failed / trainer_state.json
lwjlwj's picture
Upload 11 files
ddca772 verified
Raw
History Blame Contribute Delete
86.4 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.166709878143635,
"eval_steps": 500,
"global_step": 4500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0025926886180969665,
"grad_norm": 7.705212116241455,
"learning_rate": 7.758620689655173e-07,
"loss": 3.0227869033813475,
"step": 10
},
{
"epoch": 0.005185377236193933,
"grad_norm": 7.195669651031494,
"learning_rate": 1.6379310344827587e-06,
"loss": 3.0158885955810546,
"step": 20
},
{
"epoch": 0.0077780658542909,
"grad_norm": 5.981606483459473,
"learning_rate": 2.4999999999999998e-06,
"loss": 2.9294967651367188,
"step": 30
},
{
"epoch": 0.010370754472387866,
"grad_norm": 4.623651027679443,
"learning_rate": 3.3620689655172414e-06,
"loss": 2.9329254150390627,
"step": 40
},
{
"epoch": 0.012963443090484833,
"grad_norm": 3.7059433460235596,
"learning_rate": 4.224137931034483e-06,
"loss": 2.8506282806396483,
"step": 50
},
{
"epoch": 0.0155561317085818,
"grad_norm": 2.2888247966766357,
"learning_rate": 5.0862068965517235e-06,
"loss": 2.773244285583496,
"step": 60
},
{
"epoch": 0.018148820326678767,
"grad_norm": 1.5469928979873657,
"learning_rate": 5.948275862068966e-06,
"loss": 2.6278873443603517,
"step": 70
},
{
"epoch": 0.020741508944775732,
"grad_norm": 1.3342334032058716,
"learning_rate": 6.810344827586207e-06,
"loss": 2.5356447219848635,
"step": 80
},
{
"epoch": 0.023334197562872697,
"grad_norm": 1.1389696598052979,
"learning_rate": 7.672413793103449e-06,
"loss": 2.4633319854736326,
"step": 90
},
{
"epoch": 0.025926886180969666,
"grad_norm": 1.1860013008117676,
"learning_rate": 8.53448275862069e-06,
"loss": 2.4070077896118165,
"step": 100
},
{
"epoch": 0.02851957479906663,
"grad_norm": 1.0827945470809937,
"learning_rate": 9.396551724137931e-06,
"loss": 2.3483230590820314,
"step": 110
},
{
"epoch": 0.0311122634171636,
"grad_norm": 1.8825736045837402,
"learning_rate": 1.0258620689655173e-05,
"loss": 2.3270618438720705,
"step": 120
},
{
"epoch": 0.03370495203526057,
"grad_norm": 1.0864979028701782,
"learning_rate": 1.1120689655172414e-05,
"loss": 2.2477684020996094,
"step": 130
},
{
"epoch": 0.036297640653357534,
"grad_norm": 0.9502561092376709,
"learning_rate": 1.1982758620689655e-05,
"loss": 2.192240524291992,
"step": 140
},
{
"epoch": 0.0388903292714545,
"grad_norm": 1.07854425907135,
"learning_rate": 1.2844827586206896e-05,
"loss": 2.124846267700195,
"step": 150
},
{
"epoch": 0.041483017889551464,
"grad_norm": 1.5999815464019775,
"learning_rate": 1.370689655172414e-05,
"loss": 2.0473533630371095,
"step": 160
},
{
"epoch": 0.04407570650764843,
"grad_norm": 1.1964465379714966,
"learning_rate": 1.4568965517241379e-05,
"loss": 2.0475059509277345,
"step": 170
},
{
"epoch": 0.046668395125745395,
"grad_norm": 1.0338537693023682,
"learning_rate": 1.543103448275862e-05,
"loss": 2.029034423828125,
"step": 180
},
{
"epoch": 0.04926108374384237,
"grad_norm": 1.473418116569519,
"learning_rate": 1.6293103448275863e-05,
"loss": 1.992477798461914,
"step": 190
},
{
"epoch": 0.05185377236193933,
"grad_norm": 1.050335168838501,
"learning_rate": 1.7155172413793106e-05,
"loss": 1.9807832717895508,
"step": 200
},
{
"epoch": 0.0544464609800363,
"grad_norm": 1.4469194412231445,
"learning_rate": 1.8017241379310346e-05,
"loss": 1.9144599914550782,
"step": 210
},
{
"epoch": 0.05703914959813326,
"grad_norm": 1.9262558221817017,
"learning_rate": 1.8879310344827585e-05,
"loss": 1.9685123443603516,
"step": 220
},
{
"epoch": 0.05963183821623023,
"grad_norm": 1.44905686378479,
"learning_rate": 1.9741379310344828e-05,
"loss": 1.950737190246582,
"step": 230
},
{
"epoch": 0.0622245268343272,
"grad_norm": 1.2477736473083496,
"learning_rate": 2.060344827586207e-05,
"loss": 1.870539093017578,
"step": 240
},
{
"epoch": 0.06481721545242417,
"grad_norm": 1.5359461307525635,
"learning_rate": 2.146551724137931e-05,
"loss": 1.891302490234375,
"step": 250
},
{
"epoch": 0.06740990407052114,
"grad_norm": 1.4555562734603882,
"learning_rate": 2.232758620689655e-05,
"loss": 1.8455034255981446,
"step": 260
},
{
"epoch": 0.0700025926886181,
"grad_norm": 1.121903657913208,
"learning_rate": 2.3189655172413793e-05,
"loss": 1.8681245803833009,
"step": 270
},
{
"epoch": 0.07259528130671507,
"grad_norm": 1.450315237045288,
"learning_rate": 2.4051724137931036e-05,
"loss": 1.848301315307617,
"step": 280
},
{
"epoch": 0.07518796992481203,
"grad_norm": 1.4702492952346802,
"learning_rate": 2.4913793103448276e-05,
"loss": 1.8164592742919923,
"step": 290
},
{
"epoch": 0.077780658542909,
"grad_norm": 1.5632305145263672,
"learning_rate": 2.577586206896552e-05,
"loss": 1.8211044311523437,
"step": 300
},
{
"epoch": 0.08037334716100596,
"grad_norm": 1.3765159845352173,
"learning_rate": 2.663793103448276e-05,
"loss": 1.7973749160766601,
"step": 310
},
{
"epoch": 0.08296603577910293,
"grad_norm": 1.5355861186981201,
"learning_rate": 2.75e-05,
"loss": 1.7973670959472656,
"step": 320
},
{
"epoch": 0.0855587243971999,
"grad_norm": 1.7966196537017822,
"learning_rate": 2.836206896551724e-05,
"loss": 1.793952751159668,
"step": 330
},
{
"epoch": 0.08815141301529686,
"grad_norm": 1.443326473236084,
"learning_rate": 2.9224137931034483e-05,
"loss": 1.7765045166015625,
"step": 340
},
{
"epoch": 0.09074410163339383,
"grad_norm": 1.508481740951538,
"learning_rate": 2.9999999412317066e-05,
"loss": 1.7646129608154297,
"step": 350
},
{
"epoch": 0.09333679025149079,
"grad_norm": 1.4187544584274292,
"learning_rate": 2.9999928890420564e-05,
"loss": 1.7498319625854493,
"step": 360
},
{
"epoch": 0.09592947886958776,
"grad_norm": 1.2583993673324585,
"learning_rate": 2.9999740832570195e-05,
"loss": 1.7248340606689454,
"step": 370
},
{
"epoch": 0.09852216748768473,
"grad_norm": 1.6766241788864136,
"learning_rate": 2.9999435240239542e-05,
"loss": 1.7178813934326171,
"step": 380
},
{
"epoch": 0.10111485610578169,
"grad_norm": 1.202833890914917,
"learning_rate": 2.9999012115823158e-05,
"loss": 1.6801229476928712,
"step": 390
},
{
"epoch": 0.10370754472387866,
"grad_norm": 1.2926560640335083,
"learning_rate": 2.9998471462636546e-05,
"loss": 1.767136001586914,
"step": 400
},
{
"epoch": 0.10630023334197562,
"grad_norm": 1.941349983215332,
"learning_rate": 2.9997813284916135e-05,
"loss": 1.6747543334960937,
"step": 410
},
{
"epoch": 0.1088929219600726,
"grad_norm": 1.5845695734024048,
"learning_rate": 2.9997037587819258e-05,
"loss": 1.673520278930664,
"step": 420
},
{
"epoch": 0.11148561057816957,
"grad_norm": 1.3995505571365356,
"learning_rate": 2.999614437742409e-05,
"loss": 1.7203987121582032,
"step": 430
},
{
"epoch": 0.11407829919626652,
"grad_norm": 1.5118882656097412,
"learning_rate": 2.9995133660729633e-05,
"loss": 1.706008529663086,
"step": 440
},
{
"epoch": 0.1166709878143635,
"grad_norm": 1.319544792175293,
"learning_rate": 2.999400544565561e-05,
"loss": 1.6883546829223632,
"step": 450
},
{
"epoch": 0.11926367643246046,
"grad_norm": 1.421674370765686,
"learning_rate": 2.9992759741042464e-05,
"loss": 1.7108165740966796,
"step": 460
},
{
"epoch": 0.12185636505055743,
"grad_norm": 1.4081259965896606,
"learning_rate": 2.999139655665124e-05,
"loss": 1.6875082015991212,
"step": 470
},
{
"epoch": 0.1244490536686544,
"grad_norm": 1.405349850654602,
"learning_rate": 2.998991590316354e-05,
"loss": 1.6731761932373046,
"step": 480
},
{
"epoch": 0.12704174228675136,
"grad_norm": 1.7677608728408813,
"learning_rate": 2.998831779218142e-05,
"loss": 1.6962146759033203,
"step": 490
},
{
"epoch": 0.12963443090484833,
"grad_norm": 1.8731317520141602,
"learning_rate": 2.99866022362273e-05,
"loss": 1.6599393844604493,
"step": 500
},
{
"epoch": 0.12963443090484833,
"eval_loss": 1.6675474643707275,
"eval_runtime": 107.111,
"eval_samples_per_second": 15.162,
"eval_steps_per_second": 15.162,
"step": 500
},
{
"epoch": 0.1322271195229453,
"grad_norm": 1.4730808734893799,
"learning_rate": 2.9984769248743883e-05,
"loss": 1.6474054336547852,
"step": 510
},
{
"epoch": 0.13481980814104227,
"grad_norm": 1.7537602186203003,
"learning_rate": 2.998281884409403e-05,
"loss": 1.6060302734375,
"step": 520
},
{
"epoch": 0.13741249675913922,
"grad_norm": 1.598738670349121,
"learning_rate": 2.9980751037560658e-05,
"loss": 1.6906095504760743,
"step": 530
},
{
"epoch": 0.1400051853772362,
"grad_norm": 2.2294440269470215,
"learning_rate": 2.9978565845346622e-05,
"loss": 1.6616540908813477,
"step": 540
},
{
"epoch": 0.14259787399533316,
"grad_norm": 1.9882858991622925,
"learning_rate": 2.997626328457457e-05,
"loss": 1.7083959579467773,
"step": 550
},
{
"epoch": 0.14519056261343014,
