terry69's picture
Model save
c4eb6eb verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1862,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005370569280343716,
"grad_norm": 22.588933949376393,
"learning_rate": 5.3475935828877005e-08,
"loss": 1.3431,
"step": 1
},
{
"epoch": 0.0026852846401718583,
"grad_norm": 23.126610303920064,
"learning_rate": 2.6737967914438503e-07,
"loss": 1.3385,
"step": 5
},
{
"epoch": 0.0053705692803437165,
"grad_norm": 15.096265452912455,
"learning_rate": 5.347593582887701e-07,
"loss": 1.2761,
"step": 10
},
{
"epoch": 0.008055853920515575,
"grad_norm": 11.796547912841314,
"learning_rate": 8.021390374331551e-07,
"loss": 1.1302,
"step": 15
},
{
"epoch": 0.010741138560687433,
"grad_norm": 8.258152471654855,
"learning_rate": 1.0695187165775401e-06,
"loss": 1.0209,
"step": 20
},
{
"epoch": 0.01342642320085929,
"grad_norm": 3.436573845389504,
"learning_rate": 1.3368983957219254e-06,
"loss": 0.924,
"step": 25
},
{
"epoch": 0.01611170784103115,
"grad_norm": 3.684694803492529,
"learning_rate": 1.6042780748663103e-06,
"loss": 0.89,
"step": 30
},
{
"epoch": 0.018796992481203006,
"grad_norm": 3.0217633865657,
"learning_rate": 1.8716577540106954e-06,
"loss": 0.8615,
"step": 35
},
{
"epoch": 0.021482277121374866,
"grad_norm": 2.922890660969875,
"learning_rate": 2.1390374331550802e-06,
"loss": 0.8394,
"step": 40
},
{
"epoch": 0.024167561761546726,
"grad_norm": 3.0080941873826115,
"learning_rate": 2.4064171122994653e-06,
"loss": 0.8354,
"step": 45
},
{
"epoch": 0.02685284640171858,
"grad_norm": 3.051808184599371,
"learning_rate": 2.673796791443851e-06,
"loss": 0.8281,
"step": 50
},
{
"epoch": 0.02953813104189044,
"grad_norm": 2.9407863618110697,
"learning_rate": 2.9411764705882355e-06,
"loss": 0.8099,
"step": 55
},
{
"epoch": 0.0322234156820623,
"grad_norm": 3.0361086960659502,
"learning_rate": 3.2085561497326205e-06,
"loss": 0.8008,
"step": 60
},
{
"epoch": 0.03490870032223416,
"grad_norm": 3.0542935660919537,
"learning_rate": 3.4759358288770056e-06,
"loss": 0.7945,
"step": 65
},
{
"epoch": 0.03759398496240601,
"grad_norm": 3.1339190627740794,
"learning_rate": 3.7433155080213907e-06,
"loss": 0.7788,
"step": 70
},
{
"epoch": 0.040279269602577876,
"grad_norm": 2.96097897092436,
"learning_rate": 4.010695187165775e-06,
"loss": 0.7661,
"step": 75
},
{
"epoch": 0.04296455424274973,
"grad_norm": 3.3434671670812426,
"learning_rate": 4.2780748663101604e-06,
"loss": 0.7577,
"step": 80
},
{
"epoch": 0.04564983888292159,
"grad_norm": 3.154114094287673,
"learning_rate": 4.5454545454545455e-06,
"loss": 0.7561,
"step": 85
},
{
"epoch": 0.04833512352309345,
"grad_norm": 3.0765656232864638,
"learning_rate": 4.812834224598931e-06,
"loss": 0.753,
"step": 90
},
{
"epoch": 0.05102040816326531,
"grad_norm": 3.2354663116960323,
"learning_rate": 5.0802139037433165e-06,
"loss": 0.7524,
"step": 95
},
{
"epoch": 0.05370569280343716,
"grad_norm": 3.1193615385736244,
"learning_rate": 5.347593582887702e-06,
"loss": 0.7427,
"step": 100
},
{
"epoch": 0.05639097744360902,
"grad_norm": 3.1619975304049732,
"learning_rate": 5.614973262032086e-06,
"loss": 0.744,
"step": 105
},
{
"epoch": 0.05907626208378088,
"grad_norm": 3.061338630250798,
"learning_rate": 5.882352941176471e-06,
"loss": 0.7315,
"step": 110
},
{
"epoch": 0.06176154672395274,
"grad_norm": 3.0857057085739927,
"learning_rate": 6.149732620320856e-06,
"loss": 0.7152,
"step": 115
},
{
"epoch": 0.0644468313641246,
"grad_norm": 2.9043524672550096,
"learning_rate": 6.417112299465241e-06,
"loss": 0.7206,
"step": 120
},
{
"epoch": 0.06713211600429646,
"grad_norm": 2.9221477672316616,
"learning_rate": 6.684491978609626e-06,
"loss": 0.7281,
"step": 125
},
{
"epoch": 0.06981740064446831,
"grad_norm": 2.9152912041724166,
"learning_rate": 6.951871657754011e-06,
"loss": 0.7131,
"step": 130
},
{
"epoch": 0.07250268528464017,
"grad_norm": 2.9329788036774715,
"learning_rate": 7.219251336898396e-06,
"loss": 0.7079,
"step": 135
},
{
"epoch": 0.07518796992481203,
"grad_norm": 3.0375037435968544,
"learning_rate": 7.486631016042781e-06,
"loss": 0.7093,
"step": 140
},
{
"epoch": 0.07787325456498388,
"grad_norm": 3.051270674011824,
"learning_rate": 7.754010695187166e-06,
"loss": 0.7006,
"step": 145
},
{
"epoch": 0.08055853920515575,
"grad_norm": 2.9898744604886835,
"learning_rate": 8.02139037433155e-06,
"loss": 0.718,
"step": 150
},
{
"epoch": 0.08324382384532761,
"grad_norm": 2.8066106411748484,
"learning_rate": 8.288770053475937e-06,
"loss": 0.7019,
"step": 155
},
{
"epoch": 0.08592910848549946,
"grad_norm": 2.8665874154337407,
"learning_rate": 8.556149732620321e-06,
"loss": 0.7072,
"step": 160
},
{
"epoch": 0.08861439312567132,
"grad_norm": 2.8422820645094644,
"learning_rate": 8.823529411764707e-06,
"loss": 0.7059,
"step": 165
},
{
"epoch": 0.09129967776584318,
"grad_norm": 2.91458979270415,
"learning_rate": 9.090909090909091e-06,
"loss": 0.7098,
"step": 170
},
{
"epoch": 0.09398496240601503,
"grad_norm": 2.8378395890064994,
"learning_rate": 9.358288770053477e-06,
"loss": 0.6841,
"step": 175
},
{
"epoch": 0.0966702470461869,
"grad_norm": 2.894382082134305,
"learning_rate": 9.625668449197861e-06,
"loss": 0.7102,
"step": 180
},
{
"epoch": 0.09935553168635876,
"grad_norm": 2.9031109171921563,
"learning_rate": 9.893048128342247e-06,
"loss": 0.6908,
"step": 185
},
{
"epoch": 0.10204081632653061,
"grad_norm": 2.9094340000858496,
"learning_rate": 9.999920849895074e-06,
"loss": 0.7011,
"step": 190
},
{
"epoch": 0.10472610096670247,
"grad_norm": 2.8398808111732294,
"learning_rate": 9.99943716388422e-06,
"loss": 0.7102,
"step": 195
},
{
"epoch": 0.10741138560687433,
"grad_norm": 2.6933626648843565,
"learning_rate": 9.998513806628825e-06,
"loss": 0.7048,
"step": 200
},
{
"epoch": 0.11009667024704618,
"grad_norm": 2.7619637369366257,
"learning_rate": 9.997150859332753e-06,
"loss": 0.7019,
"step": 205
},
{
"epoch": 0.11278195488721804,
"grad_norm": 2.739895854677953,
"learning_rate": 9.995348441859243e-06,
"loss": 0.6989,
"step": 210
},
{
"epoch": 0.11546723952738991,
"grad_norm": 2.6876684923510457,
"learning_rate": 9.993106712720367e-06,
"loss": 0.6856,
"step": 215
},
{
"epoch": 0.11815252416756176,
"grad_norm": 2.733126603672575,
"learning_rate": 9.990425869063085e-06,
"loss": 0.6983,
"step": 220
},
{
"epoch": 0.12083780880773362,
"grad_norm": 2.59577973330998,
"learning_rate": 9.987306146651908e-06,
"loss": 0.6885,
"step": 225
},
{
"epoch": 0.12352309344790548,
