{ "config": { "model": "LiquidAI/LFM2.5-Encoder-350M", "init_from": "ProCreations/minima", "dataset": "HuggingFaceFW/fineweb-edu", "dataset_config": "sample-10BT", "split": "train", "text_column": "text", "output_dir": "/home/user/checkpoints/minima/encoder", "output_repo": null, "sequence_length": 1024, "batch_size": 8, "gradient_accumulation": 4, "steps": 16000, "learning_rate": 5e-05, "warmup_steps": 400, "group_size": 128, "recovery_rank": 0, "teacher_topk": 32, "hidden_loss_weight": 2.0, "layer_loss_weight": 0.5, "distill_loss_weight": 1.0, "mlm_loss_weight": 1.0, "temperature": 2.0, "mask_probability": 0.3, "seed": 42, "log_every": 10, "checkpoint_every": 1000, "resume_from": null, "train_ternary_weights": true, "max_weight_bytes": 104857600 }, "duration_seconds": 11887.770757198334, "trainable_parameters": 354483968, "weight_bytes": 94298568, "recovery_rank": 0, "profile": "strict", "history": [ { "step": 1, "lr": 1.25e-07, "elapsed_s": 8.438207387924194, "loss": 20.382107257843018, "hidden": 0.8346377909183502, "layer": 0.3416784182190895, "mlm": 7.332927703857422, "distill": 11.209064722061157, "teacher_acc": 0.741391971707344 }, { "step": 11, "lr": 1.3750000000000002e-06, "elapsed_s": 15.91100549697876, "loss": 20.231243133544922, "hidden": 0.8391025960445404, "layer": 0.3421124964952469, "mlm": 7.287261247634888, "distill": 11.094720363616943, "teacher_acc": 0.7277925461530685 }, { "step": 21, "lr": 2.6250000000000003e-06, "elapsed_s": 23.412943840026855, "loss": 19.162318229675293, "hidden": 0.8315205425024033, "layer": 0.33662645518779755, "mlm": 6.99660050868988, "distill": 10.334363460540771, "teacher_acc": 0.7113983482122421 }, { "step": 31, "lr": 3.875e-06, "elapsed_s": 30.961130142211914, "loss": 17.63284397125244, "hidden": 0.8067305237054825, "layer": 0.3340466096997261, "mlm": 6.331857204437256, "distill": 9.52050256729126, "teacher_acc": 0.7246920615434647 }, { "step": 41, "lr": 5.125e-06, "elapsed_s": 38.39629864692688, "loss": 16.680916786193848, "hidden": 0.8166581839323044, "layer": 0.33229923993349075, "mlm": 5.905057072639465, "distill": 8.976394414901733, "teacher_acc": 0.7295158505439758 }, { "step": 51, "lr": 6.375000000000001e-06, "elapsed_s": 45.90352153778076, "loss": 15.108635425567627, "hidden": 0.8116884082555771, "layer": 0.3292075991630554, "mlm": 5.3271849155426025, "distill": 7.993469953536987, "teacher_acc": 0.720592126250267 }, { "step": 61, "lr": 7.625000000000001e-06, "elapsed_s": 53.383700370788574, "loss": 14.412956714630127, "hidden": 0.7955577671527863, "layer": 0.32568876445293427, "mlm": 4.998058438301086, "distill": 7.660938382148743, "teacher_acc": 0.731194406747818 }, { "step": 71, "lr": 8.875e-06, "elapsed_s": 60.770543336868286, "loss": 13.60209035873413, "hidden": 0.7885428071022034, "layer": 0.316788449883461, "mlm": 4.6275060176849365, "distill": 7.239104628562927, "teacher_acc": 0.728519082069397 }, { "step": 81, "lr": 1.0124999999999999e-05, "elapsed_s": 68.12384033203125, "loss": 13.014343976974487, "hidden": 0.7739235609769821, "layer": 0.31509388238191605, "mlm": 4.396705627441406, "distill": 6.912244200706482, "teacher_acc": 0.7272239178419113 }, { "step": 91, "lr": 1.1375e-05, "elapsed_s": 75.48223567008972, "loss": 12.397578477859497, "hidden": 0.7607980370521545, "layer": 0.31272996962070465, "mlm": 4.1447343826293945, "distill": 6.574883222579956, "teacher_acc": 0.7345134615898132 }, { "step": 101, "lr": 1.2625000000000002e-05, "elapsed_s": 82.84921288490295, "loss": 12.093305349349976, "hidden": 0.7483604401350021, "layer": 0.3083856627345085, "mlm": 4.03705632686615, "distill": 6.405335307121277, "teacher_acc": 0.7179478406906128 }, { "step": 111, "lr": 1.3875e-05, "elapsed_s": 90.21919751167297, "loss": 11.945655822753906, "hidden": 0.7515987753868103, "layer": 0.30460746586322784, "mlm": 3.9536109566688538, "distill": 6.336543560028076, "teacher_acc": 0.7208492904901505 }, { "step": 121, "lr": 1.5125000000000002e-05, "elapsed_s": 97.58434200286865, "loss": 11.234977960586548, "hidden": 0.7261582016944885, "layer": 0.2982270270586014, "mlm": 3.7661255598068237, "distill": 5.867422580718994, "teacher_acc": 0.7092819511890411 }, { "step": 131, "lr": 1.6375e-05, "elapsed_s": 104.9761278629303, "loss": 11.587674856185913, "hidden": 0.7305631786584854, "layer": 0.2971068322658539, "mlm": 3.7347702383995056, "distill": 6.2432249784469604, "teacher_acc": 0.7257865965366364 }, { "step": 141, "lr": 1.7625e-05, "elapsed_s": 112.3357400894165, "loss": 10.880138397216797, "hidden": 0.6972691863775253, "layer": 0.2890807241201401, "mlm": 3.661649167537689, "distill": 5.679410457611084, "teacher_acc": 0.7014146000146866 }, { "step": 151, "lr": 1.8875e-05, "elapsed_s": 119.68427348136902, "loss": 11.062957286834717, "hidden": 0.6857605576515198, "layer": 0.28529219329357147, "mlm": 3.5269588232040405, "distill": 6.021831154823303, "teacher_acc": 0.7346127033233643 }, { "step": 161, "lr": 2.0125e-05, "elapsed_s": 127.03348422050476, "loss": 11.272920608520508, "hidden": 0.7007472217082977, "layer": 0.2829109951853752, "mlm": 3.5320947766304016, "distill": 6.1978759765625, "teacher_acc": 0.7471081763505936 }, { "step": 171, "lr": 2.1375e-05, "elapsed_s": 134.39313292503357, "loss": 10.751477241516113, "hidden": 0.6778112649917603, "layer": 0.2782456651329994, "mlm": 3.4939733743667603, "distill": 5.762758493423462, "teacher_acc": 0.7287603914737701 }, { "step": 181, "lr": 2.2625e-05, "elapsed_s": 141.71666169166565, "loss": 10.61971139907837, "hidden": 0.6646811664104462, "layer": 0.27351267635822296, "mlm": 3.4403656721115112, "distill": 5.713227152824402, "teacher_acc": 0.7304104864597321 }, { "step": 191, "lr": 2.3875000000000004e-05, "elapsed_s": 149.05428099632263, "loss": 10.290287256240845, "hidden": 0.6457851976156235, "layer": 0.26799193024635315, "mlm": 3.395330488681793, "distill": 5.469390392303467, "teacher_acc": 0.7201550453901291 }, { "step": 201, "lr": 2.5125e-05, "elapsed_s": 156.44250774383545, "loss": 10.08063817024231, "hidden": 0.6336404383182526, "layer": 0.2623717039823532, "mlm": 3.344578802585602, "distill": 5.337592363357544, "teacher_acc": 0.7108413875102997 }, { "step": 211, "lr": 2.6375e-05, "elapsed_s": 163.8493993282318, "loss": 9.99802565574646, "hidden": 0.6193995177745819, "layer": 0.25645096600055695, "mlm": 3.2771191596984863, "distill": 5.353882193565369, "teacher_acc": 0.7279073297977448 }, { "step": 221, "lr": 2.7625e-05, "elapsed_s": 171.25341939926147, "loss": 9.680199146270752, "hidden": 0.6044565886259079, "layer": 0.2507324330508709, "mlm": 3.2872328758239746, "distill": 5.05868661403656, "teacher_acc": 0.7153979390859604 }, { "step": 231, "lr": 2.8875000000000004e-05, "elapsed_s": 178.6449475288391, "loss": 9.647573709487915, "hidden": 0.5889715254306793, "layer": 0.24639014899730682, "mlm": 3.243684768676758, "distill": 5.102750778198242, "teacher_acc": 0.7167518138885498 }, { "step": 241, "lr": 3.0125e-05, "elapsed_s": 186.02465295791626, "loss": 9.525534629821777, "hidden": 0.5796572864055634, "layer": 0.2429041862487793, "mlm": 3.2263808250427246, "distill": 5.018387198448181, "teacher_acc": 0.7235804498195648 }, { "step": 251, "lr": 3.1375000000000004e-05, "elapsed_s": 193.4231698513031, "loss": 9.560251474380493, "hidden": 0.57901830971241, "layer": 0.24033616855740547, "mlm": 3.174620270729065, "distill": 5.107426285743713, "teacher_acc": 0.7383224368095398 }, { "step": 261, "lr": 3.2625e-05, "elapsed_s": 200.81871700286865, "loss": 8.957597255706787, "hidden": 0.5617494434118271, "layer": 0.23227909952402115, "mlm": 3.145342469215393, "distill": 4.572616219520569, "teacher_acc": 0.715526819229126 }, { "step": 271, "lr": 3.3875000000000003e-05, "elapsed_s": 208.20436096191406, "loss": 9.00001859664917, "hidden": 0.5483827590942383, "layer": 0.2310510240495205, "mlm": 3.1237074732780457, "distill": 4.66402006149292, "teacher_acc": 0.7117209136486053 }, { "step": 281, "lr": 3.5125e-05, "elapsed_s": 215.57980751991272, "loss": 8.769193887710571, "hidden": 0.5332635194063187, "layer": 0.22395243868231773, "mlm": 3.0474495887756348, "distill": 4.5432411432266235, "teacher_acc": 0.7251143306493759 }, { "step": 291, "lr": 3.6375e-05, "elapsed_s": 222.9703459739685, "loss": 8.737284183502197, "hidden": 0.5418843030929565, "layer": 0.2234797701239586, "mlm": 3.039504826068878, "distill": 4.502270817756653, "teacher_acc": 0.7075243443250656 }, { "step": 301, "lr": 3.7625e-05, "elapsed_s": 230.36128664016724, "loss": 8.394862651824951, "hidden": 0.5147878527641296, "layer": 0.21833140030503273, "mlm": 2.999567449092865, "distill": 4.256553769111633, "teacher_acc": 0.7175053507089615 }, { "step": 311, "lr": 3.8875e-05, "elapsed_s": 237.73944878578186, "loss": 8.387603521347046, "hidden": 0.505688264966011, "layer": 0.21406494081020355, "mlm": 2.982984960079193, "distill": 4.286209940910339, "teacher_acc": 0.7223232388496399 }, { "step": 321, "lr": 4.0125000000000006e-05, "elapsed_s": 245.1364848613739, "loss": 8.304641962051392, "hidden": 0.5054546743631363, "layer": 0.2127266526222229, "mlm": 2.9435108304023743, "distill": 4.243858635425568, "teacher_acc": 0.7009203433990479 }, { "step": 331, "lr": 4.1375e-05, "elapsed_s": 252.5275890827179, "loss": 7.921196460723877, "hidden": 0.49171698838472366, "layer": 0.20450466871261597, "mlm": 2.8488515615463257, "distill": 3.9866586327552795, "teacher_acc": 0.7052172422409058 }, { "step": 341, "lr": 4.2625e-05, "elapsed_s": 259.9027352333069, "loss": 7.768313050270081, "hidden": 0.48448561131954193, "layer": 0.20270055532455444, "mlm": 2.870379626750946, "distill": 3.8276119232177734, "teacher_acc": 0.7051264345645905 }, { "step": 351, "lr": 4.3874999999999996e-05, "elapsed_s": 267.29892110824585, "loss": 7.813935875892639, "hidden": 0.4834267273545265, "layer": 0.1991100274026394, "mlm": 2.8287346959114075, "distill": 3.9187928438186646, "teacher_acc": 0.717182919383049 }, { "step": 361, "lr": 4.5125e-05, "elapsed_s": 274.69245076179504, "loss": 8.06712520122528, "hidden": 0.48718203604221344, "layer": 0.2007831148803234, "mlm": 2.7557015419006348, "distill": 4.236667990684509, "teacher_acc": 0.7378624975681305 }, { "step": 371, "lr": 4.6375e-05, "elapsed_s": 282.12883591651917, "loss": 7.616874098777771, "hidden": 0.4762837290763855, "layer": 0.19511355832219124, "mlm": 2.702797293663025, "distill": 3.8639525175094604, "teacher_acc": 0.7345853894948959 }, { "step": 381, "lr": 4.7625000000000006e-05, "elapsed_s": 289.5580132007599, "loss": 7.545713305473328, "hidden": 0.4575069919228554, "layer": 0.19037995114922523, "mlm": 2.7477957606315613, "distill": 3.7877135276794434, "teacher_acc": 0.7281907051801682 }, { "step": 391, "lr": 4.8875e-05, "elapsed_s": 296.96427512168884, "loss": 7.493480682373047, "hidden": 0.4638398289680481, "layer": 0.1900879219174385, "mlm": 2.737092614173889, "distill": 3.7336645126342773, "teacher_acc": 0.7123801559209824 }, { "step": 401, "lr": 5e-05, "elapsed_s": 304.3294451236725, "loss": 6.972379684448242, "hidden": 0.4409460425376892, "layer": 0.18277034163475037, "mlm": 2.6389081478118896, "distill": 3.360194206237793, "teacher_acc": 0.7027393281459808 }, { "step": 411, "lr": 4.999994930555009e-05, "elapsed_s": 311.6836335659027, "loss": 7.326171636581421, "hidden": 0.4544595927000046, "layer": 0.1839304305613041, "mlm": 2.5980085730552673, "distill": 3.727278709411621, "teacher_acc": 0.7458912879228592 }, { "step": 421, "lr": 4.999979722240593e-05, "elapsed_s": 319.09366035461426, "loss": 7.155426383018494, "hidden": 0.4476668983697891, "layer": 0.18222976848483086, "mlm": 2.6186808943748474, "distill": 3.550296723842621, "teacher_acc": 0.7102632969617844 }, { "step": 431, "lr": 4.999954375118431e-05, "elapsed_s": 326.4686439037323, "loss": 7.080630898475647, "hidden": 0.435101181268692, "layer": 0.1784873567521572, "mlm": 2.5806180238723755, "distill": 3.5405668020248413, "teacher_acc": 0.7217626422643661 }, { "step": 441, "lr": 4.99991888929132e-05, "elapsed_s": 333.85961842536926, "loss": 6.914414763450623, "hidden": 0.4366634264588356, "layer": 0.17913294956088066, "mlm": 2.5914214849472046, "distill": 3.3600999116897583, "teacher_acc": 0.7197299003601074 }, { "step": 451, "lr": 4.9998732649031746e-05, "elapsed_s": 341.27760314941406, "loss": 6.717426776885986, "hidden": 0.4241471514105797, "layer": 0.1744411140680313, "mlm": 2.5557414889335632, "distill": 3.2261704206466675, "teacher_acc": 0.7188067734241486 }, { "step": 461, "lr": 4.999817502139027e-05, "elapsed_s": 348.68601083755493, "loss": 6.747365236282349, "hidden": 0.426373228430748, "layer": 0.1708102747797966, "mlm": 2.4684707522392273, "distill": 3.3407429456710815, "teacher_acc": 0.7260115593671799 }, { "step": 471, "lr": 4.999751601225026e-05, "elapsed_s": 356.1031880378723, "loss": 6.7500081062316895, "hidden": 0.42207154631614685, "layer": 0.17049676924943924, "mlm": 2.4504913091659546, "distill": 3.3701255321502686, "teacher_acc": 0.7383766919374466 }, { "step": 481, "lr": 4.999675562428437e-05, "elapsed_s": 363.4732165336609, "loss": 6.7328526973724365, "hidden": 0.41543419659137726, "layer": 0.16748036071658134, "mlm": 2.4592020511627197, "distill": 3.3590421080589294, "teacher_acc": 0.731430396437645 }, { "step": 491, "lr": 4.9995893860576395e-05, "elapsed_s": 370.86935925483704, "loss": 6.760748267173767, "hidden": 0.4206240624189377, "layer": 0.16873305663466454, "mlm": 2.527904212474823, "distill": 3.307229459285736, "teacher_acc": 0.7193769365549088 }, { "step": 501, "lr": 4.999493072462126e-05, "elapsed_s": 378.2529573440552, "loss": 6.353148698806763, "hidden": 0.40859969705343246, "layer": 0.1644362322986126, "mlm": 2.585409462451935, "distill": 2.868321716785431, "teacher_acc": 0.6887723803520203 }, { "step": 511, "lr": 4.9993866220325016e-05, "elapsed_s": 385.65176367759705, "loss": 6.216914534568787, "hidden": 0.40293149650096893, "layer": 0.1617247387766838, "mlm": 2.4225248098373413, "distill": 2.9076645374298096, "teacher_acc": 0.7090970426797867 }, { "step": 521, "lr": 4.999270035200483e-05, "elapsed_s": 393.05822372436523, "loss": 6.242516756057739, "hidden": 0.4046694040298462, "layer": 0.16077996790409088, "mlm": 2.341669797897339, "distill": 3.0111181139945984, "teacher_acc": 0.7241754531860352 }, { "step": 531, "lr": 4.999143312438893e-05, "elapsed_s": 400.46572065353394, "loss": 6.31710147857666, "hidden": 0.3994235023856163, "layer": 0.16054637730121613, "mlm": 2.462680220603943, "distill": 2.9753010869026184, "teacher_acc": 0.7089099436998367 }, { "step": 541, "lr": 4.9990064542616654e-05, "elapsed_s": 407.88762855529785, "loss": 5.981846332550049, "hidden": 0.3858133405447006, "layer": 0.15531393885612488, "mlm": 2.3307279348373413, "distill": 2.8018347024917603, "teacher_acc": 0.7229381501674652 }, { "step": 551, "lr": 4.9988594612238336e-05, "elapsed_s": 415.29609417915344, "loss": 6.248854994773865, "hidden": 0.3978895992040634, "layer": 0.15689504891633987, "mlm": 2.418695569038391, "distill": 2.9559327960014343, "teacher_acc": 0.7165200561285019 }, { "step": 561, "lr": 4.9987023339215374e-05, "elapsed_s": 422.70060658454895, "loss": 6.041122794151306, "hidden": 0.3875919282436371, "layer": 0.15600741654634476, "mlm": 2.3161149621009827, "distill": 2.8718201518058777, "teacher_acc": 0.7301480919122696 }, { "step": 571, "lr": 4.9985350729920153e-05, "elapsed_s": 430.1006269454956, "loss": 5.758399605751038, "hidden": 0.37757109105587006, "layer": 0.1502341777086258, "mlm": 2.241311192512512, "distill": 2.686829090118408, "teacher_acc": 0.7183603644371033 }, { "step": 581, "lr": 4.998357679113603e-05, "elapsed_s": 437.50221991539, "loss": 5.868234634399414, "hidden": 0.38468971848487854, "layer": 0.1529390700161457, "mlm": 2.305842936038971, "distill": 2.716542661190033, "teacher_acc": 0.7171104699373245 }, { "step": 591, "lr": 4.998170153005732e-05, "elapsed_s": 444.8764066696167, "loss": 5.976639986038208, "hidden": 0.39913227409124374, "layer": 0.15395262837409973, "mlm": 2.2142714262008667, "distill": 2.887127697467804, "teacher_acc": 0.7405375242233276 }, { "step": 601, "lr": 4.9979724954289244e-05, "elapsed_s": 452.2580897808075, "loss": 5.784687042236328, "hidden": 0.3792489990592003, "layer": 0.14960836619138718, "mlm": 2.266518771648407, "distill": 2.684866189956665, "teacher_acc": 0.7305253446102142 }, { "step": 611, "lr": 4.997764707184791e-05, "elapsed_s": 459.6414020061493, "loss": 5.6485384702682495, "hidden": 0.37860359996557236, "layer": 0.14826326817274094, "mlm": 2.1599996089935303, "distill": 2.65719997882843, "teacher_acc": 0.734072357416153 }, { "step": 621, "lr": 4.99754678911603e-05, "elapsed_s": 467.03337574005127, "loss": 5.639063119888306, "hidden": 0.37454646825790405, "layer": 0.14888331294059753, "mlm": 2.3160704374313354, "distill": 2.4994580149650574, "teacher_acc": 0.7011914700269699 }, { "step": 631, "lr": 4.9973187421064194e-05, "elapsed_s": 474.40744400024414, "loss": 5.670869708061218, "hidden": 0.3767525181174278, "layer": 0.14850180223584175, "mlm": 2.145396411418915, "distill": 2.6977174282073975, "teacher_acc": 0.7550195753574371 }, { "step": 641, "lr": 4.997080567080817e-05, "elapsed_s": 481.8111844062805, "loss": 5.583534002304077, "hidden": 0.37513643503189087, "layer": 0.14605392143130302, "mlm": 2.23726749420166, "distill": 2.5229666233062744, "teacher_acc": 0.7129390090703964 }, { "step": 651, "lr": 4.996832265005154e-05, "elapsed_s": 489.18649673461914, "loss": 5.6264495849609375, "hidden": 0.3813329115509987, "layer": 0.14795170724391937, "mlm": 2.212577164173126, "distill": 2.57723069190979, "teacher_acc": 0.7245818227529526 }, { "step": 661, "lr": 4.996573836886435e-05, "elapsed_s": 496.55889439582825, "loss": 5.444245219230652, "hidden": 0.3595373034477234, "layer": 0.14399639889597893, "mlm": 2.158246397972107, "distill": 2.49492609500885, "teacher_acc": 0.7313836961984634 }, { "step": 671, "lr": 4.9963052837727286e-05, "elapsed_s": 503.98105096817017, "loss": 5.625387787818909, "hidden": 0.3801627680659294, "layer": 0.1467006802558899, "mlm": 2.1434438228607178, "distill": 2.648267984390259, "teacher_acc": 0.7389213591814041 }, { "step": 681, "lr": 4.996026606753167e-05, "elapsed_s": 511.39908933639526, "loss": 5.253180503845215, "hidden": 0.35616493970155716, "layer": 0.14314910024404526, "mlm": 2.14260071516037, "distill": 2.326675236225128, "teacher_acc": 0.7218354195356369 }, { "step": 691, "lr": 4.995737806957941e-05, "elapsed_s": 518.812028169632, "loss": 5.235458612442017, "hidden": 0.34271908551454544, "layer": 0.14079836010932922, "mlm": 2.139342725276947, "distill": 2.340278446674347, "teacher_acc": 0.7233784198760986 }, { "step": 701, "lr": 4.995438885558294e-05, "elapsed_s": 526.2391893863678, "loss": 5.291362166404724, "hidden": 0.35482554882764816, "layer": 0.1406991109251976, "mlm": 2.1557281613349915, "distill": 2.3556333780288696, "teacher_acc": 0.724240243434906 }, { "step": 711, "lr": 4.995129843766518e-05, "elapsed_s": 533.6620616912842, "loss": 5.245983600616455, "hidden": 0.36287378519773483, "layer": 0.14272823557257652, "mlm": 2.1766187846660614, "distill": 2.2722529768943787, "teacher_acc": 0.7111829370260239 }, { "step": 721, "lr": 4.994810682835951e-05, "elapsed_s": 541.1082148551941, "loss": 5.072383642196655, "hidden": 0.3412201628088951, "layer": 0.13884487748146057, "mlm": 2.0981135964393616, "distill": 2.222407341003418, "teacher_acc": 0.720179557800293 }, { "step": 731, "lr": 4.9944814040609655e-05, "elapsed_s": 548.5335462093353, "loss": 5.15772557258606, "hidden": 0.3424356132745743, "layer": 0.13967958837747574, "mlm": 2.1708444356918335, "distill": 2.2321701049804688, "teacher_acc": 0.7167054563760757 }, { "step": 741, "lr": 4.994142008776972e-05, "elapsed_s": 555.9521386623383, "loss": 5.285245299339294, "hidden": 0.35129498690366745, "layer": 0.1415005959570408, "mlm": 2.142484486103058, "distill": 2.3694204688072205, "teacher_acc": 0.7157605886459351 }, { "step": 751, "lr": 4.993792498360407e-05, "elapsed_s": 563.3601932525635, "loss": 5.073930501937866, "hidden": 0.3416658937931061, "layer": 0.13778120651841164, "mlm": 2.0428466498851776, "distill": 2.278861403465271, "teacher_acc": 0.736793115735054 }, { "step": 761, "lr": 4.9934328742287285e-05, "elapsed_s": 570.8088579177856, "loss": 5.146379232406616, "hidden": 0.3481604531407356, "layer": 0.13948576524853706, "mlm": 2.0327190160751343, "distill": 2.347596526145935, "teacher_acc": 0.7375090420246124 }, { "step": 771, "lr": 4.9930631378404126e-05, "elapsed_s": 578.2377731800079, "loss": 5.095861792564392, "hidden": 0.34284236282110214, "layer": 0.1386152170598507, "mlm": 2.0887444019317627, "distill": 2.2521252036094666, "teacher_acc": 0.723158210515976 }, { "step": 781, "lr": 4.992683290694946e-05, "elapsed_s": 585.661413192749, "loss": 5.174114227294922, "hidden": 0.3386623188853264, "layer": 0.13830074667930603, "mlm": 2.135282278060913, "distill": 2.29235702753067, "teacher_acc": 0.7139520049095154 }, { "step": 791, "lr": 4.99229333433282e-05, "elapsed_s": 593.0888574123383, "loss": 4.989296197891235, "hidden": 0.3369723930954933, "layer": 0.13672567531466484, "mlm": 2.0412542819976807, "distill": 2.2057341933250427, "teacher_acc": 0.7327211797237396 }, { "step": 801, "lr": 4.9918932703355256e-05, "elapsed_s": 600.5246045589447, "loss": 4.930473446846008, "hidden": 0.3342827931046486, "layer": 0.13438121229410172, "mlm": 2.088502526283264, "distill": 2.1062145829200745, "teacher_acc": 0.7142133265733719 }, { "step": 811, "lr": 4.991483100325542e-05, "elapsed_s": 607.9515490531921, "loss": 5.094535708427429, "hidden": 0.34925705194473267, "layer": 0.1373111829161644, "mlm": 2.0720496773719788, "distill": 2.2553164958953857, "teacher_acc": 0.7279532998800278 }, { "step": 821, "lr": 4.9910628259663404e-05, "elapsed_s": 615.3874452114105, "loss": 4.867947697639465, "hidden": 0.3341575264930725, "layer": 0.13361690938472748, "mlm": 2.0251238346099854, "distill": 2.107700228691101, "teacher_acc": 0.7225870937108994 }, { "step": 831, "lr": 4.990632448962365e-05, "elapsed_s": 622.805579662323, "loss": 5.057167053222656, "hidden": 0.33050037175416946, "layer": 0.1347789242863655, "mlm": 2.109598398208618, "distill": 2.2191783785820007, "teacher_acc": 0.7204168140888214 }, { "step": 841, "lr": 4.990191971059033e-05, "elapsed_s": 630.2259871959686, "loss": 5.001285433769226, "hidden": 0.3280780613422394, "layer": 0.1360291987657547, "mlm": 2.083369165658951, "distill": 2.193745493888855, "teacher_acc": 0.7262595146894455 }, { "step": 851, "lr": 4.989741394042727e-05, "elapsed_s": 637.64075922966, "loss": 5.136803388595581, "hidden": 0.3375082463026047, "layer": 0.1416374370455742, "mlm": 2.142011284828186, "distill": 2.2489569187164307, "teacher_acc": 0.7158180624246597 }, { "step": 861, "lr": 4.98928071974079e-05, "elapsed_s": 645.0270721912384, "loss": 5.104859948158264, "hidden": 0.3423059210181236, "layer": 0.1369442194700241, "mlm": 2.0107484459877014, "distill": 2.3410274982452393, "teacher_acc": 0.7325365543365479 }, { "step": 871, "lr": 4.988809950021511e-05, "elapsed_s": 652.4525923728943, "loss": 4.788349509239197, "hidden": 0.32434888929128647, "layer": 0.13105837628245354, "mlm": 1.9612310826778412, "distill": 2.112891435623169, "teacher_acc": 0.7467294037342072 }, { "step": 881, "lr": 4.988329086794122e-05, "elapsed_s": 659.8837642669678, "loss": 5.037511944770813, "hidden": 0.3343901112675667, "layer": 0.14045323058962822, "mlm": 2.0418640077114105, "distill": 2.256641149520874, "teacher_acc": 0.7328261435031891 }, { "step": 891, "lr": 4.987838132008791e-05, "elapsed_s": 667.2961189746857, "loss": 4.8361616134643555, "hidden": 0.3259722888469696, "layer": 0.1341593973338604, "mlm": 2.0181438326835632, "distill": 2.0989935100078583, "teacher_acc": 0.7223280966281891 }, { "step": 901, "lr": 4.987337087656614e-05, "elapsed_s": 674.7099261283875, "loss": 4.822410941123962, "hidden": 0.32974011451005936, "layer": 0.13251709565520287, "mlm": 2.0140772461891174, "distill": 2.082594931125641, "teacher_acc": 0.7189608961343765 }, { "step": 911, "lr": 4.986825955769604e-05, "elapsed_s": 682.1485304832458, "loss": 4.8774436712265015, "hidden": 0.33215662091970444, "layer": 0.13729573786258698, "mlm": 2.0375206768512726, "distill": 2.106961876153946, "teacher_acc": 0.7254447191953659 }, { "step": 921, "lr": 4.9863047384206835e-05, "elapsed_s": 689.5860855579376, "loss": 4.879358887672424, "hidden": 0.33479148894548416, "layer": 0.13709333539009094, "mlm": 2.0246306359767914, "distill": 2.1165987253189087, "teacher_acc": 0.7159988582134247 }, { "step": 931, "lr": 4.98577343772368e-05, "elapsed_s": 696.9890751838684, "loss": 4.817743897438049, "hidden": 0.3220086693763733, "layer": 0.13513080030679703, "mlm": 2.078570246696472, "distill": 2.0275908410549164, "teacher_acc": 0.6991146951913834 }, { "step": 941, "lr": 4.985232055833313e-05, "elapsed_s": 704.3758549690247, "loss": 4.817591190338135, "hidden": 0.32111839950084686, "layer": 0.13454684615135193, "mlm": 2.0539687871932983, "distill": 2.0541121065616608, "teacher_acc": 0.7147301286458969 }, { "step": 951, "lr": 4.984680594945187e-05, "elapsed_s": 711.804812669754, "loss": 4.800841569900513, "hidden": 0.3201806917786598, "layer": 0.1298685036599636, "mlm": 2.092036545276642, "distill": 2.0035094618797302, "teacher_acc": 0.6876754313707352 }, { "step": 961, "lr": 4.984119057295783e-05, "elapsed_s": 719.2115852832794, "loss": 4.76696240901947, "hidden": 0.3226161077618599, "layer": 0.13571170717477798, "mlm": 1.979168713092804, "distill": 2.0747055113315582, "teacher_acc": 0.7146732956171036 }, { "step": 971, "lr": 4.983547445162447e-05, "elapsed_s": 726.6001932621002, "loss": 4.897698402404785, "hidden": 0.3398028537631035, "layer": 0.1372847780585289, "mlm": 1.9599759578704834, "distill": 2.1894743740558624, "teacher_acc": 0.7334188222885132 }, { "step": 981, "lr": 4.982965760863385e-05, "elapsed_s": 734.017664194107, "loss": 4.791213870048523, "hidden": 0.3227470964193344, "layer": 0.13101212307810783, "mlm": 2.0096512734889984, "distill": 2.070562422275543, "teacher_acc": 0.7185997366905212 }, { "step": 991, "lr": 4.982374006757651e-05, "elapsed_s": 741.4150278568268, "loss": 4.641362905502319, "hidden": 0.3129960596561432, "layer": 0.12909220345318317, "mlm": 1.9589324593544006, "distill": 1.9918922185897827, "teacher_acc": 0.7298399060964584 }, { "step": 1001, "lr": 4.981772185245135e-05, "elapsed_s": 750.3298959732056, "loss": 4.703034400939941, "hidden": 0.3219163417816162, "layer": 0.13305561244487762, "mlm": 1.922544777393341, "distill": 2.0701292753219604, "teacher_acc": 0.7312430292367935 }, { "step": 1011, "lr": 4.98116029876656e-05, "elapsed_s": 757.7499992847443, "loss": 4.610443115234375, "hidden": 0.3101794049143791, "layer": 0.1295454427599907, "mlm": 1.9870969653129578, "distill": 1.938214510679245, "teacher_acc": 0.7150159627199173 }, { "step": 1021, "lr": 4.9805383498034634e-05, "elapsed_s": 765.1673581600189, "loss": 4.622528553009033, "hidden": 0.3260825648903847, "layer": 0.1337474249303341, "mlm": 1.8741153180599213, "distill": 2.0293743014335632, "teacher_acc": 0.7508395463228226 }, { "step": 1031, "lr": 4.9799063408781964e-05, "elapsed_s": 772.5650100708008, "loss": 4.572354793548584, "hidden": 0.3046359047293663, "layer": 0.12889032438397408, "mlm": 1.9670059084892273, "distill": 1.9316319525241852, "teacher_acc": 0.7208455950021744 }, { "step": 1041, "lr": 4.979264274553905e-05, "elapsed_s": 779.9983477592468, "loss": 4.474694609642029, "hidden": 0.30292869359254837, "layer": 0.12567608430981636, "mlm": 1.8532128632068634, "distill": 1.952786237001419, "teacher_acc": 0.74128757417202 }, { "step": 1051, "lr": 4.9786121534345265e-05, "elapsed_s": 787.3985753059387, "loss": 4.554490923881531, "hidden": 0.3086903840303421, "layer": 0.12875917926430702, "mlm": 1.9715653657913208, "distill": 1.9011651575565338, "teacher_acc": 0.7115155607461929 }, { "step": 1061, "lr": 4.977949980164773e-05, "elapsed_s": 794.7527594566345, "loss": 4.721103668212891, "hidden": 0.311616025865078, "layer": 0.13088103383779526, "mlm": 2.0440208315849304, "distill": 1.9884102046489716, "teacher_acc": 0.7057228833436966 }, { "step": 1071, "lr": 4.977277757430126e-05, "elapsed_s": 802.1160862445831, "loss": 4.518136620521545, "hidden": 0.312306210398674, "layer": 0.12948568351566792, "mlm": 1.9269156754016876, "distill": 1.9018657207489014, "teacher_acc": 0.7256583422422409 }, { "step": 1081, "lr": 4.976595487956823e-05, "elapsed_s": 809.4879651069641, "loss": 4.508713006973267, "hidden": 0.3133067935705185, "layer": 0.13071466237306595, "mlm": 1.8745789229869843, "distill": 1.942163109779358, "teacher_acc": 0.7400075644254684 }, { "step": 1091, "lr": 4.975903174511846e-05, "elapsed_s": 816.9056124687195, "loss": 4.672260165214539, "hidden": 0.30830634385347366, "layer": 0.13050559163093567, "mlm": 2.0098283886909485, "distill": 1.9805662333965302, "teacher_acc": 0.7097439765930176 }, { "step": 1101, "lr": 4.97520081990291e-05, "elapsed_s": 824.3218035697937, "loss": 4.478162169456482, "hidden": 0.30132005363702774, "layer": 0.12680126167833805, "mlm": 1.934798389673233, "distill": 1.8773230910301208, "teacher_acc": 0.72244031727314 }, { "step": 1111, "lr": 4.974488426978454e-05, "elapsed_s": 831.7060656547546, "loss": 4.574786186218262, "hidden": 0.3081897348165512, "layer": 0.1299586445093155, "mlm": 1.9377944469451904, "distill": 1.9556329548358917, "teacher_acc": 0.7167164385318756 }, { "step": 1121, "lr": 4.973765998627628e-05, "elapsed_s": 839.099362373352, "loss": 4.719651937484741, "hidden": 0.3076632544398308, "layer": 0.12780077382922173, "mlm": 2.0092593729496, "distill": 2.031165659427643, "teacher_acc": 0.7114860415458679 }, { "step": 1131, "lr": 4.973033537780279e-05, "elapsed_s": 846.5289509296417, "loss": 4.613595247268677, "hidden": 0.307561457157135, "layer": 0.12706381268799305, "mlm": 1.9707413017749786, "distill": 1.964199185371399, "teacher_acc": 0.730304017663002 }, { "step": 1141, "lr": 4.972291047406945e-05, "elapsed_s": 853.9660637378693, "loss": 4.410772800445557, "hidden": 0.3032796233892441, "layer": 0.13063329830765724, "mlm": 1.8852495551109314, "distill": 1.8536473512649536, "teacher_acc": 0.7212417870759964 }, { "step": 1151, "lr": 4.971538530518836e-05, "elapsed_s": 861.391731262207, "loss": 4.5778995752334595, "hidden": 0.313470721244812, "layer": 0.132009856402874, "mlm": 1.9603157043457031, "distill": 1.9246373772621155, "teacher_acc": 0.7229406833648682 }, { "step": 1161, "lr": 4.970775990167826e-05, "elapsed_s": 868.8102362155914, "loss": 4.359367728233337, "hidden": 0.28991588950157166, "layer": 0.12484918721020222, "mlm": 1.8987728655338287, "distill": 1.8183383643627167, "teacher_acc": 0.7215947806835175 }, { "step": 1171, "lr": 4.970003429446441e-05, "elapsed_s": 876.1895446777344, "loss": 4.480438947677612, "hidden": 0.3037787601351738, "layer": 0.12765572220087051, "mlm": 1.90505912899971, "distill": 1.9039945900440216, "teacher_acc": 0.7179454863071442 }, { "step": 1181, "lr": 4.9692208514878444e-05, "elapsed_s": 883.5766868591309, "loss": 4.525385618209839, "hidden": 0.29506581276655197, "layer": 0.12710702419281006, "mlm": 1.882359355688095, "distill": 1.989341139793396, "teacher_acc": 0.7336955517530441 }, { "step": 1191, "lr": 4.9684282594658246e-05, "elapsed_s": 890.9544034004211, "loss": 4.677729249000549, "hidden": 0.3106038495898247, "layer": 0.13045357912778854, "mlm": 2.011395901441574, "distill": 1.9798988103866577, "teacher_acc": 0.7057065963745117 }, { "step": 1201, "lr": 4.967625656594782e-05, "elapsed_s": 898.3799946308136, "loss": 4.49394965171814, "hidden": 0.30099181830883026, "layer": 0.12817841582000256, "mlm": 1.9290640652179718, "distill": 1.8988126814365387, "teacher_acc": 0.7291355133056641 }, { "step": 1211, "lr": 4.9668130461297194e-05, "elapsed_s": 905.7777628898621, "loss": 4.50913679599762, "hidden": 0.3010120913386345, "layer": 0.12571420893073082, "mlm": 2.0044189393520355, "distill": 1.8398365676403046, "teacher_acc": 0.7036506235599518 }, { "step": 1221, "lr": 4.965990431366222e-05, "elapsed_s": 913.1580653190613, "loss": 4.343609809875488, "hidden": 0.2936936542391777, "layer": 0.12521342001855373, "mlm": 1.8477296829223633, "distill": 1.845886081457138, "teacher_acc": 0.7416622936725616 }, { "step": 1231, "lr": 4.965157815640452e-05, "elapsed_s": 920.537565946579, "loss": 4.40191376209259, "hidden": 0.30053282529115677, "layer": 0.1260622087866068, "mlm": 1.9028975665569305, "distill": 1.8349193632602692, "teacher_acc": 0.721520870923996 }, { "step": 1241, "lr": 4.964315202329127e-05, "elapsed_s": 927.9259502887726, "loss": 4.472258567810059, "hidden": 0.29379475861787796, "layer": 0.12663817405700684, "mlm": 1.9231075644493103, "distill": 1.8982424139976501, "teacher_acc": 0.7300374209880829 }, { "step": 1251, "lr": 4.963462594849515e-05, "elapsed_s": 935.2698395252228, "loss": 4.389858603477478, "hidden": 0.29641395807266235, "layer": 0.12565509416162968, "mlm": 1.909010797739029, "distill": 1.8251924514770508, "teacher_acc": 0.729375347495079 }, { "step": 1261, "lr": 4.962599996659411e-05, "elapsed_s": 942.6686508655548, "loss": 4.639959931373596, "hidden": 0.2991560325026512, "layer": 0.12722802348434925, "mlm": 1.9903516173362732, "distill": 1.9876822233200073, "teacher_acc": 0.7156456708908081 }, { "step": 1271, "lr": 4.961727411257131e-05, "elapsed_s": 950.0319755077362, "loss": 4.3744460344314575, "hidden": 0.3020690158009529, "layer": 0.12644479982554913, "mlm": 1.8198013305664062, "distill": 1.8872843384742737, "teacher_acc": 0.7496918588876724 }, { "step": 1281, "lr": 4.960844842181494e-05, "elapsed_s": 957.4452042579651, "loss": 4.513927221298218, "hidden": 0.29486898332834244, "layer": 0.1251782663166523, "mlm": 1.9579129815101624, "distill": 1.9036871790885925, "teacher_acc": 0.7145192176103592 }, { "step": 1291, "lr": 4.9599522930118096e-05, "elapsed_s": 964.8351647853851, "loss": 4.2646883726119995, "hidden": 0.2876865044236183, "layer": 0.12215254455804825, "mlm": 1.933357834815979, "distill": 1.69488126039505, "teacher_acc": 0.7047304958105087 }, { "step": 1301, "lr": 4.959049767367859e-05, "elapsed_s": 972.2409627437592, "loss": 4.248990058898926, "hidden": 0.28627555817365646, "layer": 0.12341926433146, "mlm": 1.848913162946701, "distill": 1.76581609249115, "teacher_acc": 0.7315411418676376 }, { "step": 1311, "lr": 4.958137268909887e-05, "elapsed_s": 979.6475322246552, "loss": 4.268232703208923, "hidden": 0.28770801424980164, "layer": 0.1230434700846672, "mlm": 1.856235146522522, "distill": 1.7750597894191742, "teacher_acc": 0.7229520380496979 }, { "step": 1321, "lr": 4.957214801338581e-05, "elapsed_s": 987.006005525589, "loss": 4.183823823928833, "hidden": 0.2891813889145851, "layer": 0.12435024045407772, "mlm": 1.7533661425113678, "distill": 1.789919674396515, "teacher_acc": 0.7429679185152054 }, { "step": 1331, "lr": 4.95628236839506e-05, "elapsed_s": 994.3906586170197, "loss": 4.391822457313538, "hidden": 0.3051561489701271, "layer": 0.12650306895375252, "mlm": 1.8430744409561157, "distill": 1.8751842081546783, "teacher_acc": 0.7304579168558121 }, { "step": 1341, "lr": 4.9553399738608586e-05, "elapsed_s": 1001.7643473148346, "loss": 4.4735177755355835, "hidden": 0.2943750470876694, "layer": 0.12432482466101646, "mlm": 1.9398589134216309, "distill": 1.882746309041977, "teacher_acc": 0.708781361579895 }, { "step": 1351, "lr": 4.954387621557911e-05, "elapsed_s": 1009.1344065666199, "loss": 4.336280822753906, "hidden": 0.3002393916249275, "layer": 0.12461583688855171, "mlm": 1.838879942893982, "distill": 1.8346141278743744, "teacher_acc": 0.7299322783946991 }, { "step": 1361, "lr": 4.953425315348534e-05, "elapsed_s": 1016.5312852859497, "loss": 4.320904970169067, "hidden": 0.2915872633457184, "layer": 0.12485742382705212, "mlm": 1.911872237920761, "distill": 1.7634294033050537, "teacher_acc": 0.7190799713134766 }, { "step": 1371, "lr": 4.9524530591354153e-05, "elapsed_s": 1023.9014797210693, "loss": 4.285800814628601, "hidden": 0.28473374992609024, "layer": 0.12136291898787022, "mlm": 1.9213156998157501, "distill": 1.7343361973762512, "teacher_acc": 0.715947300195694 }, { "step": 1381, "lr": 4.951470856861594e-05, "elapsed_s": 1031.2963905334473, "loss": 4.242612719535828, "hidden": 0.28850770741701126, "layer": 0.1227881945669651, "mlm": 1.8719923496246338, "distill": 1.7322107553482056, "teacher_acc": 0.7223887294530869 }, { "step": 1391, "lr": 4.950478712510446e-05, "elapsed_s": 1038.6915748119354, "loss": 4.047649502754211, "hidden": 0.2824060767889023, "layer": 0.11906011030077934, "mlm": 1.8015377819538116, "distill": 1.6217696070671082, "teacher_acc": 0.7295505702495575 }, { "step": 1401, "lr": 4.949476630105669e-05, "elapsed_s": 1046.0751898288727, "loss": 4.132641673088074, "hidden": 0.2914177179336548, "layer": 0.12169065326452255, "mlm": 1.8041305541992188, "distill": 1.684830367565155, "teacher_acc": 0.7275697588920593 }, { "step": 1411, "lr": 4.948464613711264e-05, "elapsed_s": 1053.4401726722717, "loss": 4.129916191101074, "hidden": 0.2892899289727211, "layer": 0.12262328527867794, "mlm": 1.758442461490631, "distill": 1.7315822541713715, "teacher_acc": 0.731286033987999 }, { "step": 1421, "lr": 4.947442667431522e-05, "elapsed_s": 1060.8332786560059, "loss": 4.327285408973694, "hidden": 0.2897583767771721, "layer": 0.1237189881503582, "mlm": 1.8594854176044464, "distill": 1.8264236450195312, "teacher_acc": 0.7237403392791748 }, { "step": 1431, "lr": 4.946410795410999e-05, "elapsed_s": 1068.1984114646912, "loss": 4.270741820335388, "hidden": 0.2866842597723007, "layer": 0.12094557844102383, "mlm": 1.8097352087497711, "distill": 1.8271653354167938, "teacher_acc": 0.7390832155942917 }, { "step": 1441, "lr": 4.9453690018345144e-05, "elapsed_s": 1075.5824282169342, "loss": 4.262914776802063, "hidden": 0.28310947865247726, "layer": 0.12107419595122337, "mlm": 1.8635119795799255, "distill": 1.7726466953754425, "teacher_acc": 0.7270894199609756 }, { "step": 1451, "lr": 4.944317290927117e-05, "elapsed_s": 1082.9756622314453, "loss": 4.196645975112915, "hidden": 0.28404614329338074, "layer": 0.12049952521920204, "mlm": 1.8071829974651337, "distill": 1.7611209452152252, "teacher_acc": 0.7384281158447266 }, { "step": 1461, "lr": 4.9432556669540816e-05, "elapsed_s": 1090.364845752716, "loss": 4.263148665428162, "hidden": 0.2885754257440567, "layer": 0.12266804836690426, "mlm": 1.8273625075817108, "distill": 1.797301173210144, "teacher_acc": 0.7298999726772308 }, { "step": 1471, "lr": 4.942184134220882e-05, "elapsed_s": 1097.748853445053, "loss": 4.262672662734985, "hidden": 0.2894189730286598, "layer": 0.12277720682322979, "mlm": 1.815561205148697, "distill": 1.8068848550319672, "teacher_acc": 0.7339396178722382 }, { "step": 1481, "lr": 4.9411026970731805e-05, "elapsed_s": 1105.1400890350342, "loss": 4.258927702903748, "hidden": 0.27983321994543076, "layer": 0.11972370743751526, "mlm": 1.8708434104919434, "distill": 1.7685560286045074, "teacher_acc": 0.716232419013977 }, { "step": 1491, "lr": 4.940011359896805e-05, "elapsed_s": 1112.508715391159, "loss": 4.23661482334137, "hidden": 0.28377529978752136, "layer": 0.12191220931708813, "mlm": 1.8968423306941986, "distill": 1.711265742778778, "teacher_acc": 0.7108533084392548 }, { "step": 1501, "lr": 4.9389101271177355e-05, "elapsed_s": 1119.8994617462158, "loss": 4.1674264669418335, "hidden": 0.2815132513642311, "layer": 0.11923379078507423, "mlm": 1.86190864443779, "distill": 1.682874321937561, "teacher_acc": 0.726785197854042 }, { "step": 1511, "lr": 4.937799003202081e-05, "elapsed_s": 1127.292000055313, "loss": 4.115518569946289, "hidden": 0.2762071117758751, "layer": 0.11728795245289803, "mlm": 1.8300577998161316, "distill": 1.6744024753570557, "teacher_acc": 0.7161758095026016 }, { "step": 1521, "lr": 4.93667799265607e-05, "elapsed_s": 1134.695062160492, "loss": 4.14449417591095, "hidden": 0.28291136026382446, "layer": 0.11974113434553146, "mlm": 1.814038246870041, "distill": 1.704762488603592, "teacher_acc": 0.7303779274225235 }, { "step": 1531, "lr": 4.9355471000260215e-05, "elapsed_s": 1142.0873663425446, "loss": 4.22127890586853, "hidden": 0.27795346081256866, "layer": 0.12069458328187466, "mlm": 1.805231511592865, "distill": 1.7997932434082031, "teacher_acc": 0.7420413345098495 }, { "step": 1541, "lr": 4.934406329898334e-05, "elapsed_s": 1149.478263616562, "loss": 4.197100579738617, "hidden": 0.27748703956604004, "layer": 0.11953026615083218, "mlm": 1.825773447751999, "distill": 1.7565878629684448, "teacher_acc": 0.7246889024972916 }, { "step": 1551, "lr": 4.933255686899465e-05, "elapsed_s": 1156.863220691681, "loss": 4.316618204116821, "hidden": 0.281481608748436, "layer": 0.1197182908654213, "mlm": 1.8745201230049133, "distill": 1.8192757070064545, "teacher_acc": 0.7336137890815735 }, { "step": 1561, "lr": 4.932095175695911e-05, "elapsed_s": 1164.292986869812, "loss": 4.202737927436829, "hidden": 0.27803388983011246, "layer": 0.11921351030468941, "mlm": 1.8015567660331726, "distill": 1.785506546497345, "teacher_acc": 0.7446371465921402 }, { "step": 1571, "lr": 4.9309248009941914e-05, "elapsed_s": 1171.6855747699738, "loss": 4.072049975395203, "hidden": 0.27580320835113525, "layer": 0.11885002069175243, "mlm": 1.8012520372867584, "distill": 1.659766435623169, "teacher_acc": 0.722566545009613 }, { "step": 1581, "lr": 4.929744567540826e-05, "elapsed_s": 1179.1023712158203, "loss": 4.242192983627319, "hidden": 0.2769583612680435, "layer": 0.11931121908128262, "mlm": 1.804571807384491, "distill": 1.8240488171577454, "teacher_acc": 0.7337799817323685 }, { "step": 1591, "lr": 4.9285544801223164e-05, "elapsed_s": 1186.5166730880737, "loss": 4.119462251663208, "hidden": 0.27202603220939636, "layer": 0.11788270249962807, "mlm": 1.7844215035438538, "distill": 1.732047289609909, "teacher_acc": 0.7386694997549057 }, { "step": 1601, "lr": 4.92735454356513e-05, "elapsed_s": 1193.9223265647888, "loss": 3.9569131731987, "hidden": 0.2660151943564415, "layer": 0.11577095463871956, "mlm": 1.795245736837387, "distill": 1.5717514753341675, "teacher_acc": 0.720261737704277 }, { "step": 1611, "lr": 4.9261447627356766e-05, "elapsed_s": 1201.325041770935, "loss": 4.203479766845703, "hidden": 0.2755109891295433, "layer": 0.11892695724964142, "mlm": 1.8778530359268188, "distill": 1.715141236782074, "teacher_acc": 0.7072772681713104 }, { "step": 1621, "lr": 4.92492514254029e-05, "elapsed_s": 1208.7398793697357, "loss": 4.1245410442352295, "hidden": 0.27370329946279526, "layer": 0.11781332828104496, "mlm": 1.7782695293426514, "distill": 1.739958256483078, "teacher_acc": 0.7412877231836319 }, { "step": 1631, "lr": 4.923695687925207e-05, "elapsed_s": 1216.1386933326721, "loss": 4.042859792709351, "hidden": 0.2672458216547966, "layer": 0.11648105457425117, "mlm": 1.8428515791893005, "distill": 1.6072761118412018, "teacher_acc": 0.7136448621749878 }, { "step": 1641, "lr": 4.922456403876552e-05, "elapsed_s": 1223.5526456832886, "loss": 4.069103121757507, "hidden": 0.27583178877830505, "layer": 0.11882580257952213, "mlm": 1.82866370677948, "distill": 1.6293628811836243, "teacher_acc": 0.709219291806221 }, { "step": 1651, "lr": 4.9212072954203086e-05, "elapsed_s": 1230.958993434906, "loss": 4.141493916511536, "hidden": 0.2743382155895233, "layer": 0.11745981499552727, "mlm": 1.8946268558502197, "distill": 1.6394605934619904, "teacher_acc": 0.6988830268383026 }, { "step": 1661, "lr": 4.919948367622307e-05, "elapsed_s": 1238.3738043308258, "loss": 3.971095621585846, "hidden": 0.27348922938108444, "layer": 0.1171498354524374, "mlm": 1.758977323770523, "distill": 1.606564998626709, "teacher_acc": 0.7259180545806885 }, { "step": 1671, "lr": 4.9186796255882e-05, "elapsed_s": 1245.7514443397522, "loss": 4.0444910526275635, "hidden": 0.27669356018304825, "layer": 0.11808189004659653, "mlm": 1.799822449684143, "distill": 1.6322405934333801, "teacher_acc": 0.7212954610586166 }, { "step": 1681, "lr": 4.917401074463441e-05, "elapsed_s": 1253.157922744751, "loss": 4.025470852851868, "hidden": 0.26970671117305756, "layer": 0.11674328707158566, "mlm": 1.7841910421848297, "distill": 1.6434946954250336, "teacher_acc": 0.7226119190454483 }, { "step": 1691, "lr": 4.9161127194332655e-05, "elapsed_s": 1260.5539331436157, "loss": 4.006395578384399, "hidden": 0.271147221326828, "layer": 0.1160933617502451, "mlm": 1.7752127647399902, "distill": 1.630841612815857, "teacher_acc": 0.726735070347786 }, { "step": 1701, "lr": 4.914814565722671e-05, "elapsed_s": 1267.9618742465973, "loss": 4.040911018848419, "hidden": 0.2694307118654251, "layer": 0.11729244142770767, "mlm": 1.7320196330547333, "distill": 1.7113837003707886, "teacher_acc": 0.7495951056480408 }, { "step": 1711, "lr": 4.9135066185963905e-05, "elapsed_s": 1275.3815183639526, "loss": 4.10949170589447, "hidden": 0.2712763324379921, "layer": 0.1159052699804306, "mlm": 1.8807397782802582, "distill": 1.628246545791626, "teacher_acc": 0.7094578593969345 }, { "step": 1721, "lr": 4.9121888833588795e-05, "elapsed_s": 1282.7949073314667, "loss": 3.8459686040878296, "hidden": 0.2645316757261753, "layer": 0.11463603936135769, "mlm": 1.7096973955631256, "distill": 1.5498898923397064, "teacher_acc": 0.7298763543367386 }, { "step": 1731, "lr": 4.9108613653542834e-05, "elapsed_s": 1290.212470293045, "loss": 4.060302257537842, "hidden": 0.2778415232896805, "layer": 0.11850542947649956, "mlm": 1.7755380868911743, "distill": 1.6698284447193146, "teacher_acc": 0.7308552116155624 }, { "step": 1741, "lr": 4.909524069966429e-05, "elapsed_s": 1297.5737907886505, "loss": 3.9033786058425903, "hidden": 0.27210283279418945, "layer": 0.11676839552819729, "mlm": 1.676222324371338, "distill": 1.6245664358139038, "teacher_acc": 0.7353321462869644 }, { "step": 1751, "lr": 4.9081770026187914e-05, "elapsed_s": 1304.9438817501068, "loss": 3.9643682837486267, "hidden": 0.268108993768692, "layer": 0.11562482826411724, "mlm": 1.7291994392871857, "distill": 1.6411384046077728, "teacher_acc": 0.742116704583168 }, { "step": 1761, "lr": 4.906820168774477e-05, "elapsed_s": 1312.3041315078735, "loss": 4.055130958557129, "hidden": 0.2741355299949646, "layer": 0.1160981860011816, "mlm": 1.7884034216403961, "distill": 1.660407394170761, "teacher_acc": 0.7300701141357422 }, { "step": 1771, "lr": 4.905453573936203e-05, "elapsed_s": 1319.7072315216064, "loss": 3.8725470900535583, "hidden": 0.25886010378599167, "layer": 0.11326215602457523, "mlm": 1.7237524092197418, "distill": 1.5744433999061584, "teacher_acc": 0.7289312928915024 }, { "step": 1781, "lr": 4.9040772236462695e-05, "elapsed_s": 1327.0891602039337, "loss": 3.910508930683136, "hidden": 0.26110412180423737, "layer": 0.11456430330872536, "mlm": 1.7168515026569366, "distill": 1.614167034626007, "teacher_acc": 0.7252945452928543 }, { "step": 1791, "lr": 4.902691123486544e-05, "elapsed_s": 1334.494841337204, "loss": 3.925660252571106, "hidden": 0.26289714127779007, "layer": 0.11490749008953571, "mlm": 1.7499323785305023, "distill": 1.5924798548221588, "teacher_acc": 0.7337967157363892 }, { "step": 1801, "lr": 4.901295279078431e-05, "elapsed_s": 1341.924957036972, "loss": 3.943657338619232, "hidden": 0.263511061668396, "layer": 0.11480100266635418, "mlm": 1.7710242867469788, "distill": 1.5882104337215424, "teacher_acc": 0.7232167720794678 }, { "step": 1811, "lr": 4.8998896960828576e-05, "elapsed_s": 1349.3606050014496, "loss": 4.007841229438782, "hidden": 0.26178329437971115, "layer": 0.11514490842819214, "mlm": 1.8540367782115936, "distill": 1.5726653635501862, "teacher_acc": 0.7053327709436417 }, { "step": 1821, "lr": 4.898474380200244e-05, "elapsed_s": 1356.791417837143, "loss": 4.013287663459778, "hidden": 0.2653432711958885, "layer": 0.11379984952509403, "mlm": 1.7653261721134186, "distill": 1.660375028848648, "teacher_acc": 0.7330894768238068 }, { "step": 1831, "lr": 4.8970493371704826e-05, "elapsed_s": 1364.2015180587769, "loss": 4.096006631851196, "hidden": 0.26983965188264847, "layer": 0.11775527149438858, "mlm": 1.8329637944698334, "distill": 1.6644857823848724, "teacher_acc": 0.7163500040769577 }, { "step": 1841, "lr": 4.8956145727729156e-05, "elapsed_s": 1371.6180520057678, "loss": 3.9370800256729126, "hidden": 0.26880139857530594, "layer": 0.1149628758430481, "mlm": 1.7297857999801636, "distill": 1.6122100353240967, "teacher_acc": 0.7322975099086761 }, { "step": 1851, "lr": 4.89417009282631e-05, "elapsed_s": 1379.0152342319489, "loss": 3.9829391837120056, "hidden": 0.26645859330892563, "layer": 0.11466134339570999, "mlm": 1.792383998632431, "distill": 1.600307434797287, "teacher_acc": 0.7116580754518509 }, { "step": 1861, "lr": 4.892715903188836e-05, "elapsed_s": 1386.3855543136597, "loss": 4.02520489692688, "hidden": 0.26583026349544525, "layer": 0.11542770266532898, "mlm": 1.84133842587471, "distill": 1.5944920480251312, "teacher_acc": 0.7134247869253159 }, { "step": 1871, "lr": 4.8912520097580395e-05, "elapsed_s": 1393.7514412403107, "loss": 4.0547550320625305, "hidden": 0.2741224393248558, "layer": 0.11564958281815052, "mlm": 1.8349095582962036, "distill": 1.6137757897377014, "teacher_acc": 0.7154436558485031 }, { "step": 1881, "lr": 4.889778418470823e-05, "elapsed_s": 1401.11745595932, "loss": 3.873760998249054, "hidden": 0.26062145084142685, "layer": 0.11372656188905239, "mlm": 1.7475957870483398, "distill": 1.5480589866638184, "teacher_acc": 0.7312120199203491 }, { "step": 1891, "lr": 4.888295135303418e-05, "elapsed_s": 1408.4978585243225, "loss": 3.8677785992622375, "hidden": 0.2633001543581486, "layer": 0.11530493013560772, "mlm": 1.7338138818740845, "distill": 1.54971182346344, "teacher_acc": 0.7224676758050919 }, { "step": 1901, "lr": 4.886802166271364e-05, "elapsed_s": 1415.885833978653, "loss": 3.8258262872695923, "hidden": 0.2571691647171974, "layer": 0.11422812938690186, "mlm": 1.6562677919864655, "distill": 1.5981061160564423, "teacher_acc": 0.7442539632320404 }, { "step": 1911, "lr": 4.88529951742948e-05, "elapsed_s": 1423.2395277023315, "loss": 4.137242794036865, "hidden": 0.2623438760638237, "layer": 0.11479996144771576, "mlm": 1.9038341641426086, "distill": 1.6513210535049438, "teacher_acc": 0.7084044516086578 }, { "step": 1921, "lr": 4.883787194871841e-05, "elapsed_s": 1430.6223375797272, "loss": 3.931863307952881, "hidden": 0.267056405544281, "layer": 0.11772950552403927, "mlm": 1.7514340579509735, "distill": 1.5874518156051636, "teacher_acc": 0.7247260808944702 }, { "step": 1931, "lr": 4.8822652047317576e-05, "elapsed_s": 1437.9897689819336, "loss": 3.9127307534217834, "hidden": 0.26528214663267136, "layer": 0.1145928930491209, "mlm": 1.6910908818244934, "distill": 1.6337791979312897, "teacher_acc": 0.7463971078395844 }, { "step": 1941, "lr": 4.880733553181745e-05, "elapsed_s": 1445.4078583717346, "loss": 3.8677561283111572, "hidden": 0.26494765281677246, "layer": 0.11483337730169296, "mlm": 1.674789547920227, "distill": 1.605654537677765, "teacher_acc": 0.7425475418567657 }, { "step": 1951, "lr": 4.8791922464335015e-05, "elapsed_s": 1452.7917742729187, "loss": 3.912749230861664, "hidden": 0.26438158005476, "layer": 0.11647258140146732, "mlm": 1.7126152217388153, "distill": 1.6131345331668854, "teacher_acc": 0.7387824803590775 }, { "step": 1961, "lr": 4.877641290737884e-05, "elapsed_s": 1460.1799867153168, "loss": 4.000911474227905, "hidden": 0.2635009437799454, "layer": 0.11493142880499363, "mlm": 1.8374084532260895, "distill": 1.5790354013442993, "teacher_acc": 0.7120477259159088 }, { "step": 1971, "lr": 4.87608069238488e-05, "elapsed_s": 1467.5589821338654, "loss": 3.952027440071106, "hidden": 0.25954311341047287, "layer": 0.11294668540358543, "mlm": 1.7966808080673218, "distill": 1.5797869861125946, "teacher_acc": 0.7198255211114883 }, { "step": 1981, "lr": 4.874510457703583e-05, "elapsed_s": 1474.9765911102295, "loss": 3.734243333339691, "hidden": 0.2588770315051079, "layer": 0.11292687244713306, "mlm": 1.6978994607925415, "distill": 1.4621263444423676, "teacher_acc": 0.7278008013963699 }, { "step": 1991, "lr": 4.872930593062168e-05, "elapsed_s": 1482.3742113113403, "loss": 3.7141858339309692, "hidden": 0.25460510328412056, "layer": 0.11156057566404343, "mlm": 