"grad_norm": 1.6550426483154297,
"learning_rate": 2.9973843373286846e-05,
"loss": 1.677723503112793,
"step": 560
},
{
"epoch": 0.1477832512315271,
"grad_norm": 2.0807480812072754,
"learning_rate": 2.9971306130445305e-05,
"loss": 1.647475814819336,
"step": 570
},
{
"epoch": 0.15037593984962405,
"grad_norm": 1.3921107053756714,
"learning_rate": 2.996865157593119e-05,
"loss": 1.6432958602905274,
"step": 580
},
{
"epoch": 0.15296862846772102,
"grad_norm": 1.399657964706421,
"learning_rate": 2.9965879730544968e-05,
"loss": 1.6632362365722657,
"step": 590
},
{
"epoch": 0.155561317085818,
"grad_norm": 1.6916463375091553,
"learning_rate": 2.996299061600619e-05,
"loss": 1.6300394058227539,
"step": 600
},
{
"epoch": 0.15815400570391497,
"grad_norm": 1.7113163471221924,
"learning_rate": 2.9959984254953276e-05,
"loss": 1.6330863952636718,
"step": 610
},
{
"epoch": 0.1607466943220119,
"grad_norm": 1.5331860780715942,
"learning_rate": 2.9956860670943375e-05,
"loss": 1.5855411529541015,
"step": 620
},
{
"epoch": 0.16333938294010888,
"grad_norm": 1.700958013534546,
"learning_rate": 2.9953619888452156e-05,
"loss": 1.61474609375,
"step": 630
},
{
"epoch": 0.16593207155820586,
"grad_norm": 1.7234867811203003,
"learning_rate": 2.995026193287365e-05,
"loss": 1.6093793869018556,
"step": 640
},
{
"epoch": 0.16852476017630283,
"grad_norm": 1.7460917234420776,
"learning_rate": 2.9946786830520007e-05,
"loss": 1.6209524154663086,
"step": 650
},
{
"epoch": 0.1711174487943998,
"grad_norm": 1.5481910705566406,
"learning_rate": 2.9943194608621323e-05,
"loss": 1.6162069320678711,
"step": 660
},
{
"epoch": 0.17371013741249675,
"grad_norm": 1.920379638671875,
"learning_rate": 2.9939485295325412e-05,
"loss": 1.6570716857910157,
"step": 670
},
{
"epoch": 0.17630282603059372,
"grad_norm": 1.456347942352295,
"learning_rate": 2.9935658919697594e-05,
"loss": 1.588156032562256,
"step": 680
},
{
"epoch": 0.1788955146486907,
"grad_norm": 1.921565294265747,
"learning_rate": 2.9931715511720455e-05,
"loss": 1.6013357162475585,
"step": 690
},
{
"epoch": 0.18148820326678766,
"grad_norm": 1.875504732131958,
"learning_rate": 2.992765510229362e-05,
"loss": 1.632054328918457,
"step": 700
},
{
"epoch": 0.18408089188488463,
"grad_norm": 1.7401937246322632,
"learning_rate": 2.992347772323352e-05,
"loss": 1.5879243850708007,
"step": 710
},
{
"epoch": 0.18667358050298158,
"grad_norm": 1.4971174001693726,
"learning_rate": 2.9919183407273126e-05,
"loss": 1.6358772277832032,
"step": 720
},
{
"epoch": 0.18926626912107855,
"grad_norm": 1.8517812490463257,
"learning_rate": 2.991477218806169e-05,
"loss": 1.5942300796508788,
"step": 730
},
{
"epoch": 0.19185895773917552,
"grad_norm": 1.7906169891357422,
"learning_rate": 2.991024410016451e-05,
"loss": 1.6056285858154298,
"step": 740
},
{
"epoch": 0.1944516463572725,
"grad_norm": 1.7057501077651978,
"learning_rate": 2.990559917906262e-05,
"loss": 1.5925214767456055,
"step": 750
},
{
"epoch": 0.19704433497536947,
"grad_norm": 1.900687336921692,
"learning_rate": 2.990083746115255e-05,
"loss": 1.5858644485473632,
"step": 760
},
{
"epoch": 0.1996370235934664,
"grad_norm": 1.8664599657058716,
"learning_rate": 2.9895958983746004e-05,
"loss": 1.6028635025024414,
"step": 770
},
{
"epoch": 0.20222971221156338,
"grad_norm": 2.207900285720825,
"learning_rate": 2.9890963785069605e-05,
"loss": 1.5772765159606934,
"step": 780
},
{
"epoch": 0.20482240082966036,
"grad_norm": 1.7628965377807617,
"learning_rate": 2.988585190426457e-05,
"loss": 1.5588774681091309,
"step": 790
},
{
"epoch": 0.20741508944775733,
"grad_norm": 2.1701314449310303,
"learning_rate": 2.98806233813864e-05,
"loss": 1.5740567207336427,
"step": 800
},
{
"epoch": 0.2100077780658543,
"grad_norm": 1.7453765869140625,
"learning_rate": 2.9875278257404583e-05,
"loss": 1.5921754837036133,
"step": 810
},
{
"epoch": 0.21260046668395124,
"grad_norm": 1.77922785282135,
"learning_rate": 2.9869816574202273e-05,
"loss": 1.5537161827087402,
"step": 820
},
{
"epoch": 0.21519315530204822,
"grad_norm": 1.8443162441253662,
"learning_rate": 2.9864238374575952e-05,
"loss": 1.5755566596984862,
"step": 830
},
{
"epoch": 0.2177858439201452,
"grad_norm": 1.913630485534668,
"learning_rate": 2.9858543702235087e-05,
"loss": 1.6065607070922852,
"step": 840
},
{
"epoch": 0.22037853253824216,
"grad_norm": 2.5680060386657715,
"learning_rate": 2.985273260180181e-05,
"loss": 1.5453169822692872,
"step": 850
},
{
"epoch": 0.22297122115633913,
"grad_norm": 2.0303702354431152,
"learning_rate": 2.984680511881055e-05,
"loss": 1.596198844909668,
"step": 860
},
{
"epoch": 0.22556390977443608,
"grad_norm": 1.5549193620681763,
"learning_rate": 2.9840761299707694e-05,
"loss": 1.568855381011963,
"step": 870
},
{
"epoch": 0.22815659839253305,
"grad_norm": 1.7885875701904297,
"learning_rate": 2.9834601191851187e-05,
"loss": 1.5498332023620605,
"step": 880
},
{
"epoch": 0.23074928701063002,
"grad_norm": 2.0089168548583984,
"learning_rate": 2.9828324843510214e-05,
"loss": 1.5433233261108399,
"step": 890
},
{
"epoch": 0.233341975628727,
"grad_norm": 2.1354048252105713,
"learning_rate": 2.9821932303864776e-05,
"loss": 1.5958542823791504,
"step": 900
},
{
"epoch": 0.23593466424682397,
"grad_norm": 2.3687899112701416,
"learning_rate": 2.981542362300533e-05,
"loss": 1.5683826446533202,
"step": 910
},
{
"epoch": 0.2385273528649209,
"grad_norm": 2.329882860183716,
"learning_rate": 2.9808798851932375e-05,
"loss": 1.6122396469116211,
"step": 920
},
{
"epoch": 0.24112004148301788,
"grad_norm": 1.9204554557800293,
"learning_rate": 2.980205804255609e-05,
"loss": 1.5680127143859863,
"step": 930
},
{
"epoch": 0.24371273010111486,
"grad_norm": 2.02498459815979,
"learning_rate": 2.9795201247695885e-05,
"loss": 1.53897123336792,
"step": 940
},
{
"epoch": 0.24630541871921183,
"grad_norm": 1.5861380100250244,
"learning_rate": 2.9788228521080002e-05,
"loss": 1.5421215057373048,
"step": 950
},
{
"epoch": 0.2488981073373088,
"grad_norm": 1.801835536956787,
"learning_rate": 2.9781139917345113e-05,
"loss": 1.5495308876037597,
"step": 960
},
{
"epoch": 0.25149079595540574,
"grad_norm": 2.1597230434417725,
"learning_rate": 2.9773935492035868e-05,
"loss": 1.5722169876098633,
"step": 970
},
{
"epoch": 0.2540834845735027,
"grad_norm": 2.119235038757324,
"learning_rate": 2.9766615301604467e-05,
"loss": 1.5267520904541017,
"step": 980
},
{
"epoch": 0.2566761731915997,
"grad_norm": 1.9513345956802368,
"learning_rate": 2.9759179403410216e-05,
"loss": 1.5414809226989745,
"step": 990
},
{
"epoch": 0.25926886180969666,
"grad_norm": 1.8692830801010132,
"learning_rate": 2.9751627855719086e-05,
"loss": 1.545905590057373,
"step": 1000
},
{
"epoch": 0.25926886180969666,
"eval_loss": 1.5521949529647827,
"eval_runtime": 105.9297,
"eval_samples_per_second": 15.331,
"eval_steps_per_second": 15.331,
"step": 1000
},
{
"epoch": 0.26186155042779363,
"grad_norm": 1.7280081510543823,
"learning_rate": 2.974396071770325e-05,
"loss": 1.5839033126831055,
"step": 1010
},
{
"epoch": 0.2644542390458906,
"grad_norm": 1.5108997821807861,
"learning_rate": 2.9736178049440613e-05,
"loss": 1.5561725616455078,
"step": 1020
},
{
"epoch": 0.2670469276639876,
"grad_norm": 1.8250467777252197,
"learning_rate": 2.9728279911914364e-05,
"loss": 1.5358820915222169,
"step": 1030
},
{
"epoch": 0.26963961628208455,
"grad_norm": 2.029668092727661,
"learning_rate": 2.972026636701246e-05,
"loss": 1.553438091278076,
"step": 1040
},
{
"epoch": 0.27223230490018147,
"grad_norm": 1.8540805578231812,
"learning_rate": 2.971213747752718e-05,
"loss": 1.5556982040405274,
"step": 1050
},
{
"epoch": 0.27482499351827844,
"grad_norm": 1.7269654273986816,
"learning_rate": 2.970389330715461e-05,
"loss": 1.5581286430358887,
"step": 1060
},
{
"epoch": 0.2774176821363754,
"grad_norm": 2.0595953464508057,
"learning_rate": 2.9695533920494154e-05,
"loss": 1.5113532066345214,
"step": 1070
},
{
"epoch": 0.2800103707544724,
"grad_norm": 2.1933727264404297,
"learning_rate": 2.968705938304802e-05,
"loss": 1.5415559768676759,
"step": 1080
},
{
"epoch": 0.28260305937256935,
"grad_norm": 2.0160536766052246,
"learning_rate": 2.9678469761220713e-05,
"loss": 1.489687156677246,
"step": 1090
},
{
"epoch": 0.2851957479906663,
"grad_norm": 1.5818418264389038,
"learning_rate": 2.9669765122318506e-05,
"loss": 1.5600990295410155,
"step": 1100
},
{
"epoch": 0.2877884366087633,
"grad_norm": 1.8866775035858154,
"learning_rate": 2.9660945534548933e-05,
"loss": 1.5680411338806153,
"step": 1110
},
{
"epoch": 0.29038112522686027,
"grad_norm": 1.8531945943832397,
"learning_rate": 2.9652011067020225e-05,
"loss": 1.5095998764038085,
"step": 1120
