Omni-Edu-27B / trainer_state.json
lhpku20010120's picture tunaaa126's picture
add OmniEdu-27B (#1)
4b4a188
Raw History Blame Contribute Delete
22.7 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 1173,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02560819462227913,
"grad_norm": 153.27353844409606,
"learning_rate": 3.813559322033899e-07,
"loss": 3.8572372436523437,
"step": 10
},
{
"epoch": 0.05121638924455826,
"grad_norm": 62.84922969850834,
"learning_rate": 8.050847457627118e-07,
"loss": 2.2734893798828124,
"step": 20
},
{
"epoch": 0.07682458386683738,
"grad_norm": 3.769755503119313,
"learning_rate": 1.228813559322034e-06,
"loss": 1.0895769119262695,
"step": 30
},
{
"epoch": 0.10243277848911651,
"grad_norm": 3.768827465389587,
"learning_rate": 1.652542372881356e-06,
"loss": 0.8416604995727539,
"step": 40
},
{
"epoch": 0.12804097311139565,
"grad_norm": 2.969249061223776,
"learning_rate": 2.076271186440678e-06,
"loss": 0.8005556106567383,
"step": 50
},
{
"epoch": 0.15364916773367476,
"grad_norm": 2.7063121167829647,
"learning_rate": 2.5e-06,
"loss": 0.7322915077209473,
"step": 60
},
{
"epoch": 0.1792573623559539,
"grad_norm": 2.688546185338879,
"learning_rate": 2.9237288135593224e-06,
"loss": 0.7061005592346191,
"step": 70
},
{
"epoch": 0.20486555697823303,
"grad_norm": 2.3050951641216195,
"learning_rate": 3.347457627118644e-06,
"loss": 0.6749155521392822,
"step": 80
},
{
"epoch": 0.23047375160051217,
"grad_norm": 2.397583668512051,
"learning_rate": 3.7711864406779664e-06,
"loss": 0.6868059635162354,
"step": 90
},
{
"epoch": 0.2560819462227913,
"grad_norm": 2.1188614813401947,
"learning_rate": 4.1949152542372886e-06,
"loss": 0.6494926452636719,
"step": 100
},
{
"epoch": 0.28169014084507044,
"grad_norm": 1.9182639067325302,
"learning_rate": 4.618644067796611e-06,
"loss": 0.6528633117675782,
"step": 110
},
{
"epoch": 0.3072983354673495,
"grad_norm": 2.3510511774564984,
"learning_rate": 4.999988915795796e-06,
"loss": 0.6406693935394288,
"step": 120
},
{
"epoch": 0.33290653008962867,
"grad_norm": 1.7556549500773726,
"learning_rate": 4.998658930215192e-06,
"loss": 0.6446515083312988,
"step": 130
},
{
"epoch": 0.3585147247119078,
"grad_norm": 1.9426400389564613,
"learning_rate": 4.995113455052006e-06,
"loss": 0.6290643692016602,
"step": 140
},
{
"epoch": 0.38412291933418696,
"grad_norm": 1.7703216191172428,
"learning_rate": 4.989355633977907e-06,
"loss": 0.6318723201751709,
"step": 150
},
{
"epoch": 0.40973111395646605,
"grad_norm": 2.016415622632667,
"learning_rate": 4.98139057228856e-06,
"loss": 0.6556029319763184,
"step": 160
},
{
"epoch": 0.4353393085787452,
"grad_norm": 1.5699072387850665,
"learning_rate": 4.971225332376911e-06,
"loss": 0.63431396484375,
"step": 170
},
{
"epoch": 0.46094750320102434,
"grad_norm": 2.239251081154673,
"learning_rate": 4.958868927471157e-06,
"loss": 0.6408280849456787,
"step": 180
},
{
"epoch": 0.48655569782330343,
"grad_norm": 2.0878104001839146,
"learning_rate": 4.9443323136429785e-06,