1.655147910118103, "distill": 1.4940473437309265, "teacher_acc": 0.7379762977361679 }, { "step": 2001, "lr": 4.8713411048678635e-05, "elapsed_s": 1491.76766872406, "loss": 3.9283209443092346, "hidden": 0.25907303765416145, "layer": 0.11318337358534336, "mlm": 1.7712864577770233, "distill": 1.5822968184947968, "teacher_acc": 0.7172820121049881 }, { "step": 2011, "lr": 4.8697419995669304e-05, "elapsed_s": 1499.1479773521423, "loss": 3.985919237136841, "hidden": 0.259055458009243, "layer": 0.11354961059987545, "mlm": 1.833306461572647, "distill": 1.577727049589157, "teacher_acc": 0.712208017706871 }, { "step": 2021, "lr": 4.868133283644627e-05, "elapsed_s": 1506.5302166938782, "loss": 3.741446614265442, "hidden": 0.24916762486100197, "layer": 0.11203144676983356, "mlm": 1.7160248458385468, "distill": 1.471070796251297, "teacher_acc": 0.7306434512138367 }, { "step": 2031, "lr": 4.866514963625192e-05, "elapsed_s": 1513.9140689373016, "loss": 3.912960648536682, "hidden": 0.2593256011605263, "layer": 0.11219154857099056, "mlm": 1.725127249956131, "distill": 1.6130864322185516, "teacher_acc": 0.7276073694229126 }, { "step": 2041, "lr": 4.864887046071813e-05, "elapsed_s": 1521.3447892665863, "loss": 3.858840227127075, "hidden": 0.25858693569898605, "layer": 0.11235799640417099, "mlm": 1.6772578060626984, "distill": 1.608229637145996, "teacher_acc": 0.7404515445232391 }, { "step": 2051, "lr": 4.8632495375866004e-05, "elapsed_s": 1528.7397742271423, "loss": 3.7260199189186096, "hidden": 0.25173715874552727, "layer": 0.11114678718149662, "mlm": 1.7014999389648438, "distill": 1.465472251176834, "teacher_acc": 0.7315275371074677 }, { "step": 2061, "lr": 4.8616024448105626e-05, "elapsed_s": 1536.2033755779266, "loss": 3.7934157848358154, "hidden": 0.25040078535676, "layer": 0.11035937070846558, "mlm": 1.7161026298999786, "distill": 1.5213318765163422, "teacher_acc": 0.7229634076356888 }, { "step": 2071, "lr": 4.859945774423575e-05, "elapsed_s": 1543.624699831009, "loss": 3.8551888465881348, "hidden": 0.25906796008348465, "layer": 0.11276037245988846, "mlm": 1.7273021638393402, "distill": 1.5533705651760101, "teacher_acc": 0.7239642888307571 }, { "step": 2081, "lr": 4.858279533144358e-05, "elapsed_s": 1551.0422327518463, "loss": 3.7497435212135315, "hidden": 0.24814024195075035, "layer": 0.11147261038422585, "mlm": 1.7492544949054718, "distill": 1.448472261428833, "teacher_acc": 0.725109875202179 }, { "step": 2091, "lr": 4.856603727730447e-05, "elapsed_s": 1558.4539713859558, "loss": 3.7135396003723145, "hidden": 0.2477710247039795, "layer": 0.1095570120960474, "mlm": 1.7603477835655212, "distill": 1.4028713703155518, "teacher_acc": 0.7150020599365234 }, { "step": 2101, "lr": 4.8549183649781626e-05, "elapsed_s": 1565.8681509494781, "loss": 3.778154730796814, "hidden": 0.2488444447517395, "layer": 0.10881204903125763, "mlm": 1.7663404941558838, "distill": 1.4597193002700806, "teacher_acc": 0.7076955437660217 }, { "step": 2111, "lr": 4.853223451722589e-05, "elapsed_s": 1573.2999246120453, "loss": 3.961124897003174, "hidden": 0.2597087174654007, "layer": 0.11299195699393749, "mlm": 1.7284411191940308, "distill": 1.6567704677581787, "teacher_acc": 0.7349591553211212 }, { "step": 2121, "lr": 4.8515189948375434e-05, "elapsed_s": 1580.6742188930511, "loss": 3.8618377447128296, "hidden": 0.2569420374929905, "layer": 0.11181840486824512, "mlm": 1.748778611421585, "distill": 1.543265849351883, "teacher_acc": 0.72219517827034 }, { "step": 2131, "lr": 4.849805001235544e-05, "elapsed_s": 1588.077444076538, "loss": 3.893868327140808, "hidden": 0.25733304768800735, "layer": 0.11332016624510288, "mlm": 1.7597509026527405, "distill": 1.5627912878990173, "teacher_acc": 0.7182294279336929 }, { "step": 2141, "lr": 4.8480814778677886e-05, "elapsed_s": 1595.4836041927338, "loss": 3.752512037754059, "hidden": 0.2519802264869213, "layer": 0.1101859100162983, "mlm": 1.7296915650367737, "distill": 1.4637670814990997, "teacher_acc": 0.7298867702484131 }, { "step": 2151, "lr": 4.8463484317241226e-05, "elapsed_s": 1602.8707621097565, "loss": 3.6804771423339844, "hidden": 0.24470311030745506, "layer": 0.10954228788614273, "mlm": 1.6736562848091125, "distill": 1.4626435935497284, "teacher_acc": 0.7283311635255814 }, { "step": 2161, "lr": 4.8446058698330115e-05, "elapsed_s": 1610.2833743095398, "loss": 3.830751061439514, "hidden": 0.26048295199871063, "layer": 0.11235157772898674, "mlm": 1.753524899482727, "distill": 1.5000845193862915, "teacher_acc": 0.7219198048114777 }, { "step": 2171, "lr": 4.842853799261513e-05, "elapsed_s": 1617.6941299438477, "loss": 3.819101631641388, "hidden": 0.2561846449971199, "layer": 0.11272404342889786, "mlm": 1.7824145555496216, "distill": 1.4679557085037231, "teacher_acc": 0.7075820714235306 }, { "step": 2181, "lr": 4.841092227115247e-05, "elapsed_s": 1625.0718519687653, "loss": 3.888596475124359, "hidden": 0.2566503472626209, "layer": 0.11228472739458084, "mlm": 1.777033507823944, "distill": 1.5421198308467865, "teacher_acc": 0.7178526520729065 }, { "step": 2191, "lr": 4.839321160538369e-05, "elapsed_s": 1632.4810466766357, "loss": 3.810259997844696, "hidden": 0.25594790279865265, "layer": 0.11116081103682518, "mlm": 1.751077264547348, "distill": 1.4917064607143402, "teacher_acc": 0.7177864909172058 }, { "step": 2201, "lr": 4.837540606713538e-05, "elapsed_s": 1639.8658628463745, "loss": 3.7928138971328735, "hidden": 0.24622415006160736, "layer": 0.11025381833314896, "mlm": 1.7675414681434631, "distill": 1.4776972532272339, "teacher_acc": 0.7079342603683472 }, { "step": 2211, "lr": 4.8357505728618886e-05, "elapsed_s": 1647.2524738311768, "loss": 3.7466330528259277, "hidden": 0.2507931999862194, "layer": 0.10913983918726444, "mlm": 1.779582291841507, "distill": 1.4108944237232208, "teacher_acc": 0.7024128586053848 }, { "step": 2221, "lr": 4.8339510662430046e-05, "elapsed_s": 1654.6791286468506, "loss": 3.839081585407257, "hidden": 0.24698897451162338, "layer": 0.1100331787019968, "mlm": 1.8070143163204193, "distill": 1.4830726385116577, "teacher_acc": 0.7061618268489838 }, { "step": 2231, "lr": 4.832142094154886e-05, "elapsed_s": 1662.0784311294556, "loss": 3.811948299407959, "hidden": 0.25376270711421967, "layer": 0.1114901565015316, "mlm": 1.6992760002613068, "distill": 1.549401730298996, "teacher_acc": 0.7325648665428162 }, { "step": 2241, "lr": 4.83032366393392e-05, "elapsed_s": 1669.5000557899475, "loss": 3.9008437991142273, "hidden": 0.2512689679861069, "layer": 0.11265360005199909, "mlm": 1.7716874778270721, "distill": 1.5702916383743286, "teacher_acc": 0.7235399931669235 }, { "step": 2251, "lr": 4.828495782954852e-05, "elapsed_s": 1676.9206519126892, "loss": 3.7354241609573364, "hidden": 0.2521323710680008, "layer": 0.11011753603816032, "mlm": 1.736986368894577, "distill": 1.439114362001419, "teacher_acc": 0.7176721841096878 }, { "step": 2261, "lr": 4.826658458630756e-05, "elapsed_s": 1684.3310117721558, "loss": 3.8716242909431458, "hidden": 0.258310966193676, "layer": 0.11187855340540409, "mlm": 1.7341187000274658, "distill": 1.564944326877594, "teacher_acc": 0.7295988500118256 }, { "step": 2271, "lr": 4.8248116984130034e-05, "elapsed_s": 1691.7226912975311, "loss": 3.731353759765625, "hidden": 0.25206349045038223, "layer": 0.11220180429518223, "mlm": 1.7203965187072754, "distill": 1.450729250907898, "teacher_acc": 0.7182573825120926 }, { "step": 2281, "lr": 4.822955509791233e-05, "elapsed_s": 1699.1242909431458, "loss": 3.761576235294342, "hidden": 0.24819886311888695, "layer": 0.1087129395455122, "mlm": 1.7110427618026733, "distill": 1.4997792541980743, "teacher_acc": 0.7260957807302475 }, { "step": 2291, "lr": 4.8210899002933235e-05, "elapsed_s": 1706.518870830536, "loss": 3.745406925678253, "hidden": 0.24332544952630997, "layer": 0.10934064909815788, "mlm": 1.7383477687835693, "distill": 1.4657378494739532, "teacher_acc": 0.7136690765619278 }, { "step": 2301, "lr": 4.819214877485358e-05, "elapsed_s": 1713.938626050949, "loss": 3.960775673389435, "hidden": 0.2648190073668957, "layer": 0.11514735035598278, "mlm": 1.7090501487255096, "distill": 1.6645138263702393, "teacher_acc": 0.737593024969101 }, { "step": 2311, "lr": 4.8173304489715953e-05, "elapsed_s": 1721.3406410217285, "loss": 3.642211079597473, "hidden": 0.2459014095366001, "layer": 0.10843637771904469, "mlm": 1.6925817131996155, "distill": 1.4036083221435547, "teacher_acc": 0.7297173589468002 }, { "step": 2321, "lr": 4.815436622394441e-05, "elapsed_s": 1728.7602188587189, "loss": 3.7932201623916626, "hidden": 0.24933533370494843, "layer": 0.10909699648618698, "mlm": 1.7553210258483887, "distill": 1.4846799075603485, "teacher_acc": 0.7145818024873734 }, { "step": 2331, "lr": 4.813533405434417e-05, "elapsed_s": 1736.188850402832, "loss": 3.704191207885742, "hidden": 0.2512279227375984, "layer": 0.11084950156509876, "mlm": 1.7046216428279877, "distill": 1.4416889548301697, "teacher_acc": 0.7253220230340958 }, { "step": 2341, "lr": 4.8116208058101236e-05, "elapsed_s": 1743.610481262207, "loss": 3.863282024860382, "hidden": 0.24838250502943993, "layer": 0.10942491888999939, "mlm": 1.7685328125953674, "distill": 1.5432717204093933, "teacher_acc": 0.7260880172252655 }, { "step": 2351, "lr": 4.8096988312782174e-05, "elapsed_s": 1751.0236730575562, "loss": 3.6840537786483765, "hidden": 0.24761249870061874, "layer": 0.10832477547228336, "mlm": 1.7780731916427612, "distill": 1.3565932512283325, "teacher_acc": 0.6999672204256058 }, { "step": 2361, "lr": 4.8077674896333725e-05, "elapsed_s": 1758.4118888378143, "loss": 3.6843072175979614, "hidden": 0.24846041202545166, "layer": 0.1089798305183649, "mlm": 1.6926963925361633, "distill": 1.440200001001358, "teacher_acc": 0.7290272563695908 }, { "step": 2371, "lr": 4.805826788708254e-05, "elapsed_s": 1765.8164603710175, "loss": 3.603092133998871, "hidden": 0.24257640168070793, "layer": 0.10641664266586304, "mlm": 1.6400000751018524, "distill": 1.4247309565544128, "teacher_acc": 0.7381000220775604 }, { "step": 2381, "lr": 4.803876736373483e-05, "elapsed_s": 1773.2482841014862, "loss": 3.6311395168304443, "hidden": 0.24065001308918, "layer": 0.10753550939261913, "mlm": 1.726937621831894, "distill": 1.369134098291397, "teacher_acc": 0.7084744423627853 }, { "step": 2391, "lr": 4.801917340537605e-05, "elapsed_s": 1780.655324459076, "loss": 3.840295970439911, "hidden": 0.24767836928367615, "layer": 0.10932904295623302, "mlm": 1.8044228553771973, "distill": 1.4858517944812775, "teacher_acc": 0.703942209482193 }, { "step": 2401, "lr": 4.799948609147061e-05, "elapsed_s": 1788.0623397827148, "loss": 3.6096293926239014, "hidden": 0.24044471234083176, "layer": 0.10646991059184074, "mlm": 1.6577262580394745, "distill": 1.4177787005901337, "teacher_acc": 0.7344533950090408 }, { "step": 2411, "lr": 4.79797055018615e-05, "elapsed_s": 1795.4843757152557, "loss": 3.6840533018112183, "hidden": 0.24279526248574257, "layer": 0.10737080127000809, "mlm": 1.6824278831481934, "distill": 1.462349385023117, "teacher_acc": 0.7308273017406464 }, { "step": 2421, "lr": 4.795983171677002e-05, "elapsed_s": 1802.9127252101898, "loss": 3.804903745651245, "hidden": 0.24725133180618286, "layer": 0.10980324260890484, "mlm": 1.7106261253356934, "distill": 1.54487344622612, "teacher_acc": 0.7355051040649414 }, { "step": 2431, "lr": 4.7939864816795416e-05, "elapsed_s": 1810.3432569503784, "loss": 3.7888460755348206, "hidden": 0.24837645888328552, "layer": 0.10931314714252949, "mlm": 1.7285901010036469, "distill": 1.5088465213775635, "teacher_acc": 0.7219253033399582 }, { "step": 2441, "lr": 4.791980488291456e-05, "elapsed_s": 1817.7673411369324, "loss": 3.7419418692588806, "hidden": 0.24069231376051903, "layer": 0.10797939263284206, "mlm": 1.7442275285720825, "distill": 1.462339997291565, "teacher_acc": 0.7189342528581619 }, { "step": 2451, "lr": 4.7899651996481656e-05, "elapsed_s": 1825.1733677387238, "loss": 3.761119782924652, "hidden": 0.25064223632216454, "layer": 0.1095963567495346, "mlm": 1.699464350938797, "distill": 1.5055726766586304, "teacher_acc": 0.7272935211658478 }, { "step": 2461, "lr": 4.787940623922784e-05, "elapsed_s": 1832.5688915252686, "loss": 3.6708080172538757, "hidden": 0.24238311126828194, "layer": 0.10794962011277676, "mlm": 1.7068127393722534, "distill": 1.4252543151378632, "teacher_acc": 0.7142873704433441 }, { "step": 2471, "lr": 4.7859067693260926e-05, "elapsed_s": 1839.965213060379, "loss": 3.5825703144073486, "hidden": 0.2462666556239128, "layer": 0.10680276341736317, "mlm": 1.592526137828827, "distill": 1.4441094100475311, "teacher_acc": 0.7498723566532135 }, { "step": 2481, "lr": 4.783863644106502e-05, "elapsed_s": 1847.3670659065247, "loss": 3.59833163022995, "hidden": 0.2421642579138279, "layer": 0.10684924758970737, "mlm": 1.6500813364982605, "distill": 1.4104971587657928, "teacher_acc": 0.7275962233543396 }, { "step": 2491, "lr": 4.781811256550023e-05, "elapsed_s": 1854.78395485878, "loss": 3.68978214263916, "hidden": 0.24138816446065903, "layer": 0.10864538140594959, "mlm": 1.6910502314567566, "distill": 1.4616328477859497, "teacher_acc": 0.7209601551294327 }, { "step": 2501, "lr": 4.7797496149802256e-05, "elapsed_s": 1862.185598373413, "loss": 3.7686917781829834, "hidden": 0.24645867198705673, "layer": 0.10835725255310535, "mlm": 1.7570590674877167, "distill": 1.4645367860794067, "teacher_acc": 0.7163214534521103 }, { "step": 2511, "lr": 4.7776787277582134e-05, "elapsed_s": 1869.598785161972, "loss": 3.7397080659866333, "hidden": 0.24499952048063278, "layer": 0.10806623473763466, "mlm": 1.7814353108406067, "distill": 1.4142406284809113, "teacher_acc": 0.7064929753541946 }, { "step": 2521, "lr": 4.7755986032825864e-05, "elapsed_s": 1876.9911653995514, "loss": 3.681542158126831, "hidden": 0.2533358745276928, "layer": 0.10940774530172348, "mlm": 1.6334728002548218, "distill": 1.4866937398910522, "teacher_acc": 0.7419825494289398 }, { "step": 2531, "lr": 4.773509249989406e-05, "elapsed_s": 1884.4329330921173, "loss": 3.831621766090393, "hidden": 0.24358056858181953, "layer": 0.10879357345402241, "mlm": 1.7595036327838898, "distill": 1.5305601954460144, "teacher_acc": 0.7233162820339203 }, { "step": 2541, "lr": 4.771410676352159e-05, "elapsed_s": 1891.8787107467651, "loss": 3.644809365272522, "hidden": 0.24500878155231476, "layer": 0.10855513252317905, "mlm": 1.5861805379390717, "distill": 1.514333724975586, "teacher_acc": 0.7467977553606033 }, { "step": 2551, "lr": 4.7693028908817315e-05, "elapsed_s": 1899.2731022834778, "loss": 3.6844981908798218, "hidden": 0.24672172591090202, "layer": 0.10882776416838169, "mlm": 1.7102844417095184, "distill": 1.4263564050197601, "teacher_acc": 0.7162268310785294 }, { "step": 2561, "lr": 4.767185902126364e-05, "elapsed_s": 1906.6529474258423, "loss": 3.5618661642074585, "hidden": 0.2363271489739418, "layer": 0.10503928922116756, "mlm": 1.7053262293338776, "distill": 1.3313659131526947, "teacher_acc": 0.7192791402339935 }, { "step": 2571, "lr": 4.765059718671623e-05, "elapsed_s": 1914.0563731193542, "loss": 3.596912682056427, "hidden": 0.24243199452757835, "layer": 0.10740852542221546, "mlm": 1.6463701725006104, "distill": 1.411974310874939, "teacher_acc": 0.7432228177785873 }, { "step": 2581, "lr": 4.7629243491403636e-05, "elapsed_s": 1921.4137330055237, "loss": 3.560342848300934, "hidden": 0.23930377885699272, "layer": 0.10598771274089813, "mlm": 1.674494743347168, "distill": 1.354246735572815, "teacher_acc": 0.7177818864583969 }, { "step": 2591, "lr": 4.760779802192698e-05, "elapsed_s": 1928.7610535621643, "loss": 3.5935680866241455, "hidden": 0.23820922896265984, "layer": 0.10677331313490868, "mlm": 1.6324653327465057, "distill": 1.4312976002693176, "teacher_acc": 0.7370318174362183 }, { "step": 2601, "lr": 4.758626086525956e-05, "elapsed_s": 1936.1127738952637, "loss": 3.7478145956993103, "hidden": 0.24265775457024574, "layer": 0.10825501941144466, "mlm": 1.800310879945755, "distill": 1.4080606698989868, "teacher_acc": 0.7111178785562515 }, { "step": 2611, "lr": 4.756463210874652e-05, "elapsed_s": 1943.4745259284973, "loss": 3.5550922751426697, "hidden": 0.2391643114387989, "layer": 0.1057338397949934, "mlm": 1.5180002450942993, "distill": 1.505896508693695, "teacher_acc": 0.7615246325731277 }, { "step": 2621, "lr": 4.754291184010449e-05, "elapsed_s": 1950.8625221252441, "loss": 3.58420729637146, "hidden": 0.23577246069908142, "layer": 0.10539300180971622, "mlm": 1.6794508397579193, "distill": 1.3805151283740997, "teacher_acc": 0.7280884981155396 }, { "step": 2631, "lr": 4.752110014742124e-05, "elapsed_s": 1958.2600302696228, "loss": 3.723642945289612, "hidden": 0.23914989084005356, "layer": 0.10667040199041367, "mlm": 1.7678002715110779, "distill": 1.4242076575756073, "teacher_acc": 0.7110923379659653 }, { "step": 2641, "lr": 4.74991971191553e-05, "elapsed_s": 1965.6535589694977, "loss": 3.7126502990722656, "hidden": 0.24177956208586693, "layer": 0.10700585879385471, "mlm": 1.693537563085556, "distill": 1.4820507764816284, "teacher_acc": 0.7239854037761688 }, { "step": 2651, "lr": 4.7477202844135646e-05, "elapsed_s": 1973.0942614078522, "loss": 3.5955039262771606, "hidden": 0.24167544767260551, "layer": 0.10688715986907482, "mlm": 1.6716265976428986, "distill": 1.3870827853679657, "teacher_acc": 0.7232551872730255 }, { "step": 2661, "lr": 4.745511741156129e-05, "elapsed_s": 1980.5191600322723, "loss": 3.6259926557540894, "hidden": 0.23596793040633202, "layer": 0.10512718930840492, "mlm": 1.69126096367836, "distill": 1.410232275724411, "teacher_acc": 0.722245380282402 }, { "step": 2671, "lr": 4.7432940911000923e-05, "elapsed_s": 1987.9092147350311, "loss": 3.6282278299331665, "hidden": 0.2408795990049839, "layer": 0.10780544392764568, "mlm": 1.6640565395355225, "distill": 1.4285092949867249, "teacher_acc": 0.7319728881120682 }, { "step": 2681, "lr": 4.7410673432392596e-05, "elapsed_s": 1995.3141012191772, "loss": 3.5768274664878845, "hidden": 0.23598787188529968, "layer": 0.10724631138145924, "mlm": 1.678175687789917, "distill": 1.3730529248714447, "teacher_acc": 0.7206576019525528 }, { "step": 2691, "lr": 4.738831506604332e-05, "elapsed_s": 2002.7380542755127, "loss": 3.7140308022499084, "hidden": 0.242545984685421, "layer": 0.10712094977498055, "mlm": 1.7198494672775269, "distill": 1.4555288255214691, "teacher_acc": 0.7228926718235016 }, { "step": 2701, "lr": 4.7365865902628684e-05, "elapsed_s": 2010.1523413658142, "loss": 3.4395722150802612, "hidden": 0.23167967796325684, "layer": 0.10434584505856037, "mlm": 1.6193323731422424, "distill": 1.304707556962967, "teacher_acc": 0.7343793958425522 }, { "step": 2711, "lr": 4.734332603319255e-05, "elapsed_s": 2017.5735819339752, "loss": 3.6597050428390503, "hidden": 0.23803844302892685, "layer": 0.10731230489909649, "mlm": 1.6911435723304749, "distill": 1.4388284981250763, "teacher_acc": 0.7284220308065414 }, { "step": 2721, "lr": 4.732069554914661e-05, "elapsed_s": 2024.9937336444855, "loss": 3.6472243070602417, "hidden": 0.2409161627292633, "layer": 0.10627330653369427, "mlm": 1.7463038265705109, "distill": 1.3659515082836151, "teacher_acc": 0.7127766609191895 }, { "step": 2731, "lr": 4.7297974542270055e-05, "elapsed_s": 2032.4183926582336, "loss": 3.631434142589569, "hidden": 0.238052599132061, "layer": 0.10654278472065926, "mlm": 1.633485198020935, "distill": 1.4685722887516022, "teacher_acc": 0.7346589714288712 }, { "step": 2741, "lr": 4.72751631047092e-05, "elapsed_s": 2039.7783660888672, "loss": 3.6866583228111267, "hidden": 0.23772570863366127, "layer": 0.10672623664140701, "mlm": 1.7171207964420319, "distill": 1.4407230019569397, "teacher_acc": 0.7275938540697098 }, { "step": 2751, "lr": 4.7252261328977115e-05, "elapsed_s": 2047.1711785793304, "loss": 3.6036709547042847, "hidden": 0.2395215667784214, "layer": 0.10622072778642178, "mlm": 1.6842427849769592, "distill": 1.3872746229171753, "teacher_acc": 0.7253856509923935 }, { "step": 2761, "lr": 4.7229269307953235e-05, "elapsed_s": 2054.5901930332184, "loss": 3.532498836517334, "hidden": 0.23626259714365005, "layer": 0.10546763986349106, "mlm": 1.6397127211093903, "distill": 1.3675271570682526, "teacher_acc": 0.733916237950325 }, { "step": 2771, "lr": 4.7206187134882977e-05, "elapsed_s": 2061.9925315380096, "loss": 3.5738848447799683, "hidden": 0.2349291294813156, "layer": 0.10499691031873226, "mlm": 1.6095466613769531, "distill": 1.4419815242290497, "teacher_acc": 0.7304109036922455 }, { "step": 2781, "lr": 4.71830149033774e-05, "elapsed_s": 2069.407297849655, "loss": 3.580619513988495, "hidden": 0.23565727844834328, "layer": 0.10646986775100231, "mlm": 1.6680371761322021, "distill": 1.3880327939987183, "teacher_acc": 0.72722327709198 }, { "step": 2791, "lr": 4.715975270741278e-05, "elapsed_s": 2076.8249473571777, "loss": 3.5825352668762207, "hidden": 0.23516757041215897, "layer": 0.10478775762021542, "mlm": 1.6737564504146576, "distill": 1.3860498070716858, "teacher_acc": 0.7210666686296463 }, { "step": 2801, "lr": 4.713640064133025e-05, "elapsed_s": 2084.247176170349, "loss": 3.664033591747284, "hidden": 0.23736470565199852, "layer": 0.10661087185144424, "mlm": 1.7583079040050507, "distill": 1.3776907324790955, "teacher_acc": 0.7080092877149582 }, { "step": 2811, "lr": 4.7112958799835424e-05, "elapsed_s": 2091.6675131320953, "loss": 3.617379665374756, "hidden": 0.2411416582763195, "layer": 0.10608030296862125, "mlm": 1.659661889076233, "distill": 1.4223942756652832, "teacher_acc": 0.7266990840435028 }, { "step": 2821, "lr": 4.708942727799801e-05, "elapsed_s": 2099.090729236603, "loss": 3.5019719004631042, "hidden": 0.23186643049120903, "layer": 0.1036705020815134, "mlm": 1.6292818784713745, "distill": 1.3571219742298126, "teacher_acc": 0.7291790544986725 }, { "step": 2831, "lr": 4.7065806171251416e-05, "elapsed_s": 2106.4805195331573, "loss": 3.7564882040023804, "hidden": 0.24046286568045616, "layer": 0.10817813500761986, "mlm": 1.7259016036987305, "distill": 1.4955718219280243, "teacher_acc": 0.7274407595396042 }, { "step": 2841, "lr": 4.7042095575392355e-05, "elapsed_s": 2113.897171497345, "loss": 3.5006067156791687, "hidden": 0.23034659028053284, "layer": 0.10453379340469837, "mlm": 1.6120376884937286, "distill": 1.3756089806556702, "teacher_acc": 0.7391497492790222 }, { "step": 2851, "lr": 4.701829558658046e-05, "elapsed_s": 2121.3115117549896, "loss": 3.4552191495895386, "hidden": 0.2289695106446743, "layer": 0.10405125841498375, "mlm": 1.6536909639835358, "distill": 1.291563630104065, "teacher_acc": 0.7207521945238113 }, { "step": 2861, "lr": 4.699440630133794e-05, "elapsed_s": 2128.734341621399, "loss": 3.503120541572571, "hidden": 0.23052410408854485, "layer": 0.10387588478624821, "mlm": 1.6073122024536133, "distill": 1.3828222453594208, "teacher_acc": 0.7410666197538376 }, { "step": 2871, "lr": 4.697042781654913e-05, "elapsed_s": 2136.164852619171, "loss": 3.4902254343032837, "hidden": 0.23738359659910202, "layer": 0.10568131506443024, "mlm": 1.5749092996120453, "distill": 1.3877082765102386, "teacher_acc": 0.7454861998558044 }, { "step": 2881, "lr": 4.694636022946012e-05, "elapsed_s": 2143.6112546920776, "loss": 3.5363218784332275, "hidden": 0.23062248155474663, "layer": 0.10387315787374973, "mlm": 1.6959924399852753, "distill": 1.3271478712558746, "teacher_acc": 0.7219624519348145 }, { "step": 2891, "lr": 4.692220363767833e-05, "elapsed_s": 2151.0236394405365, "loss": 3.6036964058876038, "hidden": 0.22718659043312073, "layer": 0.10374492965638638, "mlm": 1.6717808544635773, "distill": 1.4256699681282043, "teacher_acc": 0.7323247045278549 }, { "step": 2901, "lr": 4.68979581391722e-05, "elapsed_s": 2158.429487466812, "loss": 3.61070054769516, "hidden": 0.23945430293679237, "layer": 0.10574058815836906, "mlm": 1.7240363359451294, "distill": 1.354885309934616, "teacher_acc": 0.7143816351890564 }, { "step": 2911, "lr": 4.687362383227069e-05, "elapsed_s": 2165.8093507289886, "loss": 3.6366803646087646, "hidden": 0.23762637376785278, "layer": 0.10596693865954876, "mlm": 1.7215954959392548, "distill": 1.3868486881256104, "teacher_acc": 0.7206857204437256 }, { "step": 2921, "lr": 4.684920081566295e-05, "elapsed_s": 2173.2271959781647, "loss": 3.4630767703056335, "hidden": 0.2299012504518032, "layer": 0.10233664326369762, "mlm": 1.6417950689792633, "distill": 1.3103108406066895, "teacher_acc": 0.7232145220041275 }, { "step": 2931, "lr": 4.68246891883979e-05, "elapsed_s": 2180.6168296337128, "loss": 3.502602696418762, "hidden": 0.23003851622343063, "layer": 0.10482638515532017, "mlm": 1.6567935347557068, "distill": 1.3333189189434052, "teacher_acc": 0.7252501547336578 }, { "step": 2941, "lr": 4.680008904988379e-05, "elapsed_s": 2188.0033230781555, "loss": 3.491953432559967, "hidden": 0.23427829891443253, "layer": 0.10359874926507473, "mlm": 1.606177419424057, "distill": 1.365420013666153, "teacher_acc": 0.7423140704631805 }, { "step": 2951, "lr": 4.677540049988789e-05, "elapsed_s": 2195.373770236969, "loss": 3.580929458141327, "hidden": 0.23450344428420067, "layer": 0.10556199587881565, "mlm": 1.7018214762210846, "distill": 1.357320100069046, "teacher_acc": 0.7183585315942764 }, { "step": 2961, "lr": 4.6750623638535986e-05, "elapsed_s": 2202.7666988372803, "loss": 3.5984174013137817, "hidden": 0.2290143482387066, "layer": 0.10321427136659622, "mlm": 1.6942948997020721, "distill": 1.394486665725708, "teacher_acc": 0.7126488238573074 }, { "step": 2971, "lr": 4.6725758566312016e-05, "elapsed_s": 2210.151052713394, "loss": 3.4650648832321167, "hidden": 0.2291531153023243, "layer": 0.10461174137890339, "mlm": 1.6531810462474823, "distill": 1.3012717366218567, "teacher_acc": 0.7204356491565704 }, { "step": 2981, "lr": 4.6700805384057687e-05, "elapsed_s": 2217.5151166915894, "loss": 3.5106738209724426, "hidden": 0.22873886302113533, "layer": 0.10297016426920891, "mlm": 1.6726548373699188, "distill": 1.3290561437606812, "teacher_acc": 0.721130445599556 }, { "step": 2991, "lr": 4.667576419297202e-05, "elapsed_s": 2224.8559131622314, "loss": 3.5212265253067017, "hidden": 0.22997724637389183, "layer": 0.10374366492033005, "mlm": 1.734131783246994, "distill": 1.275268316268921, "teacher_acc": 0.702075332403183 }, { "step": 3001, "lr": 4.665063509461097e-05, "elapsed_s": 2234.205440759659, "loss": 3.4606210589408875, "hidden": 0.22931714355945587, "layer": 0.10343053191900253, "mlm": 1.6665265560150146, "distill": 1.2837449610233307, "teacher_acc": 0.7193577736616135 }, { "step": 3011, "lr": 4.6625418190887e-05, "elapsed_s": 2241.529851436615, "loss": 3.3743128180503845, "hidden": 0.2232120931148529, "layer": 0.10135133564472198, "mlm": 1.6456921696662903, "distill": 1.2315207719802856, "teacher_acc": 0.7201991677284241 }, { "step": 3021, "lr": 4.660011358406867e-05, "elapsed_s": 2248.904124736786, "loss": 3.508089780807495, "hidden": 0.2337881326675415, "layer": 0.10397909954190254, "mlm": 1.649567037820816, "distill": 1.3389569222927094, "teacher_acc": 0.7356233596801758 }, { "step": 3031, "lr": 4.657472137678024e-05, "elapsed_s": 2256.288508415222, "loss": 3.4837343096733093, "hidden": 0.22679223120212555, "layer": 0.10177144408226013, "mlm": 1.6783565282821655, "distill": 1.3009076118469238, "teacher_acc": 0.7154030948877335 }, { "step": 3041, "lr": 4.654924167200123e-05, "elapsed_s": 2263.6509714126587, "loss": 3.561523973941803, "hidden": 0.22662726417183876, "layer": 0.103306595236063, "mlm": 1.6692866086959839, "distill": 1.387329488992691, "teacher_acc": 0.7342425137758255 }, { "step": 3051, "lr": 4.6523674573066e-05, "elapsed_s": 2271.039669275284, "loss": 3.491649568080902, "hidden": 0.22500937804579735, "layer": 0.1024861540645361, "mlm": 1.6900636851787567, "distill": 1.3003240823745728, "teacher_acc": 0.7152795344591141 }, { "step": 3061, "lr": 4.649802018366336e-05, "elapsed_s": 2278.450541496277, "loss": 3.50148206949234, "hidden": 0.22964788973331451, "layer": 0.10274216905236244, "mlm": 1.6394510567188263, "distill": 1.3513641059398651, "teacher_acc": 0.7282019257545471 }, { "step": 3071, "lr": 4.647227860783612e-05, "elapsed_s": 2285.81498336792, "loss": 3.4740242958068848, "hidden": 0.2279980257153511, "layer": 0.10369544290006161, "mlm": 1.6022800505161285, "distill": 1.3639004528522491, "teacher_acc": 0.7424096465110779 }, { "step": 3081, "lr": 4.6446449949980665e-05, "elapsed_s": 2293.2138237953186, "loss": 3.6519100666046143, "hidden": 0.23669841513037682, "layer": 0.10585329681634903, "mlm": 1.7092592120170593, "distill": 1.416327327489853, "teacher_acc": 0.7229047417640686 }, { "step": 3091, "lr": 4.6420534314846585e-05, "elapsed_s": 2300.6238343715668, "loss": 3.3918741941452026, "hidden": 0.2239185944199562, "layer": 0.10104312188923359, "mlm": 1.6155100166797638, "distill": 1.2780054807662964, "teacher_acc": 0.723976656794548 }, { "step": 3101, "lr": 4.639453180753619e-05, "elapsed_s": 2308.028860092163, "loss": 3.4800446033477783, "hidden": 0.22441308945417404, "layer": 0.10252377390861511, "mlm": 1.665266752243042, "distill": 1.314689815044403, "teacher_acc": 0.7118273973464966 }, { "step": 3111, "lr": 4.63684425335041e-05, "elapsed_s": 2315.443920135498, "loss": 3.657502770423889, "hidden": 0.2322998382151127, "layer": 0.10514740087091923, "mlm": 1.7614023685455322, "distill": 1.3789271116256714, "teacher_acc": 0.7034724950790405 }, { "step": 3121, "lr": 4.6342266598556814e-05, "elapsed_s": 2322.8459804058075, "loss": 3.4586631059646606, "hidden": 0.23120060935616493, "layer": 0.10307871177792549, "mlm": 1.5992388129234314, "distill": 1.3454837501049042, "teacher_acc": 0.7405604720115662 }, { "step": 3131, "lr": 4.6316004108852305e-05, "elapsed_s": 2330.2439291477203, "loss": 3.499767541885376, "hidden": 0.2233915477991104, "layer": 0.10289429314434528, "mlm": 1.7268340587615967, "distill": 1.2747032344341278, "teacher_acc": 0.7004177868366241 }, { "step": 3141, "lr": 4.628965517089959e-05, "elapsed_s": 2337.658492088318, "loss": 3.5173186659812927, "hidden": 0.222753643989563, "layer": 0.10281359776854515, "mlm": 1.699946105480194, "distill": 1.3204584121704102, "teacher_acc": 0.7086157202720642 }, { "step": 3151, "lr": 4.6263219891558244e-05, "elapsed_s": 2345.087569952011, "loss": 3.600011706352234, "hidden": 0.22582751885056496, "layer": 0.10341009870171547, "mlm": 1.6581669747829437, "distill": 1.4384846985340118, "teacher_acc": 0.729967474937439 }, { "step": 3161, "lr": 4.6236698378038026e-05, "elapsed_s": 2352.4644508361816, "loss": 3.5091535449028015, "hidden": 0.23309017717838287, "layer": 0.10450707748532295, "mlm": 1.71028670668602, "distill": 1.2804329693317413, "teacher_acc": 0.7077615112066269 }, { "step": 3171, "lr": 4.621009073789842e-05, "elapsed_s": 2359.8673663139343, "loss": 3.527905583381653, "hidden": 0.22566555440425873, "layer": 0.10294582508504391, "mlm": 1.7181035280227661, "distill": 1.3069979846477509, "teacher_acc": 0.7122737467288971 }, { "step": 3181, "lr": 4.6183397079048205e-05, "elapsed_s": 2367.3015348911285, "loss": 3.487317204475403, "hidden": 0.23124703019857407, "layer": 0.10366122610867023, "mlm": 1.6682642698287964, "distill": 1.3047282695770264, "teacher_acc": 0.7175710648298264 }, { "step": 3191, "lr": 4.6156617509745015e-05, "elapsed_s": 2374.7088572978973, "loss": 3.4809818863868713, "hidden": 0.2208900861442089, "layer": 0.10162181593477726, "mlm": 1.6904520690441132, "distill": 1.2979387044906616, "teacher_acc": 0.7137667089700699 }, { "step": 3201, "lr": 4.6129752138594874e-05, "elapsed_s": 2382.118670463562, "loss": 3.4504796862602234, "hidden": 0.22447019815444946, "layer": 0.10228989645838737, "mlm": 1.6588618755340576, "distill": 1.2915324866771698, "teacher_acc": 0.7179579138755798 }, { "step": 3211, "lr": 4.6102801074551806e-05, "elapsed_s": 2389.5258524417877, "loss": 3.5374115705490112, "hidden": 0.2326372191309929, "layer": 0.10468166880309582, "mlm": 1.6603041291236877, "distill": 1.3594921231269836, "teacher_acc": 0.730151355266571 }, { "step": 3221, "lr": 4.607576442691737e-05, "elapsed_s": 2396.93758225441, "loss": 3.565000891685486, "hidden": 0.2248787060379982, "layer": 0.10271011479198933, "mlm": 1.697321355342865, "distill": 1.366567075252533, "teacher_acc": 0.721306636929512 }, { "step": 3231, "lr": 4.6048642305340185e-05, "elapsed_s": 2404.342048406601, "loss": 3.4903936982154846, "hidden": 0.22763410210609436, "layer": 0.10249729081988335, "mlm": 1.6350296139717102, "distill": 1.3488471806049347, "teacher_acc": 0.7368521392345428 }, { "step": 3241, "lr": 4.6021434819815555e-05, "elapsed_s": 2411.7597846984863, "loss": 3.5416045784950256, "hidden": 0.2282167673110962, "layer": 0.1037945169955492, "mlm": 1.6292797923088074, "distill": 1.4039939641952515, "teacher_acc": 0.7344960719347 }, { "step": 3251, "lr": 4.599414208068495e-05, "elapsed_s": 2419.182558774948, "loss": 3.419649362564087, "hidden": 0.23007922992110252, "layer": 0.10282059572637081, "mlm": 1.5672361552715302, "distill": 1.3408444821834564, "teacher_acc": 0.7406398355960846 }, { "step": 3261, "lr": 4.5966764198635606e-05, "elapsed_s": 2426.5875005722046, "loss": 3.4718623757362366, "hidden": 0.22298796847462654, "layer": 0.10260258428752422, "mlm": 1.672924816608429, "distill": 1.3016604483127594, "teacher_acc": 0.7142860144376755 }, { "step": 3271, "lr": 4.593930128470005e-05, "elapsed_s": 2433.978696346283, "loss": 3.5107290148735046, "hidden": 0.2212652713060379, "layer": 0.10115457512438297, "mlm": 1.715896487236023, "distill": 1.3017246723175049, "teacher_acc": 0.7148478478193283 }, { "step": 3281, "lr": 4.5911753450255665e-05, "elapsed_s": 2441.3789868354797, "loss": 3.58910071849823, "hidden": 0.23301169648766518, "layer": 0.10499644093215466, "mlm": 1.6986188292503357, "distill": 1.3719602227210999, "teacher_acc": 0.7117029875516891 }, { "step": 3291, "lr": 4.588412080702426e-05, "elapsed_s": 2448.7913999557495, "loss": 3.372100532054901, "hidden": 0.22256171703338623, "layer": 0.10064934007823467, "mlm": 1.607201725244522, "distill": 1.269450694322586, "teacher_acc": 0.7256952226161957 }, { "step": 3301, "lr": 4.5856403467071536e-05, "elapsed_s": 2456.2188000679016, "loss": 3.4336293935775757, "hidden": 0.22901742160320282, "layer": 0.10366160608828068, "mlm": 1.6359600722789764, "distill": 1.2878036499023438, "teacher_acc": 0.7136553823947906 }, { "step": 3311, "lr": 4.582860154280674e-05, "elapsed_s": 2463.6272122859955, "loss": 3.544716000556946, "hidden": 0.22044740244746208, "layer": 0.10249673761427402, "mlm": 1.694400042295456, "distill": 1.35817289352417, "teacher_acc": 0.7168470919132233 }, { "step": 3321, "lr": 4.580071514698211e-05, "elapsed_s": 2471.0372614860535, "loss": 3.3085479736328125, "hidden": 0.22407560795545578, "layer": 0.10275277495384216, "mlm": 1.5773303806781769, "distill": 1.231689989566803, "teacher_acc": 0.7351345121860504 }, { "step": 3331, "lr": 4.57727443926925e-05, "elapsed_s": 2478.4736206531525, "loss": 3.402520477771759, "hidden": 0.22688784077763557, "layer": 0.10335866920650005, "mlm": 1.5565273761749268, "distill": 1.340538114309311, "teacher_acc": 0.7515149861574173 }, { "step": 3341, "lr": 4.574468939337488e-05, "elapsed_s": 2485.8861334323883, "loss": 3.4884793162345886, "hidden": 0.2202131226658821, "layer": 0.10254723206162453, "mlm": 1.7354383170604706, "distill": 1.2613410651683807, "teacher_acc": 0.7056065946817398 }, { "step": 3351, "lr": 4.5716550262807854e-05, "elapsed_s": 2493.276671886444, "loss": 3.4397005438804626, "hidden": 0.22360840439796448, "layer": 0.10160521231591702, "mlm": 1.643522322177887, "distill": 1.2981588542461395, "teacher_acc": 0.7268181294202805 }, { "step": 3361, "lr": 4.568832711511125e-05, "elapsed_s": 2500.6512598991394, "loss": 3.588262915611267, "hidden": 0.2267148718237877, "layer": 0.10242516919970512, "mlm": 1.7419219017028809, "distill": 1.3416987359523773, "teacher_acc": 0.7026091068983078 }, { "step": 3371, "lr": 4.566002006474562e-05, "elapsed_s": 2508.05770945549, "loss": 3.514046549797058, "hidden": 0.23101866617798805, "layer": 0.10360232181847095, "mlm": 1.5809781551361084, "distill": 1.4192299246788025, "teacher_acc": 0.7460936456918716 }, { "step": 3381, "lr": 4.563162922651179e-05, "elapsed_s": 2515.4639484882355, "loss": 3.515875220298767, "hidden": 0.22301653772592545, "layer": 0.10282004997134209, "mlm": 1.6879366040229797, "distill": 1.3304955065250397, "teacher_acc": 0.7279070913791656 }, { "step": 3391, "lr": 4.5603154715550386e-05, "elapsed_s": 2522.895223379135, "loss": 3.4018912315368652, "hidden": 0.2239724136888981, "layer": 0.10192890465259552, "mlm": 1.6196550130844116, "distill": 1.2833269238471985, "teacher_acc": 0.7178000658750534 }, { "step": 3401, "lr": 4.557459664734141e-05, "elapsed_s": 2530.280441761017, "loss": 3.522800087928772, "hidden": 0.226976927369833, "layer": 0.10235772281885147, "mlm": 1.6863990128040314, "distill": 1.3312683999538422, "teacher_acc": 0.7239378839731216 }, { "step": 3411, "lr": 4.554595513770369e-05, "elapsed_s": 2537.67915892601, "loss": 3.5089078545570374, "hidden": 0.222249835729599, "layer": 0.10050370916724205, "mlm": 1.7329918444156647, "distill": 1.2811645567417145, "teacher_acc": 0.7053619176149368 }, { "step": 3421, "lr": 4.551723030279446e-05, "elapsed_s": 2545.1264295578003, "loss": 3.35947984457016, "hidden": 0.2204466313123703, "layer": 0.10075901821255684, "mlm": 1.581898272037506, "distill": 1.2863087356090546, "teacher_acc": 0.7301050275564194 }, { "step": 3431, "lr": 4.5488422259108907e-05, "elapsed_s": 2552.5427136421204, "loss": 3.3932032585144043, "hidden": 0.221500676125288, "layer": 0.10246274806559086, "mlm": 1.6904788613319397, "distill": 1.2084916830062866, "teacher_acc": 0.7053885459899902 }, { "step": 3441, "lr": 4.5459531123479676e-05, "elapsed_s": 2559.929175376892, "loss": 3.4944602847099304, "hidden": 0.23181834071874619, "layer": 0.10496977902948856, "mlm": 1.6038219034671783, "distill": 1.3745166659355164, "teacher_acc": 0.7321884483098984 }, { "step": 3451, "lr": 4.543055701307637e-05, "elapsed_s": 2567.320256948471, "loss": 3.3996405005455017, "hidden": 0.21922963112592697, "layer": 0.09974186681210995, "mlm": 1.6947680413722992, "distill": 1.2165422439575195, "teacher_acc": 0.7056132704019547 }, { "step": 3461, "lr": 4.540150004540512e-05, "elapsed_s": 2574.717602491379, "loss": 3.432230234146118, "hidden": 0.22933698445558548, "layer": 0.10330581292510033, "mlm": 1.5856387317180634, "distill": 1.3362646400928497, "teacher_acc": 0.7384810149669647 }, { "step": 3471, "lr": 4.537236033830809e-05, "elapsed_s": 2582.1194155216217, "loss": 3.3968421816825867, "hidden": 0.2132473811507225, "layer": 0.10007931850850582, "mlm": 1.6304021775722504, "distill": 1.2899055182933807, "teacher_acc": 0.7273385524749756 }, { "step": 3481, "lr": 4.534313800996299e-05, "elapsed_s": 2589.542094707489, "loss": 3.440521001815796, "hidden": 0.22472675889730453, "layer": 0.10329141095280647, "mlm": 1.676109790802002, "distill": 1.2633121013641357, "teacher_acc": 0.7177644520998001 }, { "step": 3491, "lr": 4.531383317888261e-05, "elapsed_s": 2596.9556863307953, "loss": 3.3939183950424194, "hidden": 0.21635373309254646, "layer": 0.10069276764988899, "mlm": 1.615008682012558, "distill": 1.2958558201789856, "teacher_acc": 0.7311837375164032 }, { "step": 3501, "lr": 4.528444596391433e-05, "elapsed_s": 2604.3900628089905, "loss": 3.3732004165649414, "hidden": 0.22191773727536201, "layer": 0.10196337662637234, "mlm": 1.5925023257732391, "distill": 1.2858809530735016, "teacher_acc": 0.7350538969039917 }, { "step": 3511, "lr": 4.525497648423964e-05, "elapsed_s": 2611.8201043605804, "loss": 3.463964104652405, "hidden": 0.21726492419838905, "layer": 0.10132593661546707, "mlm": 1.7119967937469482, "distill": 1.2667745351791382, "teacher_acc": 0.7097632735967636 }, { "step": 3521, "lr": 4.522542485937369e-05, "elapsed_s": 2619.2207708358765, "loss": 3.4572603702545166, "hidden": 0.2189236804842949, "layer": 0.10150349326431751, "mlm": 1.7127948105335236, "distill": 1.2558664083480835, "teacher_acc": 0.7084037959575653 }, { "step": 3531, "lr": 4.519579120916472e-05, "elapsed_s": 2626.6420307159424, "loss": 3.395686447620392, "hidden": 0.2208048291504383, "layer": 0.10194237530231476, "mlm": 1.632282555103302, "distill": 1.2708231210708618, "teacher_acc": 0.7240957915782928 }, { "step": 3541, "lr": 4.5166075653793676e-05, "elapsed_s": 2634.0398409366608, "loss": 3.405287504196167, "hidden": 0.21933967620134354, "layer": 0.10075551457703114, "mlm": 1.6624489724636078, "distill": 1.2537815570831299, "teacher_acc": 0.7112442851066589 }, { "step": 3551, "lr": 4.513627831377365e-05, "elapsed_s": 2641.4800169467926, "loss": 3.2774580121040344, "hidden": 0.21580269187688828, "layer": 0.10005523264408112, "mlm": 1.5768791139125824, "distill": 1.218945860862732, "teacher_acc": 0.7273680418729782 }, { "step": 3561, "lr": 4.510639930994942e-05, "elapsed_s": 2648.9230070114136, "loss": 3.535762667655945, "hidden": 0.22324201837182045, "layer": 0.10037110559642315, "mlm": 1.769502580165863, "distill": 1.2695905268192291, "teacher_acc": 0.7000212669372559 }, { "step": 3571, "lr": 4.507643876349698e-05, "elapsed_s": 2656.34974527359, "loss": 3.3849878907203674, "hidden": 0.22146416455507278, "layer": 0.1014827024191618, "mlm": 1.613898128271103, "distill": 1.2774201035499573, "teacher_acc": 0.7219107449054718 }, { "step": 3581, "lr": 4.5046396795922964e-05, "elapsed_s": 2663.7874853610992, "loss": 3.332967221736908, "hidden": 0.21942906081676483, "layer": 0.10010307841002941, "mlm": 1.6011481583118439, "distill": 1.242909461259842, "teacher_acc": 0.72371406853199 }, { "step": 3591, "lr": 4.501627352906429e-05, "elapsed_s": 2671.1968195438385, "loss": 3.43490993976593, "hidden": 0.2172873094677925, "layer": 0.09979121945798397, "mlm": 1.6759430766105652, "distill": 1.2744966447353363, "teacher_acc": 0.7079648226499557 }, { "step": 3601, "lr": 4.498606908508754e-05, "elapsed_s": 2678.596888780594, "loss": 3.4864338040351868, "hidden": 0.216410331428051, "layer": 0.10081839561462402, "mlm": 1.6856513917446136, "distill": 1.3175525069236755, "teacher_acc": 0.7179049700498581 }, { "step": 3611, "lr": 4.4955783586488514e-05, "elapsed_s": 2686.0373544692993, "loss": 3.3339715003967285, "hidden": 0.21926870197057724, "layer": 0.09914068505167961, "mlm": 1.645705908536911, "distill": 1.2001579105854034, "teacher_acc": 0.7183408141136169 }, { "step": 3621, "lr": 4.492541715609177e-05, "elapsed_s": 2693.4673421382904, "loss": 3.543579339981079, "hidden": 0.222660094499588, "layer": 0.10127940960228443, "mlm": 1.6892383396625519, "distill": 1.3583810925483704, "teacher_acc": 0.7298067510128021 }, { "step": 3631, "lr": 4.489496991705006e-05, "elapsed_s": 2700.8846101760864, "loss": 3.5348130464553833, "hidden": 0.2192484475672245, "layer": 0.10178992711007595, "mlm": 1.7294292449951172, "distill": 1.315991997718811, "teacher_acc": 0.7085979282855988 }, { "step": 3641, "lr": 4.486444199284386e-05, "elapsed_s": 2708.3243913650513, "loss": 3.4495468139648438, "hidden": 0.21626786515116692, "layer": 0.10042501240968704, "mlm": 1.7141005098819733, "distill": 1.2526980340480804, "teacher_acc": 0.7053470015525818 }, { "step": 3651, "lr": 4.4833833507280884e-05, "elapsed_s": 2715.731525659561, "loss": 3.2745672464370728, "hidden": 0.21886007115244865, "layer": 0.09998699836432934, "mlm": 1.607414722442627, "distill": 1.1794389188289642, "teacher_acc": 0.7276763916015625 }, { "step": 3661, "lr": 4.480314458449555e-05, "elapsed_s": 2723.1396899223328, "loss": 3.224293828010559, "hidden": 0.21279019862413406, "layer": 0.09969703480601311, "mlm": 1.5308388769626617, "distill": 1.218026041984558, "teacher_acc": 0.7359865456819534 }, { "step": 3671, "lr": 4.4772375348948514e-05, "elapsed_s": 2730.5405235290527, "loss": 3.4303205609321594, "hidden": 0.22217024862766266, "layer": 0.10104978643357754, "mlm": 1.6885684728622437, "distill": 1.2468867003917694, "teacher_acc": 0.7087351679801941 }, { "step": 3681, "lr": 4.4741525925426125e-05, "elapsed_s": 2737.9718265533447, "loss": 3.4497135281562805, "hidden": 0.2169898897409439, "layer": 0.10202844627201557, "mlm": 1.7016971409320831, "distill": 1.2630224227905273, "teacher_acc": 0.7157750129699707 }, { "step": 3691, "lr": 4.471059643903995e-05, "elapsed_s": 2745.4064025878906, "loss": 3.4879127740859985, "hidden": 0.2210364192724228, "layer": 0.10075599141418934, "mlm": 1.7257213592529297, "distill": 1.269740641117096, "teacher_acc": 0.7104261517524719 }, { "step": 3701, "lr": 4.4679587015226253e-05, "elapsed_s": 2752.8446593284607, "loss": 3.317773759365082, "hidden": 0.21198050305247307, "layer": 0.0990347359329462, "mlm": 1.612403392791748, "distill": 1.2318920195102692, "teacher_acc": 0.7241254895925522 }, { "step": 3711, "lr": 4.464849777974549e-05, "elapsed_s": 2760.2552025318146, "loss": 3.5187310576438904, "hidden": 0.22815653309226036, "layer": 0.10379868559539318, "mlm": 1.6347263753414154, "distill": 1.3757922053337097, "teacher_acc": 0.7245372980833054 }, { "step": 3721, "lr": 4.46173288586818e-05, "elapsed_s": 2767.6529121398926, "loss": 3.5593345761299133, "hidden": 0.22435739636421204, "layer": 0.10117137804627419, "mlm": 1.7613835334777832, "distill": 1.2986505031585693, "teacher_acc": 0.7059041857719421 }, { "step": 3731, "lr": 4.458608037844248e-05, "elapsed_s": 2775.083307981491, "loss": 3.3301835656166077, "hidden": 0.21828244253993034, "layer": 0.09901604987680912, "mlm": 1.6080121397972107, "distill": 1.2360985279083252, "teacher_acc": 0.7235274761915207 }, { "step": 3741, "lr": 4.455475246575749e-05, "elapsed_s": 2782.4781732559204, "loss": 3.484762966632843, "hidden": 0.2183942198753357, "layer": 0.10151520185172558, "mlm": 1.6876263320446014, "distill": 1.3095906376838684, "teacher_acc": 0.7111721634864807 }, { "step": 3751, "lr": 4.452334524767894e-05, "elapsed_s": 2789.8880689144135, "loss": 3.4765034317970276, "hidden": 0.22331636399030685, "layer": 0.10142433270812035, "mlm": 1.685680091381073, "distill": 1.2934783697128296, "teacher_acc": 0.7113285511732101 }, { "step": 3761, "lr": 4.449185885158056e-05, "elapsed_s": 2797.295140504837, "loss": 3.202395796775818, "hidden": 0.21051722019910812, "layer": 0.09814063087105751, "mlm": 1.5432848930358887, "distill": 1.189006119966507, "teacher_acc": 0.7244785130023956 }, { "step": 3771, "lr": 4.4460293405157196e-05, "elapsed_s": 2804.7213699817657, "loss": 3.422004997730255, "hidden": 0.215611781924963, "layer": 0.09998084418475628, "mlm": 1.6407859027385712, "distill": 1.3000050485134125, "teacher_acc": 0.7199901938438416 }, { "step": 3781, "lr": 4.442864903642428e-05, "elapsed_s": 2812.1592061519623, "loss": 3.3409595489501953, "hidden": 0.22222664579749107, "layer": 0.0999057237058878, "mlm": 1.5946301817893982, "distill": 1.2519233226776123, "teacher_acc": 0.7306882739067078 }, { "step": 3791, "lr": 4.439692587371731e-05, "elapsed_s": 2819.553843021393, "loss": 3.421941637992859, "hidden": 0.2181464582681656, "layer": 0.10009659826755524, "mlm": 1.6639005243778229, "distill": 1.2716999351978302, "teacher_acc": 0.7110802233219147 }, { "step": 3801, "lr": 4.436512404569136e-05, "elapsed_s": 2827.0108137130737, "loss": 3.4838470220565796, "hidden": 0.21770381927490234, "layer": 0.09972613863646984, "mlm": 1.6634467244148254, "distill": 1.3351296782493591, "teacher_acc": 0.7233183681964874 }, { "step": 3811, "lr": 4.4333243681320535e-05, "elapsed_s": 2834.431905269623, "loss": 3.407822072505951, "hidden": 0.2114402912557125, "layer": 0.09894207864999771, "mlm": 1.6837082207202911, "distill": 1.251762181520462, "teacher_acc": 0.7116187363862991 }, { "step": 3821, "lr": 4.430128490989742e-05, "elapsed_s": 2841.861021757126, "loss": 3.3526212573051453, "hidden": 0.2148815244436264, "layer": 0.09962364286184311, "mlm": 1.6373966038227081, "distill": 1.2356497943401337, "teacher_acc": 0.7233918309211731 }, { "step": 3831, "lr": 4.4269247861032614e-05, "elapsed_s": 2849.265626192093, "loss": 3.3154091238975525, "hidden": 0.20902447029948235, "layer": 0.09895804896950722, "mlm": 1.5924485623836517, "distill": 1.255432665348053, "teacher_acc": 0.728063628077507 }, { "step": 3841, "lr": 4.4237132664654154e-05, "elapsed_s": 2856.6546018123627, "loss": 3.248935580253601, "hidden": 0.2174443043768406, "layer": 0.0982291791588068, "mlm": 1.5518204867839813, "distill": 1.2131119668483734, "teacher_acc": 0.7329970300197601 }, { "step": 3851, "lr": 4.420493945100702e-05, "elapsed_s": 2864.039132118225, "loss": 3.241308331489563, "hidden": 0.21167390048503876, "layer": 0.09893447160720825, "mlm": 1.586848646402359, "distill": 1.1816445589065552, "teacher_acc": 0.7188943326473236 }, { "step": 3861, "lr": 4.417266835065259e-05, "elapsed_s": 2871.4359402656555, "loss": 3.520313799381256, "hidden": 0.22187251970171928, "layer": 0.10208077915012836, "mlm": 1.643601268529892, "distill": 1.3819271326065063, "teacher_acc": 0.7293011099100113 }, { "step": 3871, "lr": 4.414031949446812e-05, "elapsed_s": 2878.8153507709503, "loss": 3.3206436038017273, "hidden": 0.21320131793618202, "layer": 0.09920357540249825, "mlm": 1.609454721212387, "distill": 1.2351844012737274, "teacher_acc": 0.7314797937870026 }, { "step": 3881, "lr": 4.410789301364621e-05, "elapsed_s": 2886.2138121128082, "loss": 3.3598875403404236, "hidden": 0.20989752188324928, "layer": 0.10004802420735359, "mlm": 1.7030329406261444, "distill": 1.1870355904102325, "teacher_acc": 0.7016808539628983 }, { "step": 3891, "lr": 4.407538903969427e-05, "elapsed_s": 2893.605315923691, "loss": 3.3626590967178345, "hidden": 0.2143176905810833, "layer": 0.09860510751605034, "mlm": 1.6953279674053192, "distill": 1.1893931925296783, "teacher_acc": 0.7046426087617874 }, { "step": 3901, "lr": 4.404280770443398e-05, "elapsed_s": 2900.9553837776184, "loss": 3.2994500398635864, "hidden": 0.2169826552271843, "layer": 0.0994649063795805, "mlm": 1.5329503417015076, "distill": 1.2828018963336945, "teacher_acc": 0.7457766532897949 }, { "step": 3911, "lr": 4.401014914000078e-05, "elapsed_s": 2908.353337287903, "loss": 3.252126634120941, "hidden": 0.2164294384419918, "layer": 0.099966274574399, "mlm": 1.5539894998073578, "distill": 1.2152950465679169, "teacher_acc": 0.7420509904623032 }, { "step": 3921, "lr": 4.397741347884329e-05, "elapsed_s": 2915.753561258316, "loss": 3.4226454496383667, "hidden": 0.21871980279684067, "layer": 0.0997576005756855, "mlm": 1.6629964411258698, "distill": 1.2723305225372314, "teacher_acc": 0.713737279176712 }, { "step": 3931, "lr": 4.394460085372283e-05, "elapsed_s": 2923.082320690155, "loss": 3.3782944679260254, "hidden": 0.21189770475029945, "layer": 0.09814956411719322, "mlm": 1.6856461465358734, "distill": 1.2197779417037964, "teacher_acc": 0.7093459367752075 }, { "step": 3941, "lr": 4.391171139771284e-05, "elapsed_s": 2930.456774711609, "loss": 3.383235216140747, "hidden": 0.22015303745865822, "layer": 0.10052507556974888, "mlm": 1.6186807751655579, "distill": 1.2739859223365784, "teacher_acc": 0.7216889560222626 }, { "step": 3951, "lr": 4.3878745244198345e-05, "elapsed_s": 2937.8353567123413, "loss": 3.308003544807434, "hidden": 0.20746897533535957, "layer": 0.0978346262127161, "mlm": 1.6008215546607971, "distill": 1.2433266639709473, "teacher_acc": 0.7288355976343155 }, { "step": 3961, "lr": 4.384570252687542e-05, "elapsed_s": 2945.21405005455, "loss": 3.355210840702057, "hidden": 0.21652409434318542, "layer": 0.10084827803075314, "mlm": 1.586410015821457, "distill": 1.2853285372257233, "teacher_acc": 0.7303088307380676 }, { "step": 3971, "lr": 4.381258337975067e-05, "elapsed_s": 2952.630339384079, "loss": 3.3217382431030273, "hidden": 0.22013549134135246, "layer": 0.10000970214605331, "mlm": 1.5553718507289886, "distill": 1.2760905921459198, "teacher_acc": 0.7345653772354126 }, { "step": 3981, "lr": 4.377938793714064e-05, "elapsed_s": 2959.989623785019, "loss": 3.299283027648926, "hidden": 0.2244243435561657, "layer": 0.10162552073597908, "mlm": 1.463464081287384, "distill": 1.3361575305461884, "teacher_acc": 0.7579145282506943 }, { "step": 3991, "lr": 4.374611633367131e-05, "elapsed_s": 2967.376202583313, "loss": 3.354050636291504, "hidden": 0.21034714207053185, "layer": 0.09840697795152664, "mlm": 1.5843153893947601, "distill": 1.2998374700546265, "teacher_acc": 0.7269056886434555 }, { "step": 