},
{
"epoch": 0.29297381384495724,
"grad_norm": 2.0008137226104736,
"learning_rate": 2.96429617897408e-05,
"loss": 1.543956184387207,
"step": 1130
},
{
"epoch": 0.2955665024630542,
"grad_norm": 1.696394681930542,
"learning_rate": 2.9633797773618683e-05,
"loss": 1.5572497367858886,
"step": 1140
},
{
"epoch": 0.29815919108115113,
"grad_norm": 1.856203556060791,
"learning_rate": 2.9624519090460977e-05,
"loss": 1.5321713447570802,
"step": 1150
},
{
"epoch": 0.3007518796992481,
"grad_norm": 1.983908772468567,
"learning_rate": 2.9615125812973284e-05,
"loss": 1.5194916725158691,
"step": 1160
},
{
"epoch": 0.3033445683173451,
"grad_norm": 1.8463765382766724,
"learning_rate": 2.9605618014759135e-05,
"loss": 1.54110746383667,
"step": 1170
},
{
"epoch": 0.30593725693544205,
"grad_norm": 2.1281657218933105,
"learning_rate": 2.9595995770319432e-05,
"loss": 1.5438779830932616,
"step": 1180
},
{
"epoch": 0.308529945553539,
"grad_norm": 2.2548391819000244,
"learning_rate": 2.9586259155051847e-05,
"loss": 1.4930756568908692,
"step": 1190
},
{
"epoch": 0.311122634171636,
"grad_norm": 1.8192869424819946,
"learning_rate": 2.957640824525023e-05,
"loss": 1.4750795364379883,
"step": 1200
},
{
"epoch": 0.31371532278973296,
"grad_norm": 1.9327999353408813,
"learning_rate": 2.9566443118104013e-05,
"loss": 1.5061716079711913,
"step": 1210
},
{
"epoch": 0.31630801140782994,
"grad_norm": 2.6463584899902344,
"learning_rate": 2.955636385169762e-05,
"loss": 1.4914235115051269,
"step": 1220
},
{
"epoch": 0.3189007000259269,
"grad_norm": 1.802319884300232,
"learning_rate": 2.9546170525009845e-05,
"loss": 1.5331766128540039,
"step": 1230
},
{
"epoch": 0.3214933886440238,
"grad_norm": 1.733071208000183,
"learning_rate": 2.9535863217913207e-05,
"loss": 1.5249350547790528,
"step": 1240
},
{
"epoch": 0.3240860772621208,
"grad_norm": 2.096780300140381,
"learning_rate": 2.9525442011173383e-05,
"loss": 1.506511402130127,
"step": 1250
},
{
"epoch": 0.32667876588021777,
"grad_norm": 1.789000153541565,
"learning_rate": 2.9514906986448516e-05,
"loss": 1.4979613304138184,
"step": 1260
},
{
"epoch": 0.32927145449831474,
"grad_norm": 2.3496737480163574,
"learning_rate": 2.9504258226288613e-05,
"loss": 1.5362759590148927,
"step": 1270
},
{
"epoch": 0.3318641431164117,
"grad_norm": 2.1412160396575928,
"learning_rate": 2.9493495814134887e-05,
"loss": 1.5093208312988282,
"step": 1280
},
{
"epoch": 0.3344568317345087,
"grad_norm": 2.7615764141082764,
"learning_rate": 2.9482619834319088e-05,
"loss": 1.4955772399902343,
"step": 1290
},
{
"epoch": 0.33704952035260566,
"grad_norm": 1.8998992443084717,
"learning_rate": 2.9471630372062864e-05,
"loss": 1.5002532958984376,
"step": 1300
},
{
"epoch": 0.33964220897070263,
"grad_norm": 1.8375203609466553,
"learning_rate": 2.9460527513477093e-05,
"loss": 1.4847103118896485,
"step": 1310
},
{
"epoch": 0.3422348975887996,
"grad_norm": 2.5817832946777344,
"learning_rate": 2.9449311345561185e-05,
"loss": 1.4912428855895996,
"step": 1320
},
{
"epoch": 0.3448275862068966,
"grad_norm": 1.6789653301239014,
"learning_rate": 2.9437981956202422e-05,
"loss": 1.5264065742492676,
"step": 1330
},
{
"epoch": 0.3474202748249935,
"grad_norm": 1.9965680837631226,
"learning_rate": 2.9426539434175272e-05,
"loss": 1.5252839088439942,
"step": 1340
},
{
"epoch": 0.35001296344309046,
"grad_norm": 2.63002872467041,
"learning_rate": 2.941498386914067e-05,
"loss": 1.5000991821289062,
"step": 1350
},
{
"epoch": 0.35260565206118744,
"grad_norm": 1.781042218208313,
"learning_rate": 2.9403315351645336e-05,
"loss": 1.4635045051574707,
"step": 1360
},
{
"epoch": 0.3551983406792844,
"grad_norm": 2.09206223487854,
"learning_rate": 2.9391533973121064e-05,
"loss": 1.51431884765625,
"step": 1370
},
{
"epoch": 0.3577910292973814,
"grad_norm": 1.8178857564926147,
"learning_rate": 2.937963982588399e-05,
"loss": 1.5193375587463378,
"step": 1380
},
{
"epoch": 0.36038371791547835,
"grad_norm": 2.0183215141296387,
"learning_rate": 2.9367633003133886e-05,
"loss": 1.5367141723632813,
"step": 1390
},
{
"epoch": 0.3629764065335753,
"grad_norm": 1.7666372060775757,
"learning_rate": 2.9355513598953425e-05,
"loss": 1.5032243728637695,
"step": 1400
},
{
"epoch": 0.3655690951516723,
"grad_norm": 1.8232026100158691,
"learning_rate": 2.934328170830744e-05,
"loss": 1.5230186462402344,
"step": 1410
},
{
"epoch": 0.36816178376976927,
"grad_norm": 2.2781875133514404,
"learning_rate": 2.933093742704218e-05,
"loss": 1.545018196105957,
"step": 1420
},
{
"epoch": 0.37075447238786624,
"grad_norm": 1.9527894258499146,
"learning_rate": 2.9318480851884555e-05,
"loss": 1.5268414497375489,
"step": 1430
},
{
"epoch": 0.37334716100596316,
"grad_norm": 1.85111403465271,
"learning_rate": 2.93059120804414e-05,
"loss": 1.514940071105957,
"step": 1440
},
{
"epoch": 0.37593984962406013,
"grad_norm": 1.5911691188812256,
"learning_rate": 2.9293231211198678e-05,
"loss": 1.4724421501159668,
"step": 1450
},
{
"epoch": 0.3785325382421571,
"grad_norm": 1.9510048627853394,
"learning_rate": 2.9280438343520736e-05,
"loss": 1.4826346397399903,
"step": 1460
},
{
"epoch": 0.3811252268602541,
"grad_norm": 2.7119040489196777,
"learning_rate": 2.9267533577649508e-05,
"loss": 1.5354348182678224,
"step": 1470
},
{
"epoch": 0.38371791547835105,
"grad_norm": 2.071737051010132,
"learning_rate": 2.925451701470374e-05,
"loss": 1.48195161819458,
"step": 1480
},
{
"epoch": 0.386310604096448,
"grad_norm": 2.013737440109253,
"learning_rate": 2.924138875667818e-05,
"loss": 1.485996627807617,
"step": 1490
},
{
"epoch": 0.388903292714545,
"grad_norm": 2.03083872795105,
"learning_rate": 2.9228148906442822e-05,
"loss": 1.538092041015625,
"step": 1500
},
{
"epoch": 0.388903292714545,
"eval_loss": 1.5003650188446045,
"eval_runtime": 106.3328,
"eval_samples_per_second": 15.273,
"eval_steps_per_second": 15.273,
"step": 1500
},
{
"epoch": 0.39149598133264196,
"grad_norm": 1.617337703704834,
"learning_rate": 2.9214797567742036e-05,
"loss": 1.4525361061096191,
"step": 1510
},
{
"epoch": 0.39408866995073893,
"grad_norm": 2.461519718170166,
"learning_rate": 2.9201334845193823e-05,
"loss": 1.4694942474365233,
"step": 1520
},
{
"epoch": 0.3966813585688359,
"grad_norm": 1.9445669651031494,
"learning_rate": 2.918776084428893e-05,
"loss": 1.461592197418213,
"step": 1530
},
{
"epoch": 0.3992740471869328,
"grad_norm": 2.038569927215576,
"learning_rate": 2.917407567139008e-05,
"loss": 1.511174774169922,
"step": 1540
},
{
"epoch": 0.4018667358050298,
"grad_norm": 2.003824234008789,
"learning_rate": 2.91602794337311e-05,
"loss": 1.4884771347045898,
"step": 1550
},
{
"epoch": 0.40445942442312677,
"grad_norm": 3.0072197914123535,
"learning_rate": 2.9146372239416105e-05,
"loss": 1.4911428451538087,
"step": 1560
},
{
"epoch": 0.40705211304122374,
"grad_norm": 2.1022398471832275,
"learning_rate": 2.9132354197418633e-05,
"loss": 1.5100956916809083,
"step": 1570
},
{
"epoch": 0.4096448016593207,
"grad_norm": 1.8543621301651,
"learning_rate": 2.91182254175808e-05,
"loss": 1.538217258453369,
"step": 1580
},
{
"epoch": 0.4122374902774177,
"grad_norm": 1.6851848363876343,
"learning_rate": 2.9103986010612435e-05,
"loss": 1.4339521408081055,
"step": 1590
},
{
"epoch": 0.41483017889551466,
"grad_norm": 2.1606297492980957,
"learning_rate": 2.9089636088090222e-05,
"loss": 1.471330738067627,
"step": 1600
},
{
"epoch": 0.41742286751361163,
"grad_norm": 1.8915854692459106,
"learning_rate": 2.9075175762456817e-05,
"loss": 1.4531750679016113,
"step": 1610
},
{
"epoch": 0.4200155561317086,
"grad_norm": 1.9127671718597412,
"learning_rate": 2.9060605147019964e-05,
"loss": 1.5028268814086914,
"step": 1620
},
{
"epoch": 0.4226082447498056,
"grad_norm": 2.362971305847168,
"learning_rate": 2.904592435595163e-05,
"loss": 1.50010347366333,
"step": 1630
},
{
"epoch": 0.4252009333679025,
"grad_norm": 1.7769346237182617,
"learning_rate": 2.903113350428706e-05,
"loss": 1.4772180557250976,
"step": 1640
},
{
"epoch": 0.42779362198599946,
"grad_norm": 2.0999252796173096,
"learning_rate": 2.9016232707923933e-05,
"loss": 1.4838216781616211,
"step": 1650
},
{
"epoch": 0.43038631060409643,
"grad_norm": 2.012392044067383,
"learning_rate": 2.9001222083621433e-05,
"loss": 1.4446197509765626,
"step": 1660
},
{
"epoch": 0.4329789992221934,
"grad_norm": 2.1913809776306152,
"learning_rate": 2.8986101748999312e-05,
"loss": 1.4910202980041505,
"step": 1670
},
{
"epoch": 0.4355716878402904,
"grad_norm": 2.4685049057006836,
"learning_rate": 2.8970871822537e-05,
"loss": 1.4822717666625977,
"step": 1680
},
{
"epoch": 0.43816437645838735,
"grad_norm": 1.755044937133789,
"learning_rate": 2.8955532423572654e-05,