"loss": 0.6308846950531006,
"step": 190
},
{
"epoch": 0.5121638924455826,
"grad_norm": 2.2472375041536004,
"learning_rate": 4.927628380093106e-06,
"loss": 0.615133810043335,
"step": 200
},
{
"epoch": 0.5377720870678617,
"grad_norm": 2.004422315809482,
"learning_rate": 4.908771937722826e-06,
"loss": 0.6189337253570557,
"step": 210
},
{
"epoch": 0.5633802816901409,
"grad_norm": 1.6889300859400525,
"learning_rate": 4.887779706001584e-06,
"loss": 0.6117790699005127,
"step": 220
},
{
"epoch": 0.58898847631242,
"grad_norm": 1.9793492599080436,
"learning_rate": 4.864670298142303e-06,
"loss": 0.6184802055358887,
"step": 230
},
{
"epoch": 0.614596670934699,
"grad_norm": 2.5379805741664474,
"learning_rate": 4.839464204597583e-06,
"loss": 0.6326601028442382,
"step": 240
},
{
"epoch": 0.6402048655569782,
"grad_norm": 1.9814471712083004,
"learning_rate": 4.812183774891399e-06,
"loss": 0.6044825553894043,
"step": 250
},
{
"epoch": 0.6658130601792573,
"grad_norm": 1.8113978894906593,
"learning_rate": 4.782853197802417e-06,
"loss": 0.5929990768432617,
"step": 260
},
{
"epoch": 0.6914212548015365,
"grad_norm": 3.1268021252532368,
"learning_rate": 4.751498479916491e-06,
"loss": 0.6360932350158691,
"step": 270
},
{
"epoch": 0.7170294494238156,
"grad_norm": 1.9250603910066866,
"learning_rate": 4.718147422567369e-06,
"loss": 0.6308783531188965,
"step": 280
},
{
"epoch": 0.7426376440460948,
"grad_norm": 5.456601410435929,
"learning_rate": 4.682829597186042e-06,
"loss": 0.603580093383789,
"step": 290
},
{
"epoch": 0.7682458386683739,
"grad_norm": 2.635604582868932,
"learning_rate": 4.645576319080602e-06,
"loss": 0.5843267917633057,
"step": 300
},
{
"epoch": 0.793854033290653,
"grad_norm": 1.637348960037048,
"learning_rate": 4.6064206196698455e-06,
"loss": 0.6101377010345459,
"step": 310
},
{
"epoch": 0.8194622279129321,
"grad_norm": 1.9754353692781474,
"learning_rate": 4.565397217195265e-06,
"loss": 0.6075271606445313,
"step": 320
},
{
"epoch": 0.8450704225352113,
"grad_norm": 1.9177531304969357,
"learning_rate": 4.522542485937369e-06,
"loss": 0.5996335029602051,
"step": 330
},
{
"epoch": 0.8706786171574904,
"grad_norm": 1.6323748268838112,
"learning_rate": 4.477894423963649e-06,
"loss": 0.6118486404418946,
"step": 340
},
{
"epoch": 0.8962868117797695,
"grad_norm": 3.2851900535885825,
"learning_rate": 4.431492619436773e-06,
"loss": 0.5790205478668213,
"step": 350
},
{
"epoch": 0.9218950064020487,
"grad_norm": 1.3826502268499234,
"learning_rate": 4.383378215512897e-06,
"loss": 0.5924504280090332,
"step": 360
},
{
"epoch": 0.9475032010243278,
"grad_norm": 1.7371358238499215,
"learning_rate": 4.3335938738611975e-06,
"loss": 0.5803703308105469,
"step": 370
},
{
"epoch": 0.9731113956466069,
"grad_norm": 1.6403188302203746,
"learning_rate": 4.282183736836986e-06,
"loss": 0.5972010612487793,
"step": 380
},
{
"epoch": 0.998719590268886,
"grad_norm": 1.7967294815797543,
"learning_rate": 4.2291933883419475e-06,
"loss": 0.58817458152771,
