TimeCapsuleLLM-ja-v4 / training_report.json
trtd56's picture
Release phase6 staging
6f645f3 verified
Raw
History Blame Contribute Delete
29.5 kB
{
"iterations": 45300,
"parameter_count": 1046066688,
"tokens_per_step": 262144,
"processed_tokens": 11875123200,
"elapsed_seconds": 529599.8804617687,
"best_validation_loss": 3.3402066230773926,
"history": [
{
"iteration": 500,
"train_loss": 6.373349666595459,
"validation_loss": 6.335325717926025,
"learning_rate": 0.00024998914333562564,
"elapsed_seconds": 5767.518404414877,
"projected_total_hours": 145.1492131777744,
"projected_total_cost_usd": 201.75740631710642
},
{
"iteration": 1000,
"train_loss": 4.988532066345215,
"validation_loss": 4.971802234649658,
"learning_rate": 0.0002498660738422774,
"elapsed_seconds": 11607.223960213829,
"projected_total_hours": 146.05756816602403,
"projected_total_cost_usd": 203.02001975077337
},
{
"iteration": 1500,
"train_loss": 4.607588768005371,
"validation_loss": 4.590364456176758,
"learning_rate": 0.0002496061035966192,
"elapsed_seconds": 17444.452618559822,
"projected_total_hours": 146.33957474458518,
"projected_total_cost_usd": 203.41200889497338
},
{
"iteration": 2000,
"train_loss": 4.4110026359558105,
"validation_loss": 4.396660327911377,
"learning_rate": 0.00024920954933234997,
"elapsed_seconds": 23283.12628326984,
"projected_total_hours": 146.4896695322394,
"projected_total_cost_usd": 203.62064064981274
},
{
"iteration": 2500,
"train_loss": 4.2808990478515625,
"validation_loss": 4.268635272979736,
"learning_rate": 0.0002486768941897562,
"elapsed_seconds": 29123.792723594932,
"projected_total_hours": 146.58975670876117,
"projected_total_cost_usd": 203.759761825178
},
{
"iteration": 3000,
"train_loss": 4.190364837646484,
"validation_loss": 4.175224781036377,
"learning_rate": 0.00024800878712707996,
"elapsed_seconds": 34969.42657046695,
"projected_total_hours": 146.67731700390306,
"projected_total_cost_usd": 203.88147063542525
},
{
"iteration": 3500,
"train_loss": 4.114880561828613,
"validation_loss": 4.1017656326293945,
"learning_rate": 0.00024720604212986305,
"elapsed_seconds": 40825.30353703792,
"projected_total_hours": 146.77668652601727,
"projected_total_cost_usd": 204.01959427116398
},
{
"iteration": 4000,
"train_loss": 4.059500217437744,
"validation_loss": 4.044155120849609,
"learning_rate": 0.00024626963721923123,
"elapsed_seconds": 46672.65582661284,
"projected_total_hours": 146.8243964545529,
"projected_total_cost_usd": 204.08591107182852
},
{
"iteration": 4500,
"train_loss": 8.15172290802002,
"validation_loss": 8.112296104431152,
"learning_rate": 0.00024520071326032596,
"elapsed_seconds": 52528.73340205988,
"projected_total_hours": 146.8859026613156,
"projected_total_cost_usd": 204.17140469922867
},
{
"iteration": 5000,
"train_loss": 4.006167411804199,
"validation_loss": 3.99216365814209,
"learning_rate": 0.0002440005725723361,
"elapsed_seconds": 58357.20548674604,
"projected_total_hours": 146.86563380831086,
"projected_total_cost_usd": 204.1432309935521
},
{
"iteration": 5500,
"train_loss": 3.950077772140503,
"validation_loss": 3.9378490447998047,
"learning_rate": 0.00024267067734182245,
"elapsed_seconds": 64213.86831258284,
"projected_total_hours": 146.91354720000012,
"projected_total_cost_usd": 204.20983060800015
},
{
"iteration": 6000,
"train_loss": 3.9144349098205566,
"validation_loss": 3.9045145511627197,
"learning_rate": 0.0002412126478412687,
"elapsed_seconds": 70062.76474088593,
"projected_total_hours": 146.93718716491355,
"projected_total_cost_usd": 204.24269015922982
},
{
"iteration": 6500,