"loss": 1.4712723731994628,
"step": 1690
},
{
"epoch": 0.4407570650764843,
"grad_norm": 1.873952031135559,
"learning_rate": 2.894008367230224e-05,
"loss": 1.4480696678161622,
"step": 1700
},
{
"epoch": 0.4433497536945813,
"grad_norm": 2.0481786727905273,
"learning_rate": 2.8924525689778572e-05,
"loss": 1.4416559219360352,
"step": 1710
},
{
"epoch": 0.44594244231267827,
"grad_norm": 2.0595901012420654,
"learning_rate": 2.8908858597910395e-05,
"loss": 1.4915009498596192,
"step": 1720
},
{
"epoch": 0.44853513093077524,
"grad_norm": 1.6267675161361694,
"learning_rate": 2.8893082519461387e-05,
"loss": 1.4517938613891601,
"step": 1730
},
{
"epoch": 0.45112781954887216,
"grad_norm": 1.8121838569641113,
"learning_rate": 2.8877197578049233e-05,
"loss": 1.5236659049987793,
"step": 1740
},
{
"epoch": 0.4537205081669691,
"grad_norm": 2.1903886795043945,
"learning_rate": 2.8861203898144635e-05,
"loss": 1.4702713012695312,
"step": 1750
},
{
"epoch": 0.4563131967850661,
"grad_norm": 2.377471685409546,
"learning_rate": 2.8845101605070358e-05,
"loss": 1.4455768585205078,
"step": 1760
},
{
"epoch": 0.45890588540316307,
"grad_norm": 1.9816523790359497,
"learning_rate": 2.8828890825000215e-05,
"loss": 1.4934269905090332,
"step": 1770
},
{
"epoch": 0.46149857402126004,
"grad_norm": 1.8602914810180664,
"learning_rate": 2.8812571684958112e-05,
"loss": 1.497078037261963,
"step": 1780
},
{
"epoch": 0.464091262639357,
"grad_norm": 2.106839895248413,
"learning_rate": 2.8796144312817037e-05,
"loss": 1.4540966987609862,
"step": 1790
},
{
"epoch": 0.466683951257454,
"grad_norm": 2.2227728366851807,
"learning_rate": 2.8779608837298052e-05,
"loss": 1.4421021461486816,
"step": 1800
},
{
"epoch": 0.46927663987555096,
"grad_norm": 2.174560308456421,
"learning_rate": 2.8762965387969303e-05,
"loss": 1.4236719131469726,
"step": 1810
},
{
"epoch": 0.47186932849364793,
"grad_norm": 2.3142716884613037,
"learning_rate": 2.8746214095244983e-05,
"loss": 1.475877857208252,
"step": 1820
},
{
"epoch": 0.4744620171117449,
"grad_norm": 1.8860278129577637,
"learning_rate": 2.872935509038433e-05,
"loss": 1.4664278030395508,
"step": 1830
},
{
"epoch": 0.4770547057298418,
"grad_norm": 2.211853504180908,
"learning_rate": 2.871238850549058e-05,
"loss": 1.4496440887451172,
"step": 1840
},
{
"epoch": 0.4796473943479388,
"grad_norm": 1.8439429998397827,
"learning_rate": 2.8695314473509952e-05,
"loss": 1.4292086601257323,
"step": 1850
},
{
"epoch": 0.48224008296603577,
"grad_norm": 1.799233078956604,
"learning_rate": 2.867813312823058e-05,
"loss": 1.4751974105834962,
"step": 1860
},
{
"epoch": 0.48483277158413274,
"grad_norm": 1.6252014636993408,
"learning_rate": 2.8660844604281496e-05,
"loss": 1.4683155059814452,
"step": 1870
},
{
"epoch": 0.4874254602022297,
"grad_norm": 2.7162091732025146,
"learning_rate": 2.864344903713155e-05,
"loss": 1.4836492538452148,
"step": 1880
},
{
"epoch": 0.4900181488203267,
"grad_norm": 2.013542652130127,
"learning_rate": 2.8625946563088363e-05,
"loss": 1.4833683967590332,
"step": 1890
},
{
"epoch": 0.49261083743842365,
"grad_norm": 2.020002841949463,
"learning_rate": 2.8608337319297248e-05,
"loss": 1.4674368858337403,
"step": 1900
},
{
"epoch": 0.4952035260565206,
"grad_norm": 1.9161850214004517,
"learning_rate": 2.8590621443740145e-05,
"loss": 1.476041030883789,
"step": 1910
},
{
"epoch": 0.4977962146746176,
"grad_norm": 2.2676491737365723,
"learning_rate": 2.8572799075234533e-05,
"loss": 1.4649261474609374,
"step": 1920
},
{
"epoch": 0.5003889032927146,
"grad_norm": 1.9518834352493286,
"learning_rate": 2.8554870353432345e-05,
"loss": 1.4670692443847657,
"step": 1930
},
{
"epoch": 0.5029815919108115,
"grad_norm": 1.8617761135101318,
"learning_rate": 2.853683541881888e-05,
"loss": 1.4522610664367677,
"step": 1940
},
{
"epoch": 0.5055742805289085,
"grad_norm": 2.056037425994873,
"learning_rate": 2.851869441271168e-05,
"loss": 1.454219913482666,
"step": 1950
},
{
"epoch": 0.5081669691470054,
"grad_norm": 1.6573052406311035,
"learning_rate": 2.8500447477259458e-05,
"loss": 1.4870268821716308,
"step": 1960
},
{
"epoch": 0.5107596577651025,
"grad_norm": 1.8644371032714844,
"learning_rate": 2.848209475544096e-05,
"loss": 1.4083456993103027,
"step": 1970
},
{
"epoch": 0.5133523463831994,
"grad_norm": 1.9450775384902954,
"learning_rate": 2.8463636391063838e-05,
"loss": 1.4940713882446288,
"step": 1980
},
{
"epoch": 0.5159450350012963,
"grad_norm": 1.9806098937988281,
"learning_rate": 2.8445072528763543e-05,
"loss": 1.4620475769042969,
"step": 1990
},
{
"epoch": 0.5185377236193933,
"grad_norm": 3.022106170654297,
"learning_rate": 2.8426403314002182e-05,
"loss": 1.465572452545166,
"step": 2000
},
{
"epoch": 0.5185377236193933,
"eval_loss": 1.4653197526931763,
"eval_runtime": 106.759,
"eval_samples_per_second": 15.212,
"eval_steps_per_second": 15.212,
"step": 2000
},
{
"epoch": 0.5211304122374902,
"grad_norm": 1.9036056995391846,
"learning_rate": 2.8407628893067384e-05,
"loss": 1.4682519912719727,
"step": 2010
},
{
"epoch": 0.5237231008555873,
"grad_norm": 1.9992440938949585,
"learning_rate": 2.8388749413071137e-05,
"loss": 1.445728874206543,
"step": 2020
},
{
"epoch": 0.5263157894736842,
"grad_norm": 1.8911775350570679,
"learning_rate": 2.8369765021948665e-05,
"loss": 1.4920975685119628,
"step": 2030
},
{
"epoch": 0.5289084780917812,
"grad_norm": 1.8128125667572021,
"learning_rate": 2.835067586845723e-05,
"loss": 1.4684887886047364,
"step": 2040
},
{
"epoch": 0.5315011667098781,
"grad_norm": 1.9973891973495483,
"learning_rate": 2.8331482102175e-05,
"loss": 1.4452502250671386,
"step": 2050
},
{
"epoch": 0.5340938553279752,
"grad_norm": 2.3160006999969482,
"learning_rate": 2.8312183873499874e-05,
"loss": 1.4670836448669433,
"step": 2060
},
{
"epoch": 0.5366865439460721,
"grad_norm": 3.0418002605438232,
"learning_rate": 2.8292781333648276e-05,
"loss": 1.4837977409362793,
"step": 2070
},
{
"epoch": 0.5392792325641691,
"grad_norm": 2.3682308197021484,
"learning_rate": 2.827327463465399e-05,
"loss": 1.3951645851135255,
"step": 2080
},
{
"epoch": 0.541871921182266,
"grad_norm": 2.0320494174957275,
"learning_rate": 2.8253663929366985e-05,
"loss": 1.4565988540649415,
"step": 2090
},
{
"epoch": 0.5444646098003629,
"grad_norm": 2.1780645847320557,
"learning_rate": 2.8233949371452175e-05,
"loss": 1.4297452926635743,
"step": 2100
},
{
"epoch": 0.54705729841846,
"grad_norm": 1.7980337142944336,
"learning_rate": 2.8214131115388252e-05,
"loss": 1.4422244071960448,
"step": 2110
},
{
"epoch": 0.5496499870365569,
"grad_norm": 2.1459109783172607,
"learning_rate": 2.8194209316466468e-05,
"loss": 1.4406557083129883,
"step": 2120
},
{
"epoch": 0.5522426756546539,
"grad_norm": 1.6945514678955078,
"learning_rate": 2.8174184130789397e-05,
"loss": 1.461403751373291,
"step": 2130
},
{
"epoch": 0.5548353642727508,
"grad_norm": 2.0341732501983643,
"learning_rate": 2.815405571526974e-05,
"loss": 1.4341069221496583,
"step": 2140
},
{
"epoch": 0.5574280528908478,
"grad_norm": 2.373396158218384,
"learning_rate": 2.813382422762908e-05,
"loss": 1.431840705871582,
"step": 2150
},
{
"epoch": 0.5600207415089448,
"grad_norm": 2.269397497177124,
"learning_rate": 2.811348982639665e-05,
"loss": 1.4188562393188477,
"step": 2160
},
{
"epoch": 0.5626134301270418,
"grad_norm": 1.8616985082626343,
"learning_rate": 2.8093052670908085e-05,
"loss": 1.4132248878479003,
"step": 2170
},
{
"epoch": 0.5652061187451387,
"grad_norm": 2.0249667167663574,
"learning_rate": 2.8072512921304183e-05,
"loss": 1.4546266555786134,
"step": 2180
},
{
"epoch": 0.5677988073632356,
"grad_norm": 1.8128606081008911,
"learning_rate": 2.8051870738529642e-05,
"loss": 1.4023919105529785,
"step": 2190
},
{
"epoch": 0.5703914959813327,
"grad_norm": 2.3444504737854004,
"learning_rate": 2.8031126284331807e-05,
"loss": 1.4102802276611328,
"step": 2200
},
{
"epoch": 0.5729841845994296,
"grad_norm": 1.9829933643341064,
"learning_rate": 2.8010279721259394e-05,
"loss": 1.3986042976379394,
"step": 2210
},
{
"epoch": 0.5755768732175266,
"grad_norm": 1.9822620153427124,
"learning_rate": 2.7989331212661233e-05,
"loss": 1.4648804664611816,
"step": 2220
},
{
"epoch": 0.5781695618356235,
"grad_norm": 1.8543516397476196,
"learning_rate": 2.796828092268495e-05,
"loss": 1.4484143257141113,
"step": 2230
},
{
"epoch": 0.5807622504537205,
"grad_norm": 2.4332776069641113,
"learning_rate": 2.7947129016275726e-05,
"loss": 1.4220855712890625,
"step": 2240
},
{
"epoch": 0.5833549390718175,
"grad_norm": 2.7334249019622803,
"learning_rate": 2.7925875659174986e-05,
"loss": 1.4403745651245117,
"step": 2250
},
{
"epoch": 0.5859476276899145,