4001, "lr": 4.371276870427753e-05, "elapsed_s": 2976.8022191524506, "loss": 3.4065189957618713, "hidden": 0.21879760175943375, "layer": 0.10035175643861294, "mlm": 1.6638438999652863, "distill": 1.2549039721488953, "teacher_acc": 0.7246548235416412 }, { "step": 4011, "lr": 4.367934518420248e-05, "elapsed_s": 2984.1852300167084, "loss": 3.2665358781814575, "hidden": 0.21697533503174782, "layer": 0.09944034181535244, "mlm": 1.5963473916053772, "distill": 1.1865175664424896, "teacher_acc": 0.7277026772499084 }, { "step": 4021, "lr": 4.364584590899711e-05, "elapsed_s": 2991.5832533836365, "loss": 3.410503387451172, "hidden": 0.21479737758636475, "layer": 0.09951872564852238, "mlm": 1.6750191450119019, "distill": 1.2561302185058594, "teacher_acc": 0.720388725399971 }, { "step": 4031, "lr": 4.361227101451961e-05, "elapsed_s": 2999.0009472370148, "loss": 3.312085449695587, "hidden": 0.21299812942743301, "layer": 0.09873082488775253, "mlm": 1.61012402176857, "distill": 1.2265998125076294, "teacher_acc": 0.7221582680940628 }, { "step": 4041, "lr": 4.357862063693486e-05, "elapsed_s": 3006.4044857025146, "loss": 3.223383128643036, "hidden": 0.21718934550881386, "layer": 0.09884579107165337, "mlm": 1.575249046087265, "distill": 1.1643324792385101, "teacher_acc": 0.728322833776474 }, { "step": 4051, "lr": 4.354489491271383e-05, "elapsed_s": 3013.804839849472, "loss": 3.3336254358291626, "hidden": 0.21119142323732376, "layer": 0.09988928958773613, "mlm": 1.6594502627849579, "distill": 1.2018478214740753, "teacher_acc": 0.7138727158308029 }, { "step": 4061, "lr": 4.351109397863309e-05, "elapsed_s": 3021.226651906967, "loss": 3.4135611057281494, "hidden": 0.21501441299915314, "layer": 0.09955957159399986, "mlm": 1.68215212225914, "distill": 1.2516002655029297, "teacher_acc": 0.7062650769948959 }, { "step": 4071, "lr": 4.347721797177421e-05, "elapsed_s": 3028.6435391902924, "loss": 3.3159769773483276, "hidden": 0.2130233719944954, "layer": 0.0983841959387064, "mlm": 1.632628321647644, "distill": 1.2081098556518555, "teacher_acc": 0.7096691131591797 }, { "step": 4081, "lr": 4.344326702952326e-05, "elapsed_s": 3036.04949426651, "loss": 3.4724360704421997, "hidden": 0.21528591215610504, "layer": 0.09992446936666965, "mlm": 1.6721459925174713, "distill": 1.3197560608386993, "teacher_acc": 0.713673546910286 }, { "step": 4091, "lr": 4.3409241289570156e-05, "elapsed_s": 3043.4487726688385, "loss": 3.324856400489807, "hidden": 0.21483539789915085, "layer": 0.10057331807911396, "mlm": 1.5940937995910645, "distill": 1.2508050501346588, "teacher_acc": 0.7296435534954071 }, { "step": 4101, "lr": 4.337514088990822e-05, "elapsed_s": 3050.8427596092224, "loss": 3.2056392431259155, "hidden": 0.20962658524513245, "layer": 0.09801270067691803, "mlm": 1.5612215399742126, "distill": 1.1761581897735596, "teacher_acc": 0.7227577120065689 }, { "step": 4111, "lr": 4.3340965968833515e-05, "elapsed_s": 3058.261877298355, "loss": 3.2095713019371033, "hidden": 0.20669924467802048, "layer": 0.09755269065499306, "mlm": 1.5349131524562836, "distill": 1.2124833464622498, "teacher_acc": 0.7381237745285034 }, { "step": 4121, "lr": 4.3306716664944344e-05, "elapsed_s": 3065.653860092163, "loss": 3.2636516094207764, "hidden": 0.21468712389469147, "layer": 0.09911414608359337, "mlm": 1.5315880477428436, "distill": 1.2531323432922363, "teacher_acc": 0.7388000041246414 }, { "step": 4131, "lr": 4.327239311714068e-05, "elapsed_s": 3073.040103197098, "loss": 3.3153828382492065, "hidden": 0.2124047763645649, "layer": 0.09867933206260204, "mlm": 1.5492456257343292, "distill": 1.2919879853725433, "teacher_acc": 0.743598997592926 }, { "step": 4141, "lr": 4.323799546462361e-05, "elapsed_s": 3080.4622464179993, "loss": 3.2514199018478394, "hidden": 0.20567770302295685, "layer": 0.09758830443024635, "mlm": 1.583678275346756, "distill": 1.2075920403003693, "teacher_acc": 0.7260519862174988 }, { "step": 4151, "lr": 4.320352384689471e-05, "elapsed_s": 3087.8774950504303, "loss": 3.3389520049095154, "hidden": 0.21395226940512657, "layer": 0.09946276620030403, "mlm": 1.631710559129715, "distill": 1.229605495929718, "teacher_acc": 0.7242700904607773 }, { "step": 4161, "lr": 4.316897840375558e-05, "elapsed_s": 3095.2917170524597, "loss": 3.31244295835495, "hidden": 0.21337440237402916, "layer": 0.09964515455067158, "mlm": 1.5788481831550598, "distill": 1.2570233345031738, "teacher_acc": 0.7282462269067764 }, { "step": 4171, "lr": 4.313435927530719e-05, "elapsed_s": 3102.697306394577, "loss": 3.368472933769226, "hidden": 0.21270372718572617, "layer": 0.09802959859371185, "mlm": 1.6909606754779816, "distill": 1.203089952468872, "teacher_acc": 0.6991153061389923 }, { "step": 4181, "lr": 4.309966660194936e-05, "elapsed_s": 3110.094302415848, "loss": 3.403820812702179, "hidden": 0.21656644716858864, "layer": 0.09976123832166195, "mlm": 1.6377077102661133, "distill": 1.2830996215343475, "teacher_acc": 0.7238743305206299 }, { "step": 4191, "lr": 4.3064900524380156e-05, "elapsed_s": 3117.5210263729095, "loss": 3.3575798869132996, "hidden": 0.21645012125372887, "layer": 0.0990385003387928, "mlm": 1.6342847049236298, "distill": 1.240875780582428, "teacher_acc": 0.7318895757198334 }, { "step": 4201, "lr": 4.303006118359537e-05, "elapsed_s": 3124.916850090027, "loss": 3.2713816165924072, "hidden": 0.20467019826173782, "layer": 0.09689895249903202, "mlm": 1.6402555704116821, "distill": 1.1733361780643463, "teacher_acc": 0.7169571220874786 }, { "step": 4211, "lr": 4.299514872088788e-05, "elapsed_s": 3132.347605228424, "loss": 3.3704922199249268, "hidden": 0.21299269422888756, "layer": 0.09935298934578896, "mlm": 1.6011030972003937, "distill": 1.2937273383140564, "teacher_acc": 0.7330595850944519 }, { "step": 4221, "lr": 4.2960163277847144e-05, "elapsed_s": 3139.744080066681, "loss": 3.4132604002952576, "hidden": 0.22094204276800156, "layer": 0.101207559928298, "mlm": 1.6728207468986511, "distill": 1.247951716184616, "teacher_acc": 0.7104651629924774 }, { "step": 4231, "lr": 4.292510499635859e-05, "elapsed_s": 3147.1650512218475, "loss": 3.318944990634918, "hidden": 0.2157551795244217, "layer": 0.09840540960431099, "mlm": 1.6330899000167847, "distill": 1.2051419615745544, "teacher_acc": 0.7182030230760574 }, { "step": 4241, "lr": 4.288997401860303e-05, "elapsed_s": 3154.5866589546204, "loss": 3.3167114853858948, "hidden": 0.2132684588432312, "layer": 0.09918131120502949, "mlm": 1.592810332775116, "distill": 1.2477736175060272, "teacher_acc": 0.7278425097465515 }, { "step": 4251, "lr": 4.2854770487056114e-05, "elapsed_s": 3161.968564271927, "loss": 3.3776387572288513, "hidden": 0.20509525388479233, "layer": 0.09673847258090973, "mlm": 1.7136280834674835, "distill": 1.2054509222507477, "teacher_acc": 0.6952854245901108 }, { "step": 4261, "lr": 4.281949454448775e-05, "elapsed_s": 3169.3572041988373, "loss": 3.348029613494873, "hidden": 0.21489091217517853, "layer": 0.09820382855832577, "mlm": 1.64179128408432, "distill": 1.2273545265197754, "teacher_acc": 0.7184735685586929 }, { "step": 4271, "lr": 4.2784146333961484e-05, "elapsed_s": 3176.742824792862, "loss": 3.346528470516205, "hidden": 0.2108408696949482, "layer": 0.09788176417350769, "mlm": 1.6464946866035461, "distill": 1.2294111847877502, "teacher_acc": 0.7197493314743042 }, { "step": 4281, "lr": 4.274872599883396e-05, "elapsed_s": 3184.1224415302277, "loss": 3.3095152974128723, "hidden": 0.22172212228178978, "layer": 0.10062669776380062, "mlm": 1.5060188472270966, "distill": 1.3097388744354248, "teacher_acc": 0.756232351064682 }, { "step": 4291, "lr": 4.2713233682754336e-05, "elapsed_s": 3191.491533279419, "loss": 3.3153995871543884, "hidden": 0.2121831253170967, "layer": 0.09842216409742832, "mlm": 1.6252050697803497, "distill": 1.2166172564029694, "teacher_acc": 0.71697136759758 }, { "step": 4301, "lr": 4.267766952966369e-05, "elapsed_s": 3198.8597388267517, "loss": 3.2286808490753174, "hidden": 0.21142106503248215, "layer": 0.09760724380612373, "mlm": 1.4907747507095337, "distill": 1.2662602663040161, "teacher_acc": 0.7473519891500473 }, { "step": 4311, "lr": 4.264203368379444e-05, "elapsed_s": 3206.2546882629395, "loss": 3.309619665145874, "hidden": 0.21119853109121323, "layer": 0.09820627421140671, "mlm": 1.6032266020774841, "distill": 1.2348929047584534, "teacher_acc": 0.725422590970993 }, { "step": 4321, "lr": 4.260632628966974e-05, "elapsed_s": 3213.632351875305, "loss": 3.247652053833008, "hidden": 0.20677784457802773, "layer": 0.09694913029670715, "mlm": 1.6099347472190857, "distill": 1.175687164068222, "teacher_acc": 0.7078178822994232 }, { "step": 4331, "lr": 4.257054749210293e-05, "elapsed_s": 3221.0118060112, "loss": 3.382774829864502, "hidden": 0.2139727734029293, "layer": 0.09984396398067474, "mlm": 1.6403425931930542, "distill": 1.264564722776413, "teacher_acc": 0.7251731604337692 }, { "step": 4341, "lr": 4.253469743619694e-05, "elapsed_s": 3228.431436777115, "loss": 3.1757484078407288, "hidden": 0.20999810844659805, "layer": 0.0969794224947691, "mlm": 1.566969394683838, "distill": 1.140293151140213, "teacher_acc": 0.7240430414676666 }, { "step": 4351, "lr": 4.2498776267343664e-05, "elapsed_s": 3235.809595346451, "loss": 3.327117443084717, "hidden": 0.20848198980093002, "layer": 0.09885729104280472, "mlm": 1.666463017463684, "distill": 1.194261759519577, "teacher_acc": 0.707717552781105 }, { "step": 4361, "lr": 4.2462784131223434e-05, "elapsed_s": 3243.16907286644, "loss": 3.245089888572693, "hidden": 0.20396515354514122, "layer": 0.09602841548621655, "mlm": 1.6105963289737701, "distill": 1.1785490214824677, "teacher_acc": 0.7206247895956039 }, { "step": 4371, "lr": 4.242672117380434e-05, "elapsed_s": 3250.5591628551483, "loss": 3.202542722225189, "hidden": 0.20455225557088852, "layer": 0.09619609825313091, "mlm": 1.5679444670677185, "distill": 1.1773956716060638, "teacher_acc": 0.729967474937439 }, { "step": 4381, "lr": 4.239058754134175e-05, "elapsed_s": 3257.9884610176086, "loss": 3.3390700817108154, "hidden": 0.2143702432513237, "layer": 0.09926500730216503, "mlm": 1.6220947802066803, "distill": 1.2386023998260498, "teacher_acc": 0.7230208814144135 }, { "step": 4391, "lr": 4.235438338037764e-05, "elapsed_s": 3265.413781642914, "loss": 3.19665265083313, "hidden": 0.20591288432478905, "layer": 0.09592483565211296, "mlm": 1.5535687804222107, "distill": 1.1832956373691559, "teacher_acc": 0.7293404340744019 }, { "step": 4401, "lr": 4.231810883773999e-05, "elapsed_s": 3272.8304164409637, "loss": 3.3925610184669495, "hidden": 0.20864951238036156, "layer": 0.09717600978910923, "mlm": 1.7057346105575562, "distill": 1.2209393978118896, "teacher_acc": 0.7065473347902298 }, { "step": 4411, "lr": 4.228176406054225e-05, "elapsed_s": 3280.2234992980957, "loss": 3.154885172843933, "hidden": 0.20931454375386238, "layer": 0.09889213182032108, "mlm": 1.5483828485012054, "distill": 1.1384271085262299, "teacher_acc": 0.7219444215297699 }, { "step": 4421, "lr": 4.224534919618269e-05, "elapsed_s": 3287.612589120865, "loss": 3.316923677921295, "hidden": 0.2083878554403782, "layer": 0.09787110239267349, "mlm": 1.6521506011486053, "distill": 1.1990618109703064, "teacher_acc": 0.7116932272911072 }, { "step": 4431, "lr": 4.220886439234385e-05, "elapsed_s": 3294.998076915741, "loss": 3.322017788887024, "hidden": 0.20995421335101128, "layer": 0.09641577675938606, "mlm": 1.6472203135490417, "distill": 1.206681102514267, "teacher_acc": 0.7126714438199997 }, { "step": 4441, "lr": 4.217230979699188e-05, "elapsed_s": 3302.400155067444, "loss": 3.2233042120933533, "hidden": 0.21804075688123703, "layer": 0.09952028468251228, "mlm": 1.4834250807762146, "distill": 1.2540375292301178, "teacher_acc": 0.7488970756530762 }, { "step": 4451, "lr": 4.2135685558375994e-05, "elapsed_s": 3309.8062233924866, "loss": 3.243834614753723, "hidden": 0.21329382807016373, "layer": 0.09946012683212757, "mlm": 1.5552393794059753, "distill": 1.2122775614261627, "teacher_acc": 0.7356916218996048 }, { "step": 4461, "lr": 4.2098991825027844e-05, "elapsed_s": 3317.1986808776855, "loss": 3.1683651208877563, "hidden": 0.2039036601781845, "layer": 0.09574254602193832, "mlm": 1.5798918902873993, "distill": 1.1327946782112122, "teacher_acc": 0.7229364961385727 }, { "step": 4471, "lr": 4.206222874576091e-05, "elapsed_s": 3324.6185138225555, "loss": 3.5012460947036743, "hidden": 0.21331216394901276, "layer": 0.09866055101156235, "mlm": 1.688195526599884, "distill": 1.337095856666565, "teacher_acc": 0.7197980880737305 }, { "step": 4481, "lr": 4.202539646966993e-05, "elapsed_s": 3332.0245263576508, "loss": 3.235841155052185, "hidden": 0.2092849314212799, "layer": 0.09713458828628063, "mlm": 1.5866239368915558, "distill": 1.182080090045929, "teacher_acc": 0.7247676998376846 }, { "step": 4491, "lr": 4.198849514613026e-05, "elapsed_s": 3339.364906311035, "loss": 3.348326861858368, "hidden": 0.20757995173335075, "layer": 0.09760897234082222, "mlm": 1.7007623314857483, "distill": 1.1836000978946686, "teacher_acc": 0.7006926983594894 }, { "step": 4501, "lr": 4.195152492479727e-05, "elapsed_s": 3346.719263792038, "loss": 3.366444408893585, "hidden": 0.21191087737679482, "layer": 0.09849878028035164, "mlm": 1.677823781967163, "distill": 1.2155494093894958, "teacher_acc": 0.709282785654068 }, { "step": 4511, "lr": 4.1914485955605785e-05, "elapsed_s": 3354.1317234039307, "loss": 3.2004151940345764, "hidden": 0.2059791535139084, "layer": 0.09623594023287296, "mlm": 1.562754601240158, "distill": 1.1775842905044556, "teacher_acc": 0.7337772995233536 }, { "step": 4521, "lr": 4.1877378388769406e-05, "elapsed_s": 3361.514974832535, "loss": 3.3409120440483093, "hidden": 0.21115676686167717, "layer": 0.09899488277733326, "mlm": 1.678274929523468, "distill": 1.190826028585434, "teacher_acc": 0.7062052488327026 }, { "step": 4531, "lr": 4.1840202374779945e-05, "elapsed_s": 3368.8570654392242, "loss": 3.3012958765029907, "hidden": 0.21341875568032265, "layer": 0.09695042110979557, "mlm": 1.598259836435318, "distill": 1.227723240852356, "teacher_acc": 0.729526549577713 }, { "step": 4541, "lr": 4.180295806440682e-05, "elapsed_s": 3376.2064316272736, "loss": 3.30934602022171, "hidden": 0.2079078033566475, "layer": 0.0985367875546217, "mlm": 1.6045744121074677, "distill": 1.239687591791153, "teacher_acc": 0.7236827909946442 }, { "step": 4551, "lr": 4.1765645608696404e-05, "elapsed_s": 3383.593672990799, "loss": 3.3828004002571106, "hidden": 0.2159968875348568, "layer": 0.09976777620613575, "mlm": 1.702335238456726, "distill": 1.198587417602539, "teacher_acc": 0.6992685049772263 }, { "step": 4561, "lr": 4.172826515897146e-05, "elapsed_s": 3391.024036169052, "loss": 3.331816077232361, "hidden": 0.20896141231060028, "layer": 0.0994015708565712, "mlm": 1.6255565583705902, "distill": 1.2386358678340912, "teacher_acc": 0.7311897575855255 }, { "step": 4571, "lr": 4.169081686683049e-05, "elapsed_s": 3398.3837625980377, "loss": 3.42166531085968, "hidden": 0.20937034115195274, "layer": 0.0973339956253767, "mlm": 1.6915410161018372, "distill": 1.2627165913581848, "teacher_acc": 0.7185308933258057 }, { "step": 4581, "lr": 4.165330088414714e-05, "elapsed_s": 3405.7707788944244, "loss": 3.2203798294067383, "hidden": 0.20206398516893387, "layer": 0.0966983325779438, "mlm": 1.6712635159492493, "distill": 1.0966392308473587, "teacher_acc": 0.6975877285003662 }, { "step": 4591, "lr": 4.1615717363069575e-05, "elapsed_s": 3413.1664209365845, "loss": 3.208263397216797, "hidden": 0.2110174223780632, "layer": 0.09827472269535065, "mlm": 1.5549829304218292, "distill": 1.1821082532405853, "teacher_acc": 0.7375730723142624 }, { "step": 4601, "lr": 4.157806645601988e-05, "elapsed_s": 3420.52996468544, "loss": 3.1552221179008484, "hidden": 0.2047625035047531, "layer": 0.09580486454069614, "mlm": 1.49265456199646, "distill": 1.205140084028244, "teacher_acc": 0.7411182075738907 }, { "step": 4611, "lr": 4.154034831569341e-05, "elapsed_s": 3427.913978099823, "loss": 3.264908015727997, "hidden": 0.20728349313139915, "layer": 0.09630329348146915, "mlm": 1.6494484841823578, "distill": 1.1527409255504608, "teacher_acc": 0.7079003751277924 }, { "step": 4621, "lr": 4.15025630950582e-05, "elapsed_s": 3435.289041996002, "loss": 3.2947943806648254, "hidden": 0.21196464449167252, "layer": 0.09842529334127903, "mlm": 1.5996275842189789, "distill": 1.222024917602539, "teacher_acc": 0.7145718932151794 }, { "step": 4631, "lr": 4.1464710947354313e-05, "elapsed_s": 3442.657971382141, "loss": 3.199162185192108, "hidden": 0.2088560238480568, "layer": 0.09814333729445934, "mlm": 1.5912317633628845, "distill": 1.1411466300487518, "teacher_acc": 0.719153419137001 }, { "step": 4641, "lr": 4.1426792026093276e-05, "elapsed_s": 3450.0308136940002, "loss": 3.2100967168807983, "hidden": 0.20065710693597794, "layer": 0.09514385275542736, "mlm": 1.6157848238945007, "distill": 1.1454257369041443, "teacher_acc": 0.7144080400466919 }, { "step": 4651, "lr": 4.138880648505738e-05, "elapsed_s": 3457.429240465164, "loss": 3.269571363925934, "hidden": 0.20207364857196808, "layer": 0.09576329216361046, "mlm": 1.6158208847045898, "distill": 1.2017216682434082, "teacher_acc": 0.72641821205616 }, { "step": 4661, "lr": 4.1350754478299114e-05, "elapsed_s": 3464.8490397930145, "loss": 3.3542093634605408, "hidden": 0.21145424991846085, "layer": 0.09811549261212349, "mlm": 1.651604026556015, "distill": 1.2306391596794128, "teacher_acc": 0.719676747918129 }, { "step": 4671, "lr": 4.131263616014053e-05, "elapsed_s": 3472.242677927017, "loss": 3.112748682498932, "hidden": 0.20154592767357826, "layer": 0.09408058784902096, "mlm": 1.5505365431308746, "distill": 1.112079918384552, "teacher_acc": 0.72315414249897 }, { "step": 4681, "lr": 4.12744516851726e-05, "elapsed_s": 3479.6217126846313, "loss": 3.318545162677765, "hidden": 0.20495014265179634, "layer": 0.09570681303739548, "mlm": 1.618401825428009, "distill": 1.2423896491527557, "teacher_acc": 0.7313784509897232 }, { "step": 4691, "lr": 4.123620120825459e-05, "elapsed_s": 3486.988903284073, "loss": 3.135640025138855, "hidden": 0.20741036906838417, "layer": 0.09641355089843273, "mlm": 1.5327167809009552, "distill": 1.1398956775665283, "teacher_acc": 0.7309237420558929 }, { "step": 4701, "lr": 4.1197884884513474e-05, "elapsed_s": 3494.3517067432404, "loss": 3.1240809559822083, "hidden": 0.20632804185152054, "layer": 0.0962603073567152, "mlm": 1.476097822189331, "distill": 1.1871967911720276, "teacher_acc": 0.7478890419006348 }, { "step": 4711, "lr": 4.115950286934322e-05, "elapsed_s": 3501.728793144226, "loss": 3.3512917160987854, "hidden": 0.20859292894601822, "layer": 0.09733176603913307, "mlm": 1.6412251889705658, "distill": 1.2442147731781006, "teacher_acc": 0.7244714945554733 }, { "step": 4721, "lr": 4.1121055318404264e-05, "elapsed_s": 3509.08344578743, "loss": 3.1968942284584045, "hidden": 0.20581138134002686, "layer": 0.09742253832519054, "mlm": 1.5619724094867706, "distill": 1.1745876967906952, "teacher_acc": 0.7246065437793732 }, { "step": 4731, "lr": 4.108254238762279e-05, "elapsed_s": 3516.442927837372, "loss": 3.299632728099823, "hidden": 0.20540426298975945, "layer": 0.09687220677733421, "mlm": 1.6597283482551575, "distill": 1.1806597709655762, "teacher_acc": 0.7085152864456177 }, { "step": 4741, "lr": 4.1043964233190146e-05, "elapsed_s": 3523.8042390346527, "loss": 3.2163124084472656, "hidden": 0.2063148468732834, "layer": 0.09597291797399521, "mlm": 1.5742062032222748, "distill": 1.1814900636672974, "teacher_acc": 0.7179129868745804 }, { "step": 4751, "lr": 4.1005321011562206e-05, "elapsed_s": 3531.179769515991, "loss": 3.218534469604492, "hidden": 0.20405955612659454, "layer": 0.0959672536700964, "mlm": 1.559091329574585, "distill": 1.2033403515815735, "teacher_acc": 0.7293764501810074 }, { "step": 4761, "lr": 4.09666128794587e-05, "elapsed_s": 3538.5659732818604, "loss": 3.308561682701111, "hidden": 0.21187366172671318, "layer": 0.09824804961681366, "mlm": 1.604141116142273, "distill": 1.231549233198166, "teacher_acc": 0.7184893935918808 }, { "step": 4771, "lr": 4.0927839993862644e-05, "elapsed_s": 3545.9776673316956, "loss": 3.3494094610214233, "hidden": 0.20454757660627365, "layer": 0.09713119082152843, "mlm": 1.6668068170547485, "distill": 1.2249418795108795, "teacher_acc": 0.7053567618131638 }, { "step": 4781, "lr": 4.088900251201964e-05, "elapsed_s": 3553.414164543152, "loss": 3.2787808775901794, "hidden": 0.21274873241782188, "layer": 0.09825598634779453, "mlm": 1.5920704901218414, "distill": 1.2120848894119263, "teacher_acc": 0.7195242494344711 }, { "step": 4791, "lr": 4.0850100591437256e-05, "elapsed_s": 3560.8053572177887, "loss": 3.307882845401764, "hidden": 0.2057039737701416, "layer": 0.09678362868726254, "mlm": 1.7040260136127472, "distill": 1.1440570503473282, "teacher_acc": 0.6977433264255524 }, { "step": 4801, "lr": 4.0811134389884433e-05, "elapsed_s": 3568.234459877014, "loss": 3.1556836366653442, "hidden": 0.20953970029950142, "layer": 0.09672900661826134, "mlm": 1.5131571590900421, "distill": 1.1750824749469757, "teacher_acc": 0.7338665872812271 }, { "step": 4811, "lr": 4.077210406539077e-05, "elapsed_s": 3575.6317596435547, "loss": 3.2032363414764404, "hidden": 0.20511845871806145, "layer": 0.09688124619424343, "mlm": 1.504835069179535, "distill": 1.2397237420082092, "teacher_acc": 0.7389679998159409 }, { "step": 4821, "lr": 4.073300977624594e-05, "elapsed_s": 3583.0569841861725, "loss": 3.2924527525901794, "hidden": 0.21002959087491035, "layer": 0.09711155295372009, "mlm": 1.5760244727134705, "distill": 1.2478132843971252, "teacher_acc": 0.7332588732242584 }, { "step": 4831, "lr": 4.069385168099902e-05, "elapsed_s": 3590.426653623581, "loss": 3.1348413228988647, "hidden": 0.19648142158985138, "layer": 0.09512872621417046, "mlm": 1.5534532070159912, "distill": 1.1408608853816986, "teacher_acc": 0.7301175147294998 }, { "step": 4841, "lr": 4.065462993845784e-05, "elapsed_s": 3597.8248150348663, "loss": 3.2645967602729797, "hidden": 0.20437493920326233, "layer": 0.09556300565600395, "mlm": 1.6643647849559784, "distill": 1.143700659275055, "teacher_acc": 0.7002401202917099 }, { "step": 4851, "lr": 4.061534470768841e-05, "elapsed_s": 3605.1821913719177, "loss": 3.262784004211426, "hidden": 0.20648889616131783, "layer": 0.09566755220293999, "mlm": 1.6383762657642365, "distill": 1.163596123456955, "teacher_acc": 0.7078545987606049 }, { "step": 4861, "lr": 4.057599614801415e-05, "elapsed_s": 3612.5551936626434, "loss": 3.3020431995391846, "hidden": 0.20443880930542946, "layer": 0.09519122540950775, "mlm": 1.6234206557273865, "distill": 1.2221492528915405, "teacher_acc": 0.7199424654245377 }, { "step": 4871, "lr": 4.053658441901536e-05, "elapsed_s": 3619.919929265976, "loss": 3.057672083377838, "hidden": 0.19774561002850533, "layer": 0.09378297254443169, "mlm": 1.4854837656021118, "distill": 1.1298055946826935, "teacher_acc": 0.737074613571167 }, { "step": 4881, "lr": 4.049710968052851e-05, "elapsed_s": 3627.2914140224457, "loss": 3.1329058408737183, "hidden": 0.20216650888323784, "layer": 0.09563377872109413, "mlm": 1.5161761939525604, "distill": 1.1645798087120056, "teacher_acc": 0.735722005367279 }, { "step": 4891, "lr": 4.045757209264562e-05, "elapsed_s": 3634.6763672828674, "loss": 3.173789620399475, "hidden": 0.20137259736657143, "layer": 0.09478520601987839, "mlm": 1.5647208988666534, "distill": 1.1589308828115463, "teacher_acc": 0.727718323469162 }, { "step": 4901, "lr": 4.0417971815713584e-05, "elapsed_s": 3642.0988109111786, "loss": 3.2118477821350098, "hidden": 0.2055814266204834, "layer": 0.09653116017580032, "mlm": 1.5730860233306885, "distill": 1.179333359003067, "teacher_acc": 0.7336676716804504 }, { "step": 4911, "lr": 4.0378309010333535e-05, "elapsed_s": 3649.510662317276, "loss": 3.2011208534240723, "hidden": 0.203938540071249, "layer": 0.09536782465875149, "mlm": 1.56002476811409, "distill": 1.185535043478012, "teacher_acc": 0.7288943380117416 }, { "step": 4921, "lr": 4.0338583837360225e-05, "elapsed_s": 3656.876801967621, "loss": 3.2207789421081543, "hidden": 0.19918324798345566, "layer": 0.09405398555099964, "mlm": 1.6348387598991394, "distill": 1.1405466794967651, "teacher_acc": 0.710679292678833 }, { "step": 4931, "lr": 4.02987964579013e-05, "elapsed_s": 3664.236213207245, "loss": 3.2520132660865784, "hidden": 0.20406421646475792, "layer": 0.0951437670737505, "mlm": 1.5828405916690826, "distill": 1.2134723961353302, "teacher_acc": 0.7262012660503387 }, { "step": 4941, "lr": 4.025894703331671e-05, "elapsed_s": 3671.626344203949, "loss": 3.105576276779175, "hidden": 0.20592112839221954, "layer": 0.09550800919532776, "mlm": 1.478015959262848, "distill": 1.1679640710353851, "teacher_acc": 0.7497824877500534 }, { "step": 4951, "lr": 4.021903572521802e-05, "elapsed_s": 3678.9959321022034, "loss": 3.399523437023163, "hidden": 0.21514524891972542, "layer": 0.10221908055245876, "mlm": 1.5978756248950958, "distill": 1.320247769355774, "teacher_acc": 0.7314503788948059 }, { "step": 4961, "lr": 4.0179062695467784e-05, "elapsed_s": 3686.3737268447876, "loss": 3.180026412010193, "hidden": 0.20108840242028236, "layer": 0.09561615996062756, "mlm": 1.559617966413498, "distill": 1.1704235970973969, "teacher_acc": 0.730669841170311 }, { "step": 4971, "lr": 4.013902810617885e-05, "elapsed_s": 3693.774680376053, "loss": 3.2683951258659363, "hidden": 0.20495279133319855, "layer": 0.09737017937004566, "mlm": 1.5766583383083344, "distill": 1.2331461906433105, "teacher_acc": 0.7283996194601059 }, { "step": 4981, "lr": 4.009893211971376e-05, "elapsed_s": 3701.1765642166138, "loss": 3.221259891986847, "hidden": 0.20638132467865944, "layer": 0.09570233710110188, "mlm": 1.5900909006595612, "distill": 1.1705550849437714, "teacher_acc": 0.7258387058973312 }, { "step": 4991, "lr": 4.005877489868401e-05, "elapsed_s": 3708.545308828354, "loss": 3.153154134750366, "hidden": 0.20396416634321213, "layer": 0.0966196246445179, "mlm": 1.5876067280769348, "distill": 1.1093092858791351, "teacher_acc": 0.7189137041568756 }, { "step": 5001, "lr": 4.001855660594948e-05, "elapsed_s": 3717.985068321228, "loss": 3.2355785369873047, "hidden": 0.20908984914422035, "layer": 0.09800935909152031, "mlm": 1.539255976676941, "distill": 1.2291381657123566, "teacher_acc": 0.7423324584960938 }, { "step": 5011, "lr": 3.997827740461768e-05, "elapsed_s": 3725.369317293167, "loss": 3.2152320742607117, "hidden": 0.2005365490913391, "layer": 0.09435624070465565, "mlm": 1.6410862803459167, "distill": 1.1258945763111115, "teacher_acc": 0.7072471529245377 }, { "step": 5021, "lr": 3.993793745804319e-05, "elapsed_s": 3732.7243218421936, "loss": 3.241732120513916, "hidden": 0.20025945454835892, "layer": 0.0962473712861538, "mlm": 1.5967066884040833, "distill": 1.1963827908039093, "teacher_acc": 0.7308148443698883 }, { "step": 5031, "lr": 3.98975369298269e-05, "elapsed_s": 3740.0999846458435, "loss": 3.230296552181244, "hidden": 0.2036784552037716, "layer": 0.0959779042750597, "mlm": 1.6101833879947662, "distill": 1.1647672355175018, "teacher_acc": 0.7241557389497757 }, { "step": 5041, "lr": 3.985707598381544e-05, "elapsed_s": 3747.4802165031433, "loss": 3.335447609424591, "hidden": 0.21229297295212746, "layer": 0.09786086902022362, "mlm": 1.6643494069576263, "distill": 1.1975817680358887, "teacher_acc": 0.7102034389972687 }, { "step": 5051, "lr": 3.981655478410043e-05, "elapsed_s": 3754.8813359737396, "loss": 3.2025309801101685, "hidden": 0.19948890432715416, "layer": 0.09439263865351677, "mlm": 1.6363706290721893, "distill": 1.119986206293106, "teacher_acc": 0.7115653604269028 }, { "step": 5061, "lr": 3.977597349501785e-05, "elapsed_s": 3762.268499135971, "loss": 3.1651260256767273, "hidden": 0.20650998502969742, "layer": 0.09630860015749931, "mlm": 1.5793797671794891, "distill": 1.124572068452835, "teacher_acc": 0.7204500436782837 }, { "step": 5071, "lr": 3.973533228114742e-05, "elapsed_s": 3769.679871559143, "loss": 3.111977994441986, "hidden": 0.19942068681120872, "layer": 0.09455664083361626, "mlm": 1.5150408446788788, "distill": 1.150817483663559, "teacher_acc": 0.7332603186368942 }, { "step": 5081, "lr": 3.969463130731183e-05, "elapsed_s": 3777.088123559952, "loss": 3.228224515914917, "hidden": 0.21238475292921066, "layer": 0.09742080047726631, "mlm": 1.5520416498184204, "distill": 1.202702909708023, "teacher_acc": 0.7264745682477951 }, { "step": 5091, "lr": 3.965387073857617e-05, "elapsed_s": 3784.4977946281433, "loss": 3.2209428548812866, "hidden": 0.20746779069304466, "layer": 0.09702244587242603, "mlm": 1.5500885844230652, "distill": 1.2074074447154999, "teacher_acc": 0.7321085929870605 }, { "step": 5101, "lr": 3.9613050740247224e-05, "elapsed_s": 3791.930071592331, "loss": 3.1127697229385376, "hidden": 0.1943652518093586, "layer": 0.09326641820371151, "mlm": 1.5846974849700928, "distill": 1.0927084982395172, "teacher_acc": 0.7157490998506546 }, { "step": 5111, "lr": 3.957217147787276e-05, "elapsed_s": 3799.361764907837, "loss": 3.160230040550232, "hidden": 0.19682473316788673, "layer": 0.09407675080001354, "mlm": 1.5076867640018463, "distill": 1.2118555009365082, "teacher_acc": 0.7399500012397766 }, { "step": 5121, "lr": 3.9531233117240916e-05, "elapsed_s": 3806.7531530857086, "loss": 3.265174627304077, "hidden": 0.2011437937617302, "layer": 0.0954657569527626, "mlm": 1.6025209724903107, "distill": 1.2126331329345703, "teacher_acc": 0.7237385213375092 }, { "step": 5131, "lr": 3.949023582437952e-05, "elapsed_s": 3814.1271891593933, "loss": 3.2590845227241516, "hidden": 0.20793559402227402, "layer": 0.09669565036892891, "mlm": 1.604582279920578, "distill": 1.1902831494808197, "teacher_acc": 0.7265826314687729 }, { "step": 5141, "lr": 3.9449179765555375e-05, "elapsed_s": 3821.4902596473694, "loss": 3.1402412056922913, "hidden": 0.1993517056107521, "layer": 0.09362811036407948, "mlm": 1.563025563955307, "distill": 1.1316982209682465, "teacher_acc": 0.7202557474374771 }, { "step": 5151, "lr": 3.940806510727364e-05, "elapsed_s": 3828.8709874153137, "loss": 3.1213550567626953, "hidden": 0.20117231830954552, "layer": 0.09498413279652596, "mlm": 1.5935811400413513, "distill": 1.0779372155666351, "teacher_acc": 0.7177843749523163 }, { "step": 5161, "lr": 3.9366892016277096e-05, "elapsed_s": 3836.22931432724, "loss": 3.160399615764618, "hidden": 0.20244242250919342, "layer": 0.0950684193521738, "mlm": 1.5560625493526459, "distill": 1.1519179940223694, "teacher_acc": 0.7329987734556198 }, { "step": 5171, "lr": 3.932566065954553e-05, "elapsed_s": 3843.59894323349, "loss": 3.117943584918976, "hidden": 0.2046220451593399, "layer": 0.09402966313064098, "mlm": 1.530993402004242, "distill": 1.130691260099411, "teacher_acc": 0.7239188998937607 }, { "step": 5181, "lr": 3.928437120429502e-05, "elapsed_s": 3850.981483221054, "loss": 3.240496516227722, "hidden": 0.20696918666362762, "layer": 0.09686686843633652, "mlm": 1.5881038010120392, "distill": 1.1900207996368408, "teacher_acc": 0.7208735197782516 }, { "step": 5191, "lr": 3.9243023817977264e-05, "elapsed_s": 3858.3763728141785, "loss": 3.315925180912018, "hidden": 0.20436597988009453, "layer": 0.09535984136164188, "mlm": 1.6764420568943024, "distill": 1.1830712854862213, "teacher_acc": 0.7128686457872391 }, { "step": 5201, "lr": 3.920161866827889e-05, "elapsed_s": 3865.7784128189087, "loss": 3.1283793449401855, "hidden": 0.19815217703580856, "layer": 0.09389823116362095, "mlm": 1.5900116264820099, "distill": 1.0951142609119415, "teacher_acc": 0.7098075151443481 }, { "step": 5211, "lr": 3.916015592312082e-05, "elapsed_s": 3873.1706261634827, "loss": 3.154094636440277, "hidden": 0.2045869454741478, "layer": 0.09474603831768036, "mlm": 1.5561692118644714, "distill": 1.14137864112854, "teacher_acc": 0.7365899980068207 }, { "step": 5221, "lr": 3.911863575065753e-05, "elapsed_s": 3880.5756254196167, "loss": 3.2967916131019592, "hidden": 0.20082442462444305, "layer": 0.09492165967822075, "mlm": 1.6190398633480072, "distill": 1.228642076253891, "teacher_acc": 0.7256738543510437 }, { "step": 5231, "lr": 3.9077058319276395e-05, "elapsed_s": 3887.9752378463745, "loss": 3.1839446425437927, "hidden": 0.20127076283097267, "layer": 0.09562620706856251, "mlm": 1.5423905849456787, "distill": 1.1911994516849518, "teacher_acc": 0.7253284454345703 }, { "step": 5241, "lr": 3.9035423797597027e-05, "elapsed_s": 3895.364002227783, "loss": 3.158566176891327, "hidden": 0.20146454125642776, "layer": 0.09579511545598507, "mlm": 1.5601206719875336, "distill": 1.1476188004016876, "teacher_acc": 0.7257874757051468 }, { "step": 5251, "lr": 3.8993732354470556e-05, "elapsed_s": 3902.749901533127, "loss": 3.3215824961662292, "hidden": 0.20382334291934967, "layer": 0.09563855081796646, "mlm": 1.6733167171478271, "distill": 1.1927998065948486, "teacher_acc": 0.7127123326063156 }, { "step": 5261, "lr": 3.895198415897896e-05, "elapsed_s": 3910.1876792907715, "loss": 3.133697032928467, "hidden": 0.20069924369454384, "layer": 0.09434601850807667, "mlm": 1.5828094780445099, "distill": 1.1023161113262177, "teacher_acc": 0.724223792552948 }, { "step": 5271, "lr": 3.8910179380434394e-05, "elapsed_s": 3917.5856449604034, "loss": 3.070586919784546, "hidden": 0.1927967108786106, "layer": 0.0928997453302145, "mlm": 1.5592449009418488, "distill": 1.0792986750602722, "teacher_acc": 0.7200212776660919 }, { "step": 5281, "lr": 3.886831818837847e-05, "elapsed_s": 3924.9761955738068, "loss": 3.25690758228302, "hidden": 0.20462371036410332, "layer": 0.09762348234653473, "mlm": 1.557576447725296, "distill": 1.2412719428539276, "teacher_acc": 0.7409348636865616 }, { "step": 5291, "lr": 3.88264007525816e-05, "elapsed_s": 3932.4134068489075, "loss": 3.0648136138916016, "hidden": 0.18844493478536606, "layer": 0.09216207824647427, "mlm": 1.6049093902111053, "distill": 1.036933422088623, "teacher_acc": 0.7005497962236404 }, { "step": 5301, "lr": 3.8784427243042296e-05, "elapsed_s": 3939.8023250102997, "loss": 3.1235196590423584, "hidden": 0.19936472922563553, "layer": 0.09414207376539707, "mlm": 1.5542917251586914, "distill": 1.1234274804592133, "teacher_acc": 0.7233496010303497 }, { "step": 5311, "lr": 3.8742397829986465e-05, "elapsed_s": 3947.2039272785187, "loss": 3.236342191696167, "hidden": 0.20166560262441635, "layer": 0.09504166059195995, "mlm": 1.5434348583221436, "distill": 1.2420552372932434, "teacher_acc": 0.7431695461273193 }, { "step": 5321, "lr": 3.870031268386676e-05, "elapsed_s": 3954.6426210403442, "loss": 3.2960351705551147, "hidden": 0.20759271085262299, "layer": 0.09561016969382763, "mlm": 1.6015039086341858, "distill": 1.2315407693386078, "teacher_acc": 0.7288808971643448 }, { "step": 5331, "lr": 3.865817197536182e-05, "elapsed_s": 3962.060968875885, "loss": 3.268190860748291, "hidden": 0.20999006181955338, "layer": 0.09752126224339008, "mlm": 1.5789802074432373, "distill": 1.220469892024994, "teacher_acc": 0.7243476957082748 }, { "step": 5341, "lr": 3.861597587537568e-05, "elapsed_s": 3969.493040084839, "loss": 3.175324857234955, "hidden": 0.2002992145717144, "layer": 0.09486480429768562, "mlm": 1.624749481678009, "distill": 1.102544516324997, "teacher_acc": 0.7055502384901047 }, { "step": 5351, "lr": 3.857372455503697e-05, "elapsed_s": 3976.9188375473022, "loss": 3.1311481595039368, "hidden": 0.1972450613975525, "layer": 0.09321189112961292, "mlm": 1.6187196969985962, "distill": 1.0713323652744293, "teacher_acc": 0.7194712162017822 }, { "step": 5361, "lr": 3.853141818569829e-05, "elapsed_s": 3984.32852101326, "loss": 2.961795687675476, "hidden": 0.2043016441166401, "layer": 0.09525318257510662, "mlm": 1.395276963710785, "distill": 1.110288828611374, "teacher_acc": 0.7504487037658691 }, { "step": 5371, "lr": 3.8489056938935483e-05, "elapsed_s": 3991.7455537319183, "loss": 3.123678207397461, "hidden": 0.19621623307466507, "layer": 0.09361790493130684, "mlm": 1.6045169830322266, "distill": 1.079919695854187, "teacher_acc": 0.7027239501476288 }, { "step": 5381, "lr": 3.8446640986546966e-05, "elapsed_s": 3999.1811094284058, "loss": 3.175505220890045, "hidden": 0.19534580782055855, "layer": 0.0941611509770155, "mlm": 1.599379062652588, "distill": 1.1383539140224457, "teacher_acc": 0.7210898548364639 }, { "step": 5391, "lr": 3.840417050055301e-05, "elapsed_s": 4006.5692915916443, "loss": 3.003191828727722, "hidden": 0.1943880058825016, "layer": 0.09284947626292706, "mlm": 1.5219251811504364, "distill": 1.0460660606622696, "teacher_acc": 0.7238606214523315 }, { "step": 5401, "lr": 3.8361645653195026e-05, "elapsed_s": 4013.9449203014374, "loss": 3.155056059360504, "hidden": 0.1977628991007805, "layer": 0.09409528970718384, "mlm": 1.6211577355861664, "distill": 1.0913249254226685, "teacher_acc": 0.7144501209259033 }, { "step": 5411, "lr": 3.831906661693494e-05, "elapsed_s": 4021.356166124344, "loss": 3.2660038471221924, "hidden": 0.20346135646104813, "layer": 0.09643821977078915, "mlm": 1.6242025792598724, "distill": 1.1866594552993774, "teacher_acc": 0.7224602550268173 }, { "step": 5421, "lr": 3.8276433564454416e-05, "elapsed_s": 4028.758138656616, "loss": 3.194348931312561, "hidden": 0.20030442252755165, "layer": 0.0949259102344513, "mlm": 1.5808246433734894, "distill": 1.1654525101184845, "teacher_acc": 0.7303000837564468 }, { "step": 5431, "lr": 3.823374666865418e-05, "elapsed_s": 4036.1603627204895, "loss": 3.085331916809082, "hidden": 0.19843630865216255, "layer": 0.09373984299600124, "mlm": 1.5342360138893127, "distill": 1.1073534190654755, "teacher_acc": 0.7294028401374817 }, { "step": 5441, "lr": 3.819100610265332e-05, "elapsed_s": 4043.6091282367706, "loss": 3.182236135005951, "hidden": 0.2007373422384262, "layer": 0.09559807926416397, "mlm": 1.5722976922988892, "distill": 1.1606647670269012, "teacher_acc": 0.7159816771745682 }, { "step": 5451, "lr": 3.81482120397886e-05, "elapsed_s": 4051.0435740947723, "loss": 3.2362318634986877, "hidden": 0.2044500820338726, "layer": 0.09659877978265285, "mlm": 1.5844030678272247, "distill": 1.1946293115615845, "teacher_acc": 0.7308434247970581 }, { "step": 5461, "lr": 3.8105364653613744e-05, "elapsed_s": 4058.465926885605, "loss": 3.2365540266036987, "hidden": 0.20084622502326965, "layer": 0.09513790532946587, "mlm": 1.6189433336257935, "distill": 1.1683493554592133, "teacher_acc": 0.7162838578224182 }, { "step": 5471, "lr": 3.8062464117898724e-05, "elapsed_s": 4065.867518901825, "loss": 3.2040562629699707, "hidden": 0.19839361310005188, "layer": 0.09430081397294998, "mlm": 1.6644619703292847, "distill": 1.0956567823886871, "teacher_acc": 0.6927765756845474 }, { "step": 5481, "lr": 3.8019510606629064e-05, "elapsed_s": 4073.2898931503296, "loss": 3.2046201825141907, "hidden": 0.19593093171715736, "layer": 0.0933859571814537, "mlm": 1.6396242082118988, "distill": 1.1264412105083466, "teacher_acc": 0.713366910815239 }, { "step": 5491, "lr": 3.7976504294005125e-05, "elapsed_s": 4080.7035796642303, "loss": 3.1884191632270813, "hidden": 0.20163608342409134, "layer": 0.09460514783859253, "mlm": 1.5915963053703308, "distill": 1.146247997879982, "teacher_acc": 0.7161682844161987 }, { "step": 5501, "lr": 3.793344535444142e-05, "elapsed_s": 4088.109368801117, "loss": 3.290668547153473, "hidden": 0.19974730536341667, "layer": 0.09316955134272575, "mlm": 1.7141708135604858, "distill": 1.1304183304309845, "teacher_acc": 0.6968995779752731 }, { "step": 5511, "lr": 3.789033396256589e-05, "elapsed_s": 4095.519630908966, "loss": 3.137165367603302, "hidden": 0.1943967528641224, "layer": 0.09414484538137913, "mlm": 1.5985552668571472, "distill": 1.1027441322803497, "teacher_acc": 0.7089481949806213 }, { "step": 5521, "lr": 3.784717029321922e-05, "elapsed_s": 4102.946670293808, "loss": 3.0625978112220764, "hidden": 0.19923468306660652, "layer": 0.0952229555696249, "mlm": 1.5044777989387512, "distill": 1.1120392382144928, "teacher_acc": 0.7373954951763153 }, { "step": 5531, "lr": 3.7803954521454055e-05, "elapsed_s": 4110.364837408066, "loss": 3.133970618247986, "hidden": 0.20013427734375, "layer": 0.09483890421688557, "mlm": 1.5003079175949097, "distill": 1.1859746277332306, "teacher_acc": 0.7449219673871994 }, { "step": 5541, "lr": 3.77606868225344e-05, "elapsed_s": 4117.779819011688, "loss": 3.2288476824760437, "hidden": 0.20172005891799927, "layer": 0.09434804134070873, "mlm": 1.6403281092643738, "distill": 1.1379053890705109, "teacher_acc": 0.7073512226343155 }, { "step": 5551, "lr": 3.7717367371934805e-05, "elapsed_s": 4125.198168992996, "loss": 3.0198581218719482, "hidden": 0.19426102191209793, "layer": 0.09181394055485725, "mlm": 1.5087133944034576, "distill": 1.0767156481742859, "teacher_acc": 0.7334019988775253 }, { "step": 5561, "lr": 3.7673996345339765e-05, "elapsed_s": 4132.600310087204, "loss": 3.172568619251251, "hidden": 0.20363150537014008, "layer": 0.09725976921617985, "mlm": 1.4820390045642853, "distill": 1.2346367537975311, "teacher_acc": 0.7472864389419556 }, { "step": 5571, "lr": 3.763057391864287e-05, "elapsed_s": 4140.039600133896, "loss": 3.1457441449165344, "hidden": 0.19964130595326424, "layer": 0.09341919049620628, "mlm": 1.5451968610286713, "distill": 1.1545551121234894, "teacher_acc": 0.7254993468523026 }, { "step": 5581, "lr": 3.7587100267946226e-05, "elapsed_s": 4147.4629101753235, "loss": 3.1725448966026306, "hidden": 0.19636895135045052, "layer": 0.0932153444737196, "mlm": 1.6197852492332458, "distill": 1.1134141683578491, "teacher_acc": 0.7151211947202682 }, { "step": 5591, "lr": 3.754357556955966e-05, "elapsed_s": 4154.873417139053, "loss": 3.170562207698822, "hidden": 0.1973896026611328, "layer": 0.09508186392486095, "mlm": 1.574512094259262, "distill": 1.1537300646305084, "teacher_acc": 0.723589614033699 }, { "step": 5601, "lr": 3.7500000000000003e-05, "elapsed_s": 4162.27840924263, "loss": 3.2920291423797607, "hidden": 0.20497823506593704, "layer": 0.09670058265328407, "mlm": 1.6148390173912048, "distill": 1.2188833355903625, "teacher_acc": 0.720633253455162 }, { "step": 5611, "lr": 3.745637373599043e-05, "elapsed_s": 4169.682890176773, "loss": 3.0663285851478577, "hidden": 0.20180582255125046, "layer": 0.09377403371036053, "mlm": 1.486604005098343, "distill": 1.1292259991168976, "teacher_acc": 0.7422326356172562 }, { "step": 5621, "lr": 3.74126969544597e-05, "elapsed_s": 4177.069175720215, "loss": 3.1064653396606445, "hidden": 0.19697028398513794, "layer": 0.09409929066896439, "mlm": 1.5173876285552979, "distill": 1.1480874717235565, "teacher_acc": 0.7443343251943588 }, { "step": 5631, "lr": 3.736896983254144e-05, "elapsed_s": 4184.449201583862, "loss": 3.1099019646644592, "hidden": 0.19263843074440956, "layer": 0.09185251407325268, "mlm": 1.605536550283432, "distill": 1.0731623768806458, "teacher_acc": 0.7089554518461227 }, { "step": 5641, "lr": 3.732519254757344e-05, "elapsed_s": 4191.847795248032, "loss": 3.151432514190674, "hidden": 0.19703428074717522, "layer": 0.09372341074049473, "mlm": 1.5938798785209656, "distill": 1.1166223734617233, "teacher_acc": 0.7129863351583481 }, { "step": 5651, "lr": 3.728136527709694e-05, "elapsed_s": 4199.248284339905, "loss": 3.1422083973884583, "hidden": 0.19626714289188385, "layer": 0.09301349148154259, "mlm": 1.5916087925434113, "distill": 1.111558586359024, "teacher_acc": 0.7172615081071854 }, { "step": 5661, "lr": 3.7237488198855876e-05, "elapsed_s": 4206.671406984329, "loss": 3.204590380191803, "hidden": 0.2027047574520111, "layer": 0.09622904472053051, "mlm": 1.5687493085861206, "distill": 1.1823169738054276, "teacher_acc": 0.7289220541715622 }, { "step": 5671, "lr": 3.719356149079621e-05, "elapsed_s": 4214.110413312912, "loss": 3.0182340145111084, "hidden": 0.19068153202533722, "layer": 0.09195774979889393, "mlm": 1.5081001818180084, "distill": 1.0827918648719788, "teacher_acc": 0.7312351614236832 }, { "step": 5681, "lr": 3.714958533106515e-05, "elapsed_s": 4221.516685962677, "loss": 3.059345841407776, "hidden": 0.19623732566833496, "layer": 0.09316440485417843, "mlm": 1.5153020322322845, "distill": 1.1049869656562805, "teacher_acc": 0.7332832366228104 }, { "step": 5691, "lr": 3.7105559898010494e-05, "elapsed_s": 4228.908064842224, "loss": 3.1445667147636414, "hidden": 0.19566473364830017, "layer": 0.09415927529335022, "mlm": 1.6187961399555206, "distill": 1.0873614251613617, "teacher_acc": 0.7032727003097534 }, { "step": 5701, "lr": 3.7061485370179835e-05, "elapsed_s": 4236.31845664978, "loss": 3.2046861052513123, "hidden": 0.19997898116707802, "layer": 0.0945882722735405, "mlm": 1.6236422955989838, "distill": 1.1337918043136597, "teacher_acc": 0.7056026309728622 }, { "step": 5711, "lr": 3.7017361926319896e-05, "elapsed_s": 4243.7177884578705, "loss": 3.1038458943367004, "hidden": 0.19729091599583626, "layer": 0.09275224432349205, "mlm": 1.586482435464859, "distill": 1.0764055252075195, "teacher_acc": 0.7129049301147461 }, { "step": 5721, "lr": 3.697318974537577e-05, "elapsed_s": 4251.103879213333, "loss": 3.051403284072876, "hidden": 0.19367704913020134, "layer": 0.09298089891672134, "mlm": 1.5436148047447205, "distill": 1.0739439129829407, "teacher_acc": 0.7275170981884003 }, { "step": 5731, "lr": 3.692896900649021e-05, "elapsed_s": 4258.504755020142, "loss": 3.067038655281067, "hidden": 0.19476135447621346, "layer": 0.0927730593830347, "mlm": 1.5237123668193817, "distill": 1.1074170470237732, "teacher_acc": 0.7217403054237366 }, { "step": 5741, "lr": 3.688469988900291e-05, "elapsed_s": 4265.913398742676, "loss": 3.1705139875411987, "hidden": 0.1984352320432663, "layer": 0.09342442825436592, "mlm": 1.6045320630073547, "distill": 1.1223991811275482, "teacher_acc": 0.7147362381219864 }, { "step": 5751, "lr": 3.684038257244973e-05, "elapsed_s": 4273.349415063858, "loss": 3.198856294155121, "hidden": 0.19722573086619377, "layer": 0.09326377883553505, "mlm": 1.6367175579071045, "distill": 1.1210553050041199, "teacher_acc": 0.7134540975093842 }, { "step": 5761, "lr": 3.679601723656205e-05, "elapsed_s": 4280.759192228317, "loss": 3.169144868850708, "hidden": 0.20101090148091316, "layer": 0.09429389424622059, "mlm": 1.563440889120102, "distill": 1.1565352976322174, "teacher_acc": 0.7204267382621765 }, { "step": 5771, "lr": 3.675160406126598e-05, "elapsed_s": 4288.193029165268, "loss": 2.99551260471344, "hidden": 0.1948242001235485, "layer": 0.09313718788325787, "mlm": 1.48704132437706, "distill": 1.0722542703151703, "teacher_acc": 0.7360995709896088 }, { "step": 5781, "lr": 3.670714322668162e-05, "elapsed_s": 4295.629599094391, "loss": 3.1230621337890625, "hidden": 0.1968647502362728, "layer": 0.09324252419173717, "mlm": 1.6089228093624115, "distill": 1.073788583278656, "teacher_acc": 0.714422807097435 }, { "step": 5791, "lr": 3.666263491312238e-05, "elapsed_s": 4303.059733390808, "loss": 3.0092450380325317, "hidden": 0.19525746628642082, "layer": 0.09211529977619648, "mlm": 1.4981193840503693, "distill": 1.0745531022548676, "teacher_acc": 0.7241339385509491 }, { "step": 5801, "lr": 3.6618079301094216e-05, "elapsed_s": 4310.493505001068, "loss": 3.0423428416252136, "hidden": 0.19879037514328957, "layer": 0.0931391753256321, "mlm": 1.479296863079071, "distill": 1.118895635008812, "teacher_acc": 0.7410182952880859 }, { "step": 5811, "lr": 3.657347657129491e-05, "elapsed_s": 4317.898047208786, "loss": 3.1755396127700806, "hidden": 0.19853822141885757, "layer": 0.0937601588666439, "mlm": 1.583716720342636, "distill": 1.1478663980960846, "teacher_acc": 0.7128798514604568 }, { "step": 5821, "lr": 3.652882690461334e-05, "elapsed_s": 4325.2860243320465, "loss": 3.2515771985054016, "hidden": 0.19827789068222046, "layer": 0.09446846134960651, "mlm": 1.602838009595871, "distill": 1.2049491703510284, "teacher_acc": 0.7194454222917557 }, { "step": 5831, "lr": 3.6484130482128715e-05, "elapsed_s": 4332.703218460083, "loss": 3.086265802383423, "hidden": 0.1916314736008644, "layer": 0.09231014735996723, "mlm": 1.599512666463852, "distill": 1.0573351681232452, "teacher_acc": 0.7085776925086975 }, { "step": 5841, "lr": 3.643938748510989e-05, "elapsed_s": 4340.10419178009, "loss": 3.0327399373054504, "hidden": 0.1957053691148758, "layer": 0.09257950261235237, "mlm": 1.539845734834671, "distill": 1.0551936775445938, "teacher_acc": 0.7189159691333771 }, { "step": 5851, "lr": 3.639459809501458e-05, "elapsed_s": 4347.500159978867, "loss": 3.088723659515381, "hidden": 0.19210728257894516, "layer": 0.0919422097504139, "mlm": 1.5582979321479797, "distill": 1.1002400517463684, "teacher_acc": 0.7227726727724075 }, { "step": 5861, "lr": 3.634976249348867e-05, "elapsed_s": 4354.860340356827, "loss": 3.0584779381752014, "hidden": 0.1946190930902958, "layer": 0.09212624467909336, "mlm": 1.5802371203899384, "distill": 1.0429396033287048, "teacher_acc": 0.7077350914478302 }, { "step": 5871, "lr": 3.630488086236547e-05, "elapsed_s": 4362.229564666748, "loss": 3.1185101866722107, "hidden": 0.2037334106862545, "layer": 0.09478634223341942, "mlm": 1.4842193126678467, "distill": 1.1794309318065643, "teacher_acc": 0.7386865317821503 }, { "step": 5881, "lr": 3.625995338366492e-05, "elapsed_s": 4369.605774641037, "loss": 3.1529953479766846, "hidden": 0.19466375559568405, "layer": 0.09312479197978973, "mlm": 1.6404542326927185, "distill": 1.0766512602567673, "teacher_acc": 0.6927720010280609 }, { "step": 5891, "lr": 3.621498023959294e-05, "elapsed_s": 4376.983222961426, "loss": 3.1072345972061157, "hidden": 0.19316312670707703, "layer": 0.09175510704517365, "mlm": 1.5583978593349457, "distill": 1.1166329085826874, "teacher_acc": 0.7226730734109879 }, { "step": 5901, "lr": 3.6169961612540645e-05, "elapsed_s": 4384.361966371536, "loss": 3.1410861015319824, "hidden": 0.19642717018723488, "layer": 0.0932257566601038, "mlm": 1.6337474584579468, "distill": 1.0678713917732239, "teacher_acc": 0.7094090729951859 }, { "step": 5911, "lr": 3.6124897685083584e-05, "elapsed_s": 4391.746059417725, "loss": 3.122596859931946, "hidden": 0.19022661074995995, "layer": 0.09268088825047016, "mlm": 1.6028250753879547, "distill": 1.0929780900478363, "teacher_acc": 0.7101231068372726 }, { "step": 5921, "lr": 3.6079788639981036e-05, "elapsed_s": 4399.142077207565, "loss": 3.0488314628601074, "hidden": 0.1918628141283989, "layer": 0.09250980243086815, "mlm": 1.5653907358646393, "distill": 1.053460106253624, "teacher_acc": 0.7140750288963318 }, { "step": 5931, "lr": 3.603463466017526e-05, "elapsed_s": 4406.547158718109, "loss": 3.2016438245773315, "hidden": 0.2022787220776081, "layer": 0.09421056509017944, "mlm": 1.6026907861232758, "distill": 1.1472904086112976, "teacher_acc": 0.7194232791662216 }, { "step": 5941, "lr": 3.598943592879076e-05, "elapsed_s": 4413.961395740509, "loss": 3.0697553753852844, "hidden": 0.19046977534890175, "layer": 0.09219641424715519, "mlm": 1.5915293097496033, "distill": 1.0511883199214935, "teacher_acc": 0.7116304337978363 }, { "step": 5951, "lr": 3.594419262913351e-05, "elapsed_s": 4421.36256814003, "loss": 3.200571119785309, "hidden": 0.19930657744407654, "layer": 0.09469421580433846, "mlm": 1.5993623733520508, "distill": 1.155248373746872, "teacher_acc": 0.7190072238445282 }, { "step": 5961, "lr": 3.5898904944690256e-05, "elapsed_s": 4428.778516054153, "loss": 3.1300723552703857, "hidden": 0.1962214782834053, "layer": 0.09300321899354458, "mlm": 1.535264402627945, "distill": 1.1558633297681808, "teacher_acc": 0.728346198797226 }, { "step": 5971, "lr": 3.585357305912773e-05, "elapsed_s": 4436.189889907837, "loss": 3.0895994305610657, "hidden": 0.1965099312365055, "layer": 0.09366054646670818, "mlm": 1.5356993675231934, "distill": 1.1140500605106354, "teacher_acc": 0.7267555892467499 }, { "step": 5981, "lr": 3.5808197156291937e-05, "elapsed_s": 4443.58362698555, "loss": 3.1897528171539307, "hidden": 0.19996138289570808, "layer": 0.09377051703631878, "mlm": 1.614856481552124, "distill": 1.128088265657425, "teacher_acc": 0.7175811231136322 }, { "step": 5991, "lr": 3.576277742020738e-05, "elapsed_s": 4450.93958067894, "loss": 3.1116180419921875, "hidden": 0.18896225839853287, "layer": 0.09107259847223759, "mlm": 1.5880478024482727, "distill": 1.1001093983650208, "teacher_acc": 0.7248478829860687 }, { "step": 6001, "lr": 3.5717314035076355e-05, "elapsed_s": 4460.279916763306, "loss": 3.104872941970825, "hidden": 0.19399436563253403, "layer": 