"step": 390
},
{
"epoch": 1.0230473751600513,
"grad_norm": 1.2748852269941406,
"learning_rate": 4.174669813406193e-06,
"loss": 0.45647602081298827,
"step": 400
},
{
"epoch": 1.0486555697823303,
"grad_norm": 1.7376323194697032,
"learning_rate": 4.1186613565279676e-06,
"loss": 0.4439413547515869,
"step": 410
},
{
"epoch": 1.0742637644046096,
"grad_norm": 128.16545373945706,
"learning_rate": 4.061217678807974e-06,
"loss": 0.4280103206634521,
"step": 420
},
{
"epoch": 1.0998719590268886,
"grad_norm": 2.4950762574929937,
"learning_rate": 4.002389713916284e-06,
"loss": 0.40707979202270506,
"step": 430
},
{
"epoch": 1.1254801536491676,
"grad_norm": 1.8159106917780825,
"learning_rate": 3.942229622930907e-06,
"loss": 0.427966833114624,
"step": 440
},
{
"epoch": 1.151088348271447,
"grad_norm": 1.3816936430810876,
"learning_rate": 3.880790748088056e-06,
"loss": 0.41638803482055664,
"step": 450
},
{
"epoch": 1.176696542893726,
"grad_norm": 2.094197479970244,
"learning_rate": 3.8181275654851016e-06,
"loss": 0.43572521209716797,
"step": 460
},
{
"epoch": 1.2023047375160052,
"grad_norm": 1.9555639459737928,
"learning_rate": 3.7542956367781734e-06,
"loss": 0.41444945335388184,
"step": 470
},
{
"epoch": 1.2279129321382842,
"grad_norm": 1.4337283127736087,
"learning_rate": 3.689351559917227e-06,
"loss": 0.4294303894042969,
"step": 480
},
{
"epoch": 1.2535211267605635,
"grad_norm": 2.0361282406298375,
"learning_rate": 3.6233529189622536e-06,
"loss": 0.43240156173706057,
"step": 490
},
{
"epoch": 1.2791293213828425,
"grad_norm": 1.9209819867622855,
"learning_rate": 3.556358233025138e-06,
"loss": 0.44815425872802733,
"step": 500
},
{
"epoch": 1.3047375160051216,
"grad_norm": 1.6712515877306602,
"learning_rate": 3.4884269043824342e-06,
"loss": 0.405930233001709,
"step": 510
},
{
"epoch": 1.3303457106274008,
"grad_norm": 1.800941360824222,
"learning_rate": 3.4196191658050555e-06,
"loss": 0.4227952480316162,
"step": 520
},
{
"epoch": 1.3559539052496798,
"grad_norm": 1.9542602926208692,
"learning_rate": 3.349996027151601e-06,
"loss": 0.4322650909423828,
"step": 530
},
{
"epoch": 1.381562099871959,
"grad_norm": 1.7001469373500844,
"learning_rate": 3.2796192212726524e-06,
"loss": 0.4273072242736816,
"step": 540
},
{
"epoch": 1.4071702944942381,
"grad_norm": 1.3602788345502808,
"learning_rate": 3.2085511492740175e-06,
"loss": 0.40812954902648924,
"step": 550
},
{
"epoch": 1.4327784891165174,
"grad_norm": 1.4585378495150405,
"learning_rate": 3.1368548251874487e-06,
"loss": 0.4072610855102539,
"step": 560
},
{
"epoch": 1.4583866837387964,
"grad_norm": 1.3520475551677658,
"learning_rate": 3.0645938200978987e-06,
"loss": 0.4169639587402344,
"step": 570
},
{
"epoch": 1.4839948783610755,
"grad_norm": 1.4508414002019714,
"learning_rate": 2.991832205776856e-06,
"loss": 0.43181633949279785,
"step": 580
},
{
"epoch": 1.5096030729833547,
"grad_norm": 1.921667585803632,
"learning_rate": 2.918634497871731e-06,
"loss": 0.4225574493408203,
"step": 590
},
{
