mymodel / trainer_state.json
IntMeGroup's picture
Upload NLLB zh-vi model
562cd22 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"eval_steps": 500,
"global_step": 1548,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.010342598577892695,
"grad_norm": 0.27074137330055237,
"learning_rate": 1.5384615384615385e-07,
"loss": 0.5239,
"step": 4
},
{
"epoch": 0.02068519715578539,
"grad_norm": 0.2690924108028412,
"learning_rate": 3.5897435897435896e-07,
"loss": 0.519,
"step": 8
},
{
"epoch": 0.031027795733678087,
"grad_norm": 0.28973960876464844,
"learning_rate": 5.641025641025641e-07,
"loss": 0.5216,
"step": 12
},
{
"epoch": 0.04137039431157078,
"grad_norm": 0.2677304744720459,
"learning_rate": 7.692307692307693e-07,
"loss": 0.5403,
"step": 16
},
{
"epoch": 0.051712992889463474,
"grad_norm": 0.2680451571941376,
"learning_rate": 9.743589743589742e-07,
"loss": 0.518,
"step": 20
},
{
"epoch": 0.062055591467356175,
"grad_norm": 0.25933119654655457,
"learning_rate": 1.1794871794871795e-06,
"loss": 0.5192,
"step": 24
},
{
"epoch": 0.07239819004524888,
"grad_norm": 0.25746598839759827,
"learning_rate": 1.3846153846153844e-06,
"loss": 0.5164,
"step": 28
},
{
"epoch": 0.08274078862314156,
"grad_norm": 0.2424672544002533,
"learning_rate": 1.5897435897435895e-06,
"loss": 0.5016,
"step": 32
},
{
"epoch": 0.09308338720103426,
"grad_norm": 0.22520849108695984,
"learning_rate": 1.7948717948717948e-06,
"loss": 0.5133,
"step": 36
},
{
"epoch": 0.10342598577892695,
"grad_norm": 0.208700492978096,
"learning_rate": 2e-06,
"loss": 0.503,
"step": 40
},
{
"epoch": 0.11376858435681965,
"grad_norm": 0.2092197686433792,
"learning_rate": 2.2051282051282052e-06,
"loss": 0.5016,
"step": 44
},
{
"epoch": 0.12411118293471235,
"grad_norm": 0.20155887305736542,
"learning_rate": 2.41025641025641e-06,
"loss": 0.4955,
"step": 48
},
{
"epoch": 0.13445378151260504,
"grad_norm": 0.20360776782035828,
"learning_rate": 2.6153846153846154e-06,
"loss": 0.51,
"step": 52
},
{
"epoch": 0.14479638009049775,
"grad_norm": 0.20055116713047028,
"learning_rate": 2.8205128205128207e-06,
"loss": 0.5073,
"step": 56
},
{
"epoch": 0.15513897866839044,
"grad_norm": 0.2022508680820465,
"learning_rate": 3.0256410256410256e-06,
"loss": 0.4918,
"step": 60
},
{
"epoch": 0.16548157724628312,
"grad_norm": 0.1955750733613968,
"learning_rate": 3.230769230769231e-06,
"loss": 0.4917,
"step": 64
},
{
"epoch": 0.17582417582417584,
"grad_norm": 0.18670685589313507,
"learning_rate": 3.4358974358974353e-06,
"loss": 0.4936,
"step": 68
},
{
"epoch": 0.18616677440206852,
"grad_norm": 0.192545086145401,
"learning_rate": 3.6410256410256406e-06,
"loss": 0.4972,
"step": 72
},
{
"epoch": 0.1965093729799612,
"grad_norm": 0.1836402714252472,
"learning_rate": 3.846153846153846e-06,
"loss": 0.4823,
"step": 76
},
{
"epoch": 0.2068519715578539,
"grad_norm": 0.18833868205547333,
"learning_rate": 3.993881715007257e-06,
"loss": 0.4825,
"step": 80
},
{
"epoch": 0.2171945701357466,
"grad_norm": 0.18157020211219788,
"learning_rate": 3.969491760330399e-06,
"loss": 0.4829,
"step": 84
},
{
"epoch": 0.2275371687136393,
"grad_norm": 0.17653386294841766,
"learning_rate": 3.945234630128603e-06,
"loss": 0.4886,
"step": 88
},
{
"epoch": 0.23787976729153198,
"grad_norm": 0.18460187315940857,
"learning_rate": 3.9211099617411865e-06,
"loss": 0.491,
"step": 92
},
{
"epoch": 0.2482223658694247,
"grad_norm": 0.17642319202423096,
"learning_rate": 3.897117392507468e-06,
"loss": 0.4857,
"step": 96
},
{
"epoch": 0.2585649644473174,
"grad_norm": 0.17706429958343506,
"learning_rate": 3.873256559766764e-06,
"loss": 0.494,
"step": 100
},
{
"epoch": 0.2689075630252101,
"grad_norm": 0.1816156804561615,
"learning_rate": 3.8495271008583914e-06,
"loss": 0.4911,
"step": 104
},
{
"epoch": 0.2792501616031028,
"grad_norm": 0.19248028099536896,
"learning_rate": 3.825928653121668e-06,
"loss": 0.4866,
"step": 108
},
{
"epoch": 0.2895927601809955,
"grad_norm": 0.17712807655334473,
"learning_rate": 3.80246085389591e-06,
"loss": 0.4763,
"step": 112
},
{
"epoch": 0.29993535875888816,
"grad_norm": 0.18759045004844666,
"learning_rate": 3.779123340520437e-06,
"loss": 0.4812,
"step": 116
},
{
"epoch": 0.3102779573367809,
"grad_norm": 0.19693388044834137,
"learning_rate": 3.755915750334564e-06,
"loss": 0.4783,
"step": 120
},
{
"epoch": 0.3206205559146736,
"grad_norm": 0.1827310472726822,
"learning_rate": 3.7328377206776083e-06,
"loss": 0.477,
"step": 124
},
{
"epoch": 0.33096315449256625,
"grad_norm": 0.18313142657279968,
"learning_rate": 3.7098888888888884e-06,
"loss": 0.496,
"step": 128
},
{
"epoch": 0.34130575307045896,
"grad_norm": 0.17326150834560394,
"learning_rate": 3.687068892307722e-06,
"loss": 0.4778,
"step": 132
},
{
"epoch": 0.3516483516483517,
"grad_norm": 0.17738491296768188,
"learning_rate": 3.664377368273423e-06,
"loss": 0.4813,
"step": 136
},
{
"epoch": 0.36199095022624433,
"grad_norm": 0.18592627346515656,
"learning_rate": 3.6418139541253126e-06,
"loss": 0.4783,
"step": 140
},
{
"epoch": 0.37233354880413705,
"grad_norm": 0.17538052797317505,
"learning_rate": 3.6193782872027053e-06,
"loss": 0.4726,
"step": 144
},
{
"epoch": 0.3826761473820297,
"grad_norm": 0.1824338138103485,
"learning_rate": 3.5970700048449203e-06,
"loss": 0.4637,
"step": 148
},
{
"epoch": 0.3930187459599224,
"grad_norm": 0.1739794909954071,
"learning_rate": 3.5748887443912734e-06,
"loss": 0.4832,
"step": 152
},
{
"epoch": 0.40336134453781514,
"grad_norm": 0.19277994334697723,
"learning_rate": 3.552834143181082e-06,
"loss": 0.4773,
"step": 156
},
{
"epoch": 0.4137039431157078,
"grad_norm": 0.1671997308731079,
"learning_rate": 3.5309058385536637e-06,
"loss": 0.4739,
"step": 160
},
{
"epoch": 0.4240465416936005,
"grad_norm": 0.17366255819797516,
"learning_rate": 3.5091034678483365e-06,
"loss": 0.4872,
"step": 164
},
{
"epoch": 0.4343891402714932,
"grad_norm": 0.17070995271205902,
"learning_rate": 3.4874266684044155e-06,
"loss": 0.4593,
"step": 168
},
{
"epoch": 0.4447317388493859,
"grad_norm": 0.1726539433002472,
"learning_rate": 3.4658750775612206e-06,
"loss": 0.4682,
"step": 172
},
{
"epoch": 0.4550743374272786,
"grad_norm": 0.17803026735782623,
"learning_rate": 3.4444483326580667e-06,
"loss": 0.4623,
"step": 176
},
{
"epoch": 0.4654169360051713,
"grad_norm": 0.18144938349723816,
"learning_rate": 3.423146071034272e-06,
"loss": 0.4694,
"step": 180
},
{
"epoch": 0.47575953458306397,
"grad_norm": 0.18337614834308624,
"learning_rate": 3.401967930029155e-06,
"loss": 0.4697,
"step": 184
},
{
"epoch": 0.4861021331609567,
"grad_norm": 0.18037910759449005,
"learning_rate": 3.3809135469820304e-06,
"loss": 0.4664,
"step": 188
},
{
"epoch": 0.4964447317388494,
"grad_norm": 0.1738828718662262,