"grad_norm": 2.6403871223270956,
"learning_rate": 9.983747819848168e-06,
"loss": 0.6854,
"step": 230
},
{
"epoch": 0.12620837808807733,
"grad_norm": 2.5755491533468673,
"learning_rate": 9.97975120158589e-06,
"loss": 0.6825,
"step": 235
},
{
"epoch": 0.1288936627282492,
"grad_norm": 2.81952622502626,
"learning_rate": 9.975316643344257e-06,
"loss": 0.6928,
"step": 240
},
{
"epoch": 0.13157894736842105,
"grad_norm": 2.510692499419202,
"learning_rate": 9.970444535116721e-06,
"loss": 0.6871,
"step": 245
},
{
"epoch": 0.13426423200859292,
"grad_norm": 3.2383700116067438,
"learning_rate": 9.965135305376694e-06,
"loss": 0.676,
"step": 250
},
{
"epoch": 0.13694951664876476,
"grad_norm": 2.5471306267663114,
"learning_rate": 9.959389421039863e-06,
"loss": 0.6721,
"step": 255
},
{
"epoch": 0.13963480128893663,
"grad_norm": 2.5819890023767975,
"learning_rate": 9.95320738742313e-06,
"loss": 0.6805,
"step": 260
},
{
"epoch": 0.1423200859291085,
"grad_norm": 2.4981575777247014,
"learning_rate": 9.946589748200185e-06,
"loss": 0.6819,
"step": 265
},
{
"epoch": 0.14500537056928034,
"grad_norm": 2.483435225904423,
"learning_rate": 9.939537085353668e-06,
"loss": 0.6742,
"step": 270
},
{
"epoch": 0.1476906552094522,
"grad_norm": 2.8618041277945125,
"learning_rate": 9.932050019124011e-06,
"loss": 0.6644,
"step": 275
},
{
"epoch": 0.15037593984962405,
"grad_norm": 2.450026253755743,
"learning_rate": 9.924129207954877e-06,
"loss": 0.6683,
"step": 280
},
{
"epoch": 0.15306122448979592,
"grad_norm": 2.9403154726852994,
"learning_rate": 9.915775348435266e-06,
"loss": 0.6623,
"step": 285
},
{
"epoch": 0.15574650912996776,
"grad_norm": 2.4748651098342047,
"learning_rate": 9.906989175238232e-06,
"loss": 0.6699,
"step": 290
},
{
"epoch": 0.15843179377013963,
"grad_norm": 2.4957674990875067,
"learning_rate": 9.8977714610563e-06,
"loss": 0.6689,
"step": 295
},
{
"epoch": 0.1611170784103115,
"grad_norm": 2.517686854278863,
"learning_rate": 9.888123016533496e-06,
"loss": 0.6561,
"step": 300
},
{
"epoch": 0.16380236305048335,
"grad_norm": 2.528466931460507,
"learning_rate": 9.878044690194055e-06,
"loss": 0.6631,
"step": 305
},
{
"epoch": 0.16648764769065522,
"grad_norm": 2.5147869487065955,
"learning_rate": 9.86753736836781e-06,
"loss": 0.6479,
"step": 310
},
{
"epoch": 0.16917293233082706,
"grad_norm": 2.497948806933255,
"learning_rate": 9.856601975112227e-06,
"loss": 0.6407,
"step": 315
},
{
"epoch": 0.17185821697099893,
"grad_norm": 2.510845127090968,
"learning_rate": 9.84523947213116e-06,
"loss": 0.6534,
"step": 320
},
{
"epoch": 0.17454350161117077,
"grad_norm": 2.5052023969942225,
"learning_rate": 9.833450858690257e-06,
"loss": 0.6439,
"step": 325
},
{
"epoch": 0.17722878625134264,
"grad_norm": 2.6576117547178955,
"learning_rate": 9.821237171529088e-06,
"loss": 0.6619,
"step": 330
},
{
"epoch": 0.1799140708915145,
"grad_norm": 2.577684133859449,
"learning_rate": 9.808599484769971e-06,
"loss": 0.6487,
"step": 335
},
{
"epoch": 0.18259935553168635,
"grad_norm": 2.6259810690957734,
"learning_rate": 9.79553890982351e-06,
"loss": 0.6485,
"step": 340
},
{
"epoch": 0.18528464017185822,
"grad_norm": 2.423857881211141,
"learning_rate": 9.782056595290848e-06,
"loss": 0.6342,
"step": 345
},
{
"epoch": 0.18796992481203006,
"grad_norm": 2.4782068169343168,
"learning_rate": 9.768153726862652e-06,
"loss": 0.6452,
"step": 350
},
{
"epoch": 0.19065520945220193,
"grad_norm": 2.4443808217010283,
"learning_rate": 9.753831527214854e-06,
"loss": 0.651,
"step": 355
},
{
"epoch": 0.1933404940923738,
"grad_norm": 2.5231724414182968,
"learning_rate": 9.739091255901105e-06,
"loss": 0.6378,
"step": 360
},
{
"epoch": 0.19602577873254565,
"grad_norm": 2.6836920080961506,
"learning_rate": 9.723934209242015e-06,
"loss": 0.6414,
"step": 365
},
{
"epoch": 0.19871106337271752,
"grad_norm": 2.6292452798311574,
"learning_rate": 9.708361720211146e-06,
"loss": 0.6425,
"step": 370
},
{
"epoch": 0.20139634801288936,
"grad_norm": 2.475346280678399,
"learning_rate": 9.692375158317787e-06,
"loss": 0.6347,
"step": 375
},
{
"epoch": 0.20408163265306123,
"grad_norm": 2.565339369277964,
"learning_rate": 9.675975929486512e-06,
"loss": 0.6341,
"step": 380
},
{
"epoch": 0.20676691729323307,
"grad_norm": 2.503462410823786,
"learning_rate": 9.659165475933537e-06,
"loss": 0.6516,
"step": 385
},
{
"epoch": 0.20945220193340494,
"grad_norm": 2.334079164523965,
"learning_rate": 9.641945276039885e-06,
"loss": 0.6316,
"step": 390
},
{
"epoch": 0.2121374865735768,
"grad_norm": 2.8684602615312915,
"learning_rate": 9.624316844221376e-06,
"loss": 0.6227,
"step": 395
},
{
"epoch": 0.21482277121374865,
"grad_norm": 2.5720560384477342,
"learning_rate": 9.606281730795435e-06,
"loss": 0.6278,
"step": 400
},
{
"epoch": 0.21750805585392052,
"grad_norm": 2.3859750726827653,
"learning_rate": 9.587841521844755e-06,
"loss": 0.6395,
"step": 405
},
{
"epoch": 0.22019334049409237,
"grad_norm": 2.4723928529602084,
"learning_rate": 9.568997839077812e-06,
"loss": 0.6175,
"step": 410
},
{
"epoch": 0.22287862513426424,
"grad_norm": 2.3971232752859666,
"learning_rate": 9.549752339686243e-06,
"loss": 0.632,
"step": 415
},
{
"epoch": 0.22556390977443608,
"grad_norm": 2.6540817678288997,
"learning_rate": 9.530106716199103e-06,
"loss": 0.6301,
"step": 420
},
{
"epoch": 0.22824919441460795,
"grad_norm": 2.6564997195018987,
"learning_rate": 9.510062696334024e-06,
"loss": 0.6369,
"step": 425
},
{
"epoch": 0.23093447905477982,
"grad_norm": 2.473291236984028,
"learning_rate": 9.489622042845266e-06,
"loss": 0.6191,
"step": 430
},
{
"epoch": 0.23361976369495166,
"grad_norm": 2.4712483842974606,
"learning_rate": 9.468786553368694e-06,
"loss": 0.6167,
"step": 435
},
{
"epoch": 0.23630504833512353,
"grad_norm": 2.4149226844204223,
"learning_rate": 9.447558060263693e-06,
"loss": 0.6197,
"step": 440
},
{
"epoch": 0.23899033297529537,
"grad_norm": 2.5229379978319377,
"learning_rate": 9.42593843045201e-06,
"loss": 0.6222,
"step": 445
},
{
"epoch": 0.24167561761546724,
"grad_norm": 2.2881877625047125,
"learning_rate": 9.403929565253582e-06,
"loss": 0.624,
"step": 450
},
{
"epoch": 0.24436090225563908,
"grad_norm": 2.3854975770678575,
"learning_rate": 9.381533400219319e-06,
"loss": 0.6136,
"step": 455
},
{
"epoch": 0.24704618689581095,
"grad_norm": 2.3711250141523292,
"learning_rate": 9.358751904960885e-06,
"loss": 0.6112,
"step": 460
},
{
"epoch": 0.24973147153598282,
"grad_norm": 2.47727212085762,