"epoch": 1.5352112676056338,
"grad_norm": 1.4671405664975743,
"learning_rate": 2.845065598701673e-06,
"loss": 0.418547534942627,
"step": 600
},
{
"epoch": 1.5608194622279128,
"grad_norm": 1.4188762778752215,
"learning_rate": 2.771190739710534e-06,
"loss": 0.42908563613891604,
"step": 610
},
{
"epoch": 1.586427656850192,
"grad_norm": 1.5624143403752313,
"learning_rate": 2.69707542362801e-06,
"loss": 0.419779109954834,
"step": 620
},
{
"epoch": 1.6120358514724713,
"grad_norm": 1.3837172303234964,
"learning_rate": 2.62278536639024e-06,
"loss": 0.42682695388793945,
"step": 630
},
{
"epoch": 1.6376440460947503,
"grad_norm": 1.8146171083481704,
"learning_rate": 2.5483864388713608e-06,
"loss": 0.40843868255615234,
"step": 640
},
{
"epoch": 1.6632522407170294,
"grad_norm": 1.4700850995507602,
"learning_rate": 2.4739446084776785e-06,
"loss": 0.40427021980285643,
"step": 650
},
{
"epoch": 1.6888604353393086,
"grad_norm": 1.8147479971773997,
"learning_rate": 2.3995258806562556e-06,
"loss": 0.4081674098968506,
"step": 660
},
{
"epoch": 1.7144686299615877,
"grad_norm": 1.704890035046186,
"learning_rate": 2.3251962403697635e-06,
"loss": 0.415826416015625,
"step": 670
},
{
"epoch": 1.7400768245838667,
"grad_norm": 1.4295801530597483,
"learning_rate": 2.251021593589496e-06,
"loss": 0.42801637649536134,
"step": 680
},
{
"epoch": 1.765685019206146,
"grad_norm": 1.3198378159803181,
"learning_rate": 2.1770677088584315e-06,
"loss": 0.4132532119750977,
"step": 690
},
{
"epoch": 1.7912932138284252,
"grad_norm": 1.5820027588268746,
"learning_rate": 2.1034001589761343e-06,
"loss": 0.4029811382293701,
"step": 700
},
{
"epoch": 1.8169014084507042,
"grad_norm": 1.7963065436983081,
"learning_rate": 2.0300842628572284e-06,
"loss": 0.40697240829467773,
"step": 710
},
{
"epoch": 1.8425096030729833,
"grad_norm": 2.0217685766751656,
"learning_rate": 1.95718502761498e-06,
"loss": 0.43702383041381837,
"step": 720
},
{
"epoch": 1.8681177976952625,
"grad_norm": 1.467298226039554,
"learning_rate": 1.8847670909213433e-06,
"loss": 0.3957404136657715,
"step": 730
},
{
"epoch": 1.8937259923175416,
"grad_norm": 1.7444761947382206,
"learning_rate": 1.8128946636945827e-06,
"loss": 0.42693262100219725,
"step": 740
},
{
"epoch": 1.9193341869398206,
"grad_norm": 1.4400491686375012,
"learning_rate": 1.7416314731652808e-06,
"loss": 0.40868291854858396,
"step": 750
},
{
"epoch": 1.9449423815620999,
"grad_norm": 1.5745758477465968,
"learning_rate": 1.6710407063712247e-06,
"loss": 0.42135066986083985,
"step": 760
},
{
"epoch": 1.9705505761843791,
"grad_norm": 1.4583913680279406,
"learning_rate": 1.6011849541312597e-06,
"loss": 0.42116374969482423,
"step": 770
},
{
"epoch": 1.9961587708066582,
"grad_norm": 1.5372722755239894,
"learning_rate": 1.5321261555477989e-06,
"loss": 0.4099825382232666,
"step": 780
},
{
"epoch": 2.0204865556978233,
"grad_norm": 1.173579694705156,
"learning_rate": 1.4639255430871852e-06,
"loss": 0.3110218048095703,
"step": 790
},
{
"epoch": 2.0460947503201026,