"learning_rate": 3.3599825592322174e-06,
"loss": 0.4697,
"step": 192
},
{
"epoch": 0.5067873303167421,
"grad_norm": 0.17767304182052612,
"learning_rate": 3.3391746041190326e-06,
"loss": 0.4866,
"step": 196
},
{
"epoch": 0.5171299288946348,
"grad_norm": 0.17905977368354797,
"learning_rate": 3.3184893189817926e-06,
"loss": 0.4755,
"step": 200
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.18217241764068604,
"learning_rate": 3.2979263411598156e-06,
"loss": 0.4801,
"step": 204
},
{
"epoch": 0.5378151260504201,
"grad_norm": 0.17312566936016083,
"learning_rate": 3.2774853079924182e-06,
"loss": 0.4772,
"step": 208
},
{
"epoch": 0.5481577246283129,
"grad_norm": 0.17987386882305145,
"learning_rate": 3.257165856818918e-06,
"loss": 0.4731,
"step": 212
},
{
"epoch": 0.5585003232062056,
"grad_norm": 0.17333056032657623,
"learning_rate": 3.236967624978633e-06,
"loss": 0.4725,
"step": 216
},
{
"epoch": 0.5688429217840982,
"grad_norm": 0.18219755589962006,
"learning_rate": 3.2168902498108775e-06,
"loss": 0.4758,
"step": 220
},
{
"epoch": 0.579185520361991,
"grad_norm": 0.17562930285930634,
"learning_rate": 3.196933368654973e-06,
"loss": 0.4643,
"step": 224
},
{
"epoch": 0.5895281189398837,
"grad_norm": 0.21644935011863708,
"learning_rate": 3.1770966188502337e-06,
"loss": 0.4794,
"step": 228
},
{
"epoch": 0.5998707175177763,
"grad_norm": 0.18018363416194916,
"learning_rate": 3.157379637735977e-06,
"loss": 0.4668,
"step": 232
},
{
"epoch": 0.6102133160956691,
"grad_norm": 0.1677103340625763,
"learning_rate": 3.137782062651522e-06,
"loss": 0.4564,
"step": 236
},
{
"epoch": 0.6205559146735617,
"grad_norm": 0.17912864685058594,
"learning_rate": 3.1183035309361833e-06,
"loss": 0.4603,
"step": 240
},
{
"epoch": 0.6308985132514544,
"grad_norm": 0.18761886656284332,
"learning_rate": 3.0989436799292814e-06,
"loss": 0.4799,
"step": 244
},
{
"epoch": 0.6412411118293472,
"grad_norm": 0.17829325795173645,
"learning_rate": 3.079702146970131e-06,
"loss": 0.4718,
"step": 248
},
{
"epoch": 0.6515837104072398,
"grad_norm": 0.19033263623714447,
"learning_rate": 3.060578569398049e-06,
"loss": 0.4751,
"step": 252
},
{
"epoch": 0.6619263089851325,
"grad_norm": 0.1795780062675476,
"learning_rate": 3.0415725845523547e-06,
"loss": 0.4604,
"step": 256
},
{
"epoch": 0.6722689075630253,
"grad_norm": 0.18677003681659698,
"learning_rate": 3.022683829772365e-06,
"loss": 0.4677,
"step": 260
},
{
"epoch": 0.6826115061409179,
"grad_norm": 0.1794733852148056,
"learning_rate": 3.0039119423973945e-06,
"loss": 0.4671,
"step": 264
},
{
"epoch": 0.6929541047188106,
"grad_norm": 0.1785053014755249,
"learning_rate": 2.9852565597667635e-06,
"loss": 0.4761,
"step": 268
},
{
"epoch": 0.7032967032967034,
"grad_norm": 0.17754320800304413,
"learning_rate": 2.9667173192197887e-06,
"loss": 0.4707,
"step": 272
},
{
"epoch": 0.713639301874596,
"grad_norm": 0.17548543214797974,
"learning_rate": 2.9482938580957856e-06,
"loss": 0.4534,
"step": 276
},
{
"epoch": 0.7239819004524887,
"grad_norm": 0.17609195411205292,
"learning_rate": 2.9299858137340735e-06,
"loss": 0.4591,
"step": 280
},
{
"epoch": 0.7343244990303813,
"grad_norm": 0.17191891372203827,
"learning_rate": 2.911792823473968e-06,
"loss": 0.4697,
"step": 284
},
{
"epoch": 0.7446670976082741,
"grad_norm": 0.18207724392414093,
"learning_rate": 2.8937145246547875e-06,
"loss": 0.4654,
"step": 288
},
{
"epoch": 0.7550096961861668,
"grad_norm": 0.17942476272583008,
"learning_rate": 2.8757505546158493e-06,
"loss": 0.4688,
"step": 292
},
{
"epoch": 0.7653522947640594,
"grad_norm": 0.18172645568847656,
"learning_rate": 2.857900550696469e-06,
"loss": 0.4616,
"step": 296
},
{
"epoch": 0.7756948933419522,
"grad_norm": 0.18675239384174347,
"learning_rate": 2.8401641502359657e-06,
"loss": 0.4612,
"step": 300
},
{
"epoch": 0.7860374919198448,
"grad_norm": 0.18713857233524323,
"learning_rate": 2.822540990573655e-06,
"loss": 0.468,
"step": 304
},
{
"epoch": 0.7963800904977375,
"grad_norm": 0.192363440990448,
"learning_rate": 2.805030709048856e-06,
"loss": 0.472,
"step": 308
},
{
"epoch": 0.8067226890756303,
"grad_norm": 0.17535482347011566,
"learning_rate": 2.787632943000885e-06,
"loss": 0.4651,
"step": 312
},
{
"epoch": 0.8170652876535229,
"grad_norm": 0.1680748015642166,
"learning_rate": 2.7703473297690585e-06,
"loss": 0.476,
"step": 316
},
{
"epoch": 0.8274078862314156,
"grad_norm": 0.1780477613210678,
"learning_rate": 2.753173506692695e-06,
"loss": 0.4715,
"step": 320
},
{
"epoch": 0.8377504848093084,
"grad_norm": 0.17565058171749115,
"learning_rate": 2.7361111111111114e-06,
"loss": 0.4724,
"step": 324
},
{
"epoch": 0.848093083387201,
"grad_norm": 0.17358048260211945,
"learning_rate": 2.719159780363624e-06,
"loss": 0.4819,
"step": 328
},
{
"epoch": 0.8584356819650937,
"grad_norm": 0.1844065934419632,
"learning_rate": 2.702319151789551e-06,
"loss": 0.4769,
"step": 332
},
{
"epoch": 0.8687782805429864,
"grad_norm": 0.1706087440252304,
"learning_rate": 2.6855888627282097e-06,
"loss": 0.4688,
"step": 336
},
{
"epoch": 0.8791208791208791,
"grad_norm": 0.17604754865169525,
"learning_rate": 2.6689685505189168e-06,
"loss": 0.4604,
"step": 340
},
{
"epoch": 0.8894634776987718,
"grad_norm": 0.19641447067260742,
"learning_rate": 2.6524578525009895e-06,
"loss": 0.4619,
"step": 344
},
{
"epoch": 0.8998060762766645,
"grad_norm": 0.1839519441127777,
"learning_rate": 2.6360564060137445e-06,
"loss": 0.4658,
"step": 348
},
{
"epoch": 0.9101486748545572,
"grad_norm": 0.17227011919021606,
"learning_rate": 2.6197638483965012e-06,
"loss": 0.4657,
"step": 352
},
{
"epoch": 0.9204912734324499,
"grad_norm": 0.18372756242752075,
"learning_rate": 2.6035798169885755e-06,
"loss": 0.4752,
"step": 356
},
{
"epoch": 0.9308338720103426,
"grad_norm": 0.17142316699028015,
"learning_rate": 2.5875039491292835e-06,
"loss": 0.4648,
"step": 360
},
{
"epoch": 0.9411764705882353,
"grad_norm": 0.20659951865673065,
"learning_rate": 2.5715358821579443e-06,
"loss": 0.4564,
"step": 364
},
{
"epoch": 0.9515190691661279,
"grad_norm": 0.17238274216651917,
"learning_rate": 2.5556752534138737e-06,
"loss": 0.4509,
"step": 368
},
{
"epoch": 0.9618616677440207,
"grad_norm": 0.1769212931394577,
"learning_rate": 2.5399217002363903e-06,
"loss": 0.4631,
"step": 372
},
{
"epoch": 0.9722042663219134,
"grad_norm": 0.1703854501247406,
"learning_rate": 2.5242748599648104e-06,
"loss": 0.4665,
"step": 376
},
{
"epoch": 0.982546864899806,
"grad_norm": 0.17398501932621002,
"learning_rate": 2.5087343699384522e-06,
"loss": 0.4728,
"step": 380
},
{
"epoch": 0.9928894634776988,
"grad_norm": 0.20379476249217987,
"learning_rate": 2.4932998674966306e-06,
"loss": 0.4647,
"step": 384
},
{
"epoch": 1.0025856496444732,