"grad_norm": 2.114351987838745,
"learning_rate": 2.7904521017919085e-05,
"loss": 1.430521583557129,
"step": 2260
},
{
"epoch": 0.5885403163080114,
"grad_norm": 2.0641672611236572,
"learning_rate": 2.7883065259838027e-05,
"loss": 1.4642662048339843,
"step": 2270
},
{
"epoch": 0.5911330049261084,
"grad_norm": 1.8869924545288086,
"learning_rate": 2.7861508553054143e-05,
"loss": 1.4055952072143554,
"step": 2280
},
{
"epoch": 0.5937256935442053,
"grad_norm": 2.004831075668335,
"learning_rate": 2.7839851066480774e-05,
"loss": 1.4892603874206543,
"step": 2290
},
{
"epoch": 0.5963183821623023,
"grad_norm": 2.32817006111145,
"learning_rate": 2.7818092969820946e-05,
"loss": 1.4264138221740723,
"step": 2300
},
{
"epoch": 0.5989110707803993,
"grad_norm": 1.7029457092285156,
"learning_rate": 2.7796234433566045e-05,
"loss": 1.4583550453186036,
"step": 2310
},
{
"epoch": 0.6015037593984962,
"grad_norm": 3.0929977893829346,
"learning_rate": 2.7774275628994474e-05,
"loss": 1.4421024322509766,
"step": 2320
},
{
"epoch": 0.6040964480165932,
"grad_norm": 2.268214464187622,
"learning_rate": 2.775221672817032e-05,
"loss": 1.4478707313537598,
"step": 2330
},
{
"epoch": 0.6066891366346902,
"grad_norm": 2.46733021736145,
"learning_rate": 2.7730057903941997e-05,
"loss": 1.42803955078125,
"step": 2340
},
{
"epoch": 0.6092818252527872,
"grad_norm": 2.2705399990081787,
"learning_rate": 2.7707799329940905e-05,
"loss": 1.411041831970215,
"step": 2350
},
{
"epoch": 0.6118745138708841,
"grad_norm": 2.3257198333740234,
"learning_rate": 2.7685441180580045e-05,
"loss": 1.4445446014404297,
"step": 2360
},
{
"epoch": 0.6144672024889811,
"grad_norm": 1.7774648666381836,
"learning_rate": 2.7662983631052674e-05,
"loss": 1.3862037658691406,
"step": 2370
},
{
"epoch": 0.617059891107078,
"grad_norm": 1.9445077180862427,
"learning_rate": 2.7640426857330935e-05,
"loss": 1.4396771430969237,
"step": 2380
},
{
"epoch": 0.619652579725175,
"grad_norm": 1.7664343118667603,
"learning_rate": 2.7617771036164454e-05,
"loss": 1.4648002624511718,
"step": 2390
},
{
"epoch": 0.622245268343272,
"grad_norm": 1.8867270946502686,
"learning_rate": 2.7595016345078973e-05,
"loss": 1.4120534896850585,
"step": 2400
},
{
"epoch": 0.6248379569613689,
"grad_norm": 1.89567232131958,
"learning_rate": 2.757216296237496e-05,
"loss": 1.4406702995300293,
"step": 2410
},
{
"epoch": 0.6274306455794659,
"grad_norm": 1.906657099723816,
"learning_rate": 2.7549211067126216e-05,
"loss": 1.4870542526245116,
"step": 2420
},
{
"epoch": 0.6300233341975628,
"grad_norm": 2.4880735874176025,
"learning_rate": 2.7526160839178446e-05,
"loss": 1.4118797302246093,
"step": 2430
},
{
"epoch": 0.6326160228156599,
"grad_norm": 2.032667398452759,
"learning_rate": 2.7503012459147874e-05,
"loss": 1.4260003089904785,
"step": 2440
},
{
"epoch": 0.6352087114337568,
"grad_norm": 1.8648145198822021,
"learning_rate": 2.7479766108419822e-05,
"loss": 1.3991647720336915,
"step": 2450
},
{
"epoch": 0.6378014000518538,
"grad_norm": 2.0754902362823486,
"learning_rate": 2.745642196914729e-05,
"loss": 1.388667678833008,
"step": 2460
},
{
"epoch": 0.6403940886699507,
"grad_norm": 1.8423649072647095,
"learning_rate": 2.7432980224249518e-05,
"loss": 1.3759624481201171,
"step": 2470
},
{
"epoch": 0.6429867772880477,
"grad_norm": 2.0130422115325928,
"learning_rate": 2.7409441057410573e-05,
"loss": 1.4217917442321777,
"step": 2480
},
{
"epoch": 0.6455794659061447,
"grad_norm": 2.455008029937744,
"learning_rate": 2.7385804653077892e-05,
"loss": 1.456618881225586,
"step": 2490
},
{
"epoch": 0.6481721545242416,
"grad_norm": 1.8520952463150024,
"learning_rate": 2.7362071196460833e-05,
"loss": 1.4096790313720704,
"step": 2500
},
{
"epoch": 0.6481721545242416,
"eval_loss": 1.4393162727355957,
"eval_runtime": 106.7963,
"eval_samples_per_second": 15.207,
"eval_steps_per_second": 15.207,
"step": 2500
},
{
"epoch": 0.6507648431423386,
"grad_norm": 2.681671380996704,
"learning_rate": 2.733824087352925e-05,
"loss": 1.4034467697143556,
"step": 2510
},
{
"epoch": 0.6533575317604355,
"grad_norm": 1.83461332321167,
"learning_rate": 2.731431387101201e-05,
"loss": 1.449177074432373,
"step": 2520
},
{
"epoch": 0.6559502203785326,
"grad_norm": 2.2103195190429688,
"learning_rate": 2.729029037639553e-05,
"loss": 1.4404438018798829,
"step": 2530
},
{
"epoch": 0.6585429089966295,
"grad_norm": 2.1064565181732178,
"learning_rate": 2.7266170577922338e-05,
"loss": 1.4397605895996093,
"step": 2540
},
{
"epoch": 0.6611355976147265,
"grad_norm": 2.108570098876953,
"learning_rate": 2.7241954664589564e-05,
"loss": 1.4023234367370605,
"step": 2550
},
{
"epoch": 0.6637282862328234,
"grad_norm": 2.1899399757385254,
"learning_rate": 2.721764282614746e-05,
"loss": 1.3870964050292969,
"step": 2560
},
{
"epoch": 0.6663209748509205,
"grad_norm": 1.746741771697998,
"learning_rate": 2.719323525309795e-05,
"loss": 1.3814775466918945,
"step": 2570
},
{
"epoch": 0.6689136634690174,
"grad_norm": 1.656768560409546,
"learning_rate": 2.7168732136693093e-05,
"loss": 1.4419045448303223,
"step": 2580
},
{
"epoch": 0.6715063520871143,
"grad_norm": 3.0307178497314453,
"learning_rate": 2.714413366893361e-05,
"loss": 1.3995821952819825,
"step": 2590
},
{
"epoch": 0.6740990407052113,
"grad_norm": 2.4623610973358154,
"learning_rate": 2.711944004256738e-05,
"loss": 1.4528799057006836,
"step": 2600
},
{
"epoch": 0.6766917293233082,
"grad_norm": 1.8382195234298706,
"learning_rate": 2.7094651451087907e-05,
"loss": 1.3911012649536132,
"step": 2610
},
{
"epoch": 0.6792844179414053,
"grad_norm": 3.641540288925171,
"learning_rate": 2.706976808873283e-05,
"loss": 1.400215244293213,
"step": 2620
},
{
"epoch": 0.6818771065595022,
"grad_norm": 1.7411173582077026,
"learning_rate": 2.704479015048239e-05,
"loss": 1.404646873474121,
"step": 2630
},
{
"epoch": 0.6844697951775992,
"grad_norm": 2.683783769607544,
"learning_rate": 2.7019717832057904e-05,
"loss": 1.3790535926818848,
"step": 2640
},
{
"epoch": 0.6870624837956961,
"grad_norm": 1.8364287614822388,
"learning_rate": 2.699455132992022e-05,
"loss": 1.3990992546081542,
"step": 2650
},
{
"epoch": 0.6896551724137931,
"grad_norm": 2.025310754776001,
"learning_rate": 2.6969290841268202e-05,
"loss": 1.3751747131347656,
"step": 2660
},
{
"epoch": 0.6922478610318901,
"grad_norm": 2.1249916553497314,
"learning_rate": 2.6943936564037162e-05,
"loss": 1.4457441329956056,
"step": 2670
},
{
"epoch": 0.694840549649987,
"grad_norm": 2.500828504562378,
"learning_rate": 2.6918488696897317e-05,
"loss": 1.4443480491638183,
"step": 2680
},
{
"epoch": 0.697433238268084,
"grad_norm": 1.8109062910079956,
"learning_rate": 2.6892947439252235e-05,
"loss": 1.4244956016540526,
"step": 2690
},
{
"epoch": 0.7000259268861809,
"grad_norm": 1.89621901512146,
"learning_rate": 2.6867312991237273e-05,
"loss": 1.4510159492492676,
"step": 2700
},
{
"epoch": 0.702618615504278,
"grad_norm": 2.3199923038482666,
"learning_rate": 2.6841585553718004e-05,
"loss": 1.4402318000793457,
"step": 2710
},
{
"epoch": 0.7052113041223749,
"grad_norm": 2.2991762161254883,
"learning_rate": 2.6815765328288635e-05,
"loss": 1.4123191833496094,
"step": 2720
},
{
"epoch": 0.7078039927404719,
"grad_norm": 2.122211456298828,
"learning_rate": 2.678985251727046e-05,
"loss": 1.4056102752685546,
"step": 2730
},
{
"epoch": 0.7103966813585688,
"grad_norm": 2.127281665802002,
"learning_rate": 2.676384732371023e-05,
"loss": 1.403761100769043,
"step": 2740
},
{
"epoch": 0.7129893699766658,
"grad_norm": 1.9112132787704468,
"learning_rate": 2.6737749951378598e-05,
"loss": 1.4536319732666017,
"step": 2750
},
{
"epoch": 0.7155820585947628,
"grad_norm": 2.0709035396575928,
"learning_rate": 2.6711560604768498e-05,
"loss": 1.414163589477539,
"step": 2760
},
{
"epoch": 0.7181747472128598,
"grad_norm": 2.218517303466797,
"learning_rate": 2.668527948909356e-05,
"loss": 1.4018719673156739,
"step": 2770
},
{
"epoch": 0.7207674358309567,
"grad_norm": 2.193014621734619,
"learning_rate": 2.6658906810286496e-05,
"loss": 1.3908894538879395,
"step": 2780
},
{
"epoch": 0.7233601244490536,
"grad_norm": 2.02219820022583,
"learning_rate": 2.6632442774997485e-05,
"loss": 1.403691005706787,
"step": 2790
},
{
"epoch": 0.7259528130671506,
"grad_norm": 2.1701290607452393,
"learning_rate": 2.6605887590592547e-05,
"loss": 1.3933732986450196,
"step": 2800
},
{
"epoch": 0.7285455016852476,
"grad_norm": 2.215689182281494,
"learning_rate": 2.657924146515193e-05,
"loss": 1.421674633026123,
"step": 2810
},
{
"epoch": 0.7311381903033446,
"grad_norm": 1.9339823722839355,
"learning_rate": 2.655250460746848e-05,
"loss": 1.40692081451416,
"step": 2820
},
{