0.09274009987711906, "mlm": 1.5995230972766876, "distill": 1.0709910988807678, "teacher_acc": 0.707163542509079 }, { "step": 6011, "lr": 3.567180718527816e-05, "elapsed_s": 4467.658266067505, "loss": 3.192289650440216, "hidden": 0.19655533879995346, "layer": 0.09295963495969772, "mlm": 1.6005885303020477, "distill": 1.152110606431961, "teacher_acc": 0.7297551035881042 }, { "step": 6021, "lr": 3.5626257055368386e-05, "elapsed_s": 4475.001597881317, "loss": 3.0388848781585693, "hidden": 0.19529186934232712, "layer": 0.09242597594857216, "mlm": 1.559584230184555, "distill": 1.0425038933753967, "teacher_acc": 0.7169177681207657 }, { "step": 6031, "lr": 3.558066383007811e-05, "elapsed_s": 4482.408060789108, "loss": 3.190236985683441, "hidden": 0.19664927944540977, "layer": 0.09323549456894398, "mlm": 1.6449633240699768, "distill": 1.1053574085235596, "teacher_acc": 0.7008141577243805 }, { "step": 6041, "lr": 3.553502769431323e-05, "elapsed_s": 4489.808842658997, "loss": 3.0385810136795044, "hidden": 0.19561300799250603, "layer": 0.09295208565890789, "mlm": 1.4677660167217255, "distill": 1.133112907409668, "teacher_acc": 0.7505103051662445 }, { "step": 6051, "lr": 3.5489348833153645e-05, "elapsed_s": 4497.222655534744, "loss": 2.949130356311798, "hidden": 0.18863296136260033, "layer": 0.09131281450390816, "mlm": 1.5205333232879639, "distill": 1.0056747049093246, "teacher_acc": 0.7218647748231888 }, { "step": 6061, "lr": 3.5443627431852526e-05, "elapsed_s": 4504.646123886108, "loss": 3.3349632620811462, "hidden": 0.2100144326686859, "layer": 0.096647834405303, "mlm": 1.6618981659412384, "distill": 1.2047122567892075, "teacher_acc": 0.7154448330402374 }, { "step": 6071, "lr": 3.539786367583559e-05, "elapsed_s": 4512.040123939514, "loss": 3.091992497444153, "hidden": 0.19086800888180733, "layer": 0.09352634474635124, "mlm": 1.569416880607605, "distill": 1.0940764546394348, "teacher_acc": 0.713665172457695 }, { "step": 6081, "lr": 3.53520577507003e-05, "elapsed_s": 4519.456461906433, "loss": 3.1018927097320557, "hidden": 0.19065378978848457, "layer": 0.09131838567554951, "mlm": 1.612713247537613, "distill": 1.062212586402893, "teacher_acc": 0.7119351029396057 }, { "step": 6091, "lr": 3.530620984221517e-05, "elapsed_s": 4526.869574069977, "loss": 3.012139081954956, "hidden": 0.19279375672340393, "layer": 0.09181579574942589, "mlm": 1.5358278453350067, "distill": 1.044815868139267, "teacher_acc": 0.7169939875602722 }, { "step": 6101, "lr": 3.526032013631893e-05, "elapsed_s": 4534.259119749069, "loss": 3.0672601461410522, "hidden": 0.19286799430847168, "layer": 0.09271782264113426, "mlm": 1.4937605261802673, "distill": 1.1414046883583069, "teacher_acc": 0.738550990819931 }, { "step": 6111, "lr": 3.5214388819119864e-05, "elapsed_s": 4541.676528930664, "loss": 3.055286705493927, "hidden": 0.1949954628944397, "layer": 0.0916488841176033, "mlm": 1.5192622542381287, "distill": 1.1002090722322464, "teacher_acc": 0.7315688729286194 }, { "step": 6121, "lr": 3.516841607689501e-05, "elapsed_s": 4549.03208231926, "loss": 3.195590913295746, "hidden": 0.19239870086312294, "layer": 0.09298037923872471, "mlm": 1.6326356530189514, "distill": 1.131667673587799, "teacher_acc": 0.7100181132555008 }, { "step": 6131, "lr": 3.512240209608938e-05, "elapsed_s": 4556.368154525757, "loss": 3.0735949873924255, "hidden": 0.1926220767199993, "layer": 0.09290842711925507, "mlm": 1.5498071014881134, "distill": 1.0920895338058472, "teacher_acc": 0.7250847518444061 }, { "step": 6141, "lr": 3.507634706331528e-05, "elapsed_s": 4563.721066951752, "loss": 3.0311434864997864, "hidden": 0.1887418068945408, "layer": 0.09088263474404812, "mlm": 1.584464967250824, "distill": 1.023753508925438, "teacher_acc": 0.7064801007509232 }, { "step": 6151, "lr": 3.5030251165351445e-05, "elapsed_s": 4571.082675695419, "loss": 3.0998308658599854, "hidden": 0.19653206691145897, "layer": 0.09295044653117657, "mlm": 1.5395187139511108, "distill": 1.120772808790207, "teacher_acc": 0.7304093241691589 }, { "step": 6161, "lr": 3.498411458914238e-05, "elapsed_s": 4578.449160814285, "loss": 3.131224513053894, "hidden": 0.20197837427258492, "layer": 0.0953552145510912, "mlm": 1.5389502346515656, "distill": 1.1406399607658386, "teacher_acc": 0.7261212170124054 }, { "step": 6171, "lr": 3.493793752179757e-05, "elapsed_s": 4585.777254581451, "loss": 3.2380929589271545, "hidden": 0.19713333621621132, "layer": 0.0939996987581253, "mlm": 1.6172708570957184, "distill": 1.179555594921112, "teacher_acc": 0.7169123888015747 }, { "step": 6181, "lr": 3.4891720150590665e-05, "elapsed_s": 4593.138922452927, "loss": 3.0120063424110413, "hidden": 0.19103293120861053, "layer": 0.09219476580619812, "mlm": 1.4685065150260925, "distill": 1.115336537361145, "teacher_acc": 0.7322067469358444 }, { "step": 6191, "lr": 3.484546266295883e-05, "elapsed_s": 4600.499802827835, "loss": 3.0194032192230225, "hidden": 0.18530699238181114, "layer": 0.09096686542034149, "mlm": 1.5847181379795074, "distill": 1.018587738275528, "teacher_acc": 0.7122793942689896 }, { "step": 6201, "lr": 3.479916524650188e-05, "elapsed_s": 4607.893656253815, "loss": 3.1598125100135803, "hidden": 0.1954488754272461, "layer": 0.0930603425949812, "mlm": 1.6145078539848328, "distill": 1.107876718044281, "teacher_acc": 0.7155182659626007 }, { "step": 6211, "lr": 3.4752828088981584e-05, "elapsed_s": 4615.286079645157, "loss": 2.980879783630371, "hidden": 0.19297680258750916, "layer": 0.09258772619068623, "mlm": 1.4769399464130402, "distill": 1.0716923475265503, "teacher_acc": 0.7333994060754776 }, { "step": 6221, "lr": 3.470645137832087e-05, "elapsed_s": 4622.7002012729645, "loss": 3.074561297893524, "hidden": 0.1925695240497589, "layer": 0.09185802191495895, "mlm": 1.4929607510566711, "distill": 1.150532603263855, "teacher_acc": 0.7423826605081558 }, { "step": 6231, "lr": 3.46600353026031e-05, "elapsed_s": 4630.108730554581, "loss": 3.13653302192688, "hidden": 0.19634933024644852, "layer": 0.09385943599045277, "mlm": 1.5030692517757416, "distill": 1.1938354074954987, "teacher_acc": 0.7433117628097534 }, { "step": 6241, "lr": 3.461358005007128e-05, "elapsed_s": 4637.474723100662, "loss": 3.1633260846138, "hidden": 0.1962810531258583, "layer": 0.09334804303944111, "mlm": 1.6518783271312714, "distill": 1.072211593389511, "teacher_acc": 0.6963322460651398 }, { "step": 6251, "lr": 3.456708580912725e-05, "elapsed_s": 4644.8981194496155, "loss": 3.2563687562942505, "hidden": 0.19847261533141136, "layer": 0.09264726936817169, "mlm": 1.6695808470249176, "distill": 1.143519103527069, "teacher_acc": 0.7036411464214325 }, { "step": 6261, "lr": 3.452055276833103e-05, "elapsed_s": 4652.290805101395, "loss": 3.1242244243621826, "hidden": 0.1947631500661373, "layer": 0.09387802891433239, "mlm": 1.612898826599121, "distill": 1.0748602598905563, "teacher_acc": 0.7127125412225723 }, { "step": 6271, "lr": 3.447398111639997e-05, "elapsed_s": 4659.686680793762, "loss": 3.093975841999054, "hidden": 0.19122236594557762, "layer": 0.09244493581354618, "mlm": 1.5185782313346863, "distill": 1.1467305123806, "teacher_acc": 0.7303605824708939 }, { "step": 6281, "lr": 3.442737104220801e-05, "elapsed_s": 4667.111065626144, "loss": 3.1411534547805786, "hidden": 0.19359271600842476, "layer": 0.09279880858957767, "mlm": 1.5820659697055817, "distill": 1.1255027055740356, "teacher_acc": 0.7189823538064957 }, { "step": 6291, "lr": 3.438072273478493e-05, "elapsed_s": 4674.509824991226, "loss": 2.973774790763855, "hidden": 0.18445955216884613, "layer": 0.09088463708758354, "mlm": 1.5108748078346252, "distill": 1.0485386103391647, "teacher_acc": 0.7243620008230209 }, { "step": 6301, "lr": 3.433403638331553e-05, "elapsed_s": 4681.923840522766, "loss": 3.1949153542518616, "hidden": 0.1940714418888092, "layer": 0.09177921526134014, "mlm": 1.6279211044311523, "distill": 1.1329616904258728, "teacher_acc": 0.7126029282808304 }, { "step": 6311, "lr": 3.428731217713893e-05, "elapsed_s": 4689.32967042923, "loss": 3.1435269713401794, "hidden": 0.1929805986583233, "layer": 0.0920780636370182, "mlm": 1.6183415651321411, "distill": 1.0931851863861084, "teacher_acc": 0.7095890939235687 }, { "step": 6321, "lr": 3.424055030574778e-05, "elapsed_s": 4696.747277021408, "loss": 2.9731759428977966, "hidden": 0.19011976197361946, "layer": 0.09108774363994598, "mlm": 1.506452888250351, "distill": 1.040939599275589, "teacher_acc": 0.7180880010128021 }, { "step": 6331, "lr": 3.419375095878744e-05, "elapsed_s": 4704.159867048264, "loss": 2.9945162534713745, "hidden": 0.18684181943535805, "layer": 0.09163513779640198, "mlm": 1.5197808742523193, "distill": 1.0552342236042023, "teacher_acc": 0.7267776876688004 }, { "step": 6341, "lr": 3.414691432605531e-05, "elapsed_s": 4711.619735956192, "loss": 3.089985728263855, "hidden": 0.19372475519776344, "layer": 0.09256158955395222, "mlm": 1.5048571527004242, "distill": 1.1513982713222504, "teacher_acc": 0.7379518151283264 }, { "step": 6351, "lr": 3.410004059749996e-05, "elapsed_s": 4719.052491188049, "loss": 3.0789005756378174, "hidden": 0.1967955306172371, "layer": 0.09230436943471432, "mlm": 1.5036981701850891, "distill": 1.135459154844284, "teacher_acc": 0.7352399528026581 }, { "step": 6361, "lr": 3.405312996322042e-05, "elapsed_s": 4726.476742744446, "loss": 3.0318517684936523, "hidden": 0.18728180974721909, "layer": 0.09061502665281296, "mlm": 1.5571210980415344, "distill": 1.054859533905983, "teacher_acc": 0.7130605429410934 }, { "step": 6371, "lr": 3.400618261346541e-05, "elapsed_s": 4733.878169059753, "loss": 3.032357692718506, "hidden": 0.18507330864667892, "layer": 0.09065103530883789, "mlm": 1.560399204492569, "distill": 1.0564863234758377, "teacher_acc": 0.7204049080610275 }, { "step": 6381, "lr": 3.39591987386325e-05, "elapsed_s": 4741.28510761261, "loss": 3.0905752182006836, "hidden": 0.19499319791793823, "layer": 0.09273175895214081, "mlm": 1.5539273619651794, "distill": 1.100295603275299, "teacher_acc": 0.7185826301574707 }, { "step": 6391, "lr": 3.391217852926748e-05, "elapsed_s": 4748.716134309769, "loss": 3.162065804004669, "hidden": 0.19218286499381065, "layer": 0.09223482571542263, "mlm": 1.6156118214130402, "distill": 1.1159708499908447, "teacher_acc": 0.7138348519802094 }, { "step": 6401, "lr": 3.386512217606339e-05, "elapsed_s": 4756.144778251648, "loss": 3.103502035140991, "hidden": 0.1960962563753128, "layer": 0.09236952103674412, "mlm": 1.532025545835495, "distill": 1.1330991983413696, "teacher_acc": 0.7234564572572708 }, { "step": 6411, "lr": 3.3818029869859936e-05, "elapsed_s": 4763.560351133347, "loss": 3.100357413291931, "hidden": 0.19265703111886978, "layer": 0.09179454669356346, "mlm": 1.6009341776371002, "distill": 1.068211942911148, "teacher_acc": 0.7109077572822571 }, { "step": 6421, "lr": 3.3770901801642595e-05, "elapsed_s": 4770.972047805786, "loss": 3.0820988416671753, "hidden": 0.19485889747738838, "layer": 0.09259810857474804, "mlm": 1.5118177235126495, "distill": 1.134264349937439, "teacher_acc": 0.7367132753133774 }, { "step": 6431, "lr": 3.3723738162541876e-05, "elapsed_s": 4778.382648944855, "loss": 3.0686978101730347, "hidden": 0.19695492461323738, "layer": 0.09331716783344746, "mlm": 1.4770510792732239, "distill": 1.1510784029960632, "teacher_acc": 0.7403425425291061 }, { "step": 6441, "lr": 3.367653914383257e-05, "elapsed_s": 4785.777971744537, "loss": 3.0721373558044434, "hidden": 0.19112543389201164, "layer": 0.09181712381541729, "mlm": 1.5336134135723114, "distill": 1.1103644967079163, "teacher_acc": 0.7308970391750336 }, { "step": 6451, "lr": 3.362930493693295e-05, "elapsed_s": 4793.159542798996, "loss": 2.9649736881256104, "hidden": 0.18709658831357956, "layer": 0.09151283837854862, "mlm": 1.4864593744277954, "distill": 1.058564692735672, "teacher_acc": 0.7190053462982178 }, { "step": 6461, "lr": 3.358203573340396e-05, "elapsed_s": 4800.549548864365, "loss": 3.054726719856262, "hidden": 0.1893276758491993, "layer": 0.0914696604013443, "mlm": 1.572209745645523, "distill": 1.0581267476081848, "teacher_acc": 0.7191956490278244 }, { "step": 6471, "lr": 3.353473172494852e-05, "elapsed_s": 4807.918670415878, "loss": 3.14129638671875, "hidden": 0.19660811871290207, "layer": 0.09350453689694405, "mlm": 1.5831890404224396, "distill": 1.1181388795375824, "teacher_acc": 0.7138730883598328 }, { "step": 6481, "lr": 3.348739310341068e-05, "elapsed_s": 4815.320013046265, "loss": 3.100082576274872, "hidden": 0.19121718034148216, "layer": 0.09285282902419567, "mlm": 1.5914396941661835, "distill": 1.0797822177410126, "teacher_acc": 0.7088670581579208 }, { "step": 6491, "lr": 3.344002006077487e-05, "elapsed_s": 4822.720309495926, "loss": 3.086649239063263, "hidden": 0.1941196583211422, "layer": 0.09270430542528629, "mlm": 1.5763840079307556, "distill": 1.0756738036870956, "teacher_acc": 0.7164540588855743 }, { "step": 6501, "lr": 3.339261278916512e-05, "elapsed_s": 4830.096178293228, "loss": 3.1435670256614685, "hidden": 0.1970505379140377, "layer": 0.09375018440186977, "mlm": 1.5892204344272614, "distill": 1.1133703738451004, "teacher_acc": 0.716537281870842 }, { "step": 6511, "lr": 3.3345171480844275e-05, "elapsed_s": 4837.47211265564, "loss": 3.0550175309181213, "hidden": 0.19547664374113083, "layer": 0.09262915141880512, "mlm": 1.5328003764152527, "distill": 1.084949404001236, "teacher_acc": 0.727649912238121 }, { "step": 6521, "lr": 3.329769632821321e-05, "elapsed_s": 4844.863247156143, "loss": 3.157544434070587, "hidden": 0.19395290315151215, "layer": 0.0920556802302599, "mlm": 1.5867230296134949, "distill": 1.1368877291679382, "teacher_acc": 0.7227001935243607 }, { "step": 6531, "lr": 3.3250187523810074e-05, "elapsed_s": 4852.246895074844, "loss": 3.0899821519851685, "hidden": 0.19362366572022438, "layer": 0.09250318631529808, "mlm": 1.562640905380249, "distill": 1.0938422977924347, "teacher_acc": 0.7261867374181747 }, { "step": 6541, "lr": 3.3202645260309484e-05, "elapsed_s": 4859.687425136566, "loss": 2.960499405860901, "hidden": 0.19107167795300484, "layer": 0.09141702950000763, "mlm": 1.4866342842578888, "distill": 1.046013206243515, "teacher_acc": 0.7326999008655548 }, { "step": 6551, "lr": 3.3155069730521735e-05, "elapsed_s": 4867.129043340683, "loss": 3.1678892374038696, "hidden": 0.19265920296311378, "layer": 0.09390268661081791, "mlm": 1.592348963022232, "distill": 1.1432705223560333, "teacher_acc": 0.7236759662628174 }, { "step": 6561, "lr": 3.310746112739207e-05, "elapsed_s": 4874.547936201096, "loss": 2.8335387110710144, "hidden": 0.18653929233551025, "layer": 0.09028731659054756, "mlm": 1.4007984399795532, "distill": 1.0145180076360703, "teacher_acc": 0.7442683577537537 }, { "step": 6571, "lr": 3.305981964399984e-05, "elapsed_s": 4881.953952074051, "loss": 2.99005126953125, "hidden": 0.19211777672171593, "layer": 0.0928332582116127, "mlm": 1.490359902381897, "distill": 1.069039136171341, "teacher_acc": 0.7327405512332916 }, { "step": 6581, "lr": 3.301214547355774e-05, "elapsed_s": 4889.365768194199, "loss": 2.935452938079834, "hidden": 0.1935550682246685, "layer": 0.09252864494919777, "mlm": 1.4317081272602081, "distill": 1.0703704059123993, "teacher_acc": 0.7416944652795792 }, { "step": 6591, "lr": 3.296443880941106e-05, "elapsed_s": 4896.7523238658905, "loss": 2.9808900952339172, "hidden": 0.18906664475798607, "layer": 0.09109768085181713, "mlm": 1.5382168889045715, "distill": 1.0189910978078842, "teacher_acc": 0.7174976319074631 }, { "step": 6601, "lr": 3.2916699845036816e-05, "elapsed_s": 4904.1211133003235, "loss": 3.0441697239875793, "hidden": 0.1883394420146942, "layer": 0.09216994792222977, "mlm": 1.5635958909988403, "distill": 1.057809978723526, "teacher_acc": 0.7177467197179794 }, { "step": 6611, "lr": 3.286892877404307e-05, "elapsed_s": 4911.519555091858, "loss": 3.128444194793701, "hidden": 0.19554823637008667, "layer": 0.09384314715862274, "mlm": 1.5746730864048004, "distill": 1.1157531142234802, "teacher_acc": 0.7204395979642868 }, { "step": 6621, "lr": 3.282112579016808e-05, "elapsed_s": 4918.904745101929, "loss": 3.121576249599457, "hidden": 0.1997637078166008, "layer": 0.09400556981563568, "mlm": 1.5162419974803925, "distill": 1.158804014325142, "teacher_acc": 0.7303462326526642 }, { "step": 6631, "lr": 3.277329108727951e-05, "elapsed_s": 4926.328701257706, "loss": 3.1097660660743713, "hidden": 0.189231526106596, "layer": 0.09152696095407009, "mlm": 1.6516403555870056, "distill": 1.0338991731405258, "teacher_acc": 0.7059909999370575 }, { "step": 6641, "lr": 3.272542485937369e-05, "elapsed_s": 4933.771844148636, "loss": 3.0863441824913025, "hidden": 0.19343487545847893, "layer": 0.09309600107371807, "mlm": 1.5646571815013885, "distill": 1.0882692486047745, "teacher_acc": 0.7150850892066956 }, { "step": 6651, "lr": 3.267752730057477e-05, "elapsed_s": 4941.220808506012, "loss": 3.063106656074524, "hidden": 0.18942636251449585, "layer": 0.09161435253918171, "mlm": 1.54872065782547, "distill": 1.0897260904312134, "teacher_acc": 0.7225798815488815 }, { "step": 6661, "lr": 3.2629598605133996e-05, "elapsed_s": 4948.6432929039, "loss": 3.113893747329712, "hidden": 0.193775475025177, "layer": 0.09305213578045368, "mlm": 1.5490150451660156, "distill": 1.1308017075061798, "teacher_acc": 0.7287840694189072 }, { "step": 6671, "lr": 3.258163896742888e-05, "elapsed_s": 4956.052638292313, "loss": 3.068621039390564, "hidden": 0.19501608982682228, "layer": 0.09242750890552998, "mlm": 1.5083639025688171, "distill": 1.1240111887454987, "teacher_acc": 0.7380156069993973 }, { "step": 6681, "lr": 3.2533648581962404e-05, "elapsed_s": 4963.4812223911285, "loss": 3.1689722537994385, "hidden": 0.19149839878082275, "layer": 0.09236111864447594, "mlm": 1.6389763951301575, "distill": 1.1008186042308807, "teacher_acc": 0.7034313976764679 }, { "step": 6691, "lr": 3.248562764336226e-05, "elapsed_s": 4970.899342775345, "loss": 3.0094494223594666, "hidden": 0.1891632340848446, "layer": 0.09222275018692017, "mlm": 1.475536733865738, "distill": 1.1094749569892883, "teacher_acc": 0.7446059137582779 }, { "step": 6701, "lr": 3.243757634638008e-05, "elapsed_s": 4978.2990798950195, "loss": 3.0460970997810364, "hidden": 0.19436076655983925, "layer": 0.0914185643196106, "mlm": 1.5273028016090393, "distill": 1.0843634903430939, "teacher_acc": 0.7241494357585907 }, { "step": 6711, "lr": 3.238949488589056e-05, "elapsed_s": 4985.680917739868, "loss": 2.995810627937317, "hidden": 0.19724280387163162, "layer": 0.09163709543645382, "mlm": 1.4350907802581787, "distill": 1.1204157173633575, "teacher_acc": 0.7484878897666931 }, { "step": 6721, "lr": 3.234138345689077e-05, "elapsed_s": 4993.111385822296, "loss": 3.1268614530563354, "hidden": 0.19544949010014534, "layer": 0.0933297649025917, "mlm": 1.5857884883880615, "distill": 1.1035090684890747, "teacher_acc": 0.726325511932373 }, { "step": 6731, "lr": 3.22932422544993e-05, "elapsed_s": 5000.533604383469, "loss": 3.1060794591903687, "hidden": 0.1927817091345787, "layer": 0.09361829981207848, "mlm": 1.5479795932769775, "distill": 1.1257272362709045, "teacher_acc": 0.7274075001478195 }, { "step": 6741, "lr": 3.2245071473955505e-05, "elapsed_s": 5007.960158586502, "loss": 3.088205575942993, "hidden": 0.19429773464798927, "layer": 0.09291867725551128, "mlm": 1.503915011882782, "distill": 1.1492358148097992, "teacher_acc": 0.7314756512641907 }, { "step": 6751, "lr": 3.2196871310618655e-05, "elapsed_s": 5015.370353460312, "loss": 3.070266008377075, "hidden": 0.18851029872894287, "layer": 0.09133115224540234, "mlm": 1.6062949001789093, "distill": 1.0412848889827728, "teacher_acc": 0.7115263342857361 }, { "step": 6761, "lr": 3.214864195996723e-05, "elapsed_s": 5022.797037124634, "loss": 3.345462739467621, "hidden": 0.20098154619336128, "layer": 0.095725879073143, "mlm": 1.651926040649414, "distill": 1.2437106668949127, "teacher_acc": 0.7080221474170685 }, { "step": 6771, "lr": 3.210038361759807e-05, "elapsed_s": 5030.223799467087, "loss": 3.1520798206329346, "hidden": 0.1933206506073475, "layer": 0.09275970607995987, "mlm": 1.6026111841201782, "distill": 1.1164474189281464, "teacher_acc": 0.7200828641653061 }, { "step": 6781, "lr": 3.2052096479225566e-05, "elapsed_s": 5037.619102716446, "loss": 3.073320508003235, "hidden": 0.1901359036564827, "layer": 0.09135800041258335, "mlm": 1.607835054397583, "distill": 1.0395347476005554, "teacher_acc": 0.702377662062645 }, { "step": 6791, "lr": 3.200378074068092e-05, "elapsed_s": 5045.027637481689, "loss": 2.9630327820777893, "hidden": 0.188953448086977, "layer": 0.08973542228341103, "mlm": 1.4481555819511414, "distill": 1.092102587223053, "teacher_acc": 0.7447509914636612 }, { "step": 6801, "lr": 3.195543659791132e-05, "elapsed_s": 5052.455496072769, "loss": 3.184573531150818, "hidden": 0.19670430198311806, "layer": 0.09374848380684853, "mlm": 1.598709374666214, "distill": 1.1455812454223633, "teacher_acc": 0.7238747477531433 }, { "step": 6811, "lr": 3.1907064246979134e-05, "elapsed_s": 5059.8716452121735, "loss": 3.1014814376831055, "hidden": 0.198008444160223, "layer": 0.09327641502022743, "mlm": 1.526116669178009, "distill": 1.13270965218544, "teacher_acc": 0.7400634735822678 }, { "step": 6821, "lr": 3.185866388406115e-05, "elapsed_s": 5067.277510404587, "loss": 3.0280473232269287, "hidden": 0.1882462352514267, "layer": 0.09147290326654911, "mlm": 1.5396287739276886, "distill": 1.0661896169185638, "teacher_acc": 0.7172193676233292 }, { "step": 6831, "lr": 3.1810235705447736e-05, "elapsed_s": 5074.721405267715, "loss": 3.0405390858650208, "hidden": 0.18884649127721786, "layer": 0.09161466173827648, "mlm": 1.5616739392280579, "distill": 1.0553647875785828, "teacher_acc": 0.7242964059114456 }, { "step": 6841, "lr": 3.17617799075421e-05, "elapsed_s": 5082.147145748138, "loss": 3.150662899017334, "hidden": 0.19792652130126953, "layer": 0.09250216372311115, "mlm": 1.5923795104026794, "distill": 1.1161792576313019, "teacher_acc": 0.7144245207309723 }, { "step": 6851, "lr": 3.1713296686859426e-05, "elapsed_s": 5089.5581521987915, "loss": 3.0511292219161987, "hidden": 0.19369656592607498, "layer": 0.09194767847657204, "mlm": 1.5319861769676208, "distill": 1.0857761055231094, "teacher_acc": 0.722461998462677 }, { "step": 6861, "lr": 3.1664786240026136e-05, "elapsed_s": 5096.961491107941, "loss": 3.1119178533554077, "hidden": 0.19246786460280418, "layer": 0.093105249106884, "mlm": 1.5724062025547028, "distill": 1.1080233305692673, "teacher_acc": 0.7188770174980164 }, { "step": 6871, "lr": 3.161624876377906e-05, "elapsed_s": 5104.37891125679, "loss": 2.998623847961426, "hidden": 0.1897561028599739, "layer": 0.09041817486286163, "mlm": 1.5298241972923279, "distill": 1.0440782606601715, "teacher_acc": 0.723378375172615 }, { "step": 6881, "lr": 3.1567684454964675e-05, "elapsed_s": 5111.760212421417, "loss": 3.081710457801819, "hidden": 0.1989128142595291, "layer": 0.09478523023426533, "mlm": 1.5313127040863037, "distill": 1.105179488658905, "teacher_acc": 0.7259162366390228 }, { "step": 6891, "lr": 3.151909351053823e-05, "elapsed_s": 5119.181850194931, "loss": 3.1680506467819214, "hidden": 0.19792239367961884, "layer": 0.09328272752463818, "mlm": 1.6033442616462708, "distill": 1.1222202479839325, "teacher_acc": 0.7137023061513901 }, { "step": 6901, "lr": 3.147047612756302e-05, "elapsed_s": 5126.566792726517, "loss": 2.959702789783478, "hidden": 0.18608924001455307, "layer": 0.08934372663497925, "mlm": 1.5162666141986847, "distill": 1.0265858322381973, "teacher_acc": 0.7216834425926208 }, { "step": 6911, "lr": 3.142183250320957e-05, "elapsed_s": 5133.949009418488, "loss": 3.019935131072998, "hidden": 0.19341742992401123, "layer": 0.09184035658836365, "mlm": 1.5181127786636353, "distill": 1.069067269563675, "teacher_acc": 0.7371430695056915 }, { "step": 6921, "lr": 3.1373162834754834e-05, "elapsed_s": 5141.373652458191, "loss": 2.9760284423828125, "hidden": 0.18533772975206375, "layer": 0.09004099853336811, "mlm": 1.5557239651679993, "distill": 1.0046085268259048, "teacher_acc": 0.7127281129360199 }, { "step": 6931, "lr": 3.1324467319581355e-05, "elapsed_s": 5148.793612003326, "loss": 2.9915781021118164, "hidden": 0.18876386806368828, "layer": 0.09078200161457062, "mlm": 1.529301106929779, "distill": 1.0393582582473755, "teacher_acc": 0.721349835395813 }, { "step": 6941, "lr": 3.1275746155176546e-05, "elapsed_s": 5156.1771676540375, "loss": 3.071367561817169, "hidden": 0.19733679667115211, "layer": 0.0927790105342865, "mlm": 1.520515352487564, "distill": 1.109789103269577, "teacher_acc": 0.7285658717155457 }, { "step": 6951, "lr": 3.12269995391318e-05, "elapsed_s": 5163.591950416565, "loss": 3.040101647377014, "hidden": 0.19054826349020004, "layer": 0.09138341248035431, "mlm": 1.4911785125732422, "distill": 1.1221349835395813, "teacher_acc": 0.7426030337810516 }, { "step": 6961, "lr": 3.1178227669141744e-05, "elapsed_s": 5170.970824480057, "loss": 3.2094080448150635, "hidden": 0.19569090753793716, "layer": 0.0930653065443039, "mlm": 1.6358653903007507, "distill": 1.1356281042099, "teacher_acc": 0.7002932280302048 }, { "step": 6971, "lr": 3.112943074300344e-05, "elapsed_s": 5178.367203235626, "loss": 3.0443124771118164, "hidden": 0.18877273052930832, "layer": 0.09133052453398705, "mlm": 1.568383514881134, "distill": 1.0527182072401047, "teacher_acc": 0.7202931046485901 }, { "step": 6981, "lr": 3.108060895861555e-05, "elapsed_s": 5185.790980100632, "loss": 3.1210193037986755, "hidden": 0.19748305901885033, "layer": 0.09336615353822708, "mlm": 1.5967898964881897, "distill": 1.082580327987671, "teacher_acc": 0.7124812453985214 }, { "step": 6991, "lr": 3.103176251397756e-05, "elapsed_s": 5193.194725036621, "loss": 3.1837591528892517, "hidden": 0.19740600511431694, "layer": 0.09489451162517071, "mlm": 1.613466054201126, "distill": 1.1280338615179062, "teacher_acc": 0.7135652899742126 }, { "step": 7001, "lr": 3.098289160718895e-05, "elapsed_s": 5202.589289188385, "loss": 3.0009286999702454, "hidden": 0.19027046486735344, "layer": 0.09135977365076542, "mlm": 1.4727427065372467, "distill": 1.1019651293754578, "teacher_acc": 0.7417635917663574 }, { "step": 7011, "lr": 3.093399643644842e-05, "elapsed_s": 5209.9331138134, "loss": 3.109593629837036, "hidden": 0.19878026843070984, "layer": 0.09495226666331291, "mlm": 1.4822051525115967, "distill": 1.1823517978191376, "teacher_acc": 0.7377219349145889 }, { "step": 7021, "lr": 3.0885077200053086e-05, "elapsed_s": 5217.281810283661, "loss": 3.0813854932785034, "hidden": 0.18865623697638512, "layer": 0.09211434796452522, "mlm": 1.6016297340393066, "distill": 1.0563861429691315, "teacher_acc": 0.7121593803167343 }, { "step": 7031, "lr": 3.083613409639764e-05, "elapsed_s": 5224.636778831482, "loss": 3.027763605117798, "hidden": 0.19090311601758003, "layer": 0.09206153452396393, "mlm": 1.5396234691143036, "distill": 1.0603031814098358, "teacher_acc": 0.7226303815841675 }, { "step": 7041, "lr": 3.078716732397358e-05, "elapsed_s": 5232.017203569412, "loss": 3.113310396671295, "hidden": 0.1947733648121357, "layer": 0.09276142157614231, "mlm": 1.592847317457199, "distill": 1.0845356285572052, "teacher_acc": 0.7032542377710342 }, { "step": 7051, "lr": 3.073817708136839e-05, "elapsed_s": 5239.434553146362, "loss": 2.982120990753174, "hidden": 0.1879071556031704, "layer": 0.09047316014766693, "mlm": 1.508483111858368, "distill": 1.052587017416954, "teacher_acc": 0.7232035845518112 }, { "step": 7061, "lr": 3.068916356726475e-05, "elapsed_s": 5246.876905679703, "loss": 3.029772698879242, "hidden": 0.19194410368800163, "layer": 0.09143619798123837, "mlm": 1.5159733593463898, "distill": 1.084193080663681, "teacher_acc": 0.7379245758056641 }, { "step": 7071, "lr": 3.064012698043972e-05, "elapsed_s": 5254.292939186096, "loss": 2.9173487424850464, "hidden": 0.18981150910258293, "layer": 0.09117615409195423, "mlm": 1.4385906457901, "distill": 1.0535470694303513, "teacher_acc": 0.7415085732936859 }, { "step": 7081, "lr": 3.0591067519763895e-05, "elapsed_s": 5261.71030497551, "loss": 3.086690664291382, "hidden": 0.1918393149971962, "layer": 0.09144704043865204, "mlm": 1.5868307948112488, "distill": 1.0704577267169952, "teacher_acc": 0.7155803143978119 }, { "step": 7091, "lr": 3.0541985384200686e-05, "elapsed_s": 5269.148916959763, "loss": 3.0205820202827454, "hidden": 0.19150079414248466, "layer": 0.09195362590253353, "mlm": 1.5693199336528778, "distill": 1.0222836285829544, "teacher_acc": 0.7204276323318481 }, { "step": 7101, "lr": 3.0492880772805433e-05, "elapsed_s": 5276.561764001846, "loss": 3.089262306690216, "hidden": 0.19368674978613853, "layer": 0.09256312064826488, "mlm": 1.5087122917175293, "distill": 1.1468949019908905, "teacher_acc": 0.7371128350496292 }, { "step": 7111, "lr": 3.044375388472464e-05, "elapsed_s": 5283.994080543518, "loss": 2.975350260734558, "hidden": 0.18741286545991898, "layer": 0.0907050184905529, "mlm": 1.5497384369373322, "distill": 1.005433663725853, "teacher_acc": 0.7283224910497665 }, { "step": 7121, "lr": 3.0394604919195156e-05, "elapsed_s": 5291.404820919037, "loss": 3.03240966796875, "hidden": 0.18648329004645348, "layer": 0.09007862396538258, "mlm": 1.5395373702049255, "distill": 1.074866384267807, "teacher_acc": 0.7247832864522934 }, { "step": 7131, "lr": 3.0345434075543354e-05, "elapsed_s": 5298.832231998444, "loss": 2.946578860282898, "hidden": 0.1795550175011158, "layer": 0.08789872750639915, "mlm": 1.5550656914710999, "distill": 0.9884537607431412, "teacher_acc": 0.7110612243413925 }, { "step": 7141, "lr": 3.0296241553184362e-05, "elapsed_s": 5306.259646654129, "loss": 3.0904070138931274, "hidden": 0.1931934393942356, "layer": 0.09335710667073727, "mlm": 1.5571808218955994, "distill": 1.1001607775688171, "teacher_acc": 0.7159523516893387 }, { "step": 7151, "lr": 3.024702755162119e-05, "elapsed_s": 5313.671886205673, "loss": 3.080600678920746, "hidden": 0.18544824421405792, "layer": 0.09086282178759575, "mlm": 1.5931247174739838, "distill": 1.071148008108139, "teacher_acc": 0.7137468606233597 }, { "step": 7161, "lr": 3.0197792270443982e-05, "elapsed_s": 5321.093729496002, "loss": 2.995771586894989, "hidden": 0.18957290798425674, "layer": 0.09223783202469349, "mlm": 1.4757322072982788, "distill": 1.0947747081518173, "teacher_acc": 0.7404986172914505 }, { "step": 7171, "lr": 3.0148535909329185e-05, "elapsed_s": 5328.505641937256, "loss": 3.1087055802345276, "hidden": 0.20082856714725494, "layer": 0.0950765497982502, "mlm": 1.479261964559555, "distill": 1.180248200893402, "teacher_acc": 0.742479607462883 }, { "step": 7181, "lr": 3.009925866803872e-05, "elapsed_s": 5335.9043226242065, "loss": 3.051198720932007, "hidden": 0.19042016565799713, "layer": 0.09104670397937298, "mlm": 1.5633728206157684, "distill": 1.0614622235298157, "teacher_acc": 0.7152037024497986 }, { "step": 7191, "lr": 3.0049960746419205e-05, "elapsed_s": 5343.29391336441, "loss": 3.1746583580970764, "hidden": 0.20141048729419708, "layer": 0.09385591745376587, "mlm": 1.551397442817688, "distill": 1.1735118925571442, "teacher_acc": 0.7325659543275833 }, { "step": 7201, "lr": 3.0000642344401113e-05, "elapsed_s": 5350.691730976105, "loss": 3.0568103194236755, "hidden": 0.1941068433225155, "layer": 0.09366768971085548, "mlm": 1.495560646057129, "distill": 1.1262021362781525, "teacher_acc": 0.7357208132743835 }, { "step": 7211, "lr": 2.9951303661997994e-05, "elapsed_s": 5358.096495389938, "loss": 3.0217697620391846, "hidden": 0.1900668479502201, "layer": 0.09107355959713459, "mlm": 1.5312622487545013, "distill": 1.064837023615837, "teacher_acc": 0.716829776763916 }, { "step": 7221, "lr": 2.9901944899305634e-05, "elapsed_s": 5365.534209728241, "loss": 3.041344165802002, "hidden": 0.1867748312652111, "layer": 0.09121344797313213, "mlm": 1.5269192457199097, "distill": 1.0952685177326202, "teacher_acc": 0.7284190654754639 }, { "step": 7231, "lr": 2.985256625650125e-05, "elapsed_s": 5372.942424058914, "loss": 3.056334376335144, "hidden": 0.18949979916214943, "layer": 0.09091497026383877, "mlm": 1.5422196686267853, "distill": 1.089657574892044, "teacher_acc": 0.7233892679214478 }, { "step": 7241, "lr": 2.9803167933842714e-05, "elapsed_s": 5380.352122306824, "loss": 3.096451222896576, "hidden": 0.19823025912046432, "layer": 0.09320971556007862, "mlm": 1.506306141614914, "distill": 1.1470797061920166, "teacher_acc": 0.7353167086839676 }, { "step": 7251, "lr": 2.975375013166767e-05, "elapsed_s": 5387.792006969452, "loss": 3.0039161443710327, "hidden": 0.1897176057100296, "layer": 0.09119299799203873, "mlm": 1.4622952342033386, "distill": 1.116589218378067, "teacher_acc": 0.7452525645494461 }, { "step": 7261, "lr": 2.9704313050392784e-05, "elapsed_s": 5395.225994110107, "loss": 3.038465201854706, "hidden": 0.1900322064757347, "layer": 0.09257050603628159, "mlm": 1.5043206214904785, "distill": 1.1077949106693268, "teacher_acc": 0.737324059009552 }, { "step": 7271, "lr": 2.9654856890512923e-05, "elapsed_s": 5402.645349264145, "loss": 3.0819523334503174, "hidden": 0.1897885426878929, "layer": 0.09236268512904644, "mlm": 1.522098958492279, "distill": 1.1340949833393097, "teacher_acc": 0.7331811189651489 }, { "step": 7281, "lr": 2.960538185260029e-05, "elapsed_s": 5410.090573787689, "loss": 2.996766448020935, "hidden": 0.18811232969164848, "layer": 0.09148579835891724, "mlm": 1.477211058139801, "distill": 1.097587689757347, "teacher_acc": 0.7354803681373596 }, { "step": 7291, "lr": 2.9555888137303695e-05, "elapsed_s": 5417.5196833610535, "loss": 3.0930901765823364, "hidden": 0.1921503245830536, "layer": 0.09215942770242691, "mlm": 1.5601767599582672, "distill": 1.102532982826233, "teacher_acc": 0.7198748290538788 }, { "step": 7301, "lr": 2.950637594534765e-05, "elapsed_s": 5424.924043893814, "loss": 3.108459174633026, "hidden": 0.1888951063156128, "layer": 0.09175702184438705, "mlm": 1.5939758121967316, "distill": 1.0908145904541016, "teacher_acc": 0.7066957950592041 }, { "step": 7311, "lr": 2.945684547753163e-05, "elapsed_s": 5432.341083049774, "loss": 2.9740148782730103, "hidden": 0.18854829296469688, "layer": 0.0911153145134449, "mlm": 1.476170301437378, "distill": 1.0751902759075165, "teacher_acc": 0.7420265078544617 }, { "step": 7321, "lr": 2.9407296934729227e-05, "elapsed_s": 5439.782258987427, "loss": 2.996560573577881, "hidden": 0.1884702518582344, "layer": 0.09181415103375912, "mlm": 1.4930247068405151, "distill": 1.0806882977485657, "teacher_acc": 0.7325174659490585 }, { "step": 7331, "lr": 2.9357730517887322e-05, "elapsed_s": 5447.193865299225, "loss": 3.046721339225769, "hidden": 0.19253314286470413, "layer": 0.09223195165395737, "mlm": 1.5545329451560974, "distill": 1.0610061883926392, "teacher_acc": 0.719712033867836 }, { "step": 7341, "lr": 2.9308146428025302e-05, "elapsed_s": 5454.618585109711, "loss": 3.1813237071037292, "hidden": 0.19184523448348045, "layer": 0.09340518340468407, "mlm": 1.678251564502716, "distill": 1.0726790875196457, "teacher_acc": 0.6962525099515915 }, { "step": 7351, "lr": 2.9258544866234207e-05, "elapsed_s": 5462.034168958664, "loss": 2.9647884368896484, "hidden": 0.18336690217256546, "layer": 0.08902732655405998, "mlm": 1.5431723594665527, "distill": 1.0103686302900314, "teacher_acc": 0.7187994122505188 }, { "step": 7361, "lr": 2.920892603367596e-05, "elapsed_s": 5469.460248947144, "loss": 2.9791354537010193, "hidden": 0.1860056333243847, "layer": 0.09013870172202587, "mlm": 1.5175555646419525, "distill": 1.0444992780685425, "teacher_acc": 0.7327378839254379 }, { "step": 7371, "lr": 2.9159290131582516e-05, "elapsed_s": 5476.882873773575, "loss": 3.1368666291236877, "hidden": 0.19810686260461807, "layer": 0.09451708942651749, "mlm": 1.5704328417778015, "distill": 1.122961550951004, "teacher_acc": 0.7244236320257187 }, { "step": 7381, "lr": 2.910963736125505e-05, "elapsed_s": 5484.295904159546, "loss": 3.060743808746338, "hidden": 0.1894250474870205, "layer": 0.09119093976914883, "mlm": 1.543716698884964, "distill": 1.0925814807415009, "teacher_acc": 0.7256015241146088 }, { "step": 7391, "lr": 2.9059967924063153e-05, "elapsed_s": 5491.7075164318085, "loss": 3.113831579685211, "hidden": 0.1924474872648716, "layer": 0.0932778399437666, "mlm": 1.5062773823738098, "distill": 1.1760202944278717, "teacher_acc": 0.7308279871940613 }, { "step": 7401, "lr": 2.9010282021444008e-05, "elapsed_s": 5499.116909980774, "loss": 3.1071866154670715, "hidden": 0.1968911774456501, "layer": 0.09397237747907639, "mlm": 1.5194157660007477, "distill": 1.1470022797584534, "teacher_acc": 0.7352503687143326 }, { "step": 7411, "lr": 2.896057985490157e-05, "elapsed_s": 5506.489717721939, "loss": 2.9479286074638367, "hidden": 0.1880086101591587, "layer": 0.08926203474402428, "mlm": 1.5025215446949005, "distill": 1.0247588455677032, "teacher_acc": 0.7241243571043015 }, { "step": 7421, "lr": 2.8910861626005776e-05, "elapsed_s": 5513.922233819962, "loss": 3.0811870098114014, "hidden": 0.1833505742251873, "layer": 0.09057346731424332, "mlm": 1.5416740477085114, "distill": 1.1275250911712646, "teacher_acc": 0.7313091605901718 }, { "step": 7431, "lr": 2.8861127536391662e-05, "elapsed_s": 5521.347511053085, "loss": 3.0270999670028687, "hidden": 0.18751073628664017, "layer": 0.09017894044518471, "mlm": 1.5574962198734283, "distill": 1.0494927763938904, "teacher_acc": 0.7185288965702057 }, { "step": 7441, "lr": 2.8811377787758636e-05, "elapsed_s": 5528.781310081482, "loss": 2.944574534893036, "hidden": 0.18232368305325508, "layer": 0.09029307216405869, "mlm": 1.5045892298221588, "distill": 1.0301914662122726, "teacher_acc": 0.723953053355217 }, { "step": 7451, "lr": 2.876161258186958e-05, "elapsed_s": 5536.15138053894, "loss": 3.1556102633476257, "hidden": 0.19513849914073944, "layer": 0.09267156943678856, "mlm": 1.5615369379520416, "distill": 1.1574605405330658, "teacher_acc": 0.7219764143228531 }, { "step": 7461, "lr": 2.8711832120550064e-05, "elapsed_s": 5543.534348487854, "loss": 2.988038420677185, "hidden": 0.19202617928385735, "layer": 0.09188261441886425, "mlm": 1.5007283985614777, "distill": 1.0573163330554962, "teacher_acc": 0.7287907600402832 }, { "step": 7471, "lr": 2.8662036605687554e-05, "elapsed_s": 5550.948871850967, "loss": 2.9269248247146606, "hidden": 0.18331390619277954, "layer": 0.08973966538906097, "mlm": 1.4979069232940674, "distill": 1.0175202935934067, "teacher_acc": 0.7278178185224533 }, { "step": 7481, "lr": 2.8612226239230532e-05, "elapsed_s": 5558.367915391922, "loss": 2.9800788164138794, "hidden": 0.1884198561310768, "layer": 0.09018511697649956, "mlm": 1.4672073125839233, "distill": 1.0909392833709717, "teacher_acc": 0.7386022508144379 }, { "step": 7491, "lr": 2.8562401223187746e-05, "elapsed_s": 5565.77348446846, "loss": 3.1249510645866394, "hidden": 0.19266561791300774, "layer": 0.09199255704879761, "mlm": 1.5972262620925903, "distill": 1.0963972061872482, "teacher_acc": 0.7165757715702057 }, { "step": 7501, "lr": 2.851256175962732e-05, "elapsed_s": 5573.217665672302, "loss": 2.995164930820465, "hidden": 0.18643347173929214, "layer": 0.09018766134977341, "mlm": 1.5648920238018036, "distill": 1.0123121440410614, "teacher_acc": 0.714265301823616 }, { "step": 7511, "lr": 2.8462708050676002e-05, "elapsed_s": 5580.635922431946, "loss": 2.9256468415260315, "hidden": 0.18669718503952026, "layer": 0.09063789062201977, "mlm": 1.4699408113956451, "distill": 1.0369927287101746, "teacher_acc": 0.7306879311800003 }, { "step": 7521, "lr": 2.8412840298518296e-05, "elapsed_s": 5588.084744215012, "loss": 2.919109284877777, "hidden": 0.19032857194542885, "layer": 0.09216167777776718, "mlm": 1.4353613555431366, "distill": 1.0570099353790283, "teacher_acc": 0.7390284091234207 }, { "step": 7531, "lr": 2.836295870539566e-05, "elapsed_s": 5595.527212142944, "loss": 2.955470621585846, "hidden": 0.1836264282464981, "layer": 0.08975952677428722, "mlm": 1.4952533841133118, "distill": 1.048084557056427, "teacher_acc": 0.7302305102348328 }, { "step": 7541, "lr": 2.8313063473605693e-05, "elapsed_s": 5602.948579072952, "loss": 3.038730561733246, "hidden": 0.18832578882575035, "layer": 0.09172491170465946, "mlm": 1.5492113530635834, "distill": 1.0670051872730255, "teacher_acc": 0.7130984663963318 }, { "step": 7551, "lr": 2.8263154805501297e-05, "elapsed_s": 5610.368504524231, "loss": 3.0298629999160767, "hidden": 0.18473528698086739, "layer": 0.09005849435925484, "mlm": 1.5272947549819946, "distill": 1.0880683660507202, "teacher_acc": 0.7283396422863007 }, { "step": 7561, "lr": 2.8213232903489865e-05, "elapsed_s": 5617.779463768005, "loss": 2.93791264295578, "hidden": 0.18626222014427185, "layer": 0.0905433613806963, "mlm": 1.484918624162674, "distill": 1.0351979285478592, "teacher_acc": 0.72165347635746 }, { "step": 7571, "lr": 2.8163297970032486e-05, "elapsed_s": 5625.190071821213, "loss": 2.999720811843872, "hidden": 0.1854301132261753, "layer": 0.09011204913258553, "mlm": 1.528872400522232, "distill": 1.0549321323633194, "teacher_acc": 0.7186605632305145 }, { "step": 7581, "lr": 2.8113350207643057e-05, "elapsed_s": 5632.596405506134, "loss": 2.974813997745514, "hidden": 0.18493220582604408, "layer": 0.09083750285208225, "mlm": 1.5081714391708374, "distill": 1.0513594150543213, "teacher_acc": 0.7363905310630798 }, { "step": 7591, "lr": 2.8063389818887536e-05, "elapsed_s": 5640.012062072754, "loss": 2.9743377566337585, "hidden": 0.18739143386483192, "layer": 0.08994429185986519, "mlm": 1.4900241196155548, "distill": 1.0645586848258972, "teacher_acc": 0.727920725941658 }, { "step": 7601, "lr": 2.8013417006383076e-05, "elapsed_s": 5647.444077968597, "loss": 2.981498420238495, "hidden": 0.1897204890847206, "layer": 0.09059731103479862, "mlm": 1.512906700372696, "distill": 1.043852150440216, "teacher_acc": 0.7244731038808823 }, { "step": 7611, "lr": 2.7963431972797217e-05, "elapsed_s": 5654.838367938995, "loss": 2.9485782980918884, "hidden": 0.19410225376486778, "layer": 0.09177334979176521, "mlm": 1.4363177120685577, "distill": 1.07816943526268, "teacher_acc": 0.7505611926317215 }, { "step": 7621, "lr": 2.791343492084706e-05, "elapsed_s": 5662.25759768486, "loss": 3.025204658508301, "hidden": 0.18749916926026344, "layer": 0.09079484269022942, "mlm": 1.5489496886730194, "distill": 1.0558592081069946, "teacher_acc": 0.7167472690343857 }, { "step": 7631, "lr": 2.7863426053298443e-05, "elapsed_s": 5669.669215917587, "loss": 3.02725350856781, "hidden": 0.19259554147720337, "layer": 0.09250566735863686, "mlm": 1.5181101858615875, "distill": 1.0776993930339813, "teacher_acc": 0.7277562320232391 }, { "step": 7641, "lr": 2.781340557296514e-05, "elapsed_s": 5677.071400642395, "loss": 2.9722774028778076, "hidden": 0.182041946798563, "layer": 0.08988325111567974, "mlm": 1.5233929753303528, "distill": 1.0398589074611664, "teacher_acc": 0.7190651297569275 }, { "step": 7651, "lr": 2.7763373682708e-05, "elapsed_s": 5684.458467960358, "loss": 3.089523196220398, "hidden": 0.1892138607800007, "layer": 0.09187457151710987, "mlm": 1.5424006283283234, "distill": 1.122757613658905, "teacher_acc": 0.7311834245920181 }, { "step": 7661, "lr": 2.771333058543416e-05, "elapsed_s": 5691.872886896133, "loss": 2.995387315750122, "hidden": 0.19011952728033066, "layer": 0.09119386412203312, "mlm": 1.5562802255153656, "distill": 1.0132710635662079, "teacher_acc": 0.7098977267742157 }, { "step": 7671, "lr": 2.7663276484096207e-05, "elapsed_s": 5699.303705215454, "loss": 2.8965154886245728, "hidden": 0.1843484304845333, "layer": 0.08909644186496735, "mlm": 1.4668704867362976, "distill": 1.0163998901844025, "teacher_acc": 0.7363534420728683 }, { "step": 7681, "lr": 2.761321158169134e-05, "elapsed_s": 5706.749795436859, "loss": 3.0926347374916077, "hidden": 0.18979458138346672, "layer": 0.09131170809268951, "mlm": 1.5974887311458588, "distill": 1.0699010640382767, "teacher_acc": 0.7185785472393036 }, { "step": 7691, "lr": 2.7563136081260582e-05, "elapsed_s": 5714.136500120163, "loss": 2.9837409257888794, "hidden": 0.18773405998945236, "layer": 0.09011197276413441, "mlm": 1.5356006920337677, "distill": 1.0276160687208176, "teacher_acc": 0.7193203866481781 }, { "step": 7701, "lr": 2.751305018588793e-05, "elapsed_s": 5721.558113336563, "loss": 3.1053909063339233, "hidden": 0.1888025589287281, "layer": 0.09253804944455624, "mlm": 1.6056976914405823, "distill": 1.0758191347122192, "teacher_acc": 0.7100610733032227 }, { "step": 7711, "lr": 2.7462954098699534e-05, "elapsed_s": 5728.986226558685, "loss": 3.0779277086257935, "hidden": 0.20126652717590332, "layer": 0.0939593967050314, "mlm": 1.4819110929965973, "distill": 1.1465038061141968, "teacher_acc": 0.7420305013656616 }, { "step": 7721, "lr": 2.741284802286288e-05, "elapsed_s": 5736.395162820816, "loss": 2.9501550793647766, "hidden": 0.1876591332256794, "layer": 0.09038502722978592, "mlm": 1.468202918767929, "distill": 1.0614413768053055, "teacher_acc": 0.7381609529256821 }, { "step": 7731, "lr": 2.736273216158597e-05, "elapsed_s": 5743.801215648651, "loss": 2.9356051683425903, "hidden": 0.1837463080883026, "layer": 0.09037880413234234, "mlm": 1.4661276936531067, "distill": 1.0567954033613205, "teacher_acc": 0.7325938791036606 }, { "step": 7741, "lr": 2.731260671811648e-05, "elapsed_s": 5751.182297468185, "loss": 3.0258572101593018, "hidden": 0.18725182861089706, "layer": 0.09016008116304874, "mlm": 1.5631127655506134, "distill": 1.0431607514619827, "teacher_acc": 0.7235102951526642 }, { "step": 7751, "lr": 2.726247189574095e-05, "elapsed_s": 5758.559280633926, "loss": 2.832945704460144, "hidden": 0.1791805736720562, "layer": 0.08798815310001373, "mlm": 1.46523779630661, "distill": 0.9653526693582535, "teacher_acc": 0.7313100546598434 }, { "step": 7761, "lr": 2.7212327897783964e-05, "elapsed_s": 5765.917881011963, "loss": 3.1580533385276794, "hidden": 0.19244497269392014, "layer": 0.0940419677644968, "mlm": 1.6090206801891327, "distill": 1.1171217560768127, "teacher_acc": 0.7082802504301071 }, { "step": 7771, "lr": 2.7162174927607313e-05, "elapsed_s": 5773.285195589066, "loss": 2.943654716014862, "hidden": 0.18304169550538063, "layer": 0.08952835202217102, "mlm": 1.5208623111248016, "distill": 1.0119448453187943, "teacher_acc": 0.7203290611505508 }, { "step": 7781, "lr": 2.711201318860918e-05, "elapsed_s": 5780.6790289878845, "loss": 3.137402653694153, "hidden": 0.18749522417783737, "layer": 0.09220555610954762, "mlm": 1.6497911214828491, "distill": 1.0665183514356613, "teacher_acc": 0.6992761939764023 }, { "step": 7791, "lr": 2.7061842884223298e-05, "elapsed_s": 5788.098623991013, "loss": 3.0021497011184692, "hidden": 0.1877472922205925, "layer": 0.09061541594564915, "mlm": 1.5282130539417267, "distill": 1.0531344264745712, "teacher_acc": 0.7240987718105316 }, { "step": 7801, "lr": 2.7011664217918154e-05, "elapsed_s": 5795.523969173431, "loss": 3.000724971294403, "hidden": 0.18767402693629265, "layer": 0.0895928218960762, "mlm": 1.5062476694583893, "distill": 1.0743328779935837, "teacher_acc": 0.7256947606801987 }, { "step": 7811, "lr": 2.6961477393196126e-05, "elapsed_s": 5802.91160774231, "loss": 2.9824647903442383, "hidden": 0.1847437620162964, "layer": 0.08968407101929188, "mlm": 1.5046601295471191, "distill": 1.063475027680397, "teacher_acc": 0.7328593283891678 }, { "step": 7821, "lr": 2.691128261359271e-05, "elapsed_s": 5810.31370806694, "loss": 3.106727182865143, "hidden": 0.19383690878748894, "layer": 0.0913463644683361, "mlm": 1.5556681156158447, "distill": 1.1177120804786682, "teacher_acc": 0.7260778397321701 }, { "step": 7831, "lr": 2.6861080082675628e-05, "elapsed_s": 5817.710686922073, "loss": 2.9853397607803345, "hidden": 0.18875868991017342, "layer": 0.09134745970368385, "mlm": 1.494173526763916, "distill": 1.0679751336574554, "teacher_acc": 0.7298176437616348 }, { "step": 7841, "lr": 2.6810870004044063e-05, "elapsed_s": 5825.099767208099, "loss": 2.826568067073822, "hidden": 0.18371308594942093, "layer": 0.08906679600477219, "mlm": 1.3784719705581665, "distill": 1.036136507987976, "teacher_acc": 0.7488227039575577 }, { "step": 7851, "lr": 2.67606525813278e-05, "elapsed_s": 5832.521641492844, "loss": 3.0510438084602356, "hidden": 0.19090741872787476, "layer": 0.09133046306669712, "mlm": 1.5387413501739502, "distill": 1.0848223567008972, "teacher_acc": 0.7251254767179489 }, { "step": 7861, "lr": 2.6710428018186405e-05, "elapsed_s": 5839.932518720627, "loss": 2.999074161052704, "hidden": 0.18459400534629822, "layer": 0.09065555594861507, "mlm": 1.5309627950191498, "distill": 1.0535955429077148, "teacher_acc": 0.7284251600503922 }, { "step": 7871, "lr": 2.6660196518308417e-05, "elapsed_s": 5847.3681054115295, "loss": 2.9408315420150757, "hidden": 0.1881016232073307, "layer": 0.09084421023726463, "mlm": 1.4482860565185547, "distill": 1.070920154452324, "teacher_acc": 0.748839259147644 }, { "step": 7881, "lr": 2.6609958285410485e-05, "elapsed_s": 5854.807632684708, "loss": 3.0478105545043945, "hidden": 0.18967768177390099, "layer": 0.09145846217870712, "mlm": 1.552637755870819, "distill": 1.0700882375240326, "teacher_acc": 0.7214302867650986 }, { "step": 7891, "lr": 2.6559713523236583e-05, "elapsed_s": 5862.202819347382, "loss": 2.9649361968040466, "hidden": 0.17942819744348526, "layer": 0.08906545117497444, "mlm": 1.54500350356102, "distill": 1.0165435373783112, "teacher_acc": 0.7163782566785812 }, { "step": 7901, "lr": 2.6509462435557152e-05, "elapsed_s": 5869.605575323105, "loss": 2.9366695880889893, "hidden": 0.1798684112727642, "layer": 0.08826954290270805, "mlm": 1.5255488753318787, "distill": 1.0072491466999054, "teacher_acc": 0.7170481085777283 }, { "step": 7911, "lr": 2.6459205226168293e-05, "elapsed_s": 5877.024721860886, "loss": 2.873809039592743, "hidden": 0.17885932326316833, "layer": 0.0873555913567543, "mlm": 1.492055356502533, "distill": 0.9803572297096252, "teacher_acc": 0.7278437912464142 }, { "step": 7921, "lr": 2.6408942098890936e-05, "elapsed_s": 5884.407346487045, "loss": 2.9233238697052, "hidden": 0.18204207718372345, "layer": 0.08829397894442081, "mlm": 1.4539612531661987, "distill": 1.061131477355957, "teacher_acc": 0.7383329272270203 }, { "step": 7931, "lr": 2.6358673257570005e-05, "elapsed_s": 5891.8187737464905, "loss": 2.9973945021629333, "hidden": 0.1873900070786476, "layer": 0.08988468162715435, "mlm": 1.4832879900932312, "distill": 1.0943840742111206, "teacher_acc": 0.7461092621088028 }, { "step": 7941, "lr": 2.63083989060736e-05, "elapsed_s": 5899.20214509964, "loss": 2.9359678626060486, "hidden": 0.18285968527197838, "layer": 0.08933073282241821, "mlm": 1.5082913041114807, "distill": 1.017291858792305, "teacher_acc": 0.7320671230554581 }, { "step": 7951, "lr": 2.6258119248292168e-05, "elapsed_s": 5906.589183092117, "loss": 2.9894891381263733, "hidden": 0.18684188276529312, "layer": 0.08924199640750885, "mlm": 1.5283924043178558, "distill": 1.0427919030189514, "teacher_acc": 0.7254522293806076 }, { "step": 7961, "lr": 2.6207834488137677e-05, "elapsed_s": 5913.98761177063, "loss": 3.027670681476593, "hidden": 0.19101034849882126, "layer": 0.09038809314370155, "mlm": 1.5506428182125092, "distill": 1.0498132407665253, "teacher_acc": 0.7211106419563293 }, { "step": 7971, "lr": 2.6157544829542796e-05, "elapsed_s": 5921.378497838974, "loss": 2.957527756690979, "hidden": 0.19058693945407867, "layer": 0.09104156866669655, "mlm": 1.4386736750602722, "distill": 1.0921594053506851, "teacher_acc": 0.7376282960176468 }, { "step": 7981, "lr": 2.6107250476460037e-05, "elapsed_s": 5928.744864463806, "loss": 3.073564291000366, "hidden": 0.19139793515205383, "layer": 0.09154894389212132, "mlm": 1.5407046675682068, "distill": 1.104289323091507, "teacher_acc": 0.7353475540876389 }, { "step": 7991, "lr": 2.6056951632860976e-05, "elapsed_s": 5936.154704809189, "loss": 3.134876847267151, "hidden": 0.19001232460141182, "layer": 0.09071553684771061, "mlm": 1.6584240198135376, "distill": 1.051070362329483, "teacher_acc": 0.7109333276748657 }, { "step": 8001, "lr": 2.600664850273538e-05, "elapsed_s": 5945.570575237274, "loss": 2.943476974964142, "hidden": 0.18500447645783424, "layer": 0.08882680721580982, "mlm": 1.486168771982193, "distill": 1.0428857505321503, "teacher_acc": 0.73287732899189 }, { "step": 8011, "lr": 2.595634129009042e-05, "elapsed_s": 5952.920455217361, "loss": 