"grad_norm": 0.172428697347641,
"learning_rate": 2.4779709899786656e-06,
"loss": 0.4485,
"step": 388
},
{
"epoch": 1.0129282482223658,
"grad_norm": 0.18400946259498596,
"learning_rate": 2.4627473747238725e-06,
"loss": 0.4546,
"step": 392
},
{
"epoch": 1.0232708468002585,
"grad_norm": 0.177312433719635,
"learning_rate": 2.44762865907157e-06,
"loss": 0.4642,
"step": 396
},
{
"epoch": 1.0336134453781514,
"grad_norm": 0.19368407130241394,
"learning_rate": 2.4326144803610743e-06,
"loss": 0.4703,
"step": 400
},
{
"epoch": 1.043956043956044,
"grad_norm": 0.18584667146205902,
"learning_rate": 2.4177044759317023e-06,
"loss": 0.4672,
"step": 404
},
{
"epoch": 1.0542986425339367,
"grad_norm": 0.1793242245912552,
"learning_rate": 2.402898283122773e-06,
"loss": 0.4519,
"step": 408
},
{
"epoch": 1.0646412411118293,
"grad_norm": 0.17912016808986664,
"learning_rate": 2.3881955392736017e-06,
"loss": 0.4636,
"step": 412
},
{
"epoch": 1.074983839689722,
"grad_norm": 0.17298536002635956,
"learning_rate": 2.373595881723507e-06,
"loss": 0.4512,
"step": 416
},
{
"epoch": 1.0853264382676147,
"grad_norm": 0.1726359874010086,
"learning_rate": 2.3590989478118058e-06,
"loss": 0.4699,
"step": 420
},
{
"epoch": 1.0956690368455075,
"grad_norm": 0.17390099167823792,
"learning_rate": 2.3447043748778143e-06,
"loss": 0.4587,
"step": 424
},
{
"epoch": 1.1060116354234002,
"grad_norm": 0.25595802068710327,
"learning_rate": 2.3304118002608516e-06,
"loss": 0.4615,
"step": 428
},
{
"epoch": 1.1163542340012929,
"grad_norm": 0.17193318903446198,
"learning_rate": 2.3162208613002327e-06,
"loss": 0.4624,
"step": 432
},
{
"epoch": 1.1266968325791855,
"grad_norm": 0.19484907388687134,
"learning_rate": 2.302131195335277e-06,
"loss": 0.4623,
"step": 436
},
{
"epoch": 1.1370394311570782,
"grad_norm": 0.1798972338438034,
"learning_rate": 2.2881424397053003e-06,
"loss": 0.4649,
"step": 440
},
{
"epoch": 1.1473820297349708,
"grad_norm": 0.18051382899284363,
"learning_rate": 2.274254231749621e-06,
"loss": 0.4601,
"step": 444
},
{
"epoch": 1.1577246283128635,
"grad_norm": 0.17082150280475616,
"learning_rate": 2.2604662088075545e-06,
"loss": 0.4499,
"step": 448
},
{
"epoch": 1.1680672268907564,
"grad_norm": 0.1901365965604782,
"learning_rate": 2.2467780082184194e-06,
"loss": 0.4593,
"step": 452
},
{
"epoch": 1.178409825468649,
"grad_norm": 0.1783684343099594,
"learning_rate": 2.2331892673215335e-06,
"loss": 0.4529,
"step": 456
},
{
"epoch": 1.1887524240465417,
"grad_norm": 0.19588534533977509,
"learning_rate": 2.219699623456213e-06,
"loss": 0.4602,
"step": 460
},
{
"epoch": 1.1990950226244343,
"grad_norm": 0.20320181548595428,
"learning_rate": 2.206308713961775e-06,
"loss": 0.4541,
"step": 464
},
{
"epoch": 1.209437621202327,
"grad_norm": 0.18522217869758606,
"learning_rate": 2.1930161761775375e-06,
"loss": 0.4607,
"step": 468
},
{
"epoch": 1.2197802197802199,
"grad_norm": 0.1711958944797516,
"learning_rate": 2.179821647442817e-06,
"loss": 0.4604,
"step": 472
},
{
"epoch": 1.2301228183581125,
"grad_norm": 0.1926986277103424,
"learning_rate": 2.166724765096931e-06,
"loss": 0.4687,
"step": 476
},
{
"epoch": 1.2404654169360052,
"grad_norm": 0.17525337636470795,
"learning_rate": 2.1537251664791973e-06,
"loss": 0.4597,
"step": 480
},
{
"epoch": 1.2508080155138979,
"grad_norm": 0.19414155185222626,
"learning_rate": 2.1408224889289327e-06,
"loss": 0.4511,
"step": 484
},
{
"epoch": 1.2611506140917905,
"grad_norm": 0.1930965930223465,
"learning_rate": 2.1280163697854547e-06,
"loss": 0.4648,
"step": 488
},
{
"epoch": 1.2714932126696832,
"grad_norm": 0.1782602071762085,
"learning_rate": 2.115306446388079e-06,
"loss": 0.4565,
"step": 492
},
{
"epoch": 1.2818358112475758,
"grad_norm": 0.1658431589603424,
"learning_rate": 2.1026923560761246e-06,
"loss": 0.4684,
"step": 496
},
{
"epoch": 1.2921784098254687,
"grad_norm": 0.17630533874034882,
"learning_rate": 2.090173736188908e-06,
"loss": 0.4689,
"step": 500
},
{
"epoch": 1.3025210084033614,
"grad_norm": 0.16866503655910492,
"learning_rate": 2.0777502240657472e-06,
"loss": 0.4551,
"step": 504
},
{
"epoch": 1.312863606981254,
"grad_norm": 0.17106667160987854,
"learning_rate": 2.065421457045959e-06,
"loss": 0.4618,
"step": 508
},
{
"epoch": 1.3232062055591467,
"grad_norm": 0.17253316938877106,
"learning_rate": 2.0531870724688596e-06,
"loss": 0.4585,
"step": 512
},
{
"epoch": 1.3335488041370394,
"grad_norm": 0.19091737270355225,
"learning_rate": 2.0410467076737674e-06,
"loss": 0.4594,
"step": 516
},
{
"epoch": 1.3438914027149322,
"grad_norm": 0.17556996643543243,
"learning_rate": 2.0289999999999995e-06,
"loss": 0.449,
"step": 520
},
{
"epoch": 1.354234001292825,
"grad_norm": 0.17378376424312592,
"learning_rate": 2.017046586786874e-06,
"loss": 0.46,
"step": 524
},
{
"epoch": 1.3645765998707176,
"grad_norm": 0.17842325568199158,
"learning_rate": 2.005186105373706e-06,
"loss": 0.4457,
"step": 528
},
{
"epoch": 1.3749191984486102,
"grad_norm": 0.18024806678295135,
"learning_rate": 1.993418193099814e-06,
"loss": 0.4562,
"step": 532
},
{
"epoch": 1.3852617970265029,
"grad_norm": 0.1783292591571808,
"learning_rate": 1.9817424873045148e-06,
"loss": 0.4555,
"step": 536
},
{
"epoch": 1.3956043956043955,
"grad_norm": 0.19366991519927979,
"learning_rate": 1.970158625327126e-06,
"loss": 0.4619,
"step": 540
},
{
"epoch": 1.4059469941822882,
"grad_norm": 0.1875096708536148,
"learning_rate": 1.9586662445069657e-06,
"loss": 0.463,
"step": 544
},
{
"epoch": 1.416289592760181,
"grad_norm": 0.19434590637683868,
"learning_rate": 1.94726498218335e-06,
"loss": 0.4568,
"step": 548
},
{
"epoch": 1.4266321913380737,
"grad_norm": 0.18033798038959503,
"learning_rate": 1.9359544756955956e-06,
"loss": 0.4518,
"step": 552
},
{
"epoch": 1.4369747899159664,
"grad_norm": 0.17548328638076782,
"learning_rate": 1.9247343623830206e-06,
"loss": 0.4563,
"step": 556
},
{
"epoch": 1.447317388493859,
"grad_norm": 0.18100734055042267,
"learning_rate": 1.913604279584942e-06,
"loss": 0.453,
"step": 560
},
{
"epoch": 1.4576599870717517,
"grad_norm": 0.17302066087722778,
"learning_rate": 1.9025638646406777e-06,
"loss": 0.4497,
"step": 564
},
{
"epoch": 1.4680025856496446,
"grad_norm": 0.17910614609718323,
"learning_rate": 1.8916127548895444e-06,
"loss": 0.4588,
"step": 568
},
{
"epoch": 1.4783451842275372,
"grad_norm": 0.1921713948249817,
"learning_rate": 1.8807505876708593e-06,
"loss": 0.4631,
"step": 572
},
{
"epoch": 1.48868778280543,
"grad_norm": 0.18404294550418854,
"learning_rate": 1.8699770003239392e-06,
"loss": 0.4686,
"step": 576
},
{
"epoch": 1.4990303813833226,
"grad_norm": 0.1868065893650055,
"learning_rate": 1.859291630188102e-06,
"loss": 0.4594,
"step": 580
},
{