"learning_rate": 9.335587082977484e-06,
"loss": 0.6065,
"step": 465
},
{
"epoch": 0.25241675617615467,
"grad_norm": 2.431408916174766,
"learning_rate": 9.312040971479663e-06,
"loss": 0.6265,
"step": 470
},
{
"epoch": 0.25510204081632654,
"grad_norm": 2.335148053124711,
"learning_rate": 9.288115641210144e-06,
"loss": 0.5992,
"step": 475
},
{
"epoch": 0.2577873254564984,
"grad_norm": 2.4878167642614994,
"learning_rate": 9.26381319626173e-06,
"loss": 0.6053,
"step": 480
},
{
"epoch": 0.2604726100966702,
"grad_norm": 2.448826496910039,
"learning_rate": 9.239135773892249e-06,
"loss": 0.6059,
"step": 485
},
{
"epoch": 0.2631578947368421,
"grad_norm": 2.340365685512314,
"learning_rate": 9.214085544336597e-06,
"loss": 0.6051,
"step": 490
},
{
"epoch": 0.26584317937701396,
"grad_norm": 2.5813420593776324,
"learning_rate": 9.188664710615886e-06,
"loss": 0.5978,
"step": 495
},
{
"epoch": 0.26852846401718583,
"grad_norm": 2.399275132862282,
"learning_rate": 9.162875508343691e-06,
"loss": 0.5989,
"step": 500
},
{
"epoch": 0.2712137486573577,
"grad_norm": 2.326846382037779,
"learning_rate": 9.136720205529446e-06,
"loss": 0.5882,
"step": 505
},
{
"epoch": 0.2738990332975295,
"grad_norm": 2.388380879732621,
"learning_rate": 9.110201102378991e-06,
"loss": 0.6045,
"step": 510
},
{
"epoch": 0.2765843179377014,
"grad_norm": 2.6554743721903167,
"learning_rate": 9.083320531092268e-06,
"loss": 0.5989,
"step": 515
},
{
"epoch": 0.27926960257787325,
"grad_norm": 2.3647832778978946,
"learning_rate": 9.056080855658233e-06,
"loss": 0.5823,
"step": 520
},
{
"epoch": 0.2819548872180451,
"grad_norm": 2.402783295741927,
"learning_rate": 9.02848447164695e-06,
"loss": 0.5954,
"step": 525
},
{
"epoch": 0.284640171858217,
"grad_norm": 2.4179859370785586,
"learning_rate": 9.00053380599891e-06,
"loss": 0.597,
"step": 530
},
{
"epoch": 0.2873254564983888,
"grad_norm": 2.490422211781943,
"learning_rate": 8.972231316811608e-06,
"loss": 0.5922,
"step": 535
},
{
"epoch": 0.2900107411385607,
"grad_norm": 2.375268811880951,
"learning_rate": 8.943579493123354e-06,
"loss": 0.5945,
"step": 540
},
{
"epoch": 0.29269602577873255,
"grad_norm": 2.3671169905346012,
"learning_rate": 8.914580854694389e-06,
"loss": 0.5745,
"step": 545
},
{
"epoch": 0.2953813104189044,
"grad_norm": 2.33265034161182,
"learning_rate": 8.885237951785275e-06,
"loss": 0.5748,
"step": 550
},
{
"epoch": 0.2980665950590763,
"grad_norm": 2.275342128082187,
"learning_rate": 8.855553364932628e-06,
"loss": 0.5816,
"step": 555
},
{
"epoch": 0.3007518796992481,
"grad_norm": 2.4469604689397992,
"learning_rate": 8.82552970472216e-06,
"loss": 0.5914,
"step": 560
},
{
"epoch": 0.30343716433942,
"grad_norm": 2.5529524024861057,
"learning_rate": 8.795169611559108e-06,
"loss": 0.5777,
"step": 565
},
{
"epoch": 0.30612244897959184,
"grad_norm": 2.3500889773905294,
"learning_rate": 8.764475755436011e-06,
"loss": 0.5809,
"step": 570
},
{
"epoch": 0.3088077336197637,
"grad_norm": 2.5580858779377635,
"learning_rate": 8.733450835697914e-06,
"loss": 0.5782,
"step": 575
},
{
"epoch": 0.31149301825993553,
"grad_norm": 2.495153557765296,
"learning_rate": 8.702097580804962e-06,
"loss": 0.5812,
"step": 580
},
{
"epoch": 0.3141783029001074,
"grad_norm": 2.4356256924449573,
"learning_rate": 8.670418748092465e-06,
"loss": 0.5656,
"step": 585
},
{
"epoch": 0.31686358754027927,
"grad_norm": 2.3744929639725583,
"learning_rate": 8.638417123528393e-06,
"loss": 0.5644,
"step": 590
},
{
"epoch": 0.31954887218045114,
"grad_norm": 2.336786279322332,
"learning_rate": 8.60609552146837e-06,
"loss": 0.5625,
"step": 595
},
{
"epoch": 0.322234156820623,
"grad_norm": 2.304022490580247,
"learning_rate": 8.573456784408162e-06,
"loss": 0.5706,
"step": 600
},
{
"epoch": 0.3249194414607948,
"grad_norm": 2.333873371303564,
"learning_rate": 8.540503782733718e-06,
"loss": 0.5682,
"step": 605
},
{
"epoch": 0.3276047261009667,
"grad_norm": 2.453791422071271,
"learning_rate": 8.507239414468707e-06,
"loss": 0.5694,
"step": 610
},
{
"epoch": 0.33029001074113856,
"grad_norm": 2.6000564411409792,
"learning_rate": 8.473666605019673e-06,
"loss": 0.5441,
"step": 615
},
{
"epoch": 0.33297529538131043,
"grad_norm": 2.492416721336817,
"learning_rate": 8.439788306918759e-06,
"loss": 0.5619,
"step": 620
},
{
"epoch": 0.3356605800214823,
"grad_norm": 2.3074763084807866,
"learning_rate": 8.405607499564044e-06,
"loss": 0.5632,
"step": 625
},
{
"epoch": 0.3383458646616541,
"grad_norm": 2.349999778843298,
"learning_rate": 8.371127188957527e-06,
"loss": 0.5463,
"step": 630
},
{
"epoch": 0.341031149301826,
"grad_norm": 2.2581482340935337,
"learning_rate": 8.336350407440766e-06,
"loss": 0.5549,
"step": 635
},
{
"epoch": 0.34371643394199786,
"grad_norm": 2.4384782140353924,
"learning_rate": 8.3012802134282e-06,
"loss": 0.5412,
"step": 640
},
{
"epoch": 0.3464017185821697,
"grad_norm": 2.5751882880924755,
"learning_rate": 8.26591969113818e-06,
"loss": 0.5567,
"step": 645
},
{
"epoch": 0.34908700322234154,
"grad_norm": 2.518339935894107,
"learning_rate": 8.230271950321733e-06,
"loss": 0.5502,
"step": 650
},
{
"epoch": 0.3517722878625134,
"grad_norm": 2.448402050557329,
"learning_rate": 8.194340125989068e-06,
"loss": 0.5395,
"step": 655
},
{
"epoch": 0.3544575725026853,
"grad_norm": 2.4499578429656825,
"learning_rate": 8.158127378133886e-06,
"loss": 0.5342,
"step": 660
},
{
"epoch": 0.35714285714285715,
"grad_norm": 2.5511091018905896,
"learning_rate": 8.121636891455462e-06,
"loss": 0.5484,
"step": 665
},
{
"epoch": 0.359828141783029,
"grad_norm": 2.533340828939454,
"learning_rate": 8.084871875078574e-06,
"loss": 0.5457,
"step": 670
},
{
"epoch": 0.36251342642320084,
"grad_norm": 2.4448715353894066,
"learning_rate": 8.047835562271289e-06,
"loss": 0.5574,
"step": 675
},
{
"epoch": 0.3651987110633727,
"grad_norm": 2.8289943202459003,
"learning_rate": 8.010531210160594e-06,
"loss": 0.5489,
"step": 680
},
{
"epoch": 0.3678839957035446,
"grad_norm": 2.493357592170436,
"learning_rate": 7.972962099445979e-06,
"loss": 0.5292,
"step": 685
},
{
"epoch": 0.37056928034371645,
"grad_norm": 2.263143839690345,
"learning_rate": 7.935131534110893e-06,
"loss": 0.5397,
"step": 690
},
{
"epoch": 0.3732545649838883,
"grad_norm": 2.3210222371229587,
"learning_rate": 7.897042841132195e-06,
"loss": 0.5345,
"step": 695
},
{
"epoch": 0.37593984962406013,
"grad_norm": 2.390060459345618,
"learning_rate": 7.858699370187558e-06,
"loss": 0.5315,