"grad_norm": 1.9850921331690523,
"learning_rate": 1.3966435882866118e-06,
"loss": 0.2804063558578491,
"step": 800
},
{
"epoch": 2.0717029449423814,
"grad_norm": 1.2774083068020414,
"learning_rate": 1.3303399481357354e-06,
"loss": 0.26394855976104736,
"step": 810
},
{
"epoch": 2.0973111395646606,
"grad_norm": 1.4091561199201226,
"learning_rate": 1.2650734121805263e-06,
"loss": 0.26277709007263184,
"step": 820
},
{
"epoch": 2.12291933418694,
"grad_norm": 1.5244923052097017,
"learning_rate": 1.2009018503962547e-06,
"loss": 0.2693954944610596,
"step": 830
},
{
"epoch": 2.148527528809219,
"grad_norm": 1.566063938545027,
"learning_rate": 1.1378821618758347e-06,
"loss": 0.2556907176971436,
"step": 840
},
{
"epoch": 2.174135723431498,
"grad_norm": 1.3413902411262708,
"learning_rate": 1.0760702243790213e-06,
"loss": 0.26467223167419435,
"step": 850
},
{
"epoch": 2.1997439180537772,
"grad_norm": 1.3701564304583917,
"learning_rate": 1.0155208447871988e-06,
"loss": 0.2915048360824585,
"step": 860
},
{
"epoch": 2.2253521126760565,
"grad_norm": 1.285282293186625,
"learning_rate": 9.562877105076776e-07,
"loss": 0.26865172386169434,
"step": 870
},
{
"epoch": 2.2509603072983353,
"grad_norm": 1.3232832338180234,
"learning_rate": 8.98423341870604e-07,
"loss": 0.25586528778076173,
"step": 880
},
{
"epoch": 2.2765685019206146,
"grad_norm": 1.729162792877991,
"learning_rate": 8.419790455606836e-07,
"loss": 0.25625970363616946,
"step": 890
},
{
"epoch": 2.302176696542894,
"grad_norm": 1.2142111531455695,
"learning_rate": 7.87004869125006e-07,
"loss": 0.2555440902709961,
"step": 900
},
{
"epoch": 2.327784891165173,
"grad_norm": 1.6644945599214742,
"learning_rate": 7.335495565973131e-07,
"loss": 0.25954551696777345,
"step": 910
},
{
"epoch": 2.353393085787452,
"grad_norm": 1.777987853634216,
"learning_rate": 6.816605052780556e-07,
"loss": 0.263485050201416,
"step": 920
},
{
"epoch": 2.379001280409731,
"grad_norm": 1.248870947291848,
"learning_rate": 6.313837237085577e-07,
"loss": 0.2622115135192871,
"step": 930
},
{
"epoch": 2.4046094750320104,
"grad_norm": 1.4827455338456255,
"learning_rate": 5.827637908765593e-07,
"loss": 0.2656660556793213,
"step": 940
},
{
"epoch": 2.430217669654289,
"grad_norm": 1.3646405560360901,
"learning_rate": 5.358438166892954e-07,
"loss": 0.2752659320831299,
"step": 950
},
{
"epoch": 2.4558258642765685,
"grad_norm": 1.4238020101045017,
"learning_rate": 4.906654037491743e-07,
"loss": 0.26270647048950196,
"step": 960
},
{
"epoch": 2.4814340588988477,
"grad_norm": 1.5260519316724546,
"learning_rate": 4.4726861046593545e-07,
"loss": 0.25939154624938965,
"step": 970
},
{
"epoch": 2.507042253521127,
"grad_norm": 1.6173109382738884,
"learning_rate": 4.056919155380012e-07,
"loss": 0.24803729057312013,
"step": 980
},
{
"epoch": 2.532650448143406,
"grad_norm": 1.8148781008066097,
"learning_rate": 3.6597218383451345e-07,
"loss": 0.2752032518386841,
"step": 990
},
{
"epoch": 2.558258642765685,
"grad_norm": 1.8628502260268487,