"epoch": 1.5093729799612152,
"grad_norm": 0.42297038435935974,
"learning_rate": 1.8486941146026646e-06,
"loss": 0.4635,
"step": 584
},
{
"epoch": 1.5197155785391079,
"grad_norm": 0.17838597297668457,
"learning_rate": 1.8381840909069446e-06,
"loss": 0.4479,
"step": 588
},
{
"epoch": 1.5300581771170005,
"grad_norm": 0.16778771579265594,
"learning_rate": 1.8277611964402589e-06,
"loss": 0.4583,
"step": 592
},
{
"epoch": 1.5404007756948932,
"grad_norm": 0.16617390513420105,
"learning_rate": 1.817425068541925e-06,
"loss": 0.4544,
"step": 596
},
{
"epoch": 1.550743374272786,
"grad_norm": 0.1774096041917801,
"learning_rate": 1.8071753445512594e-06,
"loss": 0.4451,
"step": 600
},
{
"epoch": 1.5610859728506787,
"grad_norm": 0.19082525372505188,
"learning_rate": 1.7970116618075802e-06,
"loss": 0.4666,
"step": 604
},
{
"epoch": 1.5714285714285714,
"grad_norm": 0.26731783151626587,
"learning_rate": 1.7869336576502043e-06,
"loss": 0.4504,
"step": 608
},
{
"epoch": 1.5817711700064643,
"grad_norm": 0.17997735738754272,
"learning_rate": 1.7769409694184493e-06,
"loss": 0.4505,
"step": 612
},
{
"epoch": 1.592113768584357,
"grad_norm": 0.1862158477306366,
"learning_rate": 1.7670332344516319e-06,
"loss": 0.4554,
"step": 616
},
{
"epoch": 1.6024563671622496,
"grad_norm": 0.18264687061309814,
"learning_rate": 1.757210090089069e-06,
"loss": 0.4568,
"step": 620
},
{
"epoch": 1.6127989657401423,
"grad_norm": 0.18124184012413025,
"learning_rate": 1.7474711736700786e-06,
"loss": 0.4562,
"step": 624
},
{
"epoch": 1.623141564318035,
"grad_norm": 0.18057860434055328,
"learning_rate": 1.737816122533978e-06,
"loss": 0.4584,
"step": 628
},
{
"epoch": 1.6334841628959276,
"grad_norm": 0.1704379767179489,
"learning_rate": 1.7282445740200844e-06,
"loss": 0.4565,
"step": 632
},
{
"epoch": 1.6438267614738202,
"grad_norm": 0.17907528579235077,
"learning_rate": 1.7187561654677143e-06,
"loss": 0.4551,
"step": 636
},
{
"epoch": 1.654169360051713,
"grad_norm": 0.1727352887392044,
"learning_rate": 1.7093505342161853e-06,
"loss": 0.4626,
"step": 640
},
{
"epoch": 1.6645119586296055,
"grad_norm": 0.192378431558609,
"learning_rate": 1.7000273176048153e-06,
"loss": 0.4609,
"step": 644
},
{
"epoch": 1.6748545572074984,
"grad_norm": 0.21348994970321655,
"learning_rate": 1.6907861529729202e-06,
"loss": 0.4581,
"step": 648
},
{
"epoch": 1.685197155785391,
"grad_norm": 0.17903228104114532,
"learning_rate": 1.6816266776598186e-06,
"loss": 0.4628,
"step": 652
},
{
"epoch": 1.6955397543632837,
"grad_norm": 0.17800310254096985,
"learning_rate": 1.672548529004827e-06,
"loss": 0.4625,
"step": 656
},
{
"epoch": 1.7058823529411766,
"grad_norm": 0.17950348556041718,
"learning_rate": 1.663551344347263e-06,
"loss": 0.4595,
"step": 660
},
{
"epoch": 1.7162249515190693,
"grad_norm": 0.17900501191616058,
"learning_rate": 1.654634761026443e-06,
"loss": 0.4574,
"step": 664
},
{
"epoch": 1.726567550096962,
"grad_norm": 0.17247159779071808,
"learning_rate": 1.645798416381685e-06,
"loss": 0.4517,
"step": 668
},
{
"epoch": 1.7369101486748546,
"grad_norm": 0.18945126235485077,
"learning_rate": 1.6370419477523063e-06,
"loss": 0.4609,
"step": 672
},
{
"epoch": 1.7472527472527473,
"grad_norm": 0.1901276856660843,
"learning_rate": 1.628364992477624e-06,
"loss": 0.4538,
"step": 676
},
{
"epoch": 1.75759534583064,
"grad_norm": 0.17829464375972748,
"learning_rate": 1.6197671878969554e-06,
"loss": 0.4481,
"step": 680
},
{
"epoch": 1.7679379444085326,
"grad_norm": 0.1853664517402649,
"learning_rate": 1.6112481713496172e-06,
"loss": 0.4597,
"step": 684
},
{
"epoch": 1.7782805429864252,
"grad_norm": 0.17670245468616486,
"learning_rate": 1.6028075801749268e-06,
"loss": 0.4559,
"step": 688
},
{
"epoch": 1.788623141564318,
"grad_norm": 0.16995681822299957,
"learning_rate": 1.594445051712202e-06,
"loss": 0.4516,
"step": 692
},
{
"epoch": 1.7989657401422108,
"grad_norm": 0.18131399154663086,
"learning_rate": 1.58616022330076e-06,
"loss": 0.4574,
"step": 696
},
{
"epoch": 1.8093083387201034,
"grad_norm": 0.16902993619441986,
"learning_rate": 1.5779527322799175e-06,
"loss": 0.4506,
"step": 700
},
{
"epoch": 1.819650937297996,
"grad_norm": 0.18973788619041443,
"learning_rate": 1.5698222159889919e-06,
"loss": 0.4542,
"step": 704
},
{
"epoch": 1.829993535875889,
"grad_norm": 0.17884907126426697,
"learning_rate": 1.5617683117673004e-06,
"loss": 0.4627,
"step": 708
},
{
"epoch": 1.8403361344537816,
"grad_norm": 0.1736602783203125,
"learning_rate": 1.55379065695416e-06,
"loss": 0.447,
"step": 712
},
{
"epoch": 1.8506787330316743,
"grad_norm": 0.1826103925704956,
"learning_rate": 1.5458888888888889e-06,
"loss": 0.4634,
"step": 716
},
{
"epoch": 1.861021331609567,
"grad_norm": 0.17924711108207703,
"learning_rate": 1.5380626449108035e-06,
"loss": 0.4436,
"step": 720
},
{
"epoch": 1.8713639301874596,
"grad_norm": 0.17868177592754364,
"learning_rate": 1.5303115623592214e-06,
"loss": 0.4394,
"step": 724
},
{
"epoch": 1.8817065287653523,
"grad_norm": 0.18871541321277618,
"learning_rate": 1.522635278573459e-06,
"loss": 0.4698,
"step": 728
},
{
"epoch": 1.892049127343245,
"grad_norm": 0.17588797211647034,
"learning_rate": 1.5150334308928344e-06,
"loss": 0.4591,
"step": 732
},
{
"epoch": 1.9023917259211376,
"grad_norm": 0.18185260891914368,
"learning_rate": 1.507505656656665e-06,
"loss": 0.465,
"step": 736
},
{
"epoch": 1.9127343244990302,
"grad_norm": 0.18905200064182281,
"learning_rate": 1.5000515932042678e-06,
"loss": 0.4609,
"step": 740
},
{
"epoch": 1.9230769230769231,
"grad_norm": 0.19702599942684174,
"learning_rate": 1.4926708778749595e-06,
"loss": 0.4444,
"step": 744
},
{
"epoch": 1.9334195216548158,
"grad_norm": 0.18513160943984985,
"learning_rate": 1.4853631480080578e-06,
"loss": 0.4565,
"step": 748
},
{
"epoch": 1.9437621202327084,
"grad_norm": 0.17975644767284393,
"learning_rate": 1.4781280409428802e-06,
"loss": 0.4474,
"step": 752
},
{
"epoch": 1.9541047188106013,
"grad_norm": 0.1855587661266327,
"learning_rate": 1.4709651940187429e-06,
"loss": 0.4517,
"step": 756
},
{
"epoch": 1.964447317388494,
"grad_norm": 0.18554966151714325,
"learning_rate": 1.4638742445749645e-06,
"loss": 0.4654,
"step": 760
},
{
"epoch": 1.9747899159663866,
"grad_norm": 0.18967655301094055,
"learning_rate": 1.4568548299508615e-06,
"loss": 0.463,
"step": 764
},
{
"epoch": 1.9851325145442793,
"grad_norm": 0.17238129675388336,
"learning_rate": 1.4499065874857511e-06,
"loss": 0.4525,
"step": 768
},
{
"epoch": 1.995475113122172,
"grad_norm": 0.17824146151542664,
"learning_rate": 1.4430291545189505e-06,
"loss": 0.4443,
"step": 772
},
{
"epoch": 2.0051712992889463,
"grad_norm": 0.1638309806585312,
"learning_rate": 1.4362221683897769e-06,
"loss": 0.4533,