"epoch": 0.7337308789214415,
"grad_norm": 2.211097002029419,
"learning_rate": 2.6525677227045992e-05,
"loss": 1.4308547973632812,
"step": 2830
},
{
"epoch": 0.7363235675395385,
"grad_norm": 1.846948504447937,
"learning_rate": 2.649875953409758e-05,
"loss": 1.3544227600097656,
"step": 2840
},
{
"epoch": 0.7389162561576355,
"grad_norm": 2.253370761871338,
"learning_rate": 2.6471751739544025e-05,
"loss": 1.3974369049072266,
"step": 2850
},
{
"epoch": 0.7415089447757325,
"grad_norm": 2.584125280380249,
"learning_rate": 2.644465405501212e-05,
"loss": 1.374016284942627,
"step": 2860
},
{
"epoch": 0.7441016333938294,
"grad_norm": 2.0201058387756348,
"learning_rate": 2.6417466692833025e-05,
"loss": 1.3737750053405762,
"step": 2870
},
{
"epoch": 0.7466943220119263,
"grad_norm": 2.6641993522644043,
"learning_rate": 2.639018986604058e-05,
"loss": 1.4150461196899413,
"step": 2880
},
{
"epoch": 0.7492870106300233,
"grad_norm": 1.781146764755249,
"learning_rate": 2.6362823788369655e-05,
"loss": 1.4415416717529297,
"step": 2890
},
{
"epoch": 0.7518796992481203,
"grad_norm": 2.356492519378662,
"learning_rate": 2.6335368674254477e-05,
"loss": 1.3569241523742677,
"step": 2900
},
{
"epoch": 0.7544723878662173,
"grad_norm": 2.522078037261963,
"learning_rate": 2.6307824738826926e-05,
"loss": 1.3681366920471192,
"step": 2910
},
{
"epoch": 0.7570650764843142,
"grad_norm": 2.1201329231262207,
"learning_rate": 2.6280192197914877e-05,
"loss": 1.3817105293273926,
"step": 2920
},
{
"epoch": 0.7596577651024112,
"grad_norm": 2.2413649559020996,
"learning_rate": 2.6252471268040493e-05,
"loss": 1.400905704498291,
"step": 2930
},
{
"epoch": 0.7622504537205081,
"grad_norm": 2.4653563499450684,
"learning_rate": 2.6224662166418534e-05,
"loss": 1.403571605682373,
"step": 2940
},
{
"epoch": 0.7648431423386052,
"grad_norm": 2.268806219100952,
"learning_rate": 2.619676511095465e-05,
"loss": 1.4283622741699218,
"step": 2950
},
{
"epoch": 0.7674358309567021,
"grad_norm": 2.0980496406555176,
"learning_rate": 2.6168780320243677e-05,
"loss": 1.4140192985534668,
"step": 2960
},
{
"epoch": 0.7700285195747991,
"grad_norm": 1.9857174158096313,
"learning_rate": 2.6140708013567934e-05,
"loss": 1.3875184059143066,
"step": 2970
},
{
"epoch": 0.772621208192896,
"grad_norm": 1.9916791915893555,
"learning_rate": 2.6112548410895475e-05,
"loss": 1.365940475463867,
"step": 2980
},
{
"epoch": 0.775213896810993,
"grad_norm": 2.019430160522461,
"learning_rate": 2.6084301732878408e-05,
"loss": 1.443111515045166,
"step": 2990
},
{
"epoch": 0.77780658542909,
"grad_norm": 1.927951455116272,
"learning_rate": 2.605596820085112e-05,
"loss": 1.3543405532836914,
"step": 3000
},
{
"epoch": 0.77780658542909,
"eval_loss": 1.4166350364685059,
"eval_runtime": 107.7992,
"eval_samples_per_second": 15.065,
"eval_steps_per_second": 15.065,
"step": 3000
},
{
"epoch": 0.7803992740471869,
"grad_norm": 1.9161983728408813,
"learning_rate": 2.602754803682859e-05,
"loss": 1.3282281875610351,
"step": 3010
},
{
"epoch": 0.7829919626652839,
"grad_norm": 2.404080867767334,
"learning_rate": 2.5999041463504606e-05,
"loss": 1.3783291816711425,
"step": 3020
},
{
"epoch": 0.7855846512833808,
"grad_norm": 1.8124619722366333,
"learning_rate": 2.5970448704250046e-05,
"loss": 1.411635971069336,
"step": 3030
},
{
"epoch": 0.7881773399014779,
"grad_norm": 1.8134435415267944,
"learning_rate": 2.5941769983111126e-05,
"loss": 1.3853766441345214,
"step": 3040
},
{
"epoch": 0.7907700285195748,
"grad_norm": 2.2257771492004395,
"learning_rate": 2.5913005524807626e-05,
"loss": 1.375821304321289,
"step": 3050
},
{
"epoch": 0.7933627171376718,
"grad_norm": 2.07965087890625,
"learning_rate": 2.5884155554731156e-05,
"loss": 1.382816696166992,
"step": 3060
},
{
"epoch": 0.7959554057557687,
"grad_norm": 2.424480438232422,
"learning_rate": 2.5855220298943373e-05,
"loss": 1.3932998657226563,
"step": 3070
},
{
"epoch": 0.7985480943738656,
"grad_norm": 1.829237461090088,
"learning_rate": 2.582619998417421e-05,
"loss": 1.3987897872924804,
"step": 3080
},
{
"epoch": 0.8011407829919627,
"grad_norm": 2.279134511947632,
"learning_rate": 2.5797094837820093e-05,
"loss": 1.3800272941589355,
"step": 3090
},
{
"epoch": 0.8037334716100596,
"grad_norm": 1.6486223936080933,
"learning_rate": 2.5767905087942194e-05,
"loss": 1.4012795448303224,
"step": 3100
},
{
"epoch": 0.8063261602281566,
"grad_norm": 2.5895159244537354,
"learning_rate": 2.57386309632646e-05,
"loss": 1.3688448905944823,
"step": 3110
},
{
"epoch": 0.8089188488462535,
"grad_norm": 2.2628800868988037,
"learning_rate": 2.570927269317254e-05,
"loss": 1.3984854698181153,
"step": 3120
},
{
"epoch": 0.8115115374643506,
"grad_norm": 2.4762990474700928,
"learning_rate": 2.5679830507710586e-05,
"loss": 1.4081483840942384,
"step": 3130
},
{
"epoch": 0.8141042260824475,
"grad_norm": 2.6553421020507812,
"learning_rate": 2.5650304637580864e-05,
"loss": 1.4029975891113282,
"step": 3140
},
{
"epoch": 0.8166969147005445,
"grad_norm": 2.1516876220703125,
"learning_rate": 2.562069531414122e-05,
"loss": 1.376172161102295,
"step": 3150
},
{
"epoch": 0.8192896033186414,
"grad_norm": 1.897744059562683,
"learning_rate": 2.5591002769403423e-05,
"loss": 1.4495765686035156,
"step": 3160
},
{
"epoch": 0.8218822919367385,
"grad_norm": 1.8410879373550415,
"learning_rate": 2.5561227236031354e-05,
"loss": 1.378575611114502,
"step": 3170
},
{
"epoch": 0.8244749805548354,
"grad_norm": 1.9492700099945068,
"learning_rate": 2.553136894733916e-05,
"loss": 1.3822572708129883,
"step": 3180
},
{
"epoch": 0.8270676691729323,
"grad_norm": 2.2721168994903564,
"learning_rate": 2.550142813728945e-05,
"loss": 1.3540994644165039,
"step": 3190
},
{
"epoch": 0.8296603577910293,
"grad_norm": 1.6297799348831177,
"learning_rate": 2.5471405040491446e-05,
"loss": 1.3411558151245118,
"step": 3200
},
{
"epoch": 0.8322530464091262,
"grad_norm": 2.260117292404175,
"learning_rate": 2.5441299892199153e-05,
"loss": 1.322674560546875,
"step": 3210
},
{
"epoch": 0.8348457350272233,
"grad_norm": 2.4971811771392822,
"learning_rate": 2.541111292830951e-05,
"loss": 1.4200034141540527,
"step": 3220
},
{
"epoch": 0.8374384236453202,
"grad_norm": 2.0395963191986084,
"learning_rate": 2.5380844385360543e-05,
"loss": 1.4156583786010741,
"step": 3230
},
{
"epoch": 0.8400311122634172,
"grad_norm": 1.8945432901382446,
"learning_rate": 2.5350494500529516e-05,
"loss": 1.392031192779541,
"step": 3240
},
{
"epoch": 0.8426238008815141,
"grad_norm": 1.8795114755630493,
"learning_rate": 2.5320063511631065e-05,
"loss": 1.3640775680541992,
"step": 3250
},
{
"epoch": 0.8452164894996111,
"grad_norm": 2.0058376789093018,
"learning_rate": 2.5289551657115345e-05,
"loss": 1.3475787162780761,
"step": 3260
},
{
"epoch": 0.8478091781177081,
"grad_norm": 1.9326412677764893,
"learning_rate": 2.5258959176066147e-05,
"loss": 1.384262752532959,
"step": 3270
},
{
"epoch": 0.850401866735805,
"grad_norm": 2.3330800533294678,
"learning_rate": 2.522828630819904e-05,
"loss": 1.4128545761108398,
"step": 3280
},
{
"epoch": 0.852994555353902,
"grad_norm": 2.0641918182373047,
"learning_rate": 2.5197533293859478e-05,
"loss": 1.3618906021118165,
"step": 3290
},
{
"epoch": 0.8555872439719989,
"grad_norm": 2.4750313758850098,
"learning_rate": 2.516670037402093e-05,
"loss": 1.3589738845825194,
"step": 3300
},
{
"epoch": 0.858179932590096,
"grad_norm": 2.6838135719299316,
"learning_rate": 2.5135787790282992e-05,
"loss": 1.395717239379883,
"step": 3310
},
{
"epoch": 0.8607726212081929,
"grad_norm": 3.1425156593322754,
"learning_rate": 2.5104795784869467e-05,
"loss": 1.3734113693237304,
"step": 3320
},
{
"epoch": 0.8633653098262899,
"grad_norm": 2.109119176864624,
"learning_rate": 2.5073724600626512e-05,
"loss": 1.3802095413208009,
"step": 3330
},
{
"epoch": 0.8659579984443868,
"grad_norm": 1.866578459739685,
"learning_rate": 2.504257448102069e-05,
"loss": 1.3721683502197266,
"step": 3340
},
{
"epoch": 0.8685506870624838,
"grad_norm": 1.9887162446975708,
"learning_rate": 2.5011345670137098e-05,
"loss": 1.3654733657836915,
"step": 3350
},
{
"epoch": 0.8711433756805808,
"grad_norm": 2.299468517303467,
"learning_rate": 2.4980038412677435e-05,
"loss": 1.3257240295410155,
"step": 3360
},
{
"epoch": 0.8737360642986778,
"grad_norm": 1.8503848314285278,
"learning_rate": 2.494865295395809e-05,
"loss": 1.3851592063903808,
"step": 3370
},
{
"epoch": 0.8763287529167747,
"grad_norm": 2.9072635173797607,
"learning_rate": 2.4917189539908212e-05,
"loss": 1.4008994102478027,
"step": 3380
},
{
"epoch": 0.8789214415348716,
"grad_norm": 2.2361841201782227,
"learning_rate": 2.4885648417067797e-05,
"loss": 1.4155900955200196,