"train_loss": 3.884676933288574,
"validation_loss": 3.875600814819336,
"learning_rate": 0.00023962826045502908,
"elapsed_seconds": 75910.68644157494,
"projected_total_hours": 146.9553032394592,
"projected_total_cost_usd": 204.26787150284827
},
{
"iteration": 7000,
"train_loss": 3.8586838245391846,
"validation_loss": 3.849705219268799,
"learning_rate": 0.00023791944551507753,
"elapsed_seconds": 81744.92833834188,
"projected_total_hours": 146.94624022725742,
"projected_total_cost_usd": 204.2552739158878
},
{
"iteration": 7500,
"train_loss": 3.8353729248046875,
"validation_loss": 3.826043128967285,
"learning_rate": 0.00023608828494919563,
"elapsed_seconds": 87577.26776477997,
"projected_total_hours": 146.93519369424195,
"projected_total_cost_usd": 204.23991923499628
},
{
"iteration": 8000,
"train_loss": 3.810929775238037,
"validation_loss": 3.804882764816284,
"learning_rate": 0.00023413700974446423,
"elapsed_seconds": 93414.80510617001,
"projected_total_hours": 146.93370386491324,
"projected_total_cost_usd": 204.2378483722294
},
{
"iteration": 8500,
"train_loss": 3.7886407375335693,
"validation_loss": 3.783992290496826,
"learning_rate": 0.00023206799722914946,
"elapsed_seconds": 99244.98037643894,
"projected_total_hours": 146.92149055727725,
"projected_total_cost_usd": 204.22087187461537
},
{
"iteration": 9000,
"train_loss": 3.766958713531494,
"validation_loss": 3.7680282592773438,
"learning_rate": 0.0002298837681762942,
"elapsed_seconds": 105085.86910354486,
"projected_total_hours": 146.92561328365994,
"projected_total_cost_usd": 204.2266024642873
},
{
"iteration": 9500,
"train_loss": 3.7498161792755127,
"validation_loss": 3.7501485347747803,
"learning_rate": 0.00022758698373254472,
"elapsed_seconds": 110928.114993172,
"projected_total_hours": 146.93109968393833,
"projected_total_cost_usd": 204.23422856067427
},
{
"iteration": 10000,
"train_loss": 3.730133056640625,
"validation_loss": 3.7339835166931152,
"learning_rate": 0.00022518044217595314,
"elapsed_seconds": 116778.32068712497,
"projected_total_hours": 146.94605353129893,
"projected_total_cost_usd": 204.2550144085055
},
{
"iteration": 10500,
"train_loss": 3.7131927013397217,
"validation_loss": 3.7187798023223877,
"learning_rate": 0.00022266707550670694,
"elapsed_seconds": 122624.58746308996,
"projected_total_hours": 146.9548627533856,
"projected_total_cost_usd": 204.26725922720598
},
{
"iteration": 11000,
"train_loss": 3.6982581615448,
"validation_loss": 3.7051968574523926,
"learning_rate": 0.0002200499458749381,
"elapsed_seconds": 128481.97054895293,
"projected_total_hours": 146.9755875219083,
"projected_total_cost_usd": 204.2960666554525
},
{
"iteration": 11500,
"train_loss": 3.681401252746582,
"validation_loss": 3.6900885105133057,
"learning_rate": 0.00021733224184996498,
"elapsed_seconds": 134351.35519558704,
"projected_total_hours": 147.00764227922932,
"projected_total_cost_usd": 204.34062276812872
},
{
"iteration": 12000,
"train_loss": 3.667637825012207,
"validation_loss": 3.6769940853118896,
"learning_rate": 0.0002145172745355119,
"elapsed_seconds": 140210.84609409282,
"projected_total_hours": 147.02665111255567,
"projected_total_cost_usd": 204.36704504645238
},
{
"iteration": 12500,
"train_loss": 3.6528677940368652,
"validation_loss": 3.6665825843811035,
"learning_rate": 0.00021160847353563888,
"elapsed_seconds": 146071.26893039,
"projected_total_hours": 147.04507738992595,
"projected_total_cost_usd": 204.39265757199706
},
{
"iteration": 13000,
"train_loss": 3.639846086502075,
"validation_loss": 3.653087854385376,
"learning_rate": 0.000208609382776298,