"step": 776
},
{
"epoch": 2.015513897866839,
"grad_norm": 0.19044017791748047,
"learning_rate": 1.4294852664375482e-06,
"loss": 0.4434,
"step": 780
},
{
"epoch": 2.0258564964447316,
"grad_norm": 0.18576934933662415,
"learning_rate": 1.422818086001581e-06,
"loss": 0.4486,
"step": 784
},
{
"epoch": 2.0361990950226243,
"grad_norm": 0.17555150389671326,
"learning_rate": 1.4162202644211928e-06,
"loss": 0.4619,
"step": 788
},
{
"epoch": 2.046541693600517,
"grad_norm": 0.18890970945358276,
"learning_rate": 1.4096914390357005e-06,
"loss": 0.449,
"step": 792
},
{
"epoch": 2.0568842921784096,
"grad_norm": 0.17668835818767548,
"learning_rate": 1.4032312471844212e-06,
"loss": 0.4613,
"step": 796
},
{
"epoch": 2.0672268907563027,
"grad_norm": 0.17829003930091858,
"learning_rate": 1.3968393262066731e-06,
"loss": 0.4578,
"step": 800
},
{
"epoch": 2.0775694893341954,
"grad_norm": 0.1794648915529251,
"learning_rate": 1.3905153134417726e-06,
"loss": 0.4615,
"step": 804
},
{
"epoch": 2.087912087912088,
"grad_norm": 0.1816921979188919,
"learning_rate": 1.3842588462290373e-06,
"loss": 0.4431,
"step": 808
},
{
"epoch": 2.0982546864899807,
"grad_norm": 0.16857373714447021,
"learning_rate": 1.378069561907784e-06,
"loss": 0.4508,
"step": 812
},
{
"epoch": 2.1085972850678734,
"grad_norm": 0.18902304768562317,
"learning_rate": 1.3719470978173305e-06,
"loss": 0.4578,
"step": 816
},
{
"epoch": 2.118939883645766,
"grad_norm": 0.17235969007015228,
"learning_rate": 1.3658910912969934e-06,
"loss": 0.4504,
"step": 820
},
{
"epoch": 2.1292824822236587,
"grad_norm": 0.1716686636209488,
"learning_rate": 1.3599011796860908e-06,
"loss": 0.452,
"step": 824
},
{
"epoch": 2.1396250808015513,
"grad_norm": 0.17327377200126648,
"learning_rate": 1.3539770003239391e-06,
"loss": 0.446,
"step": 828
},
{
"epoch": 2.149967679379444,
"grad_norm": 0.1813182234764099,
"learning_rate": 1.3481181905498559e-06,
"loss": 0.4481,
"step": 832
},
{
"epoch": 2.1603102779573367,
"grad_norm": 0.17645367980003357,
"learning_rate": 1.3423243877031582e-06,
"loss": 0.4566,
"step": 836
},
{
"epoch": 2.1706528765352293,
"grad_norm": 0.17306523025035858,
"learning_rate": 1.336595229123164e-06,
"loss": 0.4514,
"step": 840
},
{
"epoch": 2.180995475113122,
"grad_norm": 0.17180515825748444,
"learning_rate": 1.3309303521491894e-06,
"loss": 0.4501,
"step": 844
},
{
"epoch": 2.191338073691015,
"grad_norm": 0.17196668684482574,
"learning_rate": 1.3253293941205526e-06,
"loss": 0.4539,
"step": 848
},
{
"epoch": 2.2016806722689077,
"grad_norm": 0.16701729595661163,
"learning_rate": 1.3197919923765701e-06,
"loss": 0.4557,
"step": 852
},
{
"epoch": 2.2120232708468004,
"grad_norm": 0.18192018568515778,
"learning_rate": 1.3143177842565595e-06,
"loss": 0.4508,
"step": 856
},
{
"epoch": 2.222365869424693,
"grad_norm": 0.17954544723033905,
"learning_rate": 1.3089064070998384e-06,
"loss": 0.4428,
"step": 860
},
{
"epoch": 2.2327084680025857,
"grad_norm": 0.185075044631958,
"learning_rate": 1.3035574982457233e-06,
"loss": 0.4536,
"step": 864
},
{
"epoch": 2.2430510665804784,
"grad_norm": 0.19131481647491455,
"learning_rate": 1.298270695033532e-06,
"loss": 0.4552,
"step": 868
},
{
"epoch": 2.253393665158371,
"grad_norm": 0.18936187028884888,
"learning_rate": 1.2930456348025814e-06,
"loss": 0.4478,
"step": 872
},
{
"epoch": 2.2637362637362637,
"grad_norm": 0.2016269713640213,
"learning_rate": 1.2878819548921887e-06,
"loss": 0.4534,
"step": 876
},
{
"epoch": 2.2740788623141563,
"grad_norm": 0.21272307634353638,
"learning_rate": 1.2827792926416714e-06,
"loss": 0.4434,
"step": 880
},
{
"epoch": 2.284421460892049,
"grad_norm": 0.18152523040771484,
"learning_rate": 1.2777372853903463e-06,
"loss": 0.4502,
"step": 884
},
{
"epoch": 2.2947640594699417,
"grad_norm": 0.17132383584976196,
"learning_rate": 1.2727555704775317e-06,
"loss": 0.4402,
"step": 888
},
{
"epoch": 2.3051066580478343,
"grad_norm": 0.17692337930202484,
"learning_rate": 1.2678337852425434e-06,
"loss": 0.4509,
"step": 892
},
{
"epoch": 2.315449256625727,
"grad_norm": 0.18354307115077972,
"learning_rate": 1.2629715670246996e-06,
"loss": 0.4508,
"step": 896
},
{
"epoch": 2.32579185520362,
"grad_norm": 0.17618027329444885,
"learning_rate": 1.258168553163317e-06,
"loss": 0.4469,
"step": 900
},
{
"epoch": 2.3361344537815127,
"grad_norm": 0.1840873807668686,
"learning_rate": 1.2534243809977136e-06,
"loss": 0.4485,
"step": 904
},
{
"epoch": 2.3464770523594054,
"grad_norm": 0.1692686676979065,
"learning_rate": 1.2487386878672057e-06,
"loss": 0.4532,
"step": 908
},
{
"epoch": 2.356819650937298,
"grad_norm": 0.17941194772720337,
"learning_rate": 1.244111111111111e-06,
"loss": 0.4601,
"step": 912
},
{
"epoch": 2.3671622495151907,
"grad_norm": 0.17824317514896393,
"learning_rate": 1.2395412880687467e-06,
"loss": 0.4653,
"step": 916
},
{
"epoch": 2.3775048480930834,
"grad_norm": 0.17118173837661743,
"learning_rate": 1.2350288560794302e-06,
"loss": 0.4535,
"step": 920
},
{
"epoch": 2.387847446670976,
"grad_norm": 0.19625437259674072,
"learning_rate": 1.2305734524824784e-06,
"loss": 0.456,
"step": 924
},
{
"epoch": 2.3981900452488687,
"grad_norm": 0.17811912298202515,
"learning_rate": 1.2261747146172087e-06,
"loss": 0.4428,
"step": 928
},
{
"epoch": 2.4085326438267614,
"grad_norm": 0.17827966809272766,
"learning_rate": 1.2218322798229384e-06,
"loss": 0.461,
"step": 932
},
{
"epoch": 2.418875242404654,
"grad_norm": 0.19108909368515015,
"learning_rate": 1.2175457854389847e-06,
"loss": 0.4569,
"step": 936
},
{
"epoch": 2.4292178409825467,
"grad_norm": 0.16872255504131317,
"learning_rate": 1.2133148688046646e-06,
"loss": 0.4529,
"step": 940
},
{
"epoch": 2.4395604395604398,
"grad_norm": 0.17768999934196472,
"learning_rate": 1.2091391672592957e-06,
"loss": 0.4512,
"step": 944
},
{
"epoch": 2.4499030381383324,
"grad_norm": 0.17542874813079834,
"learning_rate": 1.205018318142195e-06,
"loss": 0.4488,
"step": 948
},
{
"epoch": 2.460245636716225,
"grad_norm": 0.18069233000278473,
"learning_rate": 1.20095195879268e-06,
"loss": 0.4512,
"step": 952
},
{
"epoch": 2.4705882352941178,
"grad_norm": 0.17639058828353882,
"learning_rate": 1.1969397265500675e-06,
"loss": 0.4489,
"step": 956
},
{
"epoch": 2.4809308338720104,
"grad_norm": 0.17847612500190735,
"learning_rate": 1.192981258753675e-06,
"loss": 0.45,
"step": 960
},
{
"epoch": 2.491273432449903,
"grad_norm": 0.1748712956905365,
"learning_rate": 1.1890761927428197e-06,
"loss": 0.438,
"step": 964
},
{
"epoch": 2.5016160310277957,
"grad_norm": 0.1816711723804474,
"learning_rate": 1.185224165856819e-06,
"loss": 0.4513,
"step": 968
},
{
"epoch": 2.5119586296056884,
"grad_norm": 0.17945519089698792,
"learning_rate": 1.1814248154349897e-06,