2.945117950439453, "hidden": 0.18122515082359314, "layer": 0.0886444877833128, "mlm": 1.5174431502819061, "distill": 1.0209023356437683, "teacher_acc": 0.720693364739418 }, { "step": 8021, "lr": 2.590603019894981e-05, "elapsed_s": 5960.297090053558, "loss": 3.0003084540367126, "hidden": 0.18534817174077034, "layer": 0.08990722335875034, "mlm": 1.5343915522098541, "distill": 1.050266832113266, "teacher_acc": 0.7225951552391052 }, { "step": 8031, "lr": 2.5855715433352994e-05, "elapsed_s": 5967.717488765717, "loss": 2.88617867231369, "hidden": 0.18049783632159233, "layer": 0.08847105130553246, "mlm": 1.4895272850990295, "distill": 0.9914201200008392, "teacher_acc": 0.7252546399831772 }, { "step": 8041, "lr": 2.580539719735433e-05, "elapsed_s": 5975.134567975998, "loss": 2.9384419918060303, "hidden": 0.18474457412958145, "layer": 0.08918085880577564, "mlm": 1.48868328332901, "distill": 1.0356791466474533, "teacher_acc": 0.7294705808162689 }, { "step": 8051, "lr": 2.5755075695022224e-05, "elapsed_s": 5982.567674636841, "loss": 2.950936436653137, "hidden": 0.1855541728436947, "layer": 0.08908936381340027, "mlm": 1.5060684978961945, "distill": 1.0292149037122726, "teacher_acc": 0.7337286621332169 }, { "step": 8061, "lr": 2.5704751130438365e-05, "elapsed_s": 5990.005371570587, "loss": 3.024790346622467, "hidden": 0.18189985305070877, "layer": 0.08877922780811787, "mlm": 1.5554241836071014, "distill": 1.0611768066883087, "teacher_acc": 0.7132090181112289 }, { "step": 8071, "lr": 2.5654423707696833e-05, "elapsed_s": 5997.415748596191, "loss": 2.899522840976715, "hidden": 0.18285351246595383, "layer": 0.08935621753334999, "mlm": 1.5021441280841827, "distill": 0.9869936406612396, "teacher_acc": 0.7266732156276703 }, { "step": 8081, "lr": 2.5604093630903307e-05, "elapsed_s": 6004.863036632538, "loss": 2.9205490946769714, "hidden": 0.17830318212509155, "layer": 0.08855077065527439, "mlm": 1.5176686346530914, "distill": 1.0019986629486084, "teacher_acc": 0.7154610008001328 }, { "step": 8091, "lr": 2.5553761104174247e-05, "elapsed_s": 6012.247004032135, "loss": 2.871517777442932, "hidden": 0.18540479987859726, "layer": 0.08971286006271839, "mlm": 1.4624199867248535, "distill": 0.9934317469596863, "teacher_acc": 0.7362517714500427 }, { "step": 8101, "lr": 2.550342633163601e-05, "elapsed_s": 6019.658682823181, "loss": 2.9650700092315674, "hidden": 0.18772930279374123, "layer": 0.09178568981587887, "mlm": 1.484730064868927, "distill": 1.0589885413646698, "teacher_acc": 0.7409871518611908 }, { "step": 8111, "lr": 2.54530895174241e-05, "elapsed_s": 6027.053880691528, "loss": 2.8513808846473694, "hidden": 0.1870022863149643, "layer": 0.08962621912360191, "mlm": 1.4357998073101044, "distill": 0.9967633932828903, "teacher_acc": 0.7356698513031006 }, { "step": 8121, "lr": 2.5402750865682285e-05, "elapsed_s": 6034.447416782379, "loss": 2.996609628200531, "hidden": 0.18410099297761917, "layer": 0.08966064453125, "mlm": 1.5587752163410187, "distill": 1.0248021632432938, "teacher_acc": 0.7142862677574158 }, { "step": 8131, "lr": 2.535241058056178e-05, "elapsed_s": 6041.86639046669, "loss": 2.949724316596985, "hidden": 0.17665766552090645, "layer": 0.08814729377627373, "mlm": 1.5256448090076447, "distill": 1.0266906023025513, "teacher_acc": 0.7201394885778427 }, { "step": 8141, "lr": 2.5302068866220434e-05, "elapsed_s": 6049.281199216843, "loss": 2.9043164253234863, "hidden": 0.19125251471996307, "layer": 0.091706408187747, "mlm": 1.4239628612995148, "distill": 1.05199533700943, "teacher_acc": 0.7435572743415833 }, { "step": 8151, "lr": 2.5251725926821888e-05, "elapsed_s": 6056.662350654602, "loss": 2.9747021198272705, "hidden": 0.1802802011370659, "layer": 0.08784078806638718, "mlm": 1.5812806487083435, "distill": 0.9889407008886337, "teacher_acc": 0.6977644264698029 }, { "step": 8161, "lr": 2.5201381966534748e-05, "elapsed_s": 6064.076615333557, "loss": 2.921797513961792, "hidden": 0.1928202472627163, "layer": 0.09113491885364056, "mlm": 1.400384098291397, "distill": 1.0902054160833359, "teacher_acc": 0.7523217499256134 }, { "step": 8171, "lr": 2.5151037189531772e-05, "elapsed_s": 6071.50076341629, "loss": 3.0105064511299133, "hidden": 0.17669742554426193, "layer": 0.08835393935441971, "mlm": 1.5948884785175323, "distill": 1.0180462449789047, "teacher_acc": 0.6993189305067062 }, { "step": 8181, "lr": 2.5100691799989012e-05, "elapsed_s": 6078.930648803711, "loss": 2.9743165373802185, "hidden": 0.1839786097407341, "layer": 0.08974463306367397, "mlm": 1.5268478095531464, "distill": 1.0346391648054123, "teacher_acc": 0.7220877557992935 }, { "step": 8191, "lr": 2.5050346002085028e-05, "elapsed_s": 6086.32984495163, "loss": 2.96433824300766, "hidden": 0.1838577762246132, "layer": 0.08956133760511875, "mlm": 1.5015293061733246, "distill": 1.050312653183937, "teacher_acc": 0.7331461906433105 }, { "step": 8201, "lr": 2.5e-05, "elapsed_s": 6093.723961830139, "loss": 2.9922373294830322, "hidden": 0.18583258241415024, "layer": 0.08966579101979733, "mlm": 1.5211062729358673, "distill": 1.0546330511569977, "teacher_acc": 0.7330964803695679 }, { "step": 8211, "lr": 2.4949653997914978e-05, "elapsed_s": 6101.135966539383, "loss": 2.891687750816345, "hidden": 0.18434017524123192, "layer": 0.09039711207151413, "mlm": 1.511214554309845, "distill": 0.9665941745042801, "teacher_acc": 0.719714418053627 }, { "step": 8221, "lr": 2.489930820001099e-05, "elapsed_s": 6108.538053035736, "loss": 3.153267502784729, "hidden": 0.19143395498394966, "layer": 0.09137751534581184, "mlm": 1.6263537406921387, "distill": 1.0983571261167526, "teacher_acc": 0.7130441218614578 }, { "step": 8231, "lr": 2.484896281046823e-05, "elapsed_s": 6115.918032407761, "loss": 2.8901094794273376, "hidden": 0.18094927817583084, "layer": 0.08909286186099052, "mlm": 1.4574635326862335, "distill": 1.0262009352445602, "teacher_acc": 0.7466393858194351 }, { "step": 8241, "lr": 2.4798618033465258e-05, "elapsed_s": 6123.32395863533, "loss": 2.931398630142212, "hidden": 0.18789293617010117, "layer": 0.09053625538945198, "mlm": 1.4711494743824005, "distill": 1.0391951352357864, "teacher_acc": 0.7355734556913376 }, { "step": 8251, "lr": 2.4748274073178114e-05, "elapsed_s": 6130.730890274048, "loss": 2.9117440581321716, "hidden": 0.18057962879538536, "layer": 0.08870450221002102, "mlm": 1.5162672400474548, "distill": 0.9899652898311615, "teacher_acc": 0.7124912738800049 }, { "step": 8261, "lr": 2.4697931133779568e-05, "elapsed_s": 6138.126479625702, "loss": 2.950780153274536, "hidden": 0.18413323536515236, "layer": 0.09027173183858395, "mlm": 1.5216915607452393, "distill": 1.015686184167862, "teacher_acc": 0.7171885669231415 }, { "step": 8271, "lr": 2.4647589419438224e-05, "elapsed_s": 6145.502211809158, "loss": 2.9337576627731323, "hidden": 0.1831376701593399, "layer": 0.08990378491580486, "mlm": 1.4892006516456604, "distill": 1.0333296656608582, "teacher_acc": 0.7304738909006119 }, { "step": 8281, "lr": 2.459724913431772e-05, "elapsed_s": 6152.891382694244, "loss": 2.939943015575409, "hidden": 0.18573177233338356, "layer": 0.09129116125404835, "mlm": 1.4799895286560059, "distill": 1.042844295501709, "teacher_acc": 0.7333685755729675 }, { "step": 8291, "lr": 2.4546910482575908e-05, "elapsed_s": 6160.266522169113, "loss": 3.005593180656433, "hidden": 0.18121618777513504, "layer": 0.0894862674176693, "mlm": 1.5923981964588165, "distill": 1.006019487977028, "teacher_acc": 0.6983092427253723 }, { "step": 8301, "lr": 2.4496573668363996e-05, "elapsed_s": 6167.688009738922, "loss": 3.0075316429138184, "hidden": 0.18586434051394463, "layer": 0.08954703994095325, "mlm": 1.5086158514022827, "distill": 1.082413598895073, "teacher_acc": 0.7297636568546295 }, { "step": 8311, "lr": 2.4446238895825762e-05, "elapsed_s": 6175.111860752106, "loss": 2.924494981765747, "hidden": 0.18256183341145515, "layer": 0.0884410459548235, "mlm": 1.4452449679374695, "distill": 1.069905772805214, "teacher_acc": 0.7393586188554764 }, { "step": 8321, "lr": 2.43959063690967e-05, "elapsed_s": 6182.510061979294, "loss": 2.999220073223114, "hidden": 0.1881144382059574, "layer": 0.0904888715595007, "mlm": 1.5343836843967438, "distill": 1.0433630496263504, "teacher_acc": 0.7139466404914856 }, { "step": 8331, "lr": 2.4345576292303176e-05, "elapsed_s": 6189.89150261879, "loss": 2.9658464789390564, "hidden": 0.17980826646089554, "layer": 0.08801405690610409, "mlm": 1.5942479074001312, "distill": 0.9679750055074692, "teacher_acc": 0.7010392397642136 }, { "step": 8341, "lr": 2.4295248869561644e-05, "elapsed_s": 6197.270488500595, "loss": 2.9391918182373047, "hidden": 0.18330220505595207, "layer": 0.08926144987344742, "mlm": 1.479045569896698, "distill": 1.0489111542701721, "teacher_acc": 0.7308953702449799 }, { "step": 8351, "lr": 2.4244924304977785e-05, "elapsed_s": 6204.669112920761, "loss": 2.875270962715149, "hidden": 0.17996390163898468, "layer": 0.08799388445913792, "mlm": 1.4565063118934631, "distill": 1.014840006828308, "teacher_acc": 0.7316354215145111 }, { "step": 8361, "lr": 2.4194602802645682e-05, "elapsed_s": 6212.076530694962, "loss": 2.7997010350227356, "hidden": 0.1785064898431301, "layer": 0.08745672553777695, "mlm": 1.4159866571426392, "distill": 0.9829730689525604, "teacher_acc": 0.7402416169643402 }, { "step": 8371, "lr": 2.4144284566647015e-05, "elapsed_s": 6219.502213001251, "loss": 3.0549824237823486, "hidden": 0.18566689267754555, "layer": 0.09021729417145252, "mlm": 1.5863741338253021, "distill": 1.052165925502777, "teacher_acc": 0.714330643415451 }, { "step": 8381, "lr": 2.40939698010502e-05, "elapsed_s": 6226.920089483261, "loss": 2.8350305557250977, "hidden": 0.18058951944112778, "layer": 0.08789621293544769, "mlm": 1.4557102918624878, "distill": 0.9741931259632111, "teacher_acc": 0.7274690866470337 }, { "step": 8391, "lr": 2.4043658709909585e-05, "elapsed_s": 6234.333126068115, "loss": 2.8359575867652893, "hidden": 0.17768486589193344, "layer": 0.08745093271136284, "mlm": 1.4620692431926727, "distill": 0.9747931361198425, "teacher_acc": 0.7293361872434616 }, { "step": 8401, "lr": 2.399335149726463e-05, "elapsed_s": 6241.73703789711, "loss": 2.9529137015342712, "hidden": 0.17902612686157227, "layer": 0.08773896284401417, "mlm": 1.5330709517002106, "distill": 1.0179211348295212, "teacher_acc": 0.7198192924261093 }, { "step": 8411, "lr": 2.3943048367139034e-05, "elapsed_s": 6249.174750089645, "loss": 2.8508880138397217, "hidden": 0.18088247999548912, "layer": 0.08851601183414459, "mlm": 1.4675228297710419, "distill": 0.9773422181606293, "teacher_acc": 0.7270239591598511 }, { "step": 8421, "lr": 2.3892749523539975e-05, "elapsed_s": 6256.6026401519775, "loss": 2.844675660133362, "hidden": 0.18240134790539742, "layer": 0.08844905532896519, "mlm": 1.4462521076202393, "distill": 0.9893963932991028, "teacher_acc": 0.7364901006221771 }, { "step": 8431, "lr": 2.3842455170457216e-05, "elapsed_s": 6264.001533269882, "loss": 2.855037271976471, "hidden": 0.17813381552696228, "layer": 0.08849231712520123, "mlm": 1.465518206357956, "distill": 0.9890053272247314, "teacher_acc": 0.7295382171869278 }, { "step": 8441, "lr": 2.379216551186233e-05, "elapsed_s": 6271.381135225296, "loss": 2.854619085788727, "hidden": 0.17629743367433548, "layer": 0.08741213567554951, "mlm": 1.4959725737571716, "distill": 0.9623454809188843, "teacher_acc": 0.7197598069906235 }, { "step": 8451, "lr": 2.374188075170783e-05, "elapsed_s": 6278.794520139694, "loss": 2.879940688610077, "hidden": 0.18894462287425995, "layer": 0.09032072499394417, "mlm": 1.4103220999240875, "distill": 1.046568974852562, "teacher_acc": 0.7382932752370834 }, { "step": 8461, "lr": 2.3691601093926404e-05, "elapsed_s": 6286.207994699478, "loss": 2.9809134006500244, "hidden": 0.18669545277953148, "layer": 0.09018196538090706, "mlm": 1.5047359466552734, "distill": 1.0576955080032349, "teacher_acc": 0.7286570072174072 }, { "step": 8471, "lr": 2.3641326742429997e-05, "elapsed_s": 6293.6435651779175, "loss": 2.907900333404541, "hidden": 0.18374108895659447, "layer": 0.08859942108392715, "mlm": 1.4614209234714508, "distill": 1.0346974432468414, "teacher_acc": 0.7449843287467957 }, { "step": 8481, "lr": 2.3591057901109063e-05, "elapsed_s": 6301.049234628677, "loss": 2.9465858340263367, "hidden": 0.1828613616526127, "layer": 0.08813507668673992, "mlm": 1.5369316041469574, "distill": 0.9998639822006226, "teacher_acc": 0.7159930914640427 }, { "step": 8491, "lr": 2.3540794773831706e-05, "elapsed_s": 6308.484765291214, "loss": 2.911461055278778, "hidden": 0.17863063141703606, "layer": 0.08771364018321037, "mlm": 1.533032774925232, "distill": 0.9773102253675461, "teacher_acc": 0.7181064486503601 }, { "step": 8501, "lr": 2.3490537564442847e-05, "elapsed_s": 6315.90755033493, "loss": 3.124101161956787, "hidden": 0.18704332411289215, "layer": 0.090591786429286, "mlm": 1.6431399285793304, "distill": 1.0615786761045456, "teacher_acc": 0.6924787163734436 }, { "step": 8511, "lr": 2.344028647676342e-05, "elapsed_s": 6323.314769983292, "loss": 2.9573127031326294, "hidden": 0.1789483092725277, "layer": 0.08913538977503777, "mlm": 1.5469298958778381, "distill": 1.0079184919595718, "teacher_acc": 0.7063856422901154 }, { "step": 8521, "lr": 2.3390041714589514e-05, "elapsed_s": 6330.7093670368195, "loss": 2.9588323831558228, "hidden": 0.19193321466445923, "layer": 0.09050224162638187, "mlm": 1.5065864026546478, "distill": 1.023128405213356, "teacher_acc": 0.718341127038002 }, { "step": 8531, "lr": 2.333980348169158e-05, "elapsed_s": 6338.088020801544, "loss": 2.9513808488845825, "hidden": 0.1834735907614231, "layer": 0.09056422300636768, "mlm": 1.4577647745609283, "distill": 1.0813868045806885, "teacher_acc": 0.7399847656488419 }, { "step": 8541, "lr": 2.3289571981813594e-05, "elapsed_s": 6345.518124341965, "loss": 3.0267804861068726, "hidden": 0.1823589764535427, "layer": 0.08937833458185196, "mlm": 1.5498903095722198, "distill": 1.067482978105545, "teacher_acc": 0.7257059216499329 }, { "step": 8551, "lr": 2.3239347418672202e-05, "elapsed_s": 6352.943686723709, "loss": 2.8283453583717346, "hidden": 0.17376576364040375, "layer": 0.08760103024542332, "mlm": 1.4394747912883759, "distill": 0.9975385218858719, "teacher_acc": 0.7404749691486359 }, { "step": 8561, "lr": 2.3189129995955943e-05, "elapsed_s": 6360.37038564682, "loss": 2.891727030277252, "hidden": 0.18154527619481087, "layer": 0.08857088536024094, "mlm": 1.493547797203064, "distill": 0.9908032566308975, "teacher_acc": 0.7230571210384369 }, { "step": 8571, "lr": 2.3138919917324378e-05, "elapsed_s": 6367.7848508358, "loss": 2.8875765800476074, "hidden": 0.17877573892474174, "layer": 0.08766302280128002, "mlm": 1.46577787399292, "distill": 1.0204157084226608, "teacher_acc": 0.7307460159063339 }, { "step": 8581, "lr": 2.3088717386407297e-05, "elapsed_s": 6375.205098867416, "loss": 3.0409688353538513, "hidden": 0.19034617394208908, "layer": 0.09154427237808704, "mlm": 1.5139701664447784, "distill": 1.100534200668335, "teacher_acc": 0.7252182960510254 }, { "step": 8591, "lr": 2.303852260680388e-05, "elapsed_s": 6382.615610122681, "loss": 2.9315292835235596, "hidden": 0.18493446335196495, "layer": 0.08950814232230186, "mlm": 1.5043656527996063, "distill": 1.0125406682491302, "teacher_acc": 0.7180290371179581 }, { "step": 8601, "lr": 2.2988335782081855e-05, "elapsed_s": 6390.003125667572, "loss": 2.895297586917877, "hidden": 0.183767668902874, "layer": 0.09037392027676105, "mlm": 1.468329668045044, "distill": 1.0142456740140915, "teacher_acc": 0.7316508889198303 }, { "step": 8611, "lr": 2.2938157115776704e-05, "elapsed_s": 6397.380096912384, "loss": 2.93588924407959, "hidden": 0.18244516849517822, "layer": 0.0886326152831316, "mlm": 1.4861495792865753, "distill": 1.0405329763889313, "teacher_acc": 0.7311215102672577 }, { "step": 8621, "lr": 2.2887986811390828e-05, "elapsed_s": 6404.787356138229, "loss": 2.8331461548805237, "hidden": 0.1785254329442978, "layer": 0.08767159096896648, "mlm": 1.443150371313095, "distill": 0.9891091287136078, "teacher_acc": 0.7302334606647491 }, { "step": 8631, "lr": 2.283782507239269e-05, "elapsed_s": 6412.200192451477, "loss": 2.934127449989319, "hidden": 0.18885766714811325, "layer": 0.09050243906676769, "mlm": 1.477938860654831, "distill": 1.0332220792770386, "teacher_acc": 0.7288858443498611 }, { "step": 8641, "lr": 2.2787672102216042e-05, "elapsed_s": 6419.626239776611, "loss": 2.8575106859207153, "hidden": 0.17604610696434975, "layer": 0.0872959028929472, "mlm": 1.5211619436740875, "distill": 0.9406086206436157, "teacher_acc": 0.7169828861951828 }, { "step": 8651, "lr": 2.2737528104259056e-05, "elapsed_s": 6427.039954900742, "loss": 3.001944899559021, "hidden": 0.1855383887887001, "layer": 0.09014837816357613, "mlm": 1.5173896551132202, "distill": 1.0684043169021606, "teacher_acc": 0.7207956612110138 }, { "step": 8661, "lr": 2.2687393281883525e-05, "elapsed_s": 6434.469883680344, "loss": 2.897132694721222, "hidden": 0.1799173578619957, "layer": 0.08801806345582008, "mlm": 1.493676781654358, "distill": 0.9996120929718018, "teacher_acc": 0.7295356690883636 }, { "step": 8671, "lr": 2.263726783841404e-05, "elapsed_s": 6441.8876984119415, "loss": 3.007726728916168, "hidden": 0.18790575116872787, "layer": 0.08982766047120094, "mlm": 1.576948344707489, "distill": 1.0100530236959457, "teacher_acc": 0.7038985043764114 }, { "step": 8681, "lr": 2.2587151977137122e-05, "elapsed_s": 6449.317623376846, "loss": 2.8331122994422913, "hidden": 0.17551447078585625, "layer": 0.08662776090204716, "mlm": 1.465342491865158, "distill": 0.9734269827604294, "teacher_acc": 0.730484127998352 }, { "step": 8691, "lr": 2.2537045901300476e-05, "elapsed_s": 6456.731172084808, "loss": 2.968348264694214, "hidden": 0.18644027784466743, "layer": 0.08992563746869564, "mlm": 1.548774242401123, "distill": 1.0017306208610535, "teacher_acc": 0.7173354029655457 }, { "step": 8701, "lr": 2.2486949814112077e-05, "elapsed_s": 6464.127074480057, "loss": 2.807942032814026, "hidden": 0.18399015441536903, "layer": 0.08863610774278641, "mlm": 1.4037708938121796, "distill": 0.9918727874755859, "teacher_acc": 0.7371050417423248 }, { "step": 8711, "lr": 2.243686391873942e-05, "elapsed_s": 6471.529432058334, "loss": 2.965940296649933, "hidden": 0.178830087184906, "layer": 0.08769601956009865, "mlm": 1.5386537313461304, "distill": 1.025778368115425, "teacher_acc": 0.7213774770498276 }, { "step": 8721, "lr": 2.238678841830867e-05, "elapsed_s": 6478.931056022644, "loss": 2.9844260811805725, "hidden": 0.1846175603568554, "layer": 0.08937561511993408, "mlm": 1.5243127644062042, "distill": 1.0461903810501099, "teacher_acc": 0.7168848812580109 }, { "step": 8731, "lr": 2.2336723515903803e-05, "elapsed_s": 6486.3247056007385, "loss": 3.0020660161972046, "hidden": 0.18470419198274612, "layer": 0.09019277431070805, "mlm": 1.5129064917564392, "distill": 1.0746547877788544, "teacher_acc": 0.7282703816890717 }, { "step": 8741, "lr": 2.2286669414565846e-05, "elapsed_s": 6493.715079069138, "loss": 2.9585015773773193, "hidden": 0.18602298945188522, "layer": 0.09012051299214363, "mlm": 1.5135542750358582, "distill": 1.0278410464525223, "teacher_acc": 0.7184338569641113 }, { "step": 8751, "lr": 2.2236626317292007e-05, "elapsed_s": 6501.108938217163, "loss": 2.892183244228363, "hidden": 0.18466924875974655, "layer": 0.08989451080560684, "mlm": 1.4613795280456543, "distill": 1.0165180265903473, "teacher_acc": 0.7374773770570755 }, { "step": 8761, "lr": 2.2186594427034864e-05, "elapsed_s": 6508.503279685974, "loss": 2.7361000776290894, "hidden": 0.18135832995176315, "layer": 0.08705575577914715, "mlm": 1.370358556509018, "distill": 0.9594970494508743, "teacher_acc": 0.749190092086792 }, { "step": 8771, "lr": 2.213657394670156e-05, "elapsed_s": 6515.889404535294, "loss": 3.054608464241028, "hidden": 0.186349805444479, "layer": 0.08988721296191216, "mlm": 1.5879962146282196, "distill": 1.0489690899848938, "teacher_acc": 0.707442045211792 }, { "step": 8781, "lr": 2.2086565079152946e-05, "elapsed_s": 6523.287684440613, "loss": 3.07598340511322, "hidden": 0.18410733714699745, "layer": 0.08933237940073013, "mlm": 1.6352986693382263, "distill": 1.0278037935495377, "teacher_acc": 0.6948581784963608 }, { "step": 8791, "lr": 2.2036568027202793e-05, "elapsed_s": 6530.70818901062, "loss": 2.8574676513671875, "hidden": 0.18139314278960228, "layer": 0.08717617951333523, "mlm": 1.412856012582779, "distill": 1.0382372438907623, "teacher_acc": 0.7452773004770279 }, { "step": 8801, "lr": 2.1986582993616926e-05, "elapsed_s": 6538.117563724518, "loss": 3.0106810331344604, "hidden": 0.186729047447443, "layer": 0.08938080817461014, "mlm": 1.5481558740139008, "distill": 1.0443766415119171, "teacher_acc": 0.7178986072540283 }, { "step": 8811, "lr": 2.1936610181112466e-05, "elapsed_s": 6545.558225154877, "loss": 2.9059844613075256, "hidden": 0.18045691773295403, "layer": 0.08874400332570076, "mlm": 1.4922977983951569, "distill": 1.008400782942772, "teacher_acc": 0.7315785884857178 }, { "step": 8821, "lr": 2.188664979235695e-05, "elapsed_s": 6552.98779630661, "loss": 2.933813989162445, "hidden": 0.17986387014389038, "layer": 0.08861134760081768, "mlm": 1.5210449397563934, "distill": 1.008735716342926, "teacher_acc": 0.7107240557670593 }, { "step": 8831, "lr": 2.1836702029967524e-05, "elapsed_s": 6560.388173818588, "loss": 2.98126620054245, "hidden": 0.1842743642628193, "layer": 0.08878319524228573, "mlm": 1.5688044130802155, "distill": 0.9995214939117432, "teacher_acc": 0.7114357650279999 }, { "step": 8841, "lr": 2.1786767096510137e-05, "elapsed_s": 6567.799901485443, "loss": 3.0354889035224915, "hidden": 0.18559569492936134, "layer": 0.08919881843030453, "mlm": 1.59492626786232, "distill": 1.0247717499732971, "teacher_acc": 0.7039584666490555 }, { "step": 8851, "lr": 2.173684519449872e-05, "elapsed_s": 6575.241186618805, "loss": 2.9517104029655457, "hidden": 0.1806754171848297, "layer": 0.08847871236503124, "mlm": 1.5132551491260529, "distill": 1.0328650325536728, "teacher_acc": 0.7282463759183884 }, { "step": 8861, "lr": 2.168693652639432e-05, "elapsed_s": 6582.639365911484, "loss": 2.963459610939026, "hidden": 0.18071004375815392, "layer": 0.08869470097124577, "mlm": 1.529125064611435, "distill": 1.028567060828209, "teacher_acc": 0.7226865887641907 }, { "step": 8871, "lr": 2.1637041294604353e-05, "elapsed_s": 6590.060245037079, "loss": 2.9387542009353638, "hidden": 0.1904049515724182, "layer": 0.08992573246359825, "mlm": 1.4812887609004974, "distill": 1.0316926687955856, "teacher_acc": 0.7294967919588089 }, { "step": 8881, "lr": 2.1587159701481716e-05, "elapsed_s": 6597.451440572739, "loss": 3.0799967646598816, "hidden": 0.18595696613192558, "layer": 0.08928271569311619, "mlm": 1.5693759322166443, "distill": 1.0940655171871185, "teacher_acc": 0.7186525762081146 }, { "step": 8891, "lr": 2.1537291949324007e-05, "elapsed_s": 6604.86493396759, "loss": 2.8588709831237793, "hidden": 0.1773664988577366, "layer": 0.08765405975282192, "mlm": 1.4873344600200653, "distill": 0.9729765802621841, "teacher_acc": 0.7125709652900696 }, { "step": 8901, "lr": 2.148743824037269e-05, "elapsed_s": 6612.294847488403, "loss": 2.8426312804222107, "hidden": 0.17505457997322083, "layer": 0.08710480853915215, "mlm": 1.4908365607261658, "distill": 0.9581330865621567, "teacher_acc": 0.7272351384162903 }, { "step": 8911, "lr": 2.1437598776812263e-05, "elapsed_s": 6619.741770267487, "loss": 2.913152039051056, "hidden": 0.1833137758076191, "layer": 0.08867250569164753, "mlm": 1.4868301451206207, "distill": 1.015358105301857, "teacher_acc": 0.7328678071498871 }, { "step": 8921, "lr": 2.1387773760769474e-05, "elapsed_s": 6627.171642541885, "loss": 2.8973346948623657, "hidden": 0.18192962184548378, "layer": 0.08837432600557804, "mlm": 1.49186971783638, "distill": 0.9974185973405838, "teacher_acc": 0.7323737889528275 }, { "step": 8931, "lr": 2.1337963394312455e-05, "elapsed_s": 6634.618430137634, "loss": 2.9903522729873657, "hidden": 0.17788656428456306, "layer": 0.08825463242828846, "mlm": 1.555762529373169, "distill": 1.0346892476081848, "teacher_acc": 0.7117421180009842 }, { "step": 8941, "lr": 2.1288167879449935e-05, "elapsed_s": 6642.035146951675, "loss": 2.7845088243484497, "hidden": 0.18205909058451653, "layer": 0.08897701278328896, "mlm": 1.3837000131607056, "distill": 0.9922020733356476, "teacher_acc": 0.7477200031280518 }, { "step": 8951, "lr": 2.1238387418130422e-05, "elapsed_s": 6649.45331454277, "loss": 2.9792811274528503, "hidden": 0.18322540819644928, "layer": 0.08939226157963276, "mlm": 1.54749995470047, "distill": 1.0206342041492462, "teacher_acc": 0.7230598330497742 }, { "step": 8961, "lr": 2.1188622212241367e-05, "elapsed_s": 6656.87856388092, "loss": 3.056369185447693, "hidden": 0.18552593886852264, "layer": 0.09026428684592247, "mlm": 1.5303844511508942, "distill": 1.1098006963729858, "teacher_acc": 0.7350148558616638 }, { "step": 8971, "lr": 2.1138872463608334e-05, "elapsed_s": 6664.315057277679, "loss": 3.1146926283836365, "hidden": 0.1871957816183567, "layer": 0.09087642095983028, "mlm": 1.6493154466152191, "distill": 1.0455473810434341, "teacher_acc": 0.7042504251003265 }, { "step": 8981, "lr": 2.1089138373994223e-05, "elapsed_s": 6671.74267911911, "loss": 2.969256639480591, "hidden": 0.1860981360077858, "layer": 0.09092613309621811, "mlm": 1.4887465834617615, "distill": 1.0628507435321808, "teacher_acc": 0.7439458817243576 }, { "step": 8991, "lr": 2.1039420145098426e-05, "elapsed_s": 6679.1408042907715, "loss": 3.039336919784546, "hidden": 0.1812228485941887, "layer": 0.08929944410920143, "mlm": 1.5841592252254486, "distill": 1.0480823814868927, "teacher_acc": 0.7157245576381683 }, { "step": 9001, "lr": 2.098971797855599e-05, "elapsed_s": 6688.556682348251, "loss": 2.8443188667297363, "hidden": 0.17946211621165276, "layer": 0.08726046979427338, "mlm": 1.4529588520526886, "distill": 0.9888056218624115, "teacher_acc": 0.7396171540021896 }, { "step": 9011, "lr": 2.094003207593685e-05, "elapsed_s": 6695.9745762348175, "loss": 2.9383957386016846, "hidden": 0.1811458021402359, "layer": 0.08890057168900967, "mlm": 1.5210141837596893, "distill": 1.010639637708664, "teacher_acc": 0.728861078619957 }, { "step": 9021, "lr": 2.0890362638744952e-05, "elapsed_s": 6703.384733438492, "loss": 3.0423710346221924, "hidden": 0.18503785505890846, "layer": 0.08943272940814495, "mlm": 1.566678375005722, "distill": 1.0609004944562912, "teacher_acc": 0.7249512076377869 }, { "step": 9031, "lr": 2.084070986841748e-05, "elapsed_s": 6710.791173458099, "loss": 3.006297469139099, "hidden": 0.18876268342137337, "layer": 0.09146064519882202, "mlm": 1.5095337331295013, "distill": 1.0735080242156982, "teacher_acc": 0.7247065156698227 }, { "step": 9041, "lr": 2.0791073966324037e-05, "elapsed_s": 6718.199744224548, "loss": 2.9743499755859375, "hidden": 0.18308956176042557, "layer": 0.08879238180816174, "mlm": 1.5403054058551788, "distill": 1.0234692841768265, "teacher_acc": 0.7184507697820663 }, { "step": 9051, "lr": 2.0741455133765792e-05, "elapsed_s": 6725.576699733734, "loss": 2.9561312794685364, "hidden": 0.18552611023187637, "layer": 0.08953426405787468, "mlm": 1.487838089466095, "distill": 1.0524738132953644, "teacher_acc": 0.7321216762065887 }, { "step": 9061, "lr": 2.0691853571974707e-05, "elapsed_s": 6732.906847715378, "loss": 2.9539469480514526, "hidden": 0.1784037910401821, "layer": 0.08854863233864307, "mlm": 1.5525899231433868, "distill": 1.0002751350402832, "teacher_acc": 0.712956041097641 }, { "step": 9071, "lr": 2.064226948211268e-05, "elapsed_s": 6740.290674448013, "loss": 2.8657299876213074, "hidden": 0.17860187962651253, "layer": 0.08830633945763111, "mlm": 1.4841061234474182, "distill": 0.9802669137716293, "teacher_acc": 0.7153952717781067 }, { "step": 9081, "lr": 2.059270306527078e-05, "elapsed_s": 6747.6943900585175, "loss": 2.925731837749481, "hidden": 0.18265193328261375, "layer": 0.08962615951895714, "mlm": 1.4300443530082703, "distill": 1.085570588707924, "teacher_acc": 0.7369037866592407 }, { "step": 9091, "lr": 2.0543154522468378e-05, "elapsed_s": 6755.078178167343, "loss": 2.9933385848999023, "hidden": 0.18611905723810196, "layer": 0.08938478119671345, "mlm": 1.5744709074497223, "distill": 1.0019371956586838, "teacher_acc": 0.6952493041753769 }, { "step": 9101, "lr": 2.0493624054652357e-05, "elapsed_s": 6762.4684002399445, "loss": 2.8948601484298706, "hidden": 0.17796407639980316, "layer": 0.08869042247533798, "mlm": 1.5196565091609955, "distill": 0.9749303013086319, "teacher_acc": 0.7197262048721313 }, { "step": 9111, "lr": 2.0444111862696314e-05, "elapsed_s": 6769.887577056885, "loss": 3.0102808475494385, "hidden": 0.18353719636797905, "layer": 0.08963865600526333, "mlm": 1.59958216547966, "distill": 0.9988049864768982, "teacher_acc": 0.6965661942958832 }, { "step": 9121, "lr": 2.0394618147399713e-05, "elapsed_s": 6777.316593170166, "loss": 2.9312583208084106, "hidden": 0.17946429178118706, "layer": 0.0885950792580843, "mlm": 1.515754371881485, "distill": 1.0122778415679932, "teacher_acc": 0.7262444049119949 }, { "step": 9131, "lr": 2.0345143109487083e-05, "elapsed_s": 6784.73273396492, "loss": 3.0623274445533752, "hidden": 0.183815635740757, "layer": 0.08891385607421398, "mlm": 1.572904258966446, "distill": 1.0773349553346634, "teacher_acc": 0.7191461026668549 }, { "step": 9141, "lr": 2.029568694960722e-05, "elapsed_s": 6792.169924259186, "loss": 2.833001971244812, "hidden": 0.18117699772119522, "layer": 0.08910947479307652, "mlm": 1.3731937408447266, "distill": 1.0528995096683502, "teacher_acc": 0.7619260400533676 }, { "step": 9151, "lr": 2.0246249868332336e-05, "elapsed_s": 6799.594704151154, "loss": 3.013506054878235, "hidden": 0.1850515715777874, "layer": 0.0883651040494442, "mlm": 1.5346341133117676, "distill": 1.0645862519741058, "teacher_acc": 0.7193938791751862 }, { "step": 9161, "lr": 2.019683206615729e-05, "elapsed_s": 6807.020638227463, "loss": 2.927738904953003, "hidden": 0.18236613646149635, "layer": 0.08965080976486206, "mlm": 1.474910020828247, "distill": 1.043271318078041, "teacher_acc": 0.7396684736013412 }, { "step": 9171, "lr": 2.014743374349875e-05, "elapsed_s": 6814.445960521698, "loss": 2.9673004150390625, "hidden": 0.18666526675224304, "layer": 0.08934594504535198, "mlm": 1.465211659669876, "distill": 1.0840852558612823, "teacher_acc": 0.7396788746118546 }, { "step": 9181, "lr": 2.0098055100694376e-05, "elapsed_s": 6821.8679003715515, "loss": 2.9574989676475525, "hidden": 0.18415352329611778, "layer": 0.08890662156045437, "mlm": 1.5070875883102417, "distill": 1.0376510918140411, "teacher_acc": 0.7322539985179901 }, { "step": 9191, "lr": 2.0048696338002015e-05, "elapsed_s": 6829.272068977356, "loss": 2.969307065010071, "hidden": 0.18166471272706985, "layer": 0.0888749361038208, "mlm": 1.5413909256458282, "distill": 1.0201491713523865, "teacher_acc": 0.7219777256250381 }, { "step": 9201, "lr": 1.9999357655598893e-05, "elapsed_s": 6836.698894023895, "loss": 2.9928473830223083, "hidden": 0.1843622401356697, "layer": 0.08878703974187374, "mlm": 1.5087529718875885, "distill": 1.0709763765335083, "teacher_acc": 0.728574812412262 }, { "step": 9211, "lr": 1.99500392535808e-05, "elapsed_s": 6844.135104417801, "loss": 2.925539970397949, "hidden": 0.18351759016513824, "layer": 0.08963667042553425, "mlm": 1.5214453339576721, "distill": 0.9922410994768143, "teacher_acc": 0.7187430411577225 }, { "step": 9221, "lr": 1.990074133196129e-05, "elapsed_s": 6851.542471885681, "loss": 2.9569990634918213, "hidden": 0.1818954087793827, "layer": 0.08974380418658257, "mlm": 1.5206761956214905, "distill": 1.0276601314544678, "teacher_acc": 0.7194148004055023 }, { "step": 9231, "lr": 1.9851464090670817e-05, "elapsed_s": 6858.9192225933075, "loss": 2.967846930027008, "hidden": 0.1782795526087284, "layer": 0.08730392158031464, "mlm": 1.5537519454956055, "distill": 1.013883963227272, "teacher_acc": 0.7156500369310379 }, { "step": 9241, "lr": 1.980220772955602e-05, "elapsed_s": 6866.332326889038, "loss": 2.9644923210144043, "hidden": 0.18977142870426178, "layer": 0.09126338362693787, "mlm": 1.4899572432041168, "distill": 1.0493605732917786, "teacher_acc": 0.7206709831953049 }, { "step": 9251, "lr": 1.9752972448378814e-05, "elapsed_s": 6873.742569684982, "loss": 2.919346332550049, "hidden": 0.1817329190671444, "layer": 0.08774051256477833, "mlm": 1.5148523151874542, "distill": 0.9971580058336258, "teacher_acc": 0.713471457362175 }, { "step": 9261, "lr": 1.9703758446815644e-05, "elapsed_s": 6881.163727760315, "loss": 2.9146288633346558, "hidden": 0.1810181438922882, "layer": 0.08793342486023903, "mlm": 1.5002846121788025, "distill": 1.00834122300148, "teacher_acc": 0.7204383313655853 }, { "step": 9271, "lr": 1.965456592445665e-05, "elapsed_s": 6888.547842264175, "loss": 2.9853222966194153, "hidden": 0.1813402846455574, "layer": 0.08915203623473644, "mlm": 1.5814407765865326, "distill": 0.9966249614953995, "teacher_acc": 0.7130928039550781 }, { "step": 9281, "lr": 1.960539508080485e-05, "elapsed_s": 6895.972282171249, "loss": 3.0880581736564636, "hidden": 0.1843983605504036, "layer": 0.09014306217432022, "mlm": 1.5965635478496552, "distill": 1.0776262879371643, "teacher_acc": 0.7143307626247406 }, { "step": 9291, "lr": 1.9556246115275363e-05, "elapsed_s": 6903.398527622223, "loss": 2.885476231575012, "hidden": 0.18250679969787598, "layer": 0.08813094906508923, "mlm": 1.4706672728061676, "distill": 1.0057299733161926, "teacher_acc": 0.7248648554086685 }, { "step": 9301, "lr": 1.950711922719458e-05, "elapsed_s": 6910.838722705841, "loss": 3.0008015036582947, "hidden": 0.1779869943857193, "layer": 0.0865168645977974, "mlm": 1.596402257680893, "distill": 1.0051668286323547, "teacher_acc": 0.7009795606136322 }, { "step": 9311, "lr": 1.9458014615799326e-05, "elapsed_s": 6918.265877962112, "loss": 3.0652342438697815, "hidden": 0.18569746986031532, "layer": 0.08882743120193481, "mlm": 1.6116750538349152, "distill": 1.0377505719661713, "teacher_acc": 0.705446183681488 }, { "step": 9321, "lr": 1.9408932480236118e-05, "elapsed_s": 6925.684828281403, "loss": 2.8885658383369446, "hidden": 0.1742679961025715, "layer": 0.08710605278611183, "mlm": 1.5368615984916687, "distill": 0.9596152454614639, "teacher_acc": 0.7066280841827393 }, { "step": 9331, "lr": 1.9359873019560298e-05, "elapsed_s": 6933.095467805862, "loss": 2.8027408123016357, "hidden": 0.17293189838528633, "layer": 0.08650610409677029, "mlm": 1.4783698618412018, "distill": 0.9352541267871857, "teacher_acc": 0.7269388437271118 }, { "step": 9341, "lr": 1.931083643273525e-05, "elapsed_s": 6940.491014957428, "loss": 3.0786247849464417, "hidden": 0.189407829195261, "layer": 0.09113780222833157, "mlm": 1.524317055940628, "distill": 1.1299230754375458, "teacher_acc": 0.7357308566570282 }, { "step": 9351, "lr": 1.926182291863162e-05, "elapsed_s": 6947.870617866516, "loss": 2.8821210861206055, "hidden": 0.18381726369261742, "layer": 0.08906432054936886, "mlm": 1.4629663527011871, "distill": 1.0069881081581116, "teacher_acc": 0.7326804995536804 }, { "step": 9361, "lr": 1.921283267602643e-05, "elapsed_s": 6955.265247106552, "loss": 3.0665568709373474, "hidden": 0.18284516409039497, "layer": 0.08873661793768406, "mlm": 1.607182115316391, "distill": 1.0493161529302597, "teacher_acc": 0.7015600055456161 }, { "step": 9371, "lr": 1.9163865903602374e-05, "elapsed_s": 6962.685258150101, "loss": 2.99079567193985, "hidden": 0.18241433799266815, "layer": 0.08970578387379646, "mlm": 1.5495185554027557, "distill": 1.0315955579280853, "teacher_acc": 0.7178710252046585 }, { "step": 9381, "lr": 1.9114922799946923e-05, "elapsed_s": 6970.088163137436, "loss": 2.9857935905456543, "hidden": 0.18073765188455582, "layer": 0.08737485855817795, "mlm": 1.5455012321472168, "distill": 1.0351296961307526, "teacher_acc": 0.7217265367507935 }, { "step": 9391, "lr": 1.9066003563551584e-05, "elapsed_s": 6977.464441776276, "loss": 2.9821006655693054, "hidden": 0.18190068379044533, "layer": 0.08923388831317425, "mlm": 1.5737967789173126, "distill": 0.999885618686676, "teacher_acc": 0.7039564102888107 }, { "step": 9401, "lr": 1.9017108392811065e-05, "elapsed_s": 6984.848764896393, "loss": 2.9337278008461, "hidden": 0.18196579068899155, "layer": 0.08965999446809292, "mlm": 1.5058395564556122, "distill": 1.0191267430782318, "teacher_acc": 0.7280523777008057 }, { "step": 9411, "lr": 1.8968237486022454e-05, "elapsed_s": 6992.211396694183, "loss": 2.858056604862213, "hidden": 0.17986347898840904, "layer": 0.0875780712813139, "mlm": 1.4409327507019043, "distill": 1.0136079639196396, "teacher_acc": 0.7363061457872391 }, { "step": 9421, "lr": 1.891939104138445e-05, "elapsed_s": 6999.572383880615, "loss": 2.89581698179245, "hidden": 0.17713701725006104, "layer": 0.08852677047252655, "mlm": 1.5470444858074188, "distill": 0.9502349942922592, "teacher_acc": 0.7144889384508133 }, { "step": 9431, "lr": 1.887056925699656e-05, "elapsed_s": 7006.954679965973, "loss": 2.7948920726776123, "hidden": 0.17615030705928802, "layer": 0.08674420043826103, "mlm": 1.4227837920188904, "distill": 0.9764355272054672, "teacher_acc": 0.7339392006397247 }, { "step": 9441, "lr": 1.882177233085826e-05, "elapsed_s": 7014.334565401077, "loss": 3.002918004989624, "hidden": 0.18485255166888237, "layer": 0.0895133875310421, "mlm": 1.5169658362865448, "distill": 1.071490302681923, "teacher_acc": 0.7285916954278946 }, { "step": 9451, "lr": 1.8773000460868205e-05, "elapsed_s": 7021.76203250885, "loss": 2.847712218761444, "hidden": 0.18119439482688904, "layer": 0.08906062878668308, "mlm": 1.4232844412326813, "distill": 1.0175086855888367, "teacher_acc": 0.7444396317005157 }, { "step": 9461, "lr": 1.872425384482346e-05, "elapsed_s": 7029.186311721802, "loss": 2.874585211277008, "hidden": 0.18441222980618477, "layer": 0.088089969009161, "mlm": 1.4695186614990234, "distill": 0.9921971559524536, "teacher_acc": 0.7358139455318451 }, { "step": 9471, "lr": 1.867553268041864e-05, "elapsed_s": 7036.588424682617, "loss": 2.9314531683921814, "hidden": 0.18103083223104477, "layer": 0.08737107552587986, "mlm": 1.5569888055324554, "distill": 0.9687171280384064, "teacher_acc": 0.7083883136510849 }, { "step": 9481, "lr": 1.8626837165245165e-05, "elapsed_s": 7044.007306575775, "loss": 2.87921142578125, "hidden": 0.18087473139166832, "layer": 0.08881294913589954, "mlm": 1.489160418510437, "distill": 0.9838951081037521, "teacher_acc": 0.7239366918802261 }, { "step": 9491, "lr": 1.857816749679043e-05, "elapsed_s": 7051.432197809219, "loss": 2.987193465232849, "hidden": 0.18151448667049408, "layer": 0.08880833722651005, "mlm": 1.546518087387085, "distill": 1.0332422107458115, "teacher_acc": 0.7137254029512405 }, { "step": 9501, "lr": 1.852952387243698e-05, "elapsed_s": 7058.868223905563, "loss": 3.048856198787689, "hidden": 0.1871863380074501, "layer": 0.08909785002470016, "mlm": 1.5878590047359467, "distill": 1.0420755296945572, "teacher_acc": 0.7062763124704361 }, { "step": 9511, "lr": 1.8480906489461777e-05, "elapsed_s": 7066.283197641373, "loss": 2.8597522974014282, "hidden": 0.17677029967308044, "layer": 0.08772431313991547, "mlm": 1.477822870016098, "distill": 0.9845266491174698, "teacher_acc": 0.7231673300266266 }, { "step": 9521, "lr": 1.8432315545035328e-05, "elapsed_s": 7073.712001085281, "loss": 2.9775474667549133, "hidden": 0.1737140603363514, "layer": 0.0866665430366993, "mlm": 1.5912586450576782, "distill": 0.9955274164676666, "teacher_acc": 0.7076480388641357 }, { "step": 9531, "lr": 1.8383751236220932e-05, "elapsed_s": 7081.1467208862305, "loss": 2.914586842060089, "hidden": 0.17986729368567467, "layer": 0.08838069252669811, "mlm": 1.4901664853096008, "distill": 1.020495444536209, "teacher_acc": 0.7296864837408066 }, { "step": 9541, "lr": 1.8335213759973867e-05, "elapsed_s": 7088.537719964981, "loss": 2.771449565887451, "hidden": 0.17355427145957947, "layer": 0.08566816709935665, "mlm": 1.4420372545719147, "distill": 0.939469650387764, "teacher_acc": 0.7277169972658157 }, { "step": 9551, "lr": 1.828670331314058e-05, "elapsed_s": 7095.962240695953, "loss": 2.972373068332672, "hidden": 0.18390975520014763, "layer": 0.088649220764637, "mlm": 1.5491628348827362, "distill": 1.0110661089420319, "teacher_acc": 0.7177830338478088 }, { "step": 9561, "lr": 1.8238220092457907e-05, "elapsed_s": 7103.389812469482, "loss": 2.964231550693512, "hidden": 0.18690602853894234, "layer": 0.09038912691175938, "mlm": 1.5221154391765594, "distill": 1.023109570145607, "teacher_acc": 0.7127853482961655 }, { "step": 9571, "lr": 1.818976429455227e-05, "elapsed_s": 7110.818918943405, "loss": 3.039660096168518, "hidden": 0.18311809748411179, "layer": 0.09001516364514828, "mlm": 1.5474238693714142, "distill": 1.0809924751520157, "teacher_acc": 0.7194809466600418 }, { "step": 9581, "lr": 1.8141336115938855e-05, "elapsed_s": 7118.218975543976, "loss": 2.8330073952674866, "hidden": 0.17944420129060745, "layer": 0.0872870646417141, "mlm": 1.4353662431240082, "distill": 0.9951091408729553, "teacher_acc": 0.7472753375768661 }, { "step": 9591, "lr": 1.8092935753020872e-05, "elapsed_s": 7125.602208852768, "loss": 2.857641875743866, "hidden": 0.18098565563559532, "layer": 0.08737301453948021, "mlm": 1.4529776573181152, "distill": 0.999006375670433, "teacher_acc": 0.736237108707428 }, { "step": 9601, "lr": 1.8044563402088684e-05, "elapsed_s": 7133.003538131714, "loss": 2.9869678020477295, "hidden": 0.18362656980752945, "layer": 0.08825022913515568, "mlm": 1.5269827842712402, "distill": 1.0486067533493042, "teacher_acc": 0.7159464806318283 }, { "step": 9611, "lr": 1.799621925931908e-05, "elapsed_s": 7140.358384132385, "loss": 2.891387164592743, "hidden": 0.180673535913229, "layer": 0.08755313791334629, "mlm": 1.4683393239974976, "distill": 1.017924278974533, "teacher_acc": 0.7327839434146881 }, { "step": 9621, "lr": 1.794790352077444e-05, "elapsed_s": 7147.730759143829, "loss": 2.8908419609069824, "hidden": 0.17931223288178444, "layer": 0.08794867619872093, "mlm": 1.491335928440094, "distill": 0.9969072341918945, "teacher_acc": 0.7340661883354187 }, { "step": 9631, "lr": 1.7899616382401936e-05, "elapsed_s": 7155.118606090546, "loss": 2.95628160238266, "hidden": 0.18000198900699615, "layer": 0.08795659244060516, "mlm": 1.5590976476669312, "distill": 0.9932016432285309, "teacher_acc": 0.70753613114357 }, { "step": 9641, "lr": 1.7851358040032774e-05, "elapsed_s": 7162.507756948471, "loss": 3.0132035613059998, "hidden": 0.18315986916422844, "layer": 0.08948343992233276, "mlm": 1.563630759716034, "distill": 1.0385113209486008, "teacher_acc": 0.7155729830265045 }, { "step": 9651, "lr": 1.7803128689381348e-05, "elapsed_s": 7169.892201662064, "loss": 2.875238835811615, "hidden": 0.18072212859988213, "layer": 0.08905250765383244, "mlm": 1.459745466709137, "distill": 1.0095228254795074, "teacher_acc": 0.730450227856636 }, { "step": 9661, "lr": 1.7754928526044508e-05, "elapsed_s": 7177.268668889999, "loss": 2.973810315132141, "hidden": 0.1847980059683323, "layer": 0.0908763688057661, "mlm": 1.5130847096443176, "distill": 1.045691356062889, "teacher_acc": 0.7287781536579132 }, { "step": 9671, "lr": 1.7706757745500704e-05, "elapsed_s": 7184.6558883190155, "loss": 2.923809051513672, "hidden": 0.17994924634695053, "layer": 0.0881443228572607, "mlm": 1.5359739661216736, "distill": 0.983864426612854, "teacher_acc": 0.7246852517127991 }, { "step": 9681, "lr": 1.7658616543109236e-05, "elapsed_s": 7192.055111885071, "loss": 3.047480881214142, "hidden": 0.1849786527454853, "layer": 0.09122404456138611, "mlm": 1.5645566284656525, "distill": 1.0673549324274063, "teacher_acc": 0.7143561840057373 }, { "step": 9691, "lr": 1.761050511410945e-05, "elapsed_s": 7199.431858301163, "loss": 2.89900541305542, "hidden": 0.1786932721734047, "layer": 0.08856531418859959, "mlm": 1.503677785396576, "distill": 0.9936584383249283, "teacher_acc": 0.7269929200410843 }, { "step": 9701, "lr": 1.756242365361993e-05, "elapsed_s": 7206.812950134277, "loss": 2.953303575515747, "hidden": 0.1790499947965145, "layer": 0.08835804834961891, "mlm": 1.5425972640514374, "distill": 1.0084273517131805, "teacher_acc": 0.7097474932670593 }, { "step": 9711, "lr": 1.7514372356637737e-05, "elapsed_s": 7214.2141535282135, "loss": 2.9644117951393127, "hidden": 0.18014828488230705, "layer": 0.08812434785068035, "mlm": 1.5744625627994537, "distill": 0.9855905473232269, "teacher_acc": 0.7067606449127197 }, { "step": 9721, "lr": 1.746635141803761e-05, "elapsed_s": 7221.654469490051, "loss": 2.835680067539215, "hidden": 0.18059510737657547, "layer": 0.08811885118484497, "mlm": 1.423556238412857, "distill": 1.0068742334842682, "teacher_acc": 0.7343530356884003 }, { "step": 9731, "lr": 1.741836103257113e-05, "elapsed_s": 7229.05019235611, "loss": 2.9229743480682373, "hidden": 0.17685290053486824, "layer": 0.08774774894118309, "mlm": 1.5588662922382355, "distill": 0.9665284156799316, "teacher_acc": 0.7013914734125137 }, { "step": 9741, "lr": 1.737040139486601e-05, "elapsed_s": 7236.461788415909, "loss": 2.9146392941474915, "hidden": 0.1778394728899002, "layer": 0.08685998804867268, "mlm": 1.544300228357315, "distill": 0.9712301343679428, "teacher_acc": 0.7115725874900818 }, { "step": 9751, "lr": 1.7322472699425234e-05, "elapsed_s": 7243.846519708633, "loss": 2.9185555577278137, "hidden": 0.17941498011350632, "layer": 0.08871552720665932, "mlm": 1.5069102048873901, "distill": 1.0084575861692429, "teacher_acc": 0.718881145119667 }, { "step": 9761, "lr": 1.7274575140626318e-05, "elapsed_s": 7251.268625736237, "loss": 2.7823609113693237, "hidden": 0.18060053139925003, "layer": 0.08777744695544243, "mlm": 1.3797779083251953, "distill": 0.9974932074546814, "teacher_acc": 0.7495899647474289 }, { "step": 9771, "lr": 1.7226708912720495e-05, "elapsed_s": 7258.690372467041, "loss": 2.975046753883362, "hidden": 0.17362254485487938, "layer": 0.08692162297666073, "mlm": 1.5620619058609009, "distill": 1.0222789943218231, "teacher_acc": 0.7179158478975296 }, { "step": 9781, "lr": 1.7178874209831926e-05, "elapsed_s": 7266.119971990585, "loss": 2.9299359917640686, "hidden": 0.18009553477168083, "layer": 0.08906017430126667, "mlm": 1.5294901132583618, "distill": 0.9957247525453568, "teacher_acc": 0.7166904807090759 }, { "step": 9791, "lr": 1.713107122595693e-05, "elapsed_s": 7273.535041809082, "loss": 2.927403748035431, "hidden": 0.1768750362098217, "layer": 0.08731957338750362, "mlm": 1.5450462102890015, "distill": 0.9849476665258408, "teacher_acc": 0.7107117027044296 }, { "step": 9801, "lr": 1.7083300154963193e-05, "elapsed_s": 7280.95568728447, "loss": 2.7772064805030823, "hidden": 0.17559348419308662, "layer": 0.08633293025195599, "mlm": 1.4432721138000488, "distill": 0.9395809322595596, "teacher_acc": 0.7306736409664154 }, { "step": 9811, "lr": 1.7035561190588952e-05, "elapsed_s": 7288.366719245911, "loss": 3.0731698274612427, "hidden": 0.1909678913652897, "layer": 0.09065776504576206, "mlm": 1.5138513147830963, "distill": 1.1320538520812988, "teacher_acc": 0.7327067255973816 }, { "step": 9821, "lr": 1.6987854526442264e-05, "elapsed_s": 7295.805382728577, "loss": 2.967125654220581, "hidden": 0.1809689849615097, "layer": 0.08931695856153965, "mlm": 1.5038708448410034, "distill": 1.0566583424806595, "teacher_acc": 0.734115868806839 }, { "step": 9831, "lr": 1.6940180356000168e-05, "elapsed_s": 7303.246222734451, "loss": 2.9639387130737305, "hidden": 0.18302374705672264, "layer": 0.0889599658548832, "mlm": 1.4987303912639618, "distill": 1.0546807646751404, "teacher_acc": 0.7253968268632889 }, { "step": 9841, "lr": 1.6892538872607937e-05, "elapsed_s": 7310.652861595154, "loss": 2.844963312149048, "hidden": 0.17552710697054863, "layer": 0.08675637282431126, "mlm": 1.4993855357170105, "distill": 0.9511454403400421, "teacher_acc": 0.71675243973732 }, { "step": 9851, "lr": 1.6844930269478274e-05, "elapsed_s": 7318.030217170715, "loss": 2.8490097522735596, "hidden": 0.17603646218776703, "layer": 0.08703974261879921, "mlm": 1.504111260175705, "distill": 0.9493057131767273, "teacher_acc": 0.7179317623376846 }, { "step": 9861, "lr": 1.679735473969053e-05, "elapsed_s": 7325.405548334122, "loss": 2.9066742062568665, "hidden": 0.18075070902705193, "layer": 0.08813525177538395, "mlm": 1.5162778794765472, "distill": 0.9848272651433945, "teacher_acc": 0.7127037644386292 }, { "step": 9871, "lr": 1.6749812476189935e-05, "elapsed_s": 7332.798872947693, "loss": 3.1854604482650757, "hidden": 0.18603482469916344, "layer": 0.09088591858744621, "mlm": 1.558554083108902, "distill": 1.2093938887119293, "teacher_acc": 0.7316144406795502 }, { "step": 9881, "lr": 1.6702303671786797e-05, "elapsed_s": 7340.163810968399, "loss": 2.8082371950149536, "hidden": 0.18210791796445847, "layer": 0.08892356231808662, "mlm": 1.3525468707084656, "distill": 1.0470127761363983, "teacher_acc": 0.7591568678617477 }, { "step": 9891, "lr": 1.665482851915573e-05, "elapsed_s": 7347.554973125458, "loss": 2.887851655483246, "hidden": 0.1780196614563465, "layer": 0.08653615042567253, "mlm": 1.493287056684494, "distill": 0.9952571094036102, "teacher_acc": 0.7202744483947754 }, { "step": 9901, "lr": 1.6607387210834887e-05, "elapsed_s": 7354.904918670654, "loss": 3.0758196115493774, "hidden": 0.1849890537559986, "layer": 0.08875576965510845, "mlm": 1.647627055644989, "distill": 1.0138365626335144, "teacher_acc": 0.6910272836685181 }, { "step": 9911, "lr": 1.6559979939225128e-05, "elapsed_s": 7362.275346040726, "loss": 2.8595410585403442, "hidden": 0.17881251499056816, "layer": 0.08778204023838043, "mlm": 1.4244898855686188, "distill": 1.033535212278366, "teacher_acc": 0.7343051582574844 }, { "step": 9921, "lr": 1.6512606896589323e-05, "elapsed_s": 7369.682178497314, "loss": 2.8354130387306213, "hidden": 0.17696453258395195, "layer": 0.08690304309129715, "mlm": 1.5012941658496857, "distill": 0.9367383569478989, "teacher_acc": 0.7208409160375595 }, { "step": 9931, "lr": 1.646526827505148e-05, "elapsed_s": 7377.0850830078125, "loss": 2.8742676377296448, "hidden": 0.17765381932258606, "layer": 0.08699697442352772, "mlm": 1.4730963706970215, "distill": 1.002365157008171, "teacher_acc": 0.7427856922149658 }, { "step": 9941, "lr": 1.6417964266596043e-05, "elapsed_s": 7384.455932855606, "loss": 2.9628148674964905, "hidden": 0.18117588013410568, "layer": 0.08969128876924515, "mlm": 1.5167653858661652, "distill": 1.0388521254062653, "teacher_acc": 0.7283293008804321 }, { "step": 9951, "lr": 1.6370695063067053e-05, "elapsed_s": 7391.832479476929, "loss": 2.851147711277008, "hidden": 0.17699117958545685, "layer": 0.08680770173668861, "mlm": 1.4818080067634583, "distill": 0.9719534516334534, "teacher_acc": 0.7335547059774399 }, { "step": 9961, "lr": 1.6323460856167426e-05, "elapsed_s": 7399.206396579742, "loss": 3.0169769525527954, "hidden": 0.18121608719229698, "layer": 0.08835496753454208, "mlm": 1.5947742760181427, "distill": 1.0155929774045944, "teacher_acc": 0.7150907069444656 }, { "step": 9971, "lr": 1.6276261837458123e-05, "elapsed_s": 7406.59486746788, "loss": 2.8825445771217346, "hidden": 0.1777927614748478, "layer": 0.0882922112941742, "mlm": 1.4628415405750275, "distill": 1.0199714004993439, "teacher_acc": 0.7431914657354355 }, { "step": 9981, "lr": 1.6229098198357408e-05, "elapsed_s": 7413.9206635952, "loss": 2.938017189502716, "hidden": 0.1840236410498619, "layer": 0.0877886414527893, "mlm": 1.53719824552536, "distill": 0.9888773113489151, "teacher_acc": 0.7157649099826813 }, { "step": 9991, "lr": 1.6181970130140066e-05, "elapsed_s": 7421.304645776749, "loss": 2.80196076631546, "hidden": 0.1804322525858879, "layer": 0.08815579116344452, "mlm": 1.4045225381851196, "distill": 0.9924958199262619, "teacher_acc": 0.7442905008792877 }, { "step": 10001, "lr": 1.613487782393661e-05, "elapsed_s": 7430.69629073143, "loss": 3.003439486026764, "hidden": 0.17982863262295723, "layer": 0.08787352591753006, "mlm": 1.6038479506969452, "distill": 0.9959975630044937, "teacher_acc": 0.7019294500350952 }, { "step": 10011, "lr": 1.608782147073253e-05, "elapsed_s": 7438.061214208603, "loss": 3.0181021690368652, "hidden": 0.1852869726717472, "layer": 0.08996334671974182, "mlm": 1.5328517258167267, "distill": 1.0696948766708374, "teacher_acc": 