"step": 700
},
{
"epoch": 0.378625134264232,
"grad_norm": 2.2904914358187782,
"learning_rate": 7.820104493360883e-06,
"loss": 0.5492,
"step": 705
},
{
"epoch": 0.38131041890440387,
"grad_norm": 2.3805535227186385,
"learning_rate": 7.781261604845754e-06,
"loss": 0.5235,
"step": 710
},
{
"epoch": 0.38399570354457574,
"grad_norm": 2.471879540761431,
"learning_rate": 7.742174120646929e-06,
"loss": 0.5419,
"step": 715
},
{
"epoch": 0.3866809881847476,
"grad_norm": 2.5316025731740175,
"learning_rate": 7.70284547827992e-06,
"loss": 0.5258,
"step": 720
},
{
"epoch": 0.3893662728249194,
"grad_norm": 2.356021910277692,
"learning_rate": 7.663279136468696e-06,
"loss": 0.5136,
"step": 725
},
{
"epoch": 0.3920515574650913,
"grad_norm": 2.300853201320016,
"learning_rate": 7.623478574841499e-06,
"loss": 0.5334,
"step": 730
},
{
"epoch": 0.39473684210526316,
"grad_norm": 2.3471881512013177,
"learning_rate": 7.58344729362483e-06,
"loss": 0.5242,
"step": 735
},
{
"epoch": 0.39742212674543503,
"grad_norm": 2.3294738660800998,
"learning_rate": 7.5431888133356334e-06,
"loss": 0.5307,
"step": 740
},
{
"epoch": 0.40010741138560685,
"grad_norm": 2.405771728312475,
"learning_rate": 7.502706674471678e-06,
"loss": 0.5141,
"step": 745
},
{
"epoch": 0.4027926960257787,
"grad_norm": 2.334459667478728,
"learning_rate": 7.462004437200195e-06,
"loss": 0.5153,
"step": 750
},
{
"epoch": 0.4054779806659506,
"grad_norm": 2.201639201589267,
"learning_rate": 7.42108568104479e-06,
"loss": 0.5205,
"step": 755
},
{
"epoch": 0.40816326530612246,
"grad_norm": 2.34678061148915,
"learning_rate": 7.379954004570628e-06,
"loss": 0.5114,
"step": 760
},
{
"epoch": 0.41084854994629433,
"grad_norm": 2.2986824569043214,
"learning_rate": 7.338613025067977e-06,
"loss": 0.5256,
"step": 765
},
{
"epoch": 0.41353383458646614,
"grad_norm": 2.244425672653934,
"learning_rate": 7.2970663782340765e-06,
"loss": 0.5008,
"step": 770
},
{
"epoch": 0.416219119226638,
"grad_norm": 2.395122328169309,
"learning_rate": 7.25531771785341e-06,
"loss": 0.5033,
"step": 775
},
{
"epoch": 0.4189044038668099,
"grad_norm": 2.322926845207769,
"learning_rate": 7.2133707154763646e-06,
"loss": 0.5175,
"step": 780
},
{
"epoch": 0.42158968850698175,
"grad_norm": 2.37505134127978,
"learning_rate": 7.17122906009635e-06,
"loss": 0.5232,
"step": 785
},
{
"epoch": 0.4242749731471536,
"grad_norm": 2.378834002748694,
"learning_rate": 7.128896457825364e-06,
"loss": 0.4991,
"step": 790
},
{
"epoch": 0.42696025778732544,
"grad_norm": 2.282722869895024,
"learning_rate": 7.08637663156807e-06,
"loss": 0.5122,
"step": 795
},
{
"epoch": 0.4296455424274973,
"grad_norm": 2.3359093242506868,
"learning_rate": 7.043673320694386e-06,
"loss": 0.5081,
"step": 800
},
{
"epoch": 0.4323308270676692,
"grad_norm": 2.3875739801173292,
"learning_rate": 7.000790280710625e-06,
"loss": 0.5176,
"step": 805
},
{
"epoch": 0.43501611170784105,
"grad_norm": 2.363423980165021,
"learning_rate": 6.957731282929224e-06,
"loss": 0.4986,
"step": 810
},
{
"epoch": 0.4377013963480129,
"grad_norm": 2.3662866076729547,
"learning_rate": 6.914500114137082e-06,
"loss": 0.5249,
"step": 815
},
{
"epoch": 0.44038668098818473,
"grad_norm": 2.4041868855326327,
"learning_rate": 6.871100576262526e-06,
"loss": 0.5065,
"step": 820
},
{
"epoch": 0.4430719656283566,
"grad_norm": 2.2750431563086004,
"learning_rate": 6.827536486040964e-06,
"loss": 0.4998,
"step": 825
},
{
"epoch": 0.44575725026852847,
"grad_norm": 2.361946244222484,
"learning_rate": 6.783811674679216e-06,
"loss": 0.507,
"step": 830
},
{
"epoch": 0.44844253490870034,
"grad_norm": 2.2727003764122826,
"learning_rate": 6.7399299875185875e-06,
"loss": 0.5036,
"step": 835
},
{
"epoch": 0.45112781954887216,
"grad_norm": 2.3517259170227787,
"learning_rate": 6.695895283696691e-06,
"loss": 0.4789,
"step": 840
},
{
"epoch": 0.453813104189044,
"grad_norm": 2.383189304073773,
"learning_rate": 6.651711435808061e-06,
"loss": 0.4929,
"step": 845
},
{
"epoch": 0.4564983888292159,
"grad_norm": 2.360092586611737,
"learning_rate": 6.607382329563581e-06,
"loss": 0.5068,
"step": 850
},
{
"epoch": 0.45918367346938777,
"grad_norm": 2.334536482498263,
"learning_rate": 6.562911863448752e-06,
"loss": 0.4849,
"step": 855
},
{
"epoch": 0.46186895810955964,
"grad_norm": 2.322335358509275,
"learning_rate": 6.518303948380854e-06,
"loss": 0.4819,
"step": 860
},
{
"epoch": 0.46455424274973145,
"grad_norm": 2.4157418228384318,
"learning_rate": 6.473562507364995e-06,
"loss": 0.4987,
"step": 865
},
{
"epoch": 0.4672395273899033,
"grad_norm": 2.3449366499665234,
"learning_rate": 6.428691475149107e-06,
"loss": 0.4809,
"step": 870
},
{
"epoch": 0.4699248120300752,
"grad_norm": 2.365410848066476,
"learning_rate": 6.383694797877915e-06,
"loss": 0.4783,
"step": 875
},
{
"epoch": 0.47261009667024706,
"grad_norm": 2.356820466415204,
"learning_rate": 6.338576432745891e-06,
"loss": 0.4927,
"step": 880
},
{
"epoch": 0.47529538131041893,
"grad_norm": 2.3178581173038513,
"learning_rate": 6.293340347649234e-06,
"loss": 0.4883,
"step": 885
},
{
"epoch": 0.47798066595059074,
"grad_norm": 2.1615404918804284,
"learning_rate": 6.247990520836935e-06,
"loss": 0.471,
"step": 890
},
{
"epoch": 0.4806659505907626,
"grad_norm": 2.360653971901331,
"learning_rate": 6.202530940560897e-06,
"loss": 0.4822,
"step": 895
},
{
"epoch": 0.4833512352309345,
"grad_norm": 2.372568605186213,
"learning_rate": 6.156965604725202e-06,
"loss": 0.4689,
"step": 900
},
{
"epoch": 0.48603651987110635,
"grad_norm": 2.246153435426788,
"learning_rate": 6.111298520534514e-06,
"loss": 0.4721,
"step": 905
},
{
"epoch": 0.48872180451127817,
"grad_norm": 2.3625810666773073,
"learning_rate": 6.065533704141666e-06,
"loss": 0.4712,
"step": 910
},
{
"epoch": 0.49140708915145004,
"grad_norm": 2.324069609401358,
"learning_rate": 6.019675180294469e-06,
"loss": 0.4773,
"step": 915
},
{
"epoch": 0.4940923737916219,
"grad_norm": 2.3863702418734083,
"learning_rate": 5.973726981981756e-06,
"loss": 0.4767,
"step": 920
},
{
"epoch": 0.4967776584317938,
"grad_norm": 2.244690254098793,
"learning_rate": 5.9276931500787045e-06,
"loss": 0.4715,
"step": 925
},
{
"epoch": 0.49946294307196565,
"grad_norm": 2.380284031970335,
"learning_rate": 5.8815777329914655e-06,
"loss": 0.4582,
"step": 930
},
{
"epoch": 0.5021482277121375,
"grad_norm": 2.312484054724359,
"learning_rate": 5.83538478630113e-06,
"loss": 0.46,
"step": 935
},
{
"epoch": 0.5048335123523093,