"step": 3390
},
{
"epoch": 0.8815141301529686,
"grad_norm": 1.5103061199188232,
"learning_rate": 2.485402983258575e-05,
"loss": 1.383201503753662,
"step": 3400
},
{
"epoch": 0.8841068187710656,
"grad_norm": 2.3880326747894287,
"learning_rate": 2.4822334034217943e-05,
"loss": 1.422282600402832,
"step": 3410
},
{
"epoch": 0.8866995073891626,
"grad_norm": 2.0728979110717773,
"learning_rate": 2.4790561270325282e-05,
"loss": 1.3880194664001464,
"step": 3420
},
{
"epoch": 0.8892921960072595,
"grad_norm": 2.1829416751861572,
"learning_rate": 2.475871178987175e-05,
"loss": 1.3314918518066405,
"step": 3430
},
{
"epoch": 0.8918848846253565,
"grad_norm": 1.9193717241287231,
"learning_rate": 2.472678584242247e-05,
"loss": 1.357210636138916,
"step": 3440
},
{
"epoch": 0.8944775732434534,
"grad_norm": 2.5747568607330322,
"learning_rate": 2.469478367814174e-05,
"loss": 1.3450111389160155,
"step": 3450
},
{
"epoch": 0.8970702618615505,
"grad_norm": 2.431907892227173,
"learning_rate": 2.4662705547791078e-05,
"loss": 1.336769199371338,
"step": 3460
},
{
"epoch": 0.8996629504796474,
"grad_norm": 2.294434070587158,
"learning_rate": 2.4630551702727248e-05,
"loss": 1.3879555702209472,
"step": 3470
},
{
"epoch": 0.9022556390977443,
"grad_norm": 2.3190789222717285,
"learning_rate": 2.4598322394900304e-05,
"loss": 1.3749018669128419,
"step": 3480
},
{
"epoch": 0.9048483277158413,
"grad_norm": 2.1272852420806885,
"learning_rate": 2.4566017876851605e-05,
"loss": 1.3837257385253907,
"step": 3490
},
{
"epoch": 0.9074410163339383,
"grad_norm": 2.3905060291290283,
"learning_rate": 2.4533638401711846e-05,
"loss": 1.406574535369873,
"step": 3500
},
{
"epoch": 0.9074410163339383,
"eval_loss": 1.3983689546585083,
"eval_runtime": 106.204,
"eval_samples_per_second": 15.291,
"eval_steps_per_second": 15.291,
"step": 3500
},
{
"epoch": 0.9100337049520353,
"grad_norm": 2.7370753288269043,
"learning_rate": 2.4501184223199048e-05,
"loss": 1.3768909454345704,
"step": 3510
},
{
"epoch": 0.9126263935701322,
"grad_norm": 2.2996416091918945,
"learning_rate": 2.4468655595616623e-05,
"loss": 1.3813292503356933,
"step": 3520
},
{
"epoch": 0.9152190821882292,
"grad_norm": 2.329495906829834,
"learning_rate": 2.4436052773851317e-05,
"loss": 1.3564909934997558,
"step": 3530
},
{
"epoch": 0.9178117708063261,
"grad_norm": 1.9293724298477173,
"learning_rate": 2.4403376013371267e-05,
"loss": 1.4013836860656739,
"step": 3540
},
{
"epoch": 0.9204044594244232,
"grad_norm": 1.7574388980865479,
"learning_rate": 2.4370625570223964e-05,
"loss": 1.4045954704284669,
"step": 3550
},
{
"epoch": 0.9229971480425201,
"grad_norm": 2.2382349967956543,
"learning_rate": 2.433780170103426e-05,
"loss": 1.4007040977478027,
"step": 3560
},
{
"epoch": 0.925589836660617,
"grad_norm": 1.8389666080474854,
"learning_rate": 2.430490466300236e-05,
"loss": 1.3762280464172363,
"step": 3570
},
{
"epoch": 0.928182525278714,
"grad_norm": 2.4616801738739014,
"learning_rate": 2.427193471390181e-05,
"loss": 1.3494554519653321,
"step": 3580
},
{
"epoch": 0.930775213896811,
"grad_norm": 2.219825506210327,
"learning_rate": 2.4238892112077456e-05,
"loss": 1.4177600860595703,
"step": 3590
},
{
"epoch": 0.933367902514908,
"grad_norm": 2.9395411014556885,
"learning_rate": 2.420577711644344e-05,
"loss": 1.3394248008728027,
"step": 3600
},
{
"epoch": 0.9359605911330049,
"grad_norm": 2.225367784500122,
"learning_rate": 2.417258998648117e-05,
"loss": 1.3538402557373046,
"step": 3610
},
{
"epoch": 0.9385532797511019,
"grad_norm": 2.441420793533325,
"learning_rate": 2.413933098223727e-05,
"loss": 1.3856266975402831,
"step": 3620
},
{
"epoch": 0.9411459683691988,
"grad_norm": 1.911476731300354,
"learning_rate": 2.4106000364321562e-05,
"loss": 1.384410285949707,
"step": 3630
},
{
"epoch": 0.9437386569872959,
"grad_norm": 2.361011505126953,
"learning_rate": 2.4072598393905027e-05,
"loss": 1.3323063850402832,
"step": 3640
},
{
"epoch": 0.9463313456053928,
"grad_norm": 1.8206897974014282,
"learning_rate": 2.4039125332717723e-05,
"loss": 1.3785643577575684,
"step": 3650
},
{
"epoch": 0.9489240342234898,
"grad_norm": 2.124385118484497,
"learning_rate": 2.4005581443046777e-05,
"loss": 1.3628316879272462,
"step": 3660
},
{
"epoch": 0.9515167228415867,
"grad_norm": 2.1028757095336914,
"learning_rate": 2.3971966987734306e-05,
"loss": 1.3821578979492188,
"step": 3670
},
{
"epoch": 0.9541094114596836,
"grad_norm": 2.0314295291900635,
"learning_rate": 2.3938282230175367e-05,
"loss": 1.36130952835083,
"step": 3680
},
{
"epoch": 0.9567021000777807,
"grad_norm": 1.9069913625717163,
"learning_rate": 2.390452743431587e-05,
"loss": 1.3943718910217284,
"step": 3690
},
{
"epoch": 0.9592947886958776,
"grad_norm": 2.211771249771118,
"learning_rate": 2.3870702864650566e-05,
"loss": 1.2942493438720704,
"step": 3700
},
{
"epoch": 0.9618874773139746,
"grad_norm": 1.8472073078155518,
"learning_rate": 2.3836808786220898e-05,
"loss": 1.3906041145324708,
"step": 3710
},
{
"epoch": 0.9644801659320715,
"grad_norm": 1.956861138343811,
"learning_rate": 2.3802845464612993e-05,
"loss": 1.3306471824645996,
"step": 3720
},
{
"epoch": 0.9670728545501686,
"grad_norm": 2.0990774631500244,
"learning_rate": 2.376881316595553e-05,
"loss": 1.3751443862915038,
"step": 3730
},
{
"epoch": 0.9696655431682655,
"grad_norm": 2.325157403945923,
"learning_rate": 2.3734712156917696e-05,
"loss": 1.3435355186462403,
"step": 3740
},
{
"epoch": 0.9722582317863625,
"grad_norm": 1.922559142112732,
"learning_rate": 2.3700542704707047e-05,
"loss": 1.3255187034606934,
"step": 3750
},
{
"epoch": 0.9748509204044594,
"grad_norm": 1.7330152988433838,
"learning_rate": 2.3666305077067487e-05,
"loss": 1.3793014526367187,
"step": 3760
},
{
"epoch": 0.9774436090225563,
"grad_norm": 2.2448415756225586,
"learning_rate": 2.363199954227709e-05,
"loss": 1.3383570671081544,
"step": 3770
},
{
"epoch": 0.9800362976406534,
"grad_norm": 2.524059295654297,
"learning_rate": 2.3597626369146042e-05,
"loss": 1.34091796875,
"step": 3780
},
{
"epoch": 0.9826289862587503,
"grad_norm": 2.139561176300049,
"learning_rate": 2.3563185827014547e-05,
"loss": 1.3502127647399902,
"step": 3790
},
{
"epoch": 0.9852216748768473,
"grad_norm": 2.0120010375976562,
"learning_rate": 2.3528678185750673e-05,
"loss": 1.3552865982055664,
"step": 3800
},
{
"epoch": 0.9878143634949442,
"grad_norm": 1.6602357625961304,
"learning_rate": 2.349410371574827e-05,
"loss": 1.4221920013427733,
"step": 3810
},
{
"epoch": 0.9904070521130413,
"grad_norm": 2.8545217514038086,
"learning_rate": 2.3459462687924843e-05,
"loss": 1.330784225463867,
"step": 3820
},
{
"epoch": 0.9929997407311382,
"grad_norm": 2.017984628677368,
"learning_rate": 2.3424755373719434e-05,
"loss": 1.3669758796691895,
"step": 3830
},
{
"epoch": 0.9955924293492352,
"grad_norm": 1.9509679079055786,
"learning_rate": 2.3389982045090476e-05,
"loss": 1.3680663108825684,
"step": 3840
},
{
"epoch": 0.9981851179673321,
"grad_norm": 2.055434226989746,
"learning_rate": 2.3355142974513694e-05,
"loss": 1.3688017845153808,
"step": 3850
},
{
"epoch": 1.0007778065854291,
"grad_norm": 1.8395020961761475,
"learning_rate": 2.3320238434979938e-05,
"loss": 1.382623291015625,
"step": 3860
},
{
"epoch": 1.003370495203526,
"grad_norm": 1.9601069688796997,
"learning_rate": 2.3285268699993057e-05,
"loss": 1.3295875549316407,
"step": 3870
},
{
"epoch": 1.005963183821623,
"grad_norm": 1.961052417755127,
"learning_rate": 2.3250234043567762e-05,
"loss": 1.3183087348937987,
"step": 3880
},
{
"epoch": 1.00855587243972,
"grad_norm": 1.9219014644622803,
"learning_rate": 2.3215134740227477e-05,
"loss": 1.368846607208252,
"step": 3890
},
{
"epoch": 1.011148561057817,
"grad_norm": 3.1595990657806396,
"learning_rate": 2.3179971065002175e-05,
"loss": 1.3154706001281737,
"step": 3900
},
{
"epoch": 1.013741249675914,
"grad_norm": 1.7380744218826294,
"learning_rate": 2.3144743293426233e-05,
"loss": 1.3345220565795899,
"step": 3910
},
{
"epoch": 1.0163339382940109,
"grad_norm": 1.8892579078674316,
"learning_rate": 2.310945170153628e-05,
"loss": 1.316334342956543,
"step": 3920
},
{
"epoch": 1.0189266269121078,
"grad_norm": 2.266141891479492,
"learning_rate": 2.307409656586902e-05,
"loss": 1.3499970436096191,
"step": 3930
},
{
"epoch": 1.021519315530205,
"grad_norm": 3.2296090126037598,
"learning_rate": 2.303867816345907e-05,
"loss": 1.314054298400879,
"step": 3940
},
{
"epoch": 1.0241120041483018,
"grad_norm": 2.2091379165649414,
"learning_rate": 2.30031967718368e-05,
"loss": 1.3708792686462403,
"step": 3950
},
{
"epoch": 1.0267046927663988,
"grad_norm": 2.0963046550750732,
"learning_rate": 2.2967652669026133e-05,