0.7213388383388519 }, { "step": 10021, "lr": 1.6040801261367493e-05, "elapsed_s": 7445.437765598297, "loss": 2.9223610162734985, "hidden": 0.1778326965868473, "layer": 0.08830015361309052, "mlm": 1.5157210528850555, "distill": 1.006824478507042, "teacher_acc": 0.7290975898504257 }, { "step": 10031, "lr": 1.5993817386534597e-05, "elapsed_s": 7452.824325323105, "loss": 2.8421236276626587, "hidden": 0.17729509249329567, "layer": 0.08825144357979298, "mlm": 1.460149198770523, "distill": 0.9832584708929062, "teacher_acc": 0.7264283001422882 }, { "step": 10041, "lr": 1.5946870036779586e-05, "elapsed_s": 7460.190210819244, "loss": 2.9949209690093994, "hidden": 0.18199637159705162, "layer": 0.08990189991891384, "mlm": 1.5370220839977264, "distill": 1.0489552170038223, "teacher_acc": 0.7236683368682861 }, { "step": 10051, "lr": 1.5899959402500046e-05, "elapsed_s": 7467.531365156174, "loss": 2.805436432361603, "hidden": 0.18041185662150383, "layer": 0.08785103633999825, "mlm": 1.4099665582180023, "distill": 0.9907206147909164, "teacher_acc": 0.7366474866867065 }, { "step": 10061, "lr": 1.5853085673944697e-05, "elapsed_s": 7474.873639345169, "loss": 2.9663367867469788, "hidden": 0.17970432713627815, "layer": 0.08887140452861786, "mlm": 1.5310087203979492, "distill": 1.0314836949110031, "teacher_acc": 0.7196492105722427 }, { "step": 10071, "lr": 1.5806249041212563e-05, "elapsed_s": 7482.232886552811, "loss": 2.9648497700691223, "hidden": 0.17497874423861504, "layer": 0.08719329908490181, "mlm": 1.5084562003612518, "distill": 1.0628393441438675, "teacher_acc": 0.7249744683504105 }, { "step": 10081, "lr": 1.5759449694252226e-05, "elapsed_s": 7489.616062641144, "loss": 2.838091492652893, "hidden": 0.17410090565681458, "layer": 0.08699353970587254, "mlm": 1.5020561516284943, "distill": 0.9443367123603821, "teacher_acc": 0.7131647020578384 }, { "step": 10091, "lr": 1.571268782286107e-05, "elapsed_s": 7497.00991153717, "loss": 2.9380322694778442, "hidden": 0.18527715653181076, "layer": 0.08950702846050262, "mlm": 1.449166625738144, "distill": 1.0735578536987305, "teacher_acc": 0.7430115938186646 }, { "step": 10101, "lr": 1.5665963616684476e-05, "elapsed_s": 7504.36677980423, "loss": 2.930846869945526, "hidden": 0.1796138398349285, "layer": 0.08817419223487377, "mlm": 1.5123560428619385, "distill": 1.0151760578155518, "teacher_acc": 0.7207438051700592 }, { "step": 10111, "lr": 1.5619277265215077e-05, "elapsed_s": 7511.744881391525, "loss": 2.921996772289276, "hidden": 0.1769735887646675, "layer": 0.08746769651770592, "mlm": 1.5687729120254517, "distill": 0.9555428922176361, "teacher_acc": 0.7002024799585342 }, { "step": 10121, "lr": 1.557262895779199e-05, "elapsed_s": 7519.128073215485, "loss": 2.852729916572571, "hidden": 0.17312494292855263, "layer": 0.08698642253875732, "mlm": 1.5092523694038391, "distill": 0.953734427690506, "teacher_acc": 0.7120293378829956 }, { "step": 10131, "lr": 1.5526018883600037e-05, "elapsed_s": 7526.520139694214, "loss": 2.827915370464325, "hidden": 0.1762291006743908, "layer": 0.08715229481458664, "mlm": 1.4780460894107819, "distill": 0.9538348913192749, "teacher_acc": 0.726918026804924 }, { "step": 10141, "lr": 1.5479447231668978e-05, "elapsed_s": 7533.927247285843, "loss": 2.983986258506775, "hidden": 0.18912728503346443, "layer": 0.09127629175782204, "mlm": 1.466661125421524, "distill": 1.0934324264526367, "teacher_acc": 0.74553382396698 }, { "step": 10151, "lr": 1.5432914190872757e-05, "elapsed_s": 7541.360129594803, "loss": 2.7671077251434326, "hidden": 0.1783139854669571, "layer": 0.0875600166618824, "mlm": 1.4014981091022491, "distill": 0.965201660990715, "teacher_acc": 0.7436766773462296 }, { "step": 10161, "lr": 1.5386419949928732e-05, "elapsed_s": 7548.769009590149, "loss": 2.8664923906326294, "hidden": 0.17761590331792831, "layer": 0.08717396482825279, "mlm": 1.4904872477054596, "distill": 0.9771863222122192, "teacher_acc": 0.7179876863956451 }, { "step": 10171, "lr": 1.5339964697396897e-05, "elapsed_s": 7556.171970129013, "loss": 2.9887197017669678, "hidden": 0.18235337734222412, "layer": 0.08834496513009071, "mlm": 1.553718626499176, "distill": 1.0261218696832657, "teacher_acc": 0.7176017761230469 }, { "step": 10181, "lr": 1.5293548621679127e-05, "elapsed_s": 7563.583142518997, "loss": 2.894451141357422, "hidden": 0.17966174706816673, "layer": 0.08759517222642899, "mlm": 1.5086528062820435, "distill": 0.9826772511005402, "teacher_acc": 0.7285481691360474 }, { "step": 10191, "lr": 1.5247171911018427e-05, "elapsed_s": 7571.021494150162, "loss": 2.9824821949005127, "hidden": 0.1800749935209751, "layer": 0.08921219408512115, "mlm": 1.5568162202835083, "distill": 1.020909920334816, "teacher_acc": 0.7141296565532684 }, { "step": 10201, "lr": 1.5200834753498128e-05, "elapsed_s": 7578.43163728714, "loss": 2.9277824759483337, "hidden": 0.1826518028974533, "layer": 0.08851532824337482, "mlm": 1.5152919590473175, "distill": 1.0029292851686478, "teacher_acc": 0.7173645943403244 }, { "step": 10211, "lr": 1.5154537337041174e-05, "elapsed_s": 7585.876492738724, "loss": 2.8564310669898987, "hidden": 0.18232426792383194, "layer": 0.0884082205593586, "mlm": 1.4360493123531342, "distill": 1.0115291327238083, "teacher_acc": 0.7387486547231674 }, { "step": 10221, "lr": 1.5108279849409335e-05, "elapsed_s": 7593.2914979457855, "loss": 2.906259834766388, "hidden": 0.18123461678624153, "layer": 0.08788170851767063, "mlm": 1.5110745131969452, "distill": 0.9887753427028656, "teacher_acc": 0.7239549160003662 }, { "step": 10231, "lr": 1.5062062478202436e-05, "elapsed_s": 7600.722090005875, "loss": 2.947192668914795, "hidden": 0.17599565163254738, "layer": 0.08744473196566105, "mlm": 1.557024359703064, "distill": 0.9944546073675156, "teacher_acc": 0.70560422539711 }, { "step": 10241, "lr": 1.5015885410857616e-05, "elapsed_s": 7608.113600492477, "loss": 2.8559728860855103, "hidden": 0.18119856715202332, "layer": 0.08960779383778572, "mlm": 1.417513757944107, "distill": 1.0312581360340118, "teacher_acc": 0.7418114244937897 }, { "step": 10251, "lr": 1.4969748834648556e-05, "elapsed_s": 7615.547703504562, "loss": 2.7950891256332397, "hidden": 0.17494433000683784, "layer": 0.08769348077476025, "mlm": 1.396903246641159, "distill": 1.004450410604477, "teacher_acc": 0.7413361072540283 }, { "step": 10261, "lr": 1.4923652936684723e-05, "elapsed_s": 7622.975331783295, "loss": 2.853096663951874, "hidden": 0.17926686629652977, "layer": 0.08738799579441547, "mlm": 1.4810059666633606, "distill": 0.9698629826307297, "teacher_acc": 0.7235698997974396 }, { "step": 10271, "lr": 1.4877597903910617e-05, "elapsed_s": 7630.39523267746, "loss": 2.9036999940872192, "hidden": 0.17764588445425034, "layer": 0.08864590153098106, "mlm": 1.4913431704044342, "distill": 1.012742057442665, "teacher_acc": 0.7309898138046265 }, { "step": 10281, "lr": 1.4831583923104999e-05, "elapsed_s": 7637.821432590485, "loss": 2.9167041182518005, "hidden": 0.18047721683979034, "layer": 0.08668654225766659, "mlm": 1.5306980907917023, "distill": 0.9817083179950714, "teacher_acc": 0.7128436267375946 }, { "step": 10291, "lr": 1.4785611180880143e-05, "elapsed_s": 7645.225907325745, "loss": 3.012228846549988, "hidden": 0.18359127268195152, "layer": 0.08894979394972324, "mlm": 1.533097267150879, "distill": 1.067474126815796, "teacher_acc": 0.7218306511640549 }, { "step": 10301, "lr": 1.4739679863681086e-05, "elapsed_s": 7652.653679847717, "loss": 2.917469322681427, "hidden": 0.17814286053180695, "layer": 0.08777454309165478, "mlm": 1.504893273115158, "distill": 1.0124030709266663, "teacher_acc": 0.7199055850505829 }, { "step": 10311, "lr": 1.4693790157784848e-05, "elapsed_s": 7660.067158937454, "loss": 2.8820289373397827, "hidden": 0.1813196875154972, "layer": 0.08812155947089195, "mlm": 1.4435787498950958, "distill": 1.031750038266182, "teacher_acc": 0.7325315773487091 }, { "step": 10321, "lr": 1.4647942249299707e-05, "elapsed_s": 7667.485271930695, "loss": 2.9324496388435364, "hidden": 0.17789708077907562, "layer": 0.0877643059939146, "mlm": 1.4990541338920593, "distill": 1.0337191224098206, "teacher_acc": 0.7291924357414246 }, { "step": 10331, "lr": 1.4602136324164417e-05, "elapsed_s": 7674.917230606079, "loss": 2.8862799406051636, "hidden": 0.17475510761141777, "layer": 0.08737952448427677, "mlm": 1.5169754028320312, "distill": 0.9761045724153519, "teacher_acc": 0.7264734357595444 }, { "step": 10341, "lr": 1.4556372568147483e-05, "elapsed_s": 7682.341321468353, "loss": 3.048863112926483, "hidden": 0.1806645803153515, "layer": 0.08840730786323547, "mlm": 1.5391749441623688, "distill": 1.1041553914546967, "teacher_acc": 0.7199923396110535 }, { "step": 10351, "lr": 1.4510651166846367e-05, "elapsed_s": 7689.776777982712, "loss": 2.903261661529541, "hidden": 0.18201984837651253, "layer": 0.08788246847689152, "mlm": 1.5032626688480377, "distill": 0.9920180886983871, "teacher_acc": 0.7213344126939774 }, { "step": 10361, "lr": 1.4464972305686777e-05, "elapsed_s": 7697.223017215729, "loss": 2.8741148710250854, "hidden": 0.18011771887540817, "layer": 0.08773745037615299, "mlm": 1.4926083981990814, "distill": 0.9774023294448853, "teacher_acc": 0.7121809720993042 }, { "step": 10371, "lr": 1.4419336169921893e-05, "elapsed_s": 7704.64383482933, "loss": 2.858348250389099, "hidden": 0.17916475608944893, "layer": 0.08749309927225113, "mlm": 1.4723995625972748, "distill": 0.9838726371526718, "teacher_acc": 0.7229121923446655 }, { "step": 10381, "lr": 1.4373742944631622e-05, "elapsed_s": 7712.074449300766, "loss": 2.917595684528351, "hidden": 0.18145322427153587, "layer": 0.08780582807958126, "mlm": 1.5095360279083252, "distill": 1.0012503117322922, "teacher_acc": 0.7191878110170364 }, { "step": 10391, "lr": 1.4328192814721846e-05, "elapsed_s": 7719.528669595718, "loss": 2.80202579498291, "hidden": 0.17872299253940582, "layer": 0.08836937882006168, "mlm": 1.4123475551605225, "distill": 0.9880475699901581, "teacher_acc": 0.742987871170044 }, { "step": 10401, "lr": 1.4282685964923642e-05, "elapsed_s": 7726.955592632294, "loss": 2.9938812255859375, "hidden": 0.1879442222416401, "layer": 0.09049897082149982, "mlm": 1.4676394164562225, "distill": 1.1051038056612015, "teacher_acc": 0.7386718243360519 }, { "step": 10411, "lr": 1.4237222579792618e-05, "elapsed_s": 7734.3602204322815, "loss": 2.807776629924774, "hidden": 0.17281070351600647, "layer": 0.08571877330541611, "mlm": 1.492429256439209, "distill": 0.9268665760755539, "teacher_acc": 0.7185997068881989 }, { "step": 10421, "lr": 1.4191802843708062e-05, "elapsed_s": 7741.776548862457, "loss": 2.9173110127449036, "hidden": 0.18102671578526497, "layer": 0.08790738321840763, "mlm": 1.528998464345932, "distill": 0.9823053926229477, "teacher_acc": 0.7239071279764175 }, { "step": 10431, "lr": 1.4146426940872277e-05, "elapsed_s": 7749.188870191574, "loss": 2.8313148617744446, "hidden": 0.18319915235042572, "layer": 0.08748494647443295, "mlm": 1.4635584354400635, "distill": 0.9576156586408615, "teacher_acc": 0.7208824902772903 }, { "step": 10441, "lr": 1.4101095055309746e-05, "elapsed_s": 7756.6106152534485, "loss": 2.92011559009552, "hidden": 0.1835278421640396, "layer": 0.08800114318728447, "mlm": 1.5004338026046753, "distill": 1.0086255371570587, "teacher_acc": 0.7249470055103302 }, { "step": 10451, "lr": 1.4055807370866485e-05, "elapsed_s": 7764.054565906525, "loss": 2.8488921523094177, "hidden": 0.1790946125984192, "layer": 0.08824432268738747, "mlm": 1.4330228865146637, "distill": 1.013557881116867, "teacher_acc": 0.7401723563671112 }, { "step": 10461, "lr": 1.4010564071209237e-05, "elapsed_s": 7771.451988220215, "loss": 2.8307689428329468, "hidden": 0.1771230474114418, "layer": 0.08662055991590023, "mlm": 1.4766446352005005, "distill": 0.9565679430961609, "teacher_acc": 0.7279039025306702 }, { "step": 10471, "lr": 1.3965365339824732e-05, "elapsed_s": 7778.867230892181, "loss": 2.9182360768318176, "hidden": 0.1831325888633728, "layer": 0.08828550390899181, "mlm": 1.4922117590904236, "distill": 1.0156163573265076, "teacher_acc": 0.7282605767250061 }, { "step": 10481, "lr": 1.392021136001897e-05, "elapsed_s": 7786.289425611496, "loss": 2.8439837098121643, "hidden": 0.17795449122786522, "layer": 0.08859201148152351, "mlm": 1.4827484786510468, "distill": 0.9610302448272705, "teacher_acc": 0.717214897274971 }, { "step": 10491, "lr": 1.3875102314916422e-05, "elapsed_s": 7793.672843456268, "loss": 2.9404280185699463, "hidden": 0.1754220873117447, "layer": 0.08772540651261806, "mlm": 1.539043664932251, "distill": 1.0066774785518646, "teacher_acc": 0.7314690053462982 }, { "step": 10501, "lr": 1.3830038387459354e-05, "elapsed_s": 7801.119505882263, "loss": 2.8838931918144226, "hidden": 0.17829493805766106, "layer": 0.08872641064226627, "mlm": 1.480123370885849, "distill": 1.0028167814016342, "teacher_acc": 0.7373668849468231 }, { "step": 10511, "lr": 1.3785019760407053e-05, "elapsed_s": 7808.514775514603, "loss": 2.714491546154022, "hidden": 0.174835667014122, "layer": 0.08605832792818546, "mlm": 1.3704897165298462, "distill": 0.9513013362884521, "teacher_acc": 0.7451911568641663 }, { "step": 10521, "lr": 1.3740046616335079e-05, "elapsed_s": 7815.936735391617, "loss": 2.73585307598114, "hidden": 0.17594927921891212, "layer": 0.08653202652931213, "mlm": 1.3991585075855255, "distill": 0.9415299445390701, "teacher_acc": 0.7395884245634079 }, { "step": 10531, "lr": 1.3695119137634544e-05, "elapsed_s": 7823.345595598221, "loss": 2.9362568259239197, "hidden": 0.18131597340106964, "layer": 0.0884503498673439, "mlm": 1.5110560953617096, "distill": 1.0183437019586563, "teacher_acc": 0.7218842655420303 }, { "step": 10541, "lr": 1.3650237506511331e-05, "elapsed_s": 7830.731982707977, "loss": 2.8972848057746887, "hidden": 0.1792755089700222, "layer": 0.08849368244409561, "mlm": 1.4782765209674835, "distill": 1.0162105113267899, "teacher_acc": 0.7314103543758392 }, { "step": 10551, "lr": 1.3605401904985427e-05, "elapsed_s": 7838.131356954575, "loss": 3.0389745235443115, "hidden": 0.18006238713860512, "layer": 0.08841749839484692, "mlm": 1.5982315242290497, "distill": 1.0364094972610474, "teacher_acc": 0.7085699439048767 }, { "step": 10561, "lr": 1.356061251489012e-05, "elapsed_s": 7845.543134689331, "loss": 2.9946030378341675, "hidden": 0.18319226801395416, "layer": 0.09013243392109871, "mlm": 1.528556913137436, "distill": 1.0545953661203384, "teacher_acc": 0.7218819558620453 }, { "step": 10571, "lr": 1.3515869517871288e-05, "elapsed_s": 7852.972601175308, "loss": 2.9079365730285645, "hidden": 0.17865262180566788, "layer": 0.0872088111937046, "mlm": 1.462127685546875, "distill": 1.0448992252349854, "teacher_acc": 0.7356737852096558 }, { "step": 10581, "lr": 1.3471173095386669e-05, "elapsed_s": 7860.408521652222, "loss": 2.9706795811653137, "hidden": 0.18146351352334023, "layer": 0.08906749822199345, "mlm": 1.5658102929592133, "distill": 0.997408539056778, "teacher_acc": 0.718964233994484 }, { "step": 10591, "lr": 1.342652342870509e-05, "elapsed_s": 7867.839487552643, "loss": 2.820731282234192, "hidden": 0.17802704498171806, "layer": 0.08731149137020111, "mlm": 1.4431924521923065, "distill": 0.9778289347887039, "teacher_acc": 0.7360071837902069 }, { "step": 10601, "lr": 1.3381920698905787e-05, "elapsed_s": 7875.25711607933, "loss": 2.8756213188171387, "hidden": 0.1747138872742653, "layer": 0.08734213374555111, "mlm": 1.5557876825332642, "distill": 0.9267347753047943, "teacher_acc": 0.7119696736335754 }, { "step": 10611, "lr": 1.3337365086877623e-05, "elapsed_s": 7882.685705423355, "loss": 3.003625810146332, "hidden": 0.1858767867088318, "layer": 0.08926649950444698, "mlm": 1.5266430079936981, "distill": 1.0605959594249725, "teacher_acc": 0.7280881404876709 }, { "step": 10621, "lr": 1.3292856773318384e-05, "elapsed_s": 7890.094223737717, "loss": 2.8903027772903442, "hidden": 0.18244284763932228, "layer": 0.08799527771770954, "mlm": 1.504819631576538, "distill": 0.9765997678041458, "teacher_acc": 0.7186618745326996 }, { "step": 10631, "lr": 1.3248395938734032e-05, "elapsed_s": 7897.527639865875, "loss": 3.049826979637146, "hidden": 0.18883823975920677, "layer": 0.0903621856123209, "mlm": 1.5401052832603455, "distill": 1.086864173412323, "teacher_acc": 0.7175163477659225 }, { "step": 10641, "lr": 1.320398276343795e-05, "elapsed_s": 7904.978014707565, "loss": 2.7387565970420837, "hidden": 0.17387425154447556, "layer": 0.08550853095948696, "mlm": 1.3985196948051453, "distill": 0.9497341066598892, "teacher_acc": 0.7384101450443268 }, { "step": 10651, "lr": 1.315961742755027e-05, "elapsed_s": 7912.4241461753845, "loss": 2.7505109906196594, "hidden": 0.1737189069390297, "layer": 0.0857369601726532, "mlm": 1.4088835716247559, "distill": 0.9513211250305176, "teacher_acc": 0.7335278689861298 }, { "step": 10661, "lr": 1.3115300110997098e-05, "elapsed_s": 7919.868975877762, "loss": 2.897267520427704, "hidden": 0.17698285728693008, "layer": 0.08742825873196125, "mlm": 1.4780522882938385, "distill": 1.0215354710817337, "teacher_acc": 0.7327415645122528 }, { "step": 10671, "lr": 1.3071030993509788e-05, "elapsed_s": 7927.312104225159, "loss": 2.87199330329895, "hidden": 0.17923161014914513, "layer": 0.08656316436827183, "mlm": 1.489340603351593, "distill": 0.9809079021215439, "teacher_acc": 0.7273224741220474 }, { "step": 10681, "lr": 1.302681025462424e-05, "elapsed_s": 7934.736119031906, "loss": 2.896890938282013, "hidden": 0.17528121918439865, "layer": 0.08683363534510136, "mlm": 1.481823354959488, "distill": 1.0210883617401123, "teacher_acc": 0.7294953763484955 }, { "step": 10691, "lr": 1.2982638073680112e-05, "elapsed_s": 7942.174689292908, "loss": 2.759673297405243, "hidden": 0.17198539525270462, "layer": 0.08498093672096729, "mlm": 1.4453786313533783, "distill": 0.9278333932161331, "teacher_acc": 0.7291694581508636 }, { "step": 10701, "lr": 1.293851462982017e-05, "elapsed_s": 7949.615513324738, "loss": 2.9145883321762085, "hidden": 0.18482211977243423, "layer": 0.09008979983627796, "mlm": 1.4679408073425293, "distill": 1.0319584012031555, "teacher_acc": 0.736321285367012 }, { "step": 10711, "lr": 1.289444010198951e-05, "elapsed_s": 7957.037538290024, "loss": 3.049929201602936, "hidden": 0.18432985991239548, "layer": 0.08944540098309517, "mlm": 1.5419031381607056, "distill": 1.0946436524391174, "teacher_acc": 0.7228672504425049 }, { "step": 10721, "lr": 1.285041466893485e-05, "elapsed_s": 7964.456969976425, "loss": 2.964224874973297, "hidden": 0.17951473966240883, "layer": 0.0875111073255539, "mlm": 1.5440576076507568, "distill": 1.0173822790384293, "teacher_acc": 0.7159728109836578 }, { "step": 10731, "lr": 1.2806438509203803e-05, "elapsed_s": 7971.910104751587, "loss": 3.0077428817749023, "hidden": 0.186091348528862, "layer": 0.08951134793460369, "mlm": 1.5429365932941437, "distill": 1.0478679239749908, "teacher_acc": 0.7214069217443466 }, { "step": 10741, "lr": 1.2762511801144133e-05, "elapsed_s": 7979.328640222549, "loss": 2.91107714176178, "hidden": 0.1789752058684826, "layer": 0.08725208602845669, "mlm": 1.5028254389762878, "distill": 1.0066752284765244, "teacher_acc": 0.7244965136051178 }, { "step": 10751, "lr": 1.2718634722903073e-05, "elapsed_s": 7986.758846282959, "loss": 2.849497675895691, "hidden": 0.17816199362277985, "layer": 0.08739409036934376, "mlm": 1.4631358981132507, "distill": 0.9863407611846924, "teacher_acc": 0.7267728447914124 }, { "step": 10761, "lr": 1.2674807452426565e-05, "elapsed_s": 7994.169144392014, "loss": 2.9450109004974365, "hidden": 0.17648660764098167, "layer": 0.08721574582159519, "mlm": 1.5794736742973328, "distill": 0.9689561575651169, "teacher_acc": 0.7112008631229401 }, { "step": 10771, "lr": 1.2631030167458568e-05, "elapsed_s": 8001.56565785408, "loss": 2.9443331956863403, "hidden": 0.17649906873703003, "layer": 0.08623652346432209, "mlm": 1.5921371579170227, "distill": 0.9560795873403549, "teacher_acc": 0.7092689871788025 }, { "step": 10781, "lr": 1.2587303045540314e-05, "elapsed_s": 8009.01592540741, "loss": 2.8592692017555237, "hidden": 0.17810314521193504, "layer": 0.08709154278039932, "mlm": 1.4945299625396729, "distill": 0.9649871289730072, "teacher_acc": 0.7186283767223358 }, { "step": 10791, "lr": 1.2543626264009577e-05, "elapsed_s": 8016.4046857357025, "loss": 3.045073986053467, "hidden": 0.18405351415276527, "layer": 0.08889592066407204, "mlm": 1.5948028862476349, "distill": 1.037716120481491, "teacher_acc": 0.7050633430480957 }, { "step": 10801, "lr": 1.2500000000000006e-05, "elapsed_s": 8023.803291082382, "loss": 2.8610616326332092, "hidden": 0.17923183739185333, "layer": 0.08687343075871468, "mlm": 1.4446918070316315, "distill": 1.0144694596529007, "teacher_acc": 0.7359804809093475 }, { "step": 10811, "lr": 1.245642443044035e-05, "elapsed_s": 8031.231106758118, "loss": 2.919489026069641, "hidden": 0.1818200834095478, "layer": 0.08892287313938141, "mlm": 1.4692298769950867, "distill": 1.0421575605869293, "teacher_acc": 0.7311240881681442 }, { "step": 10821, "lr": 1.2412899732053773e-05, "elapsed_s": 8038.647321939468, "loss": 2.812240958213806, "hidden": 0.17376632243394852, "layer": 0.08603236451745033, "mlm": 1.4356873333454132, "distill": 0.9860048294067383, "teacher_acc": 0.7340800166130066 }, { "step": 10831, "lr": 1.2369426081357138e-05, "elapsed_s": 8046.051897764206, "loss": 2.9017006158828735, "hidden": 0.17419667169451714, "layer": 0.08619785495102406, "mlm": 1.5395678877830505, "distill": 0.9706405401229858, "teacher_acc": 0.7123187929391861 }, { "step": 10841, "lr": 1.2326003654660249e-05, "elapsed_s": 8053.444204568863, "loss": 2.926594853401184, "hidden": 0.17958706989884377, "layer": 0.08764453418552876, "mlm": 1.49676913022995, "distill": 1.0268293172121048, "teacher_acc": 0.7258793711662292 }, { "step": 10851, "lr": 1.2282632628065197e-05, "elapsed_s": 8060.847686052322, "loss": 3.173677980899811, "hidden": 0.1857832334935665, "layer": 0.09119569510221481, "mlm": 1.6747945249080658, "distill": 1.0817191302776337, "teacher_acc": 0.6949105560779572 }, { "step": 10861, "lr": 1.223931317746561e-05, "elapsed_s": 8068.2799236774445, "loss": 2.845583736896515, "hidden": 0.17506690695881844, "layer": 0.08639275655150414, "mlm": 1.5101032257080078, "distill": 0.942150354385376, "teacher_acc": 0.7145123034715652 }, { "step": 10871, "lr": 1.219604547854595e-05, "elapsed_s": 8075.700533151627, "loss": 3.042316496372223, "hidden": 0.18063481152057648, "layer": 0.08822735212743282, "mlm": 1.5936723053455353, "distill": 1.0432609468698502, "teacher_acc": 0.7096281051635742 }, { "step": 10881, "lr": 1.2152829706780786e-05, "elapsed_s": 8083.133833885193, "loss": 2.80331152677536, "hidden": 0.17149009928107262, "layer": 0.08549987524747849, "mlm": 1.50066077709198, "distill": 0.9169205576181412, "teacher_acc": 0.7157619893550873 }, { "step": 10891, "lr": 1.2109666037434103e-05, "elapsed_s": 8090.562560796738, "loss": 2.862439513206482, "hidden": 0.17378314211964607, "layer": 0.08636759035289288, "mlm": 1.4983938038349152, "distill": 0.9732956290245056, "teacher_acc": 0.7172624170780182 }, { "step": 10901, "lr": 1.2066554645558578e-05, "elapsed_s": 8098.022439241409, "loss": 2.923736035823822, "hidden": 0.17649774625897408, "layer": 0.08684984408318996, "mlm": 1.5769773125648499, "distill": 0.9503383189439774, "teacher_acc": 0.7077839225530624 }, { "step": 10911, "lr": 1.2023495705994878e-05, "elapsed_s": 8105.443075180054, "loss": 2.952065646648407, "hidden": 0.18032432720065117, "layer": 0.08837340399622917, "mlm": 1.5177892744541168, "distill": 1.0294411182403564, "teacher_acc": 0.7318726181983948 }, { "step": 10921, "lr": 1.1980489393370938e-05, "elapsed_s": 8112.8568115234375, "loss": 2.97021347284317, "hidden": 0.1823689453303814, "layer": 0.0889456607401371, "mlm": 1.5114178657531738, "distill": 1.0495848804712296, "teacher_acc": 0.7260873317718506 }, { "step": 10931, "lr": 1.1937535882101281e-05, "elapsed_s": 8120.26229095459, "loss": 2.8764527440071106, "hidden": 0.17667071893811226, "layer": 0.08732515946030617, "mlm": 1.4817224144935608, "distill": 0.9977263063192368, "teacher_acc": 0.7302416115999222 }, { "step": 10941, "lr": 1.1894635346386253e-05, "elapsed_s": 8127.668026685715, "loss": 2.897518754005432, "hidden": 0.1780134253203869, "layer": 0.08816490694880486, "mlm": 1.491661012172699, "distill": 1.0057484954595566, "teacher_acc": 0.733996793627739 }, { "step": 10951, "lr": 1.1851787960211398e-05, "elapsed_s": 8135.0835971832275, "loss": 3.082518696784973, "hidden": 0.18760431185364723, "layer": 0.091263297945261, "mlm": 1.5622581541538239, "distill": 1.0994202196598053, "teacher_acc": 0.7154341638088226 }, { "step": 10961, "lr": 1.180899389734668e-05, "elapsed_s": 8142.51713514328, "loss": 2.9126681685447693, "hidden": 0.17907466739416122, "layer": 0.08786855451762676, "mlm": 1.5165916085243225, "distill": 0.9939929097890854, "teacher_acc": 0.7216907143592834 }, { "step": 10971, "lr": 1.1766253331345819e-05, "elapsed_s": 8149.943874835968, "loss": 2.8558509349823, "hidden": 0.17591554298996925, "layer": 0.08646071888506413, "mlm": 1.5233791768550873, "distill": 0.9374103546142578, "teacher_acc": 0.714735209941864 }, { "step": 10981, "lr": 1.1723566435545586e-05, "elapsed_s": 8157.37261390686, "loss": 2.9577229022979736, "hidden": 0.18060832098126411, "layer": 0.0887327566742897, "mlm": 1.4503415524959564, "distill": 1.1017983257770538, "teacher_acc": 0.7396913170814514 }, { "step": 10991, "lr": 1.1680933383065057e-05, "elapsed_s": 8164.815044164658, "loss": 2.9793737530708313, "hidden": 0.18209616467356682, "layer": 0.08843136020004749, "mlm": 1.5104252696037292, "distill": 1.0605405569076538, "teacher_acc": 0.7222954481840134 }, { "step": 11001, "lr": 1.1638354346804971e-05, "elapsed_s": 8174.292570114136, "loss": 3.0591729879379272, "hidden": 0.18375826254487038, "layer": 0.08906274847686291, "mlm": 1.5488409101963043, "distill": 1.0982841551303864, "teacher_acc": 0.713960126042366 }, { "step": 11011, "lr": 1.1595829499446997e-05, "elapsed_s": 8181.700609445572, "loss": 2.811732530593872, "hidden": 0.17359792441129684, "layer": 0.0867298599332571, "mlm": 1.430332601070404, "distill": 0.9908391237258911, "teacher_acc": 0.7297311723232269 }, { "step": 11021, "lr": 1.1553359013453036e-05, "elapsed_s": 8189.092926263809, "loss": 2.8688098192214966, "hidden": 0.17574268206954002, "layer": 0.08731205761432648, "mlm": 1.5155298113822937, "distill": 0.9581385403871536, "teacher_acc": 0.718981072306633 }, { "step": 11031, "lr": 1.1510943061064524e-05, "elapsed_s": 8196.488725423813, "loss": 2.889613449573517, "hidden": 0.1785399131476879, "layer": 0.086368378251791, "mlm": 1.532465547323227, "distill": 0.9568838775157928, "teacher_acc": 0.7118146568536758 }, { "step": 11041, "lr": 1.1468581814301717e-05, "elapsed_s": 8203.896468400955, "loss": 2.8355020880699158, "hidden": 0.18041084706783295, "layer": 0.08836122043430805, "mlm": 1.39651557803154, "distill": 1.0339842736721039, "teacher_acc": 0.7444476783275604 }, { "step": 11051, "lr": 1.1426275444963034e-05, "elapsed_s": 8211.325413942337, "loss": 2.823788046836853, "hidden": 0.17146672680974007, "layer": 0.08550742268562317, "mlm": 1.4881187081336975, "distill": 0.9499821811914444, "teacher_acc": 0.7154545933008194 }, { "step": 11061, "lr": 1.1384024124624324e-05, "elapsed_s": 8218.712444782257, "loss": 3.0636661052703857, "hidden": 0.18050988391041756, "layer": 0.08853267505764961, "mlm": 1.5883564352989197, "distill": 1.07002355158329, "teacher_acc": 0.705975741147995 }, { "step": 11071, "lr": 1.1341828024638176e-05, "elapsed_s": 8226.138909816742, "loss": 2.8460269570350647, "hidden": 0.17565151304006577, "layer": 0.08687569014728069, "mlm": 1.4517238140106201, "distill": 0.9995622485876083, "teacher_acc": 0.7355851233005524 }, { "step": 11081, "lr": 1.1299687316133256e-05, "elapsed_s": 8233.527619123459, "loss": 2.897119104862213, "hidden": 0.18363207206130028, "layer": 0.09011726267635822, "mlm": 1.4538487195968628, "distill": 1.030947670340538, "teacher_acc": 0.7334865927696228 }, { "step": 11091, "lr": 1.125760217001354e-05, "elapsed_s": 8240.94069647789, "loss": 2.8547372817993164, "hidden": 0.18133947998285294, "layer": 0.0880105160176754, "mlm": 1.4419240951538086, "distill": 1.0061289370059967, "teacher_acc": 0.7333982437849045 }, { "step": 11101, "lr": 1.121557275695771e-05, "elapsed_s": 8248.357316493988, "loss": 2.8644628524780273, "hidden": 0.17004140466451645, "layer": 0.08553404547274113, "mlm": 1.4861394464969635, "distill": 0.9954736083745956, "teacher_acc": 0.7312144190073013 }, { "step": 11111, "lr": 1.1173599247418398e-05, "elapsed_s": 8255.764517068863, "loss": 2.893744111061096, "hidden": 0.17784874141216278, "layer": 0.08707399480044842, "mlm": 1.5358798801898956, "distill": 0.9586297124624252, "teacher_acc": 0.7142466902732849 }, { "step": 11121, "lr": 1.1131681811621527e-05, "elapsed_s": 8263.166898965836, "loss": 2.870635986328125, "hidden": 0.17893068492412567, "layer": 0.0879601389169693, "mlm": 1.50857412815094, "distill": 0.9602203816175461, "teacher_acc": 0.7221059054136276 }, { "step": 11131, "lr": 1.1089820619565613e-05, "elapsed_s": 8270.537461996078, "loss": 2.7392388582229614, "hidden": 0.17465965822339058, "layer": 0.08662197552621365, "mlm": 1.3773939311504364, "distill": 0.969214603304863, "teacher_acc": 0.7373160570859909 }, { "step": 11141, "lr": 1.1048015841021045e-05, "elapsed_s": 8277.955116271973, "loss": 2.9043917655944824, "hidden": 0.1735965758562088, "layer": 0.08871979638934135, "mlm": 1.535517692565918, "distill": 0.9773210138082504, "teacher_acc": 0.7159198969602585 }, { "step": 11151, "lr": 1.100626764552945e-05, "elapsed_s": 8285.359418392181, "loss": 2.7507399916648865, "hidden": 0.1750749908387661, "layer": 0.08621581457555294, "mlm": 1.3997158110141754, "distill": 0.9577663242816925, "teacher_acc": 0.7371083199977875 }, { "step": 11161, "lr": 1.096457620240298e-05, "elapsed_s": 8292.770998239517, "loss": 2.9044637084007263, "hidden": 0.17918264865875244, "layer": 0.08818322420120239, "mlm": 1.5083374083042145, "distill": 0.9936694204807281, "teacher_acc": 0.7113655060529709 }, { "step": 11171, "lr": 1.0922941680723609e-05, "elapsed_s": 8300.178480148315, "loss": 2.853361964225769, "hidden": 0.18020496144890785, "layer": 0.08840948529541492, "mlm": 1.4550070762634277, "distill": 0.9937402456998825, "teacher_acc": 0.7284946739673615 }, { "step": 11181, "lr": 1.0881364249342482e-05, "elapsed_s": 8307.562896251678, "loss": 2.9452579617500305, "hidden": 0.18045639619231224, "layer": 0.08787625655531883, "mlm": 1.539931297302246, "distill": 1.000475749373436, "teacher_acc": 0.7181874066591263 }, { "step": 11191, "lr": 1.0839844076879185e-05, "elapsed_s": 8314.93463420868, "loss": 3.0016876459121704, "hidden": 0.17725010961294174, "layer": 0.08656693622469902, "mlm": 1.5905376970767975, "distill": 1.0133661776781082, "teacher_acc": 0.7064286321401596 }, { "step": 11201, "lr": 1.0798381331721109e-05, "elapsed_s": 8322.33320736885, "loss": 2.978957772254944, "hidden": 0.1827639564871788, "layer": 0.08845875971019268, "mlm": 1.5099029839038849, "distill": 1.0592975169420242, "teacher_acc": 0.7345392107963562 }, { "step": 11211, "lr": 1.0756976182022738e-05, "elapsed_s": 8329.735498905182, "loss": 2.8994853496551514, "hidden": 0.18071771413087845, "layer": 0.08622293546795845, "mlm": 1.504266768693924, "distill": 0.9906716197729111, "teacher_acc": 0.7245052307844162 }, { "step": 11221, "lr": 1.0715628795704976e-05, "elapsed_s": 8337.119082450867, "loss": 2.89864045381546, "hidden": 0.17699796706438065, "layer": 0.08716765977442265, "mlm": 1.5176758170127869, "distill": 0.9833848476409912, "teacher_acc": 0.7159259617328644 }, { "step": 11231, "lr": 1.0674339340454475e-05, "elapsed_s": 8344.486906290054, "loss": 2.8088842630386353, "hidden": 0.17852935567498207, "layer": 0.0869959183037281, "mlm": 1.437552809715271, "distill": 0.9707747846841812, "teacher_acc": 0.7310845106840134 }, { "step": 11241, "lr": 1.0633107983722912e-05, "elapsed_s": 8351.880491256714, "loss": 2.8802369832992554, "hidden": 0.17473775893449783, "layer": 0.08646500110626221, "mlm": 1.4971394538879395, "distill": 0.9903894811868668, "teacher_acc": 0.7188897430896759 }, { "step": 11251, "lr": 1.059193489272637e-05, "elapsed_s": 8359.259387016296, "loss": 2.9411877393722534, "hidden": 0.17962602525949478, "layer": 0.08809495531022549, "mlm": 1.5223579108715057, "distill": 1.0155303329229355, "teacher_acc": 0.7106743305921555 }, { "step": 11261, "lr": 1.0550820234444627e-05, "elapsed_s": 8366.676477432251, "loss": 2.908635199069977, "hidden": 0.17515680193901062, "layer": 0.0872745718806982, "mlm": 1.5419666469097137, "distill": 0.972717672586441, "teacher_acc": 0.712832972407341 }, { "step": 11271, "lr": 1.0509764175620485e-05, "elapsed_s": 8374.091731071472, "loss": 2.8143728971481323, "hidden": 0.1776893511414528, "layer": 0.08701508119702339, "mlm": 1.4451144933700562, "distill": 0.9703721851110458, "teacher_acc": 0.7318149507045746 }, { "step": 11281, "lr": 1.0468766882759094e-05, "elapsed_s": 8381.511043548584, "loss": 2.824914813041687, "hidden": 0.17489682510495186, "layer": 0.08707134239375591, "mlm": 1.4373705387115479, "distill": 0.9942149072885513, "teacher_acc": 0.7397149503231049 }, { "step": 11291, "lr": 1.042782852212725e-05, "elapsed_s": 8388.949609518051, "loss": 2.738795578479767, "hidden": 0.17358281463384628, "layer": 0.08582963235676289, "mlm": 1.4490820169448853, "distill": 0.8996331244707108, "teacher_acc": 0.7238960415124893 }, { "step": 11301, "lr": 1.0386949259752785e-05, "elapsed_s": 8396.338478803635, "loss": 2.897427797317505, "hidden": 0.17370864376425743, "layer": 0.08691506274044514, "mlm": 1.5385419130325317, "distill": 0.9680110216140747, "teacher_acc": 0.7181727737188339 }, { "step": 11311, "lr": 1.0346129261423829e-05, "elapsed_s": 8403.761209964752, "loss": 2.827839434146881, "hidden": 0.1758677139878273, "layer": 0.08664453215897083, "mlm": 1.4731989800930023, "distill": 0.959582731127739, "teacher_acc": 0.7223649621009827 }, { "step": 11321, "lr": 1.0305368692688174e-05, "elapsed_s": 8411.167393922806, "loss": 2.8418572545051575, "hidden": 0.17750455811619759, "layer": 0.08730238117277622, "mlm": 1.541614055633545, "distill": 0.9015828520059586, "teacher_acc": 0.7091637849807739 }, { "step": 11331, "lr": 1.0264667718852596e-05, "elapsed_s": 8418.592934846878, "loss": 2.9483031034469604, "hidden": 0.18206826597452164, "layer": 0.08887264877557755, "mlm": 1.5284055471420288, "distill": 1.0113246589899063, "teacher_acc": 0.7131596952676773 }, { "step": 11341, "lr": 1.022402650498216e-05, "elapsed_s": 8426.022907018661, "loss": 2.825657546520233, "hidden": 0.17415465414524078, "layer": 0.08641180768609047, "mlm": 1.4823412895202637, "distill": 0.9518010765314102, "teacher_acc": 0.7236685901880264 }, { "step": 11351, "lr": 1.0183445215899584e-05, "elapsed_s": 8433.44666981697, "loss": 2.9158015847206116, "hidden": 0.17578015476465225, "layer": 0.08694989047944546, "mlm": 1.530271828174591, "distill": 0.9904945194721222, "teacher_acc": 0.7128785252571106 }, { "step": 11361, "lr": 1.0142924016184568e-05, "elapsed_s": 8440.859045505524, "loss": 2.898588180541992, "hidden": 0.17610974609851837, "layer": 0.08696969226002693, "mlm": 1.5033361315727234, "distill": 0.9995477795600891, "teacher_acc": 0.7262991666793823 }, { "step": 11371, "lr": 1.01024630701731e-05, "elapsed_s": 8448.274160861969, "loss": 3.0256532430648804, "hidden": 0.18234818428754807, "layer": 0.08838297985494137, "mlm": 1.5864404439926147, "distill": 1.0303249061107635, "teacher_acc": 0.7109770625829697 }, { "step": 11381, "lr": 1.0062062541956819e-05, "elapsed_s": 8455.704915761948, "loss": 2.896264433860779, "hidden": 0.1722925379872322, "layer": 0.08687197417020798, "mlm": 1.5256859958171844, "distill": 0.9825573712587357, "teacher_acc": 0.7164729684591293 }, { "step": 11391, "lr": 1.0021722595382324e-05, "elapsed_s": 8463.129249811172, "loss": 2.8619176149368286, "hidden": 0.17419498413801193, "layer": 0.08679201267659664, "mlm": 1.5226439237594604, "distill": 0.9474877566099167, "teacher_acc": 0.7074283063411713 }, { "step": 11401, "lr": 9.981443394050525e-06, "elapsed_s": 8470.574127674103, "loss": 2.8641727566719055, "hidden": 0.18065128102898598, "layer": 0.08835645206272602, "mlm": 1.4715473651885986, "distill": 0.9871447086334229, "teacher_acc": 0.7299947142601013 }, { "step": 11411, "lr": 9.941225101315985e-06, "elapsed_s": 8477.975200176239, "loss": 2.9649810194969177, "hidden": 0.18841061741113663, "layer": 0.09030756168067455, "mlm": 1.4516553282737732, "distill": 1.0913506895303726, "teacher_acc": 0.7407376915216446 }, { "step": 11421, "lr": 9.901067880286235e-06, "elapsed_s": 8485.38941192627, "loss": 2.80659556388855, "hidden": 0.17252138629555702, "layer": 0.08550152741372585, "mlm": 1.466357707977295, "distill": 0.9524443596601486, "teacher_acc": 0.7323374450206757 }, { "step": 11431, "lr": 9.860971893821146e-06, "elapsed_s": 8492.786566257477, "loss": 2.8184033632278442, "hidden": 0.18014365062117577, "layer": 0.08865422755479813, "mlm": 1.4193513095378876, "distill": 0.9944376349449158, "teacher_acc": 0.7395077347755432 }, { "step": 11441, "lr": 9.820937304532221e-06, "elapsed_s": 8500.177840948105, "loss": 2.9423749446868896, "hidden": 0.1759333796799183, "layer": 0.08721175417304039, "mlm": 1.5651275217533112, "distill": 0.9817748218774796, "teacher_acc": 0.7038186490535736 }, { "step": 11451, "lr": 9.780964274781984e-06, "elapsed_s": 8507.578917741776, "loss": 2.8845903277397156, "hidden": 0.18232486769557, "layer": 0.08678038604557514, "mlm": 1.4921681582927704, "distill": 0.9843822568655014, "teacher_acc": 0.7170978635549545 }, { "step": 11461, "lr": 9.741052966683294e-06, "elapsed_s": 8514.973740816116, "loss": 2.9620314836502075, "hidden": 0.17883280664682388, "layer": 0.08934056758880615, "mlm": 1.596371352672577, "distill": 0.9633242040872574, "teacher_acc": 0.689149022102356 }, { "step": 11471, "lr": 9.7012035420987e-06, "elapsed_s": 8522.418118715286, "loss": 2.944342076778412, "hidden": 0.1806718222796917, "layer": 0.08816816098988056, "mlm": 1.5170991718769073, "distill": 1.021815150976181, "teacher_acc": 0.718651607632637 }, { "step": 11481, "lr": 9.66141616263978e-06, "elapsed_s": 8529.84995007515, "loss": 2.8999286890029907, "hidden": 0.17628328502178192, "layer": 0.0872431006282568, "mlm": 1.5417075753211975, "distill": 0.9620329290628433, "teacher_acc": 0.7076239287853241 }, { "step": 11491, "lr": 9.621690989666466e-06, "elapsed_s": 8537.30105805397, "loss": 2.8464741110801697, "hidden": 0.17579087242484093, "layer": 0.08706557750701904, "mlm": 1.497264564037323, "distill": 0.9540950208902359, "teacher_acc": 0.7276084423065186 }, { "step": 11501, "lr": 9.582028184286423e-06, "elapsed_s": 8544.708785533905, "loss": 2.885443389415741, "hidden": 0.17321577668190002, "layer": 0.08608797565102577, "mlm": 1.5416736900806427, "distill": 0.9542940706014633, "teacher_acc": 0.7116115689277649 }, { "step": 11511, "lr": 9.542427907354388e-06, "elapsed_s": 8552.149512529373, "loss": 2.885970413684845, "hidden": 0.18107197806239128, "layer": 0.08855819143354893, "mlm": 1.4717864990234375, "distill": 1.0077608972787857, "teacher_acc": 0.7346422225236893 }, { "step": 11521, "lr": 9.502890319471491e-06, "elapsed_s": 8559.52800488472, "loss": 2.9210673570632935, "hidden": 0.18180108815431595, "layer": 0.08815604075789452, "mlm": 1.5517668724060059, "distill": 0.9616202712059021, "teacher_acc": 0.7162619680166245 }, { "step": 11531, "lr": 9.463415580984653e-06, "elapsed_s": 8566.934325695038, "loss": 2.8077496886253357, "hidden": 0.18027520552277565, "layer": 0.08763755857944489, "mlm": 1.4142753779888153, "distill": 0.9891051352024078, "teacher_acc": 0.7354015558958054 }, { "step": 11541, "lr": 9.42400385198586e-06, "elapsed_s": 8574.341815948486, "loss": 2.980990469455719, "hidden": 0.180645439773798, "layer": 0.08775981143116951, "mlm": 1.562819391489029, "distill": 1.013000339269638, "teacher_acc": 0.7137101590633392 }, { "step": 11551, "lr": 9.3846552923116e-06, "elapsed_s": 8581.730875730515, "loss": 2.897901773452759, "hidden": 0.17938899621367455, "layer": 0.08682218566536903, "mlm": 1.479920893907547, "distill": 1.0157918184995651, "teacher_acc": 0.7351734191179276 }, { "step": 11561, "lr": 9.345370061542158e-06, "elapsed_s": 8589.13337278366, "loss": 2.8499958515167236, "hidden": 0.1732211969792843, "layer": 0.08609162271022797, "mlm": 1.5467858016490936, "distill": 0.9137218296527863, "teacher_acc": 0.7115947306156158 }, { "step": 11571, "lr": 9.306148319000987e-06, "elapsed_s": 8596.513417005539, "loss": 2.8371639251708984, "hidden": 0.18070733919739723, "layer": 0.0883625652641058, "mlm": 1.4371312856674194, "distill": 0.994436651468277, "teacher_acc": 0.7410618811845779 }, { "step": 11581, "lr": 9.266990223754069e-06, "elapsed_s": 8603.903351783752, "loss": 2.8276089429855347, "hidden": 0.17636990174651146, "layer": 0.08723104745149612, "mlm": 1.4409880936145782, "distill": 0.9902655184268951, "teacher_acc": 0.7365210205316544 }, { "step": 11591, "lr": 9.227895934609235e-06, "elapsed_s": 8611.298266172409, "loss": 2.908479630947113, "hidden": 0.17557913064956665, "layer": 0.0872409250587225, "mlm": 1.5281242430210114, "distill": 0.9855766892433167, "teacher_acc": 0.7225566357374191 }, { "step": 11601, "lr": 9.18886561011557e-06, "elapsed_s": 8618.642398118973, "loss": 2.913455545902252, "hidden": 0.18657585605978966, "layer": 0.08977381512522697, "mlm": 1.458300918340683, "distill": 1.0371160060167313, "teacher_acc": 0.7322098165750504 }, { "step": 11611, "lr": 9.149899408562745e-06, "elapsed_s": 8626.027275562286, "loss": 2.7774588465690613, "hidden": 0.1750325784087181, "layer": 0.0866832323372364, "mlm": 1.4090064764022827, "distill": 0.9750455617904663, "teacher_acc": 0.7393578290939331 }, { "step": 11621, "lr": 9.110997487980368e-06, "elapsed_s": 8633.433954954147, "loss": 3.0530285239219666, "hidden": 0.1826467029750347, "layer": 0.08954072929918766, "mlm": 1.6053223311901093, "distill": 1.0376424342393875, "teacher_acc": 0.7058679312467575 }, { "step": 11631, "lr": 9.072160006137367e-06, "elapsed_s": 8640.843310117722, "loss": 3.0000651478767395, "hidden": 0.18736637011170387, "layer": 0.09122733399271965, "mlm": 1.5146294832229614, "distill": 1.0650892555713654, "teacher_acc": 0.7262876927852631 }, { "step": 11641, "lr": 9.033387120541306e-06, "elapsed_s": 8648.24194765091, "loss": 2.9398823380470276, "hidden": 0.18013345822691917, "layer": 0.08839108608663082, "mlm": 1.5299261808395386, "distill": 1.0054936856031418, "teacher_acc": 0.7185913473367691 }, { "step": 11651, "lr": 8.994678988437802e-06, "elapsed_s": 8655.653980731964, "loss": 2.758953332901001, "hidden": 0.1731620542705059, "layer": 0.08695606701076031, "mlm": 1.4302538335323334, "distill": 0.9388974159955978, "teacher_acc": 0.731830433011055 }, { "step": 11661, "lr": 8.956035766809853e-06, "elapsed_s": 8663.048542499542, "loss": 2.961130976676941, "hidden": 0.16989745944738388, "layer": 0.08577794022858143, "mlm": 1.5996421575546265, "distill": 0.9788049161434174, "teacher_acc": 0.7035162150859833 }, { "step": 11671, "lr": 8.917457612377209e-06, "elapsed_s": 8670.456528425217, "loss": 2.8528011441230774, "hidden": 0.17657870799303055, "layer": 0.0878971554338932, "mlm": 1.4519985020160675, "distill": 1.0036966800689697, "teacher_acc": 0.7303527295589447 }, { "step": 11681, "lr": 8.878944681595742e-06, "elapsed_s": 8677.858333349228, "loss": 2.968489646911621, "hidden": 0.17904430255293846, "layer": 0.08768092468380928, "mlm": 1.573696345090866, "distill": 0.992864266037941, "teacher_acc": 0.7049909383058548 }, { "step": 11691, "lr": 8.840497130656783e-06, "elapsed_s": 8685.288291454315, "loss": 2.863508641719818, "hidden": 0.17423254996538162, "layer": 0.08627472631633282, "mlm": 1.5310141146183014, "distill": 0.9408920556306839, "teacher_acc": 0.7106742560863495 }, { "step": 11701, "lr": 8.802115115486535e-06, "elapsed_s": 8692.70529294014, "loss": 2.824951171875, "hidden": 0.1755516491830349, "layer": 0.08589500561356544, "mlm": 1.4995906054973602, "distill": 0.9313097149133682, "teacher_acc": 0.7210783660411835 }, { "step": 11711, "lr": 8.763798791745411e-06, "elapsed_s": 8700.105291843414, "loss": 3.013614237308502, "hidden": 0.1790935955941677, "layer": 0.08957492746412754, "mlm": 1.5755402743816376, "distill": 1.0350993275642395, "teacher_acc": 0.7133761942386627 }, { "step": 11721, "lr": 8.725548314827406e-06, "elapsed_s": 8707.488520860672, "loss": 2.8423375487327576, "hidden": 0.1754515841603279, "layer": 0.08722830563783646, "mlm": 1.4775493741035461, "distill": 0.9702708274126053, "teacher_acc": 0.7252146899700165 }, { "step": 11731, "lr": 8.687363839859482e-06, "elapsed_s": 8714.86055970192, "loss": 2.8149014711380005, "hidden": 0.1809549257159233, "layer": 0.08803625218570232, "mlm": 1.3803109228610992, "distill": 1.0286626368761063, "teacher_acc": 0.7506801635026932 }, { "step": 11741, "lr": 8.649245521700897e-06, "elapsed_s": 8722.239639043808, "loss": 2.9604023694992065, "hidden": 0.17346380650997162, "layer": 0.08687496185302734, "mlm": 1.574812412261963, "distill": 0.9952247738838196, "teacher_acc": 0.7058846205472946 }, { "step": 11751, "lr": 8.611193514942634e-06, "elapsed_s": 8729.628894329071, "loss": 2.7676438689231873, "hidden": 0.17304710671305656, "layer": 0.08634073659777641, "mlm": 1.4414955377578735, "distill": 0.936883807182312, "teacher_acc": 0.7326495349407196 }, { "step": 11761, "lr": 8.573207973906735e-06, "elapsed_s": 8737.024418592453, "loss": 2.859658181667328, "hidden": 0.17218875139951706, "layer": 0.08656189776957035, "mlm": 1.5494816601276398, "distill": 0.9225181192159653, "teacher_acc": 0.7119984179735184 }, { "step": 11771, "lr": 8.535289052645689e-06, "elapsed_s": 8744.437524080276, "loss": 2.8856375217437744, "hidden": 0.17475572228431702, "layer": 0.08731837943196297, "mlm": 1.5041763186454773, "distill": 0.988290548324585, "teacher_acc": 0.7194439768791199 }, { "step": 11781, "lr": 8.497436904941813e-06, "elapsed_s": 8751.860045194626, "loss": 2.8977131247520447, "hidden": 0.1758020892739296, "layer": 0.08620345592498779, "mlm": 1.5046611726284027, "distill": 0.9983460754156113, "teacher_acc": 0.729612410068512 }, { "step": 11791, "lr": 8.459651684306597e-06, "elapsed_s": 8759.314459085464, "loss": 2.850575864315033, "hidden": 0.17216972261667252, "layer": 0.0855779591947794, "mlm": 1.4903175830841064, "distill": 0.9731298983097076, "teacher_acc": 0.7278861254453659 }, { "step": 11801, "lr": 8.421933543980126e-06, "elapsed_s": 8766.745078086853, "loss": 3.096903443336487, "hidden": 0.19534436613321304, "layer": 0.0924385953694582, "mlm": 1.4864759743213654, "distill": 1.1735194325447083, "teacher_acc": 0.7453214079141617 }, { "step": 11811, "lr": 8.384282636930427e-06, "elapsed_s": 8774.165004253387, "loss": 2.933634400367737, "hidden": 0.1803545467555523, "layer": 0.08867593854665756, "mlm": 1.5361057817935944, "distill": 0.9924814701080322, "teacher_acc": 0.7087429314851761 }, { "step": 11821, "lr": 8.346699115852865e-06, "elapsed_s": 8781.567938804626, "loss": 3.028900682926178, "hidden": 0.184206061065197, "layer": 0.08979523368179798, "mlm": 1.5382551550865173, "distill": 1.0773358047008514, "teacher_acc": 0.7254036962985992 }, { "step": 11831, "lr": 8.309183133169524e-06, "elapsed_s": 8788.969747066498, "loss": 2.920081853866577, "hidden": 0.18216409161686897, "layer": 0.088149668648839, "mlm": 1.4883165657520294, "distill": 1.0233622789382935, "teacher_acc": 0.7370486557483673 }, { "step": 11841, "lr": 8.271734841028553e-06, "elapsed_s": 8796.383830308914, "loss": 2.9474685192108154, "hidden": 0.17692579701542854, "layer": 0.08774906024336815, "mlm": 1.5228377878665924, "distill": 1.026904582977295, "teacher_acc": 0.7267642915248871 }, { "step": 11851, "lr": 8.234354391303605e-06, "elapsed_s": 8803.8024725914, "loss": 2.88394296169281, "hidden": 0.17380856350064278, "layer": 0.08699492551386356, "mlm": 1.4950258135795593, "distill": 0.9978025406599045, "teacher_acc": 0.7335617244243622 }, { "step": 11861, "lr": 8.197041935593181e-06, "elapsed_s": 8811.217730045319, "loss": 2.957947313785553, "hidden": 0.17782976850867271, "layer": 0.08744676597416401, "mlm": 1.5441320836544037, "distill": 1.0144322961568832, "teacher_acc": 0.721091166138649 }, { "step": 11871, "lr": 8.159797625220058e-06, "elapsed_s": 8818.603947162628, "loss": 2.8275174498558044, "hidden": 0.17556288093328476, "layer": 0.08728029765188694, "mlm": 1.4604116678237915, "distill": 0.9723398983478546, "teacher_acc": 0.729839101433754 }, { "step": 11881, "lr": 8.1226216112306e-06, "elapsed_s": 8825.980924844742, "loss": 2.872560143470764, "hidden": 0.1737397015094757, "layer": 0.08614519238471985, "mlm": 1.5144849121570587, "distill": 0.9675232470035553, "teacher_acc": 0.7148987948894501 }, { "step": 11891, "lr": 8.085514044394216e-06, "elapsed_s": 8833.368203639984, "loss": 2.7765116691589355, "hidden": 0.172513660043478, "layer": 0.08582797460258007, "mlm": 1.4176904261112213, "distill": 0.9708799421787262, "teacher_acc": 0.7234673351049423 }, { "step": 11901, "lr": 8.048475075202727e-06, "elapsed_s": 8840.742236614227, "loss": 2.947446286678314, "hidden": 0.17943421751260757, "layer": 0.08848432637751102, "mlm": 1.5572600066661835, "distill": 0.987075611948967, "teacher_acc": 0.7124486416578293 }, { "step": 11911, "lr": 8.011504853869742e-06, "elapsed_s": 8848.141516923904, "loss": 2.838305115699768, "hidden": 0.17934516444802284, "layer": 0.08803470432758331, "mlm": 1.4406099915504456, "distill": 0.9949873834848404, "teacher_acc": 0.7388346493244171 }, { "step": 11921, "lr": 7.974603530330069e-06, "elapsed_s": 8855.52515912056, "loss": 2.8661672472953796, "hidden": 0.17183957621455193, "layer": 0.08613789640367031, "mlm": 1.4858387410640717, "distill": 0.9935803562402725, "teacher_acc": 0.7249466776847839 }, { "step": 11931, "lr": 7.937771254239093e-06, "elapsed_s": 8862.926328897476, "loss": 2.8321884870529175, "hidden": 0.17948558181524277, "layer": 0.08656339161098003, "mlm": 1.4419536292552948, "distill": 0.9879820197820663, "teacher_acc": 0.7307125777006149 }, { "step": 11941, "lr": 7.90100817497216e-06, "elapsed_s": 8870.328876972198, "loss": 2.878299295902252, "hidden": 0.17104396224021912, "layer": 0.0856066457927227, "mlm": 1.573552131652832, "distill": 0.9198558777570724, "teacher_acc": 0.703888401389122 }, { "step": 11951, "lr": 7.864314441624004e-06, "elapsed_s": 8877.737349033356, "loss": 2.9189100861549377, "hidden": 0.17678238078951836, "layer": 0.08745857700705528, "mlm": 1.5330724716186523, "distill": 0.9885434657335281, "teacher_acc": 0.7160025238990784 }, { "step": 11961, "lr": 7.827690203008118e-06, "elapsed_s": 8885.143232584, "loss": 2.75415700674057, "hidden": 0.1705382652580738, "layer": 0.08538345992565155, "mlm": 1.4551694989204407, "distill": 0.9152192771434784, "teacher_acc": 0.7301317602396011 }, { "step": 11971, "lr": 7.791135607656147e-06, "elapsed_s": 8892.542583703995, "loss": 2.7730290293693542, "hidden": 0.17468402534723282, "layer": 0.08606037497520447, "mlm": 1.4452482461929321, "distill": 0.9353825002908707, "teacher_acc": 0.7274285107851028 }, { "step": 11981, "lr": 7.75465080381731e-06, "elapsed_s": 8899.964803695679, "loss": 2.847308933734894, "hidden": 0.17436283081769943, "layer": 0.08659091964364052, "mlm": 1.4638864994049072, "distill": 0.991401344537735, "teacher_acc": 0.7308118939399719 }, { "step": 11991, "lr": 7.718235939457758e-06, "elapsed_s": 8907.36946773529, "loss": 2.8775338530540466, "hidden": 0.18212231621146202, "layer": 0.0885999258607626, "mlm": 1.4232809245586395, "distill": 1.04570834338665, "teacher_acc": 0.7512505948543549 }, { "step": 12001, "lr": 7.681891162260015e-06, "elapsed_s": 8916.832163095474, "loss": 2.9314300417900085, "hidden": 0.17291953787207603, "layer": 0.08634726144373417, "mlm": 1.6006021201610565, "distill": 0.9418151527643204, "teacher_acc": 0.7041100710630417 }, { "step": 12011, "lr": 7.645616619622364e-06, "elapsed_s": 8924.242282152176, "loss": 2.834304451942444, "hidden": 0.1728130467236042, "layer": 0.0858449824154377, "mlm": 1.5005516409873962, "distill": 