"elapsed_seconds": 151925.76889001392,
"projected_total_hours": 147.05635322046217,
"projected_total_cost_usd": 204.40833097644241
},
{
"iteration": 13500,
"train_loss": 3.629678964614868,
"validation_loss": 3.6425936222076416,
"learning_rate": 0.0002055236561876049,
"elapsed_seconds": 157782.4660434397,
"projected_total_hours": 147.06884180592218,
"projected_total_cost_usd": 204.4256901102318
},
{
"iteration": 14000,
"train_loss": 3.6172244548797607,
"validation_loss": 3.634115219116211,
"learning_rate": 0.00020235505325208816,
"elapsed_seconds": 163627.8123262967,
"projected_total_hours": 147.07023607899285,
"projected_total_cost_usd": 204.42762814980006
},
{
"iteration": 14500,
"train_loss": 3.602062463760376,
"validation_loss": 3.626448154449463,
"learning_rate": 0.00019910743442433889,
"elapsed_seconds": 169474.427039932,
"projected_total_hours": 147.07263495994098,
"projected_total_cost_usd": 204.43096259431795
},
{
"iteration": 15000,
"train_loss": 3.596639394760132,
"validation_loss": 3.617069721221924,
"learning_rate": 0.00019578475642764132,
"elapsed_seconds": 175318.30801315093,
"projected_total_hours": 147.07258061103215,
"projected_total_cost_usd": 204.43088704933467
},
{
"iteration": 15500,
"train_loss": 3.5822103023529053,
"validation_loss": 3.604166030883789,
"learning_rate": 0.00019239106743331515,
"elapsed_seconds": 181170.80125680007,
"projected_total_hours": 147.07952145041295,
"projected_total_cost_usd": 204.440534816074
},
{
"iteration": 16000,
"train_loss": 3.5695128440856934,
"validation_loss": 3.594214677810669,
"learning_rate": 0.0001889305021286422,
"elapsed_seconds": 187022.97385376412,
"projected_total_hours": 147.0857763120749,
"projected_total_cost_usd": 204.4492290737841
},
{
"iteration": 16500,
"train_loss": 3.5584664344787598,
"validation_loss": 3.585881233215332,
"learning_rate": 0.00018540727667938712,
"elapsed_seconds": 192868.98684213776,
"projected_total_hours": 147.08695461193335,
"projected_total_cost_usd": 204.45086691058734
},
{
"iteration": 17000,
"train_loss": 3.5498061180114746,
"validation_loss": 3.5772714614868164,
"learning_rate": 0.0001818256835930484,
"elapsed_seconds": 198710.49392023915,
"projected_total_hours": 147.08472834292212,
"projected_total_cost_usd": 204.44777239666172
},
{
"iteration": 17500,
"train_loss": 3.538649797439575,
"validation_loss": 3.5700178146362305,
"learning_rate": 0.0001781900864890997,
"elapsed_seconds": 204562.4459545957,
"projected_total_hours": 147.09013971020931,
"projected_total_cost_usd": 204.45529419719094
},
{
"iteration": 18000,
"train_loss": 3.5280675888061523,
"validation_loss": 3.563185453414917,
"learning_rate": 0.00017450491478259136,
"elapsed_seconds": 210410.987407709,
"projected_total_hours": 147.09286619705583,
"projected_total_cost_usd": 204.45908401390759
},
{
"iteration": 18500,
"train_loss": 3.517913579940796,
"validation_loss": 3.5548534393310547,
"learning_rate": 0.0001707746582875906,
"elapsed_seconds": 216262.0165603701,
"projected_total_hours": 147.09713739016163,
"projected_total_cost_usd": 204.46502097232465
},
{
"iteration": 19000,
"train_loss": 3.50887393951416,
"validation_loss": 3.5479366779327393,
"learning_rate": 0.00016700386174703456,
"elapsed_seconds": 222117.43233659677,
"projected_total_hours": 147.10408895976366,
"projected_total_cost_usd": 204.47468365407147
},
{
"iteration": 19500,
"train_loss": 3.5005223751068115,
"validation_loss": 3.54071044921875,
"learning_rate": 0.00016319711929566126,
"elapsed_seconds": 227972.2531674751,
"projected_total_hours": 147.11030012089205,
"projected_total_cost_usd": 204.48331716803995