"loss": 0.4505,
"step": 972
},
{
"epoch": 2.522301228183581,
"grad_norm": 0.1755056381225586,
"learning_rate": 1.1776777788166495e-06,
"loss": 0.4587,
"step": 976
},
{
"epoch": 2.5326438267614737,
"grad_norm": 0.2565567195415497,
"learning_rate": 1.1739826933411155e-06,
"loss": 0.4578,
"step": 980
},
{
"epoch": 2.5429864253393664,
"grad_norm": 0.1997365802526474,
"learning_rate": 1.1703391963477048e-06,
"loss": 0.4487,
"step": 984
},
{
"epoch": 2.553329023917259,
"grad_norm": 0.18262676894664764,
"learning_rate": 1.1667469251757346e-06,
"loss": 0.4453,
"step": 988
},
{
"epoch": 2.5636716224951517,
"grad_norm": 0.17584246397018433,
"learning_rate": 1.1632055171645223e-06,
"loss": 0.4427,
"step": 992
},
{
"epoch": 2.5740142210730443,
"grad_norm": 0.1811375468969345,
"learning_rate": 1.1597146096533852e-06,
"loss": 0.4574,
"step": 996
},
{
"epoch": 2.5843568196509374,
"grad_norm": 0.1873408406972885,
"learning_rate": 1.1562738399816404e-06,
"loss": 0.4562,
"step": 1000
},
{
"epoch": 2.59469941822883,
"grad_norm": 0.18968404829502106,
"learning_rate": 1.152882845488605e-06,
"loss": 0.4468,
"step": 1004
},
{
"epoch": 2.6050420168067228,
"grad_norm": 0.1783261001110077,
"learning_rate": 1.1495412635135963e-06,
"loss": 0.4539,
"step": 1008
},
{
"epoch": 2.6153846153846154,
"grad_norm": 0.1903458833694458,
"learning_rate": 1.146248731395932e-06,
"loss": 0.4578,
"step": 1012
},
{
"epoch": 2.625727213962508,
"grad_norm": 0.17537672817707062,
"learning_rate": 1.1430048864749287e-06,
"loss": 0.4566,
"step": 1016
},
{
"epoch": 2.6360698125404007,
"grad_norm": 0.1887020617723465,
"learning_rate": 1.139809366089904e-06,
"loss": 0.4464,
"step": 1020
},
{
"epoch": 2.6464124111182934,
"grad_norm": 0.18123377859592438,
"learning_rate": 1.136661807580175e-06,
"loss": 0.4593,
"step": 1024
},
{
"epoch": 2.656755009696186,
"grad_norm": 0.1783813238143921,
"learning_rate": 1.133561848285059e-06,
"loss": 0.4499,
"step": 1028
},
{
"epoch": 2.6670976082740787,
"grad_norm": 0.17778170108795166,
"learning_rate": 1.130509125543873e-06,
"loss": 0.4486,
"step": 1032
},
{
"epoch": 2.677440206851972,
"grad_norm": 0.18150880932807922,
"learning_rate": 1.1275032766959346e-06,
"loss": 0.4515,
"step": 1036
},
{
"epoch": 2.6877828054298645,
"grad_norm": 0.17898158729076385,
"learning_rate": 1.1245439390805607e-06,
"loss": 0.4434,
"step": 1040
},
{
"epoch": 2.698125404007757,
"grad_norm": 0.18532375991344452,
"learning_rate": 1.1216307500370688e-06,
"loss": 0.4486,
"step": 1044
},
{
"epoch": 2.70846800258565,
"grad_norm": 0.1722891479730606,
"learning_rate": 1.118763346904776e-06,
"loss": 0.4548,
"step": 1048
},
{
"epoch": 2.7188106011635425,
"grad_norm": 0.1772516816854477,
"learning_rate": 1.1159413670229997e-06,
"loss": 0.4555,
"step": 1052
},
{
"epoch": 2.729153199741435,
"grad_norm": 0.17695064842700958,
"learning_rate": 1.1131644477310569e-06,
"loss": 0.4607,
"step": 1056
},
{
"epoch": 2.7394957983193278,
"grad_norm": 0.17609025537967682,
"learning_rate": 1.110432226368265e-06,
"loss": 0.4446,
"step": 1060
},
{
"epoch": 2.7498383968972204,
"grad_norm": 0.17976413667201996,
"learning_rate": 1.107744340273941e-06,
"loss": 0.4467,
"step": 1064
},
{
"epoch": 2.760180995475113,
"grad_norm": 0.18428538739681244,
"learning_rate": 1.1051004267874023e-06,
"loss": 0.4555,
"step": 1068
},
{
"epoch": 2.7705235940530057,
"grad_norm": 0.17254601418972015,
"learning_rate": 1.1025001232479663e-06,
"loss": 0.4432,
"step": 1072
},
{
"epoch": 2.7808661926308984,
"grad_norm": 0.17763815820217133,
"learning_rate": 1.09994306699495e-06,
"loss": 0.4533,
"step": 1076
},
{
"epoch": 2.791208791208791,
"grad_norm": 0.18219688534736633,
"learning_rate": 1.097428895367671e-06,
"loss": 0.455,
"step": 1080
},
{
"epoch": 2.8015513897866837,
"grad_norm": 0.17637620866298676,
"learning_rate": 1.0949572457054458e-06,
"loss": 0.4406,
"step": 1084
},
{
"epoch": 2.8118939883645764,
"grad_norm": 0.1767360419034958,
"learning_rate": 1.0925277553475922e-06,
"loss": 0.4504,
"step": 1088
},
{
"epoch": 2.822236586942469,
"grad_norm": 0.1777689903974533,
"learning_rate": 1.0901400616334274e-06,
"loss": 0.4443,
"step": 1092
},
{
"epoch": 2.832579185520362,
"grad_norm": 0.17348885536193848,
"learning_rate": 1.0877938019022687e-06,
"loss": 0.455,
"step": 1096
},
{
"epoch": 2.842921784098255,
"grad_norm": 0.16941364109516144,
"learning_rate": 1.0854886134934328e-06,
"loss": 0.4463,
"step": 1100
},
{
"epoch": 2.8532643826761475,
"grad_norm": 0.1874593198299408,
"learning_rate": 1.0832241337462376e-06,
"loss": 0.4498,
"step": 1104
},
{
"epoch": 2.86360698125404,
"grad_norm": 0.17837406694889069,
"learning_rate": 1.081e-06,
"loss": 0.454,
"step": 1108
},
{
"epoch": 2.8739495798319328,
"grad_norm": 0.19155140221118927,
"learning_rate": 1.0788158495940373e-06,
"loss": 0.4595,
"step": 1112
},
{
"epoch": 2.8842921784098254,
"grad_norm": 0.17509421706199646,
"learning_rate": 1.0766713198676667e-06,
"loss": 0.4567,
"step": 1116
},
{
"epoch": 2.894634776987718,
"grad_norm": 0.17931582033634186,
"learning_rate": 1.0745660481602052e-06,
"loss": 0.4536,
"step": 1120
},
{
"epoch": 2.9049773755656108,
"grad_norm": 0.1758774369955063,
"learning_rate": 1.0724996718109706e-06,
"loss": 0.4532,
"step": 1124
},
{
"epoch": 2.9153199741435034,
"grad_norm": 0.176919624209404,
"learning_rate": 1.0704718281592797e-06,
"loss": 0.4529,
"step": 1128
},
{
"epoch": 2.9256625727213965,
"grad_norm": 0.1802259087562561,
"learning_rate": 1.06848215454445e-06,
"loss": 0.4455,
"step": 1132
},
{
"epoch": 2.936005171299289,
"grad_norm": 0.16593530774116516,
"learning_rate": 1.0665302883057984e-06,
"loss": 0.4459,
"step": 1136
},
{
"epoch": 2.946347769877182,
"grad_norm": 0.17818193137645721,
"learning_rate": 1.0646158667826425e-06,
"loss": 0.4566,
"step": 1140
},
{
"epoch": 2.9566903684550745,
"grad_norm": 0.17576196789741516,
"learning_rate": 1.0627385273142993e-06,
"loss": 0.439,
"step": 1144
},
{
"epoch": 2.967032967032967,
"grad_norm": 0.1871625781059265,
"learning_rate": 1.0608979072400862e-06,
"loss": 0.4507,
"step": 1148
},
{
"epoch": 2.97737556561086,
"grad_norm": 0.18743683397769928,
"learning_rate": 1.05909364389932e-06,
"loss": 0.449,
"step": 1152
},
{
"epoch": 2.9877181641887525,
"grad_norm": 0.1833522915840149,
"learning_rate": 1.0573253746313186e-06,
"loss": 0.4577,
"step": 1156
},
{
"epoch": 2.998060762766645,
"grad_norm": 0.17550155520439148,
"learning_rate": 1.0555927367753988e-06,
"loss": 0.4523,
"step": 1160
},
{
"epoch": 3.0077569489334195,
"grad_norm": 0.17497506737709045,
"learning_rate": 1.0538953676708778e-06,
"loss": 0.443,
"step": 1164
},
{
"epoch": 3.018099547511312,
"grad_norm": 0.18479323387145996,