"grad_norm": 2.41550721343238,
"learning_rate": 5.789118372407061e-06,
"loss": 0.4574,
"step": 940
},
{
"epoch": 0.5075187969924813,
"grad_norm": 2.313665146473085,
"learning_rate": 5.7427825601696376e-06,
"loss": 0.4717,
"step": 945
},
{
"epoch": 0.5102040816326531,
"grad_norm": 2.343800549458904,
"learning_rate": 5.696381424552411e-06,
"loss": 0.4488,
"step": 950
},
{
"epoch": 0.5128893662728249,
"grad_norm": 2.308680761760831,
"learning_rate": 5.649919046263742e-06,
"loss": 0.4777,
"step": 955
},
{
"epoch": 0.5155746509129968,
"grad_norm": 2.1883219395543776,
"learning_rate": 5.6033995113979336e-06,
"loss": 0.4708,
"step": 960
},
{
"epoch": 0.5182599355531686,
"grad_norm": 2.8333844527470498,
"learning_rate": 5.556826911075867e-06,
"loss": 0.4644,
"step": 965
},
{
"epoch": 0.5209452201933404,
"grad_norm": 2.2176847173023346,
"learning_rate": 5.510205341085224e-06,
"loss": 0.4467,
"step": 970
},
{
"epoch": 0.5236305048335124,
"grad_norm": 2.288019101770923,
"learning_rate": 5.463538901520278e-06,
"loss": 0.4664,
"step": 975
},
{
"epoch": 0.5263157894736842,
"grad_norm": 2.2412931794728617,
"learning_rate": 5.416831696421325e-06,
"loss": 0.4557,
"step": 980
},
{
"epoch": 0.5290010741138561,
"grad_norm": 2.451382138891403,
"learning_rate": 5.370087833413747e-06,
"loss": 0.4698,
"step": 985
},
{
"epoch": 0.5316863587540279,
"grad_norm": 2.252017741354611,
"learning_rate": 5.323311423346775e-06,
"loss": 0.4494,
"step": 990
},
{
"epoch": 0.5343716433941997,
"grad_norm": 2.293986595976978,
"learning_rate": 5.2765065799319646e-06,
"loss": 0.4528,
"step": 995
},
{
"epoch": 0.5370569280343717,
"grad_norm": 2.2761604256781327,
"learning_rate": 5.229677419381417e-06,
"loss": 0.4614,
"step": 1000
},
{
"epoch": 0.5397422126745435,
"grad_norm": 2.4240090799649034,
"learning_rate": 5.182828060045783e-06,
"loss": 0.4468,
"step": 1005
},
{
"epoch": 0.5424274973147154,
"grad_norm": 2.442934156317595,
"learning_rate": 5.1359626220520804e-06,
"loss": 0.4389,
"step": 1010
},
{
"epoch": 0.5451127819548872,
"grad_norm": 2.2603275521364528,
"learning_rate": 5.08908522694135e-06,
"loss": 0.4567,
"step": 1015
},
{
"epoch": 0.547798066595059,
"grad_norm": 2.218667766895513,
"learning_rate": 5.042199997306185e-06,
"loss": 0.4388,
"step": 1020
},
{
"epoch": 0.550483351235231,
"grad_norm": 2.259809429069565,
"learning_rate": 4.995311056428192e-06,
"loss": 0.4364,
"step": 1025
},
{
"epoch": 0.5531686358754028,
"grad_norm": 2.2730891483819757,
"learning_rate": 4.948422527915348e-06,
"loss": 0.4333,
"step": 1030
},
{
"epoch": 0.5558539205155747,
"grad_norm": 2.39309066580743,
"learning_rate": 4.901538535339369e-06,
"loss": 0.4342,
"step": 1035
},
{
"epoch": 0.5585392051557465,
"grad_norm": 2.3112523965600436,
"learning_rate": 4.854663201873066e-06,
"loss": 0.4266,
"step": 1040
},
{
"epoch": 0.5612244897959183,
"grad_norm": 2.314393277518899,
"learning_rate": 4.807800649927723e-06,
"loss": 0.4268,
"step": 1045
},
{
"epoch": 0.5639097744360902,
"grad_norm": 2.3651606024626117,
"learning_rate": 4.760955000790572e-06,
"loss": 0.4337,
"step": 1050
},
{
"epoch": 0.5665950590762621,
"grad_norm": 2.415473492611108,
"learning_rate": 4.714130374262339e-06,
"loss": 0.4449,
"step": 1055
},
{
"epoch": 0.569280343716434,
"grad_norm": 2.3361082246507934,
"learning_rate": 4.667330888294934e-06,
"loss": 0.4107,
"step": 1060
},
{
"epoch": 0.5719656283566058,
"grad_norm": 2.360677430690215,
"learning_rate": 4.620560658629303e-06,
"loss": 0.4254,
"step": 1065
},
{
"epoch": 0.5746509129967776,
"grad_norm": 2.1700448641934544,
"learning_rate": 4.573823798433469e-06,
"loss": 0.4415,
"step": 1070
},
{
"epoch": 0.5773361976369495,
"grad_norm": 2.312801842492201,
"learning_rate": 4.527124417940812e-06,
"loss": 0.4397,
"step": 1075
},
{
"epoch": 0.5800214822771214,
"grad_norm": 2.2937353441454285,
"learning_rate": 4.48046662408858e-06,
"loss": 0.4476,
"step": 1080
},
{
"epoch": 0.5827067669172933,
"grad_norm": 2.561098663722942,
"learning_rate": 4.43385452015673e-06,
"loss": 0.4323,
"step": 1085
},
{
"epoch": 0.5853920515574651,
"grad_norm": 2.2162314798223206,
"learning_rate": 4.387292205407055e-06,
"loss": 0.4351,
"step": 1090
},
{
"epoch": 0.5880773361976369,
"grad_norm": 2.356008942163047,
"learning_rate": 4.3407837747226765e-06,
"loss": 0.4282,
"step": 1095
},
{
"epoch": 0.5907626208378088,
"grad_norm": 2.339594344704525,
"learning_rate": 4.29433331824793e-06,
"loss": 0.4174,
"step": 1100
},
{
"epoch": 0.5934479054779807,
"grad_norm": 2.2403052317925156,
"learning_rate": 4.247944921028663e-06,
"loss": 0.4134,
"step": 1105
},
{
"epoch": 0.5961331901181526,
"grad_norm": 2.2381645082625776,
"learning_rate": 4.201622662652972e-06,
"loss": 0.4189,
"step": 1110
},
{
"epoch": 0.5988184747583244,
"grad_norm": 2.2380868768618627,
"learning_rate": 4.155370616892422e-06,
"loss": 0.4129,
"step": 1115
},
{
"epoch": 0.6015037593984962,
"grad_norm": 2.339687690650304,
"learning_rate": 4.1091928513438005e-06,
"loss": 0.4158,
"step": 1120
},
{
"epoch": 0.6041890440386681,
"grad_norm": 2.3979680821995784,
"learning_rate": 4.063093427071376e-06,
"loss": 0.4224,
"step": 1125
},
{
"epoch": 0.60687432867884,
"grad_norm": 2.2120117677998126,
"learning_rate": 4.0170763982497716e-06,
"loss": 0.4131,
"step": 1130
},
{
"epoch": 0.6095596133190118,
"grad_norm": 2.2547586947580336,
"learning_rate": 3.971145811807397e-06,
"loss": 0.4205,
"step": 1135
},
{
"epoch": 0.6122448979591837,
"grad_norm": 2.2592067136128406,
"learning_rate": 3.925305707070572e-06,
"loss": 0.4258,
"step": 1140
},
{
"epoch": 0.6149301825993555,
"grad_norm": 2.3340312150224376,
"learning_rate": 3.879560115408279e-06,
"loss": 0.4241,
"step": 1145
},
{
"epoch": 0.6176154672395274,
"grad_norm": 2.1645761230380614,
"learning_rate": 3.833913059877622e-06,
"loss": 0.4146,
"step": 1150
},
{
"epoch": 0.6203007518796992,
"grad_norm": 2.327696071182452,
"learning_rate": 3.788368554870034e-06,
"loss": 0.4176,
"step": 1155
},
{
"epoch": 0.6229860365198711,
"grad_norm": 2.283585936176722,
"learning_rate": 3.7429306057582306e-06,
"loss": 0.4256,
"step": 1160
},
{
"epoch": 0.625671321160043,
"grad_norm": 2.257166305089174,
"learning_rate": 3.6976032085439563e-06,
"loss": 0.4038,
"step": 1165
},
{
"epoch": 0.6283566058002148,
"grad_norm": 2.217414085409638,
"learning_rate": 3.6523903495065634e-06,
"loss": 0.4106,
"step": 1170
},
{
"epoch": 0.6310418904403867,
"grad_norm": 2.2297466820002225,