},
{
"iteration": 20000,
"train_loss": 3.4909307956695557,
"validation_loss": 3.531663179397583,
"learning_rate": 0.00015935906886276402,
"elapsed_seconds": 233830.57044673292,
"projected_total_hours": 147.11840057273616,
"projected_total_cost_usd": 204.49457679610325
},
{
"iteration": 20500,
"train_loss": 3.486023187637329,
"validation_loss": 3.5255727767944336,
"learning_rate": 0.0001554943865215889,
"elapsed_seconds": 239679.68671904784,
"projected_total_hours": 147.12045810803343,
"projected_total_cost_usd": 204.49743677016644
},
{
"iteration": 21000,
"train_loss": 3.4791877269744873,
"validation_loss": 3.5202720165252686,
"learning_rate": 0.00015160778079226003,
"elapsed_seconds": 245518.76395338494,
"projected_total_hours": 147.1164022101632,
"projected_total_cost_usd": 204.4917990721268
},
{
"iteration": 21500,
"train_loss": 3.469804048538208,
"validation_loss": 3.5100693702697754,
"learning_rate": 0.0001477039869051728,
"elapsed_seconds": 251360.50779337808,
"projected_total_hours": 147.114095646512,
"projected_total_cost_usd": 204.48859294865167
},
{
"iteration": 22000,
"train_loss": 3.4615044593811035,
"validation_loss": 3.505176067352295,
"learning_rate": 0.00014378776103184527,
"elapsed_seconds": 257201.9809560948,
"projected_total_hours": 147.1117391074633,
"projected_total_cost_usd": 204.485317359374
},
{
"iteration": 22500,
"train_loss": 3.4569902420043945,
"validation_loss": 3.499898672103882,
"learning_rate": 0.00013986387449025582,
"elapsed_seconds": 263036.7369214799,
"projected_total_hours": 147.10573064867953,
"projected_total_cost_usd": 204.47696560166452
},
{
"iteration": 23000,
"train_loss": 3.4522955417633057,
"validation_loss": 3.4949960708618164,
"learning_rate": 0.00013593710793172693,
"elapsed_seconds": 268878.98143927194,
"projected_total_hours": 147.10408042510892,
"projected_total_cost_usd": 204.47467179090137
},
{
"iteration": 23500,
"train_loss": 3.4453978538513184,
"validation_loss": 3.488229751586914,
"learning_rate": 0.0001320122455164382,
"elapsed_seconds": 274705.03559077205,
"projected_total_hours": 147.09383111420772,
"projected_total_cost_usd": 204.46042524874872
},
{
"iteration": 24000,
"train_loss": 3.43698787689209,
"validation_loss": 3.482897996902466,
"learning_rate": 0.00012809406908466384,
"elapsed_seconds": 280538.5956518408,
"projected_total_hours": 147.08794424801377,
"projected_total_cost_usd": 204.45224250473913
},
{
"iteration": 24500,
"train_loss": 3.426966667175293,
"validation_loss": 3.475834846496582,
"learning_rate": 0.00012418735233083727,
"elapsed_seconds": 286381.1681528948,
"projected_total_hours": 147.08692650029633,
"projected_total_cost_usd": 204.45082783541187
},
{
"iteration": 25000,
"train_loss": 3.4196131229400635,
"validation_loss": 3.471196174621582,
"learning_rate": 0.00012029685498753944,
"elapsed_seconds": 292214.37232685275,
"projected_total_hours": 147.08123407118256,
"projected_total_cost_usd": 204.44291535894374
},
{
"iteration": 25500,
"train_loss": 3.4136993885040283,
"validation_loss": 3.4657559394836426,
"learning_rate": 0.00011642731702649787,
"elapsed_seconds": 298058.5812796368,
"projected_total_hours": 147.08119533733714,
"projected_total_cost_usd": 204.4428615188986
},
{
"iteration": 26000,
"train_loss": 3.4060094356536865,
"validation_loss": 3.460638999938965,
"learning_rate": 0.0001125834528836616,
"elapsed_seconds": 303898.8813599739,
"projected_total_hours": 147.07926629921815,
"projected_total_cost_usd": 204.4401801559132
},
{
"iteration": 26500,
"train_loss": 3.397285223007202,
"validation_loss": 3.456627130508423,