0.9452042132616043, "teacher_acc": 0.7179669886827469 }, { "step": 12021, "lr": 7.609412458658244e-06, "elapsed_s": 8931.641526222229, "loss": 2.8811034560203552, "hidden": 0.17153335362672806, "layer": 0.0857680905610323, "mlm": 1.511580765247345, "distill": 0.9835719615221024, "teacher_acc": 0.7131068408489227 }, { "step": 12031, "lr": 7.573278826195665e-06, "elapsed_s": 8939.061381816864, "loss": 2.835046112537384, "hidden": 0.1780453883111477, "layer": 0.08725152164697647, "mlm": 1.4468506872653961, "distill": 0.9884789288043976, "teacher_acc": 0.7248119562864304 }, { "step": 12041, "lr": 7.5372158687765784e-06, "elapsed_s": 8946.45587682724, "loss": 2.9230287671089172, "hidden": 0.17428746446967125, "layer": 0.08651290461421013, "mlm": 1.5514414608478546, "distill": 0.9797559529542923, "teacher_acc": 0.7113645821809769 }, { "step": 12051, "lr": 7.5012237326563374e-06, "elapsed_s": 8953.857497215271, "loss": 2.862743377685547, "hidden": 0.176184494048357, "layer": 0.08719086274504662, "mlm": 1.4713284373283386, "distill": 0.9954505115747452, "teacher_acc": 0.7348389327526093 }, { "step": 12061, "lr": 7.465302563803061e-06, "elapsed_s": 8961.270748853683, "loss": 2.842897951602936, "hidden": 0.1768861785531044, "layer": 0.08717388659715652, "mlm": 1.4549515545368195, "distill": 0.990587055683136, "teacher_acc": 0.7331886440515518 }, { "step": 12071, "lr": 7.429452507897069e-06, "elapsed_s": 8968.68651175499, "loss": 2.9320555925369263, "hidden": 0.18492050096392632, "layer": 0.08943217433989048, "mlm": 1.4415404498577118, "distill": 1.0759581625461578, "teacher_acc": 0.7384877651929855 }, { "step": 12081, "lr": 7.393673710330271e-06, "elapsed_s": 8976.08201622963, "loss": 2.8461391925811768, "hidden": 0.1724015325307846, "layer": 0.08482075482606888, "mlm": 1.5250435173511505, "distill": 0.9338822662830353, "teacher_acc": 0.7225817292928696 }, { "step": 12091, "lr": 7.357966316205572e-06, "elapsed_s": 8983.494993448257, "loss": 2.982856333255768, "hidden": 0.17760394513607025, "layer": 0.08684525638818741, "mlm": 1.5729098618030548, "distill": 1.0113159865140915, "teacher_acc": 0.7036267518997192 }, { "step": 12101, "lr": 7.3223304703363135e-06, "elapsed_s": 8990.903176307678, "loss": 2.875020444393158, "hidden": 0.1775338537991047, "layer": 0.08723405562341213, "mlm": 1.4764533340930939, "distill": 0.9998824000358582, "teacher_acc": 0.7245829701423645 }, { "step": 12111, "lr": 7.286766317245667e-06, "elapsed_s": 8998.329807281494, "loss": 2.947964072227478, "hidden": 0.18002808839082718, "layer": 0.08798137679696083, "mlm": 1.5169947445392609, "distill": 1.02692249417305, "teacher_acc": 0.7321084439754486 }, { "step": 12121, "lr": 7.251274001166044e-06, "elapsed_s": 9005.743683099747, "loss": 2.938950836658478, "hidden": 0.17796747013926506, "layer": 0.0879037082195282, "mlm": 1.5837144255638123, "distill": 0.9553495645523071, "teacher_acc": 0.6981218308210373 }, { "step": 12131, "lr": 7.21585366603853e-06, "elapsed_s": 9013.143601417542, "loss": 2.9448598623275757, "hidden": 0.17359739914536476, "layer": 0.08700956404209137, "mlm": 1.5934978127479553, "distill": 0.9606625139713287, "teacher_acc": 0.7057676315307617 }, { "step": 12141, "lr": 7.180505455512257e-06, "elapsed_s": 9020.588706493378, "loss": 2.8078258633613586, "hidden": 0.1770188920199871, "layer": 0.08722705021500587, "mlm": 1.462302029132843, "distill": 0.9478724598884583, "teacher_acc": 0.7265336066484451 }, { "step": 12151, "lr": 7.145229512943885e-06, "elapsed_s": 9027.999309062958, "loss": 3.004558503627777, "hidden": 0.18746376410126686, "layer": 0.0897368025034666, "mlm": 1.5376700162887573, "distill": 1.0470924973487854, "teacher_acc": 0.7244391739368439 }, { "step": 12161, "lr": 7.110025981396975e-06, "elapsed_s": 9035.426665782928, "loss": 2.8593517541885376, "hidden": 0.1728067249059677, "layer": 0.08650297485291958, "mlm": 1.4706211388111115, "distill": 0.9998656660318375, "teacher_acc": 0.7279855757951736 }, { "step": 12171, "lr": 7.074895003641416e-06, "elapsed_s": 9042.856859922409, "loss": 2.83821439743042, "hidden": 0.17724983021616936, "layer": 0.08762476406991482, "mlm": 1.451403021812439, "distill": 0.9884994179010391, "teacher_acc": 0.7327395230531693 }, { "step": 12181, "lr": 7.039836722152865e-06, "elapsed_s": 9050.303092479706, "loss": 2.8467034101486206, "hidden": 0.1751006618142128, "layer": 0.08681318536400795, "mlm": 1.510590821504593, "distill": 0.9425046592950821, "teacher_acc": 0.718340739607811 }, { "step": 12191, "lr": 7.004851279112129e-06, "elapsed_s": 9057.720226049423, "loss": 2.742767333984375, "hidden": 0.17188889160752296, "layer": 0.0852587316185236, "mlm": 1.4319615066051483, "distill": 0.9243986904621124, "teacher_acc": 0.7241169810295105 }, { "step": 12201, "lr": 6.969938816404639e-06, "elapsed_s": 9065.113187789917, "loss": 2.8497883081436157, "hidden": 0.17528287321329117, "layer": 0.08592304028570652, "mlm": 1.4684549570083618, "distill": 0.9878060668706894, "teacher_acc": 0.7345440685749054 }, { "step": 12211, "lr": 6.935099475619847e-06, "elapsed_s": 9072.514890909195, "loss": 2.939872086048126, "hidden": 0.1748601570725441, "layer": 0.08751777373254299, "mlm": 1.5013472735881805, "distill": 1.0450455844402313, "teacher_acc": 0.7260120660066605 }, { "step": 12221, "lr": 6.900333398050646e-06, "elapsed_s": 9079.923726320267, "loss": 3.0436598658561707, "hidden": 0.18855173885822296, "layer": 0.09064742922782898, "mlm": 1.4749193489551544, "distill": 1.1463133841753006, "teacher_acc": 0.742340162396431 }, { "step": 12231, "lr": 6.865640724692815e-06, "elapsed_s": 9087.297847509384, "loss": 2.8712212443351746, "hidden": 0.17112068459391594, "layer": 0.085650984197855, "mlm": 1.5542872846126556, "distill": 0.9318671673536301, "teacher_acc": 0.7158327698707581 }, { "step": 12241, "lr": 6.831021596244424e-06, "elapsed_s": 9094.621049880981, "loss": 2.967933714389801, "hidden": 0.17635205388069153, "layer": 0.0875365175306797, "mlm": 1.5603772401809692, "distill": 1.0110841542482376, "teacher_acc": 0.7126067578792572 }, { "step": 12251, "lr": 6.796476153105294e-06, "elapsed_s": 9101.958236694336, "loss": 2.8774508237838745, "hidden": 0.176167793571949, "layer": 0.08700981736183167, "mlm": 1.5261945128440857, "distill": 0.9554157704114914, "teacher_acc": 0.7251121550798416 }, { "step": 12261, "lr": 6.762004535376401e-06, "elapsed_s": 9109.346936225891, "loss": 2.9645684957504272, "hidden": 0.1791466623544693, "layer": 0.08887865953147411, "mlm": 1.5504562854766846, "distill": 1.0113795101642609, "teacher_acc": 0.7152739763259888 }, { "step": 12271, "lr": 6.727606882859322e-06, "elapsed_s": 9116.738011360168, "loss": 2.7975228428840637, "hidden": 0.1711507961153984, "layer": 0.08498072065412998, "mlm": 1.4801384508609772, "distill": 0.9325924664735794, "teacher_acc": 0.7187763154506683 }, { "step": 12281, "lr": 6.69328333505567e-06, "elapsed_s": 9124.153195142746, "loss": 2.9614241123199463, "hidden": 0.17723563686013222, "layer": 0.08690509386360645, "mlm": 1.5811430215835571, "distill": 0.9823572337627411, "teacher_acc": 0.7007973194122314 }, { "step": 12291, "lr": 6.6590340311665e-06, "elapsed_s": 9131.575122594833, "loss": 3.0274060368537903, "hidden": 0.18156101554632187, "layer": 0.08857851661741734, "mlm": 1.5915491878986359, "distill": 1.0284454971551895, "teacher_acc": 0.711734876036644 }, { "step": 12301, "lr": 6.624859110091791e-06, "elapsed_s": 9138.995480775833, "loss": 2.8635968565940857, "hidden": 0.1792665384709835, "layer": 0.08671696297824383, "mlm": 1.468196302652359, "distill": 0.9935090243816376, "teacher_acc": 0.7233945578336716 }, { "step": 12311, "lr": 6.590758710429848e-06, "elapsed_s": 9146.3963804245, "loss": 2.995170831680298, "hidden": 0.17937440797686577, "layer": 0.08788389898836613, "mlm": 1.5653658211231232, "distill": 1.02711421251297, "teacher_acc": 0.7209800034761429 }, { "step": 12321, "lr": 6.556732970476748e-06, "elapsed_s": 9153.803459405899, "loss": 2.9733137488365173, "hidden": 0.18749452009797096, "layer": 0.09024551883339882, "mlm": 1.4758122563362122, "distill": 1.0773897469043732, "teacher_acc": 0.7330247759819031 }, { "step": 12331, "lr": 6.522782028225788e-06, "elapsed_s": 9161.204004764557, "loss": 3.018292248249054, "hidden": 0.18321746587753296, "layer": 0.08959094993770123, "mlm": 1.5303759574890137, "distill": 1.076685905456543, "teacher_acc": 0.7263926267623901 }, { "step": 12341, "lr": 6.488906021366925e-06, "elapsed_s": 9168.619151115417, "loss": 2.900115728378296, "hidden": 0.17203755304217339, "layer": 0.08626106381416321, "mlm": 1.5114847719669342, "distill": 1.0014252811670303, "teacher_acc": 0.7154399901628494 }, { "step": 12351, "lr": 6.455105087286173e-06, "elapsed_s": 9176.030782699585, "loss": 2.8845927119255066, "hidden": 0.176792673766613, "layer": 0.0880075041204691, "mlm": 1.5009724497795105, "distill": 0.9860312044620514, "teacher_acc": 0.7257981896400452 }, { "step": 12361, "lr": 6.421379363065142e-06, "elapsed_s": 9183.446513414383, "loss": 2.9109652638435364, "hidden": 0.18113511055707932, "layer": 0.08939162828028202, "mlm": 1.4997273981571198, "distill": 1.0042718648910522, "teacher_acc": 0.7226878702640533 }, { "step": 12371, "lr": 6.3877289854803815e-06, "elapsed_s": 9190.869278907776, "loss": 2.925171375274658, "hidden": 0.1764317937195301, "layer": 0.08810182847082615, "mlm": 1.5235716700553894, "distill": 1.0046852827072144, "teacher_acc": 0.7173303812742233 }, { "step": 12381, "lr": 6.354154091002892e-06, "elapsed_s": 9198.286696195602, "loss": 2.940699517726898, "hidden": 0.17727218195796013, "layer": 0.08717207238078117, "mlm": 1.540239155292511, "distill": 1.00232994556427, "teacher_acc": 0.7188484072685242 }, { "step": 12391, "lr": 6.320654815797525e-06, "elapsed_s": 9205.657669067383, "loss": 2.87903094291687, "hidden": 0.17641252279281616, "layer": 0.08733411878347397, "mlm": 1.4878909289836884, "distill": 0.9946479201316833, "teacher_acc": 0.725951075553894 }, { "step": 12401, "lr": 6.28723129572247e-06, "elapsed_s": 9213.067886590958, "loss": 2.8834495544433594, "hidden": 0.17526870965957642, "layer": 0.08773728460073471, "mlm": 1.5381772816181183, "distill": 0.9508662223815918, "teacher_acc": 0.7072023004293442 }, { "step": 12411, "lr": 6.253883666328689e-06, "elapsed_s": 9220.45101594925, "loss": 2.81054550409317, "hidden": 0.17354321852326393, "layer": 0.08565921895205975, "mlm": 1.4706654846668243, "distill": 0.9499640017747879, "teacher_acc": 0.7152236849069595 }, { "step": 12421, "lr": 6.220612062859357e-06, "elapsed_s": 9227.855909824371, "loss": 2.9474292397499084, "hidden": 0.18893872573971748, "layer": 0.09117171913385391, "mlm": 1.4707243144512177, "distill": 1.0532415956258774, "teacher_acc": 0.7262109816074371 }, { "step": 12431, "lr": 6.187416620249334e-06, "elapsed_s": 9235.299842357635, "loss": 2.8519203662872314, "hidden": 0.18094110488891602, "layer": 0.08845470659434795, "mlm": 1.4203514456748962, "distill": 1.025459423661232, "teacher_acc": 0.7377538979053497 }, { "step": 12441, "lr": 6.154297473124582e-06, "elapsed_s": 9242.705707550049, "loss": 2.919790804386139, "hidden": 0.18504753336310387, "layer": 0.0893565695732832, "mlm": 1.4471072554588318, "distill": 1.0579102635383606, "teacher_acc": 0.7390169054269791 }, { "step": 12451, "lr": 6.121254755801659e-06, "elapsed_s": 9250.111196994781, "loss": 2.970368981361389, "hidden": 0.18696963787078857, "layer": 0.08923973143100739, "mlm": 1.469307541847229, "distill": 1.0825023651123047, "teacher_acc": 0.7354277670383453 }, { "step": 12461, "lr": 6.088288602287159e-06, "elapsed_s": 9257.537653446198, "loss": 2.984572172164917, "hidden": 0.18187499046325684, "layer": 0.08817940019071102, "mlm": 1.5212276875972748, "distill": 1.055504858493805, "teacher_acc": 0.7203629910945892 }, { "step": 12471, "lr": 6.055399146277166e-06, "elapsed_s": 9264.983309984207, "loss": 2.7818097472190857, "hidden": 0.17320609465241432, "layer": 0.08638905361294746, "mlm": 1.4695047438144684, "distill": 0.9226982146501541, "teacher_acc": 0.7247221022844315 }, { "step": 12481, "lr": 6.022586521156715e-06, "elapsed_s": 9272.37607216835, "loss": 2.8497734665870667, "hidden": 0.17899274826049805, "layer": 0.08826789632439613, "mlm": 1.4984366595745087, "distill": 0.949217364192009, "teacher_acc": 0.7178781777620316 }, { "step": 12491, "lr": 5.989850859999227e-06, "elapsed_s": 9279.776977300644, "loss": 2.9110100269317627, "hidden": 0.17424943298101425, "layer": 0.08676040731370449, "mlm": 1.5412298440933228, "distill": 0.977901041507721, "teacher_acc": 0.7151438444852829 }, { "step": 12501, "lr": 5.957192295566022e-06, "elapsed_s": 9287.164252281189, "loss": 2.7939191460609436, "hidden": 0.1739400289952755, "layer": 0.08644329383969307, "mlm": 1.4476470947265625, "distill": 0.9551702588796616, "teacher_acc": 0.7361476868391037 }, { "step": 12511, "lr": 5.924610960305732e-06, "elapsed_s": 9294.519112586975, "loss": 2.84879332780838, "hidden": 0.1788582168519497, "layer": 0.08684664033353329, "mlm": 1.4495508074760437, "distill": 0.9981028139591217, "teacher_acc": 0.7454253882169724 }, { "step": 12521, "lr": 5.89210698635379e-06, "elapsed_s": 9301.901784658432, "loss": 2.8524584770202637, "hidden": 0.17203010246157646, "layer": 0.08625171519815922, "mlm": 1.52052640914917, "distill": 0.9447459876537323, "teacher_acc": 0.7128268927335739 }, { "step": 12531, "lr": 5.859680505531887e-06, "elapsed_s": 9309.305381059647, "loss": 2.9700721502304077, "hidden": 0.1778218299150467, "layer": 0.0875339675694704, "mlm": 1.560851514339447, "distill": 1.009809985756874, "teacher_acc": 0.7061426639556885 }, { "step": 12541, "lr": 5.827331649347417e-06, "elapsed_s": 9316.677250385284, "loss": 3.0179476141929626, "hidden": 0.1761799454689026, "layer": 0.08757508173584938, "mlm": 1.6000151932239532, "distill": 1.021785020828247, "teacher_acc": 0.7089514434337616 }, { "step": 12551, "lr": 5.79506054899299e-06, "elapsed_s": 9324.051854610443, "loss": 2.7452880144119263, "hidden": 0.17222030460834503, "layer": 0.0865737572312355, "mlm": 1.4091834127902985, "distill": 0.9483770430088043, "teacher_acc": 0.7394954413175583 }, { "step": 12561, "lr": 5.7628673353458504e-06, "elapsed_s": 9331.41999411583, "loss": 2.7567885518074036, "hidden": 0.17702651768922806, "layer": 0.08583145588636398, "mlm": 1.429551512002945, "distill": 0.9302682876586914, "teacher_acc": 0.740069791674614 }, { "step": 12571, "lr": 5.730752138967388e-06, "elapsed_s": 9338.82175397873, "loss": 2.7882784605026245, "hidden": 0.17645251750946045, "layer": 0.08597725071012974, "mlm": 1.4847504496574402, "distill": 0.9076343029737473, "teacher_acc": 0.7077653259038925 }, { "step": 12581, "lr": 5.6987150901025855e-06, "elapsed_s": 9346.205089092255, "loss": 3.0471176505088806, "hidden": 0.1886911503970623, "layer": 0.09075606428086758, "mlm": 1.498786747455597, "distill": 1.1255705803632736, "teacher_acc": 0.7388933300971985 }, { "step": 12591, "lr": 5.66675631867947e-06, "elapsed_s": 9353.59905052185, "loss": 2.8596156239509583, "hidden": 0.18239294737577438, "layer": 0.08967356942594051, "mlm": 1.3950499594211578, "distill": 1.0549429804086685, "teacher_acc": 0.7583006322383881 }, { "step": 12601, "lr": 5.634875954308638e-06, "elapsed_s": 9360.993413686752, "loss": 2.9558114409446716, "hidden": 0.17997289448976517, "layer": 0.08749737218022346, "mlm": 1.5507054924964905, "distill": 1.0014115124940872, "teacher_acc": 0.717472717165947 }, { "step": 12611, "lr": 5.603074126282692e-06, "elapsed_s": 9368.385633468628, "loss": 2.860435903072357, "hidden": 0.17809220403432846, "layer": 0.08761430904269218, "mlm": 1.492460459470749, "distill": 0.9679839015007019, "teacher_acc": 0.7297491878271103 }, { "step": 12621, "lr": 5.571350963575728e-06, "elapsed_s": 9375.78344154358, "loss": 2.753363311290741, "hidden": 0.17181523144245148, "layer": 0.08667032979428768, "mlm": 1.449986845254898, "distill": 0.9164108484983444, "teacher_acc": 0.7283483594655991 }, { "step": 12631, "lr": 5.539706594842814e-06, "elapsed_s": 9383.168736934662, "loss": 2.8144888877868652, "hidden": 0.1860583834350109, "layer": 0.08957562409341335, "mlm": 1.3462290167808533, "distill": 1.0513553470373154, "teacher_acc": 0.7634536772966385 }, { "step": 12641, "lr": 5.5081411484194435e-06, "elapsed_s": 9390.579170942307, "loss": 2.7688790559768677, "hidden": 0.1732962615787983, "layer": 0.08614427037537098, "mlm": 1.4611330032348633, "distill": 0.9180813580751419, "teacher_acc": 0.7259592115879059 }, { "step": 12651, "lr": 5.476654752321064e-06, "elapsed_s": 9397.98660326004, "loss": 2.8267762660980225, "hidden": 0.18169112130999565, "layer": 0.08811956644058228, "mlm": 1.4484617710113525, "distill": 0.9708724170923233, "teacher_acc": 0.7284526526927948 }, { "step": 12661, "lr": 5.445247534242512e-06, "elapsed_s": 9405.392384052277, "loss": 2.8898401856422424, "hidden": 0.17887293547391891, "layer": 0.08689091727137566, "mlm": 1.4635529816150665, "distill": 1.0250958502292633, "teacher_acc": 0.7397952824831009 }, { "step": 12671, "lr": 5.413919621557523e-06, "elapsed_s": 9412.784528255463, "loss": 2.918522357940674, "hidden": 0.17639200016856194, "layer": 0.08690697140991688, "mlm": 1.5518242418766022, "distill": 0.9704606533050537, "teacher_acc": 0.7114774733781815 }, { "step": 12681, "lr": 5.382671141318208e-06, "elapsed_s": 9420.215723276138, "loss": 2.8063570857048035, "hidden": 0.17836078628897667, "layer": 0.08761309273540974, "mlm": 1.4379312098026276, "distill": 0.9678977429866791, "teacher_acc": 0.7288535088300705 }, { "step": 12691, "lr": 5.351502220254512e-06, "elapsed_s": 9427.617034435272, "loss": 2.9242215752601624, "hidden": 0.1845530904829502, "layer": 0.08981956169009209, "mlm": 1.4409829676151276, "distill": 1.0692225992679596, "teacher_acc": 0.7366450428962708 }, { "step": 12701, "lr": 5.320412984773748e-06, "elapsed_s": 9435.031553268433, "loss": 2.9122524857521057, "hidden": 0.17955318465828896, "layer": 0.08945824019610882, "mlm": 1.4768843352794647, "distill": 1.0315327495336533, "teacher_acc": 0.7308914810419083 }, { "step": 12711, "lr": 5.289403560960052e-06, "elapsed_s": 9442.44949388504, "loss": 3.1997989416122437, "hidden": 0.18525556102395058, "layer": 0.0897974744439125, "mlm": 1.6119783222675323, "distill": 1.1724107265472412, "teacher_acc": 0.7179546654224396 }, { "step": 12721, "lr": 5.258474074573877e-06, "elapsed_s": 9449.87076997757, "loss": 2.887511909008026, "hidden": 0.17830026894807816, "layer": 0.08710087463259697, "mlm": 1.5254767835140228, "distill": 0.9618841111660004, "teacher_acc": 0.7233778536319733 }, { "step": 12731, "lr": 5.2276246510514965e-06, "elapsed_s": 9457.294798612595, "loss": 2.9076144099235535, "hidden": 0.17850354313850403, "layer": 0.0884072333574295, "mlm": 1.5025262534618378, "distill": 1.003877505660057, "teacher_acc": 0.7190152406692505 }, { "step": 12741, "lr": 5.196855415504456e-06, "elapsed_s": 9464.737800598145, "loss": 2.932520270347595, "hidden": 0.17750247940421104, "layer": 0.0877245832234621, "mlm": 1.5422592759132385, "distill": 0.9913936853408813, "teacher_acc": 0.7105195820331573 }, { "step": 12751, "lr": 5.166166492719124e-06, "elapsed_s": 9472.132479667664, "loss": 2.8253825306892395, "hidden": 0.1761576309800148, "layer": 0.08738777413964272, "mlm": 1.4342655539512634, "distill": 0.9951078146696091, "teacher_acc": 0.7354120910167694 }, { "step": 12761, "lr": 5.1355580071561465e-06, "elapsed_s": 9479.545963525772, "loss": 3.0643064975738525, "hidden": 0.19268574193120003, "layer": 0.09170088917016983, "mlm": 1.47756889462471, "distill": 1.1555155813694, "teacher_acc": 0.7403616458177567 }, { "step": 12771, "lr": 5.1050300829499465e-06, "elapsed_s": 9486.959055662155, "loss": 3.0280851125717163, "hidden": 0.1866171807050705, "layer": 0.09035687893629074, "mlm": 1.518099069595337, "distill": 1.0915732234716415, "teacher_acc": 0.7338429391384125 }, { "step": 12781, "lr": 5.074582843908241e-06, "elapsed_s": 9494.351012945175, "loss": 2.9281920790672302, "hidden": 0.18735918402671814, "layer": 0.09046633914113045, "mlm": 1.4711315035820007, "distill": 1.0371090769767761, "teacher_acc": 0.7321868538856506 }, { "step": 12791, "lr": 5.044216413511494e-06, "elapsed_s": 9501.750063419342, "loss": 2.867982804775238, "hidden": 0.18388090655207634, "layer": 0.0895646046847105, "mlm": 1.403470754623413, "distill": 1.0519679486751556, "teacher_acc": 0.7465981394052505 }, { "step": 12801, "lr": 5.013930914912476e-06, "elapsed_s": 9509.129306554794, "loss": 2.7903255820274353, "hidden": 0.1703214906156063, "layer": 0.08565936423838139, "mlm": 1.4558477699756622, "distill": 0.9510051310062408, "teacher_acc": 0.7316219806671143 }, { "step": 12811, "lr": 4.983726470935721e-06, "elapsed_s": 9516.527590990067, "loss": 2.82758891582489, "hidden": 0.17570395022630692, "layer": 0.08738142624497414, "mlm": 1.4487531185150146, "distill": 0.9837372153997421, "teacher_acc": 0.7278356999158859 }, { "step": 12821, "lr": 4.95360320407704e-06, "elapsed_s": 9523.954644918442, "loss": 2.897589325904846, "hidden": 0.17975018918514252, "layer": 0.08901461400091648, "mlm": 1.4897750914096832, "distill": 1.0038065761327744, "teacher_acc": 0.7333808839321136 }, { "step": 12831, "lr": 4.923561236503033e-06, "elapsed_s": 9531.344733715057, "loss": 2.992402195930481, "hidden": 0.18500671163201332, "layer": 0.08914694748818874, "mlm": 1.474857211112976, "distill": 1.1029581427574158, "teacher_acc": 0.7388559579849243 }, { "step": 12841, "lr": 4.893600690050579e-06, "elapsed_s": 9538.727134227753, "loss": 2.890056610107422, "hidden": 0.17591312155127525, "layer": 0.08798208460211754, "mlm": 1.4926875531673431, "distill": 1.001551792025566, "teacher_acc": 0.7278572171926498 }, { "step": 12851, "lr": 4.86372168622635e-06, "elapsed_s": 9546.096660852432, "loss": 2.887464702129364, "hidden": 0.17923159524798393, "layer": 0.0877752099186182, "mlm": 1.4746856093406677, "distill": 1.0104282796382904, "teacher_acc": 0.7294062972068787 }, { "step": 12861, "lr": 4.833924346206322e-06, "elapsed_s": 9553.47875213623, "loss": 2.976298153400421, "hidden": 0.1795457825064659, "layer": 0.08712825924158096, "mlm": 1.5287494361400604, "distill": 1.0448929965496063, "teacher_acc": 0.7243291139602661 }, { "step": 12871, "lr": 4.8042087908352766e-06, "elapsed_s": 9560.872932434082, "loss": 2.7780619263648987, "hidden": 0.17690759524703026, "layer": 0.08809008821845055, "mlm": 1.4777454733848572, "distill": 0.902456134557724, "teacher_acc": 0.7153702229261398 }, { "step": 12881, "lr": 4.7745751406263165e-06, "elapsed_s": 9568.296875, "loss": 2.8947187066078186, "hidden": 0.17641475051641464, "layer": 0.08663193508982658, "mlm": 1.5103759467601776, "distill": 0.9881973415613174, "teacher_acc": 0.722339317202568 }, { "step": 12891, "lr": 4.745023515760358e-06, "elapsed_s": 9575.687087535858, "loss": 2.84686017036438, "hidden": 0.1764562986791134, "layer": 0.08673552051186562, "mlm": 1.4734503328800201, "distill": 0.9771295487880707, "teacher_acc": 0.7256836891174316 }, { "step": 12901, "lr": 4.715554036085673e-06, "elapsed_s": 9583.101128578186, "loss": 2.9557703733444214, "hidden": 0.18196866288781166, "layer": 0.08980824425816536, "mlm": 1.5450664460659027, "distill": 1.0018624812364578, "teacher_acc": 0.7099316865205765 }, { "step": 12911, "lr": 4.686166821117394e-06, "elapsed_s": 9590.482494354248, "loss": 3.006062626838684, "hidden": 0.17656185105443, "layer": 0.08685310557484627, "mlm": 1.622754991054535, "distill": 0.98675736784935, "teacher_acc": 0.7029636651277542 }, { "step": 12921, "lr": 4.656861990037009e-06, "elapsed_s": 9597.917001962662, "loss": 2.894753336906433, "hidden": 0.17806433141231537, "layer": 0.08680600300431252, "mlm": 1.5117867290973663, "distill": 0.9834349602460861, "teacher_acc": 0.7155244201421738 }, { "step": 12931, "lr": 4.6276396616919126e-06, "elapsed_s": 9605.31804561615, "loss": 2.960543155670166, "hidden": 0.17846061289310455, "layer": 0.08825407549738884, "mlm": 1.5462091565132141, "distill": 1.0132857710123062, "teacher_acc": 0.7113262414932251 }, { "step": 12941, "lr": 4.598499954594881e-06, "elapsed_s": 9612.73967218399, "loss": 2.956188440322876, "hidden": 0.1883348636329174, "layer": 0.09045879356563091, "mlm": 1.4664727449417114, "distill": 1.0678165704011917, "teacher_acc": 0.7251737415790558 }, { "step": 12951, "lr": 4.569442986923631e-06, "elapsed_s": 9620.14065527916, "loss": 3.0433897972106934, "hidden": 0.18353575468063354, "layer": 0.08933710679411888, "mlm": 1.5309925973415375, "distill": 1.1006570756435394, "teacher_acc": 0.7181217819452286 }, { "step": 12961, "lr": 4.540468876520323e-06, "elapsed_s": 9627.579767942429, "loss": 2.845133602619171, "hidden": 0.18036900833249092, "layer": 0.08745582588016987, "mlm": 1.4484224915504456, "distill": 0.992245152592659, "teacher_acc": 0.7332130074501038 }, { "step": 12971, "lr": 4.511577740891087e-06, "elapsed_s": 9635.008594751358, "loss": 2.917749583721161, "hidden": 0.17559747025370598, "layer": 0.08771784789860249, "mlm": 1.5513452589511871, "distill": 0.9713504463434219, "teacher_acc": 0.7102102935314178 }, { "step": 12981, "lr": 4.482769697205544e-06, "elapsed_s": 9642.426382780075, "loss": 2.878574550151825, "hidden": 0.17659876868128777, "layer": 0.08731736429035664, "mlm": 1.5271839201450348, "distill": 0.9545344263315201, "teacher_acc": 0.7203634530305862 }, { "step": 12991, "lr": 4.45404486229632e-06, "elapsed_s": 9649.839520215988, "loss": 3.045623540878296, "hidden": 0.18662891164422035, "layer": 0.08938478492200375, "mlm": 1.5411394536495209, "distill": 1.0865338742733002, "teacher_acc": 0.7275781482458115 }, { "step": 13001, "lr": 4.425403352658591e-06, "elapsed_s": 9659.282498598099, "loss": 2.9143919348716736, "hidden": 0.17616290971636772, "layer": 0.08753799460828304, "mlm": 1.531820297241211, "distill": 0.9864768981933594, "teacher_acc": 0.7170365452766418 }, { "step": 13011, "lr": 4.396845284449608e-06, "elapsed_s": 9666.668555498123, "loss": 2.8680944442749023, "hidden": 0.17702513933181763, "layer": 0.08729600347578526, "mlm": 1.5223488807678223, "distill": 0.9480472356081009, "teacher_acc": 0.717745378613472 }, { "step": 13021, "lr": 4.368370773488215e-06, "elapsed_s": 9674.033586740494, "loss": 3.015802502632141, "hidden": 0.18039514124393463, "layer": 0.08782284148037434, "mlm": 1.5655745267868042, "distill": 1.0455263257026672, "teacher_acc": 0.7257400006055832 }, { "step": 13031, "lr": 4.33997993525439e-06, "elapsed_s": 9681.417303085327, "loss": 2.931185007095337, "hidden": 0.1752033531665802, "layer": 0.08625833876430988, "mlm": 1.5731877386569977, "distill": 0.9644613862037659, "teacher_acc": 0.7013953626155853 }, { "step": 13041, "lr": 4.311672884888757e-06, "elapsed_s": 9688.817976474762, "loss": 2.870202124118805, "hidden": 0.17414305731654167, "layer": 0.08606310002505779, "mlm": 1.5003638863563538, "distill": 0.9785206615924835, "teacher_acc": 0.7138620018959045 }, { "step": 13051, "lr": 4.283449737192149e-06, "elapsed_s": 9696.208606004715, "loss": 2.9122373461723328, "hidden": 0.17695403844118118, "layer": 0.08789647929370403, "mlm": 1.5349477529525757, "distill": 0.9794332981109619, "teacher_acc": 0.7109359204769135 }, { "step": 13061, "lr": 4.255310606625123e-06, "elapsed_s": 9703.587857961655, "loss": 2.789665102958679, "hidden": 0.17151342704892159, "layer": 0.08601438626646996, "mlm": 1.4816088378429413, "distill": 0.9220222234725952, "teacher_acc": 0.7161831557750702 }, { "step": 13071, "lr": 4.227255607307496e-06, "elapsed_s": 9710.950668096542, "loss": 3.0212015509605408, "hidden": 0.17730635032057762, "layer": 0.08799059130251408, "mlm": 1.6220548748970032, "distill": 1.000538632273674, "teacher_acc": 0.6978080868721008 }, { "step": 13081, "lr": 4.199284853017896e-06, "elapsed_s": 9718.335723638535, "loss": 2.940508723258972, "hidden": 0.17891962081193924, "layer": 0.0870448611676693, "mlm": 1.5334879457950592, "distill": 1.0056591629981995, "teacher_acc": 0.7115296721458435 }, { "step": 13091, "lr": 4.171398457193274e-06, "elapsed_s": 9725.733839035034, "loss": 2.8743136525154114, "hidden": 0.176511000841856, "layer": 0.08644475601613522, "mlm": 1.5035784542560577, "distill": 0.9744907915592194, "teacher_acc": 0.7271473705768585 }, { "step": 13101, "lr": 4.143596532928468e-06, "elapsed_s": 9733.140990018845, "loss": 2.775389313697815, "hidden": 0.17423643171787262, "layer": 0.08601083233952522, "mlm": 1.4004228711128235, "distill": 0.9834882020950317, "teacher_acc": 0.7396484166383743 }, { "step": 13111, "lr": 4.115879192975747e-06, "elapsed_s": 9740.561436653137, "loss": 2.942090630531311, "hidden": 0.17801467329263687, "layer": 0.08715808764100075, "mlm": 1.5175164937973022, "distill": 1.0249657779932022, "teacher_acc": 0.7206477373838425 }, { "step": 13121, "lr": 4.088246549744331e-06, "elapsed_s": 9747.975591182709, "loss": 2.866785228252411, "hidden": 0.1745559647679329, "layer": 0.08631335012614727, "mlm": 1.498161256313324, "distill": 0.9763553291559219, "teacher_acc": 0.7243615686893463 }, { "step": 13131, "lr": 4.06069871529996e-06, "elapsed_s": 9755.345501422882, "loss": 2.925742983818054, "hidden": 0.1795111522078514, "layer": 0.08888725563883781, "mlm": 1.5192387402057648, "distill": 1.0030383616685867, "teacher_acc": 0.7144933193922043 }, { "step": 13141, "lr": 4.0332358013644016e-06, "elapsed_s": 9762.751586675644, "loss": 3.1206456422805786, "hidden": 0.17992790788412094, "layer": 0.08864620141685009, "mlm": 1.6399891674518585, "distill": 1.0764775723218918, "teacher_acc": 0.7002445757389069 }, { "step": 13151, "lr": 4.0058579193150535e-06, "elapsed_s": 9770.171698331833, "loss": 2.919557273387909, "hidden": 0.1816549077630043, "layer": 0.08843573741614819, "mlm": 1.4833087027072906, "distill": 1.0287209153175354, "teacher_acc": 0.7371143698692322 }, { "step": 13161, "lr": 3.978565180184449e-06, "elapsed_s": 9777.585371732712, "loss": 2.9087109565734863, "hidden": 0.18073051050305367, "layer": 0.08879253268241882, "mlm": 1.4650443196296692, "distill": 1.0378094017505646, "teacher_acc": 0.7353436499834061 }, { "step": 13171, "lr": 3.951357694659816e-06, "elapsed_s": 9784.985332489014, "loss": 2.9291704297065735, "hidden": 0.178382508456707, "layer": 0.08855052851140499, "mlm": 1.5377902686595917, "distill": 0.99033984541893, "teacher_acc": 0.7157203108072281 }, { "step": 13181, "lr": 3.924235573082644e-06, "elapsed_s": 9792.393367052078, "loss": 2.8498963713645935, "hidden": 0.17427730560302734, "layer": 0.08572972193360329, "mlm": 1.499645859003067, "distill": 0.9588310420513153, "teacher_acc": 0.7292221039533615 }, { "step": 13191, "lr": 3.897198925448201e-06, "elapsed_s": 9799.778712272644, "loss": 2.946622371673584, "hidden": 0.17694006115198135, "layer": 0.08735962398350239, "mlm": 1.5220724046230316, "distill": 1.0269900113344193, "teacher_acc": 0.7237818539142609 }, { "step": 13201, "lr": 3.8702478614051355e-06, "elapsed_s": 9807.189387321472, "loss": 2.7607191801071167, "hidden": 0.16602330654859543, "layer": 0.08407696336507797, "mlm": 1.5061639547348022, "distill": 0.8804701119661331, "teacher_acc": 0.714382603764534 }, { "step": 13211, "lr": 3.8433824902549935e-06, "elapsed_s": 9814.612425088882, "loss": 2.7988585829734802, "hidden": 0.17149867117404938, "layer": 0.08663110621273518, "mlm": 1.475572019815445, "distill": 0.9369736164808273, "teacher_acc": 0.7234218716621399 }, { "step": 13221, "lr": 3.816602920951792e-06, "elapsed_s": 9822.024948120117, "loss": 2.888017237186432, "hidden": 0.17855221033096313, "layer": 0.08737533539533615, "mlm": 1.4902073740959167, "distill": 0.9970177859067917, "teacher_acc": 0.7223703563213348 }, { "step": 13231, "lr": 3.789909262101582e-06, "elapsed_s": 9829.445343494415, "loss": 2.850633919239044, "hidden": 0.17753764614462852, "layer": 0.08807964622974396, "mlm": 1.4667156636714935, "distill": 0.9848031401634216, "teacher_acc": 0.737755075097084 }, { "step": 13241, "lr": 3.7633016219619786e-06, "elapsed_s": 9836.847332715988, "loss": 2.8578527569770813, "hidden": 0.17737197503447533, "layer": 0.08721950091421604, "mlm": 1.4773236215114594, "distill": 0.9821754395961761, "teacher_acc": 0.7243688851594925 }, { "step": 13251, "lr": 3.7367801084417618e-06, "elapsed_s": 9844.261668205261, "loss": 2.949710726737976, "hidden": 0.17219267785549164, "layer": 0.08628544770181179, "mlm": 1.6224125921726227, "distill": 0.9397700130939484, "teacher_acc": 0.691694587469101 }, { "step": 13261, "lr": 3.7103448291004176e-06, "elapsed_s": 9851.656147003174, "loss": 2.8338574171066284, "hidden": 0.17426765337586403, "layer": 0.08557852730154991, "mlm": 1.4594774842262268, "distill": 0.9830553233623505, "teacher_acc": 0.7253110706806183 }, { "step": 13271, "lr": 3.6839958911476957e-06, "elapsed_s": 9859.016288280487, "loss": 2.920965552330017, "hidden": 0.17562898248434067, "layer": 0.08750224113464355, "mlm": 1.493486374616623, "distill": 1.032470017671585, "teacher_acc": 0.7272103875875473 }, { "step": 13281, "lr": 3.6577334014432003e-06, "elapsed_s": 9866.402028083801, "loss": 3.1315943002700806, "hidden": 0.18815917521715164, "layer": 0.09127160534262657, "mlm": 1.603565126657486, "distill": 1.1060749888420105, "teacher_acc": 0.7184097319841385 }, { "step": 13291, "lr": 3.6315574664959164e-06, "elapsed_s": 9873.783749580383, "loss": 2.9850247502326965, "hidden": 0.17591681703925133, "layer": 0.0877597127109766, "mlm": 1.5690572559833527, "distill": 1.0202539265155792, "teacher_acc": 0.7122976183891296 }, { "step": 13301, "lr": 3.605468192463815e-06, "elapsed_s": 9881.175666809082, "loss": 2.965963840484619, "hidden": 0.17215122655034065, "layer": 0.08681348152458668, "mlm": 1.604857325553894, "distill": 0.9733972698450089, "teacher_acc": 0.6984842717647552 }, { "step": 13311, "lr": 3.579465685153416e-06, "elapsed_s": 9888.578418254852, "loss": 2.772668719291687, "hidden": 0.17213476449251175, "layer": 0.08514178358018398, "mlm": 1.4024863839149475, "distill": 0.9833419173955917, "teacher_acc": 0.7443005293607712 }, { "step": 13321, "lr": 3.5535500500193357e-06, "elapsed_s": 9895.972501516342, "loss": 2.8314099311828613, "hidden": 0.17797372862696648, "layer": 0.0872762780636549, "mlm": 1.438452959060669, "distill": 0.9933713376522064, "teacher_acc": 0.7434177845716476 }, { "step": 13331, "lr": 3.527721392163891e-06, "elapsed_s": 9903.37880063057, "loss": 2.8499123454093933, "hidden": 0.1729104109108448, "layer": 0.0865900106728077, "mlm": 1.5001056790351868, "distill": 0.9606907963752747, "teacher_acc": 0.714264452457428 }, { "step": 13341, "lr": 3.5019798163366424e-06, "elapsed_s": 9910.788428068161, "loss": 2.8279574513435364, "hidden": 0.18093464523553848, "layer": 0.0887424685060978, "mlm": 1.4483312666416168, "distill": 0.9733856469392776, "teacher_acc": 0.7274457663297653 }, { "step": 13351, "lr": 3.4763254269339963e-06, "elapsed_s": 9918.218132019043, "loss": 2.9681381583213806, "hidden": 0.18314063549041748, "layer": 0.08974025771021843, "mlm": 1.5136862993240356, "distill": 1.043300375342369, "teacher_acc": 0.7237362116575241 }, { "step": 13361, "lr": 3.450758327998768e-06, "elapsed_s": 9925.625757932663, "loss": 2.938211977481842, "hidden": 0.17523200437426567, "layer": 0.0886930376291275, "mlm": 1.4801146984100342, "distill": 1.063286766409874, "teacher_acc": 0.7262709587812424 }, { "step": 13371, "lr": 3.425278623219752e-06, "elapsed_s": 9933.037760972977, "loss": 2.9477908611297607, "hidden": 0.18083260208368301, "layer": 0.08948999457061291, "mlm": 1.5002566576004028, "distill": 1.0411240607500076, "teacher_acc": 0.7286197543144226 }, { "step": 13381, "lr": 3.3998864159313303e-06, "elapsed_s": 9940.452121019363, "loss": 2.8202080130577087, "hidden": 0.1717272363603115, "layer": 0.08626286685466766, "mlm": 1.5061494708061218, "distill": 0.9274726510047913, "teacher_acc": 0.7199335843324661 }, { "step": 13391, "lr": 3.3745818091130033e-06, "elapsed_s": 9947.876585245132, "loss": 2.9197599291801453, "hidden": 0.17536289989948273, "layer": 0.0863843560218811, "mlm": 1.553793340921402, "distill": 0.9720486104488373, "teacher_acc": 0.7109072804450989 }, { "step": 13401, "lr": 3.3493649053890326e-06, "elapsed_s": 9955.239881515503, "loss": 2.9269282817840576, "hidden": 0.17357299104332924, "layer": 0.08617493696510792, "mlm": 1.589437484741211, "distill": 0.947257325053215, "teacher_acc": 0.6985394358634949 }, { "step": 13411, "lr": 3.324235807027981e-06, "elapsed_s": 9962.644291639328, "loss": 2.8427634835243225, "hidden": 0.17464591562747955, "layer": 0.08647837489843369, "mlm": 1.4998052418231964, "distill": 0.950427234172821, "teacher_acc": 0.70854452252388 }, { "step": 13421, "lr": 3.2991946159423137e-06, "elapsed_s": 9970.025236606598, "loss": 2.842606246471405, "hidden": 0.173444963991642, "layer": 0.08649384044110775, "mlm": 1.5227293372154236, "distill": 0.9297401309013367, "teacher_acc": 0.7136987000703812 }, { "step": 13431, "lr": 3.2742414336879858e-06, "elapsed_s": 9977.41947054863, "loss": 2.6814911365509033, "hidden": 0.17017915472388268, "layer": 0.08438727632164955, "mlm": 1.3863603472709656, "distill": 0.912578895688057, "teacher_acc": 0.746785506606102 }, { "step": 13441, "lr": 3.249376361464021e-06, "elapsed_s": 9984.788188457489, "loss": 2.9087327122688293, "hidden": 0.17752645909786224, "layer": 0.08745256811380386, "mlm": 1.5356897413730621, "distill": 0.9742637425661087, "teacher_acc": 0.7085938304662704 }, { "step": 13451, "lr": 3.2245995001121106e-06, "elapsed_s": 9992.184267282486, "loss": 2.827235460281372, "hidden": 0.17676269263029099, "layer": 0.08634806796908379, "mlm": 1.4623760282993317, "distill": 0.968160018324852, "teacher_acc": 0.7254102379083633 }, { "step": 13461, "lr": 3.1999109501162084e-06, "elapsed_s": 9999.588663816452, "loss": 2.85288405418396, "hidden": 0.17578741908073425, "layer": 0.08693391643464565, "mlm": 1.4931911826133728, "distill": 0.9646510034799576, "teacher_acc": 0.7216839343309402 }, { "step": 13471, "lr": 3.1753108116021056e-06, "elapsed_s": 10007.00560426712, "loss": 3.0027015805244446, "hidden": 0.1762189380824566, "layer": 0.08733008429408073, "mlm": 1.5448495745658875, "distill": 1.0617490857839584, "teacher_acc": 0.722916767001152 }, { "step": 13481, "lr": 3.1507991843370526e-06, "elapsed_s": 10014.383801221848, "loss": 2.82051944732666, "hidden": 0.17620981857180595, "layer": 0.08739597909152508, "mlm": 1.4551913142204285, "distill": 0.9692105352878571, "teacher_acc": 0.7299276292324066 }, { "step": 13491, "lr": 3.126376167729314e-06, "elapsed_s": 10021.780824899673, "loss": 2.9078973531723022, "hidden": 0.17320147156715393, "layer": 0.08524545840919018, "mlm": 1.547870010137558, "distill": 0.9710016995668411, "teacher_acc": 0.7098441869020462 }, { "step": 13501, "lr": 3.1020418608278035e-06, "elapsed_s": 10029.217134714127, "loss": 2.7302801609039307, "hidden": 0.17064569145441055, "layer": 0.08427605405449867, "mlm": 1.4497428834438324, "distill": 0.8971079140901566, "teacher_acc": 0.7218370586633682 }, { "step": 13511, "lr": 3.0777963623216694e-06, "elapsed_s": 10036.617987394333, "loss": 2.8990476727485657, "hidden": 0.17579039558768272, "layer": 0.08751954883337021, "mlm": 1.506092131137848, "distill": 0.9976149499416351, "teacher_acc": 0.7273407280445099 }, { "step": 13521, "lr": 3.0536397705398843e-06, "elapsed_s": 10044.013816833496, "loss": 2.8781688809394836, "hidden": 0.1711338460445404, "layer": 0.08606979809701443, "mlm": 1.5276587009429932, "distill": 0.9652075469493866, "teacher_acc": 0.708276703953743 }, { "step": 13531, "lr": 3.029572183450868e-06, "elapsed_s": 10051.43296790123, "loss": 2.857636868953705, "hidden": 0.17460649833083153, "layer": 0.08687365986406803, "mlm": 1.5067120790481567, "distill": 0.9582749605178833, "teacher_acc": 0.711731493473053 }, { "step": 13541, "lr": 3.005593698662057e-06, "elapsed_s": 10058.829039812088, "loss": 2.8990264534950256, "hidden": 0.17268938571214676, "layer": 0.08606573939323425, "mlm": 1.5367178916931152, "distill": 0.9738968908786774, "teacher_acc": 0.7133716195821762 }, { "step": 13551, "lr": 2.9817044134195392e-06, "elapsed_s": 10066.232584953308, "loss": 2.840327560901642, "hidden": 0.170196533203125, "layer": 0.08610442839562893, "mlm": 1.5407018065452576, "distill": 0.9161804616451263, "teacher_acc": 0.7018955200910568 }, { "step": 13561, "lr": 2.957904424607652e-06, "elapsed_s": 10073.630909919739, "loss": 2.946484625339508, "hidden": 0.17957350984215736, "layer": 0.08602401986718178, "mlm": 1.5581636130809784, "distill": 0.986161932349205, "teacher_acc": 0.7082791328430176 }, { "step": 13571, "lr": 2.9341938287485855e-06, "elapsed_s": 10081.006314754486, "loss": 2.7946261763572693, "hidden": 0.17502402141690254, "layer": 0.08597644232213497, "mlm": 1.4548249542713165, "distill": 0.9467648863792419, "teacher_acc": 0.7259810417890549 }, { "step": 13581, "lr": 2.910572722001989e-06, "elapsed_s": 10088.381644487381, "loss": 2.718013107776642, "hidden": 0.17166883498430252, "layer": 0.08550783060491085, "mlm": 1.4195754826068878, "distill": 0.9123460799455643, "teacher_acc": 0.7344458103179932 }, { "step": 13591, "lr": 2.887041200164575e-06, "elapsed_s": 10095.75076842308, "loss": 2.830930471420288, "hidden": 0.17759772017598152, "layer": 0.08759403228759766, "mlm": 1.4853352010250092, "distill": 0.9466028809547424, "teacher_acc": 0.7255779206752777 }, { "step": 13601, "lr": 2.8635993586697553e-06, "elapsed_s": 10103.100806713104, "loss": 2.896745979785919, "hidden": 0.17577078938484192, "layer": 0.08677500858902931, "mlm": 1.486181527376175, "distill": 1.015635371208191, "teacher_acc": 0.7232370525598526 }, { "step": 13611, "lr": 2.8402472925872255e-06, "elapsed_s": 10110.491586208344, "loss": 2.8552364110946655, "hidden": 0.18045958876609802, "layer": 0.08799123950302601, "mlm": 1.4385304152965546, "distill": 1.011791169643402, "teacher_acc": 0.7440200001001358 }, { "step": 13621, "lr": 2.816985096622604e-06, "elapsed_s": 10117.87307214737, "loss": 2.953605592250824, "hidden": 0.1766708865761757, "layer": 0.08778412640094757, "mlm": 1.5450712442398071, "distill": 1.011300504207611, "teacher_acc": 0.7151249796152115 }, { "step": 13631, "lr": 2.7938128651170293e-06, "elapsed_s": 10125.293509244919, "loss": 2.8452564477920532, "hidden": 0.17177104577422142, "layer": 0.08644742332398891, "mlm": 1.5120657682418823, "distill": 0.9464248716831207, "teacher_acc": 0.7121517807245255 }, { "step": 13641, "lr": 2.770730692046775e-06, "elapsed_s": 10132.711966276169, "loss": 2.82638281583786, "hidden": 0.17850084602832794, "layer": 0.087546830996871, "mlm": 1.4528644979000092, "distill": 0.9727432876825333, "teacher_acc": 0.7360454350709915 }, { "step": 13651, "lr": 2.7477386710228895e-06, "elapsed_s": 10140.146907806396, "loss": 2.9267768263816833, "hidden": 0.18046989664435387, "layer": 0.08674029633402824, "mlm": 1.5328928530216217, "distill": 0.9895740002393723, "teacher_acc": 0.7141415476799011 }, { "step": 13661, "lr": 2.7248368952908053e-06, "elapsed_s": 10147.58401632309, "loss": 2.8222281336784363, "hidden": 0.1781761348247528, "layer": 0.08690999075770378, "mlm": 1.429492861032486, "distill": 0.9929278790950775, "teacher_acc": 0.7379884570837021 }, { "step": 13671, "lr": 2.7020254577299536e-06, "elapsed_s": 10154.977522850037, "loss": 2.8902623057365417, "hidden": 0.171976737678051, "layer": 0.08555602468550205, "mlm": 1.5623492002487183, "distill": 0.9411815851926804, "teacher_acc": 0.7009619623422623 }, { "step": 13681, "lr": 2.679304450853401e-06, "elapsed_s": 10162.384892463684, "loss": 2.808736562728882, "hidden": 0.1753615327179432, "layer": 0.08599212765693665, "mlm": 1.4499826431274414, "distill": 0.9650347828865051, "teacher_acc": 0.7319043576717377 }, { "step": 13691, "lr": 2.6566739668074576e-06, "elapsed_s": 10169.793513774872, "loss": 2.7754350900650024, "hidden": 0.1723586656153202, "layer": 0.08558506332337856, "mlm": 1.483440101146698, "distill": 0.9044850617647171, "teacher_acc": 0.7183823883533478 }, { "step": 13701, "lr": 2.6341340973713187e-06, "elapsed_s": 10177.182252883911, "loss": 2.778847575187683, "hidden": 0.17173828184604645, "layer": 0.08610547333955765, "mlm": 1.4377617239952087, "distill": 0.9545565545558929, "teacher_acc": 0.7317746132612228 }, { "step": 13711, "lr": 2.6116849339566875e-06, "elapsed_s": 10184.57947063446, "loss": 2.8364253640174866, "hidden": 0.1725776456296444, "layer": 0.08634312450885773, "mlm": 1.4619020521640778, "distill": 0.9861964881420135, "teacher_acc": 0.7254862040281296 }, { "step": 13721, "lr": 2.589326567607406e-06, "elapsed_s": 10191.950474262238, "loss": 2.7718119025230408, "hidden": 0.17714256793260574, "layer": 0.0865456685423851, "mlm": 1.4099999368190765, "distill": 0.9642539918422699, "teacher_acc": 0.7420271337032318 }, { "step": 13731, "lr": 2.5670590889990853e-06, "elapsed_s": 10199.346661806107, "loss": 2.8479841351509094, "hidden": 0.17484470829367638, "layer": 0.08732474967837334, "mlm": 1.4903290569782257, "distill": 0.9643032252788544, "teacher_acc": 0.722683846950531 }, { "step": 13741, "lr": 2.5448825884387185e-06, "elapsed_s": 10206.77306675911, "loss": 2.7772529125213623, "hidden": 0.17240336909890175, "layer": 0.08511606231331825, "mlm": 1.480447143316269, "distill": 0.9094410240650177, "teacher_acc": 0.706803634762764 }, { "step": 13751, "lr": 2.5227971558643537e-06, "elapsed_s": 10214.18965291977, "loss": 2.805159270763397, "hidden": 0.17355717718601227, "layer": 0.08706989884376526, "mlm": 1.46714249253273, "distill": 0.94736747443676, "teacher_acc": 0.729495644569397 }, { "step": 13761, "lr": 2.500802880844699e-06, "elapsed_s": 10221.603974342346, "loss": 2.8740991353988647, "hidden": 0.1765865683555603, "layer": 0.08629830181598663, "mlm": 1.4889123737812042, "distill": 0.9888645112514496, "teacher_acc": 0.7216536700725555 }, { "step": 13771, "lr": 2.478899852578767e-06, "elapsed_s": 10229.00546503067, "loss": 2.688551962375641, "hidden": 0.169419065117836, "layer": 0.08447246998548508, "mlm": 1.430046170949936, "distill": 0.8774314373731613, "teacher_acc": 0.7370067834854126 }, { "step": 13781, "lr": 2.457088159895518e-06, "elapsed_s": 10236.423662900925, "loss": 2.9424074292182922, "hidden": 0.17341970652341843, "layer": 0.08687831647694111, "mlm": 1.5430165231227875, "distill": 1.0091122835874557, "teacher_acc": 0.7156349718570709 }, { "step": 13791, "lr": 2.43536789125349e-06, "elapsed_s": 10243.854454755783, "loss": 2.9735423922538757, "hidden": 0.1810770407319069, "layer": 0.08804386854171753, "mlm": 1.537389189004898, "distill": 1.0299771279096603, "teacher_acc": 0.7164116054773331 }, { "step": 13801, "lr": 2.4137391347404476e-06, "elapsed_s": 10251.289105176926, "loss": 2.8571659326553345, "hidden": 0.17165841534733772, "layer": 0.08736958168447018, "mlm": 1.468131422996521, "distill": 1.002032846212387, "teacher_acc": 0.73350790143013 }, { "step": 13811, "lr": 2.3922019780730192e-06, "elapsed_s": 10258.710137844086, "loss": 2.8679582476615906, "hidden": 0.17781966924667358, "layer": 0.08721243776381016, "mlm": 1.468209058046341, "distill": 1.0005036294460297, "teacher_acc": 0.7386182695627213 }, { "step": 13821, "lr": 2.3707565085963667e-06, "elapsed_s": 10266.125086784363, "loss": 2.973024010658264, "hidden": 0.17217721417546272, "layer": 0.08818310126662254, "mlm": 1.5950253307819366, "distill": 0.9895526319742203, "teacher_acc": 0.7040073573589325 }, { "step": 13831, "lr": 2.3494028132837796e-06, "elapsed_s": 10273.559455394745, "loss": 2.7924931049346924, "hidden": 0.17540602385997772, "layer": 0.08654344268143177, "mlm": 1.4439668357372284, "distill": 0.954442486166954, "teacher_acc": 0.7309968918561935 }, { "step": 13841, "lr": 2.328140978736365e-06, "elapsed_s": 10280.958008050919, "loss": 2.9041112661361694, "hidden": 0.1775062046945095, "layer": 0.08754895254969597, "mlm": 1.4747491478919983, "distill": 1.0305751711130142, "teacher_acc": 0.7350284904241562 }, { "step": 13851, "lr": 2.306971091182686e-06, "elapsed_s": 10288.371163845062, "loss": 2.7793145179748535, "hidden": 0.1688280776143074, "layer": 0.08618584834039211, "mlm": 1.5187110006809235, "distill": 0.8798544555902481, "teacher_acc": 0.7138697952032089 }, { "step": 13861, "lr": 2.2858932364784034e-06, "elapsed_s": 10295.801223754883, "loss": 2.8965718746185303, "hidden": 0.1723787970840931, "layer": 0.08558940514922142, "mlm": 1.5538792312145233, "distill": 0.9551402628421783, "teacher_acc": 0.7150238901376724 }, { "step": 13871, "lr": 2.264907500105945e-06, "elapsed_s": 10303.24336218834, "loss": 2.8284568190574646, "hidden": 0.18051692470908165, "layer": 0.08728775195777416, "mlm": 1.4243427217006683, "distill": 0.9994364231824875, "teacher_acc": 0.7403854727745056 }, { "step": 13881, "lr": 2.2440139671741356e-06, "elapsed_s": 10310.655108690262, "loss": 2.83755362033844, "hidden": 0.17258794978260994, "layer": 0.08561290428042412, "mlm": 1.5178918838500977, "distill": 0.9316794127225876, "teacher_acc": 0.7169499397277832 }, { "step": 13891, "lr": 2.2232127224178637e-06, "elapsed_s": 10318.077113389969, "loss": 2.7351359724998474, "hidden": 0.17573755607008934, "layer": 0.08525663055479527, "mlm": 1.417270541191101, "distill": 0.9237620085477829, "teacher_acc": 0.7255730330944061 }, { "step": 13901, "lr": 2.2025038501977486e-06, "elapsed_s": 10325.500655412674, "loss": 2.7581538558006287, "hidden": 0.170022152364254, "layer": 0.084604537114501, "mlm": 1.456235557794571, "distill": 0.9195716977119446, "teacher_acc": 0.732001006603241 }, { "step": 13911, "lr": 2.181887434499774e-06, "elapsed_s": 10332.914532661438, "loss": 2.786330759525299, "hidden": 0.172620490193367, "layer": 0.0852566733956337, "mlm": 1.4611341655254364, "distill": 0.9373273104429245, "teacher_acc": 0.7210332453250885 }, { "step": 13921, "lr": 2.1613635589349756e-06, "elapsed_s": 10340.322680950165, "loss": 2.7879751920700073, "hidden": 0.1731111891567707, "layer": 0.08607964403927326, "mlm": 1.5158867537975311, "distill": 0.8828262537717819, "teacher_acc": 0.7099797278642654 }, { "step": 13931, "lr": 2.1409323067390797e-06, "elapsed_s": 10347.730446577072, "loss": 2.837278425693512, "hidden": 0.1709444634616375, "layer": 0.08515521138906479, "mlm": 1.5361400544643402, "distill": 0.9166718423366547, "teacher_acc": 0.7014962583780289 }, { "step": 13941, "lr": 2.120593760772166e-06, "elapsed_s": 10355.104372262955, "loss": 2.796305000782013, "hidden": 0.16753742098808289, "layer": 0.08469321765005589, "mlm": 1.5235105156898499, "distill": 0.8953730314970016, "teacher_acc": 0.7005200535058975 }, { "step": 13951, "lr": 2.1003480035183513e-06, "elapsed_s": 10362.49483013153, "loss": 2.8059089183807373, "hidden": 0.16784042865037918, "layer": 0.08432520367205143, "mlm": 1.5245665311813354, "distill": 0.9034988880157471, "teacher_acc": 0.7140496075153351 }, { "step": 13961, "lr": 2.08019511708544e-06, "elapsed_s": 10369.905203342438, "loss": 2.885190486907959, "hidden": 0.17706922814249992, "layer": 0.08653123304247856, "mlm": 1.5224555134773254, "distill": 0.9653308540582657, "teacher_acc": 0.7140603810548782 }, { "step": 13971, "lr": 2.0601351832045866e-06, "elapsed_s": 10377.315805196762, "loss": 2.7942179441452026, "hidden": 0.1794845461845398, "layer": 0.0889893937855959, "mlm": 1.4326823055744171, "distill": 0.9580718129873276, "teacher_acc": 0.7354013472795486 }, { "step": 13981, "lr": 2.0401682832299845e-06, "elapsed_s": 10384.733602285385, "loss": 2.793272912502289, "hidden": 0.17557357624173164, "layer": 0.08620630577206612, "mlm": 1.447041541337967, "distill": 0.9519810527563095, "teacher_acc": 0.7309431284666061 }, { "step": 13991, "lr": 2.020294498138503e-06, "elapsed_s": 10392.12751698494, "loss": 2.8158835768699646, "hidden": 0.17689795047044754, "layer": 0.08673472329974174, "mlm": 1.4679576456546783, "distill": 0.9507626444101334, "teacher_acc": 0.7258395254611969 }, { "step": 14001, "lr": 2.0005139085293945e-06, "elapsed_s": 10401.608981370926, "loss": 2.76169216632843, "hidden": 0.16610056906938553, "layer": 0.08407432027161121, "mlm": 1.46820867061615, "distill": 0.9192452281713486, "teacher_acc": 0.7223249077796936 }, { "step": 14011, "lr": 1.9808265946239523e-06, "elapsed_s": 10409.022718429565, "loss": 2.802949070930481, "hidden": 0.1710244081914425, "layer": 0.08679200895130634, "mlm": 1.4966979920864105, "distill": 