"learning_rate": 3.6072960048524443e-06,
"loss": 0.4167,
"step": 1175
},
{
"epoch": 0.6337271750805585,
"grad_norm": 2.196582517840786,
"learning_rate": 3.562324140365343e-06,
"loss": 0.4042,
"step": 1180
},
{
"epoch": 0.6364124597207304,
"grad_norm": 2.20250952239818,
"learning_rate": 3.5174787110575904e-06,
"loss": 0.3935,
"step": 1185
},
{
"epoch": 0.6390977443609023,
"grad_norm": 2.526218420849079,
"learning_rate": 3.4727636608222813e-06,
"loss": 0.4063,
"step": 1190
},
{
"epoch": 0.6417830290010741,
"grad_norm": 2.1335154360820088,
"learning_rate": 3.428182922086437e-06,
"loss": 0.4049,
"step": 1195
},
{
"epoch": 0.644468313641246,
"grad_norm": 2.252244271262109,
"learning_rate": 3.3837404154651677e-06,
"loss": 0.4009,
"step": 1200
},
{
"epoch": 0.6471535982814178,
"grad_norm": 2.4694360819768817,
"learning_rate": 3.3394400494168745e-06,
"loss": 0.4054,
"step": 1205
},
{
"epoch": 0.6498388829215896,
"grad_norm": 2.2150632695332515,
"learning_rate": 3.2952857198995304e-06,
"loss": 0.4043,
"step": 1210
},
{
"epoch": 0.6525241675617616,
"grad_norm": 2.4201560036968406,
"learning_rate": 3.2512813100280494e-06,
"loss": 0.401,
"step": 1215
},
{
"epoch": 0.6552094522019334,
"grad_norm": 2.2211755428097226,
"learning_rate": 3.2074306897327913e-06,
"loss": 0.3887,
"step": 1220
},
{
"epoch": 0.6578947368421053,
"grad_norm": 2.2326049552084126,
"learning_rate": 3.163737715419216e-06,
"loss": 0.3966,
"step": 1225
},
{
"epoch": 0.6605800214822771,
"grad_norm": 2.1800000221416798,
"learning_rate": 3.1202062296287507e-06,
"loss": 0.3936,
"step": 1230
},
{
"epoch": 0.6632653061224489,
"grad_norm": 2.2543256840697836,
"learning_rate": 3.076840060700848e-06,
"loss": 0.3999,
"step": 1235
},
{
"epoch": 0.6659505907626209,
"grad_norm": 2.1832410035100014,
"learning_rate": 3.0336430224363067e-06,
"loss": 0.4066,
"step": 1240
},
{
"epoch": 0.6686358754027927,
"grad_norm": 2.1345582981116196,
"learning_rate": 2.990618913761876e-06,
"loss": 0.3978,
"step": 1245
},
{
"epoch": 0.6713211600429646,
"grad_norm": 2.380691403939363,
"learning_rate": 2.9477715183961634e-06,
"loss": 0.3864,
"step": 1250
},
{
"epoch": 0.6740064446831364,
"grad_norm": 2.2738078409954685,
"learning_rate": 2.905104604516872e-06,
"loss": 0.3843,
"step": 1255
},
{
"epoch": 0.6766917293233082,
"grad_norm": 2.1602808837976117,
"learning_rate": 2.8626219244294074e-06,
"loss": 0.3999,
"step": 1260
},
{
"epoch": 0.6793770139634802,
"grad_norm": 2.2085763099047955,
"learning_rate": 2.820327214236904e-06,
"loss": 0.3974,
"step": 1265
},
{
"epoch": 0.682062298603652,
"grad_norm": 2.235386766709275,
"learning_rate": 2.7782241935116337e-06,
"loss": 0.385,
"step": 1270
},
{
"epoch": 0.6847475832438239,
"grad_norm": 2.188012993018142,
"learning_rate": 2.7363165649679045e-06,
"loss": 0.3827,
"step": 1275
},
{
"epoch": 0.6874328678839957,
"grad_norm": 2.226716099786791,
"learning_rate": 2.6946080141364295e-06,
"loss": 0.3943,
"step": 1280
},
{
"epoch": 0.6901181525241675,
"grad_norm": 2.2426965329620954,
"learning_rate": 2.6531022090401946e-06,
"loss": 0.3994,
"step": 1285
},
{
"epoch": 0.6928034371643395,
"grad_norm": 2.173915921830579,
"learning_rate": 2.611802799871893e-06,
"loss": 0.384,
"step": 1290
},
{
"epoch": 0.6954887218045113,
"grad_norm": 2.1709824856734605,
"learning_rate": 2.570713418672893e-06,
"loss": 0.373,
"step": 1295
},
{
"epoch": 0.6981740064446831,
"grad_norm": 2.3391765011254937,
"learning_rate": 2.529837679013841e-06,
"loss": 0.384,
"step": 1300
},
{
"epoch": 0.700859291084855,
"grad_norm": 2.2099937926483704,
"learning_rate": 2.4891791756768587e-06,
"loss": 0.3704,
"step": 1305
},
{
"epoch": 0.7035445757250268,
"grad_norm": 2.176216958310356,
"learning_rate": 2.4487414843394015e-06,
"loss": 0.3928,
"step": 1310
},
{
"epoch": 0.7062298603651987,
"grad_norm": 2.1290888658786415,
"learning_rate": 2.4085281612598027e-06,
"loss": 0.3748,
"step": 1315
},
{
"epoch": 0.7089151450053706,
"grad_norm": 2.1829182895504227,
"learning_rate": 2.368542742964519e-06,
"loss": 0.3869,
"step": 1320
},
{
"epoch": 0.7116004296455424,
"grad_norm": 2.2587981614095085,
"learning_rate": 2.3287887459371193e-06,
"loss": 0.3779,
"step": 1325
},
{
"epoch": 0.7142857142857143,
"grad_norm": 2.372100847324542,
"learning_rate": 2.2892696663090223e-06,
"loss": 0.3761,
"step": 1330
},
{
"epoch": 0.7169709989258861,
"grad_norm": 2.278334338481838,
"learning_rate": 2.2499889795520342e-06,
"loss": 0.3686,
"step": 1335
},
{
"epoch": 0.719656283566058,
"grad_norm": 2.2218577358371046,
"learning_rate": 2.2109501401727097e-06,
"loss": 0.373,
"step": 1340
},
{
"epoch": 0.7223415682062299,
"grad_norm": 2.1254755331259725,
"learning_rate": 2.1721565814085355e-06,
"loss": 0.365,
"step": 1345
},
{
"epoch": 0.7250268528464017,
"grad_norm": 2.1702115107700917,
"learning_rate": 2.133611714926005e-06,
"loss": 0.3702,
"step": 1350
},
{
"epoch": 0.7277121374865736,
"grad_norm": 2.1892322865283806,
"learning_rate": 2.0953189305205847e-06,
"loss": 0.3775,
"step": 1355
},
{
"epoch": 0.7303974221267454,
"grad_norm": 2.151212049347134,
"learning_rate": 2.057281595818592e-06,
"loss": 0.3761,
"step": 1360
},
{
"epoch": 0.7330827067669173,
"grad_norm": 2.393785451565841,
"learning_rate": 2.0195030559810387e-06,
"loss": 0.3787,
"step": 1365
},
{
"epoch": 0.7357679914070892,
"grad_norm": 2.1987458039368954,
"learning_rate": 1.981986633409447e-06,
"loss": 0.3705,
"step": 1370
},
{
"epoch": 0.738453276047261,
"grad_norm": 2.2091176561248083,
"learning_rate": 1.944735627453654e-06,
"loss": 0.3674,
"step": 1375
},
{
"epoch": 0.7411385606874329,
"grad_norm": 2.1125042254421733,
"learning_rate": 1.907753314121662e-06,
"loss": 0.3801,
"step": 1380
},
{
"epoch": 0.7438238453276047,
"grad_norm": 2.310411592482143,
"learning_rate": 1.8710429457915269e-06,
"loss": 0.39,
"step": 1385
},
{
"epoch": 0.7465091299677766,
"grad_norm": 2.2962629079030243,
"learning_rate": 1.834607750925333e-06,
"loss": 0.3676,
"step": 1390
},
{
"epoch": 0.7491944146079484,
"grad_norm": 2.35761038713381,
"learning_rate": 1.7984509337852724e-06,
"loss": 0.3822,
"step": 1395
},
{
"epoch": 0.7518796992481203,
"grad_norm": 2.0186886903779517,
"learning_rate": 1.7625756741518407e-06,
"loss": 0.3765,
"step": 1400
},
{
"epoch": 0.7545649838882922,
"grad_norm": 2.1023056656067567,
"learning_rate": 1.7269851270441978e-06,
"loss": 0.3583,
"step": 1405
},
{
"epoch": 0.757250268528464,
"grad_norm": 2.300679602655581,