"loss": 1.3194661140441895,
"step": 3960
},
{
"epoch": 1.0292973813844957,
"grad_norm": 1.9970223903656006,
"learning_rate": 2.2932046133542407e-05,
"loss": 1.3267878532409667,
"step": 3970
},
{
"epoch": 1.0318900700025926,
"grad_norm": 2.3387584686279297,
"learning_rate": 2.289637744439013e-05,
"loss": 1.366102695465088,
"step": 3980
},
{
"epoch": 1.0344827586206897,
"grad_norm": 2.5074076652526855,
"learning_rate": 2.2860646881060865e-05,
"loss": 1.3781256675720215,
"step": 3990
},
{
"epoch": 1.0370754472387866,
"grad_norm": 2.5516645908355713,
"learning_rate": 2.2824854723530996e-05,
"loss": 1.3624156951904296,
"step": 4000
},
{
"epoch": 1.0370754472387866,
"eval_loss": 1.3833566904067993,
"eval_runtime": 102.245,
"eval_samples_per_second": 15.883,
"eval_steps_per_second": 15.883,
"step": 4000
},
{
"epoch": 1.0396681358568836,
"grad_norm": 2.016517400741577,
"learning_rate": 2.2789001252259552e-05,
"loss": 1.3006293296813964,
"step": 4010
},
{
"epoch": 1.0422608244749805,
"grad_norm": 2.6499552726745605,
"learning_rate": 2.2753086748185973e-05,
"loss": 1.380314540863037,
"step": 4020
},
{
"epoch": 1.0448535130930776,
"grad_norm": 2.3887665271759033,
"learning_rate": 2.271711149272798e-05,
"loss": 1.3405844688415527,
"step": 4030
},
{
"epoch": 1.0474462017111745,
"grad_norm": 2.200329542160034,
"learning_rate": 2.26810757677793e-05,
"loss": 1.329063892364502,
"step": 4040
},
{
"epoch": 1.0500388903292714,
"grad_norm": 2.6909101009368896,
"learning_rate": 2.2644979855707486e-05,
"loss": 1.3441936492919921,
"step": 4050
},
{
"epoch": 1.0526315789473684,
"grad_norm": 2.213625192642212,
"learning_rate": 2.2608824039351723e-05,
"loss": 1.3089025497436524,
"step": 4060
},
{
"epoch": 1.0552242675654653,
"grad_norm": 2.323392152786255,
"learning_rate": 2.2572608602020563e-05,
"loss": 1.288233470916748,
"step": 4070
},
{
"epoch": 1.0578169561835624,
"grad_norm": 2.1220569610595703,
"learning_rate": 2.2536333827489763e-05,
"loss": 1.3579096794128418,
"step": 4080
},
{
"epoch": 1.0604096448016593,
"grad_norm": 2.1429178714752197,
"learning_rate": 2.25e-05,
"loss": 1.3310029983520508,
"step": 4090
},
{
"epoch": 1.0630023334197563,
"grad_norm": 2.5161702632904053,
"learning_rate": 2.2463607404254716e-05,
"loss": 1.3171113014221192,
"step": 4100
},
{
"epoch": 1.0655950220378532,
"grad_norm": 1.9193251132965088,
"learning_rate": 2.2427156325417814e-05,
"loss": 1.386863613128662,
"step": 4110
},
{
"epoch": 1.0681877106559503,
"grad_norm": 2.372840404510498,
"learning_rate": 2.2390647049111472e-05,
"loss": 1.376681137084961,
"step": 4120
},
{
"epoch": 1.0707803992740472,
"grad_norm": 1.9672595262527466,
"learning_rate": 2.2354079861413896e-05,
"loss": 1.2816861152648926,
"step": 4130
},
{
"epoch": 1.0733730878921441,
"grad_norm": 2.1304564476013184,
"learning_rate": 2.2317455048857048e-05,
"loss": 1.3413150787353516,
"step": 4140
},
{
"epoch": 1.075965776510241,
"grad_norm": 2.1898391246795654,
"learning_rate": 2.2280772898424454e-05,
"loss": 1.3329020500183106,
"step": 4150
},
{
"epoch": 1.0785584651283382,
"grad_norm": 2.1792447566986084,
"learning_rate": 2.22440336975489e-05,
"loss": 1.3798859596252442,
"step": 4160
},
{
"epoch": 1.0811511537464351,
"grad_norm": 1.954807162284851,
"learning_rate": 2.220723773411023e-05,
"loss": 1.3178838729858398,
"step": 4170
},
{
"epoch": 1.083743842364532,
"grad_norm": 2.392474889755249,
"learning_rate": 2.217038529643305e-05,
"loss": 1.356794834136963,
"step": 4180
},
{
"epoch": 1.086336530982629,
"grad_norm": 2.129551887512207,
"learning_rate": 2.213347667328449e-05,
"loss": 1.3579363822937012,
"step": 4190
},
{
"epoch": 1.0889292196007259,
"grad_norm": 2.6340548992156982,
"learning_rate": 2.2096512153871938e-05,
"loss": 1.3126588821411134,
"step": 4200
},
{
"epoch": 1.091521908218823,
"grad_norm": 1.7375941276550293,
"learning_rate": 2.2059492027840766e-05,
"loss": 1.3306168556213378,
"step": 4210
},
{
"epoch": 1.09411459683692,
"grad_norm": 2.017371892929077,
"learning_rate": 2.202241658527207e-05,
"loss": 1.3037184715270995,
"step": 4220
},
{
"epoch": 1.0967072854550168,
"grad_norm": 2.2290050983428955,
"learning_rate": 2.1985286116680404e-05,
"loss": 1.3164632797241211,
"step": 4230
},
{
"epoch": 1.0992999740731138,
"grad_norm": 2.352050542831421,
"learning_rate": 2.1948100913011475e-05,
"loss": 1.3569565773010255,
"step": 4240
},
{
"epoch": 1.101892662691211,
"grad_norm": 2.4853835105895996,
"learning_rate": 2.1910861265639897e-05,
"loss": 1.3593795776367188,
"step": 4250
},
{
"epoch": 1.1044853513093078,
"grad_norm": 1.8722959756851196,
"learning_rate": 2.1873567466366874e-05,
"loss": 1.3257516860961913,
"step": 4260
},
{
"epoch": 1.1070780399274047,
"grad_norm": 2.722330093383789,
"learning_rate": 2.1836219807417953e-05,
"loss": 1.330971622467041,
"step": 4270
},
{
"epoch": 1.1096707285455016,
"grad_norm": 2.2173590660095215,
"learning_rate": 2.1798818581440696e-05,
"loss": 1.3463165283203125,
"step": 4280
},
{
"epoch": 1.1122634171635986,
"grad_norm": 3.126631259918213,
"learning_rate": 2.1761364081502414e-05,
"loss": 1.3597925186157227,
"step": 4290
},
{
"epoch": 1.1148561057816957,
"grad_norm": 2.877528429031372,
"learning_rate": 2.1723856601087854e-05,
"loss": 1.3126080513000489,
"step": 4300
},
{
"epoch": 1.1174487943997926,
"grad_norm": 2.2296814918518066,
"learning_rate": 2.1686296434096913e-05,
"loss": 1.3086021423339844,
"step": 4310
},
{
"epoch": 1.1200414830178895,
"grad_norm": 2.710542917251587,
"learning_rate": 2.164868387484232e-05,
"loss": 1.3922597885131835,
"step": 4320
},
{
"epoch": 1.1226341716359864,
"grad_norm": 2.929488182067871,
"learning_rate": 2.161101921804734e-05,
"loss": 1.3066654205322266,
"step": 4330
},
{
"epoch": 1.1252268602540836,
"grad_norm": 2.615806818008423,
"learning_rate": 2.1573302758843466e-05,
"loss": 1.2853778839111327,
"step": 4340
},
{
"epoch": 1.1278195488721805,
"grad_norm": 2.019347906112671,
"learning_rate": 2.1535534792768094e-05,
"loss": 1.2719595909118653,
"step": 4350
},
{
"epoch": 1.1304122374902774,
"grad_norm": 2.1242213249206543,
"learning_rate": 2.1497715615762226e-05,
"loss": 1.3072625160217286,
"step": 4360
},
{
"epoch": 1.1330049261083743,
"grad_norm": 2.1568093299865723,
"learning_rate": 2.145984552416814e-05,
"loss": 1.264606761932373,
"step": 4370
},
{
"epoch": 1.1355976147264712,
"grad_norm": 2.133017063140869,
"learning_rate": 2.1421924814727058e-05,
"loss": 1.355167770385742,
"step": 4380
},
{
"epoch": 1.1381903033445684,
"grad_norm": 2.135843515396118,
"learning_rate": 2.1383953784576843e-05,
"loss": 1.3303000450134277,
"step": 4390
},
{
"epoch": 1.1407829919626653,
"grad_norm": 2.278923511505127,
"learning_rate": 2.134593273124965e-05,
"loss": 1.3016818046569825,
"step": 4400
},
{
"epoch": 1.1433756805807622,
"grad_norm": 1.8876979351043701,
"learning_rate": 2.1307861952669617e-05,
"loss": 1.335930347442627,
"step": 4410
},
{
"epoch": 1.1459683691988591,
"grad_norm": 1.9353163242340088,
"learning_rate": 2.1269741747150506e-05,
"loss": 1.314860725402832,
"step": 4420
},
{
"epoch": 1.1485610578169563,
"grad_norm": 1.979556918144226,
"learning_rate": 2.123157241339338e-05,
"loss": 1.3145623207092285,
"step": 4430
},
{
"epoch": 1.1511537464350532,
"grad_norm": 2.4763894081115723,
"learning_rate": 2.1193354250484268e-05,
"loss": 1.340696144104004,
"step": 4440
},
{
"epoch": 1.15374643505315,
"grad_norm": 2.164473295211792,
"learning_rate": 2.115508755789179e-05,
"loss": 1.3050660133361816,
"step": 4450
},
{
"epoch": 1.156339123671247,
"grad_norm": 2.4587583541870117,
"learning_rate": 2.1116772635464863e-05,
"loss": 1.2169719696044923,
"step": 4460
},
{
"epoch": 1.1589318122893442,
"grad_norm": 2.6631503105163574,
"learning_rate": 2.10784097834303e-05,
"loss": 1.294164276123047,
"step": 4470
},
{
"epoch": 1.161524500907441,
"grad_norm": 2.023618221282959,
"learning_rate": 2.103999930239049e-05,
"loss": 1.3531569480895995,
"step": 4480
},
{
"epoch": 1.164117189525538,
"grad_norm": 3.4511115550994873,
"learning_rate": 2.1001541493321022e-05,
"loss": 1.2678154945373534,
"step": 4490
},
{
"epoch": 1.166709878143635,
"grad_norm": 2.3503637313842773,
"learning_rate": 2.096303665756835e-05,
"loss": 1.3296841621398925,
"step": 4500
},
{
"epoch": 1.166709878143635,
"eval_loss": 1.3733285665512085,
"eval_runtime": 102.1475,
"eval_samples_per_second": 15.899,
"eval_steps_per_second": 15.899,
"step": 4500
}
],
"logging_steps": 10,
"max_steps": 11571,
"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": false
},
"attributes": {}
}
},
"total_flos": 2.162907701796864e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}