"learning_rate": 1.052232904657073e-06,
"loss": 0.4476,
"step": 1168
},
{
"epoch": 3.028442146089205,
"grad_norm": 0.17023231089115143,
"learning_rate": 1.0506049850733017e-06,
"loss": 0.4446,
"step": 1172
},
{
"epoch": 3.0387847446670975,
"grad_norm": 0.194169819355011,
"learning_rate": 1.0490112462588812e-06,
"loss": 0.4436,
"step": 1176
},
{
"epoch": 3.04912734324499,
"grad_norm": 0.16968706250190735,
"learning_rate": 1.0474513255531283e-06,
"loss": 0.4445,
"step": 1180
},
{
"epoch": 3.059469941822883,
"grad_norm": 0.18906928598880768,
"learning_rate": 1.0459248602953606e-06,
"loss": 0.464,
"step": 1184
},
{
"epoch": 3.069812540400776,
"grad_norm": 0.17577582597732544,
"learning_rate": 1.0444314878248952e-06,
"loss": 0.4505,
"step": 1188
},
{
"epoch": 3.0801551389786685,
"grad_norm": 0.16838566958904266,
"learning_rate": 1.0429708454810495e-06,
"loss": 0.4438,
"step": 1192
},
{
"epoch": 3.090497737556561,
"grad_norm": 0.18139545619487762,
"learning_rate": 1.0415425706031406e-06,
"loss": 0.4515,
"step": 1196
},
{
"epoch": 3.100840336134454,
"grad_norm": 0.17523127794265747,
"learning_rate": 1.0401463005304855e-06,
"loss": 0.4475,
"step": 1200
},
{
"epoch": 3.1111829347123465,
"grad_norm": 0.18693816661834717,
"learning_rate": 1.0387816726024021e-06,
"loss": 0.4447,
"step": 1204
},
{
"epoch": 3.121525533290239,
"grad_norm": 0.16429254412651062,
"learning_rate": 1.0374483241582069e-06,
"loss": 0.4509,
"step": 1208
},
{
"epoch": 3.131868131868132,
"grad_norm": 0.18026259541511536,
"learning_rate": 1.0361458925372175e-06,
"loss": 0.4548,
"step": 1212
},
{
"epoch": 3.1422107304460245,
"grad_norm": 0.19680114090442657,
"learning_rate": 1.034874015078751e-06,
"loss": 0.4477,
"step": 1216
},
{
"epoch": 3.152553329023917,
"grad_norm": 0.17316031455993652,
"learning_rate": 1.033632329122125e-06,
"loss": 0.4493,
"step": 1220
},
{
"epoch": 3.16289592760181,
"grad_norm": 0.16267041862010956,
"learning_rate": 1.0324204720066564e-06,
"loss": 0.4409,
"step": 1224
},
{
"epoch": 3.1732385261797025,
"grad_norm": 0.2089986652135849,
"learning_rate": 1.0312380810716623e-06,
"loss": 0.4504,
"step": 1228
},
{
"epoch": 3.183581124757595,
"grad_norm": 0.16956327855587006,
"learning_rate": 1.0300847936564602e-06,
"loss": 0.4471,
"step": 1232
},
{
"epoch": 3.1939237233354882,
"grad_norm": 0.17798687517642975,
"learning_rate": 1.0289602471003672e-06,
"loss": 0.4507,
"step": 1236
},
{
"epoch": 3.204266321913381,
"grad_norm": 0.17512640357017517,
"learning_rate": 1.0278640787427008e-06,
"loss": 0.446,
"step": 1240
},
{
"epoch": 3.2146089204912736,
"grad_norm": 0.17578400671482086,
"learning_rate": 1.0267959259227778e-06,
"loss": 0.4484,
"step": 1244
},
{
"epoch": 3.224951519069166,
"grad_norm": 0.17712455987930298,
"learning_rate": 1.0257554259799157e-06,
"loss": 0.4481,
"step": 1248
},
{
"epoch": 3.235294117647059,
"grad_norm": 0.1793729066848755,
"learning_rate": 1.0247422162534318e-06,
"loss": 0.441,
"step": 1252
},
{
"epoch": 3.2456367162249515,
"grad_norm": 0.16967114806175232,
"learning_rate": 1.0237559340826432e-06,
"loss": 0.4525,
"step": 1256
},
{
"epoch": 3.255979314802844,
"grad_norm": 0.1762080043554306,
"learning_rate": 1.022796216806867e-06,
"loss": 0.4344,
"step": 1260
},
{
"epoch": 3.266321913380737,
"grad_norm": 0.1827186495065689,
"learning_rate": 1.021862701765421e-06,
"loss": 0.4519,
"step": 1264
},
{
"epoch": 3.2766645119586295,
"grad_norm": 0.17989112436771393,
"learning_rate": 1.0209550262976217e-06,
"loss": 0.4513,
"step": 1268
},
{
"epoch": 3.287007110536522,
"grad_norm": 0.18342699110507965,
"learning_rate": 1.0200728277427867e-06,
"loss": 0.4485,
"step": 1272
},
{
"epoch": 3.297349709114415,
"grad_norm": 0.19681668281555176,
"learning_rate": 1.0192157434402333e-06,
"loss": 0.4429,
"step": 1276
},
{
"epoch": 3.3076923076923075,
"grad_norm": 0.172057643532753,
"learning_rate": 1.0183834107292785e-06,
"loss": 0.4525,
"step": 1280
},
{
"epoch": 3.3180349062702,
"grad_norm": 0.16999749839305878,
"learning_rate": 1.0175754669492397e-06,
"loss": 0.4532,
"step": 1284
},
{
"epoch": 3.3283775048480932,
"grad_norm": 0.18436214327812195,
"learning_rate": 1.0167915494394342e-06,
"loss": 0.4566,
"step": 1288
},
{
"epoch": 3.338720103425986,
"grad_norm": 0.16745057702064514,
"learning_rate": 1.016031295539179e-06,
"loss": 0.4605,
"step": 1292
},
{
"epoch": 3.3490627020038786,
"grad_norm": 0.18557773530483246,
"learning_rate": 1.0152943425877918e-06,
"loss": 0.4457,
"step": 1296
},
{
"epoch": 3.3594053005817712,
"grad_norm": 0.181436225771904,
"learning_rate": 1.0145803279245893e-06,
"loss": 0.439,
"step": 1300
},
{
"epoch": 3.369747899159664,
"grad_norm": 0.17534784972667694,
"learning_rate": 1.0138888888888887e-06,
"loss": 0.4437,
"step": 1304
},
{
"epoch": 3.3800904977375565,
"grad_norm": 0.17567597329616547,
"learning_rate": 1.0132196628200078e-06,
"loss": 0.4405,
"step": 1308
},
{
"epoch": 3.390433096315449,
"grad_norm": 0.17782679200172424,
"learning_rate": 1.0125722870572635e-06,
"loss": 0.4468,
"step": 1312
},
{
"epoch": 3.400775694893342,
"grad_norm": 0.17457668483257294,
"learning_rate": 1.011946398939973e-06,
"loss": 0.454,
"step": 1316
},
{
"epoch": 3.4111182934712345,
"grad_norm": 0.16642296314239502,
"learning_rate": 1.0113416358074535e-06,
"loss": 0.4465,
"step": 1320
},
{
"epoch": 3.421460892049127,
"grad_norm": 0.17336755990982056,
"learning_rate": 1.0107576349990224e-06,
"loss": 0.456,
"step": 1324
},
{
"epoch": 3.4318034906270203,
"grad_norm": 0.18164758384227753,
"learning_rate": 1.010194033853997e-06,
"loss": 0.4469,
"step": 1328
},
{
"epoch": 3.442146089204913,
"grad_norm": 0.1722988784313202,
"learning_rate": 1.009650469711694e-06,
"loss": 0.4471,
"step": 1332
},
{
"epoch": 3.4524886877828056,
"grad_norm": 0.17613555490970612,
"learning_rate": 1.0091265799114313e-06,
"loss": 0.4473,
"step": 1336
},
{
"epoch": 3.4628312863606983,
"grad_norm": 0.17907673120498657,
"learning_rate": 1.008622001792526e-06,
"loss": 0.4611,
"step": 1340
},
{
"epoch": 3.473173884938591,
"grad_norm": 0.18107053637504578,
"learning_rate": 1.0081363726942948e-06,
"loss": 0.4415,
"step": 1344
},
{
"epoch": 3.4835164835164836,
"grad_norm": 0.19422635436058044,
"learning_rate": 1.0076693299560557e-06,
"loss": 0.4413,
"step": 1348
},
{
"epoch": 3.4938590820943762,
"grad_norm": 0.1928495168685913,
"learning_rate": 1.0072205109171253e-06,
"loss": 0.4525,
"step": 1352
},
{
"epoch": 3.504201680672269,
"grad_norm": 0.17438076436519623,
"learning_rate": 1.0067895529168213e-06,
"loss": 0.4435,
"step": 1356
},
{
"epoch": 3.5145442792501616,
"grad_norm": 0.17133189737796783,
"learning_rate": 1.0063760932944606e-06,
"loss": 0.4574,
"step": 1360
},
{
"epoch": 3.524886877828054,
