047,
"step": 2570
},
{
"epoch": 3.0317273795534665,
"grad_norm": 0.18090492486953735,
"learning_rate": 0.0001481506006338239,
"loss": 0.4978,
"step": 2580
},
{
"epoch": 3.0434782608695654,
"grad_norm": 0.13307633996009827,
"learning_rate": 0.0001472259888088545,
"loss": 0.4961,
"step": 2590
},
{
"epoch": 3.055229142185664,
"grad_norm": 0.11283300817012787,
"learning_rate": 0.00014630148240988775,
"loss": 0.4969,
"step": 2600
}
],
"logging_steps": 10,
"max_steps": 5106,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 40,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 5.510648440062738e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}