"learning_rate": 3.281446337083039e-07,
"loss": 0.2631263494491577,
"step": 1000
},
{
"epoch": 2.5838668373879643,
"grad_norm": 1.1435963697391183,
"learning_rate": 2.9224280576878763e-07,
"loss": 0.26247210502624513,
"step": 1010
},
{
"epoch": 2.609475032010243,
"grad_norm": 1.9509332740805303,
"learning_rate": 2.582985331424598e-07,
"loss": 0.2643585205078125,
"step": 1020
},
{
"epoch": 2.6350832266325224,
"grad_norm": 1.5904515189022093,
"learning_rate": 2.2634191324737404e-07,
"loss": 0.26303515434265134,
"step": 1030
},
{
"epoch": 2.6606914212548016,
"grad_norm": 1.3261214225853823,
"learning_rate": 1.9640128110661543e-07,
"loss": 0.2749610424041748,
"step": 1040
},
{
"epoch": 2.686299615877081,
"grad_norm": 1.495889175623159,
"learning_rate": 1.6850318422444805e-07,
"loss": 0.2622413635253906,
"step": 1050
},
{
"epoch": 2.7119078104993597,
"grad_norm": 1.6516426608653414,
"learning_rate": 1.4267235904739856e-07,
"loss": 0.2718184232711792,
"step": 1060
},
{
"epoch": 2.737516005121639,
"grad_norm": 1.290344433955146,
"learning_rate": 1.1893170903115592e-07,
"loss": 0.2675800800323486,
"step": 1070
},
{
"epoch": 2.763124199743918,
"grad_norm": 1.2342435708595192,
"learning_rate": 9.730228433272982e-08,
"loss": 0.27097086906433104,
"step": 1080
},
{
"epoch": 2.788732394366197,
"grad_norm": 1.8795545401525064,
"learning_rate": 7.780326314587722e-08,
"loss": 0.2591713905334473,
"step": 1090
},
{
"epoch": 2.8143405889884763,
"grad_norm": 1.4002746914320383,
"learning_rate": 6.045193469634558e-08,
"loss": 0.2686860799789429,
"step": 1100
},
{
"epoch": 2.8399487836107555,
"grad_norm": 1.421889664318597,
"learning_rate": 4.526368391200881e-08,
"loss": 0.26590893268585203,
"step": 1110
},
{
"epoch": 2.865556978233035,
"grad_norm": 1.3630144335918553,
"learning_rate": 3.225197778149225e-08,
"loss": 0.27231292724609374,
"step": 1120
},
{
"epoch": 2.8911651728553136,
"grad_norm": 2.4428236421892233,
"learning_rate": 2.1428353413376346e-08,
"loss": 0.2678102970123291,
"step": 1130
},
{
"epoch": 2.916773367477593,
"grad_norm": 2.9866361225125138,
"learning_rate": 1.2802407806572215e-08,
"loss": 0.26076421737670896,
"step": 1140
},
{
"epoch": 2.942381562099872,
"grad_norm": 1.3463810104092713,
"learning_rate": 6.381789340937361e-09,
"loss": 0.2603736162185669,
"step": 1150
},
{
"epoch": 2.967989756722151,
"grad_norm": 1.5282382163608847,
"learning_rate": 2.172190995674284e-09,
"loss": 0.26784801483154297,
"step": 1160
},
{
"epoch": 2.99359795134443,
"grad_norm": 1.3701388641937626,
"learning_rate": 1.7734530152940798e-10,
"loss": 0.26529083251953123,
"step": 1170
},
{
"epoch": 3.0,
"step": 1173,
"total_flos": 2298630685327360.0,
"train_loss": 0.4866108725646166,
"train_runtime": 83589.2896,
"train_samples_per_second": 1.794,
"train_steps_per_second": 0.014
}
],
"logging_steps": 10,
"max_steps": 1173,
"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": 2298630685327360.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}