0.9208062589168549, "teacher_acc": 0.7197669893503189 }, { "step": 14021, "lr": 1.9612326362651757e-06, "elapsed_s": 10416.40318441391, "loss": 2.794956624507904, "hidden": 0.1750604845583439, "layer": 0.08662434853613377, "mlm": 1.4720516502857208, "distill": 0.9294718205928802, "teacher_acc": 0.7237173467874527 }, { "step": 14031, "lr": 1.941732112917466e-06, "elapsed_s": 10423.815347194672, "loss": 2.929684281349182, "hidden": 0.17674985900521278, "layer": 0.08677071332931519, "mlm": 1.5664366483688354, "distill": 0.9663625955581665, "teacher_acc": 0.705165222287178 }, { "step": 14041, "lr": 1.922325103666281e-06, "elapsed_s": 10431.199553966522, "loss": 2.904448091983795, "hidden": 0.1739608570933342, "layer": 0.08673299476504326, "mlm": 1.5817512273788452, "distill": 0.9314086586236954, "teacher_acc": 0.7042127847671509 }, { "step": 14051, "lr": 1.9030116872178316e-06, "elapsed_s": 10438.59989619255, "loss": 2.752030670642853, "hidden": 0.17183400318026543, "layer": 0.08621217496693134, "mlm": 1.449620246887207, "distill": 0.9156363606452942, "teacher_acc": 0.7328990399837494 }, { "step": 14061, "lr": 1.8837919418987659e-06, "elapsed_s": 10445.975409269333, "loss": 2.7731663584709167, "hidden": 0.17027044668793678, "layer": 0.084932342171669, "mlm": 1.493860274553299, "distill": 0.896298959851265, "teacher_acc": 0.7175787091255188 }, { "step": 14071, "lr": 1.8646659456558357e-06, "elapsed_s": 10453.361553668976, "loss": 2.873856484889984, "hidden": 0.17382044717669487, "layer": 0.08752700127661228, "mlm": 1.5031442642211914, "distill": 0.9793078303337097, "teacher_acc": 0.7198782861232758 }, { "step": 14081, "lr": 1.8456337760555915e-06, "elapsed_s": 10460.736646175385, "loss": 2.745754837989807, "hidden": 0.1751195378601551, "layer": 0.08550835400819778, "mlm": 1.4350703358650208, "distill": 0.9176911860704422, "teacher_acc": 0.731780931353569 }, { "step": 14091, "lr": 1.8266955102840544e-06, "elapsed_s": 10468.110454559326, "loss": 3.016284704208374, "hidden": 0.17835402861237526, "layer": 0.08700285479426384, "mlm": 1.5910156667232513, "distill": 1.0250595957040787, "teacher_acc": 0.7032258063554764 }, { "step": 14101, "lr": 1.8078512251464286e-06, "elapsed_s": 10475.516586065292, "loss": 2.8399804830551147, "hidden": 0.16947676241397858, "layer": 0.08494937233626842, "mlm": 1.5065691471099854, "distill": 0.9519830495119095, "teacher_acc": 0.7126374989748001 }, { "step": 14111, "lr": 1.7891009970667672e-06, "elapsed_s": 10482.91712474823, "loss": 2.9532009959220886, "hidden": 0.17750415205955505, "layer": 0.08710438385605812, "mlm": 1.5591579973697662, "distill": 0.9954824596643448, "teacher_acc": 0.7058866769075394 }, { "step": 14121, "lr": 1.77044490208767e-06, "elapsed_s": 10490.346314907074, "loss": 2.7569345831871033, "hidden": 0.1716279461979866, "layer": 0.0856749676167965, "mlm": 1.4318766295909882, "distill": 0.9389645159244537, "teacher_acc": 0.7311614155769348 }, { "step": 14131, "lr": 1.7518830158699761e-06, "elapsed_s": 10497.791120767593, "loss": 2.7607027292251587, "hidden": 0.17083078250288963, "layer": 0.08581781387329102, "mlm": 1.4493281245231628, "distill": 0.9268041253089905, "teacher_acc": 0.7253232151269913 }, { "step": 14141, "lr": 1.7334154136924491e-06, "elapsed_s": 10505.176270246506, "loss": 2.799915075302124, "hidden": 0.174549151211977, "layer": 0.08530793711543083, "mlm": 1.4337543547153473, "distill": 0.9744085073471069, "teacher_acc": 0.7375188320875168 }, { "step": 14151, "lr": 1.7150421704514863e-06, "elapsed_s": 10512.559198856354, "loss": 2.733894169330597, "hidden": 0.17086751759052277, "layer": 0.08504052460193634, "mlm": 1.4350909292697906, "distill": 0.9145479649305344, "teacher_acc": 0.7287153452634811 }, { "step": 14161, "lr": 1.696763360660808e-06, "elapsed_s": 10519.944802999496, "loss": 2.8709142208099365, "hidden": 0.17224057763814926, "layer": 0.08669607527554035, "mlm": 1.5268691182136536, "distill": 0.9562158435583115, "teacher_acc": 0.7134450227022171 }, { "step": 14171, "lr": 1.6785790584511435e-06, "elapsed_s": 10527.368250131607, "loss": 2.822826087474823, "hidden": 0.17584363371133804, "layer": 0.08717238530516624, "mlm": 1.4723452627658844, "distill": 0.9552074074745178, "teacher_acc": 0.7209930568933487 }, { "step": 14181, "lr": 1.6604893375699594e-06, "elapsed_s": 10534.792336940765, "loss": 2.793032944202423, "hidden": 0.17144005373120308, "layer": 0.08522113040089607, "mlm": 1.4916033446788788, "distill": 0.9159389138221741, "teacher_acc": 0.7202620506286621 }, { "step": 14191, "lr": 1.6424942713811204e-06, "elapsed_s": 10542.209605932236, "loss": 2.7623318433761597, "hidden": 0.17746607214212418, "layer": 0.0878321249037981, "mlm": 1.4097042679786682, "distill": 0.9537792950868607, "teacher_acc": 0.7382763624191284 }, { "step": 14201, "lr": 1.624593932864632e-06, "elapsed_s": 10549.643550634384, "loss": 2.880506217479706, "hidden": 0.17743392288684845, "layer": 0.0868946835398674, "mlm": 1.483972042798996, "distill": 0.9982190579175949, "teacher_acc": 0.7198678553104401 }, { "step": 14211, "lr": 1.6067883946163154e-06, "elapsed_s": 10557.080504179, "loss": 2.8627567887306213, "hidden": 0.1716657169163227, "layer": 0.08384089544415474, "mlm": 1.54677215218544, "distill": 0.9307327121496201, "teacher_acc": 0.7150154411792755 }, { "step": 14221, "lr": 1.5890777288475296e-06, "elapsed_s": 10564.52091050148, "loss": 2.8106547594070435, "hidden": 0.16821079328656197, "layer": 0.08497673831880093, "mlm": 1.465882569551468, "distill": 0.9658621996641159, "teacher_acc": 0.7320643067359924 }, { "step": 14231, "lr": 1.5714620073848774e-06, "elapsed_s": 10571.960143327713, "loss": 2.806226134300232, "hidden": 0.1807350590825081, "layer": 0.08767815679311752, "mlm": 1.404232770204544, "distill": 0.996684119105339, "teacher_acc": 0.7395389527082443 }, { "step": 14241, "lr": 1.5539413016698922e-06, "elapsed_s": 10579.395082712173, "loss": 2.6752718687057495, "hidden": 0.1680995263159275, "layer": 0.08456046134233475, "mlm": 1.4084307849407196, "distill": 0.8883618414402008, "teacher_acc": 0.7343160659074783 }, { "step": 14251, "lr": 1.5365156827587822e-06, "elapsed_s": 10586.809281349182, "loss": 2.7044894099235535, "hidden": 0.17138204351067543, "layer": 0.08655286207795143, "mlm": 1.4075784385204315, "distill": 0.9108704477548599, "teacher_acc": 0.7320179343223572 }, { "step": 14261, "lr": 1.5191852213221197e-06, "elapsed_s": 10594.208156824112, "loss": 2.729857385158539, "hidden": 0.17048194631934166, "layer": 0.08541163802146912, "mlm": 1.4426599442958832, "distill": 0.903527706861496, "teacher_acc": 0.7260657995939255 }, { "step": 14271, "lr": 1.501949987644566e-06, "elapsed_s": 10601.633776426315, "loss": 2.897200345993042, "hidden": 0.17486248165369034, "layer": 0.08685139194130898, "mlm": 1.4816516041755676, "distill": 1.022398054599762, "teacher_acc": 0.7214303314685822 }, { "step": 14281, "lr": 1.4848100516245717e-06, "elapsed_s": 10609.034410476685, "loss": 2.7583463191986084, "hidden": 0.17370961606502533, "layer": 0.08594811521470547, "mlm": 1.408496618270874, "distill": 0.9594565182924271, "teacher_acc": 0.7314571589231491 }, { "step": 14291, "lr": 1.4677654827741111e-06, "elapsed_s": 10616.44923901558, "loss": 2.8035049438476562, "hidden": 0.17421622574329376, "layer": 0.08625682070851326, "mlm": 1.4719065427780151, "distill": 0.9400375336408615, "teacher_acc": 0.7200664430856705 }, { "step": 14301, "lr": 1.4508163502183786e-06, "elapsed_s": 10623.89735174179, "loss": 2.8051029443740845, "hidden": 0.1713331751525402, "layer": 0.08489186689257622, "mlm": 1.5115172863006592, "distill": 0.9084734320640564, "teacher_acc": 0.7066345363855362 }, { "step": 14311, "lr": 1.4339627226955392e-06, "elapsed_s": 10631.30501484871, "loss": 2.760395646095276, "hidden": 0.17375002056360245, "layer": 0.08588007092475891, "mlm": 1.4438023269176483, "distill": 0.9261532723903656, "teacher_acc": 0.7217451930046082 }, { "step": 14321, "lr": 1.4172046685564212e-06, "elapsed_s": 10638.763637304306, "loss": 2.872941493988037, "hidden": 0.17066996544599533, "layer": 0.08552526123821735, "mlm": 1.515047937631607, "distill": 0.9737909883260727, "teacher_acc": 0.7192364633083344 }, { "step": 14331, "lr": 1.4005422557642533e-06, "elapsed_s": 10646.162722587585, "loss": 2.828407406806946, "hidden": 0.17114480957388878, "layer": 0.08599905669689178, "mlm": 1.498354583978653, "distill": 0.9447636604309082, "teacher_acc": 0.7211867421865463 }, { "step": 14341, "lr": 1.3839755518943786e-06, "elapsed_s": 10653.594453811646, "loss": 2.8147324323654175, "hidden": 0.17176616936922073, "layer": 0.08574691228568554, "mlm": 1.5120875537395477, "distill": 0.9162391424179077, "teacher_acc": 0.7049439400434494 }, { "step": 14351, "lr": 1.3675046241339918e-06, "elapsed_s": 10661.027324438095, "loss": 2.929498076438904, "hidden": 0.18100519850850105, "layer": 0.08845037780702114, "mlm": 1.4862072467803955, "distill": 1.037055253982544, "teacher_acc": 0.7324432730674744 }, { "step": 14361, "lr": 1.35112953928187e-06, "elapsed_s": 10668.443279027939, "loss": 2.8735697865486145, "hidden": 0.1717100478708744, "layer": 0.08651827462017536, "mlm": 1.522817313671112, "distill": 0.9640732109546661, "teacher_acc": 0.713957279920578 }, { "step": 14371, "lr": 1.3348503637480774e-06, "elapsed_s": 10675.880018234253, "loss": 2.7407710552215576, "hidden": 0.1716291680932045, "layer": 0.08558456785976887, "mlm": 1.4371619820594788, "distill": 0.9175583869218826, "teacher_acc": 0.7340006083250046 }, { "step": 14381, "lr": 1.318667163553733e-06, "elapsed_s": 10683.281696796417, "loss": 2.8329426646232605, "hidden": 0.1754225268959999, "layer": 0.08518490754067898, "mlm": 1.4657265543937683, "distill": 0.973778635263443, "teacher_acc": 0.7269022464752197 }, { "step": 14391, "lr": 1.302580004330703e-06, "elapsed_s": 10690.667478322983, "loss": 2.9925026297569275, "hidden": 0.18222379684448242, "layer": 0.08886671997606754, "mlm": 1.5541399419307709, "distill": 1.0294816046953201, "teacher_acc": 0.7146477401256561 }, { "step": 14401, "lr": 1.286588951321363e-06, "elapsed_s": 10698.068416595459, "loss": 2.7938133478164673, "hidden": 0.17523540556430817, "layer": 0.0857910756021738, "mlm": 1.4221921563148499, "distill": 0.9782548099756241, "teacher_acc": 0.7374463826417923 }, { "step": 14411, "lr": 1.2706940693783225e-06, "elapsed_s": 10705.505653381348, "loss": 2.7076727747917175, "hidden": 0.16958023980259895, "layer": 0.08545582368969917, "mlm": 1.4056776762008667, "distill": 0.9201067388057709, "teacher_acc": 0.7409806102514267 }, { "step": 14421, "lr": 1.2548954229641725e-06, "elapsed_s": 10712.97174334526, "loss": 2.864917516708374, "hidden": 0.1760558933019638, "layer": 0.08566531166434288, "mlm": 1.5528311729431152, "distill": 0.9171419441699982, "teacher_acc": 0.7019470483064651 }, { "step": 14431, "lr": 1.2391930761512045e-06, "elapsed_s": 10720.386365175247, "loss": 2.7830395698547363, "hidden": 0.17527521774172783, "layer": 0.08628619275987148, "mlm": 1.4018632173538208, "distill": 0.9874828457832336, "teacher_acc": 0.7434203028678894 }, { "step": 14441, "lr": 1.2235870926211619e-06, "elapsed_s": 10727.794499397278, "loss": 2.8224573135375977, "hidden": 0.17201048880815506, "layer": 0.08530403487384319, "mlm": 1.4746313691139221, "distill": 0.961152970790863, "teacher_acc": 0.7275345772504807 }, { "step": 14451, "lr": 1.2080775356649866e-06, "elapsed_s": 10735.195686101913, "loss": 2.8824841380119324, "hidden": 0.1731123961508274, "layer": 0.08634190075099468, "mlm": 1.5141050517559052, "distill": 0.9789833575487137, "teacher_acc": 0.7098517864942551 }, { "step": 14461, "lr": 1.1926644681825556e-06, "elapsed_s": 10742.586343765259, "loss": 2.897954821586609, "hidden": 0.17373031377792358, "layer": 0.0867721289396286, "mlm": 1.5148891806602478, "distill": 0.9922189712524414, "teacher_acc": 0.7212705314159393 }, { "step": 14471, "lr": 1.1773479526824282e-06, "elapsed_s": 10750.023885250092, "loss": 2.8197315335273743, "hidden": 0.17528011277318, "layer": 0.08631559833884239, "mlm": 1.4834266901016235, "distill": 0.9425867944955826, "teacher_acc": 0.719948410987854 }, { "step": 14481, "lr": 1.162128051281594e-06, "elapsed_s": 10757.447720766068, "loss": 2.881897807121277, "hidden": 0.17308423295617104, "layer": 0.0865514948964119, "mlm": 1.5254969596862793, "distill": 0.9669566005468369, "teacher_acc": 0.7233994603157043 }, { "step": 14491, "lr": 1.1470048257052085e-06, "elapsed_s": 10764.848556756973, "loss": 2.8593088388442993, "hidden": 0.17850501090288162, "layer": 0.08657425083220005, "mlm": 1.4811260104179382, "distill": 0.9778856635093689, "teacher_acc": 0.7271009534597397 }, { "step": 14501, "lr": 1.1319783372863602e-06, "elapsed_s": 10772.25808763504, "loss": 2.786432921886444, "hidden": 0.17393088713288307, "layer": 0.08689089305698872, "mlm": 1.462539255619049, "distill": 0.9325863867998123, "teacher_acc": 0.7282358258962631 }, { "step": 14511, "lr": 1.1170486469658182e-06, "elapsed_s": 10779.63590502739, "loss": 2.821333885192871, "hidden": 0.16686134040355682, "layer": 0.08442057855427265, "mlm": 1.6068719029426575, "distill": 0.838528960943222, "teacher_acc": 0.6733581721782684 }, { "step": 14521, "lr": 1.102215815291774e-06, "elapsed_s": 10787.04955625534, "loss": 2.856306552886963, "hidden": 0.17236362025141716, "layer": 0.08624440431594849, "mlm": 1.4837678968906403, "distill": 0.9846892058849335, "teacher_acc": 0.7233289629220963 }, { "step": 14531, "lr": 1.0874799024196137e-06, "elapsed_s": 10794.463998317719, "loss": 2.823406457901001, "hidden": 0.17308861017227173, "layer": 0.08762641064822674, "mlm": 1.4940694570541382, "distill": 0.9393465220928192, "teacher_acc": 0.7214764058589935 }, { "step": 14541, "lr": 1.0728409681116492e-06, "elapsed_s": 10801.889160394669, "loss": 2.69081974029541, "hidden": 0.17080075666308403, "layer": 0.08561859652400017, "mlm": 1.4093118011951447, "distill": 0.8970970958471298, "teacher_acc": 0.7368239611387253 }, { "step": 14551, "lr": 1.0582990717369013e-06, "elapsed_s": 10809.300548791885, "loss": 2.764712929725647, "hidden": 0.17329735308885574, "layer": 0.08581766672432423, "mlm": 1.4008901715278625, "distill": 0.9743192344903946, "teacher_acc": 0.7484188824892044 }, { "step": 14561, "lr": 1.0438542722708445e-06, "elapsed_s": 10816.719276428223, "loss": 2.9092506766319275, "hidden": 0.1757342740893364, "layer": 0.0870184637606144, "mlm": 1.5078702867031097, "distill": 1.006402626633644, "teacher_acc": 0.7252167463302612 }, { "step": 14571, "lr": 1.0295066282951738e-06, "elapsed_s": 10824.136897087097, "loss": 2.815778911113739, "hidden": 0.17264306545257568, "layer": 0.08592127077281475, "mlm": 1.4873088002204895, "distill": 0.9402233511209488, "teacher_acc": 0.7176450937986374 }, { "step": 14581, "lr": 1.0152561979975633e-06, "elapsed_s": 10831.550125837326, "loss": 2.8162782788276672, "hidden": 0.17506588250398636, "layer": 0.08703228645026684, "mlm": 1.4762937128543854, "distill": 0.9463365972042084, "teacher_acc": 0.7226410508155823 }, { "step": 14591, "lr": 1.0011030391714278e-06, "elapsed_s": 10838.968429327011, "loss": 2.858545958995819, "hidden": 0.17958089336752892, "layer": 0.08726862072944641, "mlm": 1.490052878856659, "distill": 0.9656970202922821, "teacher_acc": 0.7152596712112427 }, { "step": 14601, "lr": 9.87047209215694e-07, "elapsed_s": 10846.409361362457, "loss": 2.786189079284668, "hidden": 0.1754492148756981, "layer": 0.08665314316749573, "mlm": 1.4200316369533539, "distill": 0.9719324111938477, "teacher_acc": 0.7383500933647156 }, { "step": 14611, "lr": 9.730887651345722e-07, "elapsed_s": 10853.813233852386, "loss": 2.861258029937744, "hidden": 0.1722641997039318, "layer": 0.08585125394165516, "mlm": 1.5347341895103455, "distill": 0.9390698820352554, "teacher_acc": 0.7050961554050446 }, { "step": 14621, "lr": 9.592277635373097e-07, "elapsed_s": 10861.250692129135, "loss": 2.7728896141052246, "hidden": 0.16919482126832008, "layer": 0.08548467978835106, "mlm": 1.5000942945480347, "distill": 0.8916633725166321, "teacher_acc": 0.7130042463541031 }, { "step": 14631, "lr": 9.454642606379793e-07, "elapsed_s": 10868.68359208107, "loss": 2.751961410045624, "hidden": 0.17055664956569672, "layer": 0.08580171316862106, "mlm": 1.4170801937580109, "distill": 0.9508669674396515, "teacher_acc": 0.7317867428064346 }, { "step": 14641, "lr": 9.317983122552332e-07, "elapsed_s": 10876.109104633331, "loss": 2.782758414745331, "hidden": 0.16910052672028542, "layer": 0.08481230586767197, "mlm": 1.4876843988895416, "distill": 0.9144667834043503, "teacher_acc": 0.7128712385892868 }, { "step": 14651, "lr": 9.182299738120931e-07, "elapsed_s": 10883.49386048317, "loss": 2.7592004537582397, "hidden": 0.17571571096777916, "layer": 0.08717487752437592, "mlm": 1.4334011673927307, "distill": 0.9307804256677628, "teacher_acc": 0.7200534790754318 }, { "step": 14661, "lr": 9.047593003357141e-07, "elapsed_s": 10890.887219667435, "loss": 2.869601309299469, "hidden": 0.1723918840289116, "layer": 0.08528394065797329, "mlm": 1.539952278137207, "distill": 0.9422232508659363, "teacher_acc": 0.717275008559227 }, { "step": 14671, "lr": 8.913863464571654e-07, "elapsed_s": 10898.248170375824, "loss": 2.8651984333992004, "hidden": 0.17677663639187813, "layer": 0.08796209469437599, "mlm": 1.5254859030246735, "distill": 0.9421782791614532, "teacher_acc": 0.7144770920276642 }, { "step": 14681, "lr": 8.781111664112162e-07, "elapsed_s": 10905.6598072052, "loss": 2.860907196998596, "hidden": 0.17617647722363472, "layer": 0.08662915043532848, "mlm": 1.488585501909256, "distill": 0.976654127240181, "teacher_acc": 0.7255280166864395 }, { "step": 14691, "lr": 8.649338140360952e-07, "elapsed_s": 10913.085814237595, "loss": 2.8184260725975037, "hidden": 0.17308060079813004, "layer": 0.08560461550951004, "mlm": 1.4963504076004028, "distill": 0.9331120997667313, "teacher_acc": 0.7166269421577454 }, { "step": 14701, "lr": 8.51854342773295e-07, "elapsed_s": 10920.47568154335, "loss": 2.766369044780731, "hidden": 0.17789726331830025, "layer": 0.08677062578499317, "mlm": 1.4088303744792938, "distill": 0.9583588093519211, "teacher_acc": 0.7401765882968903 }, { "step": 14711, "lr": 8.388728056673428e-07, "elapsed_s": 10927.87915802002, "loss": 2.785901188850403, "hidden": 0.17261191457509995, "layer": 0.08565591648221016, "mlm": 1.4966124594211578, "distill": 0.9012369513511658, "teacher_acc": 0.7152309417724609 }, { "step": 14721, "lr": 8.259892553655946e-07, "elapsed_s": 10935.32442164421, "loss": 2.742553412914276, "hidden": 0.1710566058754921, "layer": 0.08520496636629105, "mlm": 1.4401735067367554, "distill": 0.9176642894744873, "teacher_acc": 0.7316845804452896 }, { "step": 14731, "lr": 8.132037441180046e-07, "elapsed_s": 10942.72343301773, "loss": 2.9203909635543823, "hidden": 0.17939673364162445, "layer": 0.0879576038569212, "mlm": 1.5438344478607178, "distill": 0.9737842679023743, "teacher_acc": 0.718051016330719 }, { "step": 14741, "lr": 8.005163237769315e-07, "elapsed_s": 10950.079406738281, "loss": 2.7834248542785645, "hidden": 0.16955074667930603, "layer": 0.08497501909732819, "mlm": 1.4784665703773499, "distill": 0.9233692735433578, "teacher_acc": 0.727058157324791 }, { "step": 14751, "lr": 7.879270457969184e-07, "elapsed_s": 10957.475257873535, "loss": 2.7895267605781555, "hidden": 0.17260537296533585, "layer": 0.08561785519123077, "mlm": 1.466191291809082, "distill": 0.9353158622980118, "teacher_acc": 0.7240082770586014 }, { "step": 14761, "lr": 7.754359612344859e-07, "elapsed_s": 10964.890647172928, "loss": 2.8747113943099976, "hidden": 0.16749923676252365, "layer": 0.08415411971509457, "mlm": 1.5662117302417755, "distill": 0.9314241260290146, "teacher_acc": 0.6985058635473251 }, { "step": 14771, "lr": 7.630431207479277e-07, "elapsed_s": 10972.337652683258, "loss": 2.678408622741699, "hidden": 0.16675327718257904, "layer": 0.0834511611610651, "mlm": 1.4248882830142975, "distill": 0.8782881647348404, "teacher_acc": 0.7339321076869965 }, { "step": 14781, "lr": 7.507485745971043e-07, "elapsed_s": 10979.734361886978, "loss": 2.7640058994293213, "hidden": 0.17048689350485802, "layer": 0.08561656810343266, "mlm": 1.4236049354076385, "distill": 0.9566189497709274, "teacher_acc": 0.736858531832695 }, { "step": 14791, "lr": 7.385523726432364e-07, "elapsed_s": 10987.128791570663, "loss": 2.9336647987365723, "hidden": 0.1749587319791317, "layer": 0.08641347475349903, "mlm": 1.5253080427646637, "distill": 1.0152325183153152, "teacher_acc": 0.7199874073266983 }, { "step": 14801, "lr": 7.264545643486997e-07, "elapsed_s": 10994.506994485855, "loss": 2.9238389134407043, "hidden": 0.17551898211240768, "layer": 0.08702125027775764, "mlm": 1.5654364228248596, "distill": 0.9638539105653763, "teacher_acc": 0.7080443352460861 }, { "step": 14811, "lr": 7.144551987768338e-07, "elapsed_s": 11001.889144659042, "loss": 2.720135509967804, "hidden": 0.1703076921403408, "layer": 0.08404413796961308, "mlm": 1.4455814063549042, "distill": 0.8919166177511215, "teacher_acc": 0.7328233569860458 }, { "step": 14821, "lr": 7.02554324591742e-07, "elapsed_s": 11009.279310703278, "loss": 2.8809213638305664, "hidden": 0.17310554161667824, "layer": 0.08566122129559517, "mlm": 1.5834597647190094, "distill": 0.9084198921918869, "teacher_acc": 0.6890660971403122 }, { "step": 14831, "lr": 6.907519900580861e-07, "elapsed_s": 11016.695277452469, "loss": 2.84211403131485, "hidden": 0.17318176478147507, "layer": 0.0866678562015295, "mlm": 1.4875557124614716, "distill": 0.9648608565330505, "teacher_acc": 0.7249263375997543 }, { "step": 14841, "lr": 6.79048243040889e-07, "elapsed_s": 11024.071609973907, "loss": 2.8912243247032166, "hidden": 0.17129940167069435, "layer": 0.0856372807174921, "mlm": 1.577330619096756, "distill": 0.9284763187170029, "teacher_acc": 0.7010038197040558 }, { "step": 14851, "lr": 6.674431310053519e-07, "elapsed_s": 11031.486183643341, "loss": 2.6856426000595093, "hidden": 0.1736750639975071, "layer": 0.08531162142753601, "mlm": 1.3865609765052795, "distill": 0.9090756177902222, "teacher_acc": 0.7390550673007965 }, { "step": 14861, "lr": 6.559367010166628e-07, "elapsed_s": 11038.906079530716, "loss": 2.8512858152389526, "hidden": 0.17514295130968094, "layer": 0.08675952069461346, "mlm": 1.4962226450443268, "distill": 0.9613975286483765, "teacher_acc": 0.7240743786096573 }, { "step": 14871, "lr": 6.44528999739788e-07, "elapsed_s": 11046.336796283722, "loss": 2.6999950408935547, "hidden": 0.1696496084332466, "layer": 0.08490796200931072, "mlm": 1.4013757407665253, "distill": 0.9168660938739777, "teacher_acc": 0.7382998615503311 }, { "step": 14881, "lr": 6.332200734393057e-07, "elapsed_s": 11053.765421390533, "loss": 2.891092538833618, "hidden": 0.17457423359155655, "layer": 0.08579068444669247, "mlm": 1.5424642860889435, "distill": 0.9565844386816025, "teacher_acc": 0.7157268971204758 }, { "step": 14891, "lr": 6.220099679791897e-07, "elapsed_s": 11061.224831104279, "loss": 2.87156218290329, "hidden": 0.17565599083900452, "layer": 0.08607467077672482, "mlm": 1.5146782398223877, "distill": 0.962534710764885, "teacher_acc": 0.7170919477939606 }, { "step": 14901, "lr": 6.108987288226536e-07, "elapsed_s": 11068.579588413239, "loss": 2.8931609988212585, "hidden": 0.17428219318389893, "layer": 0.08652433939278126, "mlm": 1.5220081806182861, "distill": 0.9793262332677841, "teacher_acc": 0.7207663655281067 }, { "step": 14911, "lr": 5.998864010319516e-07, "elapsed_s": 11076.005879878998, "loss": 2.8689403533935547, "hidden": 0.16883435100317, "layer": 0.08595230989158154, "mlm": 1.5905997157096863, "distill": 0.8976957648992538, "teacher_acc": 0.6956483274698257 }, { "step": 14921, "lr": 5.889730292681972e-07, "elapsed_s": 11083.402671813965, "loss": 2.782044768333435, "hidden": 0.17074234038591385, "layer": 0.0857284776866436, "mlm": 1.434402346611023, "distill": 0.9632934033870697, "teacher_acc": 0.7369923889636993 }, { "step": 14931, "lr": 5.781586577911807e-07, "elapsed_s": 11090.83666753769, "loss": 2.8406795263290405, "hidden": 0.17498242855072021, "layer": 0.08501601405441761, "mlm": 1.5035149157047272, "distill": 0.9446917176246643, "teacher_acc": 0.7136219292879105 }, { "step": 14941, "lr": 5.674433304591859e-07, "elapsed_s": 11098.282428503036, "loss": 2.9502903819084167, "hidden": 0.17157406359910965, "layer": 0.08604967035353184, "mlm": 1.6335065960884094, "distill": 0.930610716342926, "teacher_acc": 0.688972994685173 }, { "step": 14951, "lr": 5.568270907288287e-07, "elapsed_s": 11105.713072538376, "loss": 3.057758152484894, "hidden": 0.182733204215765, "layer": 0.08912954479455948, "mlm": 1.613631159067154, "distill": 1.0340958386659622, "teacher_acc": 0.6886073648929596 }, { "step": 14961, "lr": 5.463099816548579e-07, "elapsed_s": 11113.147362470627, "loss": 2.838450849056244, "hidden": 0.1726633571088314, "layer": 0.08526210114359856, "mlm": 1.5155292451381683, "distill": 0.9349637925624847, "teacher_acc": 0.7131546437740326 }, { "step": 14971, "lr": 5.358920458900046e-07, "elapsed_s": 11120.59383058548, "loss": 2.7409510016441345, "hidden": 0.1745554320514202, "layer": 0.08602048270404339, "mlm": 1.3818857967853546, "distill": 0.9669440388679504, "teacher_acc": 0.7473931163549423 }, { "step": 14981, "lr": 5.255733256847889e-07, "elapsed_s": 11128.035746097565, "loss": 2.888481855392456, "hidden": 0.17650017514824867, "layer": 0.08692662604153156, "mlm": 1.4895232021808624, "distill": 1.0024949759244919, "teacher_acc": 0.7313336133956909 }, { "step": 14991, "lr": 5.15353862887355e-07, "elapsed_s": 11135.480044603348, "loss": 2.767621636390686, "hidden": 0.17124944925308228, "layer": 0.08611654862761497, "mlm": 1.449194997549057, "distill": 0.9328694343566895, "teacher_acc": 0.7302902787923813 }, { "step": 15001, "lr": 5.052336989433082e-07, "elapsed_s": 11144.962507009506, "loss": 2.7852954268455505, "hidden": 0.16580792516469955, "layer": 0.08434540964663029, "mlm": 1.5190192759037018, "distill": 0.8924875557422638, "teacher_acc": 0.7058766037225723 }, { "step": 15011, "lr": 4.952128748955398e-07, "elapsed_s": 11152.387697935104, "loss": 2.8101967573165894, "hidden": 0.1703622080385685, "layer": 0.08521559461951256, "mlm": 1.5014455020427704, "distill": 0.9254190027713776, "teacher_acc": 0.7126597315073013 }, { "step": 15021, "lr": 4.852914313840662e-07, "elapsed_s": 11159.805647611618, "loss": 2.892549514770508, "hidden": 0.17474956065416336, "layer": 0.08611348643898964, "mlm": 1.5126395225524902, "distill": 0.9873540997505188, "teacher_acc": 0.7213145792484283 }, { "step": 15031, "lr": 4.7546940864585387e-07, "elapsed_s": 11167.245911121368, "loss": 2.7559183835983276, "hidden": 0.1737385205924511, "layer": 0.08533759973943233, "mlm": 1.4436572194099426, "distill": 0.922115296125412, "teacher_acc": 0.7263970077037811 }, { "step": 15041, "lr": 4.6574684651466415e-07, "elapsed_s": 11174.70185470581, "loss": 2.8239579796791077, "hidden": 0.1735365055501461, "layer": 0.08519955538213253, "mlm": 1.4950356483459473, "distill": 0.939249575138092, "teacher_acc": 0.7233349680900574 }, { "step": 15051, "lr": 4.5612378442089766e-07, "elapsed_s": 11182.15726184845, "loss": 2.887046158313751, "hidden": 0.1757766604423523, "layer": 0.08700550347566605, "mlm": 1.5277834832668304, "distill": 0.964206650853157, "teacher_acc": 0.7099229246377945 }, { "step": 15061, "lr": 4.4660026139141385e-07, "elapsed_s": 11189.59115767479, "loss": 2.9336275458335876, "hidden": 0.17395057901740074, "layer": 0.08630500175058842, "mlm": 1.574600338935852, "distill": 0.9679735898971558, "teacher_acc": 0.6972937881946564 }, { "step": 15071, "lr": 4.371763160494008e-07, "elapsed_s": 11197.014613389969, "loss": 2.673524022102356, "hidden": 0.1666432023048401, "layer": 0.0833622869104147, "mlm": 1.4084221720695496, "distill": 0.890134260058403, "teacher_acc": 0.7342276126146317 }, { "step": 15081, "lr": 4.278519866141972e-07, "elapsed_s": 11204.436433315277, "loss": 2.7788753509521484, "hidden": 0.16438215598464012, "layer": 0.08395221643149853, "mlm": 1.5118547081947327, "distill": 0.8962802439928055, "teacher_acc": 0.7074703872203827 }, { "step": 15091, "lr": 4.1862731090113736e-07, "elapsed_s": 11211.850955963135, "loss": 2.8283971548080444, "hidden": 0.16993208229541779, "layer": 0.08386317826807499, "mlm": 1.5140541195869446, "distill": 0.9325472712516785, "teacher_acc": 0.71501125395298 }, { "step": 15101, "lr": 4.095023263214121e-07, "elapsed_s": 11219.232813358307, "loss": 2.7722848057746887, "hidden": 0.17030474543571472, "layer": 0.08593831025063992, "mlm": 1.4777165353298187, "distill": 0.9109897166490555, "teacher_acc": 0.723077118396759 }, { "step": 15111, "lr": 4.004770698819077e-07, "elapsed_s": 11226.648528575897, "loss": 2.8092472553253174, "hidden": 0.17700574919581413, "layer": 0.08727842383086681, "mlm": 1.4097817540168762, "distill": 1.00181482732296, "teacher_acc": 0.7426606565713882 }, { "step": 15121, "lr": 3.915515781850565e-07, "elapsed_s": 11234.046501874924, "loss": 2.775519073009491, "hidden": 0.16705475002527237, "layer": 0.08439456671476364, "mlm": 1.475652813911438, "distill": 0.9235594868659973, "teacher_acc": 0.7204635739326477 }, { "step": 15131, "lr": 3.827258874286921e-07, "elapsed_s": 11241.43199634552, "loss": 2.8294626474380493, "hidden": 0.170627199113369, "layer": 0.08523484319448471, "mlm": 1.487058013677597, "distill": 0.9585328251123428, "teacher_acc": 0.7237738072872162 }, { "step": 15141, "lr": 3.7400003340589687e-07, "elapsed_s": 11248.831955432892, "loss": 2.7984516620635986, "hidden": 0.17136017233133316, "layer": 0.08504154719412327, "mlm": 1.5199095606803894, "distill": 0.8933009952306747, "teacher_acc": 0.711412638425827 }, { "step": 15151, "lr": 3.653740515048576e-07, "elapsed_s": 11256.241410255432, "loss": 2.740207076072693, "hidden": 0.1714858077466488, "layer": 0.08514353260397911, "mlm": 1.4663298726081848, "distill": 0.888333797454834, "teacher_acc": 0.7218104004859924 }, { "step": 15161, "lr": 3.568479767087296e-07, "elapsed_s": 11263.62489104271, "loss": 2.8266592621803284, "hidden": 0.1737096905708313, "layer": 0.08576507121324539, "mlm": 1.474443793296814, "distill": 0.9619135558605194, "teacher_acc": 0.7256395667791367 }, { "step": 15171, "lr": 3.484218435954839e-07, "elapsed_s": 11271.041904449463, "loss": 2.7838099598884583, "hidden": 0.16890650242567062, "layer": 0.08483339846134186, "mlm": 1.5078443884849548, "distill": 0.8957358300685883, "teacher_acc": 0.7034810483455658 }, { "step": 15181, "lr": 3.4009568633777964e-07, "elapsed_s": 11278.43856716156, "loss": 2.783474326133728, "hidden": 0.17270272970199585, "layer": 0.08548083528876305, "mlm": 1.4582253098487854, "distill": 0.9371031671762466, "teacher_acc": 0.7310761660337448 }, { "step": 15191, "lr": 3.3186953870281144e-07, "elapsed_s": 11285.848642349243, "loss": 2.724146842956543, "hidden": 0.174867145717144, "layer": 0.08671503514051437, "mlm": 1.4237720966339111, "distill": 0.9072829335927963, "teacher_acc": 0.7289159595966339 }, { "step": 15201, "lr": 3.237434340521789e-07, "elapsed_s": 11293.2278444767, "loss": 2.842944622039795, "hidden": 0.17046865075826645, "layer": 0.08616664819419384, "mlm": 1.4970521032810211, "distill": 0.9618718475103378, "teacher_acc": 0.7204853147268295 }, { "step": 15211, "lr": 3.157174053417589e-07, "elapsed_s": 11300.616320848465, "loss": 2.6735154390335083, "hidden": 0.16860781610012054, "layer": 0.0845844317227602, "mlm": 1.3955365121364594, "distill": 0.8984711468219757, "teacher_acc": 0.7283686846494675 }, { "step": 15221, "lr": 3.077914851215585e-07, "elapsed_s": 11307.995571613312, "loss": 2.820692777633667, "hidden": 0.17071133479475975, "layer": 0.0852662306278944, "mlm": 1.5015047192573547, "distill": 0.9351322650909424, "teacher_acc": 0.7226359099149704 }, { "step": 15231, "lr": 2.9996570553559036e-07, "elapsed_s": 11315.422125816345, "loss": 2.76784211397171, "hidden": 0.17098674550652504, "layer": 0.08554156310856342, "mlm": 1.4920405745506287, "distill": 0.8910572379827499, "teacher_acc": 0.7135284394025803 }, { "step": 15241, "lr": 2.922400983217416e-07, "elapsed_s": 11322.840555429459, "loss": 2.828190326690674, "hidden": 0.1737024113535881, "layer": 0.08665317110717297, "mlm": 1.501670002937317, "distill": 0.9357889145612717, "teacher_acc": 0.7138854116201401 }, { "step": 15251, "lr": 2.846146948116468e-07, "elapsed_s": 11330.231798648834, "loss": 2.847204625606537, "hidden": 0.17968131601810455, "layer": 0.08791285008192062, "mlm": 1.438569724559784, "distill": 1.0053158104419708, "teacher_acc": 0.7285197228193283 }, { "step": 15261, "lr": 2.770895259305517e-07, "elapsed_s": 11337.652816295624, "loss": 2.7813690900802612, "hidden": 0.17074116319417953, "layer": 0.0855549443513155, "mlm": 1.4502010941505432, "distill": 0.9469082355499268, "teacher_acc": 0.7345093339681625 }, { "step": 15271, "lr": 2.6966462219720767e-07, "elapsed_s": 11345.087265968323, "loss": 2.8319063782691956, "hidden": 0.17446884140372276, "layer": 0.08587104827165604, "mlm": 1.5276874601840973, "distill": 0.9123456478118896, "teacher_acc": 0.706764742732048 }, { "step": 15281, "lr": 2.6234001372372194e-07, "elapsed_s": 11352.514022827148, "loss": 2.9520995020866394, "hidden": 0.17718017101287842, "layer": 0.08712559193372726, "mlm": 1.549910694360733, "distill": 1.0042656362056732, "teacher_acc": 0.7122835069894791 }, { "step": 15291, "lr": 2.5511573021545775e-07, "elapsed_s": 11359.91390490532, "loss": 2.9148569107055664, "hidden": 0.1740666702389717, "layer": 0.08655950240790844, "mlm": 1.544133722782135, "distill": 0.9793101400136948, "teacher_acc": 0.7155590057373047 }, { "step": 15301, "lr": 2.479918009708981e-07, "elapsed_s": 11367.32721042633, "loss": 2.8702393770217896, "hidden": 0.1685887724161148, "layer": 0.085444500669837, "mlm": 1.5528983175754547, "distill": 0.937441274523735, "teacher_acc": 0.7047758102416992 }, { "step": 15311, "lr": 2.4096825488154063e-07, "elapsed_s": 11374.730768680573, "loss": 2.734600245952606, "hidden": 0.1728328838944435, "layer": 0.08564070425927639, "mlm": 1.421353965997696, "distill": 0.9247601479291916, "teacher_acc": 0.7346855700016022 }, { "step": 15321, "lr": 2.3404512043176675e-07, "elapsed_s": 11382.143733739853, "loss": 2.7793914675712585, "hidden": 0.17512977868318558, "layer": 0.08723573945462704, "mlm": 1.4644586443901062, "distill": 0.9210553616285324, "teacher_acc": 0.726467490196228 }, { "step": 15331, "lr": 2.2722242569873654e-07, "elapsed_s": 11389.524953126907, "loss": 2.761188566684723, "hidden": 0.17053695395588875, "layer": 0.08595173247158527, "mlm": 1.4431284070014954, "distill": 0.9340104162693024, "teacher_acc": 0.7336760312318802 }, { "step": 15341, "lr": 2.2050019835227198e-07, "elapsed_s": 11396.910083055496, "loss": 2.674768567085266, "hidden": 0.16720469668507576, "layer": 0.0843095351010561, "mlm": 1.3607600033283234, "distill": 0.9374445080757141, "teacher_acc": 0.7474536150693893 }, { "step": 15351, "lr": 2.1387846565474045e-07, "elapsed_s": 11404.321236371994, "loss": 2.7620485424995422, "hidden": 0.17009568959474564, "layer": 0.08555116504430771, "mlm": 1.453881412744522, "distill": 0.9252002388238907, "teacher_acc": 0.7210217416286469 }, { "step": 15361, "lr": 2.0735725446094923e-07, "elapsed_s": 11411.71713423729, "loss": 2.8076502084732056, "hidden": 0.17113498225808144, "layer": 0.08519008755683899, "mlm": 1.4688905775547028, "distill": 0.9538945704698563, "teacher_acc": 0.7295829802751541 }, { "step": 15371, "lr": 2.009365912180372e-07, "elapsed_s": 11419.124678134918, "loss": 2.7209373712539673, "hidden": 0.16764381155371666, "layer": 0.08463571406900883, "mlm": 1.4407899975776672, "distill": 0.9025418609380722, "teacher_acc": 0.7254003584384918 }, { "step": 15381, "lr": 1.9461650196536675e-07, "elapsed_s": 11426.508699655533, "loss": 2.8376436829566956, "hidden": 0.17487308755517006, "layer": 0.08794470317661762, "mlm": 1.433811217546463, "distill": 1.0101139545440674, "teacher_acc": 0.738265261054039 }, { "step": 15391, "lr": 1.8839701233440697e-07, "elapsed_s": 11433.90235209465, "loss": 2.7133408784866333, "hidden": 0.174795251339674, "layer": 0.0857569258660078, "mlm": 1.3814596831798553, "distill": 0.9394122213125229, "teacher_acc": 0.7513058185577393 }, { "step": 15401, "lr": 1.8227814754865068e-07, "elapsed_s": 11441.23759508133, "loss": 2.930616557598114, "hidden": 0.17531239613890648, "layer": 0.086771784350276, "mlm": 1.5424167215824127, "distill": 0.9941891133785248, "teacher_acc": 0.7146186083555222 }, { "step": 15411, "lr": 1.762599324234948e-07, "elapsed_s": 11448.62261557579, "loss": 2.866721212863922, "hidden": 0.17771394923329353, "layer": 0.08792668022215366, "mlm": 1.4676828384399414, "distill": 0.9996471405029297, "teacher_acc": 0.7261768132448196 }, { "step": 15421, "lr": 1.7034239136614894e-07, "elapsed_s": 11456.047062635422, "loss": 2.8820990324020386, "hidden": 0.17983843758702278, "layer": 0.08759019523859024, "mlm": 1.4681333005428314, "distill": 1.0104937106370926, "teacher_acc": 0.7319972813129425 }, { "step": 15431, "lr": 1.645255483755326e-07, "elapsed_s": 11463.449441194534, "loss": 2.8942481875419617, "hidden": 0.17976617068052292, "layer": 0.08776849322021008, "mlm": 1.4939399361610413, "distill": 0.996891662478447, "teacher_acc": 0.7243596911430359 }, { "step": 15441, "lr": 1.5880942704217527e-07, "elapsed_s": 11470.891865730286, "loss": 2.8291927576065063, "hidden": 0.17578815668821335, "layer": 0.08656280860304832, "mlm": 1.460192620754242, "distill": 0.9741424471139908, "teacher_acc": 0.721147283911705 }, { "step": 15451, "lr": 1.5319405054813052e-07, "elapsed_s": 11478.332643508911, "loss": 2.7968022227287292, "hidden": 0.17093294113874435, "layer": 0.08572666347026825, "mlm": 1.4891286492347717, "distill": 0.9229443371295929, "teacher_acc": 0.7256985157728195 }, { "step": 15461, "lr": 1.476794416668703e-07, "elapsed_s": 11485.751631259918, "loss": 2.900018632411957, "hidden": 0.1731034368276596, "layer": 0.08644472435116768, "mlm": 1.5199704766273499, "distill": 0.9906189292669296, "teacher_acc": 0.7156846523284912 }, { "step": 15471, "lr": 1.422656227631991e-07, "elapsed_s": 11493.179045677185, "loss": 2.74891996383667, "hidden": 0.17418503016233444, "layer": 0.08691488020122051, "mlm": 1.4397330284118652, "distill": 0.9173594266176224, "teacher_acc": 0.7351050227880478 }, { "step": 15481, "lr": 1.3695261579316777e-07, "elapsed_s": 11500.58942270279, "loss": 2.797867000102997, "hidden": 0.187094334512949, "layer": 0.09093068540096283, "mlm": 1.3367797434329987, "distill": 1.0414333194494247, "teacher_acc": 0.7683060169219971 }, { "step": 15491, "lr": 1.3174044230396532e-07, "elapsed_s": 11507.972880601883, "loss": 2.697475790977478, "hidden": 0.16979219019412994, "layer": 0.08494482561945915, "mlm": 1.4055123627185822, "distill": 0.9099066704511642, "teacher_acc": 0.7353493720293045 }, { "step": 15501, "lr": 1.266291234338607e-07, "elapsed_s": 11515.363358259201, "loss": 2.774468421936035, "hidden": 0.17112699896097183, "layer": 0.08599593490362167, "mlm": 1.4664761126041412, "distill": 0.9227403551340103, "teacher_acc": 0.7165646702051163 }, { "step": 15511, "lr": 1.2161867991208886e-07, "elapsed_s": 11522.779840707779, "loss": 2.719054102897644, "hidden": 0.1716201901435852, "layer": 0.0852173175662756, "mlm": 1.442199170589447, "distill": 0.8910059183835983, "teacher_acc": 0.729556068778038 }, { "step": 15521, "lr": 1.167091320587843e-07, "elapsed_s": 11530.179162740707, "loss": 2.6373308897018433, "hidden": 0.16968093067407608, "layer": 0.08435825631022453, "mlm": 1.3382934629917145, "distill": 0.9174964725971222, "teacher_acc": 0.7584157586097717 }, { "step": 15531, "lr": 1.119004997848977e-07, "elapsed_s": 11537.605904340744, "loss": 2.8385590314865112, "hidden": 0.17810656130313873, "layer": 0.08805380575358868, "mlm": 1.445037990808487, "distill": 0.9932809770107269, "teacher_acc": 0.7315360903739929 }, { "step": 15541, "lr": 1.0719280259210152e-07, "elapsed_s": 11545.037128925323, "loss": 2.856227397918701, "hidden": 0.1728021465241909, "layer": 0.08584113605320454, "mlm": 1.45015949010849, "distill": 1.0175431072711945, "teacher_acc": 0.7391324192285538 }, { "step": 15551, "lr": 1.0258605957272627e-07, "elapsed_s": 11552.449007749557, "loss": 2.767713725566864, "hidden": 0.17111529409885406, "layer": 0.08525202050805092, "mlm": 1.4145541191101074, "distill": 0.9683030396699905, "teacher_acc": 0.7463905513286591 }, { "step": 15561, "lr": 9.808028940967718e-08, "elapsed_s": 11559.867485761642, "loss": 2.712779223918915, "hidden": 0.16991673409938812, "layer": 0.08541332371532917, "mlm": 1.4094305634498596, "distill": 0.9208085387945175, "teacher_acc": 0.7332517504692078 }, { "step": 15571, "lr": 9.367551037635924e-08, "elapsed_s": 11567.29406094551, "loss": 2.781728982925415, "hidden": 0.16719579324126244, "layer": 0.08423412591218948, "mlm": 1.4767448604106903, "distill": 0.9284754991531372, "teacher_acc": 0.7210367023944855 }, { "step": 15581, "lr": 8.937174033659956e-08, "elapsed_s": 11574.731894731522, "loss": 2.6527915596961975, "hidden": 0.16574443131685257, "layer": 0.08442026749253273, "mlm": 1.38564932346344, "distill": 0.893443301320076, "teacher_acc": 0.7301554828882217 }, { "step": 15591, "lr": 8.516899674457513e-08, "elapsed_s": 11582.152236700058, "loss": 2.731054425239563, "hidden": 0.16816063970327377, "layer": 0.08369730040431023, "mlm": 1.5257735848426819, "distill": 0.8271108567714691, "teacher_acc": 0.6990182250738144 }, { "step": 15601, "lr": 8.106729664475176e-08, "elapsed_s": 11589.59359741211, "loss": 2.7752684950828552, "hidden": 0.16980299726128578, "layer": 0.08391544967889786, "mlm": 1.4720353186130524, "distill": 0.9216694384813309, "teacher_acc": 0.7206307947635651 }, { "step": 15611, "lr": 7.706665667180091e-08, "elapsed_s": 11597.043562173843, "loss": 2.866943836212158, "hidden": 0.17594660818576813, "layer": 0.08696525916457176, "mlm": 1.4615337252616882, "distill": 1.0100342780351639, "teacher_acc": 0.7308745086193085 }, { "step": 15621, "lr": 7.316709305054403e-08, "elapsed_s": 11604.479805231094, "loss": 2.8374080061912537, "hidden": 0.17499275505542755, "layer": 0.08651051856577396, "mlm": 1.478503704071045, "distill": 0.9656636118888855, "teacher_acc": 0.7266622483730316 }, { "step": 15631, "lr": 6.936862159588054e-08, "elapsed_s": 11611.885043621063, "loss": 2.7846860885620117, "hidden": 0.17538509890437126, "layer": 0.08712207712233067, "mlm": 1.4803510308265686, "distill": 0.910003736615181, "teacher_acc": 0.7198794931173325 }, { "step": 15641, "lr": 6.567125771272387e-08, "elapsed_s": 11619.297068119049, "loss": 2.7804161310195923, "hidden": 0.16963930428028107, "layer": 0.08610764518380165, "mlm": 1.481711745262146, "distill": 0.9163719862699509, "teacher_acc": 0.7207148373126984 }, { "step": 15651, "lr": 6.207501639593493e-08, "elapsed_s": 11626.726328372955, "loss": 2.7207136750221252, "hidden": 0.17279021069407463, "layer": 0.08498672768473625, "mlm": 1.3902694880962372, "distill": 0.9423703998327255, "teacher_acc": 0.7362833768129349 }, { "step": 15661, "lr": 5.8579912230280476e-08, "elapsed_s": 11634.180311441422, "loss": 2.8041076064109802, "hidden": 0.1762543022632599, "layer": 0.0865848958492279, "mlm": 1.4167143404483795, "distill": 0.991592213511467, "teacher_acc": 0.746922492980957 }, { "step": 15671, "lr": 5.5185959390344214e-08, "elapsed_s": 11641.609824895859, "loss": 2.8151450753211975, "hidden": 0.17407775297760963, "layer": 0.08576864935457706, "mlm": 1.4950434863567352, "distill": 0.929061770439148, "teacher_acc": 0.715582087635994 }, { "step": 15681, "lr": 5.189317164049634e-08, "elapsed_s": 11649.019064188004, "loss": 2.709412634372711, "hidden": 0.17108751833438873, "layer": 0.08563871309161186, "mlm": 1.3972118198871613, "distill": 0.927206352353096, "teacher_acc": 0.7404645830392838 }, { "step": 15691, "lr": 4.87015623348186e-08, "elapsed_s": 11656.459064245224, "loss": 2.766219973564148, "hidden": 0.17129210010170937, "layer": 0.08537965640425682, "mlm": 1.4616104066371918, "distill": 0.9193355590105057, "teacher_acc": 0.7261091768741608 }, { "step": 15701, "lr": 4.56111444170626e-08, "elapsed_s": 11663.897270202637, "loss": 2.7890841364860535, "hidden": 0.17125079780817032, "layer": 0.08567921072244644, "mlm": 1.459015130996704, "distill": 0.9447278380393982, "teacher_acc": 0.7240240126848221 }, { "step": 15711, "lr": 4.262193042059437e-08, "elapsed_s": 11671.331955194473, "loss": 2.8594861030578613, "hidden": 0.17046421393752098, "layer": 0.08591949567198753, "mlm": 1.5165071785449982, "distill": 0.9590907394886017, "teacher_acc": 0.7138648182153702 }, { "step": 15721, "lr": 3.9733932468333234e-08, "elapsed_s": 11678.756972551346, "loss": 2.7832525968551636, "hidden": 0.16877593100070953, "layer": 0.08500281721353531, "mlm": 1.4773665368556976, "distill": 0.9258327484130859, "teacher_acc": 0.722317099571228 }, { "step": 15731, "lr": 3.694716227271855e-08, "elapsed_s": 11686.15344619751, "loss": 2.7412885427474976, "hidden": 0.16807739436626434, "layer": 0.08430268615484238, "mlm": 1.4419969022274017, "distill": 0.920985534787178, "teacher_acc": 0.7319333702325821 }, { "step": 15741, "lr": 3.426163113565417e-08, "elapsed_s": 11693.575344324112, "loss": 2.8108537793159485, "hidden": 0.1713666431605816, "layer": 0.086165651679039, "mlm": 1.4792713522911072, "distill": 0.945766344666481, "teacher_acc": 0.720917820930481 }, { "step": 15751, "lr": 3.167734994846128e-08, "elapsed_s": 11700.987768888474, "loss": 2.872600495815277, "hidden": 0.17223602533340454, "layer": 0.0851020161062479, "mlm": 1.5030353963375092, "distill": 0.9825419932603836, "teacher_acc": 0.7255667448043823 }, { "step": 15761, "lr": 2.919432919183396e-08, "elapsed_s": 11708.395985126495, "loss": 2.9179238080978394, "hidden": 0.17500020563602448, "layer": 0.08687887154519558, "mlm": 1.5587475001811981, "distill": 0.9657364785671234, "teacher_acc": 0.6993413120508194 }, { "step": 15771, "lr": 2.6812578935808685e-08, "elapsed_s": 11715.799767971039, "loss": 2.8110761046409607, "hidden": 0.17201600223779678, "layer": 0.08508848026394844, "mlm": 1.5100273191928864, "distill": 0.9144725948572159, "teacher_acc": 0.713136151432991 }, { "step": 15781, "lr": 2.453210883970325e-08, "elapsed_s": 11723.212426662445, "loss": 2.9278329014778137, "hidden": 0.17803650349378586, "layer": 0.08790086023509502, "mlm": 1.4933663308620453, "distill": 1.034443125128746, "teacher_acc": 0.7301563024520874 }, { "step": 15791, "lr": 2.2352928152089003e-08, "elapsed_s": 11730.609036445618, "loss": 2.749425530433655, "hidden": 0.16751904040575027, "layer": 0.08425705507397652, "mlm": 1.449153572320938, "distill": 0.9231053739786148, "teacher_acc": 0.723153829574585 }, { "step": 15801, "lr": 2.0275045710760334e-08, "elapsed_s": 11737.999054670334, "loss": 2.7756863236427307, "hidden": 0.17044877633452415, "layer": 0.0850465577095747, "mlm": 1.4676402509212494, "distill": 0.9246252477169037, "teacher_acc": 0.7168364822864532 }, { "step": 15811, "lr": 1.8298469942681916e-08, "elapsed_s": 11745.423281908035, "loss": 2.8402692675590515, "hidden": 0.17299408465623856, "layer": 0.0863008163869381, "mlm": 1.5062010288238525, "distill": 0.9449296444654465, "teacher_acc": 0.7153492122888565 }, { "step": 15821, "lr": 1.642320886396931e-08, "elapsed_s": 11752.82661986351, "loss": 2.7874521613121033, "hidden": 0.17109298706054688, "layer": 0.08533688075840473, "mlm": 1.452109545469284, "distill": 0.9504881948232651, "teacher_acc": 0.7301358282566071 }, { "step": 15831, "lr": 1.4649270079847289e-08, "elapsed_s": 11760.205814123154, "loss": 2.7630205154418945, "hidden": 0.16908187419176102, "layer": 0.08499930985271931, "mlm": 1.4343226552009583, "distill": 0.9480345249176025, "teacher_acc": 0.7382134795188904 }, { "step": 15841, "lr": 1.297666078462767e-08, "elapsed_s": 11767.572574138641, "loss": 2.832963705062866, "hidden": 0.17833144962787628, "layer": 0.08663557656109333, "mlm": 1.46321240067482, "distill": 0.9697706550359726, "teacher_acc": 0.7351847290992737 }, { "step": 15851, "lr": 1.1405387761664887e-08, "elapsed_s": 11774.998354911804, "loss": 2.851606845855713, "hidden": 0.17633429169654846, "layer": 0.08667857572436333, "mlm": 1.4800944030284882, "distill": 0.9755045622587204, "teacher_acc": 0.7151873707771301 }, { "step": 15861, "lr": 9.935457383350444e-09, "elapsed_s": 11782.42622590065, "loss": 2.697765529155731, "hidden": 0.16493499279022217, "layer": 0.0839875377714634, "mlm": 1.4364041984081268, "distill": 0.8894975334405899, "teacher_acc": 0.7233511954545975 }, { "step": 15871, "lr": 8.566875611068504e-09, "elapsed_s": 11789.846040725708, "loss": 2.838391423225403, "hidden": 0.1720663458108902, "layer": 0.08621477521955967, "mlm": 1.5018529891967773, "distill": 0.9492983669042587, "teacher_acc": 0.7157105356454849 }, { "step": 15881, "lr": 7.299647995176462e-09, "elapsed_s": 11797.272265195847, "loss": 2.691572427749634, "hidden": 0.16422618553042412, "layer": 0.08310709707438946, "mlm": 1.4307821691036224, "distill": 0.890784278512001, "teacher_acc": 0.7298342734575272 }, { "step": 15891, "lr": 6.133779674988294e-09, "elapsed_s": 11804.711457014084, "loss": 2.728629410266876, "hidden": 0.16765647381544113, "layer": 0.08523947186768055, "mlm": 1.409932404756546, "distill": 0.9407642930746078, "teacher_acc": 0.7432170361280441 }, { "step": 15901, "lr": 5.069275378746796e-09, "elapsed_s": 11812.161114931107, "loss": 2.7574667930603027, "hidden": 0.17347335442900658, "layer": 0.0868199598044157, "mlm": 1.4555469751358032, "distill": 0.9115630835294724, "teacher_acc": 0.7215050607919693 }, { "step": 15911, "lr": 4.106139423612487e-09, "elapsed_s": 11819.616875171661, "loss": 2.794040083885193, "hidden": 0.16787945851683617, "layer": 0.08559676259756088, "mlm": 1.451412171125412, "distill": 0.964070588350296, "teacher_acc": 0.7366849184036255 }, { "step": 15921, "lr": 3.2443757156330744e-09, "elapsed_s": 11827.041406154633, "loss": 2.7593058943748474, "hidden": 0.17117313295602798, "layer": 0.08550054579973221, "mlm": 1.4391368627548218, "distill": 0.9350724518299103, "teacher_acc": 0.7349251955747604 }, { "step": 15931, "lr": 2.4839877497406792e-09, "elapsed_s": 11834.427202939987, "loss": 2.7896527647972107, "hidden": 0.17236778885126114, "layer": 0.08558817766606808, "mlm": 1.4373078346252441, "distill": 0.9648153185844421, "teacher_acc": 0.7295483499765396 }, { "step": 15941, "lr": 1.8249786097324084e-09, "elapsed_s": 11841.825204610825, "loss": 2.8704652786254883, "hidden": 0.17005695402622223, "layer": 0.08615738712251186, "mlm": 1.4916811287403107, "distill": 0.9955915659666061, "teacher_acc": 0.7347802966833115 }, { "step": 15951, "lr": 1.2673509682564755e-09, "elapsed_s": 11849.230217218399, "loss": 2.799567937850952, "hidden": 0.1709761656820774, "layer": 0.08514441922307014, "mlm": 1.4847007095813751, "distill": 0.9303427338600159, "teacher_acc": 0.7220852971076965 }, { "step": 15961, "lr": 8.111070868010995e-10, "elapsed_s": 11856.628919363022, "loss": 2.7967717051506042, "hidden": 0.1717565394937992, "layer": 0.08530361950397491, "mlm": 1.4237821400165558, "distill": 0.9868247359991074, "teacher_acc": 0.7447926998138428 }, { "step": 15971, "lr": 4.5624881569172885e-10, "elapsed_s": 11863.996557712555, "loss": 2.7791637778282166, "hidden": 0.16775130853056908, "layer": 0.08401280827820301, "mlm": 1.5047166645526886, "distill": 0.8969380706548691, "teacher_acc": 0.7125802636146545 }, { "step": 15981, "lr": 2.027775940743881e-10, "elapsed_s": 11871.401898145676, "loss": 2.748114824295044, "hidden": 0.1705903746187687, "layer": 0.08697794377803802, "mlm": 1.3905678391456604, "distill": 0.9728772938251495, "teacher_acc": 0.7344939261674881 }, { "step": 15991, "lr": 5.0694449918453625e-11, "elapsed_s": 11878.81341791153, "loss": 2.6740256547927856, "hidden": 0.1680052988231182, "layer": 0.0850144512951374, "mlm": 1.376772940158844, "distill": 0.9187349230051041, "teacher_acc": 0.744279220700264 }, { "step": 16000, "lr": 5.069446695760149e-13, "elapsed_s": 11885.497461795807, "loss": 2.7582311034202576, "hidden": 0.16607901453971863, "layer": 0.08408323675394058, "mlm": 1.4867496192455292, "distill": 0.8972818106412888, "teacher_acc": 0.7201758027076721 } ] }