"grad_norm": 0.18594177067279816,
"learning_rate": 1.0059797693893605e-06,
"loss": 0.4434,
"step": 1364
},
{
"epoch": 3.535229476405947,
"grad_norm": 0.1890227347612381,
"learning_rate": 1.0056002185408385e-06,
"loss": 0.4556,
"step": 1368
},
{
"epoch": 3.5455720749838395,
"grad_norm": 0.17522525787353516,
"learning_rate": 1.0052370780882114e-06,
"loss": 0.4506,
"step": 1372
},
{
"epoch": 3.555914673561732,
"grad_norm": 0.18247763812541962,
"learning_rate": 1.0048899853707968e-06,
"loss": 0.4485,
"step": 1376
},
{
"epoch": 3.566257272139625,
"grad_norm": 0.18556474149227142,
"learning_rate": 1.0045585777279118e-06,
"loss": 0.4579,
"step": 1380
},
{
"epoch": 3.5765998707175175,
"grad_norm": 0.17300067842006683,
"learning_rate": 1.0042424924988736e-06,
"loss": 0.4512,
"step": 1384
},
{
"epoch": 3.5869424692954106,
"grad_norm": 0.18004953861236572,
"learning_rate": 1.0039413670229995e-06,
"loss": 0.4453,
"step": 1388
},
{
"epoch": 3.5972850678733033,
"grad_norm": 0.1785740703344345,
"learning_rate": 1.0036548386396067e-06,
"loss": 0.4449,
"step": 1392
},
{
"epoch": 3.607627666451196,
"grad_norm": 0.16730371117591858,
"learning_rate": 1.0033825446880127e-06,
"loss": 0.4485,
"step": 1396
},
{
"epoch": 3.6179702650290886,
"grad_norm": 0.18206489086151123,
"learning_rate": 1.0031241225075341e-06,
"loss": 0.4471,
"step": 1400
},
{
"epoch": 3.6283128636069812,
"grad_norm": 0.17622709274291992,
"learning_rate": 1.0028792094374887e-06,
"loss": 0.4436,
"step": 1404
},
{
"epoch": 3.638655462184874,
"grad_norm": 0.18737947940826416,
"learning_rate": 1.0026474428171935e-06,
"loss": 0.4389,
"step": 1408
},
{
"epoch": 3.6489980607627666,
"grad_norm": 0.17098890244960785,
"learning_rate": 1.0024284599859658e-06,
"loss": 0.4363,
"step": 1412
},
{
"epoch": 3.659340659340659,
"grad_norm": 0.17516440153121948,
"learning_rate": 1.0022218982831228e-06,
"loss": 0.4503,
"step": 1416
},
{
"epoch": 3.669683257918552,
"grad_norm": 0.18128778040409088,
"learning_rate": 1.0020273950479815e-06,
"loss": 0.441,
"step": 1420
},
{
"epoch": 3.680025856496445,
"grad_norm": 0.18445086479187012,
"learning_rate": 1.0018445876198597e-06,
"loss": 0.4389,
"step": 1424
},
{
"epoch": 3.6903684550743376,
"grad_norm": 0.18264997005462646,
"learning_rate": 1.0016731133380744e-06,
"loss": 0.4394,
"step": 1428
},
{
"epoch": 3.7007110536522303,
"grad_norm": 0.17699220776557922,
"learning_rate": 1.0015126095419424e-06,
"loss": 0.4494,
"step": 1432
},
{
"epoch": 3.711053652230123,
"grad_norm": 0.17461882531642914,
"learning_rate": 1.0013627135707816e-06,
"loss": 0.4521,
"step": 1436
},
{
"epoch": 3.7213962508080156,
"grad_norm": 0.17526471614837646,
"learning_rate": 1.0012230627639088e-06,
"loss": 0.4389,
"step": 1440
},
{
"epoch": 3.7317388493859083,
"grad_norm": 0.17140990495681763,
"learning_rate": 1.0010932944606414e-06,
"loss": 0.4489,
"step": 1444
},
{
"epoch": 3.742081447963801,
"grad_norm": 0.19351443648338318,
"learning_rate": 1.0009730460002965e-06,
"loss": 0.4436,
"step": 1448
},
{
"epoch": 3.7524240465416936,
"grad_norm": 0.1850733458995819,
"learning_rate": 1.0008619547221914e-06,
"loss": 0.4514,
"step": 1452
},
{
"epoch": 3.7627666451195863,
"grad_norm": 0.18625636398792267,
"learning_rate": 1.0007596579656435e-06,
"loss": 0.4484,
"step": 1456
},
{
"epoch": 3.773109243697479,
"grad_norm": 0.18134167790412903,
"learning_rate": 1.00066579306997e-06,
"loss": 0.4549,
"step": 1460
},
{
"epoch": 3.7834518422753716,
"grad_norm": 0.19236284494400024,
"learning_rate": 1.0005799973744876e-06,
"loss": 0.4433,
"step": 1464
},
{
"epoch": 3.7937944408532642,
"grad_norm": 0.1741548478603363,
"learning_rate": 1.0005019082185143e-06,
"loss": 0.4476,
"step": 1468
},
{
"epoch": 3.804137039431157,
"grad_norm": 0.17673614621162415,
"learning_rate": 1.000431162941367e-06,
"loss": 0.4462,
"step": 1472
},
{
"epoch": 3.8144796380090495,
"grad_norm": 0.1771819293498993,
"learning_rate": 1.0003673988823628e-06,
"loss": 0.4561,
"step": 1476
},
{
"epoch": 3.824822236586942,
"grad_norm": 0.17858363687992096,
"learning_rate": 1.0003102533808192e-06,
"loss": 0.4479,
"step": 1480
},
{
"epoch": 3.8351648351648353,
"grad_norm": 0.16550451517105103,
"learning_rate": 1.0002593637760531e-06,
"loss": 0.4488,
"step": 1484
},
{
"epoch": 3.845507433742728,
"grad_norm": 0.17858079075813293,
"learning_rate": 1.0002143674073823e-06,
"loss": 0.45,
"step": 1488
},
{
"epoch": 3.8558500323206206,
"grad_norm": 0.187116801738739,
"learning_rate": 1.0001749016141235e-06,
"loss": 0.4474,
"step": 1492
},
{
"epoch": 3.8661926308985133,
"grad_norm": 0.18668505549430847,
"learning_rate": 1.0001406037355939e-06,
"loss": 0.4432,
"step": 1496
},
{
"epoch": 3.876535229476406,
"grad_norm": 0.17585262656211853,
"learning_rate": 1.0001111111111112e-06,
"loss": 0.4439,
"step": 1500
},
{
"epoch": 3.8868778280542986,
"grad_norm": 0.17823632061481476,
"learning_rate": 1.0000860610799922e-06,
"loss": 0.4576,
"step": 1504
},
{
"epoch": 3.8972204266321913,
"grad_norm": 0.1767703890800476,
"learning_rate": 1.0000650909815542e-06,
"loss": 0.4542,
"step": 1508
},
{
"epoch": 3.907563025210084,
"grad_norm": 0.16956399381160736,
"learning_rate": 1.0000478381551149e-06,
"loss": 0.4533,
"step": 1512
},
{
"epoch": 3.9179056237879766,
"grad_norm": 0.17914198338985443,
"learning_rate": 1.000033939939991e-06,
"loss": 0.4456,
"step": 1516
},
{
"epoch": 3.9282482223658697,
"grad_norm": 0.1634252965450287,
"learning_rate": 1.0000230336754998e-06,
"loss": 0.4466,
"step": 1520
},
{
"epoch": 3.9385908209437623,
"grad_norm": 0.17150919139385223,
"learning_rate": 1.0000147567009588e-06,
"loss": 0.4466,
"step": 1524
},
{
"epoch": 3.948933419521655,
"grad_norm": 0.18172475695610046,
"learning_rate": 1.0000087463556851e-06,
"loss": 0.4431,
"step": 1528
},
{
"epoch": 3.9592760180995477,
"grad_norm": 0.1767711490392685,
"learning_rate": 1.000004639978996e-06,
"loss": 0.4512,
"step": 1532
},
{
"epoch": 3.9696186166774403,
"grad_norm": 0.1694304198026657,
"learning_rate": 1.0000020749102083e-06,
"loss": 0.4483,
"step": 1536
},
{
"epoch": 3.979961215255333,
"grad_norm": 0.18949837982654572,
"learning_rate": 1.0000006884886399e-06,
"loss": 0.4464,
"step": 1540
},
{
"epoch": 3.9903038138332256,
"grad_norm": 0.17919163405895233,
"learning_rate": 1.0000001180536076e-06,
"loss": 0.4572,
"step": 1544
},
{
"epoch": 4.0,
"grad_norm": 0.3023968040943146,
"learning_rate": 1.0000000009444288e-06,
"loss": 0.4456,
"step": 1548
}
],
"logging_steps": 4,
"max_steps": 1548,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 15000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6.286572983201956e+17,
"train_batch_size": 216,
"trial_name": null,
"trial_params": null
}