"learning_rate": 1.6916824224427098e-06,
"loss": 0.3866,
"step": 1410
},
{
"epoch": 0.7599355531686359,
"grad_norm": 2.0668614724801606,
"learning_rate": 1.6566706650136704e-06,
"loss": 0.3553,
"step": 1415
},
{
"epoch": 0.7626208378088077,
"grad_norm": 2.294458578577542,
"learning_rate": 1.6219529338362756e-06,
"loss": 0.3642,
"step": 1420
},
{
"epoch": 0.7653061224489796,
"grad_norm": 2.0628194904498836,
"learning_rate": 1.587532282131835e-06,
"loss": 0.3596,
"step": 1425
},
{
"epoch": 0.7679914070891515,
"grad_norm": 2.0587824624449826,
"learning_rate": 1.5534117369952523e-06,
"loss": 0.3627,
"step": 1430
},
{
"epoch": 0.7706766917293233,
"grad_norm": 2.1599902106655198,
"learning_rate": 1.5195942991288214e-06,
"loss": 0.3627,
"step": 1435
},
{
"epoch": 0.7733619763694952,
"grad_norm": 2.2640334867648155,
"learning_rate": 1.4860829425783151e-06,
"loss": 0.3625,
"step": 1440
},
{
"epoch": 0.776047261009667,
"grad_norm": 2.2124168087140874,
"learning_rate": 1.4528806144714546e-06,
"loss": 0.3595,
"step": 1445
},
{
"epoch": 0.7787325456498388,
"grad_norm": 2.337523902238021,
"learning_rate": 1.4199902347587186e-06,
"loss": 0.3707,
"step": 1450
},
{
"epoch": 0.7814178302900108,
"grad_norm": 2.096978060408682,
"learning_rate": 1.3874146959565387e-06,
"loss": 0.3713,
"step": 1455
},
{
"epoch": 0.7841031149301826,
"grad_norm": 2.0894953589815253,
"learning_rate": 1.3551568628929434e-06,
"loss": 0.3584,
"step": 1460
},
{
"epoch": 0.7867883995703545,
"grad_norm": 2.1767739733098774,
"learning_rate": 1.3232195724555919e-06,
"loss": 0.3508,
"step": 1465
},
{
"epoch": 0.7894736842105263,
"grad_norm": 2.0541945214281814,
"learning_rate": 1.291605633342301e-06,
"loss": 0.3478,
"step": 1470
},
{
"epoch": 0.7921589688506981,
"grad_norm": 2.024608217596787,
"learning_rate": 1.2603178258140264e-06,
"loss": 0.3523,
"step": 1475
},
{
"epoch": 0.7948442534908701,
"grad_norm": 2.143945397214433,
"learning_rate": 1.22935890145036e-06,
"loss": 0.3476,
"step": 1480
},
{
"epoch": 0.7975295381310419,
"grad_norm": 2.008431036790706,
"learning_rate": 1.198731582907547e-06,
"loss": 0.3667,
"step": 1485
},
{
"epoch": 0.8002148227712137,
"grad_norm": 2.036066654414611,
"learning_rate": 1.1684385636790368e-06,
"loss": 0.362,
"step": 1490
},
{
"epoch": 0.8029001074113856,
"grad_norm": 2.066841030662012,
"learning_rate": 1.1384825078586114e-06,
"loss": 0.3619,
"step": 1495
},
{
"epoch": 0.8055853920515574,
"grad_norm": 2.219785683686726,
"learning_rate": 1.108866049906096e-06,
"loss": 0.3476,
"step": 1500
},
{
"epoch": 0.8082706766917294,
"grad_norm": 2.032441941191992,
"learning_rate": 1.079591794415667e-06,
"loss": 0.3613,
"step": 1505
},
{
"epoch": 0.8109559613319012,
"grad_norm": 2.2803586671679037,
"learning_rate": 1.0506623158867952e-06,
"loss": 0.3468,
"step": 1510
},
{
"epoch": 0.813641245972073,
"grad_norm": 1.9788164235546355,
"learning_rate": 1.0220801584978408e-06,
"loss": 0.3544,
"step": 1515
},
{
"epoch": 0.8163265306122449,
"grad_norm": 2.2037987602808475,
"learning_rate": 9.93847835882296e-07,
"loss": 0.3538,
"step": 1520
},
{
"epoch": 0.8190118152524167,
"grad_norm": 2.0816795942958817,
"learning_rate": 9.659678309077374e-07,
"loss": 0.3481,
"step": 1525
},
{
"epoch": 0.8216970998925887,
"grad_norm": 1.9823282088006486,
"learning_rate": 9.384425954574617e-07,
"loss": 0.3577,
"step": 1530
},
{
"epoch": 0.8243823845327605,
"grad_norm": 2.030845811179057,
"learning_rate": 9.112745502148629e-07,
"loss": 0.3559,
"step": 1535
},
{
"epoch": 0.8270676691729323,
"grad_norm": 2.1777276043921936,
"learning_rate": 8.844660844505498e-07,
"loss": 0.3525,
"step": 1540
},
{
"epoch": 0.8297529538131042,
"grad_norm": 2.0300477472798812,
"learning_rate": 8.580195558122167e-07,
"loss": 0.3508,
"step": 1545
},
{
"epoch": 0.832438238453276,
"grad_norm": 2.0221512590268156,
"learning_rate": 8.319372901173045e-07,
"loss": 0.3469,
"step": 1550
},
{
"epoch": 0.835123523093448,
"grad_norm": 2.1138683649194507,
"learning_rate": 8.062215811484652e-07,
"loss": 0.3539,
"step": 1555
},
{
"epoch": 0.8378088077336198,
"grad_norm": 2.040376339189134,
"learning_rate": 7.808746904518261e-07,
"loss": 0.351,
"step": 1560
},
{
"epoch": 0.8404940923737916,
"grad_norm": 2.2124273072385106,
"learning_rate": 7.558988471381063e-07,
"loss": 0.3425,
"step": 1565
},
{
"epoch": 0.8431793770139635,
"grad_norm": 2.1703815796790598,
"learning_rate": 7.312962476865831e-07,
"loss": 0.3488,
"step": 1570
},
{
"epoch": 0.8458646616541353,
"grad_norm": 2.124785306636511,
"learning_rate": 7.070690557519139e-07,
"loss": 0.3509,
"step": 1575
},
{
"epoch": 0.8485499462943072,
"grad_norm": 2.2867701473619055,
"learning_rate": 6.832194019738686e-07,
"loss": 0.3553,
"step": 1580
},
{
"epoch": 0.8512352309344791,
"grad_norm": 1.9550073938057098,
"learning_rate": 6.597493837899377e-07,
"loss": 0.3568,
"step": 1585
},
{
"epoch": 0.8539205155746509,
"grad_norm": 1.9281450180746198,
"learning_rate": 6.366610652508875e-07,
"loss": 0.3413,
"step": 1590
},
{
"epoch": 0.8566058002148228,
"grad_norm": 2.1382579942417843,
"learning_rate": 6.13956476839237e-07,
"loss": 0.351,
"step": 1595
},
{
"epoch": 0.8592910848549946,
"grad_norm": 2.119115312173987,
"learning_rate": 5.916376152906761e-07,
"loss": 0.3412,
"step": 1600
},
{
"epoch": 0.8619763694951665,
"grad_norm": 2.012427806717363,
"learning_rate": 5.697064434184835e-07,
"loss": 0.3379,
"step": 1605
},
{
"epoch": 0.8646616541353384,
"grad_norm": 2.203625853262407,
"learning_rate": 5.481648899408943e-07,
"loss": 0.3432,
"step": 1610
},
{
"epoch": 0.8673469387755102,
"grad_norm": 2.116502964909563,
"learning_rate": 5.270148493114896e-07,
"loss": 0.3452,
"step": 1615
},
{
"epoch": 0.8700322234156821,
"grad_norm": 2.1766860996156048,
"learning_rate": 5.062581815525819e-07,
"loss": 0.3367,
"step": 1620
},
{
"epoch": 0.8727175080558539,
"grad_norm": 2.1775147697129373,
"learning_rate": 4.858967120916436e-07,
"loss": 0.3436,
"step": 1625
},
{
"epoch": 0.8754027926960258,
"grad_norm": 2.2442167220688463,
"learning_rate": 4.659322316007714e-07,
"loss": 0.3433,
"step": 1630
},
{
"epoch": 0.8780880773361976,
"grad_norm": 2.075788617747793,
"learning_rate": 4.463664958392017e-07,
"loss": 0.3405,
"step": 1635
},
{
"epoch": 0.8807733619763695,
"grad_norm": 1.8687131233491732,
"learning_rate": 4.2720122549890607e-07,
"loss": 0.3384,
"step": 1640
},
{
"epoch": 0.8834586466165414,
"grad_norm": 2.0370021636119935,