"learning_rate": 0.00010876994571538669,
"elapsed_seconds": 309734.5375928958,
"projected_total_hours": 147.0752049576329,
"projected_total_cost_usd": 204.43453489110973
},
{
"iteration": 27000,
"train_loss": 3.3896384239196777,
"validation_loss": 3.450105667114258,
"learning_rate": 0.00010499144169273202,
"elapsed_seconds": 315585.65890582977,
"projected_total_hours": 147.0785015270997,
"projected_total_cost_usd": 204.43911712266856
},
{
"iteration": 27500,
"train_loss": 3.3839428424835205,
"validation_loss": 3.444591999053955,
"learning_rate": 0.0001012525443408152,
"elapsed_seconds": 321438.789508109,
"projected_total_hours": 147.08259762340742,
"projected_total_cost_usd": 204.4448106965363
},
{
"iteration": 28000,
"train_loss": 3.3783419132232666,
"validation_loss": 3.4397692680358887,
"learning_rate": 9.755780893012659e-05,
"elapsed_seconds": 327273.82601866405,
"projected_total_hours": 147.0784158595782,
"projected_total_cost_usd": 204.43899804481367
},
{
"iteration": 28500,
"train_loss": 3.3702282905578613,
"validation_loss": 3.4354019165039062,
"learning_rate": 9.391173692663375e-05,
"elapsed_seconds": 333119.06978819985,
"projected_total_hours": 147.07888753806483,
"projected_total_cost_usd": 204.43965367791012
},
{
"iteration": 29000,
"train_loss": 3.364657402038574,
"validation_loss": 3.432204246520996,
"learning_rate": 9.03187705074386e-05,
"elapsed_seconds": 338967.86247838195,
"projected_total_hours": 147.08088285699907,
"projected_total_cost_usd": 204.4424271712287
},
{
"iteration": 29500,
"train_loss": 3.361586332321167,
"validation_loss": 3.4272539615631104,
"learning_rate": 8.678328714866887e-05,
"elapsed_seconds": 344816.71290178783,
"projected_total_hours": 147.08283516432195,
"projected_total_cost_usd": 204.4451408784075
},
{
"iteration": 30000,
"train_loss": 3.3544201850891113,
"validation_loss": 3.4213171005249023,
"learning_rate": 8.330959429219775e-05,
"elapsed_seconds": 350665.20799918985,
"projected_total_hours": 147.08457335521572,
"projected_total_cost_usd": 204.44755696374983
},
{
"iteration": 30500,
"train_loss": 3.3491179943084717,
"validation_loss": 3.4158291816711426,
"learning_rate": 7.99019240976895e-05,
"elapsed_seconds": 356519.57499028975,
"projected_total_hours": 147.0886771134802,
"projected_total_cost_usd": 204.45326118773747
},
{
"iteration": 31000,
"train_loss": 3.34259033203125,
"validation_loss": 3.414461135864258,
"learning_rate": 7.656442828636477e-05,
"elapsed_seconds": 362371.10408779606,
"projected_total_hours": 147.09149655176665,
"projected_total_cost_usd": 204.45718020695563
},
{
"iteration": 31500,
"train_loss": 3.336934804916382,
"validation_loss": 3.4084677696228027,
"learning_rate": 7.330117308276784e-05,
"elapsed_seconds": 368224.406660873,
"projected_total_hours": 147.0949349359572,
"projected_total_cost_usd": 204.46195956098052
},
{
"iteration": 32000,
"train_loss": 3.332810878753662,
"validation_loss": 3.4053311347961426,
"learning_rate": 7.011613426069842e-05,
"elapsed_seconds": 374078.46307888115,
"projected_total_hours": 147.09856230445587,
"projected_total_cost_usd": 204.46700160319364
},
{
"iteration": 32500,
"train_loss": 3.325847864151001,
"validation_loss": 3.3993771076202393,
"learning_rate": 6.701319229934343e-05,
"elapsed_seconds": 379934.33091358515,
"projected_total_hours": 147.1027794050035,
"projected_total_cost_usd": 204.47286337295486
},
{
"iteration": 33000,
"train_loss": 3.3214898109436035,
"validation_loss": 3.3968589305877686,
"learning_rate": 6.39961276555114e-05,
"elapsed_seconds": 385785.82466378994,
"projected_total_hours": 147.1052008187684,
"projected_total_cost_usd": 204.47622913808806
},
{
"iteration": 33500,
"train_loss": 3.3171088695526123,
"validation_loss": 3.393434762954712,
"learning_rate": 6.106861615772748e-05,
"elapsed_seconds": 391644.3146269447,
"projected_total_hours": 147.11017788226033,
"projected_total_cost_usd": 204.48314725634185
},
{
"iteration": 34000,
"train_loss": 3.312814712524414,
"validation_loss": 3.388615131378174,
"learning_rate": 5.823422452780332e-05,
"elapsed_seconds": 397495.1632606508,
"projected_total_hours": 147.11218052048596,
"projected_total_cost_usd": 204.48593092347548
},
{
"iteration": 34500,
"train_loss": 3.305443048477173,
"validation_loss": 3.3842084407806396,
"learning_rate": 5.549640603533529e-05,
"elapsed_seconds": 403351.415478304,
"projected_total_hours": 147.11609598363265,
"projected_total_cost_usd": 204.49137341724938
},
{
"iteration": 35000,
"train_loss": 3.299060583114624,
"validation_loss": 3.3820013999938965,
"learning_rate": 5.285849629042789e-05,
"elapsed_seconds": 409202.1039497829,
"projected_total_hours": 147.11789927718385,
"projected_total_cost_usd": 204.49387999528554
},
{
"iteration": 35500,
"train_loss": 3.2942333221435547,
"validation_loss": 3.3802318572998047,
"learning_rate": 5.032370917976645e-05,
"elapsed_seconds": 415038.40922521707,
"projected_total_hours": 147.11455350471311,
"projected_total_cost_usd": 204.4892293715512
},
{
"iteration": 36000,
"train_loss": 3.2915239334106445,
"validation_loss": 3.375929594039917,
"learning_rate": 4.7895132950991336e-05,
"elapsed_seconds": 420878.96743322304,
"projected_total_hours": 147.11278722781637,
"projected_total_cost_usd": 204.48677424666474
},
{
"iteration": 36500,
"train_loss": 3.284877300262451,
"validation_loss": 3.3734710216522217,
"learning_rate": 4.55757264501437e-05,
"elapsed_seconds": 426712.58293662686,
"projected_total_hours": 147.1086758525814,
"projected_total_cost_usd": 204.48105943508813
},
{
"iteration": 37000,
"train_loss": 3.2819366455078125,
"validation_loss": 3.370877742767334,
"learning_rate": 4.336831551676778e-05,
"elapsed_seconds": 432558.64357199613,
"projected_total_hours": 147.10890806164736,
"projected_total_cost_usd": 204.4813822056898
},
{
"iteration": 37500,
"train_loss": 3.2778007984161377,
"validation_loss": 3.368626594543457,
"learning_rate": 4.12755895410602e-05,
"elapsed_seconds": 438408.5406104899,
"projected_total_hours": 147.11042140485327,
"projected_total_cost_usd": 204.48348575274602
},
{
"iteration": 38000,
"train_loss": 3.2740094661712646,
"validation_loss": 3.3664190769195557,
"learning_rate": 3.930009818726269e-05,
"elapsed_seconds": 444255.0420406908,
"projected_total_hours": 147.11077050031648,
"projected_total_cost_usd": 204.48397099543988
},
{
"iteration": 38500,
"train_loss": 3.270355224609375,
"validation_loss": 3.36319637298584,
"learning_rate": 3.744424828728872e-05,
"elapsed_seconds": 450094.42088113073,
"projected_total_hours": 147.10878258236093,
"projected_total_cost_usd": 204.4812077894817
},
{
"iteration": 39000,
"train_loss": 3.267413854598999,
"validation_loss": 3.3608386516571045,
"learning_rate": 3.571030090836964e-05,
"elapsed_seconds": 455934.32394408295,
"projected_total_hours": 147.1070147768302,
"projected_total_cost_usd": 204.47875053979396
},
{
"iteration": 39500,
"train_loss": 3.2651331424713135,
"validation_loss": 3.3594908714294434,
"learning_rate": 3.410036859829256e-05,
"elapsed_seconds": 461770.6794984429,
"projected_total_hours": 147.10416161237316,
"projected_total_cost_usd": 204.47478464119868
},
{
"iteration": 40000,