"learning_rate": 4.084381060532672e-07,
"loss": 0.3474,
"step": 1645
},
{
"epoch": 0.8861439312567132,
"grad_norm": 2.0405991135848827,
"learning_rate": 3.9007878760884856e-07,
"loss": 0.3316,
"step": 1650
},
{
"epoch": 0.888829215896885,
"grad_norm": 2.127376968302403,
"learning_rate": 3.721248847602771e-07,
"loss": 0.3453,
"step": 1655
},
{
"epoch": 0.8915145005370569,
"grad_norm": 2.0017662232647906,
"learning_rate": 3.5457797644825376e-07,
"loss": 0.3427,
"step": 1660
},
{
"epoch": 0.8941997851772288,
"grad_norm": 2.1671592537785314,
"learning_rate": 3.3743960582068745e-07,
"loss": 0.3439,
"step": 1665
},
{
"epoch": 0.8968850698174007,
"grad_norm": 2.2292025445441466,
"learning_rate": 3.207112800969925e-07,
"loss": 0.3474,
"step": 1670
},
{
"epoch": 0.8995703544575725,
"grad_norm": 2.2814733309910924,
"learning_rate": 3.0439447043553005e-07,
"loss": 0.3369,
"step": 1675
},
{
"epoch": 0.9022556390977443,
"grad_norm": 2.0190392021288277,
"learning_rate": 2.884906118042313e-07,
"loss": 0.344,
"step": 1680
},
{
"epoch": 0.9049409237379162,
"grad_norm": 2.0932363804553438,
"learning_rate": 2.730011028544044e-07,
"loss": 0.3386,
"step": 1685
},
{
"epoch": 0.907626208378088,
"grad_norm": 2.0530951304640914,
"learning_rate": 2.579273057977244e-07,
"loss": 0.3424,
"step": 1690
},
{
"epoch": 0.91031149301826,
"grad_norm": 2.2057752335811975,
"learning_rate": 2.4327054628643764e-07,
"loss": 0.337,
"step": 1695
},
{
"epoch": 0.9129967776584318,
"grad_norm": 1.9338355970542782,
"learning_rate": 2.29032113296781e-07,
"loss": 0.3369,
"step": 1700
},
{
"epoch": 0.9156820622986036,
"grad_norm": 2.0345360518554654,
"learning_rate": 2.1521325901561918e-07,
"loss": 0.3427,
"step": 1705
},
{
"epoch": 0.9183673469387755,
"grad_norm": 2.004334408060014,
"learning_rate": 2.018151987303263e-07,
"loss": 0.3447,
"step": 1710
},
{
"epoch": 0.9210526315789473,
"grad_norm": 2.0641637729486177,
"learning_rate": 1.8883911072190619e-07,
"loss": 0.3426,
"step": 1715
},
{
"epoch": 0.9237379162191193,
"grad_norm": 1.9761026710032998,
"learning_rate": 1.7628613616137048e-07,
"loss": 0.3342,
"step": 1720
},
{
"epoch": 0.9264232008592911,
"grad_norm": 2.1350718022308004,
"learning_rate": 1.6415737900937811e-07,
"loss": 0.3377,
"step": 1725
},
{
"epoch": 0.9291084854994629,
"grad_norm": 2.055196159373768,
"learning_rate": 1.5245390591914877e-07,
"loss": 0.3378,
"step": 1730
},
{
"epoch": 0.9317937701396348,
"grad_norm": 1.9690007377565177,
"learning_rate": 1.4117674614265885e-07,
"loss": 0.3355,
"step": 1735
},
{
"epoch": 0.9344790547798066,
"grad_norm": 1.9739725581772325,
"learning_rate": 1.3032689144012457e-07,
"loss": 0.3328,
"step": 1740
},
{
"epoch": 0.9371643394199786,
"grad_norm": 2.021766909349921,
"learning_rate": 1.1990529599277656e-07,
"loss": 0.3317,
"step": 1745
},
{
"epoch": 0.9398496240601504,
"grad_norm": 2.031112789362354,
"learning_rate": 1.0991287631895498e-07,
"loss": 0.3395,
"step": 1750
},
{
"epoch": 0.9425349087003222,
"grad_norm": 1.9213664207732846,
"learning_rate": 1.0035051119349881e-07,
"loss": 0.3344,
"step": 1755
},
{
"epoch": 0.9452201933404941,
"grad_norm": 2.0021558728542392,
"learning_rate": 9.121904157046779e-08,
"loss": 0.3398,
"step": 1760
},
{
"epoch": 0.9479054779806659,
"grad_norm": 2.0885143729585716,
"learning_rate": 8.251927050918262e-08,
"loss": 0.3322,
"step": 1765
},
{
"epoch": 0.9505907626208379,
"grad_norm": 2.113089044300656,
"learning_rate": 7.425196310360094e-08,
"loss": 0.3377,
"step": 1770
},
{
"epoch": 0.9532760472610097,
"grad_norm": 2.074323605100398,
"learning_rate": 6.64178464150339e-08,
"loss": 0.3355,
"step": 1775
},
{
"epoch": 0.9559613319011815,
"grad_norm": 1.8952573799315888,
"learning_rate": 5.9017609408203445e-08,
"loss": 0.3424,
"step": 1780
},
{
"epoch": 0.9586466165413534,
"grad_norm": 2.112107225346643,
"learning_rate": 5.2051902890651316e-08,
"loss": 0.3382,
"step": 1785
},
{
"epoch": 0.9613319011815252,
"grad_norm": 1.995864796648848,
"learning_rate": 4.5521339455507075e-08,
"loss": 0.345,
"step": 1790
},
{
"epoch": 0.9640171858216972,
"grad_norm": 2.0423181341142085,
"learning_rate": 3.9426493427611177e-08,
"loss": 0.3242,
"step": 1795
},
{
"epoch": 0.966702470461869,
"grad_norm": 2.049708585546813,
"learning_rate": 3.3767900813007623e-08,
"loss": 0.3349,
"step": 1800
},
{
"epoch": 0.9693877551020408,
"grad_norm": 2.096305223227572,
"learning_rate": 2.8546059251806092e-08,
"loss": 0.3499,
"step": 1805
},
{
"epoch": 0.9720730397422127,
"grad_norm": 2.0761286658261775,
"learning_rate": 2.3761427974416383e-08,
"loss": 0.3517,
"step": 1810
},
{
"epoch": 0.9747583243823845,
"grad_norm": 2.050778707489503,
"learning_rate": 1.9414427761162423e-08,
"loss": 0.3454,
"step": 1815
},
{
"epoch": 0.9774436090225563,
"grad_norm": 1.9902866670914756,
"learning_rate": 1.5505440905276835e-08,
"loss": 0.3375,
"step": 1820
},
{
"epoch": 0.9801288936627283,
"grad_norm": 2.1252055010410076,
"learning_rate": 1.203481117928007e-08,
"loss": 0.345,
"step": 1825
},
{
"epoch": 0.9828141783029001,
"grad_norm": 1.9597127591634178,
"learning_rate": 9.002843804748473e-09,
"loss": 0.3366,
"step": 1830
},
{
"epoch": 0.985499462943072,
"grad_norm": 1.9937617229080937,
"learning_rate": 6.409805425470761e-09,
"loss": 0.3383,
"step": 1835
},
{
"epoch": 0.9881847475832438,
"grad_norm": 2.0752840809597792,
"learning_rate": 4.255924083999552e-09,
"loss": 0.3405,
"step": 1840
},
{
"epoch": 0.9908700322234156,
"grad_norm": 2.0871755576857893,
"learning_rate": 2.5413892015951903e-09,
"loss": 0.3429,
"step": 1845
},
{
"epoch": 0.9935553168635876,
"grad_norm": 2.154732166762825,
"learning_rate": 1.266351561568513e-09,
"loss": 0.3208,
"step": 1850
},
{
"epoch": 0.9962406015037594,
"grad_norm": 2.106067074324966,
"learning_rate": 4.3092329601923664e-10,
"loss": 0.3483,
"step": 1855
},
{
"epoch": 0.9989258861439313,
"grad_norm": 2.0654612280200046,
"learning_rate": 3.517787597440148e-11,
"loss": 0.3318,
"step": 1860
},
{
"epoch": 1.0,
"eval_runtime": 3.3748,
"eval_samples_per_second": 2.963,
"eval_steps_per_second": 0.889,
"step": 1862
},
{
"epoch": 1.0,
"step": 1862,
"total_flos": 194932459438080.0,
"train_loss": 0.0,
"train_runtime": 0.0092,
"train_samples_per_second": 3252649.769,
"train_steps_per_second": 203358.87
}
],
"logging_steps": 5,
"max_steps": 1862,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 194932459438080.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}