"train_loss": 3.261547803878784,
"validation_loss": 3.3563365936279297,
"learning_rate": 3.261641281158625e-05,
"elapsed_seconds": 467615.53966924874,
"projected_total_hours": 147.1040551876178,
"projected_total_cost_usd": 204.47463671078873
},
{
"iteration": 40500,
"train_loss": 3.2590126991271973,
"validation_loss": 3.3551130294799805,
"learning_rate": 3.126024151979095e-05,
"elapsed_seconds": 473461.22736253403,
"projected_total_hours": 147.10420850152806,
"projected_total_cost_usd": 204.47484981712398
},
{
"iteration": 41000,
"train_loss": 3.255312919616699,
"validation_loss": 3.3526666164398193,
"learning_rate": 3.0033507008723506e-05,
"elapsed_seconds": 479312.32710030675,
"projected_total_hours": 147.1060190897283,
"projected_total_cost_usd": 204.47736653472234
},
{
"iteration": 41500,
"train_loss": 3.2539491653442383,
"validation_loss": 3.350898504257202,
"learning_rate": 2.8937703865421725e-05,
"elapsed_seconds": 485160.5302867908,
"projected_total_hours": 147.10690777772172,
"projected_total_cost_usd": 204.47860181103317
},
{
"iteration": 42000,
"train_loss": 3.2522432804107666,
"validation_loss": 3.349637746810913,
"learning_rate": 2.797416715722014e-05,
"elapsed_seconds": 491000.89962377073,
"projected_total_hours": 147.1054282602964,
"projected_total_cost_usd": 204.47654528181198
},
{
"iteration": 42500,
"train_loss": 3.2494194507598877,
"validation_loss": 3.347707509994507,
"learning_rate": 2.7144070805176307e-05,
"elapsed_seconds": 496843.76710513374,
"projected_total_hours": 147.10472320171607,
"projected_total_cost_usd": 204.47556525038533
},
{
"iteration": 43000,
"train_loss": 3.247154474258423,
"validation_loss": 3.3457424640655518,
"learning_rate": 2.6448426153828607e-05,
"elapsed_seconds": 502679.92955206474,
"projected_total_hours": 147.10207240767787,
"projected_total_cost_usd": 204.47188064667222
},
{
"iteration": 43500,
"train_loss": 3.2443184852600098,
"validation_loss": 3.3455331325531006,
"learning_rate": 2.588808073902886e-05,
"elapsed_seconds": 508520.75622208,
"projected_total_hours": 147.10083178071662,
"projected_total_cost_usd": 204.47015617519608
},
{
"iteration": 44000,
"train_loss": 3.2425286769866943,
"validation_loss": 3.344048500061035,
"learning_rate": 2.5463717255350436e-05,
"elapsed_seconds": 514355.92856104113,
"projected_total_hours": 147.0980022968129,
"projected_total_cost_usd": 204.4662231925699
},
{
"iteration": 44500,
"train_loss": 3.2407639026641846,
"validation_loss": 3.343557834625244,
"learning_rate": 2.5175852724329982e-05,
"elapsed_seconds": 520196.1437763069,
"projected_total_hours": 147.0966623786935,
"projected_total_cost_usd": 204.46436070638396
},
{
"iteration": 45000,
"train_loss": 3.239764928817749,
"validation_loss": 3.3421542644500732,
"learning_rate": 2.5024837864556432e-05,
"elapsed_seconds": 526028.3676926447,
"projected_total_hours": 147.09311763257287,
"projected_total_cost_usd": 204.45943350927627
},
{
"iteration": 45300,
"train_loss": 3.2387826442718506,
"validation_loss": 3.3402066230773926,
"learning_rate": 2.5000000274155676e-05,
"elapsed_seconds": 529567.9590760078,
"projected_total_hours": 147.1022108544466,
"projected_total_cost_usd": 204.47207308768077
}
],
"environment": {
"python": "3.11.10",
"platform": "Linux-6.8.0-124-generic-x86_64-with-glibc2.35",
"torch": "2.5.1+cu124",
"cuda": "12.4",
"gpu": "NVIDIA A100 80GB PCIe"
},
"data_manifest_sha256": "c8cb248a827a40f241297474b8e1c2e64589ecd3dbaebe860474aa401697bf98",
"peak_vram_bytes": 54941026304,
"gpu_total_bytes": 85093777408,
"estimated_training_cost_usd": 204.4843982894051
}